Kyrre Glette

• Bruin, Ege de; Glette, Kyrre & Ellefsen, Kai Olav (2026). Lamarckian Inheritance in Dynamic Environments: How Key Variables Affect Evolutionary Dynamics. ALIFE : Proceedings of the Artificial Life Conference. isal2026. doi: https:/direct.mit.edu/isal/proceedings/isal2026/38/35/138242. Fulltekst i vitenarkiv
• Bruin, Ege de; Glette, Kyrre; Ellefsen, Kai; Nadizar, Giorgia & Medvet, Eric (2026). Social Learning Strategies for Evolved Virtual Soft Robots. I Trujillo, Leonardo & Hu, Ting (Red.), GECCO '26: Proceedings of the Genetic and Evolutionary Computation Conference. Association for Computing Machinery (ACM). ISSN 9798400724879. s. 96–105. doi: 10.1145/3795095.3805149. Fulltekst i vitenarkiv
• Kvalsund, Mia-Katrin Ose; Ellefsen, Kai Olav; Glette, Kyrre; Pontes-Filho, Sidney & Lepperød, Mikkel Elle (2026). Sensor movement drives emergent attention and scalability in active neural cellular automata. Neural Networks. ISSN 0893-6080. 200. doi: 10.1016/j.neunet.2026.108798. Fulltekst i vitenarkiv
• Bruin, Ege de; Glette, Kyrre & Ellefsen, Kai Olav (2025). Integrating Sample Inheritance into Bayesian Optimization for Evolutionary Robotics. I Witkowski, Olaf; Adams, Alyssa M.; Sinapayen, Lana; Baltieri, Manuel & Khosravy, Mahdi (Red.), ALIFE 2025: Ciphers of Life: Proceedings of the Artificial Life Conference 2025. MIT Press. doi: 10.1162/ISAL.a.866. Fulltekst i vitenarkiv Vis sammendrag

  In evolutionary robotics, robot morphologies are designed automatically using evolutionary algorithms. This creates a body-brain optimization problem, where both morphology and control must be optimized together. A common approach is to include controller optimization for each morphology, but starting from scratch for every new body may require a high controller learning budget. We address this by using Bayesian optimization for controller optimization, exploiting its sample efficiency and strong exploration capabilities, and using sample inheritance as a form of Lamarckian inheritance. Under a deliberately low controller learning budget for each morphology, we investigate two types of sample inheritance: (1) transferring all the parent’s samples to the offspring to be used as prior without evaluating them, and (2) reevaluating the parent’s best samples on the offspring. Both are compared to a baseline without inheritance. Our results show that reevaluation performs best, with prior-based inheritance also outperforming no inheritance. Analysis reveals that while the learning budget is too low for a single morphology, generational inheritance compensates for this by accumulating learned adaptations across generations. Furthermore, inheritance mainly benefits offspring morphologies that are similar to their parents. Finally, we demonstrate the critical role of the environment, with more challenging environments resulting in more stable walking gaits. Our findings highlight that inheritance mechanisms can boost performance in evolutionary robotics without needing large learning budgets, offering an efficient path toward more capable robot design.

• Bravo, Pedro Pablo Lucas; Szorkovszky, Alexander; Fasciani, Stefano & Glette, Kyrre (2025). HS-ims: A Platform for Human-Swarm Interactive Music Systems. I Tei, Kenji & Zambonelli, Franco (Red.), 2025 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9798331502157. doi: 10.1109/ACSOS-C66519.2025.00067. Fulltekst i vitenarkiv Vis sammendrag

  This paper introduces HS-ims, an integrated virtual environment designed for developing real-time musical multiagent systems. It addresses the need for technological platforms that emphasize sound applications, flexible prototyping, and comprehensive data collection from these multi-agent systems. HS-ims offers a 3D virtual environment with built-in sound synthesis via binaural audio, an Open Sound Control (OSC) API implementation that is language-agnostic, and a data collection module. The platform operates with an External Controller managing multi-agent logic. We present relevant performance metrics and provide examples highlighting how HS-ims has proven valuable in research and education. This encourages further exploration and establishes it as a useful tool for music performance.

• Jónsson, Björn Thór; Erdem, Cagri; Fasciani, Stefano & Glette, Kyrre (2025). Live Coding the Lineage. I Sedo, Anna Xambo & Buffa, Michel (Red.), Proceedings of the International Web Audio Conference (WAC). IRCAM. doi: 10.5281/zenodo.17642435. Fulltekst i vitenarkiv Vis sammendrag

  This paper presents a web-based system for exploring and performing with sounds discovered through Quality Diver- sity evolutionary algorithms. Our system renders interactive phylogenetic trees of evolutionary sound discovery processes, transforming genealogical relationships into a performable interface—the “Harpsitree”—using trajectory-based interaction and automatic code generation. The core concept we explore is “algorithmic sketching,” where trajectory-based discovery through evolutionary structures progressively formalises into executable code, bridging visual exploration and textual live coding paradigms. This work contributes a novel performance interface as part of a larger research project investigating evolutionary computation for sound discovery, demonstrating how phylogenetic structures can reveal com- positional affordances through appropriate interaction design.

• Bruin, Ege de; Glette, Kyrre & Ellefsen, Kai Olav (2025). Generational Replacement and Learning for High-Performing and Diverse Populations in Evolvable Robots. I Obafemi-Ajayi, Tayo (Red.), 2025 IEEE Symposium on Computational Intelligence in Artificial Life and Cooperative Intelligent Systems. IEEE (Institute of Electrical and Electronics Engineers). ISSN 9798331508388. doi: 10.1109/alife-cis64968.2025.10979828. Fulltekst i vitenarkiv Vis sammendrag

  Evolutionary Robotics offers the possibility to design robots to solve a specific task automatically by optimizing their morphology and control together. However, this co-optimization of body and control is challenging, because controllers need some time to adapt to the evolving morphology - which may make it difficult for new and promising designs to enter the evolving population. A solution to this is to add intra-life learning, defined as an additional controller optimization loop, to each individual in the evolving population. A related problem is the lack of diversity often seen in evolving populations as evolution narrows the search down to a few promising designs too quickly. This problem can be mitigated by implementing full generational replacement, where offspring robots replace the whole population. This solution for increasing diversity usually comes at the cost of lower performance compared to using elitism. In this work, we show that combining such generational replacement with intra-life learning can increase diversity while retaining performance. We also highlight the importance of performance metrics when studying learning in morphologically evolving robots, showing that evaluating according to function evaluations versus according to generations of evolution can give different conclusions.

• Milojevic, Andrija & Glette, Kyrre (2025). Design and fabrication of soft locomotion robots based on spatial compliant mechanisms. Smart materials and structures (Print). ISSN 0964-1726. 34(7). doi: 10.1088/1361-665x/addf98. Fulltekst i vitenarkiv Vis sammendrag

  Soft robotics has emerged as a promising technology that holds great potential for various application areas. This is due to soft materials unique properties, including flexibility, safety, and shock absorption, among others. Despite many advancement in the field, the development of effective design methodologies and production techniques for soft robots remains a challenge. Although numerous robot prototypes have been proposed in recent years, their designs are often complex and difficult to produce. As such, there is a need for more efficient and unified design approaches that can facilitate the production of soft robots with desirable properties. In this paper, we propose a method for designing soft robots using elastic beams and spatial compliant mechanisms. The method is based on an evolutionary approach that enables the creation of designs with both high motion and force transmission ratios. Specifically, we focus on the development of locomotion mechanisms using a central linear actuator. Our approach involves the use of commonly available plastic materials and a 3D printer to manufacture the designs. We demonstrate the feasibility of our approach by presenting experimental results that show successful production and real-world operation. Overall, our findings suggest that the use of elastic beams and an evolutionary approach can facilitate the creation of soft robots with desirable locomotion properties, including fast locomotion up to 3.7 body lengths per second, locomotion with a payload, and underwater locomotion. This method has the potential to enable the development of more efficient and practical soft robots for various applications.

• Christodoulou, Anna-Maria; Glette, Kyrre; Lartillot, Olivier & Jensenius, Alexander Refsum (2025). MusiQAl: A Dataset for Music Question–Answering through Audio–Video Fusion. Transactions of the International Society for Music Information Retrieval. 8(1), s. 265–282. doi: 10.5334/tismir.222. Fulltekst i vitenarkiv Vis sammendrag

  Music question–answering (MQA) is a machine learning task where a computational system analyzes and answers questions about music‑related data. Traditional methods prioritize audio, overlooking visual and embodied aspects crucial to music performance understanding. We introduce MusiQAl, a multimodal dataset of 310 music performance videos and 11,793 human‑annotated question–answer pairs, spanning diverse musical traditions and styles. Grounded in musicology and music psychology, MusiQAl emphasizes multimodal reasoning, causal inference, and cross‑cultural understanding of performer–music interaction. We benchmark AVST and LAVISH architectures on MusiQAI, revealing strengths and limitations, underscoring the importance of integrating multimodal learning and domain expertise to advance MQA and music information retrieval.

• Wallace, Benedikte; Glette, Kyrre & Szorkovszky, Alexander (2025). How can we make robot dance expressive and responsive? A survey of methods and future directions. Frontiers in Computer Science. 7. doi: 10.3389/fcomp.2025.1575667. Fulltekst i vitenarkiv Vis sammendrag

  The development of robots that can dance like humans presents a complex challenge due to the disparate abilities involved and various aesthetic qualities that need to be achieved. This article reviews recent advances in robotics, artificial intelligence, and human-robot interaction toward enabling various aspects of realistic dance, and examines potential paths toward a fully embodied dancing agent. We begin by outlining the essential abilities required for a robot to perform human-like dance movements and the resulting aesthetic qualities, summarized under the terms expressiveness and responsiveness . Subsequently, we present a review of the current state-of-the-art in dance-related robot technology, highlighting notable achievements, limitations and trade-offs in existing systems. Our analysis covers various approaches, including traditional control systems, machine learning algorithms, and hybrid systems that aim to imbue robots with the capacity for responsive, expressive movement. Finally, we identify and discuss the critical gaps in current research and technology that need to be addressed for the full realization of realistic dancing robots. These include challenges in real-time motion planning, adaptive learning from human dancers, and morphology independence. By mapping out current methods and challenges, we aim to provide insights that may guide future innovations in creating more engaging, responsive, and expressive robotic systems.

