Robust Neural Control for Distributed Formation of UAVs under Uncertain Disturbances

Li, C., Xie, A., Zhou, J., Tian, D., Duan, X., Sheng, Z. and Zhao, D. (2023) Robust Neural Control for Distributed Formation of UAVs under Uncertain Disturbances. In: The Fourteenth International Conference on Swarm Intelligence (ICSI'2023), Shenzhen, China, 14-18 Jul 2023, (Accepted for Publication)

Abstract

The problem of multi-agent cooperative control has been widely studied in recent years. Quadrotor UAVs have received wide attention because of their mobility, flexibility, ability to perform complex tasks instead of humans, and low cost. Multi-quadrotor formation can have higher performance. However, formation flight is inevitably affected by model uncertainties and external disturbances, which significantly challenge the design of quadrotor formation controllers. Traditional robust controllers tend to limit the performance of the intelligence, and deep reinforcement learning can achieve high performance in control tasks but need more robustness. This paper uses a neural network-based robust control strategy to control a quadrotor formation to ensure robustness and performance under uncertainty disturbances. The formation is modeled using the leader-follower approach. We conducted simulation experiments to verify the feasibility of the method.

• Item Type: Conference Proceedings
• Status: Accepted for Publication
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Zhao, Dr Dezong
• Authors: Li, C., Xie, A., Zhou, J., Tian, D., Duan, X., Sheng, Z., and Zhao, D.
• College/School: College of Science and Engineering > School of Engineering > Autonomous Systems and Connectivity