An efficient scan-to-map matching approach for autonomous driving

Accurately localizing the vehicle against a pre-built high precision map is an essential step for the Autonomous Land Vehicle (ALV). This paper proposes an efficient scan-to-map matching approach based on multi-channel lidar. We firstly advocate the usage of both the lidar reflectance map and the height map, as these two maps contain complementary information. Then, borrowing ideas from image optical flow literature, we formulate the scan-to-map matching problem as an optical flow computation problem, and propose an efficient gradient descent approach to solve it. Finally, the proposed approach is integrated into a filtering framework for realtime online localization. Experiments on real-world dataset have demonstrated the validity of our approach. The dataset is also made publicly available for future research.