Trajectory Optimization for Safe Navigation in Maritime Traffic Using Historical Data

Authors Chaithanya Basrur, Arambam James Singh, Arunesh Sinha, Akshat Kumar, T. K. Satish Kumar

Thumbnail PDF


  • Filesize: 3.65 MB
  • 17 pages

Document Identifiers

Author Details

Chaithanya Basrur
  • Singapore Management University, Singapore
Arambam James Singh
  • National University of Singapore, Singapore
Arunesh Sinha
  • Singapore Management University, Singapore
Akshat Kumar
  • Singapore Management University, Singapore
T. K. Satish Kumar
  • University of Southern California, Los Angeles, CA, USA

Cite AsGet BibTex

Chaithanya Basrur, Arambam James Singh, Arunesh Sinha, Akshat Kumar, and T. K. Satish Kumar. Trajectory Optimization for Safe Navigation in Maritime Traffic Using Historical Data. In 28th International Conference on Principles and Practice of Constraint Programming (CP 2022). Leibniz International Proceedings in Informatics (LIPIcs), Volume 235, pp. 5:1-5:17, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2022)


Increasing maritime trade often results in congestion in busy ports, thereby necessitating planning methods to avoid close quarter risky situations among vessels. Rapid digitization and automation of port operations and vessel navigation provide unique opportunities for significantly improving navigation safety. Our key contributions are as follows. First, given a set of future candidate trajectories for vessels in a traffic hotspot zone, we develop a multiagent trajectory optimization method to choose trajectories that result in the best overall close quarter risk reduction. Our novel MILP-based optimization method is more than an order-of-magnitude faster than a standard MILP for this problem, and runs in near real-time. Second, although automation has improved in maritime operations, current vessel traffic systems (in our case study of a busy Asian port) predict only a single future trajectory of a vessel based on linear extrapolation. Therefore, using historical data we learn a generative model that predicts multiple possible future trajectories of each vessel in a given traffic hotspot, reflecting past vessel movement patterns, and integrate it with our trajectory optimizer. Third, we validate our trajectory optimization and generative model extensively using a real world maritime traffic dataset containing 6 million Automated Identification System (AIS) data records detailing vessel movements over 1.5 years from one of the world’s busiest ports, demonstrating effective risk reduction.

Subject Classification

ACM Subject Classification
  • Computing methodologies → Multi-agent planning
  • Multi-Agent Path Coordination
  • Maritime Traffic Control