• Norstein, Emma Stensby; Yasui, Kotaro; Kano, Takeshi; Ishiguro, Akio & Glette, Kyrre (2025). Behaviour Diversity in a Walking and Climbing Centipede-Like Virtual Creature. Artificial Life. ISSN 1064-5462. 31(3), s. 321–344. doi: 10.1162/artl_a_00476. Fulltekst i vitenarkiv Vis sammendrag

  Robot controllers are often optimized for a single robot in a single environment. This approach proves brittle, as such a controller will often fail to produce sensible behavior for a new morphology or environment. In comparison, animal gaits are robust and versatile. By observing animals, and attempting to extract general principles of locomotion from their movement, we aim to design a single, decentralized controller applicable to diverse morphologies and environments. The controller implements the three components of (a) undulation, (b) peristalsis, and (c) leg motion, which we believe are the essential elements in most animal gaits. This work is a first step toward a general controller. Accordingly, the controller has been evaluated on a limited range of simulated centipede-like robot morphologies. The centipede is chosen as inspiration because it moves using both body contractions and legged locomotion. For a controller to work in qualitatively different settings, it must also be able to exhibit qualitatively different behaviors. We find that six different modes of locomotion emerge from our controller in response to environmental and morphological changes. We also find that different parts of the centipede model can exhibit different modes of locomotion, simultaneously, based on local morphological features. This controller can potentially aid in the design or evolution of robots, by quickly testing the potential of a morphology, or be used to get insights about underlying locomotion principles in the centipede.

• Bravo, Pedro Pablo Lucas; Fasciani, Stefano; Szorkovszky, Alexander & Glette, Kyrre (2025). An Interactive Self-Assembly Swarm Music System in Extended Reality. I Seiça, Mariana & Wirfs-Brock, Jordan (Red.), AM '25: Proceedings of the 20th International Audio Mostly Conference. Association for Computing Machinery (ACM). ISSN 9798400720659. s. 255–269. doi: 10.1145/3771594.3771620. Fulltekst i vitenarkiv Vis sammendrag

  This paper explores the music-making capabilities of a swarm intelligence type of algorithm known as self-assembly in an interactive context using Extended Reality (XR) technologies. We describe the modifications made to a fully autonomous version of this algorithm, which we proposed in a previous work, allowing us to adapt it for user-interactive music. Moreover, we present the design of an XR system that supports this adaptation, modelled as a human-swarm interactive music system, which is implemented in the Meta Quest 3 headset. An auto-ethnographic study was conducted to discover the affordances of the system in a music improvisation session. The study, supported by empirical measurements collected during the session, enables a comparison between the interactive version and the original autonomous offline version, providing valuable insights into how a user can influence the swarm's behaviour. The results are used to discuss the music performance possibilities and future directions for this type of interactive music system.

• Fuhrer, Julian; Glette, Kyrre; Ivanovic, Jugoslav; Larsson, Pål Gunnar; Bekinschtein, Tristan & Kochen, Silvia [Vis alle 11 forfattere av denne artikkelen] (2025). Direct brain recordings reveal implicit encoding of structure in random auditory streams. Scientific Reports. 15. doi: 10.1038/s41598-025-98865-5. Fulltekst i vitenarkiv Vis sammendrag

  The brain excels at processing sensory input, even in rich or chaotic environments. Mounting evidence attributes this to sophisticated internal models of the environment that draw on statistical structures in the unfolding sensory input. Understanding how and where such modeling proceeds is a core question in statistical learning and predictive processing. In this context, we address the role of transitional probabilities as an implicit structure supporting the encoding of the temporal structure of a random auditory stream. Leveraging information-theoretical principles and the high spatiotemporal resolution of intracranial electroencephalography, we analyzed the trial-by-trial high-frequency activity representation of transitional probabilities. This unique approach enabled us to demonstrate how the brain automatically and continuously encodes structure in random stimuli and revealed the involvement of a network outside of the auditory system, including hippocampal, frontal, and temporal regions. Our work provides a comprehensive picture of the neural correlates of automatic encoding of implicit structure that can be the crucial substrate for the swift detection of patterns and unexpected events in the environment.

• Bravo, Pedro Pablo Lucas; Szorkovszky, Alexander; Fasciani, Stefano & Glette, Kyrre (2024). Self-Assembly and Synchronization: Crafting Music with Multi-Agent Embodied Oscillators. I IEEE, IEEE (Red.), 2024 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9798350363876. s. 145–150. doi: 10.1109/ACSOS61780.2024.00034. Fulltekst i vitenarkiv Vis sammendrag

  This paper proposes a self-assembly algorithm that generates rhythmic music. It uses multiple pulsed oscillators embedded in cube-shaped agents in a virtual 3D space. When these units connect with each other, their oscillators synchronize, triggering regular sound events that produce musical notes whose sound dynamics change based on the size of the structures formed. This study examines the synchronization time of these oscillators and the emergent properties of the structures formed during the algorithm’s execution. Moreover, the resulting sound, determined by multiple interactions among agents, is analyzed in the time and frequency domains from its signal. The results show that the synchronization time slightly increases when more agents participate, although with high variability. Also, a quasi-regular pattern of increase and decrease in the number of structures over time is observed. Additionally, the signal analysis illustrates the effect of the self-assembly strategy in terms of rhythmical patterns and sound energy over time. We discuss these results and the potential applications of this multi-agent approach in the sound and music field.

• Guo, Jinyue; Christodoulou, Anna-Maria; Laczko, Balint & Glette, Kyrre (2024). LVNS-RAVE: Diversified audio generation with RAVE and Latent Vector Novelty Search. I Li, Xiaodong & Handl, Julia (Red.), GECCO '24 Companion: Proceedings of the Genetic and Evolutionary Computation Conference Companion. Association for Computing Machinery (ACM). ISSN 9798400704956. s. 667–670. doi: 10.1145/3638530.3654432. Fulltekst i vitenarkiv Vis sammendrag

  Evolutionary Algorithms and Generative Deep Learning have been two of the most powerful tools for sound generation tasks. However, they have limitations: Evolutionary Algorithms require complicated designs, posing challenges in control and achieving realistic sound generation. Generative Deep Learning models often copy from the dataset and lack creativity. In this paper, we propose LVNS-RAVE, a method to combine Evolutionary Algorithms and Generative Deep Learning to produce realistic and novel sounds. We use the RAVE model as the sound generator and the VGGish model as a novelty evaluator in the Latent Vector Novelty Search (LVNS) algorithm. The reported experiments show that the method can successfully generate diversified, novel audio samples under different mutation setups using different pre-trained RAVE models. The characteristics of the generation process can be easily controlled with the mutation parameters. The proposed algorithm can be a creative tool for sound artists and musicians.

• Christodoulou, Anna-Maria; Dutta, Sagar; Lartillot, Olivier Serge Gabriel; Glette, Kyrre & Jensenius, Alexander Refsum (2024). Exploring Convolutional Neural Network Models for Multimodal Classification of Expressive Piano Performance, Proceedings of the Sound and Music Computing Conference 2024. SMC Network. ISSN 9789893520758. Fulltekst i vitenarkiv Vis sammendrag

  This paper addresses improving performance analysis by automating the recognition of expressive performance styles. We propose a multimodal fusion approach integrating audio, video, and motion data. We demonstrate the effectiveness of our approach by utilizing convolutional neural network (CNN) models. Training is done on a classical piano dataset of 211 excerpts containing audio, video, MIDI, and motion capture data. The results highlight the robustness of the CNN models; they achieve high accuracy even when trained on a limited dataset. Our study contributes to advancing the field of performance analysis by applying deep learning techniques to multimodal data.

• Bravo, Pedro Pablo Lucas; Fasciani, Stefano & Glette, Kyrre (2024). Csound vs. ChucK: Sound Generation for XR Multi-Agent Audio Systems in the Meta Quest 3 Using the Unity Game Engine, Proceedings of the Sound and Music Computing Conference 2024. SMC Network. ISSN 9789893520758. doi: 10.5281/zenodo.14339046. Fulltekst i vitenarkiv Vis sammendrag

  Extended Reality (XR) technologies, particularly headsets like the Meta Quest 3, are revolutionizing the field of immersive sound and music applications by offering new depths of user experience. As such, the Unity game engine emerges as a preferred platform for building such auditory environments. As part of its capabilities, Unity allows the programming of sound generation through a low-level digital signal processing API, which requires specialized knowledge and significant effort for development. However, wrappers that integrate Unity with programming languages for sound synthesis can facilitate the implementation of this task. In this work, we focus on applications for the Meta Quest 3 involving multiple spatialized audio sources; such applications can be framed as XR multi-agent audio systems. We consider two wrappers, CsoundUnity and Chunity, featuring Csound and ChucK programming languages. We test and analyze these wrappers in a minimal XR application, varying the number of audio sources to measure the performance of both tools in two device environments: the development machine and the Meta Quest 3. We found that CsoundUnity performs better in the headset, but Chunity performs better in the development machine. We discuss the advantages, limitations, and computational issues found on both wrappers, as well as the criteria for choosing them to develop XR multi-agent audio applications in Unity.

• Bravo, Pedro Pablo Lucas; Fasciani, Stefano; Szorkovszky, Alexander & Glette, Kyrre (2024). Interactive Sonification of 3D Swarmalators, Proceedings of the International Conference on New Interfaces for Musical Expression. NIME. s. 252–260. doi: 10.5281/zenodo.13904846. Fulltekst i vitenarkiv Vis sammendrag

  This paper explores the sound and music possibilities obtained from the sonification of a swarm of coupled oscillators moving in a virtual space called “Swarmalators”. We describe the design and implementation of a Human-Swarm Interactive Music System based on the 3D version of the Swarmalator model, which is used for signal analysis of the overall sound output in terms of scalability; that is, the effect of varying the number of agents in a swarm system. We also study the behaviour of autonomous swarmalators in the presence of one user-controlled agent, which we call the interactive swarmalator. We observed that sound frequencies barely deviate from their initial values when there are few agents, but they diverge significantly in a highly dense swarm. Additionally, with the inclusion of the interactive swarmalator, the group’s behaviour tends to adjust towards it. We use these results to explore the potential of swarmalators in music performance under various scenarios. Finally, we discuss opportunities and challenges to use the Swarmalator model for sound and music systems.

• Jónsson, Björn Thor; Erdem, Cagri; Fasciani, Stefano & Glette, Kyrre (2024). Cultivating Open-Earedness with Sound Objects discovered by Open-Ended Evolutionary Systems. I Grace, Kazjon; Llano, Maria Teresa; Martins, Pedro & Hedblom, Maria (Red.), Proceedings of the Fifteenth International Conference on Computational Creativity. Association for Computational Creativity (ACC). ISSN 9789895416066. s. 381–386. Fulltekst i vitenarkiv Vis sammendrag

  Interaction with generative systems can face the choice of generalising towards a middle ground or diverging towards novelty. Efforts have been made in the domain of sounds to enable divergent exploration in search of interesting discoveries. Those efforts have been confined by pre-trained models and single environments. We are building on those efforts to enable autonomous discovery of sonic landscapes. Furthermore, we draw inspiration from research on open-ended evolution to continuously provide evolutionary processes with new opportunities for sonic discoveries. Exposure to autonomously discovered sound objects can elevate openness to sonic experiences, which in turn offers inspiring opportunities for creative work involving sounds.

