期刊
2022 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2022)
卷 -, 期 -, 页码 4163-4169出版社
IEEE
DOI: 10.1109/ICRA46639.2022.9812266
关键词
-
资金
- Baden-Wurttemberg Stiftung gGmbH
- Bundesministerium fur Bildung und Forschung
This paper presents a novel monocular localization approach that achieves accurate and robust vehicle localization in sparse maps using a sliding-window pose graph and predicted uncertainties. Additionally, the use of differentiable cost maps further improves the accuracy of localization.
Robust localization in dense urban scenarios using a low-cost sensor setup and sparse HD maps is highly relevant for the current advances in autonomous driving, but remains a challenging topic in research. We present a novel monocular localization approach based on a sliding-window pose graph that leverages predicted uncertainties for increased precision and robustness against challenging scenarios and perframe failures. To this end, we propose an efficient multi-task uncertainty-aware perception module, which covers semantic segmentation, as well as bounding box detection, to enable the localization of vehicles in sparse maps, containing only lane borders and traffic lights. Further, we design differentiable cost maps that are directly generated from the estimated uncertainties. This opens up the possibility to minimize the reprojection loss of amorphous map elements in an association-free and uncertainty-aware manner. Extensive evaluation on the Lyft 5 dataset shows that, despite the sparsity of the map, our approach enables robust and accurate 6D localization in challenging urban scenarios using only monocular camera images and vehicle odometry.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据