Explainable AI for Ship Collision Avoidance: Decoding Decision-Making Processes and Behavioral Intentions
It addresses the problem of interpretability in AI for maritime safety, making DRL-based controllers more understandable, though it is incremental as it builds on existing explainable AI methods.
This study developed an explainable AI for ship collision avoidance by using a critic network and attention mechanisms to decode decision-making processes and behavioral intentions, confirming safe collision avoidance under various congestion levels and making the AI's decisions comprehensible to humans.
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.