Collaborative Collision Avoidance for Autonomous Ships Using Informed Scenario-Based Model Predictive Control
Melih Akdağ, Thor I. Fossen, Tor Arne Johansen
Abstract
There exist several collision avoidance algorithms for autonomous ships. But the majority of them do not utilize information about other ships’ intentions, except for observed position and velocity. As the attention for large-sized autonomous ships to be used in logistics is growing, autonomous ships will need to collaborate and negotiate with other ships to prevent reactive and agile collision avoidance maneuvers. As a first step towards a collaborative collision avoidance algorithm, we implemented a reactive short-range algorithm by utilizing other ships’ trajectory plans. We aimed to improve the existing Scenario-Based Model Predictive Control (SB-MPC) algorithm by including route exchange-based trajectory predictions and called it the Informed SB-MPC. Additionally, we introduce adaptive and conditional parameter selection methods for the SB-MPC design. Hereby we implemented the compliance with the COLREGs Rule 18 concerning responsibility between vessels in addition to the existing Rules 13-17. The performance of the new method is demonstrated with head-on, crossing, overtaking, and multiple ships scenarios.