Improving Map Re-localization with Deep 'Movable' Objects Segmentation on 3D LiDAR Point Clouds
This addresses the lack of robustness in localization algorithms against dynamic obstacles for autonomous vehicles, though it is incremental as it builds on existing mapping methods with a new segmentation approach.
The paper tackles the problem of map re-localization in autonomous vehicles by segmenting movable objects from 3D LiDAR point clouds to create longer-lasting maps, resulting in reduced trajectory errors by an average of 35.1% compared to non-filtered maps and 47.9% compared to standalone session maps.
Localization and Mapping is an essential component to enable Autonomous Vehicles navigation, and requires an accuracy exceeding that of commercial GPS-based systems. Current odometry and mapping algorithms are able to provide this accurate information. However, the lack of robustness of these algorithms against dynamic obstacles and environmental changes, even for short time periods, forces the generation of new maps on every session without taking advantage of previously obtained ones. In this paper we propose the use of a deep learning architecture to segment movable objects from 3D LiDAR point clouds in order to obtain longer-lasting 3D maps. This will in turn allow for better, faster and more accurate re-localization and trajectoy estimation on subsequent days. We show the effectiveness of our approach in a very dynamic and cluttered scenario, a supermarket parking lot. For that, we record several sequences on different days and compare localization errors with and without our movable objects segmentation method. Results show that we are able to accurately re-locate over a filtered map, consistently reducing trajectory errors between an average of 35.1% with respect to a non-filtered map version and of 47.9% with respect to a standalone map created on the current session.