Probabilistic Allocation of Specialized Robots on Targets Detected Using Deep Learning Networks
Task allocation for specialized unmanned robotic agents is addressed in this paper. Based on the assumptions that each individual robotic agent possesses specialized capabilities and that targets representing the tasks to be performed in the surrounding environment impose specific requirements, the...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-07-01
|
| Series: | Robotics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2218-6581/9/3/54 |
| _version_ | 1827712957034790912 |
|---|---|
| author | Omar Al-Buraiki Wenbo Wu Pierre Payeur |
| author_facet | Omar Al-Buraiki Wenbo Wu Pierre Payeur |
| author_sort | Omar Al-Buraiki |
| collection | DOAJ |
| description | Task allocation for specialized unmanned robotic agents is addressed in this paper. Based on the assumptions that each individual robotic agent possesses specialized capabilities and that targets representing the tasks to be performed in the surrounding environment impose specific requirements, the proposed approach computes task-agent fitting probabilities to efficiently match the available robotic agents with the detected targets. The framework is supported by a deep learning method with an object instance segmentation capability, Mask R-CNN, that is adapted to provide target object recognition and localization estimates from vision sensors mounted on the robotic agents. Experimental validation, for indoor search-and-rescue (SAR) scenarios, is conducted and results demonstrate the reliability and efficiency of the proposed approach. |
| first_indexed | 2024-03-10T18:25:31Z |
| format | Article |
| id | doaj.art-28951730e6804a4b9af0af2b2d6020cc |
| institution | Directory Open Access Journal |
| issn | 2218-6581 |
| language | English |
| last_indexed | 2024-03-10T18:25:31Z |
| publishDate | 2020-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Robotics |
| spelling | doaj.art-28951730e6804a4b9af0af2b2d6020cc2023-11-20T07:01:37ZengMDPI AGRobotics2218-65812020-07-01935410.3390/robotics9030054Probabilistic Allocation of Specialized Robots on Targets Detected Using Deep Learning NetworksOmar Al-Buraiki0Wenbo Wu1Pierre Payeur2School of Electrical Engineering and Computer Science, University of Ottawa, 800 King Edward, Ottawa, ON K1N 6N5, CanadaSchool of Electrical Engineering and Computer Science, University of Ottawa, 800 King Edward, Ottawa, ON K1N 6N5, CanadaSchool of Electrical Engineering and Computer Science, University of Ottawa, 800 King Edward, Ottawa, ON K1N 6N5, CanadaTask allocation for specialized unmanned robotic agents is addressed in this paper. Based on the assumptions that each individual robotic agent possesses specialized capabilities and that targets representing the tasks to be performed in the surrounding environment impose specific requirements, the proposed approach computes task-agent fitting probabilities to efficiently match the available robotic agents with the detected targets. The framework is supported by a deep learning method with an object instance segmentation capability, Mask R-CNN, that is adapted to provide target object recognition and localization estimates from vision sensors mounted on the robotic agents. Experimental validation, for indoor search-and-rescue (SAR) scenarios, is conducted and results demonstrate the reliability and efficiency of the proposed approach.https://www.mdpi.com/2218-6581/9/3/54task allocationmulti-agent systemsspecialized robotsprobabilistic representationtarget object detectiondeep learning |
| spellingShingle | Omar Al-Buraiki Wenbo Wu Pierre Payeur Probabilistic Allocation of Specialized Robots on Targets Detected Using Deep Learning Networks Robotics task allocation multi-agent systems specialized robots probabilistic representation target object detection deep learning |
| title | Probabilistic Allocation of Specialized Robots on Targets Detected Using Deep Learning Networks |
| title_full | Probabilistic Allocation of Specialized Robots on Targets Detected Using Deep Learning Networks |
| title_fullStr | Probabilistic Allocation of Specialized Robots on Targets Detected Using Deep Learning Networks |
| title_full_unstemmed | Probabilistic Allocation of Specialized Robots on Targets Detected Using Deep Learning Networks |
| title_short | Probabilistic Allocation of Specialized Robots on Targets Detected Using Deep Learning Networks |
| title_sort | probabilistic allocation of specialized robots on targets detected using deep learning networks |
| topic | task allocation multi-agent systems specialized robots probabilistic representation target object detection deep learning |
| url | https://www.mdpi.com/2218-6581/9/3/54 |
| work_keys_str_mv | AT omaralburaiki probabilisticallocationofspecializedrobotsontargetsdetectedusingdeeplearningnetworks AT wenbowu probabilisticallocationofspecializedrobotsontargetsdetectedusingdeeplearningnetworks AT pierrepayeur probabilisticallocationofspecializedrobotsontargetsdetectedusingdeeplearningnetworks |