UncAD: Towards Safe End-to-end Autonomous Driving via Online Map Uncertainty
This work addresses safety issues in autonomous driving systems by reducing collisions, though it is incremental as it builds on existing end-to-end methods.
The paper tackles the problem of unsafe planning in end-to-end autonomous driving due to deterministic online map modeling, proposing UncAD to incorporate online map uncertainty into perception, prediction, and planning. Experiments on nuScenes show that integrating UncAD reduces collision rates by up to 26% and drivable area conflict rates by up to 42% with only a 1.9% parameter increase.
End-to-end autonomous driving aims to produce planning trajectories from raw sensors directly. Currently, most approaches integrate perception, prediction, and planning modules into a fully differentiable network, promising great scalability. However, these methods typically rely on deterministic modeling of online maps in the perception module for guiding or constraining vehicle planning, which may incorporate erroneous perception information and further compromise planning safety. To address this issue, we delve into the importance of online map uncertainty for enhancing autonomous driving safety and propose a novel paradigm named UncAD. Specifically, UncAD first estimates the uncertainty of the online map in the perception module. It then leverages the uncertainty to guide motion prediction and planning modules to produce multi-modal trajectories. Finally, to achieve safer autonomous driving, UncAD proposes an uncertainty-collision-aware planning selection strategy according to the online map uncertainty to evaluate and select the best trajectory. In this study, we incorporate UncAD into various state-of-the-art (SOTA) end-to-end methods. Experiments on the nuScenes dataset show that integrating UncAD, with only a 1.9% increase in parameters, can reduce collision rates by up to 26% and drivable area conflict rate by up to 42%. Codes, pre-trained models, and demo videos can be accessed at https://github.com/pengxuanyang/UncAD.