Multi-UAV Conflict Resolution with Graph Convolutional Reinforcement Learning
Safety is the primary concern when it comes to air traffic. In-flight safety between Unmanned Aircraft Vehicles (UAVs) is ensured through pairwise separation minima, utilizing conflict detection and resolution methods. Existing methods mainly deal with pairwise conflicts, however, due to an expected...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/2/610 |
| _version_ | 1797496158522703872 |
|---|---|
| author | Ralvi Isufaj Marsel Omeri Miquel Angel Piera |
| author_facet | Ralvi Isufaj Marsel Omeri Miquel Angel Piera |
| author_sort | Ralvi Isufaj |
| collection | DOAJ |
| description | Safety is the primary concern when it comes to air traffic. In-flight safety between Unmanned Aircraft Vehicles (UAVs) is ensured through pairwise separation minima, utilizing conflict detection and resolution methods. Existing methods mainly deal with pairwise conflicts, however, due to an expected increase in traffic density, encounters with more than two UAVs are likely to happen. In this paper, we model multi-UAV conflict resolution as a multiagent reinforcement learning problem. We implement an algorithm based on graph neural networks where cooperative agents can communicate to jointly generate resolution maneuvers. The model is evaluated in scenarios with 3 and 4 present agents. Results show that agents are able to successfully solve the multi-UAV conflicts through a cooperative strategy. |
| first_indexed | 2024-03-10T01:59:42Z |
| format | Article |
| id | doaj.art-49e25aa810de48ff95e6091724d9b571 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T01:59:42Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-49e25aa810de48ff95e6091724d9b5712023-11-23T12:49:53ZengMDPI AGApplied Sciences2076-34172022-01-0112261010.3390/app12020610Multi-UAV Conflict Resolution with Graph Convolutional Reinforcement LearningRalvi Isufaj0Marsel Omeri1Miquel Angel Piera2Logistic and Aeronautics Group, Department of Telecommunications and System Engineering, Autonomous University of Barcelona, 08202 Sabadell, SpainLogistic and Aeronautics Group, Department of Telecommunications and System Engineering, Autonomous University of Barcelona, 08202 Sabadell, SpainLogistic and Aeronautics Group, Department of Telecommunications and System Engineering, Autonomous University of Barcelona, 08202 Sabadell, SpainSafety is the primary concern when it comes to air traffic. In-flight safety between Unmanned Aircraft Vehicles (UAVs) is ensured through pairwise separation minima, utilizing conflict detection and resolution methods. Existing methods mainly deal with pairwise conflicts, however, due to an expected increase in traffic density, encounters with more than two UAVs are likely to happen. In this paper, we model multi-UAV conflict resolution as a multiagent reinforcement learning problem. We implement an algorithm based on graph neural networks where cooperative agents can communicate to jointly generate resolution maneuvers. The model is evaluated in scenarios with 3 and 4 present agents. Results show that agents are able to successfully solve the multi-UAV conflicts through a cooperative strategy.https://www.mdpi.com/2076-3417/12/2/610UTMUASmachine learningartificial intelligencemulti-UAS cooperative controlmultiagent reinforcement learning |
| spellingShingle | Ralvi Isufaj Marsel Omeri Miquel Angel Piera Multi-UAV Conflict Resolution with Graph Convolutional Reinforcement Learning Applied Sciences UTM UAS machine learning artificial intelligence multi-UAS cooperative control multiagent reinforcement learning |
| title | Multi-UAV Conflict Resolution with Graph Convolutional Reinforcement Learning |
| title_full | Multi-UAV Conflict Resolution with Graph Convolutional Reinforcement Learning |
| title_fullStr | Multi-UAV Conflict Resolution with Graph Convolutional Reinforcement Learning |
| title_full_unstemmed | Multi-UAV Conflict Resolution with Graph Convolutional Reinforcement Learning |
| title_short | Multi-UAV Conflict Resolution with Graph Convolutional Reinforcement Learning |
| title_sort | multi uav conflict resolution with graph convolutional reinforcement learning |
| topic | UTM UAS machine learning artificial intelligence multi-UAS cooperative control multiagent reinforcement learning |
| url | https://www.mdpi.com/2076-3417/12/2/610 |
| work_keys_str_mv | AT ralviisufaj multiuavconflictresolutionwithgraphconvolutionalreinforcementlearning AT marselomeri multiuavconflictresolutionwithgraphconvolutionalreinforcementlearning AT miquelangelpiera multiuavconflictresolutionwithgraphconvolutionalreinforcementlearning |