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

2025-11-23

AI Summary

In end-to-end autonomous driving planning, imitation-based methods suffer from multimodal trajectory collapse, while generative approaches struggle to incorporate safety and physical constraints. This paper proposes a constraint-guided flow matching framework: it is the first to explicitly integrate safety and physical constraints directly into the flow matching process; jointly trains an energy-based model (EBM) to enhance autonomous optimization; and introduces driving aggressiveness as a controllable conditional signal to enable diverse, regulation-compliant, and style-tunable trajectory generation. The method achieves state-of-the-art performance across multiple benchmarks—including Bench2Drive, nuScenes, NavSim, and ADV-nuScenes—attaining an EPDMS score of 43.0 on the challenging Navhard test set. Key contributions include: (1) joint modeling of constraints and flow matching, (2) EBM-augmented collaborative optimization, and (3) a controllable trajectory generation mechanism.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Agentic search
• Security and Privacy: Large-scale security measurements

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 extit{ extbf{GuideFlow}}, a novel planning framework that leverages Constrained Flow Matching. Concretely, extit{ extbf{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, extit{ extbf{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, extit{ extbf{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 extit{ extbf{GuideFlow}}. Notably, on the NavSim test hard split (Navhard), extit{ extbf{GuideFlow}} achieved SOTA with an EPDMS score of 43.0. The code will be released.

Problem

• Addresses multimodal trajectory mode collapse in autonomous driving planners
• Incorporates safety and physical constraints directly into trajectory generation
• Enables precise control over driving aggressiveness during trajectory planning

Innovation

• Uses Constrained Flow Matching for trajectory planning
• Integrates Energy-Based Model training for constraint optimization
• Parameterizes driving aggressiveness as controllable generation signal