为了有效地将人工智能集成到高风险,关键环境中，例如医疗保健,自动驾驶,和航空，并迈向更高水平的自动化和无缝人机与人工智能协作，建立对人工智能驱动解决方案的信任至关重要。信任, 反过来, 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进步凸显了建立信任,的挑战，当应用于深度学习时，人们对人工智能可解释性的兴趣日益浓厚。在这种情况下,目前的工作旨在探索可解释性技术在强化学习(RL)算法,中的应用，特别是在空中交通管制(ATC)的安全关键领域内。使用简化的 ATC 环境作为初始测试平台,，智能代理通过强化学习算法进行训练，以做出避开禁飞区的替代飞行路线的决策。作为初步的可解释性方法,，采用显着性图,，提供对对代理 决策过程影响最显着的输入特征的洞察。
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的 decision-making process.
科目:人工智能(cs.AI)
Subjects: Artificial Intelligence (cs.AI)