Beyond Imitation: Constraint-Aware Trajectory Generation with Flow Matching For End-to-End Autonomous Driving

2025-10-30

AI Summary

End-to-end autonomous driving planning faces two key challenges: (1) imitation learning often suffers from mode collapse, limiting trajectory diversity; and (2) existing generative models lack explicit integration of safety and kinematic constraints during sampling, necessitating post-hoc correction. To address these, we propose Constraint-Aware Trajectory Generation (CATG), the first framework to embed explicit safety constraints—such as collision avoidance and lane keeping—as well as vehicle kinematic models directly into the flow matching process. CATG further introduces tunable driving aggressiveness as a conditional control signal, enabling controllable, regulation-compliant, and diverse trajectory generation. By leveraging multi-condition guidance and constraint-augmented flow matching, CATG achieves second place (EPDMS 51.31) and the Innovation Award in the NavSim v2 Challenge.

Technology Category

• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Multiagent Systems: Multiagent Planning

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

Planning is a critical component of end-to-end autonomous driving. However, prevailing imitation learning methods often suffer from mode collapse, failing to produce diverse trajectory hypotheses. Meanwhile, existing generative approaches struggle to incorporate crucial safety and physical constraints directly into the generative process, necessitating an additional optimization stage to refine their outputs. To address these limitations, we propose CATG, a novel planning framework that leverages Constrained Flow Matching. Concretely, CATG explicitly models the flow matching process, which inherently mitigates mode collapse and allows for flexible guidance from various conditioning signals. Our primary contribution is the novel imposition of explicit constraints directly within the flow matching process, ensuring that the generated trajectories adhere to vital safety and kinematic rules. Secondly, CATG parameterizes driving aggressiveness as a control signal during generation, enabling precise manipulation of trajectory style. Notably, on the NavSim v2 challenge, CATG achieved 2nd place with an EPDMS score of 51.31 and was honored with the Innovation Award.

Problem

• Overcoming mode collapse in imitation learning for autonomous driving
• Integrating safety constraints directly into trajectory generation
• Enabling controlled trajectory style through driving aggressiveness parameterization

Innovation

• Leverages Constrained Flow Matching for trajectory generation
• Imposes explicit constraints within flow matching process
• Parameterizes driving aggressiveness as control signal