Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Jingyi, Chu, Duanfeng, Deng, Zejian, Lu, Liping, Wang, Jinxiang, Sun, Chen
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2504.02450
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910206315724800
author Wang, Jingyi
Chu, Duanfeng
Deng, Zejian
Lu, Liping
Wang, Jinxiang
Sun, Chen
author_facet Wang, Jingyi
Chu, Duanfeng
Deng, Zejian
Lu, Liping
Wang, Jinxiang
Sun, Chen
contents To address the challenge of insufficient interactivity and behavioral diversity in autonomous driving decision-making, this paper proposes a Cognitive Hierarchical Agent for Reasoning and Motion Stylization (CHARMS). By leveraging Level-k game theory, CHARMS captures human-like reasoning patterns through a two-stage training pipeline comprising reinforcement learning pretraining and supervised fine-tuning. This enables the resulting models to exhibit diverse and human-like behaviors, enhancing their decision-making capacity and interaction fidelity in complex traffic environments. Building upon this capability, we further develop a scenario generation framework that utilizes the Poisson cognitive hierarchy theory to control the distribution of vehicles with different driving styles through Poisson and binomial sampling. Experimental results demonstrate that CHARMS is capable of both making intelligent driving decisions as an ego vehicle and generating diverse, realistic driving scenarios as environment vehicles. The code for CHARMS is released at https://github.com/chuduanfeng/CHARMS.
format Preprint
id arxiv_https___arxiv_org_abs_2504_02450
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CHARMS: A Cognitive Hierarchical Agent for Reasoning and Motion Stylization in Autonomous Driving
Wang, Jingyi
Chu, Duanfeng
Deng, Zejian
Lu, Liping
Wang, Jinxiang
Sun, Chen
Robotics
Artificial Intelligence
Machine Learning
To address the challenge of insufficient interactivity and behavioral diversity in autonomous driving decision-making, this paper proposes a Cognitive Hierarchical Agent for Reasoning and Motion Stylization (CHARMS). By leveraging Level-k game theory, CHARMS captures human-like reasoning patterns through a two-stage training pipeline comprising reinforcement learning pretraining and supervised fine-tuning. This enables the resulting models to exhibit diverse and human-like behaviors, enhancing their decision-making capacity and interaction fidelity in complex traffic environments. Building upon this capability, we further develop a scenario generation framework that utilizes the Poisson cognitive hierarchy theory to control the distribution of vehicles with different driving styles through Poisson and binomial sampling. Experimental results demonstrate that CHARMS is capable of both making intelligent driving decisions as an ego vehicle and generating diverse, realistic driving scenarios as environment vehicles. The code for CHARMS is released at https://github.com/chuduanfeng/CHARMS.
title CHARMS: A Cognitive Hierarchical Agent for Reasoning and Motion Stylization in Autonomous Driving
topic Robotics
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2504.02450