Results 31 to 40 of about 1,466,211 (327)
PD-Type Iterative Learning Control for Uncertain Spatially Interconnected Systems
Mathematics, 2020 This paper puts forward a PD-type iterative learning control algorithm for a class of discrete spatially interconnected systems with unstructured uncertainty.
Longhui Zhou +4 more
doaj +1 more source
International journal of circuit theory and applications, 2022 Since last 40 years, the theory and technology of model predictive control (MPC) have been developed rapidly. However, nonlinear MPC still faces difficulties such as high online computational complexity and inability to accurately model the system.
Fei Meng, Xuyu Shen, H. Karimi
semanticscholar +1 more source
Learning Deep Energy Shaping Policies for Stability-Guaranteed Manipulation [PDF]
IEEE Robotics and Automation Letters, 2021 Deep reinforcement learning (DRL) has been successfully used to solve various robotic manipulation tasks. However, most of the existing works do not address the issue of control stability.
S. A. Khader +3 more
semanticscholar +1 more source
Design and Implementation of Novel LMI-Based Iterative Learning Robust Nonlinear Controller
Complexity, 2021 An iterative learning robust fault-tolerant control algorithm is proposed for a class of uncertain discrete systems with repeated action with nonlinear and actuator faults. First, by defining an actuator fault coefficient matrix, we convert the iterative
Saleem Riaz +3 more
doaj +1 more source
Imitation Learning With Stability and Safety Guarantees [PDF]
IEEE Control Systems Letters, 2020 A method is presented to learn neural network (NN) controllers with stability and safety guarantees through imitation learning (IL). Convex stability and safety conditions are derived for linear time-invariant systems with NN controllers by merging ...
He Yin, P. Seiler, Ming Jin, M. Arcak
semanticscholar +1 more source
Efficient Learning of a Linear Dynamical System With Stability Guarantees [PDF]
IEEE Transactions on Automatic Control, 2021 We propose a principled method for projecting an arbitrary square matrix to the nonconvex set of asymptotically stable matrices. Leveraging ideas from large deviations theory, we show that this projection is optimal in an information-theoretic sense and ...
Wouter Jongeneel, Tobias Sutter, D. Kuhn
semanticscholar +1 more source
An Actor-Critic Framework for Online Control With Environment Stability Guarantee
IEEE Access, 2023 Online actor-critic reinforcement learning is concerned with training an agent on-the-fly via dynamic interaction with the environment. Due to the specifics of the application, it is not generally possible to perform long pre-training, as it is commonly ...
Pavel Osinenko +3 more
doaj +1 more source
Evolving stochastic learning algorithm based on Tsallis entropic index [PDF]
, 2005 In this paper, inspired from our previous algorithm, which was based on the theory of Tsallis statistical mechanics, we develop a new evolving stochastic learning algorithm for neural networks.
Anastasiadis, A.D., Magoulas, George D.
core +3 more sources
Stability-Guaranteed Reinforcement Learning for Contact-Rich Manipulation [PDF]
IEEE Robotics and Automation Letters, 2020 Reinforcement learning (RL) has had its fair share of success in contact-rich manipulation tasks but it still lags behind in benefiting from advances in robot control theory such as impedance control and stability guarantees.
S. A. Khader +3 more
semanticscholar +1 more source