• Jónsson, Björn Thor; Erdem, Cagri & Glette, Kyrre (2024). A System for Sonic Explorations With Evolutionary Algorithms. Journal of The Audio Engineering Society. ISSN 1549-4950. 72(4), s. 257–266. doi: 10.17743/jaes.2022.0137. Fulltekst i vitenarkiv
• Jónsson, Björn Thor; Erdem, Cagri; Fasciani, Stefano & Glette, Kyrre (2024). Towards Sound Innovation Engines Using Pattern-Producing Networks and Audio Graphs. I Johnson, Colin; Rebelo, Sérgio M. & Santos, Iria (Red.), Artificial Intelligence in Music, Sound, Art and Design. Springer Nature. ISSN 9783031569920. doi: 10.1007/978-3-031-56992-0_14. Fulltekst i vitenarkiv Vis sammendrag

  This study draws on the challenges that composers and sound designers face in creating and refining new tools to achieve their musical goals. Utilising evolutionary processes to promote diversity and foster serendipitous discoveries, we propose to automate the search through uncharted sonic spaces for sound discovery. We argue that such diversity promoting algorithms can bridge a technological gap between the theoretical realisation and practical accessibility of sounds. Specifically, in this paper we describe a system for generative sound synthesis using a combination of Quality Diversity (QD) algorithms and a supervised discriminative model, inspired by the Innovation Engine algorithm. The study explores different configurations of the generative system and investigates the interplay between the chosen sound synthesis approach and the discriminative model. The results indicate that a combination of Compositional Pattern Producing Network (CPPN) + Digital Signal Processing (DSP) graphs coupled with Multi-dimensional Archive of Phenotypic Elites (MAP-Elites) and a deep learning classifier can generate a substantial variety of synthetic sounds. The study concludes by presenting the generated sound objects through an online explorer and as rendered sound files. Furthermore, in the context of music composition, we present an experimental application that showcases the creative potential of our discovered sounds.

• Veenstra, Frank; Szorkovszky, Alexander & Glette, Kyrre (2023). Decentralized Control and Morphological Evolution of 2D Virtual Creatures. I Iizuki, Hiroyuki; Suzuki, Keisuke; Uno, Ryoko; Damiano, Luisa; Spychala, Nadine; Aguilera, Miguel; Izquierdo, Eduardo; Suzuki, Reiji & Baltieri, Manuel (Red.), ALIFE 2023: Ghost in the Machine: Proceedings of the 2023 Artificial Life Conference. MIT Press. doi: 10.1162/isal_a_00656. Fulltekst i vitenarkiv
• Szorkovszky, Alexander; Veenstra, Frank & Glette, Kyrre (2023). From real-time adaptation to social learning in robot ecosystems. Frontiers in Robotics and AI. 10. doi: 10.3389/frobt.2023.1232708. Fulltekst i vitenarkiv Vis sammendrag

  While evolutionary robotics can create novel morphologies and controllers that are well-adapted to their environments, learning is still the most efficient way to adapt to changes that occur on shorter time scales. Learning proposals for evolving robots to date have focused on new individuals either learning a controller from scratch, or building on the experience of direct ancestors and/or robots with similar configurations. Here we propose and demonstrate a novel means for social learning of gait patterns, based on sensorimotor synchronization. Using movement patterns of other robots as input can drive nonlinear decentralized controllers such as CPGs into new limit cycles, hence encouraging diversity of movement patterns. Stable autonomous controllers can then be locked in, which we demonstrate using a quasi-Hebbian feedback scheme. We propose that in an ecosystem of robots evolving in a heterogeneous environment, such a scheme may allow for the emergence of generalist task-solvers from a population of specialists.

• Szorkovszky, Alexander; Veenstra, Frank & Glette, Kyrre (2023). Central pattern generators evolved for real-time adaptation to rhythmic stimuli. Bioinspiration & Biomimetics. ISSN 1748-3182. 18(4). doi: 10.1088/1748-3190/ace017. Fulltekst i vitenarkiv Vis sammendrag

  Abstract For a robot to be both autonomous and collaborative requires the ability to adapt its movement to a variety of external stimuli, whether these come from humans or other robots. Typically, legged robots have oscillation periods explicitly defined as a control parameter, limiting the adaptability of walking gaits. Here we demonstrate a virtual quadruped robot employing a bio-inspired central pattern generator (CPG) that can spontaneously synchronize its movement to a range of rhythmic stimuli. Multi-objective evolutionary algorithms were used to optimize the variation of movement speed and direction as a function of the brain stem drive and the centre of mass control respectively. This was followed by optimization of an additional layer of neurons that filters fluctuating inputs. As a result, a range of CPGs were able to adjust their gait pattern and/or frequency to match the input period. We show how this can be used to facilitate coordinated movement despite differences in morphology, as well as to learn new movement patterns.

• Fuhrer, Julian; Glette, Kyrre; Anais, Llorens; Endestad, Tor; Solbakk, Anne-Kristin & Blenkmann, Alejandro Omar (2023). Quantifying evoked responses through information-theoretical measures. Frontiers in Neuroinformatics. 17. doi: 10.3389/fninf.2023.1128866. Fulltekst i vitenarkiv Vis sammendrag

  Information theory is a viable candidate to advance our understanding of how the brain processes information generated in the internal or external environment. With its universal applicability, information theory enables the analysis of complex data sets, is free of requirements about the data structure, and can help infer the underlying brain mechanisms. Information-theoretical metrics such as Entropy or Mutual Information have been highly beneficial for analyzing neurophysiological recordings. However, a direct comparison of the performance of these methods with well-established metrics, such as the t- test, is rare. Here, such a comparison is carried out by evaluating the novel method of Encoded Information with Mutual Information, Gaussian Copula Mutual Information, Neural Frequency Tagging, and t -test. We do so by applying each method to event-related potentials and event-related activity in different frequency bands originating from intracranial electroencephalography recordings of humans and marmoset monkeys. Encoded Information is a novel procedure that assesses the similarity of brain responses across experimental conditions by compressing the respective signals. Such an information-based encoding is attractive whenever one is interested in detecting where in the brain condition effects are present.

• Szorkovszky, Alexander; Veenstra, Frank; Lartillot, Olivier Serge Gabriel; Jensenius, Alexander Refsum & Glette, Kyrre (2023). Embodied Tempo Tracking with a Virtual Quadruped, Proceedings of the Sound and Music Computing Conference 2023. SMC Network . ISSN 9789152773727. doi: 10.5281/zenodo.10060970. Fulltekst i vitenarkiv Vis sammendrag

  Dynamic attending theory posits that we entrain to time-structured events in a similar way to synchronizing oscillators. Hence, a tempo tracker based on oscillators may replicate humans' ability to rapidly and robustly identify musical tempi. We demonstrate this idea using virtual quadrupeds, whose gaits are controlled by oscillatory neural circuits known as central pattern generators (CPGs). The quadruped CPGs were first optimized for flexible gait frequency and direction, and then an additional recurrent layer was optimized for entrainment to isochronous pulses. Using excerpts of musical pieces, we find that the motion of these agents can rapidly entrain to simple rhythms. Performance was found to be partially predicted by pulse entropy, a measure of the sample's rhythmic complexity. Notably, in addition to having wide tempo ranges, the best performing agents can also entrain to rhythms that are periodic but not quantized on a grid. Our approach offers an embodied alternative to other dynamical systems-based approaches to entrainment, such as gradient-frequency arrays. Such agents could find use as participants in virtual musicking environments, or as real-world musical robots.

• Erdem, Cagri; Wallace, Benedikte; Glette, Kyrre & Jensenius, Alexander Refsum (2023). Tool or Actor? Expert Improvisers’ Evaluation of a Musical AI “Toddler”. Computer Music Journal. ISSN 0148-9267. 46(4), s. 26–42. doi: 10.1162/comj_a_00657. Fulltekst i vitenarkiv Vis sammendrag

  Abstract In this article, we introduce the coadaptive audiovisual instrument, CAVI. This instrument uses deep learning to generate control signals based on muscle and motion data of a performer's actions. The generated signals control time-based live sound-processing modules. How does a performer perceive such an instrument? Does it feel like a machine learning–based musical tool? Or is it an actor with the potential to become a musical partner? We report on an evaluation of CAVI after it had been used in two public performances. The evaluation is based on interviews with the performers, audience questionnaires, and the creator's self-analysis. Our findings suggest that the perception of CAVI as a tool or actor correlates with the performer's sense of agency. The perceived agency changes throughout a performance based on several factors, including perceived musical coordination, the balance between surprise and familiarity, a “common sense,” and the physical characteristics of the performance setting.

• Norstein, Emma Stensby; Veenstra, Frank; Ellefsen, Kai Olav; Nygaard, Tønnes & Glette, Kyrre (2023). Effects of compliant and structural parts in evolved modular robots. I Iizuki, Hiroyuki; Suzuki, Keisuke; Uno, Ryoko; Damiano, Luisa; Spychala, Nadine; Aguilera, Miguel; Izquierdo, Eduardo; Suzuki, Reiji & Baltieri, Manuel (Red.), ALIFE 2023: Ghost in the Machine: Proceedings of the 2023 Artificial Life Conference. MIT Press. doi: 10.1162/isal_a_00689. Fulltekst i vitenarkiv Vis sammendrag

  A striking difference between animals and traditional robots is that the latter usually have rigid and non-flexible bodies. Animals, on the other hand, exhibit highly adapted traits, such as elastic tendons. The tendons work as springs, storing and releasing kinetic energy during an animal’s gait cycle. Springs have been used in some hand designed robots for similar benefits. However, little research has been done on springs in robots with evolving morphology. We examine the use of compliant and structural modules in modular robots, using a standard evolutionary algorithm. We also look at connections between spring stiffness and robot size using the quality diversity algorithm MAP-Elites. We found that the modular robots evolved to use elastic actuators, and that structural modules enabled morphologies that use less actuators, but still achieve the same walking speed as the robots with actuators in every module. We also observe some indications that larger robots may require lower elasticity.

• Norstein, Emma Stensby; Ellefsen, Kai Olav; Veenstra, Frank; Nygaard, Tønnes & Glette, Kyrre (2023). Evolution of linkages for prototyping of linkage based robots, Proceedings of the 2022 IEEE Symposium Series on Computational Intelligence (SSCI 2022). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781665487689. s. 1283–1290. doi: 10.1109/SSCI51031.2022.10022197. Fulltekst i vitenarkiv Vis sammendrag

  Prototyping robotic systems is a time consuming process. Computer aided design, however, might speed up the process significantly. Quality-diversity evolutionary approaches optimise for novelty as well as performance, and can be used to generate a repertoire of diverse designs. This design repertoire could be used as a tool to guide a designer and kick-start the rapid prototyping process. This paper explores this idea in the context of mechanical linkage based robots. These robots can be a good test-bed for rapid prototyping, as they can be modified quickly for swift iterations in design. We compare three evolutionary algorithms for optimising 2D mechanical linkages: 1) a standard evolutionary algorithm, 2) the multi-objective algorithm NSGA-II, and 3) the quality-diversity algorithm MAP-Elites. Some of the found linkages are then realized on a physical hexapod robot through a prototyping process, and tested on two different floors. We find that all the tested approaches, except the standard evolutionary algorithm, are capable of finding mechanical linkages that creates a path similar to a specified desired path. However, the quality-diversity approaches that had the length of the linkage as a behaviour descriptor were the most useful when prototyping. This was due to the quality-diversity approaches having a larger variety of similar designs to choose from, and because the search could be constrained by the behaviour descriptors to make linkages that were viable for construction on our hexapod platform.

