Vol 77 No 2 77203

Abstract

With the gradual development of Maritime Autonomous Surface Ships (MASS), sea traffic is expected to remain in mixed navigation scenarios where autonomous and conventional ships operate concurrently. General collision avoidance methods and autonomous algorithms resolve encounter situations independently, but disparities in decision-making logic and approaches leave uncoordinated collision risks. This study constructs a bilateral negotiation model that enables autonomous and conventional ships to resolve uncoordinated collision avoidance through negotiation. The Zeuthen strategy is applied to ensure convergence and consensus in bargaining, while unilateral Bayesian learning is embedded to allow autonomous ships to estimate relevant information from conventional ships for improved negotiation capacity. The method exploits the computational capability of autonomous ships while imposing only lightweight information exchange requirements on conventional ships. Simulation experiments in representative mixed navigation scenarios demonstrate that the method resolves previously uncoordinated encounters, eliminates unnecessary evasive maneuvers by autonomous ships, and significantly improves overall navigational safety. This research addresses the limited studies on collaborative collision avoidance in such scenarios, reduces unnecessary active avoidance by autonomous ships, enhances the safety of decision-making for heterogeneous fleets, and provides a reference for the design and optimization of mixed navigation methods.