Robustness Enhancement for Multi-Quadrotor Centralized Transportation System via Online Tuning and Learning

2025-09-02

AI Summary

To address insufficient robustness of multi-quadrotor cooperative transportation systems under environmental disturbances and model uncertainties, this paper proposes an adaptive neural geometric control method. The approach innovatively integrates a geometric nonlinear control framework with a multi-neural-network architecture to enable online joint estimation of model parameters and real-time learning of external disturbances—without requiring pre-training or persistent excitation conditions. Adaptive laws are rigorously designed via Lyapunov theory, incorporating neural network approximation and real-time parameter tuning, and uniform ultimate boundedness of the closed-loop system is formally proven. Numerical simulations demonstrate that the proposed method achieves high-precision trajectory tracking and attitude synchronization even under significant model mismatch and strong time-varying disturbances, markedly improving robustness over conventional geometric control methods.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Adversarial Learning & Robustness
• Multiagent Systems: Adversarial Agents

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

This paper introduces an adaptive-neuro geometric control for a centralized multi-quadrotor cooperative transportation system, which enhances both adaptivity and disturbance rejection. Our strategy is to coactively tune the model parameters and learn the external disturbances in real-time. To realize this, we augmented the existing geometric control with multiple neural networks and adaptive laws, where the estimated model parameters and the weights of the neural networks are simultaneously tuned and adjusted online. The Lyapunov-based adaptation guarantees bounded estimation errors without requiring either pre-training or the persistent excitation (PE) condition. The proposed control system has been proven to be stable in the sense of Lyapunov under certain preconditions, and its enhanced robustness under scenarios of disturbed environment and model-unmatched plant was demonstrated by numerical simulations.

Problem

• Enhancing robustness in multi-quadrotor transportation systems
• Real-time tuning of model parameters and disturbances
• Improving adaptivity and disturbance rejection capabilities

Innovation

• Adaptive-neuro geometric control for quadrotors
• Online tuning of model parameters and disturbances
• Lyapunov-based adaptation without pre-training