Assistive Gym: A Physics Simulation Framework for Assistive Robotics
This provides a tool for researchers in assistive robotics to safely simulate physical interactions, though it is incremental as it extends existing simulation methods to multiple tasks.
The authors tackled the challenge of training assistive robots for multiple tasks by developing Assistive Gym, an open-source physics simulation framework that includes six environments for activities of daily living, and demonstrated improved assistance through modeling human motion with baseline policies for four commercial robots.
Autonomous robots have the potential to serve as versatile caregivers that improve quality of life for millions of people worldwide. Yet, conducting research in this area presents numerous challenges, including the risks of physical interaction between people and robots. Physics simulations have been used to optimize and train robots for physical assistance, but have typically focused on a single task. In this paper, we present Assistive Gym, an open source physics simulation framework for assistive robots that models multiple tasks. It includes six simulated environments in which a robotic manipulator can attempt to assist a person with activities of daily living (ADLs): itch scratching, drinking, feeding, body manipulation, dressing, and bathing. Assistive Gym models a person's physical capabilities and preferences for assistance, which are used to provide a reward function. We present baseline policies trained using reinforcement learning for four different commercial robots in the six environments. We demonstrate that modeling human motion results in better assistance and we compare the performance of different robots. Overall, we show that Assistive Gym is a promising tool for assistive robotics research.