cs.RONov 15, 2026

SAFER: Navigating the Exploration-Exploitation Dilemma in World-Model-Based Planning for Autonomous Driving

Authors: Yansong Qu, Zilin Huang, Zihao Sheng, Sikai Chen, Samuel Labi

Organizations: Lyles School of Civil and Construction Engineering, Purdue University, West Lafayette 47907, USA · Department of Civil and Environmental Engineering, University of Wisconsin–Madison, Madison 53706, USA

Abstract

An autonomous vehicle must foresee the consequences of its actions, especially in the rare, time-critical situations where crashes happen. A world model offers this foresight, but only within the coverage of its training data, which poses an exploration-exploitation dilemma. Within this coverage a planner can hardly improve on the data, and beyond it the model's errors mislead it. Logs of competent driving rarely contain the failures that would widen the coverage, and agents that learn from interaction gain them only by failing themselves, without being shown what to do instead. We propose SAFER, a framework that learns offline from failures that others make, judged by an expert, and keeps learning online from its own driving. Offline, partially trained agents and scripted, recoverable perturbations Stage failures in simulation, and an expert Annotates every visited state with its action and value, so that much of what the planner explores is covered before it drives. In planning, a chunked latent world model Foresees the consequences fast enough for real-time use, and a risk-aware sampling-based planner Evaluates candidate maneuvers by their return minus a bounded collision penalty. Online, a loop continuously Refines the model wherever this driving leaves the coverage of the offline data. In closed-loop evaluation against the compared methods, SAFER reaches the highest route completion and reward per step on the CARLA Leaderboard routes, 0.95 and 0.77 from a privileged bird's-eye view, and the highest episode reward in MetaDrive, 53.4 in regular and 49.0 in safety-critical traffic. Project page: https://ys-qu.github.io/safer-website.

Figures & tables

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. CorrectionPlanner: Self-Correction Planner with Reinforcement Learning in Autonomous Driving

    Mar 16, 2026Yihong Guo, Dongqiangzi Ye, Sijia Chen +2Autonomous Driving PlanningSafe Motion Planning

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

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

  3. World4Scorer: Outcome-Grounded World Modeling for Autonomous Driving

    Sep 29, 2026Jieyuan Pei, Meiyi Lu, Sining Ang +12World Model-Based PlanningWorld Models for Autonomous Driving