Multiagent Decision Making For Maritime Traffic Management
Speaker (s):
Arambam James SINGH
PhD Candidate
School of Information Systems
Singapore Management University
|
|
Date:
Time:
Venue:
|
|
January 24, 2019, Thursday
1:00pm - 1:30pm
Meeting Room 4.4, Level 4
School of Information Systems
Singapore Management University
80 Stamford Road
Singapore 178902
We look forward to seeing you at this research seminar.
|
|
About the Talk
We address the problem of maritime traffic management in busy waterways to increase the safety of navigation by reducing congestion. We model maritime traffic as a large multiagent systems with individual vessels as agents, and the port authority as the regulatory agent. We develop a maritime traffic simulator based on historical traffic data that incorporates realistic domain constraints such as uncertain and asynchronous movement of vessels. We also develop a traffic co- ordination approach that provides speed recommendation to vessels in different zones. We exploit the nature of collective interactions among agents to develop a scalable policy gradient approach that can scale up to real world problems. Empirical results on synthetic and real world problems show that our approach can significantly reduce congestion while keeping the traffic throughput high.
This a pre-conference talk for Association for the Advancement of Artificial Intelligence (AAAI-19).
About the Speaker
Arambam James SINGH is a PhD candidate at School of Information Systems, Singapore Management University advised by Assistant Prof. Akshat Kumar and Prof. Hoong Chuin Lau. His research focuses on deep reinforcement learning and optimisation for maritime traffic domain.
