The goal of this project is to contribute to a reliable remote operation of a robotic platform with haptic feedback to the operator (a tactile system, one alternative is the Shadow Robot Hand. In that way, a human can interact within a real-world environment, and touch and feel, although not physically there. However, to make the control smooth and responsive, the project is concerned with hiding delay (latency) and a potentially unstable network connection. That would be on both ends: If the user commands are delayed, the robot platform needs to make a best guess on the next motion. If the feedback from the sensors in the robot platform is delayed, the user still needs to get some haptic feedback. Thus, in both ways, the system needs to model the ongoing motions and actions to compensate for the instability.
The candidate(s) will achieve these goals in a team where the research and researchers in the following Research Council of Norway project are relevant: DRIVE: Brain-driven Remote Collaborative Physical Work
Learning outcome
- Be one of the first to propose a potential solution in enabling a remote-controlled robotic system over the tactile Internet.
- Get insight into the current state-of-the-art within robust remote robot operation with haptic feedback.
- Deep understanding of applying machine learning (data-based design) and/or mathematical optimization (model-based design) in the robust operation of a remote robot controlled through a haptic feedback interface
- The project can start with using openly available datasets but should also contain work with a real robotic system available in the SINLAB: Sustainable Immersive Networking Lab at IFI
- Possibility to publish the result in and attend an international conference.
References
A. Aijaz and M. Sooriyabandara, "The Tactile Internet for Industries: A Review," in Proceedings of the IEEE, vol. 107, no. 2, pp. 414-435, Feb. 2019, doi: 10.1109/JPROC.2018.2878265.
A. Rudenko, L. Palmieri, M. Herman, K.M. Kitani, D.M. Gavrila, K.O. Arras. (2020). “Human motion trajectory prediction: a survey,” The International Journal of Robotics Research, 39(8): 895-935.
J. Tremblay, T. To, A. Molchanov, S. Tyree, J. Kautz and S. Birchfield (2018). “Synthetically Trained Neural Networks for Learning Human-Readable Plans from Real-World Demonstrations,” International Conference on Robotics and Automation (ICRA).
L.-Y. Gui, K. Zhang, Y.-X. Wang, X. Liang, J. M. F. Moura, and M. Veloso. (2018). “Teaching Robots to Predict Human Motion,” IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 562–567.
Pattiwar, Shravan Kumar; Tilleman, Myrthe; Kousias, Konstantinos; Saxena, Paresh; Alay, Ozgu & Griwodz, Carsten (2026). Impact of Latency on User Experience in Immersive Teleoperation: A Study with Motion Capture Gloves and Dexterous Robotic Hand. In Malekian, Reza & Singh, Dhananjay (Ed.), 2025 IEEE Smart World Congress (SWC). ISSN 9798331575984. p. 1787–1794. doi: 10.1109/swc65939.2025.00277. Full text in Research Archive
Qualifications
The candidate(s) is (are) expected to have experience in programming and a basic understanding of network protocols. Preferably, the expertise in designing robotic embedded system and background in machine learning would be a big help.