Cooperative multi-task traversing with complex marine environment for multiple unmanned surface vehicles inspired by membrane computing

This paper deals with cooperative multi-task traversing scheme for multiple unmanned surface vehicles (USVs) under complex marine environments. Due to the dynamic characteristics of the marine environment, the factors including the assignment efficiency, path length, safety and optimization cost are critical issues that cannot be ignored in cooperative multi-task traversing for multi-USV. The main contributions of this paper are as follows: (1) Based on genetic algorithm, a membrane reward-mechanism genetic-optimization (M-RM-GO) algorithm that can enhance the task assignment speed and achieve priority is proposed to solve the cooperative multi-task assignment problem. (2) In the case of marine environmental loads, a deflection factor is introduced into the fast marching method to make the avoidance path in the traversal process adapt to the dynamic characteristics of environmental loads. (3) In order to decrease the optimization cost of the above collision avoidance paths, an avoidance path optimization strategy with membrane structure is designed. Comparative studies with the state-of-the-art methods demonstrate that the proposed cooperative multiple task traversing scheme has superior performance. •Based on genetic algorithm, a membrane reward mechanism genetic-optimization (M-RM-GO) algorithm to enhance the task assignment speed and achieve priority.•In the case of marine environmental loads, a deflection factor is introduced into the fast marching method.•In order to decrease the optimization cost of the above collision avoidance paths, an avoidance path optimization strategy with membrane structure is designed.