VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning

By Shaoyu Chen, Bo Jiang, Hao Gao, Bencheng Liao, Qing Xu, Qian Zhang, Chang Huang, Wenyu Liu, Xinggang Wang. arXiv.org, 2024

298 citations recorded by the source corpus.

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. Existing learning-based planning methods follow a deterministic paradigm to directly regress the action, failing to cope with the uncertainty problem. In this work, we propose a probabilistic planning model for end-to-end autonomous driving, termed VADv2. We resort to a probabilistic field function to model the mapping from the action space to the probabilistic distribution. Since the planning action space is a high-dimensional continuous spatiotemporal space and hard to tackle, we first discretize the planning action space to a large planning vocabulary and then tokenize the planning vocabulary into planning tokens. Planning tokens interact with scene tokens and output the probabilistic distribution of action. Mass driving demonstrations are leveraged to supervise the distribution. VADv2 achieves state-of-the-art closed-loop performance on the CARLA Town05 benchmark, significantly outperforming existing methods, and also leads the recent Bench2Drive benchmark. We further provide comprehensive evaluations on NAVSIM and a large-scale 3DGS-based benchmark, demonstrating its effectiveness in real-world applications. Code is available at https://github.com/hustvl/VAD.

View Paper: https://www.semanticscholar.org/paper/f54c02f651b2568b00143c1fad2942860f353324

Citations in the corpus

• DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving (2024, unknown): “The training objective combines trajectory reconstruction and classification: [4] C & L ResNet-34 [13] 8192 97.2 89.1 91.6 100 76.0 80.9 Hydra-MDP-V 8192 [25] C & L ResNet-34 [13] 8192 97.9 91.7 92.9 100 77.6 83.0 Hydra-MDP-V 8192 -W-EP [25] C & L ResNet-34 [13] 8192 where λ balances the simple L1…”
• End-to-End Autonomous Driving: Challenges and Frontiers (2023, unknown): “In contrast, industries with the resources to deploy fleets of driverless vehicles could rely on real-world evaluation to benchmark improvements in their algorithms.”
• NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking (2024, unknown): “…from multi-billion parameter vision language models [45, 33, 53, 58] to more efficient and recently overlooked approaches based on trajectory sampling and scoring [40, 20, 10], demonstrating the remarkable ability of the broader community to advance AV research when provided with the right tools.”