AgentC: Employing Computational Modeling, Simulation, and Optimization to Fight Maritime Piracy
[NEW] We are looking for partners that would help us bring our results closer to real-world deployment.
TopMotivation
Around 90% of the world trade is transported by the international shipping industry. Any disruption to world shipping lanes thus has a significant impact on the world economy. The recent steep rise of maritime piracy represents one of the biggest threats to maritime shipping in decades. Even though various countermeasures have been put into effect, no solution has been found yet, and the pirates grow stronger with each year. Only in 2010, 53 cargo-vessels were hijacked and 1181 crew members held hostage. The situation has been further deteriorating in 2011, with further steep increases in attack numbers, pirate brutality and ransom paid, which reached an all-time high in April 2011 with $13M paid for the release of the Greek owned oil tanker Irene SL.
TopResearch Objectives
We explore how multi-agent systems, a branch of artificial intelligence, can be used to improve maritime security, with particular focus on fighting maritime piracy. Our ultimate objective is to develop an integrated set of algorithmic techniques for maximizing transit security given the limited protection resources available. We achieve this by improving the coordination of the movement of merchant vessels and naval patrols, while taking into account the behavior of pirates.
In order to evaluate the proposed techniques and to gain better insight into the structure and dynamics of maritime piracy, we also employ agent-based simulation and machine learning techniques to build dynamic models of maritime transit and to model and assess piracy risk.
All methods are implemented within a modular software testbed featuring a scalable simulation engine, connectors to real-world data sources and powerful visualization front-end based on Google Earth.
TopResults and Tools
Vessel trajectories data
Maritime traffic simulation
Piracy risk estimation
Risk-minimizing transit and patrol routing
Data and Analysis
- Maritime Domain Data -- We have assembled real-world data sources concerning key aspects of maritime transit, including AIS vessel trajectories, transit corridors, piracy incidents etc.
- Piracy Risk Modeling and Assessment -- We have applied data mining and machine learning on real-world pirate incidents data and derived models predicting piracy risk in different regions.
Simulation
- Vessel Behavior Models -- We have developed a highly-detailed agent-based model of each vessel class. The model uses real-world data and it is based on Finite State Machines.
- Maritime Simulation Framework -- We have developed a modular maritime simulation framework utilizing know-how of our center, with a maritime system simulation being at its core. The simulation allows to evaluate various what-if scenarios and effectiveness of deployed or proposed countermeasures.
- What-if Scenario Analyzer -- Using the maritime simulation framework, we are able to evaluate effectiveness of various piracy countermeasures, including different grouping schemes and extended corridor placements.
Optimization
- Optimization of Group Transit Schedules -- We have designed an optimized group transit scheme which results in shorter delay and higher speed of travel when transiting pirate waters (e.g. the Gulf of Aden).
- Intelligent Route Planner -- We have developed a bi-objective route planner optimizing overall route cost with respect to the route distance and to the risk of incident along the route.
- Optimal Patrol Deployment and Merchant Vessel Protection -- We have applied latest results in game theory and security games to propose deployment of naval patrols in the area and developed stochastic patrolling policies to effectively cover multiple mobile targets and maximize deterrence of naval units.
Collaboration Partners
We are looking for partners that would help us bring our results closer to real-world deployment. This includes not only maritime security domain experts and technology providers as well as potential users of the system or its parts from the ranks of ship owners, policy makers and security services providers.
