Visualization and Control Synthesis for Rehabilitation and Training

Our group is also interested in building tools to make movement-based learning accessible. Developing such tools will require addressing several separate, but related problems:

  1. generating comprehensible visualizations 
  2. automatically measuring performance

We have developed,visualization tools that present a full body, real-time reconstruction of an individual to allow for distance based motion learning. We have verified this system, which allows users to choose their own view and rate of play, improves the quality and rate of learning. To aid in increasing the rate of learning and to prevent injury, current research has shifted to devising theoretical and numerical techniques to compare the performance of a student to an expert and to develop automated procedures to modify the presentation.

References

  1. S. Burden, H. Gonzalez, R. Vasudevan, R. Bajcsy and S. S. Sastry, “Metrization and Simulation of Controlled Hybrid Systems,” IEEE Transactions on Automatic Control, vol. 60, no. 9, September 2015. [preprint]
  2. A. Majumdar, R. Vasudevan, M. M. Tobenkin and R. Tedrake, “Convex Optimization of Nonlinear Feedback Controllers via Occupation Measures,” International Journal of Robotics Research, vol. 33, pp. 1209-1230, August 2014. [url]
  3. R. Vasudevan, G. Kurillo, E. Lobaton, T. Bernardin, O. Kreylos, R. Bajcsy and K. Nahrstedt, “High Quality Visualization for Geographically Distributed 3D Teleimmersive Applications,” IEEE Transactions on Multimedia, vol. 13, no. 3, pp. 573-584, 2011. [url]