A multi-agent system for coordinating vessel traffic

• Main Authors: TENG, Teck-Hou, LAU, Hoong Chuin, KUMAR, Akshat
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2017
• Subjects: Autonomous agents; Efficiency; Geographical regions; Iterative methods; Problem solving; Waterway transportation; Singapore; Artificial Intelligence and Robotics; Computer Sciences; Operations Research, Systems Engineering and Industrial Engineering; Transportation
• Online Access: https://ink.library.smu.edu.sg/sis_research/3863; https://ink.library.smu.edu.sg/context/sis_research/article/4865/viewcontent/p1814.pdf
• Institution: Singapore Management University

Environmental, regulatory and resource constraints affects the safety and efficiency of vessels navigating in and out of the ports. Movement of vessels under such constraints must be coordinated for improving safety and efficiency. Thus, we frame the vessel coordination problem as a multi-agent path-finding (MAPF) problem. We solve this MAPF problem using a Coordinated Path-Finding (CPF) algorithm. Based on the local search paradigm, the CPF algorithm improves on the aggregated path quality of the vessels iteratively. Outputs of the CPF algorithm are the coordinated trajectories. The Vessel Coordination Module (VCM) described here is the module encapsulating our MAPF-based approach for coordinating vessel traffic. Our demonstration of VCM is conducted using two maritime scenarios of vessel traffic at two geographical regions of Singapore Waters.