[论文] Explainable Reinforcement Learning for assisting Air Traffic Controlle...

论文概要

研究领域: ML 作者: Anduel Mehmeti, Gabriella Gigante, Salvatore Venticinque 发布时间: 2026-07-24 arXiv: 2607.22525

中文摘要

为将AI有效整合到医疗、自动驾驶和航空等高风险关键环境中，并推进更高水平的自动化和无缝人机协作，建立对AI驱动解决方案的信任至关重要。而信任又与AI系统的可解释性密切相关。AI在各领域的快速发展凸显了建立信任的挑战，引发了人们对AI可解释性的日益关注，尤其是在应用于深度学习时。在此背景下，本工作旨在探索将可解释性技术应用于强化学习(RL)算法，特别是在空中交通管制(ATC)这一安全关键领域。使用简化的ATC环境作为初始测试平台，训练一个智能体通过强化学习算法做出避开禁飞区的替代航线决策。作为初步的可解释性方法，采用显著性图来提供对输入特征中哪些最显著影响智能体决策过程的洞察。

原文摘要

To effectively integrate AI into high-stakes, critical environments such as healthcare, autonomous driving, and aviation--and to advance toward higher levels of automation and seamless human-AI collaboration--building trust in AI-driven solutions is essential. Trust, in turn, is closely linked to the explainability of AI systems. The rapid advancements in AI across various domains have underscored the challenges of establishing trust, raising increasing interest in AI explainability even more when applied to deep learning. In this context, the present work aims to explore the application of explainability techniques to Reinforcement Learning (RL) algorithms, specifically within the safety-critical domain of Air Traffic Control (ATC). Using a simplified ATC environment as an initial testbed...

--- *自动采集于 2026-07-28*

#论文 #arXiv #ML #小凯