Henry Diaz-Iza

RESEARCH, TEACHING, or OTHER INTERESTS

Control and Optimization, Control and Systems Engineering, Electrical and Electronic Engineering

Scopus Publications

Analysis of the Reliability of the Calibration of a Camera Through the Knowledge of Its Extrinsic Parameters
Henry Dí­az-Iza, Harold Díaz-Iza, Wilmer Albarracín, and Rene Cortijo
Springer Nature Switzerland



Fuzzy Control Application to an Irrigation System of Hydroponic Crops under Greenhouse: Case Cultivation of Strawberries (Fragaria Vesca)
Edgar Maya Olalla, Andres Lopez Flores, Marcelo Zambrano, Mauricio Domínguez Limaico, Henry Diaz Iza, and Carlos Vasquez Ayala
MDPI AG
Hydroponics refers to a modern set of agricultural techniques that do not require the use of natural soil for plant germination and development. These types of crops use artificial irrigation systems that, together with fuzzy control methods, allow plants to be provided with the exact amount of nutrients for optimal growth. The diffuse control begins with the sensorization of the agricultural variables that intervene in the hydroponic ecosystem, such as the environmental temperature, electrical conductivity of the nutrient solution and the temperature, humidity, and pH of the substrate. Based on this knowledge, these variables can be controlled to be within the ranges required for optimal plant growth, reducing the risk of a negative impact on the crop. This research takes, as a case study, the application of fuzzy control methods to hydroponic strawberry crops (Fragaria vesca). It is shown that, under this scheme, a greater foliage of the plants and a larger size of the fruits are obtained in comparison with natural cultivation systems in which irrigation and fertilization are carried out by default, without considering the alterations in the aforementioned variables. It is concluded that the combination of modern agricultural techniques such as hydroponics and diffuse control allow us to improve the quality of the crops and the optimization of the required resources.


Open-Source Technologies for Simulation and Operation of a Low-Cost Robotic Platform for Educational Mobile Robotics
Henry Díaz-Iza, Harold Díaz-Iza, Wilmer Albarracín, and Rene Cortijo
Springer Nature Singapore



Design of Optimal Controllers Applying Reinforcement Learning on an Inverted Pendulum Using Co-simulation NX/Simulink
Henry Díaz-Iza, Karla Negrete, and Jenyffer Yépez
Springer Nature Switzerland



Learning an Improved LMI Controller Based on Takagi-Sugeno Models via Value Iteration
Henry Díaz, Karla Negrete, and Jenyffer Yépez
Springer International Publishing



A linear programming methodology for approximate dynamic programming
Henry Díaz, Antonio Sala, and Leopoldo Armesto
University of Zielona Góra, Poland
Abstract The linear programming (LP) approach to solve the Bellman equation in dynamic programming is a well-known option for finite state and input spaces to obtain an exact solution. However, with function approximation or continuous state spaces, refinements are necessary. This paper presents a methodology to make approximate dynamic programming via LP work in practical control applications with continuous state and input spaces. There are some guidelines on data and regressor choices needed to obtain meaningful and well-conditioned value function estimates. The work discusses the introduction of terminal ingredients and computation of lower and upper bounds of the value function. An experimental inverted-pendulum application will be used to illustrate the proposal and carry out a suitable comparative analysis with alternative options in the literature.


Fitted Q-Function Control Methodology Based on Takagi-Sugeno Systems
Henry Diaz, Leopoldo Armesto, and Antonio Sala
Institute of Electrical and Electronics Engineers (IEEE)
This paper presents a combined identification/ Q-function fitting methodology that involves identification of a Takagi–Sugeno model, computation of (sub)optimal controllers from linear matrix inequalities (LMIs), and subsequent data-based fitting of the Q-function via monotonic optimization. The LMI-based initialization provides a conservative solution, but it is a sensible starting point to avoid convergence/local-minima issues in raw data-based fitted Q-iteration or Bellman residual minimization. An inverted-pendulum experimental case study illustrates the approach.


Approximate dynamic programming methodology for data-based optimal controllers
Henry Díaz, Leopoldo Armesto, and Antonio Sala
Universitat Politecnica de Valencia
<p>En este artículo se presenta una metodología para el aprendizaje de controladores óptimos basados en datos, en el contexto de la programación dinámica aproximada. Existen soluciones previas en programación dinámica que utilizan programación lineal en espacios de estado discretos, pero que no se pueden aplicar directamente a espacios continuos. El objetivo de la metodología es calcular controladores óptimos para espacios de estados continuos, basados en datos, obtenidos mediante una estimación inferior del coste acumulado a través de aproximadores funcionales con parametrización lineal. Esto se resuelve de forma no iterativa con programación lineal, pero requiere proporcionar las condiciones adecuadas de regularización de regresores e introducir un coste de abandono de la región con datos válidos, con el fin de obtener resultados satisfactorios (evitando soluciones no acotadas o mal condicionadas).</p>


Learning Upper-Level Policy using Importance Sampling-based Policy Search Method
Jose Pastor, Henry Diaz, Leopoldo Armesto, Alicia Esparza, and Antonio Sala
IEEE
Policy search methods are a successful approach to reinforcement learning. These allow to learn upper-level policies whose main advantage is that these distributions explore directly in the parameter space. The contribution of this paper is to propose an algorithm based on importance sampling methods and local linear regression that uses the samples in an efficient way. In order to get this aim, we propose to include information of all the past samples in the learning process using importance sampling methods. Additionally, we use the gradient direction of the linear local model reward to explore regions where the prediction of the reward could be better.


Improving LMI controllers for discrete nonlinear systems using policy iteration
Henry Diaz, Antonio Sala, and Leopoldo Armesto
IEEE
This paper presents a method to improve the conservative (shape-independent) controllers from guaranteed-cost LMIs using Q-learning policy iteration setups which learn optimal controllers from data. In this context, the proposed approach uses an initial parametrization based on the LMI solution and the learning process includes parameters related to the nonlinearity of the system (and its gradient). An approximation of the Q-function using polynomials of the membership functions in Takagi-Sugeno models is obtained using a policy iteration algorithm. The resulting controller is shape-dependent, that is, uses the knowledge of membership functions, their gradients and data to improve well-known LMI solutions.


Improvement of LMI controllers of Takagi-Sugeno models via Q-learning
Henry Díaz, Leopoldo Armesto, and Antonio Sala
Elsevier BV