.jpg)
.jpg?alt=original&vrtx=view-as-webpage
){kind=link}
I am a researcher at the Robotics and Intelligent Systems (ROBIN) group, Department of Informatics, and the RITMO Centre for Interdisciplinary Studies in Rhythm, Time and Motion, University of Oslo. My work lies at the intersection of machine learning, deep learning, reinforcement learning, multimodal sensing, control, and robotics, with applications in human–robot interaction (HRI), human activity recognition, healthcare, and music.
I hold a Ph.D. in Computer Science from the University of Oslo (2020–2024), where my research—conducted within the Vulnerabilities in the Robot Society (VIROS) project—focused on advancing safety and privacy in human–robot interaction. My doctoral work explored the integration of Model Predictive Control (MPC) with reinforcement learning to improve the safety of robotic manipulation, and developed multimodal deep learning–based sensor fusion algorithms for enhanced robot perception using privacy-preserving sensors such as thermal cameras and LiDARs.
More broadly, my PhD research investigated how robots can achieve human-like decision-making and perception through multimodal sensing, sensor fusion, and multi-layered control frameworks.
Before my PhD, I earned an M.Sc. in Mechanical Engineering (Control Engineering, 2014–2017) from Sharif University of Technology, and a B.Sc. in Mechanical Engineering (2010–2014) from Amirkabir University of Technology. My master’s thesis focused on assistive controllers for balance rehabilitation robotics.
Professionally, I have worked as a Control Engineer at the Djavad Mowafaghian Center for Intelligent NeuroRehabilitation Technologies, contributing to the development of the Sharif Balance Assessment and Rehabilitation Robot (SBARA), and as an R&D Engineer at the Sharif Technology Services Complex, focusing on sensor fusion, control, and machine learning for dynamic systems.
In my current role as a researcher on the Predictive and Intuitive Robot Companion (PIRC) project at RITMO, I work on integrating Large Language Models (LLMs) and Vision–Language Models (VLMs) into robotic systems. My research also explores multimodal machine learning, robotic perception, and adaptive control frameworks inspired by dual-process thinking in humans. This work is highly interdisciplinary, involving collaboration with experts in psychology, music, sports science, and medicine, with the overarching goal of developing robots that are more adaptive, perceptive, and trustworthy partners in complex real-world environments.
Research Interests
-
Machine learning and deep learning
-
Reinforcement learning and robot control
-
Multimodal sensing and sensor fusion
-
Human–robot interaction (HRI)
-
Cognitive robotics and human-like decision-making
-
Model Predictive Control (MPC)
-
Human activity recognition