TY - GEN
T1 - Learning decentralized control policies for multi-robot formation
AU - Chao, Jiang
AU - Zhuo, Chen
AU - Yi, Guo
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/7
Y1 - 2019/7
N2 - Decentralized formation control has been extensively studied using model-based methods, which rely on model accuracy and communication reliability. Motivated by recent advances in deep learning techniques whereby an intelligent agent is trained to compute its actions directly from highdimensional raw sensory inputs using end-to-end decisionmaking policies, we consider the problem of learning decentralized control policies for multi-robot formation. A deep neural network is designed to model the control policy that maps the robot's local observations to control commands. We propose to use a centralized training framework based on supervised learning for control policy learning. The learned policy is then deployed on each robot in a decentralized manner for online formation control. Our proposed approach is verified and evaluated in experiments using a robotic simulator. Simulation results demonstrate satisfactory performance of formation control. Compared with existing methods for formation control, the proposed approach does not need inter-robot communication, and avoids hand-engineering the components of perception and control separately.
AB - Decentralized formation control has been extensively studied using model-based methods, which rely on model accuracy and communication reliability. Motivated by recent advances in deep learning techniques whereby an intelligent agent is trained to compute its actions directly from highdimensional raw sensory inputs using end-to-end decisionmaking policies, we consider the problem of learning decentralized control policies for multi-robot formation. A deep neural network is designed to model the control policy that maps the robot's local observations to control commands. We propose to use a centralized training framework based on supervised learning for control policy learning. The learned policy is then deployed on each robot in a decentralized manner for online formation control. Our proposed approach is verified and evaluated in experiments using a robotic simulator. Simulation results demonstrate satisfactory performance of formation control. Compared with existing methods for formation control, the proposed approach does not need inter-robot communication, and avoids hand-engineering the components of perception and control separately.
UR - http://www.scopus.com/inward/record.url?scp=85074258932&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85074258932&partnerID=8YFLogxK
U2 - 10.1109/AIM.2019.8868898
DO - 10.1109/AIM.2019.8868898
M3 - Conference contribution
AN - SCOPUS:85074258932
T3 - IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM
SP - 758
EP - 765
BT - Proceedings of the 2019 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2019
T2 - 2019 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2019
Y2 - 8 July 2019 through 12 July 2019
ER -