Evidential occupancy grid mapping with stereo-vision

Occupancy grids have shown interesting properties to model the environment for intelligent vehicles perception. In this paper, we present a novel approach to build 2D occupancy grid maps with stereo-vision. Our approach proposes a fitted sensor model based on the disparity space to interpret the stereo-vision information onto an occupancy grid map. The evidential model deals with sensor uncertainties by using Dempster-Shafer theory. Our approach exploits the U-disparity space to model the obstacle information and the V-disparity space to model the road space information. The fusion of these two sources of complementary information results to an enhanced environmental model. In a first experimental data set, results based on real road data and comparisons with Lidar grids show that the proposed evidential sensor model can model efficiently the environment. In a second one, the mapping of a road environment is reported to show the performance of the proposed model with another stereo-vision system.