用不到1%的数据让交通模拟模型支持多种可控输入。
ECoSim: Data Efficient Fine-Tuning for Controllable Traffic Simulation
- 通过轻量级特征调制实现多模态控制，不需重训练
- 仅用不足1%标注数据即达成强可控性
- 适合自动驾驶测试中的罕见场景生成
可控交通模拟对自动驾驶系统测试至关重要，但现有方法常需重新训练大型生成模型并依赖大量标注数据。我们提出一种轻量级控制适配框架，可为预训练的先进扩散与自回归交通模型添加多模态控制能力（草图、潜在行为码、文本）。通过身份初始化的FiLM层调节中间特征，该方法高效引入新控制模态，同时保留基础模型的生成先验。在Waymo Open Sim Agents Challenge上评估显示，本方法仅需少于1%的配对控制数据即可实现强可控性。借助上下文感知条件迁移，框架支持反事实场景生成与长尾样本合成，同时保持闭环驾驶的真实性和安全性。该框架为可控交通模拟开辟新可能，通过轻量级适配预训练生成模型，实现针对性场景生成。项目页：https://ecosim-web.github.io/
原文摘要 · Abstract (English)
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/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。