Freespace estimation in an autonomous wheelchair using a stereoscopic camera system

Abstract

This paper is concerned with the estimation of the height and width of freespace based on a Bayesian Recursive (BR) algorithm for an autonomous wheelchair using a stereoscopic camera system for disabled people. A 2D distance map for the purpose of freespace estimation is converted from a 3D point map using geometric projection and computation. The comparison of this 2D map to a 2D map obtained from Laser is carried out. Moreover, freespaces in the 2D map are estimated using a BR algorithm based on uncertainty information and control data. Given the average probability, a possible movement decision is then made for the mobile wheelchair. Experimental results obtained in an indoor environment prove the effectiveness of this estimation algorithm.