arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.03112cs.RO
收藏

通过扩散生成场景自适应候选集的统一候选集用于端到端自动驾驶

A Unified Candidate Set with Scene-Adaptive Refinement via Diffusion for End-to-End Autonomous Driving

School of Automotive Studies, Tongji University, Shanghai, China(同济大学汽车学院)

Zhengfei Wu, Shuaixi Pan, Shuohan Chen, Shuo Yang, Yanjun Huang

AI总结:

CdDrive通过扩散生成场景自适应候选集,提升端到端自动驾驶的候选集设计与轨迹平滑性

摘要:

端到端自动驾驶正越来越多地采用多模态规划范式,生成多个轨迹候选并选择最终计划,使候选集设计至关重要。固定轨迹词汇表在常规驾驶中提供稳定的覆盖,但在复杂交互中常遗漏最优解,而场景自适应细化在简单场景中可能因不必要的扰动已强词汇表轨迹而产生过纠正。我们提出了CdDrive,它保留原始词汇候选并用词汇条件扩散去噪生成附加的场景自适应候选。两种候选类型通过共享的选择模块联合评分,使在常规和高度交互场景中都能实现可靠性能。我们进一步引入HATNA(视界感知轨迹噪声适配器)通过时间平滑和视界感知噪声调节来提高扩散候选的平滑性和几何连续性。在NAVSIM v1和NAVSIM v2上的实验显示了领先性能,消融实验验证了每个组件的贡献。代码:https://github.com/WWW-TJ/CdDrive。

英文摘要:

End-to-end autonomous driving is increasingly adopting a multimodal planning paradigm that generates multiple trajectory candidates and selects the final plan, making candidate-set design critical. A fixed trajectory vocabulary provides stable coverage in routine driving but often misses optimal solutions in complex interactions, while scene-adaptive refinement can cause over-correction in simple scenarios by unnecessarily perturbing already strong vocabulary trajectories.We propose CdDrive, which preserves the original vocabulary candidates and augments them with scene-adaptive candidates generated by vocabulary-conditioned diffusion denoising. Both candidate types are jointly scored by a shared selection module, enabling reliable performance across routine and highly interactive scenarios. We further introduce HATNA (Horizon-Aware Trajectory Noise Adapter) to improve the smoothness and geometric continuity of diffusion candidates via temporal smoothing and horizon-aware noise modulation. Experiments on NAVSIM v1 and NAVSIM v2 demonstrate leading performance, and ablations verify the contribution of each component. Code: https://github.com/WWW-TJ/CdDrive.

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。

↑