Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lin, Enli, Yang, Ziyuan, Lu, Qiujing, Hu, Jianming, Feng, Shuo
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2510.11534
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914090417389568
author Lin, Enli
Yang, Ziyuan
Lu, Qiujing
Hu, Jianming
Feng, Shuo
author_facet Lin, Enli
Yang, Ziyuan
Lu, Qiujing
Hu, Jianming
Feng, Shuo
contents Realistic traffic simulation is critical for ensuring the safety and reliability of autonomous vehicles (AVs), especially in complex and diverse urban traffic environments. However, existing data-driven simulators face two key challenges: a limited focus on modeling dense, heterogeneous interactions at urban intersections - which are prevalent, crucial, and practically significant in countries like China, featuring diverse agents including motorized vehicles (MVs), non-motorized vehicles (NMVs), and pedestrians - and the inherent difficulty in robustly learning high-dimensional joint distributions for such high-density scenes, often leading to mode collapse and long-term simulation instability. We introduce City Crossings Dataset (CiCross), a large-scale dataset collected from a real-world urban intersection, uniquely capturing dense, heterogeneous multi-agent interactions, particularly with a substantial proportion of MVs, NMVs and pedestrians. Based on this dataset, we propose IntersectioNDE (Intersection Naturalistic Driving Environment), a data-driven simulator tailored for complex urban intersection scenarios. Its core component is the Interaction Decoupling Strategy (IDS), a training paradigm that learns compositional dynamics from agent subsets, enabling the marginal-to-joint simulation. Integrated into a scene-aware Transformer network with specialized training techniques, IDS significantly enhances simulation robustness and long-term stability for modeling heterogeneous interactions. Experiments on CiCross show that IntersectioNDE outperforms baseline methods in simulation fidelity, stability, and its ability to replicate complex, distribution-level urban traffic dynamics.
format Preprint
id arxiv_https___arxiv_org_abs_2510_11534
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle IntersectioNDE: Learning Complex Urban Traffic Dynamics based on Interaction Decoupling Strategy
Lin, Enli
Yang, Ziyuan
Lu, Qiujing
Hu, Jianming
Feng, Shuo
Robotics
Systems and Control
Realistic traffic simulation is critical for ensuring the safety and reliability of autonomous vehicles (AVs), especially in complex and diverse urban traffic environments. However, existing data-driven simulators face two key challenges: a limited focus on modeling dense, heterogeneous interactions at urban intersections - which are prevalent, crucial, and practically significant in countries like China, featuring diverse agents including motorized vehicles (MVs), non-motorized vehicles (NMVs), and pedestrians - and the inherent difficulty in robustly learning high-dimensional joint distributions for such high-density scenes, often leading to mode collapse and long-term simulation instability. We introduce City Crossings Dataset (CiCross), a large-scale dataset collected from a real-world urban intersection, uniquely capturing dense, heterogeneous multi-agent interactions, particularly with a substantial proportion of MVs, NMVs and pedestrians. Based on this dataset, we propose IntersectioNDE (Intersection Naturalistic Driving Environment), a data-driven simulator tailored for complex urban intersection scenarios. Its core component is the Interaction Decoupling Strategy (IDS), a training paradigm that learns compositional dynamics from agent subsets, enabling the marginal-to-joint simulation. Integrated into a scene-aware Transformer network with specialized training techniques, IDS significantly enhances simulation robustness and long-term stability for modeling heterogeneous interactions. Experiments on CiCross show that IntersectioNDE outperforms baseline methods in simulation fidelity, stability, and its ability to replicate complex, distribution-level urban traffic dynamics.
title IntersectioNDE: Learning Complex Urban Traffic Dynamics based on Interaction Decoupling Strategy
topic Robotics
Systems and Control
url https://arxiv.org/abs/2510.11534