• Bravo, Pedro Pablo Lucas & Glette, Kyrre (2023). Human-Swarm Interactive Music Systems: Design, Algorithms, Technologies, and Evaluation. I Kitahara, Tetsuro; Aramaki, Mitsuko; Kronland-Martinet, Richard & Ystad, Sølvi (Red.), Proceedings of the 16th International Symposium on Computer Music Multidisciplinary Research. Zenodo. ISSN 9791097498047. s. 347–358. doi: 10.5281/zenodo.10113081. Fulltekst i vitenarkiv Vis sammendrag

  This paper presents considerations for developing Human-Swarm Interactive Music Systems (IMS), based on previous work in the field. We discuss design principles, algorithms, technologies, and evaluation methods for creating user-centered Human-Swarm IMSs using architectural ap­proaches, swarm strategies, and levels of embodiment in implementation. Our contribution aims to establish a framework for future applications and research studies on swarm-based music platforms.

• Kvalsund, Mia-Katrin Ose; Glette, Kyrre & Veenstra, Frank (2022). Centralized and Decentralized Control in Modular Robots and Their Effect on Morphology. I Holler, Silvia; Löffler, Richard & Bartlett, Stuart (Red.), ALIFE 2022: The 2022 Conference on Artificial Life. MIT Press. doi: 10.1162/isal_a_00533. Fulltekst i vitenarkiv Vis sammendrag

  In Evolutionary Robotics, evolutionary algorithms are used to co-optimize morphology and control. However, co-optimizing leads to different challenges: How do you optimize a controller for a body that often changes its number of inputs and outputs? Researchers must then make some choice between centralized or decentralized control. In this article, we study the effects of centralized and decentralized controllers on modular robot performance and morphologies. This is done by implementing one centralized and two decentralized continuous time recurrent neural network controllers, as well as a sine wave controller for a baseline. We found that a decentralized approach that was more independent of morphology size performed significantly better than the other approaches. It also worked well in a larger variety of morphology sizes. In addition, we highlighted the difficulties of implementing centralized control for a changing morphology, and saw that our centralized controller struggled more with early convergence than the other approaches. Our findings indicate that duplicated decentralized networks are beneficial when evolving both the morphology and control of modular robots. Overall, if these findings translate to other robot systems, our results and issues encountered can help future researchers make a choice of control method when co-optimizing morphology and control.

• Veenstra, Frank; Olsen, Martin Herring & Glette, Kyrre (2022). Effects of Encodings and Quality-diversity on Evolving 2D Virtual Creatures, GECCO '22: Proceedings of the Genetic and Evolutionary Computation Conference Companion. Association for Computing Machinery (ACM). ISSN 9781450392686. s. 164–167. doi: 10.1145/3520304.3529053. Fulltekst i vitenarkiv
• Szorkovszky, Alexander; Veenstra, Frank & Glette, Kyrre (2022). Rapid rhythmic entrainment in bio-inspired central pattern generators, 2022 International Joint Conference on Neural Networks (IJCNN). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781728186719. doi: 10.1109/IJCNN55064.2022.9891909. Fulltekst i vitenarkiv Vis sammendrag

  Entrainment of movement to a periodic stimulus is a characteristic intelligent behaviour in humans and an important goal for adaptive robotics. We demonstrate a quadruped central pattern generator (CPG), consisting of modified Matsuoka neurons, that spontaneously adjusts its period of oscillation to that of a periodic input signal. This is done by simple forcing, with the aid of a filtering network as well as a neural model with tonic input-dependent oscillation period. We first use the NSGA3 algorithm to evolve the CPG parameters, using separate fitness functions for period tunability, limb homogeneity and gait stability. Four CPGs, maximizing different weighted averages of the fitness functions, are then selected from the Pareto front and each is used as a basis for optimizing a filter network. Different numbers of neurons are tested for each filter network. We find that period tunability in particular facilitates robust entrainment, that bounding gaits entrain more easily than walking gaits, and that more neurons in the filter network are beneficial for pre-processing input signals. The system that we present can be used in conjunction with sensory feedback to allow low-level adaptive and robust behaviour in walking robots.

• Torpmann-Hagen, Birk Sebastian Frostelid; Thambawita, Vajira L B; Riegler, Michael; Halvorsen, Pål & Glette, Kyrre (2022). Segmentation Consistency Training: Out-of-Distribution Generalization for Medical Image Segmentation. I Bulterman, Dick; Kankanhalli, Mohan S.; Muehlhaeuser, Max; Persia, Fabio; Sheu, Phillip; Tsai, Jeffrey J.P.; D’Auria, Daniela; Ge, Mouzhi; Sert, Mustafa; Swaminathan, Vishy & Yamasaki, Toshihiko (Red.), Proceedings of the 2022 IEEE International Symposium on Multimedia (ISM). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781665471725. s. 42–49. doi: 10.1109/ISM55400.2022.00012. Fulltekst i vitenarkiv
• Norstein, Emma Stensby; Ellefsen, Kai Olav & Glette, Kyrre (2022). Open-Ended Search for Environments and Adapted Agents Using MAP-Elites, Applications of Evolutionary Computation. EvoApplications 2022.. Springer. ISSN 9783031024610. s. 651–666. doi: 10.1007/978-3-031-02462-7_41. Fulltekst i vitenarkiv
• Nygaard, Tønnes Frostad & Glette, Kyrre (2022). Benefits and Challenges of Morphological Adaptation in Real-world Robots. IOP Conference Series: Materials Science and Engineering. ISSN 1757-8981. 1261. doi: 10.1088/1757-899X/1261/1/012017. Fulltekst i vitenarkiv Vis sammendrag

  Abstract For many years, the main target of robotics research has been how to improve control and behavior to allow robots to solve more challenging tasks. Recently, the concept of embodied intelligence has shifted this focus from pure control to a more holistic approach. The mind, body, environment, and the interactions between all these are all highly important for the performance of a robot system. This has previously been investigated in virtual robots in simulation or very simple physical robots in the lab, but the benefits for more advanced and capable real-world robots are still to be determined. We present a case study with several examples of real-world adaptation of morphology, and discuss the benefits and challenges as this direction becomes more important in the field of robotics. Taking an embodied approach promises more adaptive and robust robots, but there are many challenges that need to be addressed before wide-spread adoption in the robotics community.

• Krzyzaniak, Michael; Erdem, Cagri & Glette, Kyrre (2022). What Makes Interactive Art Engaging? Frontiers in Computer Science. 4. doi: 10.3389/fcomp.2022.859496. Fulltekst i vitenarkiv Vis sammendrag

  Interactive art requires people to engage with it, and some works of interactive art are more intrinsically engaging than others. This article asks what properties of a work of interactive art promote engagement. More specifically, it examines four properties: (1) the number of controllable parameters in the interaction, (2) the use of fantasy in the work, (3) the timescale on which the work responds, and (4) the amount agency ascribed to the work. Each of these is hypothesized to promote engagement, and each hypothesis is tested with a controlled user study in an ecologically valid setting on the Internet. In these studies, we found that more controllable parameters increases engagement; the use of fantasy increases engagement for some users and not others; the timescale surprisingly has no significant on engagement but may relate to the style of interaction; and more ascribed agency is correlated with greater engagement although the direction of causation is not known. This is not intended to be an exhaustive list of all properties that may promote engagement, but rather a starting point for more studies of this kind.

• Fuhrer, Julian; Blenkmann, Alejandro Omar; Endestad, Tor; Solbakk, Anne-Kristin & Glette, Kyrre (2022). Complexity-based Encoded Information Quantification in Neurophysiological Recordings. Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). s. 2319–2323. doi: 10.1109/EMBC48229.2022.9871501. Fulltekst i vitenarkiv Vis sammendrag

  Brain activity differs vastly between sleep, cognitive tasks, and action. Information theory is an appropriate concept to analytically quantify these brain states. Based on neurophysiological recordings, this concept can handle complex data sets, is free of any requirements about the data structure, and can infer the present underlying brain mechanisms. Specifically, by utilizing algorithmic information theory, it is possible to estimate the absolute information contained in brain responses. While current approaches that apply this theory to neurophysiological recordings can discriminate between different brain states, they are limited in directly quantifying the degree of similarity or encoded information between brain responses. Here, we propose a method grounded in algorithmic information theory that affords direct statements about responses' similarity by estimating the encoded information through a compression-based scheme. We validated this method by applying it to both synthetic and real neurophysiological data and compared its efficiency to the mutual information measure. This proposed procedure is especially suited for task paradigms contrasting different event types because it can precisely quantify the similarity of neuronal responses.

• Côté-Allard, Ulysse; Gagnon-Turcotte, Gabriel; Phinyomark, Angkoon; Glette, Kyrre Harald; Scheme, Erik & Laviolette, François [Vis alle 7 forfattere av denne artikkelen] (2021). A Transferable Adaptive Domain Adversarial Neural Network for Virtual Reality Augmented EMG-Based Gesture Recognition. IEEE transactions on neural systems and rehabilitation engineering. ISSN 1534-4320. doi: 10.1109/TNSRE.2021.3059741. Fulltekst i vitenarkiv Vis sammendrag

  Within the field of electromyography-based (EMG) gesture recognition, disparities exist between the offline accuracy reported in the literature and the real-time usability of a classifier. This gap mainly stems from two factors: 1) The absence of a controller, making the data collected dissimilar to actual control. 2) The difficulty of including the four main dynamic factors (gesture intensity, limb position, electrode shift, and transient changes in the signal), as including their permutations drastically increases the amount of data to be recorded. Contrarily, online datasets are limited to the exact EMG-based controller used to record them, necessitating the recording of a new dataset for each control method or variant to be tested. Consequently, this paper proposes a new type of dataset to serve as an intermediate between offline and online datasets, by recording the data using a real-time experimental protocol. The protocol, performed in virtual reality, includes the four main dynamic factors and uses an EMG-independent controller to guide movements. This EMG-independent feedback ensures that the user is in-the-loop during recording, while enabling the resulting dynamic dataset to be used as an EMG-based benchmark. The dataset is comprised of 20 able-bodied participants completing three to four sessions over a period of 14 to 21 days. The ability of the dynamic dataset to serve as a benchmark is leveraged to evaluate the impact of different recalibration techniques for long-term (across-day) gesture recognition, including a novel algorithm, named TADANN. TADANN consistently and significantly ( p<0.05 ) outperforms using fine-tuning as the recalibration technique.

