Autonomous Machinery Management for Supervisory Risk Control Using Particle Swarm Optimization

Safe navigation for maritime autonomous surface ships (MASS) is a challenging task, and generally highly dependent on effective collaboration between multiple sub-systems in environments with various levels of uncertainty. This paper presents novel methodology combining risk-based optimal control path following machinery management (AMM) MASS supervisory risk control. Specifically, risk-aware particle swarm optimization (PSO) scheme utilizes “time-to-grounding” predictions based weather data electronic navigational charts (ENC) to simultaneously both the ship’s motion as well system operation (MSO) mode during transit. The proposed (ANS) comprised an online receding horizon that uses PSO approach from previous works, which produces dynamic respect grounding obstacles pre-planned path, subsequently given input line-of-sight guidance controller following. Moreover, MSO AMM selected assigned explicit segments along throughout horizon, effectively introduces into additional safety layer another dimension or resource minimization. performance resulting ANS demonstrated verified through simulations scenario human assessment generated paths. results show optimized paths are more efficient line how navigators would maneuver ship close nearby obstacles, compared works.