長期交通模擬與交錯式自迴歸運動及場景生成

摘要

理想的交通模擬器應能重現自駕系統在實際部署中所經歷的長期點對點行程。先前的研究模型與基準測試主要集中於場景中初始代理的閉環運動模擬，這對長期模擬而言存在問題。隨著自駕車輛進入新區域，代理會不斷進出場景。我們提出了InfGen，這是一個統一的下一令牌預測模型，能夠交替進行閉環運動模擬與場景生成。InfGen能自動在閉環運動模擬與場景生成模式間切換，從而實現穩定的長期滾動模擬。在短期（9秒）交通模擬中，InfGen表現出頂尖水平，而在長期（30秒）模擬中，其性能顯著超越所有其他方法。InfGen的程式碼與模型將於https://orangesodahub.github.io/InfGen發布。

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

長期交通模擬與交錯式自迴歸運動及場景生成

Long-term Traffic Simulation with Interleaved Autoregressive Motion and Scenario Generation

摘要

Support