Deep Learning-Based Consensus Control of a Multi-Agents System with Unknown Time-Varying Delay

Abstract

Despite the enormous progress in consensus control of a multi-agents system (MAS), amodel-based consensus control is valid only when the assumption on the system environment and on the model is valid. To overcome this limitation, several deep learning (DL) based consensus controls directly learn how to generate a control signal from the model-based control. Depending on the exploitation of knowledge from the model-based control structure, four different deep learning models were considered. Numerical simulations of MAS with unknown time-varying delays and disturbance verify that, while providing comparable performance to the model-based control for many different system configurations, the DL-based controls with explicit knowledge of the control signal structure are preferred to that with implicit knowledge of the control signal or no knowledge, which shows the promising potential of DL-based control with supervised learning.

Anti-Skid Aircraft Braking Mechanism using Consensus Control over Wireless Avionic Intra-Communication

“…In [24], the authors discussed communication delays for a consensus controller as a denial of service attack, where the attack can be seen as a communication loss. A time-varying delay-based consensus control scheme is discussed in [25]. In the prior literature, authors have studied the impact of random losses and delay on the system, but they have not discussed the effect of wireless communication protocol design and the radio interference intensity in the context of a wireless avionics environment.…”

Reinforcement Learning with Side Information for the Uncertainties

“…Alternatively, an RL approach that utilizes learning through experience without specific model knowledge may be adopted. However, most existing RL algorithms are sensitive to parameterizations and convergence problems [27].…”