Network


Latest external collaboration on country level. Dive into details by clicking on the dots.

Hotspot


Dive into the research topics where Bernardo Morcego is active.

Publication


Featured researches published by Bernardo Morcego.


advances in computing and communications | 2010

Negotiation and Learning in distributed MPC of Large Scale Systems

Valeria Javalera; Bernardo Morcego; Vicenç Puig

A key issue in distributed MPC control of Large Scale Systems (LSS) is how shared variables among the different MPC controller in charge of controlling each system partition (subsystems) are handled. When these connections represent control variables, the distributed control has to be consistent for both subsystems and the optimal value of these variables will have to accomplish a common goal. In order to achieve this, the present work combines ideas from Distributed Artificial Intelligence (DAI), Reinforcement Learning (RL) and Model Predictive Control (MPC) in order to provide an approach based on negotiation, cooperation and learning techniques. Results of the application of this approach to a small drinking water network show that the resulting trajectories of the levels in tanks (control variables) can be acceptable compared to the centralized solution. The application to a real network (the Barcelona case) is currently under development.


mediterranean conference on control and automation | 2011

Heading control system design for an unmanned helicopter

Fatiha Nejjari; Eleazar Saldívar; Bernardo Morcego

Unmanned Aerial Vehicles (UAVs) are used for a variety of activities, such as rescuing, reconnaissance and surveillance. Thus, more and more fully autonomous UAVs are expected. In this paper, we consider the problem of modelling and controlling the tail motion of an UAV along a desired trajectory. First, the response data of the system is collected during special flight test and a linear time invariant model is extracted by identification technique. Then, the control system is designed and implemented using a PID feedback/feedforward control method. Simulation results show that the identified model is very accurate and the designed control system is quite well.


Applied Intelligence | 2004

MIGA, A Software Tool for Nonlinear System Modelling with Modular Neural Networks

Bernardo Morcego; Josep M. Fuertes; Gabriela Cembrano

This paper presents a software tool suitable for dynamic system modelling. The models generated by this tool are modular neural networks, see [1]. Each module behaves like a functional block and is connected to the other modules like in classical block diagrams. This tool allows the inclusion of a priori knowledge and, furthermore, to extract physical information from the models, once the system has learned. The modelling tool is capable of automatic model generation, parameter estimation and model validation.


Proceedings of International Workshop on Neural Networks for Identification, Control, Robotics and Signal/Image Processing | 1996

Neural modules: networks with constrained architectures for nonlinear function identification

Bernardo Morcego; Josep M. Fuertes; Gabriela Cembrano

The aim of this work is the design of a class of neural networks for nonlinear function identification: the so-called neural modules. A neural module is a neural network with an internal structure specially designed to be able to learn and mimic the behaviour of a certain class of dynamic systems. Neural networks are abstract models well suited for approximating nonlinear functions. The training cost and the structural complexity of neural networks can be drastically reduced if a-priori knowledge of the function to be learned is internally incorporated in the form of structural constraints. The resulting neural network has less parameters than a conventional one, much faster learning convergence and it can provide meaningful information about the learned nonlinear function. This paper describes the design of a useful set of neural modules for system identification and gives general guidelines for the design of neural modules. The resulting networks are evaluated and their use on general systems identification is pointed out.


Archive | 2014

Distributed MPC Using Reinforcement Learning Based Negotiation: Application to Large Scale Systems

Bernardo Morcego; Valeria Javalera; Vicenç Puig; R. Vito

This chapter describes a methodology to deal with the interaction (negotiation) between MPC controllers in a distributed MPC architecture. This approach combines ideas from Distributed Artificial Intelligence (DAI) and Reinforcement Learning (RL) in order to provide a controller interaction based on negotiation, cooperation and learning techniques. The aim of this methodology is to provide a general structure to perform optimal control in networked distributed environments, where multiple dependencies between subsystems are found. Those dependencies or connections often correspond to control variables. In that case, the distributed control has to be consistent in each subsystem. One of the main new concepts of this architecture is the negotiator agent. Negotiator agents interact with MPC agents to reach an agreement on the optimal value of the shared control variables. The optimal value of those shared control variables has to accomplish a common goal, probably incompatible with the specific goals of each partition that share the variable. Two cases of study are discussed, a small water distribution network and the Barcelona water network. The results suggest that this approach is a promising strategy when centralized control is not a reasonable choice.


mediterranean conference on control and automation | 2012

Coaxial UAV helicopter control laboratory design

Bernardo Morcego

This paper describes the design of a low cost laboratory platform to perform control related exercises with an UAV (Unmanned Aerial Vehicle). All the elements this platform is made up of are very common laboratory instruments or of the shelf toys. The types of experiments one can perform are SISO and MIMO UAV modeling and identification as well as control.


