AAAI Publications, Twenty-First IAAI Conference

Font Size: 
Application of the Actor-Critic Architecture to Functional Electrical Stimulation Control of a Human Arm
Philip Sebastian Thomas, Antonie van den Bogert, Kathleen Jagodnik, Michael Branicky

Last modified: 2009-04-09


Clinical tests have shown that the dynamics of a human arm, controlled using Functional Electrical Stimulation (FES), can vary significantly between and during trials. In this paper, we study the application of the actor-critic architecture, with neural networks for the both the actor and the critic, as a controller that can adapt to these changing dynamics of a human arm. Development and tests were done in simulation using a planar arm model and Hill-based muscle dynamics. We begin by training it using a Proportional Derivative (PD) controller as a supervisor. We then make clinically relevant changes to the dynamics of the arm and test the actor-critic's ability to adapt without supervision in a reasonable number of episodes. Finally, we devise methods for achieving both rapid learning and long-term stability.


continuous actor-critic, stability, robustness, reinforcement learning, functional electrical stimulation, artificial neural network, proportional derivative controller, adaptive controller

Full Text: PDF