Trajectory Prediction for Autonomous Driving with Topometric Map

TL;DR

This paper introduces an end-to-end transformer-based approach for trajectory prediction in autonomous driving that does not rely on high-definition maps, using raw LiDAR data and noisy topometric maps, effective in urban and rural environments.

Contribution

The work presents a novel transformer network model for map-less autonomous driving, capable of handling noisy topometric maps and outperforming existing multimodal methods.

Findings

Outperforms state-of-the-art multimodal methods

Robust to topometric map perturbations

Effective in both urban and rural driving scenarios

Abstract

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}.