A Laserscanner-Vision Fusion System Implemented on the TerraMax Autonomous Vehicle

This paper presents a sensor fusion model developed for the 2005 Grand Challenge competition, an autonomous ground vehicle race across the Mojave desert organized by DARPA. The two sensors used in this work are a stereo vision camera pair and an ALASCA laserscanner. An algorithm to filter laserscanner's raw scan data and to remove ground reflections is also presented. Several tests were made to prove the reliability of this method, that has proved to be useful to extract the information required by the race. Fusion was performed both at a low and medium level: terrain slope, detected with stereo vision, was used to correct pitch information of laserscanner raw data. Object segmentation is applied on a bird view bitmap where each pixel represents a square area of the world in front of the vehicle; this bitmap is obtained from the fusion of the ones generated by each sensor