T.T. Ho

Model-Free Swing-Up and Balance Control of a Rotary Inverted Pendulum using the TD3 Algorithm: Simulation and Experiments

T.T. Ho, Van-Dong-Hai Nguyen

The Rotary Inverted Pendulum (RIP) system is a highly nonlinear and under-actuated mechanical system, which presents significant challenges for traditional control techniques. In recent years, Reinforcement Learning (RL) has emerged as a prominent nonlinear control technique, demonstrating efficacy in regulating systems exhibiting …

vn (code pays fourni par la source)

Applying DDPG Algorithm to Swing-Up and Balance Control for a Double Inverted Pendulum on a Cart

T.T. Ho, Thanh-Sang Tat, Hoang-Anh Ngo, Truong-Son Nguyen et autres

In this study, we apply the Deep Deterministic Policy Gradient (DDPG) algorithm in reinforcement learning to control a double inverted pendulum on a cart (DIPC)- a high order single input-multi output (SIMO) system . The simulation results demonstrate DDPG's stability and effectiveness …

vn (code pays fourni par la source)

Stochastic neural adaptive control for nonlinear time varying systems based on Newton and gradient optimizations

T.T. Ho, Hai T. Ho

The authors present a stochastic neural adaptive control algorithm for nonlinear time-varying systems. The implicit neural identification is derived based on the Newton optimization approach. Using the one-step-prediction quadratic performance index, the authors design a control law which in combination with the …

us (code pays fourni par la source)

Stochastic neural direct adaptive control based on minimum variance optimization

T.T. Ho, Hai T. Ho

Based on the state space control theory and a neural network architecture, the authors present a stochastic neural direct adaptive control algorithm (SNDAC) for partially known state space nonlinear time varying plants. A neural network is used to generate the control signal, …

us (code pays fourni par la source)

Generalized stochastic state space neural adaptive control

T.T. Ho

A generalized stochastic neural adaptive control algorithm is presented, where the system identification is based on the state space innovations model and a neural network architecture. This identification algorithm is derived from three different optimization approaches, i.e., the gradient, Newton, and minimum …

Stochastic neural direct adaptive control

T.T. Ho, Hai T. Ho, Jan T. Białasiewicz, Edward T. Wall

A stochastic neural direct adaptive control algorithm for partially known state-space nonlinear time-varying plants is presented. A neural network is used to generate the control signal, which optimizes a quadratic (one-step-ahead prediction) performance index. In comparison to conventional stochastic state-space adaptive control, …

us (code pays fourni par la source)

Stochastic fuzzy direct adaptive control

T.T. Ho

Presents a stochastic fuzzy adaptive control algorithm for a class of nonlinear systems, where the control signal is generated by a fuzzy controller based on optimization of a quadratic performance index. Additionally, the described control approach connects the classical optimal state-space controls …

Stochastic neural adaptive control using state space innovations model

T.T. Ho, Shine Tzong HO, Jan T. Białasiewicz, Edward T. Wall

An attempt is made to contribute to the unification of traditional state space adaptive control and neural system theory. A stochastic neural adaptive control algorithm, where the system identification is based on the state space innovations model, which employs a neural network …

us (code pays fourni par la source)