GoalFlow：面向端到端自动驾驶的多模态轨迹生成之目标驱动流匹配

GoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous Driving

March 7, 2025

作者: Zebin Xing, Xingyu Zhang, Yang Hu, Bo Jiang, Tong He, Qian Zhang, Xiaoxiao Long, Wei Yin

cs.AI

摘要

我们提出了GoalFlow，一种端到端的自动驾驶方法，用于生成高质量的多模态轨迹。在自动驾驶场景中，单一合适的轨迹极为罕见。近期方法日益关注于建模多模态轨迹分布，然而，它们因轨迹选择复杂度高、轨迹间差异过大以及引导信息与场景信息不一致而面临轨迹质量下降的问题。为解决这些问题，我们引入了GoalFlow，这一新颖方法有效约束生成过程，以产出高质量的多模态轨迹。针对基于扩散方法固有的轨迹发散问题，GoalFlow通过引入目标点来约束生成轨迹。GoalFlow建立了一种新颖的评分机制，依据场景信息从候选点中选取最合适的目标点。此外，GoalFlow采用高效的生成方法——流匹配（Flow Matching）来生成多模态轨迹，并结合精炼的评分机制从候选轨迹中选出最优解。我们的实验结果在NavsimDauner2024_navsim上得到验证，表明GoalFlow实现了业界领先的性能，为自动驾驶提供了稳健的多模态轨迹。GoalFlow的PDMS达到了90.3，显著超越其他方法。与基于扩散策略的其他方法相比，我们的方法仅需一次去噪步骤即可获得卓越性能。代码已发布于https://github.com/YvanYin/GoalFlow。

English

We propose GoalFlow, an end-to-end autonomous driving method for generating high-quality multimodal trajectories. In autonomous driving scenarios, there is rarely a single suitable trajectory. Recent methods have increasingly focused on modeling multimodal trajectory distributions. However, they suffer from trajectory selection complexity and reduced trajectory quality due to high trajectory divergence and inconsistencies between guidance and scene information. To address these issues, we introduce GoalFlow, a novel method that effectively constrains the generative process to produce high-quality, multimodal trajectories. To resolve the trajectory divergence problem inherent in diffusion-based methods, GoalFlow constrains the generated trajectories by introducing a goal point. GoalFlow establishes a novel scoring mechanism that selects the most appropriate goal point from the candidate points based on scene information. Furthermore, GoalFlow employs an efficient generative method, Flow Matching, to generate multimodal trajectories, and incorporates a refined scoring mechanism to select the optimal trajectory from the candidates. Our experimental results, validated on the NavsimDauner2024_navsim, demonstrate that GoalFlow achieves state-of-the-art performance, delivering robust multimodal trajectories for autonomous driving. GoalFlow achieved PDMS of 90.3, significantly surpassing other methods. Compared with other diffusion-policy-based methods, our approach requires only a single denoising step to obtain excellent performance. The code is available at https://github.com/YvanYin/GoalFlow.