Recently, the diffusion model has emerged as a powerful generative technique for robotic policy learning, capable of modeling multi-mode action distributions. Leveraging its capability for end-to-end autonomous driving is a promising direction. However, the numerous denoising steps in the robotic diffusion policy and the more dynamic, open-world nature of traffic scenes pose substantial challenges for generating diverse driving actions at a real-time speed. To address these challenges, we propose a novel truncated diffusion policy that incorporates prior multi-mode anchors and truncates the diffusion schedule, enabling the model to learn denoising from anchored Gaussian distribution to the multi-mode driving action distribution. Additionally, we design an efficient cascade diffusion decoder for enhanced interaction with conditional scene context. The proposed model, DiffusionDrive, demonstrates 10$\times$ reduction in denoising steps compared to vanilla diffusion policy, delivering superior diversity and quality in just 2 steps. On the planning-oriented NAVSIM dataset, with the aligned ResNet-34 backbone, DiffusionDrive achieves 88.1 PDMS without bells and whistles, setting a new record, while running at a real-time speed of 45 FPS on an NVIDIA 4090. Qualitative results on challenging scenarios further confirm that DiffusionDrive can robustly generate diverse plausible driving actions. Code and model will be available at https://github.com/hustvl/DiffusionDrive.

翻译：近年来，扩散模型已成为机器人策略学习中强大的生成技术，能够建模多模态动作分布。利用其能力实现端到端自动驾驶是一个前景广阔的方向。然而，机器人扩散策略中大量的去噪步骤以及交通场景更具动态性、开放性的特点，对实时生成多样化驾驶动作构成了重大挑战。为解决这些挑战，我们提出了一种新颖的截断扩散策略，该策略融合了先验多模态锚点并截断扩散调度，使模型能够学习从锚定高斯分布到多模态驾驶动作分布的去噪过程。此外，我们设计了一种高效的级联扩散解码器，以增强与条件场景上下文的交互。所提出的模型DiffusionDrive相比原始扩散策略实现了10倍的去噪步骤缩减，仅需2步即可提供卓越的多样性和质量。在面向规划的NAVSIM数据集上，采用对齐的ResNet-34骨干网络，DiffusionDrive在未使用额外技巧的情况下实现了88.1的PDMS分数，创造了新纪录，同时在NVIDIA 4090上以45 FPS的实时速度运行。在挑战性场景下的定性结果进一步证实，DiffusionDrive能够稳健地生成多样化的合理驾驶动作。代码和模型将在https://github.com/hustvl/DiffusionDrive 发布。