End-to-end decentralized formation control using a graph neural network-based learning method
Multi-robot cooperative control has been extensively studied using model-based distributed control methods. However, such control methods rely on sensing and perception modules in a sequential pipeline design, and the separation of perception and controls may cause processing latencies and compoundi...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2023-11-01
|
Series: | Frontiers in Robotics and AI |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/frobt.2023.1285412/full |
_version_ | 1797635054261764096 |
---|---|
author | Chao Jiang Xinchi Huang Yi Guo |
author_facet | Chao Jiang Xinchi Huang Yi Guo |
author_sort | Chao Jiang |
collection | DOAJ |
description | Multi-robot cooperative control has been extensively studied using model-based distributed control methods. However, such control methods rely on sensing and perception modules in a sequential pipeline design, and the separation of perception and controls may cause processing latencies and compounding errors that affect control performance. End-to-end learning overcomes this limitation by implementing direct learning from onboard sensing data, with control commands output to the robots. Challenges exist in end-to-end learning for multi-robot cooperative control, and previous results are not scalable. We propose in this article a novel decentralized cooperative control method for multi-robot formations using deep neural networks, in which inter-robot communication is modeled by a graph neural network (GNN). Our method takes LiDAR sensor data as input, and the control policy is learned from demonstrations that are provided by an expert controller for decentralized formation control. Although it is trained with a fixed number of robots, the learned control policy is scalable. Evaluation in a robot simulator demonstrates the triangular formation behavior of multi-robot teams of different sizes under the learned control policy. |
first_indexed | 2024-03-11T12:16:47Z |
format | Article |
id | doaj.art-80ef210212e642ff91c44d4d5a71d549 |
institution | Directory Open Access Journal |
issn | 2296-9144 |
language | English |
last_indexed | 2024-03-11T12:16:47Z |
publishDate | 2023-11-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Robotics and AI |
spelling | doaj.art-80ef210212e642ff91c44d4d5a71d5492023-11-07T07:56:31ZengFrontiers Media S.A.Frontiers in Robotics and AI2296-91442023-11-011010.3389/frobt.2023.12854121285412End-to-end decentralized formation control using a graph neural network-based learning methodChao Jiang0Xinchi Huang1Yi Guo2Department of Electrical Engineering and Computer Science, University of Wyoming, Laramie, WY, United StatesDepartment of Electrical and Computer Engineering, Stevens Institute of Technology, Hoboken, NJ, United StatesDepartment of Electrical and Computer Engineering, Stevens Institute of Technology, Hoboken, NJ, United StatesMulti-robot cooperative control has been extensively studied using model-based distributed control methods. However, such control methods rely on sensing and perception modules in a sequential pipeline design, and the separation of perception and controls may cause processing latencies and compounding errors that affect control performance. End-to-end learning overcomes this limitation by implementing direct learning from onboard sensing data, with control commands output to the robots. Challenges exist in end-to-end learning for multi-robot cooperative control, and previous results are not scalable. We propose in this article a novel decentralized cooperative control method for multi-robot formations using deep neural networks, in which inter-robot communication is modeled by a graph neural network (GNN). Our method takes LiDAR sensor data as input, and the control policy is learned from demonstrations that are provided by an expert controller for decentralized formation control. Although it is trained with a fixed number of robots, the learned control policy is scalable. Evaluation in a robot simulator demonstrates the triangular formation behavior of multi-robot teams of different sizes under the learned control policy.https://www.frontiersin.org/articles/10.3389/frobt.2023.1285412/fulldistributed multi-robot controlmulti-robot learninggraph neural networkformation control and coordinationautonomous robots |
spellingShingle | Chao Jiang Xinchi Huang Yi Guo End-to-end decentralized formation control using a graph neural network-based learning method Frontiers in Robotics and AI distributed multi-robot control multi-robot learning graph neural network formation control and coordination autonomous robots |
title | End-to-end decentralized formation control using a graph neural network-based learning method |
title_full | End-to-end decentralized formation control using a graph neural network-based learning method |
title_fullStr | End-to-end decentralized formation control using a graph neural network-based learning method |
title_full_unstemmed | End-to-end decentralized formation control using a graph neural network-based learning method |
title_short | End-to-end decentralized formation control using a graph neural network-based learning method |
title_sort | end to end decentralized formation control using a graph neural network based learning method |
topic | distributed multi-robot control multi-robot learning graph neural network formation control and coordination autonomous robots |
url | https://www.frontiersin.org/articles/10.3389/frobt.2023.1285412/full |
work_keys_str_mv | AT chaojiang endtoenddecentralizedformationcontrolusingagraphneuralnetworkbasedlearningmethod AT xinchihuang endtoenddecentralizedformationcontrolusingagraphneuralnetworkbasedlearningmethod AT yiguo endtoenddecentralizedformationcontrolusingagraphneuralnetworkbasedlearningmethod |