Vectorized maps forecast beyond vehicle view for safer driving
Generation of Vectorized Maps Beyond Vehicle View
RoboticsArtificial IntelligenceMachine Learning
Summary
HD maps help self-driving cars navigate safely, but they are expensive and slow to update. The authors look at creating map sections beyond what a car's sensors can currently see by predicting likely road layouts ahead. They created a new method called BeyondFormer and built a dataset to test it. The results show it's possible to predict map extensions confidently, which can improve safety and planning for autonomous vehicles. They also discuss current challenges and directions for future work.
What this means in practice
- •For autonomous vehicle engineers: Extend vehicle sensor maps beyond line of sight to improve driving route planning safety.
- •For urban traffic management teams: Use predicted map continuations to anticipate road layout changes and manage traffic flows more effectively.
Authors
Clara Gomez, Alberto Jaenal, Antonio Artuñedo, Jorge Godoy, Jorge Villagra
Abstract
Autonomous driving relies on High Definition (HD) maps for safe navigation. Traditional HD maps construction is costly in hardware, data and human resources, which together with its update limitations hinders scalability. Recent works have proposed online alternatives for HD vectorized mapping from onboard sensors. However, sensor field of view is limited, and the range of the reconstructed maps ahead of the vehicle is insufficient for safe planning. This paper aims to address this limitation by proposing the novel beyond-view vectorized map generation problem: given vectorized maps of the area sensed by the vehicle (in-view), to generate plausible map continuations. To experimentally assess its feasibility, we propose BeyondFormer, which, to the best of out knowledge, is the first work designed towards beyond-view map generation. Given the novelty of the problem, we generate the first dataset specifically designed for it and evaluate the proposed approach. The results demonstrate consistent performance across diverse scenarios, establishing learning-based methods as a promising direction for map forecasting in autonomous driving. Beyond demonstrating the feasibility of the task, we provide an extensive discussion of the method's limitations and identify key future research directions for scaling it to more complex driving conditions. Code is available at https://git-autopia.car.upm-csic.es/beyondformer.