CPS: Synergy: Collaborative Research: Learning Control Sharing Strategies for Assistive Cyber-Physical Systems

Assistive machines such as robotic arms and powered wheelchairs promote independence and ability in those with severe motor impairments. As the field of assistive robotics progresses rapidly, these devices are becoming more capable and dextrous and as a result, higher dimensional and harder to control. The dimensionality mismatch between high-dimensional robots and low-dimensional control interfaces requires the control space to be partitioned into control modes. For full control of the robot the user switches between these partitions and this is known as mode switching. Mode switching adds to the cognitive workload and degrades task performance. Shared autonomy helps to alleviate some of the task burden by letting the robot take partial responsibility of task execution. In this work we investigate different paradigms for assistive mode-switching: a) Data-driven approaches to learn models for individual mode-switching behavior and b) identifying control modes that will elicit more informative control commands from the human which will help the robot to perform more accurate intent inference. Our pilot studies indicate that with the learned models the robot is able to predict the correct control modes. Additionally operating the robot in information-maximizing control modes results in better task performance as measured by the number of mode switches and task completion times.