cs.RONov 8, 2026

Breaking survivorship bias in driving world models

Authors: Zihao Sheng, Zilin Huang, Yuhao Luo, Zhengyang Wan, Boyue Wang, Soyoung Ahn, David A. Noyce, Sikai Chen

Organizations: Department of Civil and Environmental Engineering, University of Wisconsin–Madison, Madison, WI, USA · Wisconsin Transportation Center, University of Wisconsin–Madison, Madison, WI, USA

Abstract

World models allow autonomous vehicles to imagine the consequences of candidate actions before execution, but their reliability depends on the futures represented in their training data. We identify a survivorship bias in driving world models: because the futures recorded in prevailing driving datasets almost always end safely, existing models often imagine benign outcomes even when a collision is imminent. We introduce a neutral world model (NWM) that learns both routine and safety-critical futures from a mixture of routine driving and real accident videos with a bounding-box-guided objective. The NWM more faithfully anticipates imminent collisions, while maintaining a low false collision rate and competitive generation quality in routine driving. We further use the model as an imagination engine for decision-making. Given multiple ego trajectories, the NWM predicts the future associated with each candidate, and a reward function evaluates these imagined outcomes before selecting an action. On challenging NAVSIM scenarios, this procedure selects the better trajectory more reliably than the baseline world model. Zero-shot experiments with real-world pedestrian dummy crossing data collected using an autonomous research vehicle further demonstrate transfer to unseen sensor observations. These results show that correcting survivorship bias enables world models to more faithfully reason about futures and support safety-critical decision-making in autonomous driving.

Figures & tables

Appendix figures & tables10 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Reinforcing End-to-End Autonomous Driving Safety via Negative-Aware Planning in a Unified World-Action Model

    Nov 5, 2026Zihao Zhang, Xinyu Zhang, Bing Zeng +4End-to-End Autonomous DrivingWorld Action Models

  2. DA-WAM: Decision-Aligned Future Latents for Driving World Models

    Aug 19, 2026Ruiguo Zhong, Xiaolong Chen, Benshan Ma +5World Models for Autonomous DrivingAutonomous Driving Planning

  3. Learning Vision-Language-Action World Models for Autonomous Driving

    Apr 10, 2026Guoqing Wang, Pin Tang, Xiangxuan Ren +3World Models for Autonomous DrivingVision-Language-Action Models