  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    PDF Downloads


  1. Lucas Agussurja, Akshat Kumar, and Hoong Chuin Lau. Resource-constrained scheduling for maritime traffic management. In AAAI Conference, 2018. Google Scholar
  2. Alexandre Alahi, Kratarth Goel, Vignesh Ramanathan, Alexandre Robicquet, Li Fei-Fei, and Silvio Savarese. Social lstm: Human trajectory prediction in crowded spaces. In IEEE conference on CVPR, pages 961-971, 2016. Google Scholar
  3. Christophe Andrieu, Nando De Freitas, Arnaud Doucet, and Michael I Jordan. An introduction to mcmc for machine learning. Machine learning, 50(1):5-43, 2003. Google Scholar
  4. Saumya Bhatnagar, Akshat Kumar, and Hoong Chuin Lau. Decision making for improving maritime traffic safety using constraint programming. In Proceedings of the 28th IJCAI, 2019. Google Scholar
  5. S. Choudhury, K. Solovey, M. J. Kochenderfer, and M. Pavone. Efficient large-scale multi-drone delivery using transit networks. In IEEE ICRA, pages 4543-4550, 2020. Google Scholar
  6. Lei Du, Floris Goerlandt, and Pentti Kujala. Review and analysis of methods for assessing maritime waterway risk based on non-accident critical events detected from ais data. Reliability Engineering and System Safety, 200, 2020. Google Scholar
  7. Haoqiang Fan, Hao Su, and Leonidas J Guibas. A point set generation network for 3d object reconstruction from a single image. In IEEE conference on CVPR, pages 605-613, 2017. Google Scholar
  8. Futurenautics. Autonomous ships | white paper., 2016.
  9. Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. Generative adversarial networks. Communications of the ACM, 63(11):139-144, 2020. Google Scholar
  10. Agrim Gupta, Justin Johnson, Li Fei-Fei, Silvio Savarese, and Alexandre Alahi. Social gan: Socially acceptable trajectories with generative adversarial networks. In IEEE Conference on CVPR, pages 2255-2264, 2018. Google Scholar
  11. Sepp Hochreiter and Jürgen Schmidhuber. Long short-term memory. Neural Computation, 9(8):1735-1780, 1997. Google Scholar
  12. IMO. E-navigation., 2019.
  13. International Maritime Organization. Electronic Nautical Charts (ENC) and Electronic Chart Display and Information Systems (ECDIS)., 2022.
  14. Laura Leal-Taixé, Michele Fenzi, Alina Kuznetsova, Bodo Rosenhahn, and Silvio Savarese. Learning an image-based motion context for multiple people tracking. In IEEE Conference on CVPR, pages 3542-3549, 2014. Google Scholar
  15. Namhoon Lee, Wongun Choi, Paul Vernaza, Christopher B Choy, Philip HS Torr, and Manmohan Chandraker. Desire: Distant future prediction in dynamic scenes with interacting agents. In IEEE Conference on CVPR, pages 336-345, 2017. Google Scholar
  16. H. Ma, C. Tovey, G. Sharon, T. K. S. Kumar, and S. Koenig. Multi-agent path finding with payload transfers and the package-exchange robot-routing problem. In AAAI Conference, pages 3166-3173, 2016. Google Scholar
  17. Faris Mokhtar. Busy shipping lane’s narrow passageway hard for vessels to navigate., 2017.
  18. Robert Morris, Corina S. Pasareanu, Kasper Søe Luckow, Waqar Malik, Hang Ma, T. K. Satish Kumar, and Sven Koenig. Planning, scheduling and monitoring for airport surface operations. In AAAI Workshop on Planning for Hybrid Systems, 2016. Google Scholar
  19. MPA. Vessel Traffic Information System., 2021.
  20. MPA Singapore. Over 250 participate in Joint Oil Spill Exercise to Test Responsiveness to Oil Spills at Sea., 2018.
  21. International Maritime Organization. Autonomous shipping. URL:
  22. Stefano Pellegrini, Andreas Ess, and Luc Van Gool. Improving data association by joint modeling of pedestrian trajectories and groupings. In European conference on computer vision, pages 452-465. Springer, 2010. Google Scholar
  23. Henrik Ringbom. Regulating autonomous ships - concepts, challenges and precedents. Ocean Development & International Law, 50(2-3):141-169, 2019. Google Scholar
  24. Rolls-Royce. Remote and autonomous ship - The next steps., 2016.
  25. David Silver. Cooperative pathfinding. In AIIDE, pages 117-122, 2005. Google Scholar
  26. Arambam James Singh, Akshat Kumar, and Hoong Chuin Lau. Hierarchical multiagent reinforcement learning for maritime traffic management. In Proceedings of the 19th AAMAS, 2020. Google Scholar
  27. Arambam James Singh, Duc Thien Nguyen, Akshat Kumar, and Hoong Chuin Lau. Multiagent decision making for maritime traffic management. In AAAI Conference, 2019. Google Scholar
  28. Roni Stern, Nathan R. Sturtevant, Ariel Felner, Sven Koenig, Hang Ma, Thayne T. Walker, Jiaoyang Li, Dor Atzmon, Liron Cohen, T. K. Satish Kumar, Roman Barták, and Eli Boyarski. Multi-agent pathfinding: Definitions, variants, and benchmarks. In SoCS, pages 151-159, 2019. Google Scholar
  29. Teck-Hou Teng, Hoong Chuin Lau, and Akshat Kumar. Coordinating vessel traffic to improve safety and efficiency. In Proceedings of the 16th AAMAS, pages 141-149. ACM, 2017. Google Scholar
  30. Leo Törnqvist, Pentti Vartia, and Yrjö O Vartia. How should relative changes be measured? The American Statistician, 39(1):43-46, 1985. Google Scholar
  31. Kevin Varley. Ships Queues Worsen Port Delays From Singapore to Piraeus., 2021.
  32. Peter R. Wurman, Raffaello D'Andrea, and Mick Mountz. Coordinating hundreds of cooperative, autonomous vehicles in warehouses. AI Magazine, 29(1):9-20, 2008. Google Scholar
  33. Jinsung Yoon, Daniel Jarrett, and Mihaela van der Schaar. Time-series generative adversarial networks. Advances in Neural Information Processing Systems, 32:5508-5518, 2019. Google Scholar
  34. J. Yu and S. M. LaValle. Structure and intractability of optimal multi-robot path planning on graphs. In AAAI Conference, pages 1443-1449, 2013. Google Scholar
  35. Jinfen Zhang, Tiago A Santos, C Guedes Soares, and Xinping Yan. Sequential ship traffic scheduling model for restricted two-way waterway transportation. Proceedings of the Institution of Mechanical Engineers, Part M: Journal of Engineering for the Maritime Environment, 231(1):86-97, 2017. Google Scholar
Questions / Remarks / Feedback

Feedback for Dagstuhl Publishing

Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail