Robustness Enhancement for Multi-Quadrotor Centralized Transportation System via Online Tuning and Learning
By: Tianhua Gao, Kohji Tomita, Akiya Kamimura
Potential Business Impact:
Drones work together better, even when pushed.
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.
Similar Papers
Online Identification using Adaptive Laws and Neural Networks for Multi-Quadrotor Centralized Transportation System
Systems and Control
Drones carry heavy loads more steadily.
Enhanced Robust Tracking Control: An Online Learning Approach
Systems and Control
Fixes robots that go off course.
Learning Robust Agile Flight Control with Stability Guarantees
Robotics
Lets drones fly faster and safer.