Occupancy grids generation based on Geometric-Featured Voxel maps

Abstract : Navigability assessment is useful for planning obstacles free trajectories in autonomous navigation tasks in 3D environments. Based on Geometric-Featured Voxel (GFV) maps developed in previous works, this paper proposes a method for 2D occupancy grid generation which is efficient for local navigation in natural environments. Built from a point cloud, a GFV map consists of voxels that are classified as tubular, planar, or scatter depending on the local spatial distribution of their inner points. Besides, each voxel is labelled as ground or non-ground considering slopes and rough surfaces found in unstructured scenarios. The proposed 2D occupancy grid represents accessible areas by considering the attributes and the height of each voxel over the ground level in relation to vehicle dimensions. The paper presents experimental results with 3D laser scans in natural environments.