Empirical framework for autonomous wheelchair systems in human-shared environments

Autonomous robotic wheelchairs are normally used in human-shared environments and hence they need to move in a safe and comfortable way. Here, we propose a framework that enables such motions in real indoor environments. Initially human regions are detected and tracked from head cues information. Next, the tracking attributes is interpreted for modeling human´s comfort zone (CZ) based on human interaction rules rooted from Proxemics concept. Finally, the wheelchair´s trajectory is generated by respecting the CZ and simultaneously avoiding in place obstacle. Experimental results demonstrate the feasibility of the proposed framework.