TY - JOUR
T1 - End-to-end decentralized formation control using a graph neural network-based learning method
AU - Jiang, Chao
AU - Huang, Xinchi
AU - Guo, Yi
N1 - Publisher Copyright:
Copyright © 2023 Jiang, Huang and Guo.
PY - 2023
Y1 - 2023
N2 - 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.
AB - 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.
KW - autonomous robots
KW - distributed multi-robot control
KW - formation control and coordination
KW - graph neural network
KW - multi-robot learning
UR - http://www.scopus.com/inward/record.url?scp=85177458444&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85177458444&partnerID=8YFLogxK
U2 - 10.3389/frobt.2023.1285412
DO - 10.3389/frobt.2023.1285412
M3 - Article
AN - SCOPUS:85177458444
VL - 10
JO - Frontiers Robotics AI
JF - Frontiers Robotics AI
M1 - 1285412
ER -