cs.RONov 17, 2026

FIRE-Drive: Feasibility-Informed Risk Evaluation for End-to-End Diffusion Planning

Authors: Qifeng Xie, Kai-Yuan Feng, Wenkang Wan, Yue Wu, Maoguo Gong, Kai Sheng

Organizations: School of Electronic Engineering, Xidian University · Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University · Faculty of Infor-X, Xidian University · College of Artificial Intelligence, Inner Mongolia Normal University

Abstract

Diffusion-based end-to-end autonomous driving models have shown strong potential in generating multimodal planning trajectories. However, their performance still depends heavily on trajectory initialization, mode evaluation, and supervision quality. Weakly constrained noisy initialization may introduce infeasible proposals and increase the burden of denoising. Moreover, selecting the optimal mode remains challenging when candidate trajectories are geometrically similar but differ in safety, interaction risk, and progress. To address these issues, we propose FIRE-Drive, a feasibility-informed risk evaluation framework for end-to-end autonomous driving. FIRE-Drive improves diffusion-based planning through dynamic feasible anchor initialization, candidate-specific bird's-eye-view risk evidence, and compact high-quality candidate supervision with lightweight refinement. This design aligns the initial support, risk-aware scoring, and multimodal supervision of trajectory modes under a unified planning objective. It enables the diffusion decoder to focus on refining plausible trajectories while the scorer distinguishes modes using local risk evidence. Experiments on NAVSIM v1 show that FIRE-Drive achieves a Predictive Driver Model Score of 91.5 with a ResNet34 backbone. Additional closed-loop evaluation on 220 Bench2Drive routes yields a Driving Score of 71.43 and a Success Rate of 42.73%. Component ablations and a scorer comparison under matched candidate inputs support the contributions of feasible initialization, auxiliary supervision, and risk-informed selection. Our code is available at https://github.com/Latte00/FIRE-drive.

Figures & tables

Explore similar work

CardsList
  1. FeaXDrive: Feasibility-aware Trajectory-Centric Diffusion Planning for End-to-End Autonomous Driving

    Apr 14, 2026Baoyun Wang, Zhuoren Li, Ran Yu +6Diffusion-Based PlanningMotion Planning

  2. DriveSafer: End-to-End Autonomous Driving with Safety Guidance

    May 16, 2026Shounak Sural, Raj RajkumarEnd-to-End Autonomous DrivingDiffusion-Based Planning

  3. Data-Driven Risk Fields for Safer End-to-End Autonomous Driving

    Sep 9, 2026Yuanxin Tian, Zhiyuan Liu, Jinhao Li +9End-to-End Autonomous DrivingSafe Motion Planning