Mobile robotics for the automatic surveillance of premises and identification of dangerous situations in challenging conditions using deep learning techniques

Title: Mobile robotics for surveillance using deep learning techniques

Funded by: Agencia Estatal de Investigación - Ministerio de Ciencia, Innovación y Universidades

Duration: Desde 01/09/2024 hasta 31/12/2027

Description: The project proposes the use of mobile robots for the automatic surveillance of premises, including indoor and outdoor areas and for the identification of risk situations in challenging operation conditions, with the common philosophy of using AI tools for the robust approach to these issues. Currently, these tasks are carried out by specialized personnel, with the help of cameras located in fixed positions. We propose to achieve much more effective surveillance through mobile robots that can patrol the areas to be monitored and use different types of sensors (visible spectrum cameras, infrared cameras, laser range sensors, etc.) to detect both risk elements and situations. It is expected that the results of this project can be relevant both for security companies and for the State security forces and bodies.

To achieve this goal, the project is structured into two main objectives. The first one consists in the development of algorithms for the navigation of mobile robots in large social environments and in challenging operation conditions. The second will address the perception and integration of technologies for interpretation of the environment and the resolution of security and surveillance tasks with mobile robots. Both objectives are fully aligned with current research trends in mobile robotics and sensory perception and the research team plans to contribute to the generation of knowledge in these areas.

In addition, the proposal also provides solutions to specific problems in the thematic priority "Digital world, industry, space and defense", since it pursues the digitalization of tasks related to improving the security of venues, infrastructures, buildings and industrial facilities. The fact of using mobile robots gives the proposal great capacity and versatility to detect risk situations. However, this requires that the methods developed within the framework of the two objectives expressly take into account the specificities of this kind of applications. In this way, the project addresses, among other tasks: (a) the creation of maps of extensive environments, indoors and outdoors, with useful semantic information for security and surveillance tasks, including the systematic exploration of a priori unknown environments, (b) the location of the robot itself (both indoors and outdoors, including adverse lighting conditions) and the alarms or risk situations detected from the fusion of sensory information, (c) the planning of trajectories for surveillance, carrying out sweeps of the assigned areas, paying special attention to critical points and boundaries of the enclosure and in collaboration with the human operator, (d) the interpretation of the environment based on sensory data, with special attention to critical elements for security tasks and to the risk situations detected, such as fire outbreaks or people falling. In addition to the development of these algorithms designed to address the specificities of this type of applications, the work plan contemplates the integration and implementation of a common graphical interface that shows the created map, the estimated position of the robot and the alarms, intrusions or elements potentially dangerous detected and that will allow interaction with the operator, so that he of she can influence the task carried out by the mobile robot.

Grant funded by Agencia Estatal de Investigación - Ministerio de Ciencia, Innovación y Universidades and by the European Union.

This website is part of the project PID2023-149575OB-I00, funded by MICIU/AEI/10.13039/501100011033 and by FEDER, UE.

Keywords: Mobile robot, visual perception, point cloud, deep learning, sensor fusion, localization, mapping, environment interpretation

Head Researcher: A. Gil, L. Payá

IA-GAMMAPATIA

Title: Análisis inicial de herramientas de IA para la predicción de la malignización de las gammapatías de significado incierto a mieloma múltiple u otras patologías linfoproliferativas

Funded by: Generalitat Valenciana

Duration: 01/2023 - 12/2023

Description: Existe el riesgo de progresión de pacientes con gammapatía monoclonal de significado incierto a Mieloma Múltiple. Aunque se conocen clasificaciones basadas en el riesgo de evolución a cáncer, hay que realizar controles médicos de por vida para detectar la evolución hacia la malignización de las gammapatías. Se explorarán los datos existentes y se realizará un análisis inicial del funcionamiento de diversas herramientas de IA, para establecer la capacidad de predicción de cada una de ellas.

Proyecto financiado por la Consellería de Innovación, Universidades, Ciencia y Sociedad Digital de la Generalitat Valenciana
Valencian Innovation Agency

Head Researcher: L. Payá

AViRobots

Title: Development of an intelligent surveillance and security infrastructure system based on mobile robots

Funded by: AVI (Agència Valenciana de la Innovació)

Duration: 01/2023 - 12/2025

Description: The project focuses on the use of terrestrial mobile robots for the surveillance of indoor and outdoor environments, access control and people identification. It is proposed the realization of technological developments that digitize and automate the tasks of surveillance of buildings and infrastructures by means of mobile robots aided by artificial intelligence techniques. The project considers the development of a complete surveillance system that will integrate: a set of intelligent mobile robots equipped with sensors, a human-machine interface software system that will allow efficient interaction between operators and robots and, finally, a wireless communications system that will allow the exchange of information in the system.

The developed system can be exploited by security companies for the surveillance of indoor or outdoor environments or by law enforcement agencies. During the course of the project, a demonstration system will be created to validate this application and make it ready for a level close to the market. In this way, the aim is to reduce uncertainties about the technical and commercial viability of this technology. The demonstrators will make it possible to test the operation of the monitoring system under real operating conditions and will also make it possible to present the product to companies interested in its commercial exploitation.

This project with reference INNVA1/2023/61 has been funded by the Valencian Innovation Agency.

Keywords: Mobile robots, visual perception, multisensory fusion, infrastructure surveillance

Head Researcher: Arturo Gil, Luis Payá

NANOTERASUCO

Title: Nanoformulaciones de sulfuro de cobre como agentes terapéuticos para tumores de mal pronóstico

Funded by: Unisalut

Duration: 2023

Description: Esta acción preparatoria se centrará en demostrar la capacidad de nanoformulaciones de sulfuro de cobre (CuS) de producir hipertermia e inducir muerte celular selectiva en modelos celulares de tres tipos de tumores de mal pronóstico (glioblastoma, carcinoma de páncreas exocrino y de colon). Evaluar su potencial como monoterapia o terapia combinada en este tipo de tumores y explorar las ventajas que supone la activación de estas nanoformulaciones por irradiación en el infrarrojo cercano.

Head Researcher: J.C. Ferrer

Modelado predictivo y caracterización física de dispositivos optoelectrónicos e híbridos mediante técnicas de inteligencia artificial soportadas por aprendizaje automático y profundo

Title: Modelado predictivo y caracterización física de dispositivos optoelectrónicos e híbridos mediante técnicas de inteligencia artificial soportadas por aprendizaje automático y profundo

Funded by: Generalitat Valenciana. Programa I+D+i 2022. Conselleria de Innovación, Universidades, Ciencia y Sociedad Digital.

Duration: 01/01/2022 - 31/12/2023

Description: Este proyecto plantea la optimización y mejora de las propiedades de dispositivos optoelectrónicos como fotodectectores orgánicos e híbridos mediante modelado predictivo sustentado por técnicas computacionales de Inteligencia Artificial tales como regresión e inferencia gaussiana, aprendizaje automático y profundo, aprendizaje por refuerzo y aprendizaje por transferencia. El procedimiento de fabricación de estos dispositivos entraña una serie de costes y riesgos, los cuales se pretenden minimizar a partir de la obtención de una caracterización predicha mediante modelos predictivos computacionales, sustentados principalmente por redes neuronales convolucionales. Así pues, se espera mejorar los resultados reales en términos de sus propiedades eléctricas, como son sus magnitudes de tensión, corriente y eficiencia de conversión. Pero también en términos de comportamiento temporal, ciclos de vida medio, durabilidad, así como en aspectos relacionados con el ecodiseño: residuos de fabricación, huella de CO2, huella hídrica, etc.

A su vez, las mencionadas técnicas computacionales, permitirán actualizar los modelos predictivos con los datos de caracterización reales, medidos tras la fabricación de los dispositivos. El modelado también tendrá por objeto la optimización de las variables y parámetros implicados en la fabricación, especialmente concentrada en los materiales fotoelectrónicos basados en el dopados por óxido de grafeno reducido con inclusión del rGO en la capa de transporte. Además, también se trabajará con dispositivos asistidos por nanopartículas semiconductoras inorgánicas con inclusión de nanocompuestos en la capa activa. Finalmente, y dado el bajo coste de estos dispositivos, también se modelará el comportamiento de los mismos, una vez integrados en un sistema de comunicaciones digitales con luz en el espectro visible.

Head Researcher: David Valiente

HORAS

Title: Optimal classification of pieces in production proceses

Funded by: Ministerio de Ciencia e Innovación

Duration: 3 años

Description: HORAS project is composed of two parts. First one, aims to design and program a robotic station, formed by a set of "n" robots, performing a pick-and-place process of flat pieces for the apparel industry and its subsequent classification, either by type or by pieces needed to create a product. The second part is software development based on the programming of a system using Python to obtain data from CAD files from industrial machinery and send it directly to the set of robots transferring CAD information directly to the system to perform the gripping and sorting operations. First, we will conduct a study of the current state of the art in the use of general purpose, parallel and collaborative industrial robots to determine which ones are best suited to the task to perform. Once the process features and robots have been analyzed, the virtual station will be designed using selected manufacturer's software. This station will perform the process of cutting sheets of a material using a CNC machine and then, thanks to a conveyor belt, these pieces will be transported to the pick- and-place station, where the robots, suspended on a gantry on the belt, will be in charge of performing the pick-and-place task and its subsequent classification and placement of the pieces. Finally, we will focus on the simulation of the station, with the analysis and evaluation of obtained results to check its correct operation. To carry out this process, we will design and build the necessary tooling to equip the robot system with the capacity to grip flat pieces for optimized sorting. This tooling will take into account that some of the materials used in the fashion industry are very porous, so it will be equipped with a matrix of vacuum suction cups and an additional matrix of needles for gripping porous and delicate materials. Each of the matrix elements will be selectively activated to grip only the target piece and not the adjacent ones. To this end, a computer vision algorithm will be created with the ability to position the robot tooling so that there are the maximum number of tool gripping points for each of the pieces being handled. The gripping of the pieces by the robot cannot be done by vision recognition since the pieces are cut in the raw material from which they come out. This cut is so thin that it is imperceptible to the machine vision system and it is necessary to use the information coming from the CAD file of the machine to be able to know the position and orientation of each of the pieces. Therefore, in the second part of the project, we will develop a Python program to read the files obtained from a CNC machine with the design of the cut made, provided by the company Comelz and with which we will obtain the position data, rotation, and the name of each of the template models present in the file. These data will be sent through a socket to the robot in its native language. With this data, the robot will be able to perform the pick-and-place task, in a more automated way, and its subsequent classification. The goal of the system is to perform the manipulation of hundreds of pieces in the shortest time possible. For this purpose, a set of robots will be used working coordinated so as not to collide with each other and to grab each piece to perform the task in the minimum possible time, including especially the order of the operations to be performed.

Keywords: Computer vision, robotics, optimization

Head Researcher: Carlos Pérez Vidal

TED2021

Title: Development of intelligent mobile technologies to address security tasks and surveillance indoors and outdoors

Funded by: Agencia Estatal de Investigación. Ministerio de Ciencia e Innovación

Duration: 12/2022 - 11/2024

Description: This project proposes using mobile robots and machine learning technologies to carry out surveillance and security tasks in indoor and outdoor environments. During the course of the project, it is expected to generate scientific knowledge and carry out technological developments that digitize and automate the tasks of surveillance of buildings, infrastructures and industry. Such developments are expected to have potential of technology transfer to security companies, State security forces and emergency units.

Currently, these tasks are carried out by specialized personnel, with the aid mainly of cameras located in fixed positions and cctv systems. In this project, it is proposed to perform this surveillance in a much more effective way and more safely for these personnel, with the support of cooperating mobile robots that can patrol the areas to be monitored and use different types of sensors (omnidirectional vision cameras, infrared cameras, laser range and proximity sensors) and sensor fusion technologies to address two major problems: (a) robot navigation through the environment to be monitored, including building a model or map, localization and trajectory planning and (b) interpretation of the environment so that suspicious objects, intrusions by unauthorized personnel and other potentially dangerous situations such as fire sources and overheating in facilities can be detected. The project includes the creation of an intuitive graphical interface that allows the user to interact with the robots and maps created, know the alarms that have been generated and influence the task carried out by the robots.

Both the cooperation between the robots themselves and the cooperation between the potential remote operator and the robots is critical to effective surveillance. It is a cutting-edge technological aspect with great development in current international research works. Other technologies involved in the project, such as object and person recognition, deep learning and autonomous robot navigation, are also among the most developed today. The proposing research group has a consolidated track record and extensive experience in the fields of mobile robotics, machine learning, image processing and sensor fusion.

