SmartWheeler: A Robotic Wheelchair Test-Bed for Investigating New Models of Human-Robot Interaction.

Abstract

The goal of the SmartWheeler project is to increase the autonomy and safety of individuals with severe mobility impairments by developing a robotic wheelchair that is adapted to their needs. The project tackles a range of challenging issues, focusing in particular on tasks pertaining to human-robot interaction, and on robust control of the intelligent wheelchair. The platform we have built also serves as a test-bed for validating novel concepts and algorithms for automated decisionmaking onboard socially assistive robots. This paper introduces the wheelchair platform, and outlines technique contributions in four ongoing research areas: adaptive planning in large-scale environments, learning and control under model uncertainty, large-scale dialogue management, and communication protocols for the tactile interface.