Trajectory prediction is an essential component in autonomous driving, particularly for collision avoidance systems. Considering the inherent uncertainty of the task, numerous studies have utilized generative models to produce multiple plausible future trajectories for each agent. However, most of them suffer from restricted representation ability or unstable training issues. To overcome these limitations, we propose utilizing the diffusion model to generate the distribution of future trajectories. Two cruxes are to be settled to realize such an idea. First, the diversity of intention is intertwined with the uncertain surroundings, making the true distribution hard to parameterize. Second, the diffusion process is time-consuming during the inference phase, rendering it unrealistic to implement in a real-time driving system. We propose an Intention-aware denoising Diffusion Model (IDM), which tackles the above two problems. We decouple the original uncertainty into intention uncertainty and action uncertainty and model them with two dependent diffusion processes. To decrease the inference time, we reduce the variable dimensions in the intention-aware diffusion process and restrict the initial distribution of the action-aware diffusion process, which leads to fewer diffusion steps. To validate our approach, we conduct experiments on the Stanford Drone Dataset (SDD) and ETH/UCY dataset. Our methods achieve state-of-the-art results, with an FDE of 13.83 pixels on the SDD dataset and 0.36 meters on the ETH/UCY dataset. Compared with the original diffusion model, IDM reduces inference time by two-thirds. Interestingly, our experiments further reveal that introducing intention information is beneficial in modeling the diffusion process of fewer steps.

翻译：轨迹预测是自动驾驶中的关键组成部分，尤其对于碰撞避免系统而言。考虑到任务固有的不确定性，大量研究利用生成模型为每个智能体生成多条合理的未来轨迹。然而，大多数方法存在表示能力受限或训练不稳定的问题。为克服这些局限，我们提出利用扩散模型生成未来轨迹的分布。实现这一想法需解决两个关键问题：首先，意图的多样性与不确定的环境交织，使得真实分布难以参数化；其次，扩散过程在推理阶段耗时较长，使其在实时驾驶系统中不切实际。我们提出一种面向意图的去噪扩散模型（IDM），解决了上述两个问题。我们将原始不确定性解耦为意图不确定性和动作不确定性，并通过两个依赖的扩散过程对其进行建模。为减少推理时间，我们降低了面向意图的扩散过程中的变量维度，并限制了面向动作的扩散过程的初始分布，从而减少了扩散步数。为验证我们的方法，我们在斯坦福无人机数据集（SDD）和ETH/UCY数据集上进行了实验。我们的方法取得了最先进的结果，在SDD数据集上的最终位移误差（FDE）为13.83像素，在ETH/UCY数据集上为0.36米。与原始扩散模型相比，IDM将推理时间减少了三分之二。有趣的是，我们的实验进一步揭示，引入意图信息有助于在较少步数的扩散过程中进行建模。