IFAC Proceedings Volumes | 2010

Distributed MPC for large scale systems using agent-based reinforcement learning

Valeria Javalera; Bernardo Morcego; Vicenç Puig

Abstract In the present work, distributed control and artificial intelligence are combined in a control architecture for Large Scale Systems (LSS). The aim of this architecture is to provide a general structure and methodology to perform optimal control in networked distributed environments where multiple dependencies between sub-***systems are found. Often these dependencies or connections represent control variables so the distributed control has to be consistent for both subsystems and the optimal value of these variables has to accomplish a common goal. The aim of the research described in this paper is to exploit the attractive features of MPC (meaningful objective functions and constraints) in a distributed implementation combining learning techniques to perform the negotiation of these variables in a cooperative Multi Agent environment and over a Multi Agent platform to provide speed, scalability, and computational effort reduction. This approach is based on negotiation, cooperation and learning. Results of the application of this architecture to a small drinking water network show that the resulting trajectories of the levels in tanks (control variables) can be acceptable compared to the centralized solution. The application to a real network (the Barcelona case) is currently under development.


Journal of Biomedical Optics | 2016

Blinking supervision in a working environment

Bernardo Morcego; Marc Argilés; Marc Cabrerizo; Genís Cardona; Ramon Pérez; Elisabet Pérez-Cabré; Joan Gispets

Abstract. The health of the ocular surface requires blinks of the eye to be frequent in order to provide moisture and to renew the tear film. However, blinking frequency has been shown to decrease in certain conditions such as when subjects are conducting tasks with high cognitive and visual demands. These conditions are becoming more common as people work or spend their leisure time in front of video display terminals. Supervision of blinking frequency in such environments is possible, thanks to the availability of computer-integrated cameras. Therefore, the aim of the present study is to develop an algorithm for the detection of eye blinks and to test it, in a number of videos captured, while subjects are conducting a variety of tasks in front of the computer. The sensitivity of the algorithm for blink detection was found to be of 87.54% (range 30% to 100%), with a mean false-positive rate of 0.19% (range 0% to 1.7%), depending on the illumination conditions during which the image was captured and other computer–user spatial configurations. The current automatic process is based on a partly modified pre-existing eye detection and image processing algorithms and consists of four stages that are aimed at eye detection, eye tracking, iris detection and segmentation, and iris height/width ratio assessment.


conference on control and fault tolerant systems | 2016

Modelling and control of a coaxial helicopter UAV in an indoor laboratory

Bartomeu Rubi; Ramon Pérez; Bernardo Morcego

This paper describes the modelling, the control algorithm and the flight experiments performed with an Unmanned Aerial Vehicle (UAV). The vehicle is a coaxial toy helicopter and the control platform is an indoor platform with a computer vision sensor. The dynamic model of the vehicle as well as the identification process of its parameters are described. The controller consists on a cascade control structure formed by trajectory, velocity and attitude control loops implemented with PID-based controllers. The experimental results show a maximum position error of 5cm on hovering experiments and exhibit a great precision in the trajectory tracking experiments.


Optometry and Vision Science | 2016

Real-Time Non-Intrusive Assessment of Viewing Distance during Computer Use.

Marc Argilés; Genís Cardona; Elisabet Pérez-Cabré; Ramon Pérez-Magrané; Bernardo Morcego; Joan Gispets

Purpose To develop and test the sensitivity of an ultrasound-based sensor to assess the viewing distance of visual display terminals operators in real-time conditions. Methods A modified ultrasound sensor was attached to a computer display to assess viewing distance in real time. Sensor functionality was tested on a sample of 20 healthy participants while they conducted four 10-minute randomly presented typical computer tasks (a match-three puzzle game, a video documentary, a task requiring participants to complete a series of sentences, and a predefined internet search). Results The ultrasound sensor offered good measurement repeatability. Game, text completion, and web search tasks were conducted at shorter viewing distances (54.4 cm [95% CI 51.3–57.5 cm], 54.5 cm [95% CI 51.1–58.0 cm], and 54.5 cm [95% CI 51.4–57.7 cm], respectively) than the video task (62.3 cm [95% CI 58.9–65.7 cm]). Statistically significant differences were found between the video task and the other three tasks (all p < 0.05). Range of viewing distances (from 22 to 27 cm) was similar for all tasks (F = 0.996; p = 0.413). Conclusions Real-time assessment of the viewing distance of computer users with a non-intrusive ultrasonic device disclosed a task-dependent pattern.

Collaboration


Dive into the Bernardo Morcego's collaboration.

Top Co-Authors

Avatar

Vicenç Puig

Spanish National Research Council

View shared research outputs
Top Co-Authors

Avatar

Valeria Javalera

Polytechnic University of Catalonia

View shared research outputs
Top Co-Authors

Avatar

Carlos Ocampo

Polytechnic University of Catalonia

View shared research outputs
Top Co-Authors

Avatar

Joseba Quevedo

Polytechnic University of Catalonia

View shared research outputs
Top Co-Authors

Avatar

Ramon Pérez

Polytechnic University of Catalonia

View shared research outputs
Top Co-Authors

Avatar

Teresa Escobet

Polytechnic University of Catalonia

View shared research outputs
Top Co-Authors

Avatar

Elisabet Pérez-Cabré

Polytechnic University of Catalonia

View shared research outputs
Top Co-Authors

Avatar

Fatiha Nejjari

Polytechnic University of Catalonia

View shared research outputs
Top Co-Authors

Avatar

Gabriela Cembrano

Spanish National Research Council

View shared research outputs
Top Co-Authors

Avatar

Genís Cardona

Polytechnic University of Catalonia

View shared research outputs
Researchain Logo
Decentralizing Knowledge