Human-Robotic Collaborative Intelligent Control for Reaching Performance

Abstract

In most human-robot interfaces, the user completely controls the robot that operates as a passive tool without adaptation capabilities. However, a synergetic human-robot interface where both agents collaborate could improve the user's performance while reducing the cognitive and physical workload. Specifically, when considering this framework applied to rehabilitation, we examined a shared collaborative control between a human user and an adaptive biologically inspired neurocontroller in order to perform reaching movements with a simulated prosthetic arm. When this neurocontroller was enabled, it progressively learned from the user to control the prosthetic arm, increasing its role in the shared performance and facilitating the user's reaching movements. This resulted in the user's performance enhancement and in a reduction of his/her cognitive workload. The long term goal of this work is to contribute to the development of the next generation of intelligent human-robotic interfaces for rehabilitation.