Answers are grounded in this paper and cite their sources.
Demonstrates improved decision-making and mission success in autonomous underwater vehicles, suggesting a new approach.
During underwater operations, Autonomous Underwater Vehicles (AUVs) operate with minimal human intervention, necessitating robust risk-informed decision-making to ensure safety. Existing decision-making frameworks, however, exhibit a gap between deliberation and execution, that limits their applicability to complex, multi-phase missions. To bridge this gap, a Behaviour Tree (BT)-based framework that integrates knowledge representation with reactive execution is proposed. Across different mission phases, the proposed framework reconfigures tasks based on both risk levels and the action dependencies explicitly represented by the BT. A hierarchical BT structure, aligned with task elements, is designed to encapsulate task knowledge. Furthermore, a task-decision tree incorporating subsumption and fault-tolerant strategies is constructed to fully leverage BT reactivity. A case study on a multi-phase mine countermeasure mission demonstrates that the proposed model effectively utilizes task knowledge to enable correct decision-making, and improves the mission success rate in recoverable anomaly scenarios.
No takes yet. Share an insight, caveat, or question.
Lin et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: