arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.03581cs.ROcs.CV
收藏

HAD:结合分层扩散与度量解耦RL的端到端驾驶

HAD: Combining Hierarchical Diffusion with Metric-Decoupled RL for End-to-End Driving

Fudan University(复旦大学);NVIDIA(英伟达)

Wenhao Yao, Xinglong Sun, Zhenxin Li, Shiyi Lan, Zi Wang, Jose M. Alvarez, Zuxuan Wu

AI总结:

HAD提出一种端到端规划框架,结合分层扩散策略与度量解耦RL,通过结构保持轨迹扩展生成真实轨迹并提升驾驶目标优化效果,实验表明在NAVSIM和HUGSIM上取得新突破。

摘要:

端到端规划已成为自动驾驶的主导范式,近期模型常采用评分-选择框架从大量候选轨迹中选择,基于扩散的解码方法显示出强大潜力。然而,直接从整个候选空间中选择仍难以优化,扩散中使用的高斯扰动常引入不现实的轨迹,使去噪过程复杂化。此外,训练这些模型时,强化学习(RL)显示出前景,但现有端到端RL方法通常依赖单一耦合奖励,缺乏结构化信号,限制了优化效果。为解决这些挑战,我们提出HAD,一种端到端规划框架,其分层扩散策略将规划分解为粗到细的过程。为提高轨迹生成,我们引入结构保持轨迹扩展,生成真实候选轨迹的同时保持运动学结构。对于策略学习,我们开发了度量解耦策略优化(MDPO),以实现跨多个驾驶目标的结构化RL优化。大量实验表明,HAD在NAVSIM和HUGSIM上取得了新的状态-of-the-art性能,优于现有方法:在NAVSIM上+2.3 EPDMS,在HUGSIM上+4.9 Route Completion。

英文摘要:

End-to-end planning has emerged as a dominant paradigm for autonomous driving, where recent models often adopt a scoring-selection framework to choose trajectories from a large set of candidates, with diffusion-based decoding showing strong promise. However, directly selecting from the entire candidate space remains difficult to optimize, and Gaussian perturbations used in diffusion often introduce unrealistic trajectories that complicate the denoising process. In addition, for training these models, reinforcement learning (RL) has shown promise, but existing end-to-end RL approaches typically rely on a single coupled reward without structured signals, limiting optimization effectiveness. To address these challenges, we propose HAD, an end-to-end planning framework with a Hierarchical Diffusion Policy that decomposes planning into a coarse-to-fine process. To improve trajectory generation, we introduce Structure-Preserved Trajectory Expansion, which produces realistic candidates while maintaining kinematic structure. For policy learning, we develop Metric-Decoupled Policy Optimization (MDPO) to enable structured RL optimization across multiple driving objectives. Extensive experiments show that HAD achieves new state-of-the-art performance on both NAVSIM and HUGSIM, outperforming prior arts by a huge margin: +2.3 EPDMS on NAVSIM and +4.9 Route Completion on HUGSIM.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