Semantic-level decentralized multi-robot decision-making using probabilistic macro-observations
Robust environment perception is essential for decision-making on robots operating in complex domains. Intelligent task execution requires principled treatment of uncertainty sources in a robot's observation model. This is important not only for low-level observations (e.g., accelerom-eter data...
| Main Authors: | , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2018
|
| Online Access: | http://hdl.handle.net/1721.1/114737 https://orcid.org/0000-0003-0903-0137 https://orcid.org/0000-0002-9838-1221 https://orcid.org/0000-0001-9377-6745 https://orcid.org/0000-0001-5366-911X https://orcid.org/0000-0002-1648-8325 https://orcid.org/0000-0001-8576-1930 |
| _version_ | 1826201529361629184 |
|---|---|
| author | Amato, Christopher Vian, John Omidshafiei, Shayegan Liu, Shih-Yuan Everett, Michael F Lopez, Brett Thomas Liu, Miao How, Jonathan P |
| author2 | Massachusetts Institute of Technology. Department of Aeronautics and Astronautics |
| author_facet | Massachusetts Institute of Technology. Department of Aeronautics and Astronautics Amato, Christopher Vian, John Omidshafiei, Shayegan Liu, Shih-Yuan Everett, Michael F Lopez, Brett Thomas Liu, Miao How, Jonathan P |
| author_sort | Amato, Christopher |
| collection | MIT |
| description | Robust environment perception is essential for decision-making on robots operating in complex domains. Intelligent task execution requires principled treatment of uncertainty sources in a robot's observation model. This is important not only for low-level observations (e.g., accelerom-eter data), but also for high-level observations such as semantic object labels. This paper formalizes the concept of macro-observations in Decentralized Partially Observable Semi-Markov Decision Processes (Dec-POSMDPs), allowing scalable semantic-level multi-robot decision making. A hierarchical Bayesian approach is used to model noise statistics of low-level classifier outputs, while simultaneously allowing sharing of domain noise characteristics between classes. Classification accuracy of the proposed macro-observation scheme, called Hierarchical Bayesian Noise Inference (HBNI), is shown to exceed existing methods. The macro-observation scheme is then integrated into a Dec-POSMDP planner, with hardware experiments running onboard a team of dynamic quadrotors in a challenging domain where noise-agnostic filtering fails. To the best of our knowledge, this is the first demonstration of a real-time, convolutional neural net-based classification framework running fully onboard a team of quadrotors in a multi-robot decision-making domain. |
| first_indexed | 2024-09-23T11:52:52Z |
| format | Article |
| id | mit-1721.1/114737 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T11:52:52Z |
| publishDate | 2018 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/1147372022-09-27T22:34:48Z Semantic-level decentralized multi-robot decision-making using probabilistic macro-observations Amato, Christopher Vian, John Omidshafiei, Shayegan Liu, Shih-Yuan Everett, Michael F Lopez, Brett Thomas Liu, Miao How, Jonathan P Massachusetts Institute of Technology. Department of Aeronautics and Astronautics Massachusetts Institute of Technology. Department of Mechanical Engineering Massachusetts Institute of Technology. Laboratory for Information and Decision Systems Omidshafiei, Shayegan Liu, Shih-Yuan Everett, Michael F Lopez, Brett Thomas Liu, Miao How, Jonathan P Robust environment perception is essential for decision-making on robots operating in complex domains. Intelligent task execution requires principled treatment of uncertainty sources in a robot's observation model. This is important not only for low-level observations (e.g., accelerom-eter data), but also for high-level observations such as semantic object labels. This paper formalizes the concept of macro-observations in Decentralized Partially Observable Semi-Markov Decision Processes (Dec-POSMDPs), allowing scalable semantic-level multi-robot decision making. A hierarchical Bayesian approach is used to model noise statistics of low-level classifier outputs, while simultaneously allowing sharing of domain noise characteristics between classes. Classification accuracy of the proposed macro-observation scheme, called Hierarchical Bayesian Noise Inference (HBNI), is shown to exceed existing methods. The macro-observation scheme is then integrated into a Dec-POSMDP planner, with hardware experiments running onboard a team of dynamic quadrotors in a challenging domain where noise-agnostic filtering fails. To the best of our knowledge, this is the first demonstration of a real-time, convolutional neural net-based classification framework running fully onboard a team of quadrotors in a multi-robot decision-making domain. Boeing Company 2018-04-13T21:42:25Z 2018-04-13T21:42:25Z 2017-07 2017-06 2018-03-21T16:28:33Z Article http://purl.org/eprint/type/ConferencePaper 978-1-5090-4633-1 978-1-5090-4634-8 http://hdl.handle.net/1721.1/114737 Omidshafiei, Shayegan, Shih-Yuan Liu, Michael Everett, Brett T. Lopez, Christopher Amato, Miao Liu, Jonathan P. How, and John Vian. “Semantic-Level Decentralized Multi-Robot Decision-Making Using Probabilistic Macro-Observations.” 2017 IEEE International Conference on Robotics and Automation (ICRA), May 2017, Singapore, Singapore, 2017. https://orcid.org/0000-0003-0903-0137 https://orcid.org/0000-0002-9838-1221 https://orcid.org/0000-0001-9377-6745 https://orcid.org/0000-0001-5366-911X https://orcid.org/0000-0002-1648-8325 https://orcid.org/0000-0001-8576-1930 http://dx.doi.org/10.1109/ICRA.2017.7989107 2017 IEEE International Conference on Robotics and Automation (ICRA) Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) arXiv |
| spellingShingle | Amato, Christopher Vian, John Omidshafiei, Shayegan Liu, Shih-Yuan Everett, Michael F Lopez, Brett Thomas Liu, Miao How, Jonathan P Semantic-level decentralized multi-robot decision-making using probabilistic macro-observations |
| title | Semantic-level decentralized multi-robot decision-making using probabilistic macro-observations |
| title_full | Semantic-level decentralized multi-robot decision-making using probabilistic macro-observations |
| title_fullStr | Semantic-level decentralized multi-robot decision-making using probabilistic macro-observations |
| title_full_unstemmed | Semantic-level decentralized multi-robot decision-making using probabilistic macro-observations |
| title_short | Semantic-level decentralized multi-robot decision-making using probabilistic macro-observations |
| title_sort | semantic level decentralized multi robot decision making using probabilistic macro observations |
| url | http://hdl.handle.net/1721.1/114737 https://orcid.org/0000-0003-0903-0137 https://orcid.org/0000-0002-9838-1221 https://orcid.org/0000-0001-9377-6745 https://orcid.org/0000-0001-5366-911X https://orcid.org/0000-0002-1648-8325 https://orcid.org/0000-0001-8576-1930 |
| work_keys_str_mv | AT amatochristopher semanticleveldecentralizedmultirobotdecisionmakingusingprobabilisticmacroobservations AT vianjohn semanticleveldecentralizedmultirobotdecisionmakingusingprobabilisticmacroobservations AT omidshafieishayegan semanticleveldecentralizedmultirobotdecisionmakingusingprobabilisticmacroobservations AT liushihyuan semanticleveldecentralizedmultirobotdecisionmakingusingprobabilisticmacroobservations AT everettmichaelf semanticleveldecentralizedmultirobotdecisionmakingusingprobabilisticmacroobservations AT lopezbrettthomas semanticleveldecentralizedmultirobotdecisionmakingusingprobabilisticmacroobservations AT liumiao semanticleveldecentralizedmultirobotdecisionmakingusingprobabilisticmacroobservations AT howjonathanp semanticleveldecentralizedmultirobotdecisionmakingusingprobabilisticmacroobservations |