arXiv 2512.007232025-11-30cs.CVcs.RO

TrajDiff: 无需感知标注的端到端自动驾驶

TrajDiff: End-to-end Autonomous Driving without Perception Annotation

SKL-IOTSC, CIS, University of Macau（澳门大学智能物联网与交通系统研究中心，计算机学院）；University of Science and Technology of China（中国科学技术大学）；Mach Drive

Xingtai Gui, Jianbo Zhao, Wencheng Han, Jikai Wang, Jiahao Gong, Feiyang Tan, Cheng-zhong Xu, Jianbing Shen

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

TrajDiff通过无需感知标注的轨迹导向鸟瞰图扩散框架，实现了端到端自动驾驶，达到领先性能。

摘要：

端到端自动驾驶系统直接从原始传感器输入生成驾驶策略。尽管这些系统能够提取有效的环境特征用于规划，但依赖辅助感知任务，开发无需感知标注的规划范式变得越来越关键，因为手动感知标注成本高昂。在本文中，我们提出了TrajDiff，一种以轨迹为导向的鸟瞰图条件扩散框架，建立了一种完全无需感知标注的生成方法用于端到端自动驾驶。TrajDiff仅需要原始传感器输入和未来轨迹，构建高斯鸟瞰图热图目标，这些目标本质上捕捉了驾驶模式。我们设计了一个简单而有效的轨迹导向的鸟瞰图编码器，提取TrajBEV特征而无需感知监督。此外，我们引入了轨迹导向的鸟瞰图扩散变压器（TB-DiT），它利用自身状态信息和预测的TrajBEV特征，直接生成多样化且合理的轨迹，消除了对手工制作运动先验的依赖。除了架构创新外，TrajDiff还使在无标注设置下的数据扩展收益得以探索。在NAVSIM基准测试中，TrajDiff达到了87.5 PDMS，成为所有无标注方法中性能最佳的。在数据扩展后，其进一步提升到88.5 PDMS，与先进的感知方法相当。我们的代码和模型将公开发布。

英文摘要：

End-to-end autonomous driving systems directly generate driving policies from raw sensor inputs. While these systems can extract effective environmental features for planning, relying on auxiliary perception tasks, developing perception annotation-free planning paradigms has become increasingly critical due to the high cost of manual perception annotation. In this work, we propose TrajDiff, a Trajectory-oriented BEV Conditioned Diffusion framework that establishes a fully perception annotation-free generative method for end-to-end autonomous driving. TrajDiff requires only raw sensor inputs and future trajectory, constructing Gaussian BEV heatmap targets that inherently capture driving modalities. We design a simple yet effective trajectory-oriented BEV encoder to extract the TrajBEV feature without perceptual supervision. Furthermore, we introduce Trajectory-oriented BEV Diffusion Transformer (TB-DiT), which leverages ego-state information and the predicted TrajBEV features to directly generate diverse yet plausible trajectories, eliminating the need for handcrafted motion priors. Beyond architectural innovations, TrajDiff enables exploration of data scaling benefits in the annotation-free setting. Evaluated on the NAVSIM benchmark, TrajDiff achieves 87.5 PDMS, establishing state-of-the-art performance among all annotation-free methods. With data scaling, it further improves to 88.5 PDMS, which is comparable to advanced perception-based approaches. Our code and model will be made publicly available.

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。