• Glette, Kyrre (2021). Forskningsfeltet robotikk og intelligente systemer. Nytt Norsk Tidsskrift (NNT). ISSN 0800-336X. 38(4), s. 326–330. doi: 10.18261/issn.1504-3053-2021-04-07. Fulltekst i vitenarkiv
• Ahmadi, Arash; Till, Katharina; Backe, Paul Hoff; Blicher, Pernille; Diekmann, Robin & Schüttpelz, Mark [Vis alle 11 forfattere av denne artikkelen] (2021). Non-flipping DNA glycosylase AlkD scans DNA without formation of a stable interrogation complex. Communications Biology. 4. doi: 10.1038/s42003-021-02400-x. Fulltekst i vitenarkiv Vis sammendrag

  Abstract The multi-step base excision repair (BER) pathway is initiated by a set of enzymes, known as DNA glycosylases, able to scan DNA and detect modified bases among a vast number of normal bases. While DNA glycosylases in the BER pathway generally bend the DNA and flip damaged bases into lesion specific pockets, the HEAT-like repeat DNA glycosylase AlkD detects and excises bases without sequestering the base from the DNA helix. We show by single-molecule tracking experiments that AlkD scans DNA without forming a stable interrogation complex. This contrasts with previously studied repair enzymes that need to flip bases into lesion-recognition pockets and form stable interrogation complexes. Moreover, we show by design of a loss-of-function mutant that the bimodality in scanning observed for the structural homologue AlkF is due to a key structural differentiator between AlkD and AlkF; a positively charged β-hairpin able to protrude into the major groove of DNA.

• Nordmoen, Jørgen; Nygaard, Tønnes Frostad; Samuelsen, Eivind & Glette, Kyrre (2021). On Restricting Real-Valued Genotypes in Evolutionary Algorithms. I Castillo, Pedro A. & Laredo, Juan Luiz Jiménez (Red.), Applications of Evolutionary Computation. Springer. ISSN 9783030726997. s. 3–16. doi: 10.1007/978-3-030-72699-7_1. Fulltekst i vitenarkiv Vis sammendrag

  Real-valued genotypes together with the variation operators, mutation and crossover, constitute some of the fundamental building blocks of Evolutionary Algorithms. Real-valued genotypes are utilized in a broad range of contexts, from weights in Artificial Neural Networks to parameters in robot control systems. Shared between most uses of real-valued genomes is the need for limiting the range of individual parameters to allowable bounds. In this paper we will illustrate the challenge of limiting the parameters of real-valued genomes and analyse the most promising method to properly limit these values. We utilize both empirical as well as benchmark examples to demonstrate the utility of the proposed method and through a literature review show how the insight of this paper could impact other research within the field. The proposed method requires minimal intervention from Evolutionary Algorithm practitioners and behaves well under repeated application of variation operators, leading to better theoretical properties as well as significant differences in well-known benchmarks.

• Potel, Pierre; Veenstra, Frank & Glette, Kyrre (2021). SoloJam Island : a platform for rhythmic experimentation in spatially segmented multi-agent systems. I Kantan, Prithvi Ravi; Paisa, Razvan & Willemsen, Silvin (Red.), Proceedings of the 2nd Nordic Sound and Music Computing (NordicSMC) Conference. Aalborg Universitetsforlag. doi: 10.5281/zenodo.5717860. Fulltekst i vitenarkiv Vis sammendrag

  The development of musical robots which create musical performances or assist musicians during their performances has been an active subject of research in the last few years. In this paper we consider a multi-agent system for the improvisation of rhythmic patterns, where agents compete to take the lead and play musical solos. This competing mechanism is based on evolutionary algorithms and auctions. As such a natural evolution of this system, is to investigate the ways in which separating these agents into multiple subpopulations, where some agents occasionally migrate from one subpopulation to the other and try to bring with them rhythmic knowledge of their past experience, affects the musical dynamics of these subgroups. Simulation’s results show that migrating agent’s can disrupt the musical play in those subgroups and ensure diversity in the musical compositions.

• Barnes, Chloe M; Ekárt, Anikó; Ellefsen, Kai Olav; Glette, Kyrre; Lewis, Peter R. & Tørresen, Jim (2021). Behavioural Plasticity Can Help Evolving Agents in Dynamic Environments but at the Cost of Volatility. ACM Transactions on Autonomous and Adaptive Systems. ISSN 1556-4665. 15(4). doi: 10.1145/3487918. Fulltekst i vitenarkiv Vis sammendrag

  Neural networks have been widely used in agent learning architectures; however, learnings for one task might nullify learnings for another. Behavioural plasticity enables humans and animals alike to respond to environmental changes without degrading learned knowledge; this can be achieved by regulating behaviour with neuromodulation—a biological process found in the brain. We demonstrate that by modulating activity-propagating signals, neurally trained agents evolving to solve tasks in dynamic environments that are prone to change can expect a significantly higher fitness than non-modulatory agents and also achieve their goals more often. Further, we show that while behavioural plasticity can help agents to achieve goals in these variable environments, this ability to overcome environmental changes with greater success comes at the cost of highly volatile evolution.

• Norstein, Emma Stensby; Ellefsen, Kai Olav & Glette, Kyrre (2021). Co-optimising Robot Morphology and Controller in a Simulated Open-Ended Environment. I Castillo, Pedro A. & Laredo, Juan Luiz Jiménez (Red.), Applications of Evolutionary Computation. Springer. ISSN 9783030726997. doi: 10.1007/978-3-030-72699-7_3. Fulltekst i vitenarkiv Vis sammendrag

  Designing robots by hand can be costly and time consuming, especially if the robots have to be created with novel materials, or be robust to internal or external changes. In order to create robots automatically, without the need for human intervention, it is necessary to optimise both the behaviour and the body design of the robot. However, when co-optimising the morphology and controller of a locomoting agent the morphology tends to converge prematurely, reaching a local optimum. Approaches such as explicit protection of morphological innovation have been used to reduce this problem, but it might also be possible to increase exploration of morphologies using a more indirect approach. We explore how changing the environment, where the agent locomotes, affects the convergence of morphologies. The agents’ morphologies and controllers are co-optimised, while the environments the agents locomote in are evolved open-endedly with the Paired Open-Ended Trailblazer (POET). We compare the diversity, fitness and robustness of agents evolving in environments generated by POET to agents evolved in handcrafted curricula of environments. Our agents each contain of a population of individuals being evolved with a genetic algorithm. This population is called the agent-population. We show that agent-populations evolving in open-endedly evolving environments exhibit larger morphological diversity than agent-populations evolving in hand crafted curricula of environments. POET proved capable of creating a curriculum of environments which encouraged both diversity and quality in the populations. This suggests that POET may be capable of reducing premature convergence in co-optimisation of morphology and controllers.

• Nordmoen, Jørgen Halvorsen; Veenstra, Frank; Ellefsen, Kai Olav & Glette, Kyrre (2021). MAP-Elites Enables Powerful Stepping Stones and Diversity for Modular Robotics. Frontiers in Robotics and AI. 8. doi: 10.3389/frobt.2021.639173. Fulltekst i vitenarkiv Vis sammendrag

  In modular robotics modules can be reconfigured to change the morphology of the robot, making it able to adapt to specific tasks. However, optimizing both the body and control of such robots is a difficult challenge due to the intricate relationship between fine-tuning control and morphological changes that can invalidate such optimizations. These challenges can trap many optimization algorithms in local optima, halting progress towards better solutions. To solve this challenge we compare three different Evolutionary Algorithms on their capacity to optimize high performing and diverse morphologies and controllers in modular robotics. We compare two objective-based search algorithms, with and without a diversity promoting objective, with a Quality Diversity algorithm—MAP-Elites. The results show that MAP-Elites is capable of evolving the highest performing solutions in addition to generating the largest morphological diversity. Further, MAP-Elites is superior at regaining performance when transferring the population to new and more difficult environments. By analyzing genealogical ancestry we show that MAP-Elites produces more diverse and higher performing stepping stones than the two other objective-based search algorithms. The experiments transitioning the populations to new environments show the utility of morphological diversity, while the analysis of stepping stones show a strong correlation between diversity of ancestry and maximum performance on the locomotion task. Together, these results demonstrate the suitability of MAP-elites for the challenging task of morphology-control search for modular robots, and shed light on the algorithm’s capability of generating stepping stones for reaching high-performing solutions.

• Nygaard, Tønnes; Martin, Charles Patrick; Tørresen, Jim; Glette, Kyrre & Howard, David (2021). Real-world embodied AI through a morphologically adaptive quadruped robot. Nature Machine Intelligence. doi: 10.1038/s42256-021-00320-3. Fulltekst i vitenarkiv Vis sammendrag

  Robots are traditionally bound by a fixed morphology during their operational lifetime, which is limited to adapting only their control strategies. Here we present the first quadrupedal robot that can morphologically adapt to different environmental conditions in outdoor, unstructured environments. Our solution is rooted in embodied AI and comprises two components: (1) a robot that permits in situ morphological adaptation and (2) an adaptation algorithm that transitions between the most energy-efficient morphologies on the basis of the currently sensed terrain. We first build a model that describes how the robot morphology affects performance on selected terrains. We then test continuous adaptation on realistic outdoor terrain while allowing the robot to constantly update its model. We show that the robot exploits its training to effectively transition between different morphological configurations, exhibiting substantial performance improvements over a non-adaptive approach. The demonstrated benefits of real-world morphological adaptation demonstrate the potential for a new embodied way of incorporating adaptation into future robotic designs.

• Barnes, Chloe M; Ekárt, Anikó; Ellefsen, Kai Olav; Glette, Kyrre; Lewis, Peter R. & Tørresen, Jim (2021). Evolving Neuromodulated Controllers in Variable Environments, 2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems. IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781665412612. s. 164–169. doi: 10.1109/ACSOS52086.2021.00037. Fulltekst i vitenarkiv Vis sammendrag

  Modern technical systems are increasingly composed of heterogeneous components that are situated in variable environments. In nature, organisms can temporarily adapt their behaviour to novel stimuli with behavioural plasticity; this can be achieved with neuromodulation, a biological process that modulates synaptic activity in the brain. We explore how neuromodulation affects goal-achievement in evolved neural controllers for artificial agents in variable environments. As variability can arise from the actions of others, we show that the benefit of plasticity can increase with variability, as agents can temporarily change their phenotype within their lifetime. Further, we show that cooperation can emerge between plastic agents that cannot perceive one another in highly variable environments.

• Nygaard, Tønnes; Martin, Charles Patrick; Howard, David; Tørresen, Jim & Glette, Kyrre (2021). Environmental Adaptation of Robot Morphology and Control Through Real-world Evolution. Evolutionary Computation. ISSN 1063-6560. doi: 10.1162/evco_a_00291. Fulltekst i vitenarkiv Vis sammendrag

  Robots operating in the real world will experience a range of different environments and tasks. It is essential for the robot to have the ability to adapt to its surroundings to work efficiently in changing conditions. Evolutionary robotics aims to solve this by optimizing both the control and body (morphology) of a robot, allowing adaptation to internal, as well as external factors. Most work in this field has been done in physics simulators, which are relatively simple and not able to replicate the richness of interactions found in the real world. Solutions that rely on the complex interplay between control, body, and environment are therefore rarely found. In this paper, we rely solely on real-world evaluations and apply evolutionary search to yield combinations of morphology and control for our mechanically self-reconfiguring quadruped robot. We evolve solutions on two distinct physical surfaces and analyze the results in terms of both control and morphology. We then transition to two previously unseen surfaces to demonstrate the generality of our method. We find that the evolutionary search finds high-performing and diverse morphology-controller configurations by adapting both control and body to the different properties of the physical environments. We additionally find that morphology and control vary with statistical significance between the environments. Moreover, we observe that our method allows for morphology and control parameters to transfer to previously-unseen terrains, demonstrating the generality of our approach.

