Abstract
Scalable driving simulators typically execute vehicle commands using prescribed behavioral or kinematic rules, overlooking the physics of tire-road interfaces, thereby limiting their ability to capture how adverse road and environmental conditions alter vehicle execution and propagate through traffic. To address this limitation, we present SceneFactory-3D, a GPU-batched, physics-grounded multi-agent driving simulator. Vehicles execute acceleration and steering commands via suspension- and friction-limited forces evaluated at each wheel-contact point. Spatially varying friction, per-world 3D heightfields, gravity, and rigid contact consistently govern wheel motion and chassis collisions. Per-world terrain isolation and GPU batching enable SceneFactory-3D to run matched physical counterfactuals in parallel: traffic scenario setup and vehicle controllers remain fixed while only the road condition changes, enabling the resulting closed-loop effects to be evaluated across parallel worlds. To demonstrate the advantage of the SceneFactory-3D-enabled counterfactual evaluation, we conduct an empirical study on vehicle controllers' sensitivity to road conditions. We study three learned-policy families on 1,024 matched 12-vehicle worlds per condition, and two classical planners on a shared 32-world subset, across 21 friction and grade conditions. When friction drops from 1.0 to 0.18, the share of vehicles that clear the work zone safely falls by 6 to 90 percentage points across learned policies (18-19 for classical planners), and near-collision situations become more frequent for every learned policy. Code: https://github.com/SmallWorldLab/SceneFactory_3D
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Zhu, Y., Tian, L., Zhao, T., Chen, Y., Zuo, F., Li, T., & Bian, Z. (2026). SceneFactory-3D: Lifting 2D Traffic Scenes into 3D Physical Counterfactuals for Scalable Physically Grounded Safety Evaluation. https://omanscience.com/en/articles/scenefactory-3d-lifting-2d-traffic-scenes-into-3d-physical-counterfactuals-for-scalable-physically-grounded-safety-evaluation
MLA 9
Zhu, Yicheng, et al. "SceneFactory-3D: Lifting 2D Traffic Scenes into 3D Physical Counterfactuals for Scalable Physically Grounded Safety Evaluation." https://omanscience.com/en/articles/scenefactory-3d-lifting-2d-traffic-scenes-into-3d-physical-counterfactuals-for-scalable-physically-grounded-safety-evaluation.
Chicago (author–date)
Zhu, Yicheng, Linfeng Tian, Tianmu Zhao, Yang Chen, Fan Zuo, Tao Li, and Zilin Bian. 2026. "SceneFactory-3D: Lifting 2D Traffic Scenes into 3D Physical Counterfactuals for Scalable Physically Grounded Safety Evaluation." https://omanscience.com/en/articles/scenefactory-3d-lifting-2d-traffic-scenes-into-3d-physical-counterfactuals-for-scalable-physically-grounded-safety-evaluation.
Harvard
Zhu, Y., Tian, L., Zhao, T., Chen, Y., Zuo, F., Li, T. and Bian, Z. (2026) 'SceneFactory-3D: Lifting 2D Traffic Scenes into 3D Physical Counterfactuals for Scalable Physically Grounded Safety Evaluation', Available at: https://omanscience.com/en/articles/scenefactory-3d-lifting-2d-traffic-scenes-into-3d-physical-counterfactuals-for-scalable-physically-grounded-safety-evaluation.
Vancouver
Zhu Y, Tian L, Zhao T, Chen Y, Zuo F, Li T, et al. SceneFactory-3D: Lifting 2D Traffic Scenes into 3D Physical Counterfactuals for Scalable Physically Grounded Safety Evaluation. https://omanscience.com/en/articles/scenefactory-3d-lifting-2d-traffic-scenes-into-3d-physical-counterfactuals-for-scalable-physically-grounded-safety-evaluation
IEEE
Y. Zhu, L. Tian, T. Zhao, Y. Chen, F. Zuo, T. Li, and Z. Bian, "SceneFactory-3D: Lifting 2D Traffic Scenes into 3D Physical Counterfactuals for Scalable Physically Grounded Safety Evaluation," https://omanscience.com/en/articles/scenefactory-3d-lifting-2d-traffic-scenes-into-3d-physical-counterfactuals-for-scalable-physically-grounded-safety-evaluation.