Path planning algorithm for ship collisions avoidance in environment with changing strategy of dynamic obstacles

Abstract

In this paper a path planning algorithm for the ship collision avoidance is presented. Tested algorithm is used to determine close to optimal ship paths taking into account changing strategy of dynamic obstacles. For this purpose a path planning problem is defined. A specific structure of the individual path and fitness function is presented. Principle of operation of evolutionary algorithm and based on it dedicated application vEP/N++ is described. Using presented algorithm the simulations on close-to-real sea environment is performed. Tested environment presents the problem of avoiding one static obstacle representing island and two dynamic objects representing strange ships. Obtained results proof that used approach allows to calculate efficient and close-to-optimal path for marine vessel in close-to-real time.