Path Planning Based on Traversability Evaluation from Occupancy-Elevation Grid Maps

Abstract

Path planning in Robotics is a fundamental point towards autonomy, and it refers to the capability to estimate safe and collision free paths from a point of interest to another. This paper introduces a path planning approach for autonomous navigation based on Occupancy-Elevation Grid (OEG) maps. OEG maps provide probabilistic information about the existence and the height of obstacles in an environment. Thus, in this proposed approach, probabilistic information about the terrain are taken from a OEG map in order to an autonomous vehicle compute a feasible path. In addition, the vehicle must consider its physical characteristics and navigation capability to proceed with the path planning process, verifying if it is possible to traverse specific places in its environment. Experiments carried out with real data demonstrate that the proposed approach yields useful results for vehicles autonomous navigation.