• Nygaard, Tønnes; Howard, David & Glette, Kyrre (2020). Real world morphological evolution is feasible. I Coello, Carlos A. Coello (Red.), GECCO '20: Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion. Association for Computing Machinery (ACM). ISSN 9781450371278. s. 1392–1394. doi: 10.1145/3377929.3398095. Fulltekst i vitenarkiv Vis sammendrag

  Evolutionary algorithms offer great promise for the automatic design of robot bodies, tailoring them to specific environments or tasks. Most research is done on simplified models or virtual robots in physics simulators, which do not capture the natural noise and richness of the real world. Very few of these virtual robots are built as physical robots, and the few that are will rarely be further improved in the actual environment they operate in, limiting the effectiveness of the automatic design process. We utilize our shape-shifting quadruped robot, which allows us to optimize the design in its real-world environment. The robot is able to change the length of its legs during operation, and is robust enough for complex experiments and tasks. We have co-evolved control and morphology in several different scenarios, and have seen that the algorithm is able to exploit the dynamic morphology solely through real-world experiments.

• Côté-Allard, Ulysse; Gagnon-Turcotte, Gabriel; Phinyomark, Angkoon; Glette, Kyrre; Scheme, Erik & Laviolette, Francois [Vis alle 7 forfattere av denne artikkelen] (2020). Unsupervised Domain Adversarial Self-Calibration for Electromyography-Based Gesture Recognition. IEEE Access. 8, s. 177941–177955. doi: 10.1109/ACCESS.2020.3027497. Fulltekst i vitenarkiv Vis sammendrag

  Surface electromyography (sEMG) provides an intuitive and non-invasive interface from which to control machines. However, preserving the myoelectric control system’s performance over multiple days is challenging, due to the transient nature of the signals obtained with this recording technique. In practice, if the system is to remain usable, a time-consuming and periodic recalibration is necessary. In the case where the sEMG interface is employed every few days, the user might need to do this recalibration before every use. Thus, severely limiting the practicality of such a control method. Consequently, this paper proposes tackling the especially challenging task of unsupervised adaptation of sEMG signals, when multiple days have elapsed between each recording, by introducing Self-Calibrating Asynchronous Domain Adversarial Neural Network (SCADANN). SCADANN is compared with two state-of-the-art self-calibrating algorithms developed specifically for deep learning within the context of EMG-based gesture recognition and three state-of-the-art domain adversarial algorithms. The comparison is made both on an offline and a dynamic dataset (20 participants per dataset), using two different deep network architectures with two different input modalities (temporal-spatial descriptors and spectrograms). Overall, SCADANN is shown to substantially and systematically improves classification performances over no recalibration and obtains the highest average accuracy for all tested cases across all methods.

• Milojevic, Andrija & Glette, Kyrre (2020). Design Optimization of Terrestrial-Walking Soft Robots, Proceedings of The Fifth International Conference – MASING 2020. Faculty of Mechanical Engineering in Niš. ISSN 9788660551391. s. 225–228. Fulltekst i vitenarkiv
• Erdem, Cagri; Jensenius, Alexander Refsum; Glette, Kyrre; Krzyzaniak, Michael Joseph & Veenstra, Frank (2020). Air-Guitar Control of Interactive Rhythmic Robots. Proceedings of the International Conference on Live Interfaces (Proceedings of ICLI). s. 208–210. Fulltekst i vitenarkiv Vis sammendrag

  This paper describes an interactive art installation shown at ICLI in Trondheim in March 2020. The installation comprised three musical robots (Dr. Squiggles) that play rhythms by tapping. Visitors were invited to wear muscle-sensor armbands, through which they could control the robots by performing ‘air-guitar’-like gestures.

• Martin, Charles Patrick; Glette, Kyrre; Nygaard, Tønnes & Tørresen, Jim (2020). Understanding Musical Predictions With an Embodied Interface for Musical Machine Learning. Frontiers in Artificial Intelligence. 3(6). doi: 10.3389/frai.2020.00006. Fulltekst i vitenarkiv Vis sammendrag

  Machine-learning models of music often exist outside the worlds of musical performance practice and abstracted from the physical gestures of musicians. In this work, we consider how a recurrent neural network (RNN) model of simple music gestures may be integrated into a physical instrument so that predictions are sonically and physically entwined with the performer's actions. We introduce EMPI, an embodied musical prediction interface that simplifies musical interaction and prediction to just one dimension of continuous input and output. The predictive model is a mixture density RNN trained to estimate the performer's next physical input action and the time at which this will occur. Predictions are represented sonically through synthesized audio, and physically with a motorized output indicator. We use EMPI to investigate how performers understand and exploit different predictive models to make music through a controlled study of performances with different models and levels of physical feedback. We show that while performers often favor a model trained on human-sourced data, they find different musical affordances in models trained on synthetic, and even random, data. Physical representation of predictions seemed to affect the length of performances. This work contributes new understandings of how musicians use generative ML models in real-time performance backed up by experimental evidence. We argue that a constrained musical interface can expose the affordances of embodied predictive interactions.

• Veenstra, Frank & Glette, Kyrre (2020). How Different Encodings Affect Performance and Diversification when Evolving the Morphology and Control of 2D Virtual Creatures. I Bongard, Josh (Red.), The 2020 Conference on Artificial Life. MIT Press. s. 592–601. doi: 10.1162/isal_a_00295. Fulltekst i vitenarkiv Vis sammendrag

  A challenge in evolutionary robotics is the in parallel adaptation of morphologies and controllers. Here, we considered encoding methods for morphogenesis of 2D virtual creatures that can be created from directed trees. Using an evolutionary algorithm, we optimized locomotion in these virtual creatures and compared a direct encoding, an L-System, and two types of encodings that produce neural networks—a Compositional Pattern Producing Network (CPPN) and a Cellular Encoding (CE). We evaluated these encodings based on performance and diversification, and we introduced an OpenAI gym environment as a computationally inexpensive benchmark for exploring morphological evolution. The direct encoding and L-System generated more fit solutions compared to the network strategies. Considering morphological diversity, the direct encoding finds solutions more locally in the morphological search space, the L-System made larger jumps across this search space, and both network approaches also make larger jumps though find fewer solutions in this space. With these results we show how encodings exhibit different characteristics as developmental approaches. Since the genotype-phenotype mapping plays a major role in evolutionary robotics, further modifications using more complex tasks and environments can lead to a better understanding of morphogenesis and thereby improve how morphologies and controllers of robots are evolved.

• Barnes, Chloe M; Ekárt, Anikó; Ellefsen, Kai Olav; Glette, Kyrre; Lewis, Peter R. & Tørresen, Jim (2020). Coevolutionary Learning of Neuromodulated Controllers for Multi-Stage and Gamified Tasks, 2020 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781728172781. s. 129–138. doi: 10.1109/ACSOS49614.2020.00034. Fulltekst i vitenarkiv
• Nordmoen, Jørgen Halvorsen; Veenstra, Frank; Ellefsen, Kai Olav & Glette, Kyrre (2020). Quality and Diversity in Evolutionary Modular Robotics, 2020 IEEE Symposium Series on Computational Intelligence (SSCI). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781728125473. s. 2109–2116. doi: 10.1109/SSCI47803.2020.9308511. Fulltekst i vitenarkiv
• Engebråten, Sondre Andreas; Moen, Hans Jonas Fossum; Yakimenko, Oleg A. & Glette, Kyrre (2020). A framework for automatic behavior generation in multi-function swarms. Frontiers in Robotics and AI. doi: 10.3389/frobt.2020.579403. Fulltekst i vitenarkiv Vis sammendrag

  Multi-function swarms are swarms that solve multiple tasks at once. For example, a quadcopter swarm could be tasked with exploring an area of interest while simultaneously functioning as ad-hoc relays. With this type of multi-function comes the challenge of handling potentially conflicting requirements simultaneously. Using the Quality-Diversity algorithm MAP-elites in combination with a suitable controller structure, a framework for automatic behavior generation in multi-function swarms is proposed. The framework is tested on a scenario with three simultaneous tasks: exploration, communication network creation and geolocation of Radio Frequency (RF) emitters. A repertoire is evolved, consisting of a wide range of controllers, or behavior primitives, with different characteristics and trade-offs in the different tasks. This repertoire enables the swarm to online transition between behaviors featuring different trade-offs of applications depending on the situational requirements. Furthermore, the effect of noise on the behavior characteristics in MAP-elites is investigated. A moderate number of re-evaluations is found to increase the robustness while keeping the computational requirements relatively low. A few selected controllers are examined, and the dynamics of transitioning between these controllers are explored. Finally, the study investigates the importance of individual sensor or controller inputs. This is done through ablation, where individual inputs are disabled and their impact on the performance of the swarm controllers is assessed and analyzed.

• Nygaard, Tønnes Frostad; Nordmoen, Jørgen Halvorsen; Ellefsen, Kai Olav; Martin, Charles Patrick; Tørresen, Jim & Glette, Kyrre (2019). Experiences from Real-World Evolution with DyRET: Dynamic Robot for Embodied Testing, Nordic Artificial Intelligence Research and Development: Third Symposium of the Norwegian AI Society, NAIS 2019. Springer. ISSN 9783030356644. s. 58–68. doi: 10.1007/978-3-030-35664-4_6. Fulltekst i vitenarkiv
• St-Onge, David; Côté-Allard, Ulysse; Glette, Kyrre Harald; Gosselin, Benoit & Beltrame, Giovanni (2019). Engaging with Robotic Swarms: Commands from Expressive Motion. ACM Transactions on Human-Robot Interaction. doi: 10.1145/3323213. Fulltekst i vitenarkiv
• Côté-Allard, Ulysse; Fall, Cheikh Latyr; Drouin, Alexandre; Campeau-Lecours, Alexandre; Gosselin, Clément & Glette, Kyrre Harald [Vis alle 8 forfattere av denne artikkelen] (2019). Deep Learning for Electromyographic Hand Gesture Signal Classification Using Transfer Learning. IEEE transactions on neural systems and rehabilitation engineering. ISSN 1534-4320. doi: 10.1109/TNSRE.2019.2896269. Fulltekst i vitenarkiv
• Miseikis, Justinas; Brijacak, Inka; Yahyanejad, Saeed; Glette, Kyrre; Elle, Ole Jacob & Tørresen, Jim (2019). Two-Stage Transfer Learning for Heterogeneous Robot Detection and 3D Joint Position Estimation in a 2D Camera Image Using CNN. IEEE International Conference on Robotics and Automation (ICRA). ISSN 1050-4729. 2019-May, s. 8883–8889. doi: 10.1109/ICRA.2019.8794077. Fulltekst i vitenarkiv Vis sammendrag

  Collaborative robots are becoming more common on factory floors as well as regular environments, however, their safety still is not a fully solved issue. Collision detection does not always perform as expected and collision avoidance is still an active research area. Collision avoidance works well for fixed robot-camera setups, however, if they are shifted around, Eye-to-Hand calibration becomes invalid making it difficult to accurately run many of the existing collision avoidance algorithms. We approach the problem by presenting a stand-alone system capable of detecting the robot and estimating its position, including individual joints, by using a simple 2D colour image as an input, where no Eye-to-Hand calibration is needed. As an extension of previous work, a two-stage transfer learning approach is used to re-train a multi-objective convolutional neural network (CNN) to allow it to be used with heterogeneous robot arms. Our method is capable of detecting the robot in real-time and new robot types can be added by having significantly smaller training datasets compared to the requirements of a fully trained network. We present data collection approach, the structure of the multi-objective CNN, the two-stage transfer learning training and test results by using real robots from Universal Robots, Kuka, and Franka Emika. Eventually, we analyse possible application areas of our method together with the possible improvements.

