I am Robot: Neuromuscular Reinforcement Learning to Actuate Human Limbs through Functional Electrical Stimulation
This addresses the challenge of controlling non-stationary human muscles for individuals with movement disorders or paralysis, representing an incremental advance in FES control methods.
The paper tackled the problem of restoring motor abilities to human limbs via Functional Electrical Stimulation (FES) by developing a Deep Reinforcement Learning controller that learns to manipulate human muscles, compensating for fatigue and achieving tasks in simulations and human experiments.
Human movement disorders or paralysis lead to the loss of control of muscle activation and thus motor control. Functional Electrical Stimulation (FES) is an established and safe technique for contracting muscles by stimulating the skin above a muscle to induce its contraction. However, an open challenge remains on how to restore motor abilities to human limbs through FES, as the problem of controlling the stimulation is unclear. We are taking a robotics perspective on this problem, by developing robot learning algorithms that control the ultimate humanoid robot, the human body, through electrical muscle stimulation. Human muscles are not trivial to control as actuators due to their force production being non-stationary as a result of fatigue and other internal state changes, in contrast to robot actuators which are well-understood and stationary over broad operation ranges. We present our Deep Reinforcement Learning approach to the control of human muscles with FES, using a recurrent neural network for dynamic state representation, to overcome the unobserved elements of the behaviour of human muscles under external stimulation. We demonstrate our technique both in neuromuscular simulations but also experimentally on a human. Our results show that our controller can learn to manipulate human muscles, applying appropriate levels of stimulation to achieve the given tasks while compensating for advancing muscle fatigue which arises throughout the tasks. Additionally, our technique can learn quickly enough to be implemented in real-world human-in-the-loop settings.