Physics-Generated AIs of Robust Nonlinear Filter and Control Designs for Complicated Man-Made Machines

This book introduces a robust H? physics-generated AI-driven filter and controller, along with a nonlinear Luenberger observer model and a state estimation error dynamic model, to effectively address HJIEs for robust H? state estimation (filtering) and reference trajectory tracking control in nonlinear stochastic systems. Additionally, it presents a method for training deep neural networks (DNNs) using these models, alongside a physics-generated AI-driven observer-based reference tracking control scheme, with applications in the guidance and control of relevant systems.

Key features:

Provides theoretical analysis and detailed design procedure for physics-generated AI-driven H? or mixed H2/H? filter

Applies physics-generated AI-driven robust H? or mixed H2/H? filter and reference tracking control schemes to the trajectory estimation and reference tracking control of man-made machines

Introduces physics-generated AI-driven decentralized H? observer-based team formation tracking control of large-scale quadrotor UAVs, biped robots or LEO satellites

Promulgates the idea of the forthcoming age of physics-generated AI in robot

Describes robust physics-generated AI-driven filter and control schemes for complex man-made machines

This book is aimed at graduate students and researchers in control science, signal processing and artificial intelligence.