• Nygaard, Tønnes Frostad; Martin, Charles Patrick; Tørresen, Jim & Glette, Kyrre (2019). Self-Modifying Morphology Experiments with DyRET: Dynamic Robot for Embodied Testing. IEEE International Conference on Robotics and Automation (ICRA). ISSN 1050-4729. 2019-May, s. 9446–9452. doi: 10.1109/ICRA.2019.8793663. Fulltekst i vitenarkiv Vis sammendrag

  If robots are to become ubiquitous, they will need to be able to adapt to complex and dynamic environments. Robots that can adapt their bodies while deployed might be flexible and robust enough to meet this challenge. Previous work on dynamic robot morphology has focused on simulation, combining simple modules, or switching between locomotion modes. Here, we present an alternative approach: a self-reconfigurable morphology that allows a single four-legged robot to actively adapt the length of its legs to different environments. We report the design of our robot, as well as the results of a study that verifies the performance impact of self-reconfiguration. This study compares three different control and morphology pairs under different levels of servo supply voltage in the lab. We also performed preliminary tests in different uncontrolled outdoor environments to see if changes to the external environment supports our findings in the lab. Our results show better performance with an adaptable body, lending evidence to the value of self-reconfiguration for quadruped robots.

• Nygaard, Tønnes Frostad; Martin, Charles Patrick; Tørresen, Jim & Glette, Kyrre (2019). Evolving Robots on Easy Mode: Towards a Variable Complexity Controller for Quadrupeds. Lecture Notes in Computer Science (LNCS). ISSN 0302-9743. 11454 LNCS, s. 616–632. doi: 10.1007/978-3-030-16692-2_41. Fulltekst i vitenarkiv Vis sammendrag

  The complexity of a legged robot’s environment or task can inform how specialised its gait must be to ensure success. Evolving specialised robotic gaits demands many evaluations—acceptable for computer simulations, but not for physical robots. For some tasks, a more general gait, with lower optimization costs, could be satisfactory. In this paper, we introduce a new type of gait controller where complexity can be set by a single parameter, using a dynamic genotype-phenotype mapping. Low controller complexity leads to conservative gaits, while higher complexity allows more sophistication and high performance for demanding tasks, at the cost of optimization effort. We investigate the new controller on a virtual robot in simulations and do preliminary testing on a real-world robot. We show that having variable complexity allows us to adapt to different optimization budgets. With a high evaluation budget in simulation, a complex controller performs best. Moreover, real-world evolution with a limited evaluation budget indicates that a lower gait complexity is preferable for a relatively simple environment.

Se alle arbeider i NVA

• Glette, Kyrre (2026). How can we use ALICE concepts for creative purposes? doi: https:/2026.aliceworkshop.org/speakers/. Fulltekst i vitenarkiv
• Stensby, Emma Hjellbrekke; Yasui, Kotaro; Kano, Takeshi; Ishiguro, Akio & Glette, Kyrre (2026). Behaviour Diversity in a Walking and Climbing Centipede-Like Virtual Creature. Fulltekst i vitenarkiv
• Ellefsen, Kai Olav; Bruin, Ege de; Glette, Kyrre & Luck, Kevin (2026). Special Session: Co-design of Robot Morphology and Control. doi: https:/www.mn.uio.no/ifi/english/people/aca/kaiolae/alife-2026-special-session-on-co-design-of-robot-m.html. Fulltekst i vitenarkiv
• Veenstra, Frank; Bruin, Ege de; Glette, Kyrre & Ellefsen, Kai Olav (2025). Co-Optimization of Robot Bodies and Brains with Evolutionary Algorithms. Fulltekst i vitenarkiv Vis sammendrag

  Read this story on the University of Oslo's website.

• Christodoulou, Anna-Maria; Glette, Kyrre; Lartillot, Olivier & Jensenius, Alexander Refsum (2025). MusiQAl: Music Question Answering through Audio-Video fusion. doi: https:/ismir2025.ismir.net/program-detailed-schedule. Fulltekst i vitenarkiv
• Glette, Kyrre (2025). Biologically-inspired AI: A framework for designing adaptive robots. Fulltekst i vitenarkiv
• Glette, Kyrre (2024). Evolutionary design of morphology and control for simulated and real-world robots. Fulltekst i vitenarkiv
• Søyseth, Vegard; Bergflødt, Adrian Anderson; Glette, Kyrre; Watanabe, Shin & Otterdijk, Marieke van (2024). Utstilling av roboter på SENT @ Teknisk museum. Fulltekst i vitenarkiv
• Jónsson, Björn Thór; Erdem, Çağri; Fasciani, Stefano & Glette, Kyrre (2024). Towards Sound Innovation Engines Using Pattern-Producing Networks and Audio Graphs. Fulltekst i vitenarkiv Vis sammendrag

  This study draws on the challenges that composers and sound designers face in creating and refining new tools to achieve their musical goals. Utilising evolutionary processes to promote diversity and foster serendipitous discoveries, we propose to automate the search through uncharted sonic spaces for sound discovery. We argue that such diversity promoting algorithms can bridge a technological gap between the theoretical realisation and practical accessibility of sounds. Specifically, in this paper we describe a system for generative sound synthesis using a combination of Quality Diversity (QD) algorithms and a discriminative model, inspired by the Innovation Engine algorithm. The study explores different configurations of the generative system and investigates the interplay between the chosen sound synthesis approach and the discriminative model. The results indicate that a combination of Compositional Pattern Producing Network (CPPN) + Digital Signal Processing (DSP) graphs coupled with Multi-dimensional Archive of Phenotypic Elites (MAP-Elites) and a deep learning classifier can generate a substantial variety of synthetic sounds. The study concludes by presenting the generated sound objects through an online explorer and as rendered sound files. Furthermore, in the context of music composition, we present an experimental application that showcases the creative potential of our discovered sounds.

• Glette, Kyrre (2024). Bio-inspiration and divergent search algorithms for robotics and sound exploration. Fulltekst i vitenarkiv
• Norstein, Emma Stensby; Yasui, Kotaro; Kano, Takeshi; Glette, Kyrre & Ishiguro, Akio (2024). A bio-inspired decentralized approach to multi-morphology control. Fulltekst i vitenarkiv Vis sammendrag

  Traditional robot controllers are usually optimized for a specific robot design, and will often fail if the robot’s morphology is changed. This can be a challenge for robustness to damage, self-reconfiguring robots, or in the case of morphology design search algorithms, where each new robot design dictates re-learning the controller. Here, we take on a highly bio-inspired approach, taking inspiration from the versatility of myriapod locomotion, to create a multi-morphology controller. We propose a simple decentralized controller model, which can, without change in parameters, adapt to various centipede-like morphologies and display different behaviors based on changes in the morphology and environment. The approach shows potential for robot design and could potentially be useful for understanding mechanisms of animal locomotion.

• Glette, Kyrre; Ellefsen, Kai Olav; Norstein, Emma Stensby & Bruin, Ege de (2024). Automatic Design of Robot Bodies and Brains with Evolutionary Algorithms - Tutorial. Fulltekst i vitenarkiv Vis sammendrag

  The evolution of robot bodies and brains allows researchers to investigate which building blocks are interesting for evolving Artificial Life, and how controllers and morphologies can be shaped together for automated robot design. This tutorial aims to introduce evolution of robot body and control, and some of the key challenges one faces when doing experiments in Evolutionary Robotics. These include finding good ways to represent robots (genotypic encodings), challenges related to co-optimizing morphology and control, how environments shape body and control, and selecting the right physical substrate for evolving robots. After introducing these challenges and showing relevant examples from our own and other labs’ research, we will present a short demo of how to run Evolutionary Robotics experiments in practice, with the Unity ML-Agents framework.

• Glette, Kyrre (2024). Evolution of morphology and control - from simulation to reality. Fulltekst i vitenarkiv
• Jónsson, Björn Thór; Erdem, Cagri; Fasciani, Stefano & Glette, Kyrre (2024). Cultivating Open-Earedness with Sound Objects discovered by Open-Ended Evolutionary Systems. Fulltekst i vitenarkiv Vis sammendrag

  Interaction with generative systems can face the choice of generalising towards a middle ground or diverging towards novelty. Efforts have been made in the domain of sounds to enable divergent exploration in search of interesting discoveries. Those efforts have been confined by pre-trained models and single environments. We are building on those efforts to enable autonomous discovery of sonic landscapes. Furthermore, we draw inspiration from research on open-ended evolution to continuously provide evolutionary processes with new opportunities for sonic discoveries. Exposure to autonomously discovered sound objects can elevate openness to sonic experiences, which in turn offers inspiring opportunities for creative work involving sounds.

• Christodoulou, Anna-Maria; Dutta, Sagar; Lartillot, Olivier; Glette, Kyrre & Jensenius, Alexander Refsum (2024). Exploring Convolutional Neural Network Models for Multimodal Classification of Expressive Piano Performance. Fulltekst i vitenarkiv
• Kvalsund, Mia-Katrin; Ellefsen, Kai; Glette, Kyrre; Pontes-Filho, Sidney & Lepperød, Mikkel (2023). The distributed neocortex: How neuroscience can inspire distributed AI systems. Fulltekst i vitenarkiv
• Szorkovszky, Alexander; Veenstra, Frank & Glette, Kyrre (2023). Toward cultures of rhythm in legged robots. doi: 10.1162/isal_a_00673. Fulltekst i vitenarkiv Vis sammendrag

  It is widely thought that sensorimotor synchronization, underpinning cultural domains such as music and dance, played a critical role in the evolution of human sociality. Here, we present virtual legged robots controlled by central pattern generators (CPGs) that evolve to synchronize motion to rhythmic sensory input in real time. Multi-stage, multi-objective evolutionary algorithms were used to maximize flexibility of the CPGs with respect to control parameters, and then to optimize a neural input layer for wide-ranging susceptibility to rhythmic inputs. The evolved CPGs self-organize to accommodate the input sequence over a range of frequencies and patterns while keeping the agents upright. We show how this behaviour can be scaled up to multiple interacting agents, including with differing morphologies, to produce novel behaviours. We then outline how spike timing dependent plasticity can be used for the acquisition of new motor patterns. Finally, taking inspiration from biocultural evolution and cognitive neuroscience, we suggest ways in which real-time social adaptation can play a key role in the evolution of complex social behaviours in robots.

