发表机构
Department of Engineering, University of Campania "Luigi Vanvitelli"; CIRA（工程学院，坎帕尼亚"路易吉·范维蒂利"大学; CIRA研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
探索可解释性技术在强化学习算法中的应用，以协助空中交通管制员。用强化学习算法在简化ATC环境训练智能体决策避禁飞区路线，采用显著性图作为初步可解释性方法，为智能体决策提供关键输入特征见解。
AI 中文摘要
为了有效地将人工智能集成到医疗、自动驾驶和航空等高风险关键环境中，并朝着更高水平的自动化和无缝人机协作迈进，建立对人工智能驱动解决方案的信任至关重要。而信任又与人工智能系统的可解释性密切相关。人工智能在各个领域的快速发展凸显了建立信任的挑战，在应用于深度学习时，对人工智能可解释性的兴趣日益增加。在此背景下，本工作旨在探索可解释性技术在强化学习（RL）算法中的应用，特别是在安全关键的空中交通管制（ATC）领域。使用简化的ATC环境作为初始测试平台，用强化学习算法训练智能体，以对避开禁飞区的替代飞行路线做出决策。作为一种初步的可解释性方法，采用了显著性图，以深入了解对智能体决策过程影响最大的输入特征。
英文摘要
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, an intelligent agent is trained with a reinforcement learning algorithm to make decisions on alternative flight routes that avoid no-fly zones. As a preliminary explainability approach, a saliency map is employed, providing insights into the input features that most significantly influence the agent's decision-making process.
Comments11 pages (10-page paper plus 1 cover/citation page), 4 figures, 1 table; published in AINA 2025
Journal refIn: L. Barolli (ed.), Advanced Information Networking and Applications (AINA 2025), Lecture Notes on Data Engineering and Communications Technologies, vol. 250, pp. 148-157, Springer, Cham (2025)
DOI：10.1007/978-3-031-87778-0_14
