Risk-based path planning for autonomous underwater vehicles in an oil spill environment

Autonomous underwater vehicles (AUVs) are advanced platforms for detecting and mapping oil spills in deep water. However, their applications in complex spill environments have been hindered by the risk of vehicle loss. Path planning for AUVs is an effective technique for mitigating such risks and ensuring safer routing. Yet pre-vious studies did not address path searching problems for AUVs based on probabilistic risk reasoning. This study aims to propose an offboard risk-based path planning approach for AUVs operating in an oil spill environment. A risk model based on the Bayesian network was developed for probabilistic reasoning of risk states given varied environmental observations. This risk model further assisted in generating a spatially-distributed risk map covering a potential mission area. An A*-based searching algorithm was then employed to plan an optimal-risk path through the constructed risk map. The proposed planner was applied in a case study with a Slocum G1 Glider in a real-world spill environment around Baffin Bay. Simulation results proved that the optimal-risk planner outperforms in risk mitigation while achieving competitive path lengths and mission efficiency. The proposed method is not constrained to AUVs but can be adapted to other marine robotic systems.