GuideFlow: Constraint-Guided Flow Matching for Planning in End-to-End Autonomous Driving

TL;DR

GuideFlow introduces a constraint-guided flow matching framework for autonomous driving planning, effectively mitigating mode collapse, enforcing safety constraints, and enabling trajectory style control, validated by state-of-the-art results on multiple benchmarks.

Contribution

It proposes a novel flow matching approach with explicit constraint enforcement and integration with Energy-Based Models for robust, diverse, and controllable autonomous driving planning.

Findings

Achieved state-of-the-art performance on NavSim with an EPDMS score of 43.0.

Effectively mitigated trajectory mode collapse and incorporated safety constraints.

Enabled precise control of driving aggressiveness during trajectory generation.

Abstract

Driving planning is a critical component of end-to-end (E2E) autonomous driving. However, prevailing Imitative E2E Planners often suffer from multimodal trajectory mode collapse, failing to produce diverse trajectory proposals. Meanwhile, Generative E2E Planners struggle to incorporate crucial safety and physical constraints directly into the generative process, necessitating an additional optimization stage to refine their outputs. In this paper, we propose \textit{\textbf{GuideFlow}}, a novel planning framework that leverages Constrained Flow Matching. Concretely, \textit{\textbf{GuideFlow}} explicitly models the flow matching process, which inherently mitigates mode collapse and allows for flexible guidance from various conditioning signals. Our core contribution lies in directly enforcing explicit constraints within the flow matching generation process, rather than relying on implicit constraint encoding. Crucially, \textit{\textbf{GuideFlow}} unifies the training of the flow matching with the Energy-Based Model (EBM) to enhance the model's autonomous optimization capability to robustly satisfy physical constraints. Secondly, \textit{\textbf{GuideFlow}} parameterizes driving aggressiveness as a control signal during generation, enabling precise manipulation of trajectory style. Extensive evaluations on major driving benchmarks (Bench2Drive, NuScenes, NavSim and ADV-NuScenes) validate the effectiveness of \textit{\textbf{GuideFlow}}. Notably, on the NavSim test hard split (Navhard), \textit{\textbf{GuideFlow}} achieved SOTA with an EPDMS score of 43.0. The code will be in https://github.com/liulin815/GuideFlow.