This project focuses on the development of upper limb rehabilitation robots and therapies that can best adapt to the patients’ level of motor skills and promote stroke recovery. Following my previous research on bio-inspired methods for rendering natural human arm motion, this project further pursue low-level learning for generating dexterous manipulation motions that involve fine motor skills, and high-level motion learning for inferring human intent, preference, and task objectives.
Recent updates
Spring 2018: Nathaniel Goldfarb is continuing to refine the design of the robotic system from the previous semester’s group. The API incorporates the robot dynamics into a ROS architecture to provide a flexible application design platform. Our goal is to perform a usability pilot study by the end of the semester.
Fall 2017: Students in the Synergy of Human and Robotic Systems class developed a prototype of a 3-DOF robotic arm for stroke rehabilitation. The system is designed to operate on a tabletop and be grasped by the operator, which reduces the customization necessary in the system for each operator. The arm is 3D-printed, so this design is cost-effective and easily modified.
Representative publications
- Zhi Li, Dejan Milutinovic and Jacob Rosen, “From Reaching to Reach-to-grasp: the Arm Posture Difference and its Implications on Human Motion Control Strategy”. Experimental Brain Research, 235(5), pp.1627-1642, 2017. download
- Zhi Li, Dejan Milutinovic and Jacob Rosen, “Spatial Map of Synthesized Criteria for the Redundancy Resolution of Human Arm Movements”. IEEE Transactions on Neural Systems & Rehabilitation Engineering, 23(6), pp. 1020 – 1030, Nov. 2015. download
- Zhi Li, Kris Hauser, Jay Ryan Roldan, Dejan Milutinovic, Jacob Rosen, “A Novel Method for Quantifying Arm Motion Similarity”, 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2015), Milan, Italy, August, 2015. download
- Zhi Li, Jay Ryan Roldan, Dejan Milutinovic, Jacob Rosen, “Task-relevance of Grasping-related Degrees of Freedom in Reach-to-grasp Movements”, 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2014), Chicago, USA, September, 2014. download
Active Projects and Desirable Skills
- Integrating haptic devices with rehabilitation video game (Game design, C++, Python, ROS)
- Developing video games for stroke rehabilitation (Game design, C++, python)
- Investigating learning algorithm for motor skill evaluation (AI, C++, python)