Realtime Brain-Inspired Adaptive Learning Control for Nonlinear Systems With Configuration Uncertainties

This paper investigates the problem of adaptive tracking control for quadcopter in the presence of nonlinear configuration uncertainties. It utilizes a real-time brain-inspired learning control (RBiLC) method to address the challenges posed by nonlinear time-varying uncertain instructions. To address the issue of flight control law reconfiguration caused by unknown changes in the fuselage configuration (e.g., propellers or motors), this paper introduces an online learning-evaluation-optimization reconstruction mechanism based on RBiLC. The proposed adaptive learning controller mitigates the need for extensive human resources and reduces the time required for flight controller design. The Lyapunov-Krasovskii function is introduced as a compensatory measure to address the impact of parameter uncertainty on system stability. Furthermore, this paper proposes a signed sinusoidal function perturbation estimate to guide the direction and magnitude throughout the online learning process. The approach conducts a theoretical stability analysis on a quadcopter vehicle considering uncertainties in UAV dynamics modeling. The results demonstrate that the proposed scheme achieves superior control and faster adaptation, enabling the system to ultimately converge to a compact set within a limited time domain. Finally, software-in-the-loop (SITL) simulations and flight verification results are presented to validate the proposed control strategy
Note to Practitioners
—In various UAV application scenarios, UAVs often necessitate multiple motor and size configurations to accommodate diverse mission load requirements. This paper examines the self-learning reconfiguration control of a nonlinear UAV controller, focusing on achieving stable control despite uncertain propeller configurations. The proposed self-learning control method is inspired by the self-learning mechanism observed in the human brain. Without any manual intervention, the traditional proportional-integral-derivative (PID) control serves as the benchmark and is intricately combined with an evolutionary strategy for iterative learning. The learning process is realized during flight without relying on a precise model through real-time evaluation, nonlinear command tracking response, and iterative reconstruction using a design-based symbolic sine function optimal controller. The practice has proved that when the UAV model cannot be identified in real-time, the UAV controller can be reconfigured in real-time through the model-free control method based on brain-inspired learning iterations to achieve stable control of the UAV. The notable feature of this paper is the establishment of the RBiLC framework, the completion of the theoretical proof of stability, and the real-world flight experiment on the quadcopter