Port-Hamiltonian systems in adaptive and learning control: A survey

SP Nageshrao, GAD Lopes, D Jeltsema… - IEEE Transactions on …, 2015 - ieeexplore.ieee.org
Port-Hamiltonian (PH) theory is a novel, but well established modeling framework for
nonlinear physical systems. Due to the emphasis on the physical structure and modular …

Adaptive neural network tracking control for underactuated systems with matched and mismatched disturbances

P Liu, H Yu, S Cang - Nonlinear Dynamics, 2019 - Springer
This paper studies neural network-based tracking control of underactuated systems with
unknown parameters and with matched and mismatched disturbances. Novel adaptive …

[HTML][HTML] Q-Learning-based model predictive variable impedance control for physical human-robot collaboration

L Roveda, A Testa, AA Shahid, F Braghin, D Piga - Artificial Intelligence, 2022 - Elsevier
Physical human-robot collaboration is increasingly required in many contexts (such as
industrial and rehabilitation applications). The robot needs to interact with the human to …

[BOEK][B] Motion control of underactuated mechanical systems

The growth in automated manufacturing since the '60s has motivated the study of the control
and motion planning of many types of mechanical systems, such as industrial manipulators …

An overview on recent machine learning techniques for Port Hamiltonian systems

K Cherifi - Physica D: Nonlinear Phenomena, 2020 - Elsevier
Port Hamiltonian systems have grown in interest in recent years due to their modular
property, close relation with physical modelling and the interesting properties arising from …

Distributed neural network control with dependability guarantees: a compositional port-Hamiltonian approach

L Furieri, CL Galimberti, M Zakwan… - … for dynamics and …, 2022 - proceedings.mlr.press
Large-scale cyber-physical systems require that control policies are distributed, that is, that
they only rely on local real-time measurements and communication with neighboring agents …

A fast sampling method for estimating the domain of attraction

E Najafi, R Babuška, GAD Lopes - Nonlinear dynamics, 2016 - Springer
Most stabilizing controllers designed for nonlinear systems are valid only within a specific
region of the state space, called the domain of attraction (DoA). Computation of the DoA is …

Adaptive neural network control for the trajectory tracking of the Furuta pendulum

J Moreno-Valenzuela, C Aguilar-Avelar… - IEEE transactions on …, 2016 - ieeexplore.ieee.org
The purpose of this paper is to introduce a novel adaptive neural network-based control
scheme for the Furuta pendulum, which is a two degree-of-freedom underactuated system …

Machine Learning in Computer Aided Engineering

FJ Montáns, E Cueto, KJ Bathe - Machine Learning in Modeling and …, 2023 - Springer
The extraordinary success of Machine Learning (ML) in many complex heuristic fields has
promoted its introduction in more analytical engineering fields, improving or substituting …

Multilayer perception based reinforcement learning supervisory control of energy systems with application to a nuclear steam supply system

Z Dong, X Huang, Y Dong, Z Zhang - Applied Energy, 2020 - Elsevier
Energy system optimization is important in strengthening stability, reliability and economy,
which is usually given by static linear or nonlinear programming. However, the challenge …