UAV Cooperative Control with Stochastic Risk Models
Risk and reward are fundamental concepts in the cooperative control of unmanned systems. This paper focuses on a constructive relationship between a cooperative planner and a learner in order to mitigate the learning risk while boosting the asymptotic performance and safety of agent behavior. Our fr...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2013
|
| Online Access: | http://hdl.handle.net/1721.1/81838 https://orcid.org/0000-0002-2508-1957 https://orcid.org/0000-0001-8576-1930 https://orcid.org/0000-0002-8293-0492 |
| _version_ | 1826189984484294656 |
|---|---|
| author | Geramifard, Alborz Redding, Joshua Roy, Nicholas How, Jonathan P. |
| author2 | Massachusetts Institute of Technology. Aerospace Controls Laboratory |
| author_facet | Massachusetts Institute of Technology. Aerospace Controls Laboratory Geramifard, Alborz Redding, Joshua Roy, Nicholas How, Jonathan P. |
| author_sort | Geramifard, Alborz |
| collection | MIT |
| description | Risk and reward are fundamental concepts in the cooperative control of unmanned systems. This paper focuses on a constructive relationship between a cooperative planner and a learner in order to mitigate the learning risk while boosting the asymptotic performance and safety of agent behavior. Our framework is an instance of the intelligent cooperative control architecture (iCCA) where a learner (Natural actor-critic, Sarsa) initially follows a “safe” policy generated by a cooperative planner (consensus-based bundle algorithm). The learner incrementally improves this baseline policy through interaction, while avoiding behaviors believed to be “risky”. This paper extends previous work toward the coupling of learning and cooperative control strategies in real-time stochastic domains in two ways: (1) the risk analysis module supports stochastic risk models, and (2) learning schemes that do not store the policy as a separate entity are integrated with the cooperative planner extending the applicability of iCCA framework. The performance of the resulting approaches are demonstrated through simulation of limited fuel UAVs in a stochastic task assignment problem. Results show an 8% reduction in risk, while improving the performance up to 30%. |
| first_indexed | 2024-09-23T08:33:14Z |
| format | Article |
| id | mit-1721.1/81838 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T08:33:14Z |
| publishDate | 2013 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/818382022-09-23T12:51:07Z UAV Cooperative Control with Stochastic Risk Models Geramifard, Alborz Redding, Joshua Roy, Nicholas How, Jonathan P. Massachusetts Institute of Technology. Aerospace Controls Laboratory Massachusetts Institute of Technology. Laboratory for Information and Decision Systems Geramifard, Alborz Redding, Joshua Roy, Nicholas How, Jonathan P. Risk and reward are fundamental concepts in the cooperative control of unmanned systems. This paper focuses on a constructive relationship between a cooperative planner and a learner in order to mitigate the learning risk while boosting the asymptotic performance and safety of agent behavior. Our framework is an instance of the intelligent cooperative control architecture (iCCA) where a learner (Natural actor-critic, Sarsa) initially follows a “safe” policy generated by a cooperative planner (consensus-based bundle algorithm). The learner incrementally improves this baseline policy through interaction, while avoiding behaviors believed to be “risky”. This paper extends previous work toward the coupling of learning and cooperative control strategies in real-time stochastic domains in two ways: (1) the risk analysis module supports stochastic risk models, and (2) learning schemes that do not store the policy as a separate entity are integrated with the cooperative planner extending the applicability of iCCA framework. The performance of the resulting approaches are demonstrated through simulation of limited fuel UAVs in a stochastic task assignment problem. Results show an 8% reduction in risk, while improving the performance up to 30%. United States. Air Force Office of Scientific Research (Grant FA9550-09-1-0522) Boeing Scientific Research Laboratories 2013-10-29T16:58:49Z 2013-10-29T16:58:49Z 2011-06 Article http://purl.org/eprint/type/ConferencePaper 978-1-4577-0081-1 http://hdl.handle.net/1721.1/81838 Geramifard, Alborz et al. "UAV Cooperative Control with Stochastic Risk Models." IEEE American Control Conference, 2011. https://orcid.org/0000-0002-2508-1957 https://orcid.org/0000-0001-8576-1930 https://orcid.org/0000-0002-8293-0492 en_US http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5991309 Proceedings of the 2011 American Control Conference Creative Commons Attribution-Noncommercial-Share Alike 3.0 http://creativecommons.org/licenses/by-nc-sa/3.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) MIT web domain |
| spellingShingle | Geramifard, Alborz Redding, Joshua Roy, Nicholas How, Jonathan P. UAV Cooperative Control with Stochastic Risk Models |
| title | UAV Cooperative Control with Stochastic Risk Models |
| title_full | UAV Cooperative Control with Stochastic Risk Models |
| title_fullStr | UAV Cooperative Control with Stochastic Risk Models |
| title_full_unstemmed | UAV Cooperative Control with Stochastic Risk Models |
| title_short | UAV Cooperative Control with Stochastic Risk Models |
| title_sort | uav cooperative control with stochastic risk models |
| url | http://hdl.handle.net/1721.1/81838 https://orcid.org/0000-0002-2508-1957 https://orcid.org/0000-0001-8576-1930 https://orcid.org/0000-0002-8293-0492 |
| work_keys_str_mv | AT geramifardalborz uavcooperativecontrolwithstochasticriskmodels AT reddingjoshua uavcooperativecontrolwithstochasticriskmodels AT roynicholas uavcooperativecontrolwithstochasticriskmodels AT howjonathanp uavcooperativecontrolwithstochasticriskmodels |