AD-R1: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving with Impartial World Models

• URL: http://arxiv.org/abs/2511.20325v1
• Date: Tue, 25 Nov 2025 13:57:24 GMT
• Title: AD-R1: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving with Impartial World Models
• Authors: Tianyi Yan, Tao Tang, Xingtai Gui, Yongkang Li, Jiasen Zhesng, Weiyao Huang, Lingdong Kong, Wencheng Han, Xia Zhou, Xueyang Zhang, Yifei Zhan, Kun Zhan, Cheng-zhong Xu, Jianbing Shen,
• Abstract summary: We introduce a framework for post-training policy refinement built around an Impartial World Model.<n>Our primary contribution is to teach this model to be honest about danger.<n>We demonstrate through extensive experiments, that our model significantly outperforms baselines in predicting failures.
• Score: 75.214287449744
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: End-to-end models for autonomous driving hold the promise of learning complex behaviors directly from sensor data, but face critical challenges in safety and handling long-tail events. Reinforcement Learning (RL) offers a promising path to overcome these limitations, yet its success in autonomous driving has been elusive. We identify a fundamental flaw hindering this progress: a deep seated optimistic bias in the world models used for RL. To address this, we introduce a framework for post-training policy refinement built around an Impartial World Model. Our primary contribution is to teach this model to be honest about danger. We achieve this with a novel data synthesis pipeline, Counterfactual Synthesis, which systematically generates a rich curriculum of plausible collisions and off-road events. This transforms the model from a passive scene completer into a veridical forecaster that remains faithful to the causal link between actions and outcomes. We then integrate this Impartial World Model into our closed-loop RL framework, where it serves as an internal critic. During refinement, the agent queries the critic to ``dream" of the outcomes for candidate actions. We demonstrate through extensive experiments, including on a new Risk Foreseeing Benchmark, that our model significantly outperforms baselines in predicting failures. Consequently, when used as a critic, it enables a substantial reduction in safety violations in challenging simulations, proving that teaching a model to dream of danger is a critical step towards building truly safe and intelligent autonomous agents.

Related papers

• Risk-Aware World Model Predictive Control for Generalizable End-to-End Autonomous Driving [82.69496624372944]
  "Only driving like the expert" suffers from limited generalization.<n>Can an E2E-AD system make reliable decisions without any expert action supervision?<n>We propose a unified framework named Risk-aware World Model Predictive Control.
  arXiv  Detail & Related papers  (2026-02-26T17:32:30Z)
• Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models [62.16655896700062]
  Activation steering is a technique to enhance the utility of Large Language Models (LLMs)<n>We show that it unintentionally introduces critical and under-explored safety risks.<n>Experiments reveal that these interventions act as a force multiplier, creating new vulnerabilities to jailbreaks and increasing attack success rates to over 80% on standard benchmarks.
  arXiv  Detail & Related papers  (2026-02-03T12:32:35Z)
• Adversarial Generation and Collaborative Evolution of Safety-Critical Scenarios for Autonomous Vehicles [47.25901323750217]
  The generation of safety-critical scenarios in simulation has become increasingly crucial for safety evaluation in autonomous vehicles prior to road deployment in society.<n>We propose ScenGE, a framework that can generate plentiful safety-critical scenarios by reasoning novel adversarial cases and then amplifying them with complex traffic flows.<n>We validate our framework through real-world vehicle tests and human evaluation, confirming that the generated scenarios are both plausible and critical.
  arXiv  Detail & Related papers  (2025-08-20T08:36:57Z)
• Offline Robotic World Model: Learning Robotic Policies without a Physics Simulator [50.191655141020505]
  Reinforcement Learning (RL) has demonstrated impressive capabilities in robotic control but remains challenging due to high sample complexity, safety concerns, and the sim-to-real gap.<n>We introduce Offline Robotic World Model (RWM-O), a model-based approach that explicitly estimates uncertainty to improve policy learning without reliance on a physics simulator.
  arXiv  Detail & Related papers  (2025-04-23T12:58:15Z)
• AI in a vat: Fundamental limits of efficient world modelling for agent sandboxing and interpretability [84.52205243353761]
  Recent work proposes using world models to generate controlled virtual environments in which AI agents can be tested before deployment.<n>We investigate ways of simplifying world models that remain agnostic to the AI agent under evaluation.
  arXiv  Detail & Related papers  (2025-04-06T20:35:44Z)
• Adversarial Safety-Critical Scenario Generation using Naturalistic Human Driving Priors [2.773055342671194]
  We introduce a natural adversarial scenario generation solution using naturalistic human driving priors and reinforcement learning techniques. Our findings demonstrate that the proposed model can generate realistic safety-critical test scenarios covering both naturalness and adversariality.
  arXiv  Detail & Related papers  (2024-08-06T13:58:56Z)
• Zero-shot Safety Prediction for Autonomous Robots with Foundation World Models [0.12499537119440243]
  A world model creates a surrogate world to train a controller and predict safety violations by learning the internal dynamic model of systems. We propose foundation world models that embed observations into meaningful and causally latent representations. This enables the surrogate dynamics to directly predict causal future states by leveraging a training-free large language model.
  arXiv  Detail & Related papers  (2024-03-30T20:03:49Z)
• SAFE-SIM: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversaries [94.84458417662407]
  We introduce SAFE-SIM, a controllable closed-loop safety-critical simulation framework. Our approach yields two distinct advantages: 1) generating realistic long-tail safety-critical scenarios that closely reflect real-world conditions, and 2) providing controllable adversarial behavior for more comprehensive and interactive evaluations. We validate our framework empirically using the nuScenes and nuPlan datasets across multiple planners, demonstrating improvements in both realism and controllability.
  arXiv  Detail & Related papers  (2023-12-31T04:14:43Z)
• Reinforcement Learning with Human Feedback for Realistic Traffic Simulation [53.85002640149283]
  Key element of effective simulation is the incorporation of realistic traffic models that align with human knowledge. This study identifies two main challenges: capturing the nuances of human preferences on realism and the unification of diverse traffic simulation models.
  arXiv  Detail & Related papers  (2023-09-01T19:29:53Z)
• UMBRELLA: Uncertainty-Aware Model-Based Offline Reinforcement Learning Leveraging Planning [1.1339580074756188]
  Offline reinforcement learning (RL) provides a framework for learning decision-making from offline data. Self-driving vehicles (SDV) learn a policy, which potentially even outperforms the behavior in the sub-optimal data set. This motivates the use of model-based offline RL approaches, which leverage planning.
  arXiv  Detail & Related papers  (2021-11-22T10:37:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.