Evidential Occupancy Grid Map Augmentation using Deep Learning

TL;DR

This paper introduces a deep learning method to augment occupancy grid maps with evidential information, improving environment representation for automated vehicles by estimating uncertainty from single sensor views.

Contribution

It presents a novel deep learning approach to generate evidential occupancy maps from single-range sensor scans, incorporating uncertainty modeling and real-time inference.

Findings

Accurately infers evidential measures in real-time

Enhances environment representation with uncertainty information

Demonstrates effectiveness through quantitative and qualitative evaluation

Abstract

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.