让自动驾驶更像人：生成多样且拟人的驾驶行为
CHARMS: A Cognitive Hierarchical Agent for Reasoning and Motion Stylization in Autonomous Driving
- 用分层博弈论模拟人类决策，分两阶段训练提升智能体交互能力
- 可生成不同风格的车辆行为，使交通场景更真实复杂
- 适合研究自动驾驶交互与场景生成的学者和工程师
为解决自动驾驶决策中互动性不足与行为单一的问题，本文提出认知分层智能体CHARMS，基于层级k博弈论，通过强化学习预训练与监督微调的两阶段训练流程，捕捉类人推理模式。该方法使模型具备多样化且类人行为，显著提升复杂交通环境下的决策能力与交互真实性。在此基础上，进一步构建场景生成框架，利用泊松认知层级理论，通过泊松与二项抽样控制不同驾驶风格车辆的分布。实验表明，CHARMS既能作为自车做出智能决策，也能作为环境车辆生成多样、真实的交通场景。代码已开源：https://github.com/chuduanfeng/CHARMS。
原文摘要 · Abstract (English)
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.
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。