Adaptive collaborative assistance for wheelchair driving via CBR learning

Abstract

This work presents a new approach to shared control driving a robotic wheelchair for persons with disabilities. The proposal is based on weighting the robot and human commands by their respective efficiencies to obtain an emergent command in a reactive way. It was tested with a robotized Meyra wheelchair at Fondazione Santa Lucia (FSL) in Rome with volunteers presenting different disabilities and we observed that the system seemed to help less persons with better cognitive skills. This seemed to be due to disagreement between the users and the machine when they realized that they were being helped. In order to improve that, we added a Case Based Reasoning module to absorb how the user drives to replace the robot navigation algorithm. New tests with the adaptive system showed an increase in efficiency in all cases.