AutoWorld：基于自监督世界模型的多智能体交通仿真
AutoWorld: Learning Multi-Agent Traffic Simulation with Self-Supervised World Models
AI 导读
AutoWorld 是一个交通仿真框架，通过在 LiDAR 占据数据上训练的自监督世界模型，把智能体行为锚定在原始传感器观测上，并配合多智能体运动生成模型输出场景。在 nuPlan 和 Waymo 上的实验显示其生成真实度更高，碰撞率降低 36%，在部分观测场景中收益最大。该框架在规划器控制的自车行为下仍保持物理合理性，支持可控且多样的安全关键场景生成。
正文 · 原文
Abstract:Simulation with realistic traffic agents is essential for validating autonomous driving systems. Existing data-driven simulators learn agent behavior from higher-level abstractions such as 3D bounding boxes and polylines, inferred by upstream perception pipelines. These lossy abstractions discard sensory context that directly shapes agent behavior, limiting the distributional realism that simulation aims to reproduce. To address this limitation, we propose AutoWorld, a traffic simulation framework that grounds agent behavior in raw sensor observations through a self-supervised world model trained on LiDAR occupancy data. Given world model samples, AutoWorld constructs a coarse-to-fine predictive scene context as input to a multi-agent motion generation model. Furthermore, we designed a motion-aware latent supervision objective that enriches AutoWorld's latent representation of scene dynamics. To better exploit this latent space during inference, AutoWorld employs a cascaded Determinantal Point Process framework to guide diversity-aware sampling across both the world model and motion model. Experiments on nuPlan and Waymo demonstrate that AutoWorld improves generation realism, with larger gains in partially observed scenarios where trajectory abstractions are most limited, reducing collision rates by 36%. AutoWorld also remains physically plausible under planner-controlled ego behavior and supports controllable, diverse safety-critical scenario generation.
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG) |
| Cite as: | arXiv:2603.28963 [cs.RO] |
| (or arXiv:2603.28963v3 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2603.28963 arXiv-issued DOI via DataCite |
Submission history
From: Mozhgan Pourkeshavarz [view email]
[v1]
Mon, 30 Mar 2026 20:10:21 UTC (18,202 KB)
[v2]
Mon, 27 Jul 2026 15:18:15 UTC (10,873 KB)
[v3]
Mon, 26 Oct 2026 01:31:34 UTC (11,517 KB)
来源：arXiv cs.AI · arxiv.org