TopTeam
Michal Jakob (project leader, contact person), Ondrej Vanek, Ondrej Hrstka, Ondrej Pelech, Branislav Bosansky and Michal Pechoucek (principal investigator)
TopPublications
Papers
- [NEW] Michal Jakob, Ondrej Vanek, Ondrej Hrstka and Michal Pechoucek: Agents vs. Pirates: Multi-Agent Simulation and Optimization to Fight Maritime Piracy. In 12th International Conference on Autonomous Agents and Multiagent Systems (to appear). 2012. PDF
- Ondrej Vanek, Michal Jakob, Ondrej Hrstka and Michal Pechoucek: Using Multi-Agent Simulation to Improve the Security of Maritime Transit. In Postproceedings of 12th International Workshop on Multi-Agent-Based Simulation (MABS). Springer Verlag, 2011. PDF
- Ondřej Vaněk, Michal Pěchouček, Michal Jakob, Branislav Bošanský a Viliam Lisý: Agentní simulací proti somálským pirátům. Scientific American, České vydání. 2011. PDF
- Michal Jakob, Ondrej Vanek, Ondrej Hrstka, and Michal Pechoucek. AgentC: Agent-based System for Securing Maritime Transit (Demonstration). In Proceedings of Tenth International Conference on Autonomous Agents and Multiagent Systems. 2011. PDF
- Branislav Bosansky, Viliam Lisy, Michal Jakob and Michal Pechoucek: Computing Time-Dependent Policies for Patrolling Games with Mobile Targets. In Proceedings of Tenth International Conference on Autonomous Agents and Multiagent Systems. 2011. PDF
- Ondrej Vanek and Michal Jakob and Viliam Lisy and Branislav Bosansky and Michal Pechoucek: Iterative Game-theoretic Route Selection for Hostile Area Transit and Patrolling. In Proceedings of Tenth International Conference on Autonomous Agents and Multiagent Systems. 2011.PDF
- Michal Jakob and Ondrej Vanek and Michal Pechoucek: Using Agents to Improve International Maritime Transport Security. IEEE Intelligent Systems. 2011, vol. 26, p. 90-96. ISSN 1541-1672.PDF
- Ondrej Vanek and Branislav Bosansky and Michal Jakob and Michal Pechoucek: Transiting Areas Patrolled by a Mobile Adversary. In Proceedings of 2010 IEEE Conference on Computational Intelligence and Games. 2010. PDF.
- Michal Jakob and Ondrej Vanek and Stepan Urban and Petr Benda and Michal Pechoucek: Employing Agents to Improve the Security of International Maritime Transport. In Proceedings of AAMAS 2010 Workshop on Agents In Traffic and Transportation. 2010. PDF
- Stepan Urban, Michal Jakob, and Michal Pechoucek: Probabilistic modeling of mobile agents’ trajectories. In Proceedings of the International Workshop on Agents and Data Mining Interaction (ADMI 2010), May 2010. PDF
- Michal Jakob and Ondrej Vanek and Stepan Urban and Petr Benda and Michal Pechoucek: AgentC: Agent-based Testbed for Adversarial Modeling and Reasoning in the Maritime Domain (Demo). In Proceedings of The Ninth International Conference on Autonomous Agents and Multiagent Systems. 2010. PDF
- Ondrej Vanek: Agent-based Simulation of the Maritime Domain. In POSTER 2010, 14th International Student Conference on Electrical Engineering. CVUT, Fakulta elektrotechnicka, 2010. PDF
- Ondrej Vanek: Agent-based Simulation of the Maritime Domain. Acta Polytechnica. 2010, vol. 50, p. 94-99. PDF
Presentations
- [NEW] Michal Jakob: Modelling and Optimisation of Counter-Piracy Operations. Presented at 11th Official Combating Piracy Update, Hamburg, 25 Apr 2012 PPTX | PDF
Reports
- Michal Jakob and Ondrej Vanek and Branislav Bosansky and Ondrej Hrstka and Vojtech Krizek and Stepan Urban and Petr Benda and Michal Pechoucek: Adversarial Modeling and Reasoning in the Maritime Domain (Year 2 Report). 2010.PDF
- Michal Jakob and Ondrej Vanek and Stepan Urban and Petr Benda and Michal Pechoucek: Adversarial Modeling and Reasoning in the Maritime Domain (Year 1 Report). 2009.PDF
Posters
- AgentC: Agent-based System for Securing Maritime Transit (May 2011)
- Iterative Game-theoretic Route Selection for Hostile Area Transit and Patrolling (May 2011)
- Computing Time-Dependent Policies for Patrolling Games with Mobile Targets (May 2011)
Acknowledgements
The work presented is supported by the Office of Naval Research project no. N00014-09-1-0537 and by the Czech Ministry of Education, Youth and Sports under Research Programme no. MSM6840770038: Decision Making and Control for Manufacturing III.
Top