"Why This Avoidance Maneuver?" Contrastive Explanations in Human-Supervised Maritime Autonomous Navigation

2026-04-09

AI Summary

This study addresses the lack of transparent and interpretable decision explanations in existing automated ship collision avoidance systems under human supervision. It introduces contrastive explanations—a novel approach in maritime autonomous navigation—by comparing the system’s recommended maneuver against feasible alternatives, leveraging multimodal visual and textual cues to clearly convey the rationale to human supervisors with nautical expertise. The research integrates state-of-the-art collision avoidance algorithms, contrastive explanation generation, and a human-centered interface. An exploratory user study with four experienced mariners demonstrates that this method enhances understanding of the system’s intent; however, it may impose additional cognitive load in complex multi-ship scenarios. The findings suggest adopting on-demand or context-adaptive explanation strategies to balance interpretability and operational efficiency.

Abstract

Automated maritime collision avoidance will rely on human supervision for the foreseeable future. This necessitates transparency into how the system perceives a scenario and plans a maneuver. However, the causal logic behind avoidance maneuvers is often complex and difficult to convey to a navigator. This paper explores how to explain these factors in a selective, understandable manner for supervisors with a nautical background. We propose a method for generating contrastive explanations, which provide human-centric insights by comparing a system's proposed solution against relevant alternatives. To evaluate this, we developed a framework that uses visual and textual cues to highlight key objectives from a state-of-the-art collision avoidance system. An exploratory user study with four experienced marine officers suggests that contrastive explanations support the understanding of the system's objectives. However, our findings also reveal that while these explanations are highly valuable in complex multi-vessel encounters, they can increase cognitive workload, suggesting that future maritime interfaces may benefit most from demand-driven or scenario-specific explanation strategies.

Problem

• maritime autonomous navigation
• collision avoidance
• contrastive explanations
• human supervision
• explainable AI

Innovation

• contrastive explanations
• maritime autonomous navigation
• human-supervised AI
• collision avoidance
• explainable AI