Policy Learning for Social Robot-Led Physiotherapy
This work addresses the problem of personalized physiotherapy guidance for patients using social robots, but it is incremental as it builds on existing methods with simulated data from proxies.
The paper tackled the challenge of developing adaptive decision-making policies for social robot-led physiotherapy by using expert healthcare practitioners as patient proxies to generate behavior data, resulting in a reinforcement learning policy that adapts exercise instructions to individual exertion tolerances and performance fluctuations.
Social robots offer a promising solution for autonomously guiding patients through physiotherapy exercise sessions, but effective deployment requires advanced decision-making to adapt to patient needs. A key challenge is the scarcity of patient behavior data for developing robust policies. To address this, we engaged 33 expert healthcare practitioners as patient proxies, using their interactions with our robot to inform a patient behavior model capable of generating exercise performance metrics and subjective scores on perceived exertion. We trained a reinforcement learning-based policy in simulation, demonstrating that it can adapt exercise instructions to individual exertion tolerances and fluctuating performance, while also being applicable to patients at different recovery stages with varying exercise plans.