World Engine: Towards the Era of Post-Training for Autonomous Driving

• URL: http://arxiv.org/abs/2606.19836v1
• Date: Thu, 18 Jun 2026 06:28:33 GMT
• Title: World Engine: Towards the Era of Post-Training for Autonomous Driving
• Abstract summary: We introduce World Engine, a generative framework that reconstructs high-fidelity interactive environments from real-world logs.<n>World Engine substantially reduces failures in rare safety-critical scenarios and yields significantly larger gains than scaling pre-training data alone.<n>When deployed on a production-scale autonomous driving system, the resulting policy reduces simulated collisions.
• Score: 63.61277741443647
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Autonomous vehicles must operate safely in the real world, where errors can have severe consequences. Although modern end-to-end driving policies excel in routine scenarios, their reliability is limited by the scarcity of safety-critical ``long-tail'' events in real driving datasets. These rare interactions define the practical safety boundary of the learned policy, yet they are difficult to collect at scale in the real world. Here we show that this fundamental limitation can be addressed by post-training pre-trained driving models on synthesized high-stakes interactions. We introduce World Engine, a generative framework that reconstructs high-fidelity interactive environments from real-world logs and systematically extrapolates them into realistic safety-critical variations. This paradigm enables reinforcement-based post-training to align policies with safety constraints, circumventing the physical risks inherent in real-world exploration. On a public benchmark built on nuPlan, World Engine substantially reduces failures in rare safety-critical scenarios and yields significantly larger gains than scaling pre-training data alone. Furthermore, when deployed on a production-scale autonomous driving system, the resulting policy reduces simulated collisions and demonstrates measurable improvements in on-road testing, showing that post-training on synthesized, safety-critical interactions offers a scalable and effective pathway to safer autonomous driving. The full codebase suite, including training, is released to the public.

Related papers

• Formal Safety Guarantees for Autonomous Vehicles using Barrier Certificates [0.1019561860229868]
  This work develops a formally verified safety framework for Connected and Autonomous Vehicles.<n>It integrates Barrier (BCs) with interpretable traffic conflict metrics, specifically Time-to-temporal safety metric.<n>This approach provides both interpretable and provable safety guarantees, demonstrating a practical and scalable strategy for safe autonomous driving.
  arXiv  Detail & Related papers  (2026-01-08T19:44:13Z)
• AD-R1: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving with Impartial World Models [75.214287449744]
  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.
  arXiv  Detail & Related papers  (2025-11-25T13:57:24Z)
• Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving [1.2891210250935148]
  We present a hierarchical Safe Reinforcement Learning framework that augments standard driving objectives with ethics-aware cost signals.<n>A Safe RL agent is trained using a composite ethical risk cost, combining collision probability and harm severity, to generate high-level motion targets.<n>A dynamic, risk-sensitive Prioritized Experience mechanism amplifies learning from rare but critical, high-risk events.
  arXiv  Detail & Related papers  (2025-08-19T14:24:02Z)
• VL-SAFE: Vision-Language Guided Safety-Aware Reinforcement Learning with World Models for Autonomous Driving [1.9242820889313577]
  Reinforcement learning (RL)-based autonomous driving policy learning faces critical limitations.<n>RL often fail to capture the true semantic meaning of "safety" in complex driving contexts.<n>We propose VL-SAFE, a world model-based safe RL framework with Vision-Language model (VLM)-as-safety-guidance paradigm.
  arXiv  Detail & Related papers  (2025-05-22T08:29:59Z)
• Enhancing Autonomous Driving Safety with Collision Scenario Integration [36.83682052117178]
  We propose SafeFusion, a training framework to learn from collision data.<n>Instead of over-relying on imitation learning, SafeFusion integrates safety-oriented metrics during training to enable collision avoidance learning.<n>We also propose CollisionGen, a scalable data generation pipeline to generate diverse, high-quality scenarios.
  arXiv  Detail & Related papers  (2025-03-05T23:08:43Z)
• ReGentS: Real-World Safety-Critical Driving Scenario Generation Made Stable [88.08120417169971]
  Machine learning based autonomous driving systems often face challenges with safety-critical scenarios that are rare in real-world data. This work explores generating safety-critical driving scenarios by modifying complex real-world regular scenarios through trajectory optimization. Our approach addresses unrealistic diverging trajectories and unavoidable collision scenarios that are not useful for training robust planner.
  arXiv  Detail & Related papers  (2024-09-12T08:26:33Z)
• RACER: Epistemic Risk-Sensitive RL Enables Fast Driving with Fewer Crashes [57.319845580050924]
  We propose a reinforcement learning framework that combines risk-sensitive control with an adaptive action space curriculum. We show that our algorithm is capable of learning high-speed policies for a real-world off-road driving task.
  arXiv  Detail & Related papers  (2024-05-07T23:32:36Z)
• 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)
• Safety-aware Causal Representation for Trustworthy Offline Reinforcement Learning in Autonomous Driving [33.672722472758636]
  offline Reinforcement Learning(RL) approaches exhibit notable efficacy in addressing sequential decision-making problems from offline datasets. We introduce the saFety-aware strUctured Scenario representatION ( Fusion) to facilitate the learning of a generalizable end-to-end driving policy. Empirical evidence in various driving scenarios attests that Fusion significantly enhances the safety and generalizability of autonomous driving agents.
  arXiv  Detail & Related papers  (2023-10-31T18:21:24Z)
• Differentiable Control Barrier Functions for Vision-based End-to-End Autonomous Driving [100.57791628642624]
  We introduce a safety guaranteed learning framework for vision-based end-to-end autonomous driving. We design a learning system equipped with differentiable control barrier functions (dCBFs) that is trained end-to-end by gradient descent.
  arXiv  Detail & Related papers  (2022-03-04T16:14:33Z)

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.