High-precision multi-layer visual and semantic map for autonomous driving

摘要

Roughly described, a three-dimensional, multi-layer map is built employing sensory data gathering and analysis. The sensory data are gathered from multiple operational cameras and one or more auxiliary sensors. The multi-layer maps are stored in a map stored to be distributed to one or more autonomous vehicles and robots in the future. The techniques herein are described with reference to specific example implementations to implement improvements in navigation in autonomous vehicles and robots.