Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Tian, Zhen, Yuan, Fujiang, Yuan, Chunhong, Peng, Yanhong
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2509.08147
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916943466856448
author Tian, Zhen
Yuan, Fujiang
Yuan, Chunhong
Peng, Yanhong
author_facet Tian, Zhen
Yuan, Fujiang
Yuan, Chunhong
Peng, Yanhong
contents Interactive trajectory planning in autonomous driving must balance safety, efficiency, and scalability under heterogeneous driving behaviors. Existing methods often face high computational cost or rely on external safety critics. To address this, we propose an Interaction-Enriched Unified Potential Field (IUPF) framework that fuses style-dependent benefit and risk fields through a physics-inspired variational model, grounded in mean field game theory. The approach captures conservative, aggressive, and cooperative behaviors without additional safety modules, and employs stochastic differential equations to guarantee Nash equilibrium with exponential convergence. Simulations on lane changing and overtaking scenarios show that IUPF ensures safe distances, generates smooth and efficient trajectories, and outperforms traditional optimization and game-theoretic baselines in both adaptability and computational efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2509_08147
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Mean Field Game-Based Interactive Trajectory Planning Using Physics-Inspired Unified Potential Fields
Tian, Zhen
Yuan, Fujiang
Yuan, Chunhong
Peng, Yanhong
Robotics
Interactive trajectory planning in autonomous driving must balance safety, efficiency, and scalability under heterogeneous driving behaviors. Existing methods often face high computational cost or rely on external safety critics. To address this, we propose an Interaction-Enriched Unified Potential Field (IUPF) framework that fuses style-dependent benefit and risk fields through a physics-inspired variational model, grounded in mean field game theory. The approach captures conservative, aggressive, and cooperative behaviors without additional safety modules, and employs stochastic differential equations to guarantee Nash equilibrium with exponential convergence. Simulations on lane changing and overtaking scenarios show that IUPF ensures safe distances, generates smooth and efficient trajectories, and outperforms traditional optimization and game-theoretic baselines in both adaptability and computational efficiency.
title Mean Field Game-Based Interactive Trajectory Planning Using Physics-Inspired Unified Potential Fields
topic Robotics
url https://arxiv.org/abs/2509.08147