AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

DriveArena: A Closed-loop Generative Simulation Platform for Autonomous Driving

Xuemeng Yang, Licheng Wen, Tiantian Wei, Yukai Ma, Jianbiao Mei, Xin Li, Wenjie Lei, Daocheng Fu, Pinlong Cai, Min Dou, Liang He, Yong Liu and 2 more

ICCV 2025 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Data-driven traffic simulation · 85 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace MagicDrive with World Dreamer as the image generatorUniAD evaluator on generated nuScenes val · nuScenes val fidelity3D detection mAP: 12.92 -> 16.06Improved
replace MagicDrive with World Dreamer as the image generatorUniAD evaluator on generated nuScenes val · nuScenes val fidelityBEV seg Drivable mIoU: 51.46 -> 59.37Improved
replace MagicDrive with World Dreamer as the image generatorUniAD evaluator on generated nuScenes val · nuScenes val fidelityCollision rate avg (%): 0.35 -> 0.24Improved
replace real nuScenes images with World Dreamer generated imagesUniAD · nuScenes valPDMS: 0.910 -> 0.902No clear effect
run UniAD in DriveArena open-loop simulation instead of nuScenes replayUniAD · DriveArena open-loopPDMS: 0.902 -> 0.636Hurt
run UniAD in DriveArena open-loop simulation instead of nuScenes replayUniAD · DriveArena open-loopNo collisions (NC): 0.993 -> 0.792Hurt
switch UniAD from open-loop to closed-loop controlUniAD · DriveArenaPDMS: 0.636 -> 0.667No clear effect
closed-loop control reveals route failure hidden by open-loop metricsUniAD · DriveArena closed-loopRoute completion: 13.7% average route completionHurt

Later papers that compared with this method

1 later accepted paper reports DriveArena as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy