Evidential Occupancy Grid Map Augmentation using Deep Learning
This work addresses the need for detailed environment representations in automated vehicles, though it is incremental as it builds on existing evidential mapping techniques with deep learning enhancements.
The paper tackles the problem of sparse and occluded single-view range sensor data for automated vehicles by presenting a deep learning method to augment occupancy grid maps to resemble evidential maps from multiple views, achieving real-time inference with accurate evidential measures as shown in quantitative and qualitative evaluations.
A detailed environment representation is a crucial component of automated vehicles. Using single range sensor scans, data is often too sparse and subject to occlusions. Therefore, we present a method to augment occupancy grid maps from single views to be similar to evidential occupancy maps acquired from different views using Deep Learning. To accomplish this, we estimate motion between subsequent range sensor measurements and create an evidential 3D voxel map in an extensive post-processing step. Within this voxel map, we explicitly model uncertainty using evidence theory and create a 2D projection using combination rules. As input for our neural networks, we use a multi-layer grid map consisting of the three features detections, transmissions and intensity, each for ground and non-ground measurements. Finally, we perform a quantitative and qualitative evaluation which shows that different network architectures accurately infer evidential measures in real-time.