Trajectory Prediction for Autonomous Driving with Topometric Map
This work addresses the costly and limited applicability of HD maps for autonomous driving, particularly in unstructured environments like rural areas.
The paper tackles the problem of autonomous driving without high-definition maps by proposing an end-to-end transformer network that uses raw LiDAR data and noisy topometric maps to generate precise local trajectories. The method outperforms state-of-the-art multimodal approaches and is robust to map perturbations, as demonstrated on real-world urban and rural driving data.
State-of-the-art autonomous driving systems rely on high definition (HD) maps for localization and navigation. However, building and maintaining HD maps is time-consuming and expensive. Furthermore, the HD maps assume structured environment such as the existence of major road and lanes, which are not present in rural areas. In this work, we propose an end-to-end transformer networks based approach for map-less autonomous driving. The proposed model takes raw LiDAR data and noisy topometric map as input and produces precise local trajectory for navigation. We demonstrate the effectiveness of our method in real-world driving data, including both urban and rural areas. The experimental results show that the proposed method outperforms state-of-the-art multimodal methods and is robust to the perturbations of the topometric map. The code of the proposed method is publicly available at \url{https://github.com/Jiaolong/trajectory-prediction}.