TY - GEN
T1 - Cooperative Route Planning Framework for Multiple Distributed Assets in Maritime Applications
AU - Nikookar, Sepideh
AU - Sakharkar, Paras
AU - Somasunder, Sathyanarayanan
AU - Basu Roy, Senjuti
AU - Bienkowski, Adam
AU - MacEsker, Matthew
AU - Pattipati, Krishna R.
AU - Sidoti, David
N1 - Publisher Copyright:
© 2022 ACM.
PY - 2022/6/10
Y1 - 2022/6/10
N2 - This work formalizes the Route Planning Problem (RPP), wherein a set of distributed assets (e.g., ships, submarines, unmanned systems) simultaneously plan routes to optimize a team goal (e.g., find the location of an unknown threat or object in minimum time and/or fuel consumption) while ensuring that the planned routes satisfy certain constraints (e.g., avoiding collisions and obstacles). This problem becomes overwhelmingly complex for multiple distributed assets as the search space grows exponentially to design such plans. The RPP is formalized as a Team Discrete Markov Decision Process (TDMDP) and we propose a Multi-agent Multi-objective Reinforcement Learning (MaMoRL) framework for solving it. We investigate challenges in deploying the solution in real-world settings and study approximation opportunities. We experimentally demonstrate MaMoRL's effectiveness on multiple real-world and synthetic grids, as well as for transfer learning. MaMoRL is deployed for use by the Naval Research Laboratory-Marine Meteorology Division (NRL-MMD), Monterey, CA.
AB - This work formalizes the Route Planning Problem (RPP), wherein a set of distributed assets (e.g., ships, submarines, unmanned systems) simultaneously plan routes to optimize a team goal (e.g., find the location of an unknown threat or object in minimum time and/or fuel consumption) while ensuring that the planned routes satisfy certain constraints (e.g., avoiding collisions and obstacles). This problem becomes overwhelmingly complex for multiple distributed assets as the search space grows exponentially to design such plans. The RPP is formalized as a Team Discrete Markov Decision Process (TDMDP) and we propose a Multi-agent Multi-objective Reinforcement Learning (MaMoRL) framework for solving it. We investigate challenges in deploying the solution in real-world settings and study approximation opportunities. We experimentally demonstrate MaMoRL's effectiveness on multiple real-world and synthetic grids, as well as for transfer learning. MaMoRL is deployed for use by the Naval Research Laboratory-Marine Meteorology Division (NRL-MMD), Monterey, CA.
KW - data management for ai
KW - function approximation
KW - multi-agent reinforcement learning
KW - route planning
KW - scalable solution design
UR - http://www.scopus.com/inward/record.url?scp=85132707036&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85132707036&partnerID=8YFLogxK
U2 - 10.1145/3514221.3526131
DO - 10.1145/3514221.3526131
M3 - Conference contribution
AN - SCOPUS:85132707036
T3 - Proceedings of the ACM SIGMOD International Conference on Management of Data
SP - 1518
EP - 1527
BT - SIGMOD 2022 - Proceedings of the 2022 International Conference on Management of Data
PB - Association for Computing Machinery
T2 - 2022 ACM SIGMOD International Conference on the Management of Data, SIGMOD 2022
Y2 - 12 June 2022 through 17 June 2022
ER -