arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2607.00545cs.CV
收藏

ECoSim:面向可控交通模拟的数据高效微调

ECoSim: Data Efficient Fine-Tuning for Controllable Traffic Simulation

National Yang Ming Chiao Tung University(国立阳明交通大学);University of California, Berkeley(加州大学伯克利分校)

Yu-Hsiang Chen, Wei-Jer Chang, Yi-Ting Chen, Masayoshi Tomizuka

AI总结:

提出轻量级控制适应框架,通过身份初始化的FiLM层调制中间特征,为预训练的扩散和自回归交通模型添加多模态控制(草图、潜在行为编码和文本),使用不到1%的配对数据实现强可控性。

摘要:

可控交通模拟对于测试自动驾驶系统至关重要,但现有方法通常需要使用大量标注数据重新训练大型生成模型。我们引入了一个轻量级控制适应框架,为预训练的最先进的扩散和自回归交通模型实现多模态可控性(草图、潜在行为编码和文本)。通过身份初始化的FiLM层调制中间特征,我们的方法在保留基础模型生成先验的同时,高效地添加了新的控制模态。在Waymo Open Sim Agents Challenge上的评估表明,我们的方法使用不到1%的配对控制数据就展现了强大的可控性。通过上下文感知的条件转移,我们的框架能够生成反事实场景和长尾合成,同时保持稳定的闭环驾驶真实性和安全性。我们的框架为可控交通模拟开辟了新的可能性,通过轻量级适应预训练生成模型实现目标场景生成。项目页面:此 https URL

英文摘要:

Controllable traffic simulation is critical for testing autonomous driving systems, yet existing approaches often require retraining large generative models with extensive annotated data. We introduce a lightweight control adaptation framework that enables multi-modal controllability (sketch, latent behavior codes, and text) for pretrained state-of-the-art diffusion and autoregressive traffic models. By modulating intermediate features through identity-initialized FiLM layers, our method efficiently adds new control modalities while preserving the base model's generative prior. Evaluated on Waymo Open Sim Agents Challenge, our approach demonstrates strong controllability with less than 1% of the paired control data. Through context-aware condition transfer, our framework enables counterfactual scenario generation and long-tail synthesis while maintaining stable closed-loop driving realism and safety. Our framework unlocks new possibilities for controllable traffic simulation, enabling targeted scenario generation through lightweight adaptation of pretrained generative models. Project page: https://ecosim-web.github.io/

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