Heterogeneous Self-Play for Realistic Highway Traffic Simulation

• URL: http://arxiv.org/abs/2604.16406v1
• Date: Tue, 31 Mar 2026 19:39:29 GMT
• Title: Heterogeneous Self-Play for Realistic Highway Traffic Simulation
• Abstract summary: PHASE, Policy for Heterogeneous Agent Self-play on Expressway, is a context-aware self-play framework.<n>It supports different vehicle profiles, for example, passenger cars and articulated trailer trucks, within a single policy.<n>It achieves a 96.3% success rate and reduces ADE/FDE from 6.57/12.07 m to 2.44/5.25 m relative to a prior self-play baseline.
• Score: 42.67401323169807
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Realistic highway simulation is critical for scalable safety evaluation of autonomous vehicles, particularly for interactions that are too rare to study from logged data alone. Yet highway traffic generation remains challenging because it requires broad coverage across speeds and maneuvers, controllable generation of rare safety-critical scenarios, and behavioral credibility in multi-agent interactions. We present PHASE, Policy for Heterogeneous Agent Self-play on Expressway, a context-aware self-play framework that addresses these three requirements through explicit per-agent conditioning for controllability, synthetic scenario generation for broad highway coverage, and closed-loop multi-agent training for realistic interaction dynamics. PHASE further supports different vehicle profiles, for example, passenger cars and articulated trailer trucks, within a single policy via vehicle-aware dynamics and context-conditioned actions, and stabilizes self-play with early termination of unrecoverable states, at-fault collision attribution, highway-aware reward shaping, coupled curricula, and robust policy optimization. Despite being trained only on synthetic data, PHASE transfers zero-shot to 512 unseen high-interaction real scenarios in exiD, achieving a 96.3% success rate and reducing ADE/FDE from 6.57/12.07 m to 2.44/5.25 m relative to a prior self-play baseline. In a learned trajectory embedding space, it also improves behavioral realism over IDM, reducing Frechet trajectory distance by 13.1% and energy distance by 20.2%. These results show that synthetic self-play can provide a scalable route to controllable and realistic highway scenario generation without direct imitation of expert logs.

Related papers

• World Engine: Towards the Era of Post-Training for Autonomous Driving [63.61277741443647]
  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.
  arXiv  Detail & Related papers  (2026-06-18T06:28:33Z)
• Optimization-Guided Diffusion for Interactive Scene Generation [52.23368750264419]
  We present OMEGA, an optimization-guided, training-free framework that enforces structural consistency and interaction awareness during diffusion-based sampling.<n>We show that OMEGA improves generation realism, consistency, and controllability, increasing the ratio of physically and behaviorally valid scenes.<n>Our approach can also generate $5times$ more near-collision frames with a time-to-collision under three seconds.
  arXiv  Detail & Related papers  (2025-12-08T15:56:18Z)
• HABIT: Human Action Benchmark for Interactive Traffic in CARLA [0.2905751301655124]
  We introduce HABIT (Human Action Benchmark for Interactive Traffic), a high-fidelity simulation benchmark.<n>From an initial pool of approximately 30,000 retargeted motions, we curate 4,730 traffic-compatible pedestrian motions.<n>Our safety metrics, including Abbreviated Injury Scale (AIS) and False Positive Braking Rate (FPBR), reveal critical failure modes in state-of-the-art AD agents missed by prior evaluations.
  arXiv  Detail & Related papers  (2025-11-24T13:43:39Z)
• SPACeR: Self-Play Anchoring with Centralized Reference Models [50.55045557371374]
  Sim agent policies are realistic, human-like, fast, and scalable in multi-agent settings.<n>Recent progress in imitation learning with large diffusion-based or tokenized models has shown that behaviors can be captured directly from human driving data.<n>We propose SPACeR, a framework that leverages a pretrained tokenized autoregressive motion model as a central reference policy.
  arXiv  Detail & Related papers  (2025-10-20T19:53:02Z)
• RADE: Learning Risk-Adjustable Driving Environment via Multi-Agent Conditional Diffusion [17.46462636610847]
  Risk- Driving Environment (RADE) is a simulation framework that generates statistically realistic and risk-adjustable traffic scenes.<n>RADE learns risk-conditioned behaviors directly from data, preserving naturalistic multi-agent interactions with controllable risk levels.<n>We validate RADE on the real-world rounD dataset, demonstrating that it preserves statistical realism across varying risk levels.
  arXiv  Detail & Related papers  (2025-05-06T04:41:20Z)
• Reinforcement Learning with Latent State Inference for Autonomous On-ramp Merging under Observation Delay [6.0111084468944]
  We introduce the Lane-keeping, Lane-changing with Latent-state Inference and Safety Controller (L3IS) agent. L3IS is designed to perform the on-ramp merging task safely without comprehensive knowledge about surrounding vehicles' intents or driving styles. We present an augmentation of this agent called AL3IS that accounts for observation delays, allowing the agent to make more robust decisions in real-world environments.
  arXiv  Detail & Related papers  (2024-03-18T15:02:46Z)
• 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)
• ReMAV: Reward Modeling of Autonomous Vehicles for Finding Likely Failure Events [1.84926694477846]
  We propose a black-box testing framework that uses offline trajectories first to analyze the existing behavior of autonomous vehicles. Our experiment shows an increase in 35, 23, 48, and 50% in the occurrences of vehicle collision, road object collision, pedestrian collision, and offroad steering events.
  arXiv  Detail & Related papers  (2023-08-28T13:09:00Z)
• Generative AI-empowered Simulation for Autonomous Driving in Vehicular Mixed Reality Metaverses [130.15554653948897]
  In vehicular mixed reality (MR) Metaverse, distance between physical and virtual entities can be overcome. Large-scale traffic and driving simulation via realistic data collection and fusion from the physical world is difficult and costly. We propose an autonomous driving architecture, where generative AI is leveraged to synthesize unlimited conditioned traffic and driving data in simulations.
  arXiv  Detail & Related papers  (2023-02-16T16:54:10Z)

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.