3D LiDAR Mapping in Dynamic Environments Using a 4D Implicit Neural Representation

arXiv:2405.03388v1 Announce Type: new
Abstract: Building accurate maps is a key building block to enable reliable localization, planning, and navigation of autonomous vehicles. We propose a novel approach for building accurate maps of dynamic environments utilizing a sequence of LiDAR scans. To this end, we propose encoding the 4D scene into a novel spatio-temporal implicit neural map representation by fitting a time-dependent truncated signed distance function to each point. Using our representation, we extract the static map by filtering the …

arxiv cs.cv cs.ro dynamic environments lidar mapping representation type