Dynamic game collision avoidance decision-making for autonomous and manned ships

ObjectiveThis study investigates the interactive collision avoidance （CA） problem of autonomous and manned ships in mixed navigation scenarios in order to achieve the efficient collision avoidance and safe navigation of ships. To this end, a multi-agent interactive ship dynamic game collision avoidance decision-making method is proposed. MethodsAccording to sailing practices, the ship collision avoidance problem in mixed navigation environments is analyzed and understood, and the ship encounter situation and collision risk are quantified on the basis of the International Regulations for Preventing Collisions at Sea (COLREGs). Dynamic game theory is introduced to model individual ships with collision risk as participants with independent thinking in the game, and the course changes of ships are taken as the strategy for determining the optimal action sequence under the constraints of ship safety and social and economic benefits. Different ship maneuvering modes are introduced to the simulation experiment, and the effectiveness of the collision avoidance decision-making method is verified using Python. ResultsThe results show that this method can realize the safe encounter of multiple ships in a mixed navigation environment of autonomous and manned ships, and each ship can adjust its behavior strategy to achieve safe avoidance when facing target ships with different sailing styles. ConclusionThis study can provide valuable references for the collision avoidance decision-making of autonomous and manned ships.