VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning
This work addresses uncertainty in autonomous driving planning for improved safety and performance, representing a strong specific gain in the domain.
The authors tackled the challenge of uncertainty in autonomous driving planning by proposing VADv2, an end-to-end model based on probabilistic planning that uses only camera sensors, achieving state-of-the-art closed-loop performance on the CARLA Town05 benchmark and significantly outperforming existing methods.
Learning a human-like driving policy from large-scale driving demonstrations is promising, but the uncertainty and non-deterministic nature of planning make it challenging. In this work, to cope with the uncertainty problem, we propose VADv2, an end-to-end driving model based on probabilistic planning. VADv2 takes multi-view image sequences as input in a streaming manner, transforms sensor data into environmental token embeddings, outputs the probabilistic distribution of action, and samples one action to control the vehicle. Only with camera sensors, VADv2 achieves state-of-the-art closed-loop performance on the CARLA Town05 benchmark, significantly outperforming all existing methods. It runs stably in a fully end-to-end manner, even without the rule-based wrapper. Closed-loop demos are presented at https://hgao-cv.github.io/VADv2.