提出统一模型实现交通模拟与场景生成的交替推理，支持长期稳定仿真。
Long-term Traffic Simulation with Interleaved Autoregressive Motion and Scenario Generation
- 采用交替闭合回路运动与场景生成的统一预测机制
- 30秒长时仿真性能显著优于现有方法，9秒短时达顶尖水平
- 适合自动驾驶系统长期路径验证与复杂场景测试
理想的交通模拟器应能复现自动驾驶系统在实际部署中经历的长期点对点行程。以往模型和基准主要关注场景初始阶段的闭合回路运动模拟，这不适用于长期仿真——随着自车进入新区域，车辆不断进出场景。本文提出InfGen，一种统一的下一个标记预测模型，实现运动与场景生成的交替闭合回路模拟。InfGen可自动在运动与场景生成模式间切换，实现稳定长期滚动仿真。在短时（9秒）交通模拟中达到当前最优表现，在长时（30秒）模拟中显著超越所有其他方法。代码与模型将发布于https://orangesodahub.github.io/InfGen。
原文摘要 · Abstract (English)
An ideal traffic simulator replicates the realistic long-term point-to-point trip that a self-driving system experiences during deployment. Prior models and benchmarks focus on closed-loop motion simulation for initial agents in a scene. This is problematic for long-term simulation. Agents enter and exit the scene as the ego vehicle enters new regions. We propose InfGen, a unified next-token prediction model that performs interleaved closed-loop motion simulation and scene generation. InfGen automatically switches between closed-loop motion simulation and scene generation mode. It enables stable long-term rollout simulation. InfGen performs at the state-of-the-art in short-term (9s) traffic simulation, and significantly outperforms all other methods in long-term (30s) simulation. The code and model of InfGen will be released at https://orangesodahub.github.io/InfGen
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。