Adversarial imitation learning with deep attention network for swarm systems
Abstract Swarm systems consist of a large number of interacting individuals, which exhibit complex behavior despite having simple interaction rules. However, crafting individual motion policies that can manifest desired collective behaviors poses a significant challenge due to the intricate relation...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2024-11-01
|
| Series: | Complex & Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s40747-024-01662-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571185839210496 |
|---|---|
| author | Yapei Wu Tao Wang Tong Liu Zhicheng Zheng Demin Xu Xingguang Peng |
| author_facet | Yapei Wu Tao Wang Tong Liu Zhicheng Zheng Demin Xu Xingguang Peng |
| author_sort | Yapei Wu |
| collection | DOAJ |
| description | Abstract Swarm systems consist of a large number of interacting individuals, which exhibit complex behavior despite having simple interaction rules. However, crafting individual motion policies that can manifest desired collective behaviors poses a significant challenge due to the intricate relationship between individual policies and swarm dynamics. This paper addresses this issue by proposing an imitation learning method, which derives individual policies from collective behavior data. The approach leverages an adversarial imitation learning framework, with a deep attention network serving as the individual policy network. Our method successfully imitates three distinct collective behaviors. Utilizing the ease of analysis provided by the deep attention network, we have verified that the individual policies underlying a certain collective behavior are not unique. Additionally, we have analyzed the different individual policies discovered. Lastly, we validate the applicability of the proposed method in designing policies for swarm robots through practical implementation on swarm robots. |
| format | Article |
| id | doaj-art-9bd03965936248abbc96acf7467bbaf6 |
| institution | Kabale University |
| issn | 2199-4536 2198-6053 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Springer |
| record_format | Article |
| series | Complex & Intelligent Systems |
| spelling | doaj-art-9bd03965936248abbc96acf7467bbaf62025-02-02T12:48:41ZengSpringerComplex & Intelligent Systems2199-45362198-60532024-11-0111111810.1007/s40747-024-01662-2Adversarial imitation learning with deep attention network for swarm systemsYapei Wu0Tao Wang1Tong Liu2Zhicheng Zheng3Demin Xu4Xingguang Peng5School of Marine Science and Technology, Northwestern Polytechnical UniversitySchool of Marine Science and Technology, Northwestern Polytechnical UniversitySchool of Marine Science and Technology, Northwestern Polytechnical UniversitySchool of Marine Science and Technology, Northwestern Polytechnical UniversitySchool of Marine Science and Technology, Northwestern Polytechnical UniversitySchool of Marine Science and Technology, Northwestern Polytechnical UniversityAbstract Swarm systems consist of a large number of interacting individuals, which exhibit complex behavior despite having simple interaction rules. However, crafting individual motion policies that can manifest desired collective behaviors poses a significant challenge due to the intricate relationship between individual policies and swarm dynamics. This paper addresses this issue by proposing an imitation learning method, which derives individual policies from collective behavior data. The approach leverages an adversarial imitation learning framework, with a deep attention network serving as the individual policy network. Our method successfully imitates three distinct collective behaviors. Utilizing the ease of analysis provided by the deep attention network, we have verified that the individual policies underlying a certain collective behavior are not unique. Additionally, we have analyzed the different individual policies discovered. Lastly, we validate the applicability of the proposed method in designing policies for swarm robots through practical implementation on swarm robots.https://doi.org/10.1007/s40747-024-01662-2Swarm systemAdversarial imitation learningDeep attention networkSwarm robots |
| spellingShingle | Yapei Wu Tao Wang Tong Liu Zhicheng Zheng Demin Xu Xingguang Peng Adversarial imitation learning with deep attention network for swarm systems Complex & Intelligent Systems Swarm system Adversarial imitation learning Deep attention network Swarm robots |
| title | Adversarial imitation learning with deep attention network for swarm systems |
| title_full | Adversarial imitation learning with deep attention network for swarm systems |
| title_fullStr | Adversarial imitation learning with deep attention network for swarm systems |
| title_full_unstemmed | Adversarial imitation learning with deep attention network for swarm systems |
| title_short | Adversarial imitation learning with deep attention network for swarm systems |
| title_sort | adversarial imitation learning with deep attention network for swarm systems |
| topic | Swarm system Adversarial imitation learning Deep attention network Swarm robots |
| url | https://doi.org/10.1007/s40747-024-01662-2 |
| work_keys_str_mv | AT yapeiwu adversarialimitationlearningwithdeepattentionnetworkforswarmsystems AT taowang adversarialimitationlearningwithdeepattentionnetworkforswarmsystems AT tongliu adversarialimitationlearningwithdeepattentionnetworkforswarmsystems AT zhichengzheng adversarialimitationlearningwithdeepattentionnetworkforswarmsystems AT deminxu adversarialimitationlearningwithdeepattentionnetworkforswarmsystems AT xingguangpeng adversarialimitationlearningwithdeepattentionnetworkforswarmsystems |