Hierarchical multiagent reinforcement learning for maritime traffic management

• Main Authors: SINGH, Arambam James, KUMAR, Akshat, LAU, Hoong Chuin
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2020
• Subjects: Autonomous agents; Multi agent systems; Reinforcement learning; Service vessels; Waterway transportation; Artificial Intelligence and Robotics; Operations Research, Systems Engineering and Industrial Engineering; Transportation
• Online Access: https://ink.library.smu.edu.sg/sis_research/5403; https://ink.library.smu.edu.sg/context/sis_research/article/6406/viewcontent/p1278.pdf
• Institution: Singapore Management University

Increasing global maritime traffic coupled with rapid digitization and automation in shipping mandate developing next generation maritime traffic management systems to mitigate congestion, increase safety of navigation, and avoid collisions in busy and geographically constrained ports (such as Singapore's). To achieve these objectives, we model the maritime traffic as a large multiagent system with individual vessels as agents, and VTS (Vessel Traffic Service) authority as a regulatory agent. We develop a hierarchical reinforcement learning approach where vessels first select a high level action based on the underlying traffic flow, and then select the low level action that determines their future speed. We exploit the nature of collective interactions among agents to develop a policy gradient approach that can scale up to large real world problems. We also develop an effective multiagent credit assignment scheme that significantly improves the convergence of policy gradient. Extensive empirical results on synthetic and real world data from one of the busiest port in the world show that our approach consistently performs significantly better than the previous best approach.