Rapidly Estimating Swarm Resource Needs Through Autonomous Simulation
The maritime industry spends significant time and resources accomplishing long lasting collaborative tasks such as search and rescue or ocean surveying. Autonomous swarm ships’ ability to scale rapidly and operate with limited resources allows them to outperform conventional crewed ships at these co...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Published: |
Massachusetts Institute of Technology
2023
|
| Online Access: | https://hdl.handle.net/1721.1/151377 |
| _version_ | 1811091503539290112 |
|---|---|
| author | Young, Eric |
| author2 | Benjamin, Michael |
| author_facet | Benjamin, Michael Young, Eric |
| author_sort | Young, Eric |
| collection | MIT |
| description | The maritime industry spends significant time and resources accomplishing long lasting collaborative tasks such as search and rescue or ocean surveying. Autonomous swarm ships’ ability to scale rapidly and operate with limited resources allows them to outperform conventional crewed ships at these collaborative operations. Despite their incredible potential, perpetually operating productive autonomous swarms creates significant logistic challenges. This thesis aims to solve these problems. Specifically, this thesis aims to maximize collaborative swarm productivity, by predicting and managing robot resource needs, using operations theory, simulation, and machine learning.
Maximizing swarm productivity first requires developing a common scenario to measure productivity. Drawing from multi-robot patrol research, this thesis implements two resource-aware multi-robot patrol missions in MOOS-IvP. In each mission, vehicles perpetually patrol a grid and must periodically break patrol formation to refuel at a depot. Missions measure their performance based on how frequently robots visit each portion of the mission operating area (grid idle time) and how much area each robot controls (average Voronoi polygon area). With a common patrol scenario developed, this thesis then simulates patrol missions using different vehicle and depot parameters to generate a broad performance dataset.
Finally, this thesis develops a method to predict future mission performance from the simulated productivity dataset. Simulated mission data is post processed and used to train XGBoost models. Compared to mission simulations, these models take far less time to produce while still showing planners what performance and vehicle output they can expect from a given mission. |
| first_indexed | 2024-09-23T15:03:24Z |
| format | Thesis |
| id | mit-1721.1/151377 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T15:03:24Z |
| publishDate | 2023 |
| publisher | Massachusetts Institute of Technology |
| record_format | dspace |
| spelling | mit-1721.1/1513772023-08-01T03:15:54Z Rapidly Estimating Swarm Resource Needs Through Autonomous Simulation Young, Eric Benjamin, Michael Massachusetts Institute of Technology. Department of Mechanical Engineering System Design and Management Program. The maritime industry spends significant time and resources accomplishing long lasting collaborative tasks such as search and rescue or ocean surveying. Autonomous swarm ships’ ability to scale rapidly and operate with limited resources allows them to outperform conventional crewed ships at these collaborative operations. Despite their incredible potential, perpetually operating productive autonomous swarms creates significant logistic challenges. This thesis aims to solve these problems. Specifically, this thesis aims to maximize collaborative swarm productivity, by predicting and managing robot resource needs, using operations theory, simulation, and machine learning. Maximizing swarm productivity first requires developing a common scenario to measure productivity. Drawing from multi-robot patrol research, this thesis implements two resource-aware multi-robot patrol missions in MOOS-IvP. In each mission, vehicles perpetually patrol a grid and must periodically break patrol formation to refuel at a depot. Missions measure their performance based on how frequently robots visit each portion of the mission operating area (grid idle time) and how much area each robot controls (average Voronoi polygon area). With a common patrol scenario developed, this thesis then simulates patrol missions using different vehicle and depot parameters to generate a broad performance dataset. Finally, this thesis develops a method to predict future mission performance from the simulated productivity dataset. Simulated mission data is post processed and used to train XGBoost models. Compared to mission simulations, these models take far less time to produce while still showing planners what performance and vehicle output they can expect from a given mission. Nav.E. S.M. 2023-07-31T19:35:14Z 2023-07-31T19:35:14Z 2023-06 2023-06-23T19:57:22.671Z Thesis https://hdl.handle.net/1721.1/151377 In Copyright - Educational Use Permitted Copyright retained by author(s) https://rightsstatements.org/page/InC-EDU/1.0/ application/pdf Massachusetts Institute of Technology |
| spellingShingle | Young, Eric Rapidly Estimating Swarm Resource Needs Through Autonomous Simulation |
| title | Rapidly Estimating Swarm Resource Needs Through Autonomous Simulation |
| title_full | Rapidly Estimating Swarm Resource Needs Through Autonomous Simulation |
| title_fullStr | Rapidly Estimating Swarm Resource Needs Through Autonomous Simulation |
| title_full_unstemmed | Rapidly Estimating Swarm Resource Needs Through Autonomous Simulation |
| title_short | Rapidly Estimating Swarm Resource Needs Through Autonomous Simulation |
| title_sort | rapidly estimating swarm resource needs through autonomous simulation |
| url | https://hdl.handle.net/1721.1/151377 |
| work_keys_str_mv | AT youngeric rapidlyestimatingswarmresourceneedsthroughautonomoussimulation |