• Glette, Kyrre (2023). Adaptive robots through evolutionary algorithms and machine learning. Fulltekst i vitenarkiv
• Glette, Kyrre (2023). Evolutionary and adaptive robotics: from simulation to reality. Fulltekst i vitenarkiv
• Glette, Kyrre (2023). Bio-inspiration for robot design and adaptation. Fulltekst i vitenarkiv
• Veenstra, Frank; Norstein, Emma Stensby & Glette, Kyrre (2023). Tutorial: Evolving Robot Bodies and Brains with Unity. Fulltekst i vitenarkiv Vis sammendrag

  The evolution of robot bodies and brains allows researchers to investigate which building blocks are interesting for evolving artificial life. Agnostic to the evolutionary approach used, the supplied building blocks influence how artificial organisms will behave. What should these building blocks look like? How should we associate control units with these building blocks? How should we represent the genomes of these robots? In this tutorial we discuss (1) previous approaches to evolving robots and virtual creatures, (2) outline how Unity simulations and Unity's ML-agents package can be used as an interface, and (3) our approach to evolving bodies and brains using Unity. There are many existing solutions that are tailored to experimenting with body brain co-optimization and we have been using several simulation approaches to evolve modular robots that are represented by directed trees (directed acyclic graphs). Since evolving bodies can be relatively complex, we give participants an overview of existing methods and invite the participants to get some guided hands-on experience using the Unity ML-Agents for evolving robots. The Unity ML-Agents toolkit is an open-source toolkit for game developers, AI researchers, and hobbyists that can be used to train agents using various AI methods. Similar to OpenAI gym, it supplies a Python API through which one can optimize agents in a variety of environments. The Unity ML-Agents toolkit provides an easy-to-use interface that is flexible enough to allow for quick design iterations for evolving robot bodies and brains. This tutorial is aimed at researchers that are interested in simulating the evolution of bodies and brains of robots. The tutorial will provide an overview of existing approaches to evolving bodies and brains of robots, and demonstrate how to design and incorporate control units, morphological components, environments and objectives. Participants will learn how to use Unity ML-Agents as a tool with evolutionary algorithms and learn how they can create incorporate their own robotic modules for evolving robots.

• Howard, David; Glette, Kyrre & Cheney, Nick (2022). Editorial: Evolving Robotic Morphologies. Frontiers in Robotics and AI. 9. doi: 10.3389/frobt.2022.874853. Fulltekst i vitenarkiv
• Fuhrer, Julian; Glette, Kyrre; Ivanovic, Jugoslav; Larsson, Pål Gunnar; Bekinschtein, Tristan & Kochen, Silvia [Vis alle 11 forfattere av denne artikkelen] (2022). Direct brain recordings reveal continuous encoding of structure in random stimuli. Fulltekst i vitenarkiv
• Fuhrer, Julian; Blenkmann, Alejandro Omar; Endestad, Tor; Solbakk, Anne-Kristin & Glette, Kyrre (2022). Complexity-Based Encoded Information Quantification in Neurophysiological Recordings. Fulltekst i vitenarkiv
• Blenkmann, Alejandro Omar; Fuhrer, Julian; Glette, Kyrre; Ivanovic, Jugoslav; Larsson, Pål Gunnar & Bekinschtein, Tristan [Vis alle 11 forfattere av denne artikkelen] (2022). Direct brain recordings reveal continuous encoding of structure in random stimuli. Fulltekst i vitenarkiv
• Szorkovszky, Alexander; Veenstra, Frank & Glette, Kyrre (2022). From real-time adaptation to social learning in robots. Fulltekst i vitenarkiv
• Glette, Kyrre (2020). Evolutionary algorithms for intelligent robots. Fulltekst i vitenarkiv
• Ahmadi, Arash; Rosnes, Ida; Blicher, Pernille; Diekmann, Robin; Schuttpelz, Mark & Glette, Kyrre [Vis alle 10 forfattere av denne artikkelen] (2019). Publisher Correction: Breaking the speed limit with multimode fast scanning of DNA by Endonuclease V (Nature Communications, (2018), 9, 1, (5381), 10.1038/s41467-018-07797-4). Nature Communications. 10(1). doi: 10.1038/s41467-019-10070-x. Fulltekst i vitenarkiv
• Miseikis, Justinas; Brijacak, Inka; Yahyanejad, Saeed; Glette, Kyrre; Elle, Ole Jacob & Tørresen, Jim (2019). Two-Stage Transfer Learning for Heterogeneous Robot Detection and 3D Joint Position Estimation in a 2D Camera Image Using CNN. Fulltekst i vitenarkiv
• Nygaard, Tønnes Frostad; Martin, Charles Patrick; Tørresen, Jim & Glette, Kyrre (2019). Self-Modifying Morphology Experiments with DyRET: Dynamic Robot for Embodied Testing. Fulltekst i vitenarkiv
• Nygaard, Tønnes Frostad; Nordmoen, Jørgen Halvorsen; Martin, Charles Patrick; Tørresen, Jim & Glette, Kyrre (2019). Lessons Learned from Real-World Experiments with DyRET: the Dynamic Robot for Embodied Testing. Fulltekst i vitenarkiv
• Glette, Kyrre (2019). Kunstig intelligens for tilpasningsdyktige roboter. Fulltekst i vitenarkiv
• Nordmoen, Jørgen; Glette, Kyrre & Ellefsen, Kai Olav (2021). Enhancing MAP-Elites to overcome challenges in Evolutionary Robotics. University of Oslo. Fulltekst i vitenarkiv
• Nygaard, Tønnes; Glette, Kyrre; Tørresen, Jim & Martin, Charles Patrick (2020). Legging It: An Evolutionary Approach to Morphological Adaptation for a Real-World Quadruped Robot. Universitetet i Oslo. Fulltekst i vitenarkiv Vis sammendrag

  Robots are used in increasingly complex environments and need to be able to adapt to changes and unexpected events. This has traditionally been solved by changing the control of a robot, but having an adjustable body can unlock new and powerful adaptive capabilities. An adaptive morphology allows tuning of the physical structure of the robot to different, often conflicting, dynamic requirements, including speed, stability, and efficiency. It can also unlock new functionalities that might not be possible with static morphologies, including variable gearing and multiple locomotion modalities. Even with the potential benefits of morphological adaptation, the methods and technology are still not at a point where there is wide-spread use of adaptive morphologies in physical robots. The main goal of the thesis is to develop methods and technology to enable adaptation of the physical body of a robot to new real-world environments. An evolutionary approach is taken, and to what degree evolutionary algorithms are able to exploit the dynamic morphology of a legged robot is investigated. The feasibility of continuous adaptation of morphology in realistic outdoor environments is also explored. A quadruped mammal-inspired robot with the ability to continuously adjust the length of its legs during operation has been designed and implemented as part of the work outlined in the thesis. Evolutionary algorithms are used to optimize both the control and morphology of the robot to different hardware conditions and walking surfaces in the lab. To achieve this, a new gait controller concept with an adjustable complexity is introduced. This allows evolution in scenarios with a wide range of evaluation budgets. A final proof-of-concept implementation of adaptive morphology is also demonstrated. Our robot was shown to be able to adapt its body continuously while walking in different unstructured outdoor terrains, significantly outperforming a non-adaptive approach. The thesis concludes that adaptation of the physical body of a robot is feasible, and in fact, already shows significant benefits with current technology and methods. Evolutionary algorithms are shown to be effective for adaptation of morphology in a range of different conditions. By developing new methods and technology, as well as demonstrating their utility through real-world experiments, we hope to inspire others to use adaptive morphology on their physical robots.

• Stensby, Emma Hjellbrekke & Glette, Kyrre (2020). Co-evolving morphology and controller in an open-ended environment. Universitetet i Oslo. Fulltekst i vitenarkiv Vis sammendrag

  Designing robots by hand is often both costly and time consuming. In order to create robots automatically, without the need for human intervention, it is necessary to optimise both the behaviour and the body design of the robot. However, when co-optimising the morphology and controller of a locomoting agent the morphology tends to converge prematurely, reaching a local optimum. Approaches such as explicit protection of morphological innovation have been used to reduce this problem, but it might also be possible to increase the exploration of morphologies using a more indirect approach. We explore how changing the environment the agent locomotes in affects the convergence of morphologies. Inspired by POET, an algorithm which evolves environments open-endedly, we create POET-M, an expansion of POET which includes evolution of morphologies. We compare the morphological change and diversity of agents evolving in a static environment, a curriculum of hand crafted environments, and in POET-M. We show that the agents experience increased morphological change in response to environmental change, and that agents evolving in an open-ended environment exhibit larger morphological diversity in the population than agents evolving in a static flat environment or a hand crafted curriculum of environments. POET-M proved capable of creating a curricula of environments which encouraged both diversity and quality in the population. This might suggest that the open-endedly evolving environments in POET-M act as stepping stones for the agents, enabling the morphology to escape local optima and continue evolving past the early stages of the evolution.

• Lee, Wonho & Glette, Kyrre (2020). A Neuroevolutionary Approach to Evolve a Flexible Neural Controller for a Morphology Changing Quadruped Robot. Universitetet i Oslo. Fulltekst i vitenarkiv Vis sammendrag

  Designing a gait controller for a morphology changing robot is a challenging problem due to the high degree of freedom. In 2013, Risi showed that by learning the relation between morphology and controller, it is possible to evolve a neural network-based controller that can walk on different morphologies. This thesis aims to implement Risi's flexible controller for a robot platform that features a morphology changing physical robot, Dynamic Robot for Embodied Testing: DyRET, developed at the University of Oslo. Also, it compares which of the evolutionary algorithms (EA) would be the best fit for the task - among behavior diversity, fitness-based and multi-objective EA (MOEA), and combinations of different behavior descriptors for behavior diversity EA. In particular, this thesis implements a flexible controller based on Hypercube-based NeuroEvolution of Augmented Topologies, designed to learn the relation between the morphology and the controller based on the previous work. The controller is evolved by Novelty search, fitness, and MOEA, combining both. Three behavior descriptors are implemented - max-min amplitude, duty factor, and the last position. The experiments are conducted on the simulation environment provided by DyRET. The results show that it is possible to evolve a stable controller that can walk on various morphology for DyRET platform while not all the evolved controllers learned the relationship between the controller and the morphology. Also, the comparison of EA's revealed that fitness-based EA could produce controllers that are as good as the behavior diversity EA and MOEA for the given constraints. The experiment also indicates that combining all three behavior descriptors can generate most fit controllers while not statistically significant when comparing the walking distance.

Se alle arbeider i NVA