Shared Control Design Methodologies of an Electric Wheelchair for Individuals with Severe Disabilities using Reinforcement Learning

Abstract

Individuals with severe disabilities typically suffer from lack of muscle power and deformation of their hands. This significantly affects their ability to operate an Electric Wheelchair (EW) especially when using joystick controllers because one operation of a joystick affects both the straight and turning motions of an EW. Thus, individuals with severe disabilities typically exhibit difficulties in operating an EW, especially in the cases that require fine steering capabilities. In contrast to autonomous driving, the study proposes a novel shared control method using reinforcement learning considering utilizing users' residual physical functions. With the use of online learning, the shared controller provides proper assistance based on the driving environments and each user's input characteristics. The effectiveness and the characteristics of the novel shared controller are discussed via simulations.