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

In this paper, we propose an end-to-end autonomous driving method focused on generating high-quality multimodal trajectories. In autonomous driving scenarios, there is rarely a single suitable trajectory; multimodal trajectory generation aims to provide multiple trajectory candidates, enhancing the system's reliability and human-computer interaction. Although recent works have shown success, 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. To tackle the issue of information inconsistency, 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 Navsim, demonstrate that GoalFlow achieves state-of-the-art performance, delivering robust multimodal trajectories for autonomous driving. Compared to the state-of-the-art methods, which scored 84.0, our model achieves an improvement of 5 points, reaching a score of 89.4. Moreover, our method achieves excellent performance with just a single inference step, achieving a score of 88.9, resulting in an inference speedup of up to 16$\times$.