Q-learning-based model predictive variable impedance control for physical human-robot collaboration

DOI10.1016/j.artint.2022.103771OpenAlexW4291006859MaRDI QIDQ2093371

Asad Ali Shahid, Loris Roveda, Andrea Testa, Dario Piga, Francesco Braghin

Publication date: 8 November 2022

Published in: Artificial Intelligence (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.artint.2022.103771

zbMATH Keywords

stabilityneural networksmachine learningQ-learningindustry 4.0model-based reinforcement learning controlphysical human-robot collaborationvariable impedance control

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Uses Software

• Adam

Cites Work

• A single network adaptive critic (SNAC) architecture for optimal control synthesis for a class of nonlinear systems
• \({\mathcal Q}\)-learning
• A `universal' construction of Artstein's theorem on nonlinear stabilization
• Modelling and control of robot manipulators.
• Nonlinear model predictive control. Theory and algorithms
• Stabilization of nonlinear systems with state and control constraints using Lyapunov-based predictive control
• Stabilization with relaxed controls
• Lyapunov stability theory of nonsmooth systems
• A receding horizon generalization of pointwise min-norm controllers
• Unconstrained receding-horizon control of nonlinear systems
• Nonlinear Systems Analysis
• Inverse Optimality in Robust Stabilization
• Lyapunov-Based Model Predictive Control of Nonlinear Systems Subject to Data Losses
• On the stability of receding horizon control with a general terminal cost
• Predictive control of switched nonlinear systems with scheduled mode transitions

This page was built for publication: Q-learning-based model predictive variable impedance control for physical human-robot collaboration