提出安全优先的类人决策框架，提升自动驾驶在复杂交通中的安全与适应性。
Toward Safety-First Human-Like Decision Making for Autonomous Vehicles in Time-Varying Traffic Flow
- 分层渐进架构融合时空注意力与社会合规评估，推断周围车辆意图并调节行为。
- 采用深度进化强化学习拓展搜索空间，避免局部最优，提升决策多样性与鲁棒性。
- 兼顾安全性、舒适性与社交兼容性，适合高密度交互场景下的自动驾驶应用。
尽管人工智能技术在提升交通效率与安全方面展现出巨大潜力，自动驾驶车辆在动态变化的交通流中仍面临严峻挑战，尤其在密集且高度互动的场景下。人类驾驶员具有自由意志，即使处于完全相同的场景也常做出不同决策，导致数据驱动方法存在迁移性差、搜索成本高的问题，降低了行为策略的效率与有效性。本研究提出一种安全优先的类人决策框架（SF-HLDM），使自动驾驶车辆在复杂交通中实现安全、舒适且具备社交兼容性的高效决策。该框架采用分层渐进结构，结合时空注意力（S-TA）机制以推断其他道路使用者的意图，引入社会合规评估模块进行行为调控，并使用深度进化强化学习（DERL）模型高效拓展搜索空间，避免陷入局部最优，降低过拟合风险，从而生成可解释、灵活的人类化决策。该框架使自动驾驶智能体能够动态调整决策参数，在保障安全裕度的同时遵循情境适配的驾驶行为。
原文摘要 · Abstract (English)
Despite the recent advancements in artificial intelligence technologies have shown great potential in improving transport efficiency and safety, autonomous vehicles(AVs) still face great challenge of driving in time-varying traffic flow, especially in dense and interactive situations. Meanwhile, human have free wills and usually do not make the same decisions even situate in the exactly same scenarios, leading to the data-driven methods suffer from poor migratability and high search cost problems, decreasing the efficiency and effectiveness of the behavior policy. In this research, we propose a safety-first human-like decision-making framework(SF-HLDM) for AVs to drive safely, comfortably, and social compatiblely in effiency. The framework integrates a hierarchical progressive framework, which combines a spatial-temporal attention (S-TA) mechanism for other road users' intention inference, a social compliance estimation module for behavior regulation, and a Deep Evolutionary Reinforcement Learning(DERL) model for expanding the search space efficiently and effectively to make avoidance of falling into the local optimal trap and reduce the risk of overfitting, thus make human-like decisions with interpretability and flexibility. The SF-HLDM framework enables autonomous driving AI agents dynamically adjusts decision parameters to maintain safety margins and adhering to contextually appropriate driving behaviors at the same time.
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。