Ship-GAN: Generative modeling based maritime traffic simulator

• Main Authors: BASRUR, Chaithanya, SINGH, Arambam James, SINHA, Arunesh, KUMAR, Akshat
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2021
• Subjects: Generative adversarial networks; Maritime traffic simulation; Artificial Intelligence and Robotics
• Online Access: https://ink.library.smu.edu.sg/sis_research/6902; https://ink.library.smu.edu.sg/context/sis_research/article/7905/viewcontent/Ship_GAN.pdf
• Institution: Singapore Management University

Modeling vessel movement in a maritime environment is an extremely challenging task given the complex nature of vessel behavior. Several existing multiagent maritime decision making frameworks require access to an accurate traffic simulator. We develop a system using electronic navigation charts to generate realistic and high fidelity vessel traffic data using Generative Adversarial Networks (GANs). Our proposed Ship-GAN uses a conditional Wasserstein GAN to model a vessel's behavior. The generator can simulate the travel time of vessels across different maritime zones conditioned on vessels' speeds and traffic intensity. Furthermore, it can be used as an accurate simulator for prior decision making approaches for maritime traffic coordination, which used less accurate model than our approach. Experiments performed on the historical data from heavily trafficked Singapore strait show that our Ship- GAN system generates data whose statistical distribution is close to the real data distribution, and better fit than prior methods. © 2021 International Foundation for Autonomous Agents and Multiagent Systems