Imitation Learning with Graph Neural Networks for Improving Swarm Robustness under Restricted Communications
This paper focuses on generating distributed flocking strategies via imitation learning. The primary motivation is to improve the swarm robustness and achieve better consistency while respecting the communication constraints. This paper first proposes a quantitative metric of swarm robustness based...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/19/9055 |
| _version_ | 1797516800933494784 |
|---|---|
| author | Ce Guo Pengming Zhu Zhiqian Zhou Lin Lang Zhiwen Zeng Huimin Lu |
| author_facet | Ce Guo Pengming Zhu Zhiqian Zhou Lin Lang Zhiwen Zeng Huimin Lu |
| author_sort | Ce Guo |
| collection | DOAJ |
| description | This paper focuses on generating distributed flocking strategies via imitation learning. The primary motivation is to improve the swarm robustness and achieve better consistency while respecting the communication constraints. This paper first proposes a quantitative metric of swarm robustness based on entropy evaluation. Then, the graph importance consistency is also proposed, which is one of the critical goals of the flocking task. Moreover, the importance-correlated directed graph convolutional networks (IDGCNs) are constructed for multidimensional feature extraction and structure-related aggregation of graph data. Next, by employing IDGCNs-based imitation learning, a distributed and scalable flocking strategy is obtained, and its performance is very close to the centralized strategy template while considering communication constraints. To speed up and simplify the training process, we train the flocking strategy with a small number of agents and set restrictions on communication. Finally, various simulation experiments are executed to verify the advantages of the obtained strategy in terms of realizing the swarm consistency and improving the swarm robustness. The results also show that the performance is well maintained while the scale of agents expands (tested with 20, 30, 40 robots). |
| first_indexed | 2024-03-10T07:06:55Z |
| format | Article |
| id | doaj.art-9c7ec0c0b685497ba721a5b030c43c2e |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T07:06:55Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-9c7ec0c0b685497ba721a5b030c43c2e2023-11-22T15:47:03ZengMDPI AGApplied Sciences2076-34172021-09-011119905510.3390/app11199055Imitation Learning with Graph Neural Networks for Improving Swarm Robustness under Restricted CommunicationsCe Guo0Pengming Zhu1Zhiqian Zhou2Lin Lang3Zhiwen Zeng4Huimin Lu5Robotics Research Center, College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, ChinaRobotics Research Center, College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, ChinaRobotics Research Center, College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, ChinaRobotics Research Center, College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, ChinaRobotics Research Center, College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, ChinaRobotics Research Center, College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, ChinaThis paper focuses on generating distributed flocking strategies via imitation learning. The primary motivation is to improve the swarm robustness and achieve better consistency while respecting the communication constraints. This paper first proposes a quantitative metric of swarm robustness based on entropy evaluation. Then, the graph importance consistency is also proposed, which is one of the critical goals of the flocking task. Moreover, the importance-correlated directed graph convolutional networks (IDGCNs) are constructed for multidimensional feature extraction and structure-related aggregation of graph data. Next, by employing IDGCNs-based imitation learning, a distributed and scalable flocking strategy is obtained, and its performance is very close to the centralized strategy template while considering communication constraints. To speed up and simplify the training process, we train the flocking strategy with a small number of agents and set restrictions on communication. Finally, various simulation experiments are executed to verify the advantages of the obtained strategy in terms of realizing the swarm consistency and improving the swarm robustness. The results also show that the performance is well maintained while the scale of agents expands (tested with 20, 30, 40 robots).https://www.mdpi.com/2076-3417/11/19/9055swarm robustnessgraph importance entropygraph convolutional networksimitation learning |
| spellingShingle | Ce Guo Pengming Zhu Zhiqian Zhou Lin Lang Zhiwen Zeng Huimin Lu Imitation Learning with Graph Neural Networks for Improving Swarm Robustness under Restricted Communications Applied Sciences swarm robustness graph importance entropy graph convolutional networks imitation learning |
| title | Imitation Learning with Graph Neural Networks for Improving Swarm Robustness under Restricted Communications |
| title_full | Imitation Learning with Graph Neural Networks for Improving Swarm Robustness under Restricted Communications |
| title_fullStr | Imitation Learning with Graph Neural Networks for Improving Swarm Robustness under Restricted Communications |
| title_full_unstemmed | Imitation Learning with Graph Neural Networks for Improving Swarm Robustness under Restricted Communications |
| title_short | Imitation Learning with Graph Neural Networks for Improving Swarm Robustness under Restricted Communications |
| title_sort | imitation learning with graph neural networks for improving swarm robustness under restricted communications |
| topic | swarm robustness graph importance entropy graph convolutional networks imitation learning |
| url | https://www.mdpi.com/2076-3417/11/19/9055 |
| work_keys_str_mv | AT ceguo imitationlearningwithgraphneuralnetworksforimprovingswarmrobustnessunderrestrictedcommunications AT pengmingzhu imitationlearningwithgraphneuralnetworksforimprovingswarmrobustnessunderrestrictedcommunications AT zhiqianzhou imitationlearningwithgraphneuralnetworksforimprovingswarmrobustnessunderrestrictedcommunications AT linlang imitationlearningwithgraphneuralnetworksforimprovingswarmrobustnessunderrestrictedcommunications AT zhiwenzeng imitationlearningwithgraphneuralnetworksforimprovingswarmrobustnessunderrestrictedcommunications AT huiminlu imitationlearningwithgraphneuralnetworksforimprovingswarmrobustnessunderrestrictedcommunications |