LiDAR Lateral Localisation Despite Challenging Occlusion from Traffic
This work addresses localization challenges for autonomous vehicles in urban environments, though it appears incremental as it builds on existing LiDAR systems with a novel inference component.
The paper tackles the problem of robust LiDAR lateral localization under occlusion from traffic by inferring invisible road boundaries with a deep neural network, demonstrating a performance gain over 40 km of driving in Oxford.
This paper presents a system for improving the robustness of LiDAR lateral localisation systems. This is made possible by including detections of road boundaries which are invisible to the sensor (due to occlusion, e.g. traffic) but can be located by our Occluded Road Boundary Inference Deep Neural Network. We show an example application in which fusion of a camera stream is used to initialise the lateral localisation. We demonstrate over four driven forays through central Oxford - totalling 40 km of driving - a gain in performance that inferring of occluded road boundaries brings.