Agent capability in persistent mission planning using approximate dynamic programming
This paper presents an extension of our previous work on the persistent surveillance problem. An extended problem formulation incorporates real-time changes in agent capabilities as estimated by an onboard health monitoring system in addition to the existing communication constraints, stochastic se...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers
2010
|
| Online Access: | http://hdl.handle.net/1721.1/58888 https://orcid.org/0000-0001-8576-1930 |
| _version_ | 1826198947457138688 |
|---|---|
| author | Bethke, Brett M. Redding, Josh How, Jonathan P. Vavrina, Matthew A. Vian, John |
| author2 | Massachusetts Institute of Technology. Aerospace Controls Laboratory |
| author_facet | Massachusetts Institute of Technology. Aerospace Controls Laboratory Bethke, Brett M. Redding, Josh How, Jonathan P. Vavrina, Matthew A. Vian, John |
| author_sort | Bethke, Brett M. |
| collection | MIT |
| description | This paper presents an extension of our previous work on the persistent surveillance problem. An extended problem formulation incorporates real-time changes in agent capabilities as estimated by an onboard health monitoring system in addition to the existing communication constraints, stochastic sensor failure and fuel flow models, and the basic constraints of providing surveillance coverage using a team of autonomous agents. An approximate policy for the persistent surveillance problem is computed using a parallel, distributed implementation of the approximate dynamic programming algorithm known as Bellman Residual Elimination. This paper also presents flight test results which demonstrate that this approximate policy correctly coordinates the team to simultaneously provide reliable surveillance coverage and a communications link for the duration of the mission and appropriately retasks agents to maintain these services in the event of agent capability degradation. |
| first_indexed | 2024-09-23T11:12:24Z |
| format | Article |
| id | mit-1721.1/58888 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T11:12:24Z |
| publishDate | 2010 |
| publisher | Institute of Electrical and Electronics Engineers |
| record_format | dspace |
| spelling | mit-1721.1/588882022-09-27T17:50:01Z Agent capability in persistent mission planning using approximate dynamic programming Bethke, Brett M. Redding, Josh How, Jonathan P. Vavrina, Matthew A. Vian, John Massachusetts Institute of Technology. Aerospace Controls Laboratory Massachusetts Institute of Technology. Department of Aeronautics and Astronautics How, Jonathan P. Bethke, Brett M. Redding, Josh How, Jonathan P. This paper presents an extension of our previous work on the persistent surveillance problem. An extended problem formulation incorporates real-time changes in agent capabilities as estimated by an onboard health monitoring system in addition to the existing communication constraints, stochastic sensor failure and fuel flow models, and the basic constraints of providing surveillance coverage using a team of autonomous agents. An approximate policy for the persistent surveillance problem is computed using a parallel, distributed implementation of the approximate dynamic programming algorithm known as Bellman Residual Elimination. This paper also presents flight test results which demonstrate that this approximate policy correctly coordinates the team to simultaneously provide reliable surveillance coverage and a communications link for the duration of the mission and appropriately retasks agents to maintain these services in the event of agent capability degradation. United States. Air Force Office of Scientific Research (grant FA9550-08-1-0086) Boeing Scientific Research Laboratories Hertz Foundation 2010-10-06T14:11:43Z 2010-10-06T14:11:43Z 2010-07 2010-06 Article http://purl.org/eprint/type/ConferencePaper 978-1-4244-7426-4 0743-1619 INSPEC Accession Number: 11509070 http://hdl.handle.net/1721.1/58888 Bethke, B. et al. “Agent capability in persistent mission planning using approximate dynamic programming.” American Control Conference (ACC), 2010. 2010. 1623-1628. ©2010 IEEE. https://orcid.org/0000-0001-8576-1930 en_US http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5531611&isnumber=5530425 Proceedings of the American Control Conference, 2010 Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf Institute of Electrical and Electronics Engineers IEEE |
| spellingShingle | Bethke, Brett M. Redding, Josh How, Jonathan P. Vavrina, Matthew A. Vian, John Agent capability in persistent mission planning using approximate dynamic programming |
| title | Agent capability in persistent mission planning using approximate dynamic programming |
| title_full | Agent capability in persistent mission planning using approximate dynamic programming |
| title_fullStr | Agent capability in persistent mission planning using approximate dynamic programming |
| title_full_unstemmed | Agent capability in persistent mission planning using approximate dynamic programming |
| title_short | Agent capability in persistent mission planning using approximate dynamic programming |
| title_sort | agent capability in persistent mission planning using approximate dynamic programming |
| url | http://hdl.handle.net/1721.1/58888 https://orcid.org/0000-0001-8576-1930 |
| work_keys_str_mv | AT bethkebrettm agentcapabilityinpersistentmissionplanningusingapproximatedynamicprogramming AT reddingjosh agentcapabilityinpersistentmissionplanningusingapproximatedynamicprogramming AT howjonathanp agentcapabilityinpersistentmissionplanningusingapproximatedynamicprogramming AT vavrinamatthewa agentcapabilityinpersistentmissionplanningusingapproximatedynamicprogramming AT vianjohn agentcapabilityinpersistentmissionplanningusingapproximatedynamicprogramming |