This study developed an explainable AI for ship collision avoidance. Initially, a critic network composed of sub-task critic networks was proposed to individually evaluate each sub-task in collision avoidance to clarify the AI decision-making processes involved. Additionally, an attempt was made to discern behavioral intentions through a Q-value analysis and an Attention mechanism. The former focused on interpreting intentions by examining the increment of the Q-value resulting from AI actions, while the latter incorporated the significance of other ships in the decision-making process for collision avoidance into the learning objective. AI's behavioral intentions in collision avoidance were visualized by combining the perceived collision danger with the degree of attention to other ships. The proposed method was evaluated through a numerical experiment. The developed AI was confirmed to be able to safely avoid collisions under various congestion levels, and AI's decision-making process was rendered comprehensible to humans. The proposed method not only facilitates the understanding of DRL-based controllers/systems in the ship collision avoidance task but also extends to any task comprising sub-tasks.

翻译：本研究开发了一种用于船舶避碰的可解释人工智能。首先，提出了一种由子任务批评网络组成的批评网络，用于分别评估避碰过程中的每个子任务，以阐明其中涉及的AI决策过程。此外，通过Q值分析与注意力机制尝试识别AI的行为意图。前者通过检查AI动作产生的Q值增量来解读意图，后者则将其他船舶在避碰决策中的重要性纳入学习目标。通过将感知到的碰撞危险与其他船舶的关注度相结合，可视化了AI在避碰中的行为意图。通过数值实验对所提方法进行了评估，结果表明所开发的AI能够在各种拥堵程度下安全避碰，且其决策过程对人类而言具有可理解性。该方法不仅有助于理解基于深度强化学习的船舶避碰控制器/系统，还可扩展至包含子任务的任何任务。