Therefore, the proposed idea is framed within the field of digital transition and seeks to improve and enhance technology to apply it to security and surveillance tasks in buildings, infrastructures and facilities. The main goal of the project is to ameliorate the quality of the work of security employees and improve the competitiveness of security companies. In particular, the use of mobile robots is proposed in situations in which the use of static security cameras is inappropriate or insufficient, or to serve as support and assistance to existing security personnel. A use case will be, for example, the surveillance of large areas of land in adverse conditions (cold, extreme heat). In addition, the mobile robots will be equipped with sensors that will allow the detection of intrusions or security failures in low or no lighting conditions. The proposal also aims to have a minimum ecological impact, as it will use highly efficient electric mobile robots.

This project has been founded by Agencia Estatal de Investigación. Ministerio de Ciencia e Innovación

MICIU Servicio de Comunicación, Marketing y Atención al ...

Keywords: Mobile robot, computer vision, image processing, sensor fusion, robot navigation, deep learning

Head Researcher: A. Gil, L. Payá

SubActuatedRobots

Title: Securing manipulator robots with free-swinging joint failures by extinguishing their uncontrolled self-movements

Funded by: CONSELLERIA DE INNOVACIÓN, UNIVERSIDADES, CIENCIA Y SOCIEDAD DIGITAL

Duration: 1/1/22-31/12/23

Description:

When a fully actuated robot suffers a free swing failure (or torque failure) in any of its actuated joints, the robot becomes underactuated and allows uncontrolled movements even if we block the rest of the healthy actuators. Such uncontrolled movements are dangerous because they can cause the robot to collide with itself or with obstacles in the environment.

In this project we propose to develop a method to control robots that have suffered such free swing failure, in order to lock the underactuated robot without using redundant actuators or brakes, safely suppressing its uncontrolled free swing movements. The proposed method consists of varying the healthy actuated joints until the self-motion motions of the underactuated robot degenerate to a point. Such self-motion varieties are higher-dimensional curves, surfaces, and analogs, and their shape and size change as the healthy actuated joints move. Since uncontrolled motions of an underactuated robot occur along such self-motion moieties, making such moieties degenerate at a point effectively suppresses such uncontrolled motions, since the range of uncontrolled motion of the robot is reduced to a single point.
Valencian Innovation Agency

Keywords: Parallel robot, underactuated, redundant, self-moving varieties, free swing failure, torque failure

Head Researcher: Adrián Peidró

TorqFailRob

Title: Control of parallel robots that have suffered torque failure

Funded by: Universidad Miguel Hernández, Vdo. de Investigación

Duration: 1/1/22-31/12/22

Description:

This project aims to develop control and stabilization algorithms for parallel robots that have suffered torque failure in one of their actuators. When this happens, the joint connected to the failed actuator behaves as a passive joint that can rotate freely, causing the loss of control of the robot. This is a dangerous situation since the robot can move freely without control and could collide with itself or with objects in the environment.

The method intended to be applied in this project is novel since it does not require brakes or redundant actuators, and consists of moving the healthy actuators of the robot to positions where the self-motion varieties vanish. Such self-motion varieties are curves or surfaces on which the robot can slide freely when its healthy actuators are blocked.

Keywords: variety of self-motion, parallel, underactuated robot

Head Researcher: Adrián Peidró

HyReBot

Title: Hybrid Robots and Multisensory Reconstruction for Applications in Lattice Structures (HyReBot)

Funded by: Ministerio de Ciencia e Innovación

Duration: 09/2021 - 08/2024

Description: The use of reticular structures, which are composed of a number of beams or bars closely intertwined, is widespread nowadays in the construction of all types of fastening and support components for different infrastructures. They are especially indicated in metal bridges but also in roofs of hangars and spacious industrial buildings. They are generally formed by a set of highly interlinked and interconnected bars, joined together by nodes (either rigid or articulated), forming a three-dimensional structural mesh. The execution of both inspection and maintenance tasks on this type of reticular structures is especially challenging owing to (a) the access problems because of the high interconnection of the bars through the nodes and (b) the complexity of going through paths that permit moving from one starting point to a target point while traversing these structural nodes.

Aerial vehicles have been considered along the past few years as a possible solution to automate these inspection and maintenance tasks on reticular three-dimensional structures. However, the high complexity of such structures (often including narrow gaps between nodes and bars and with a strongly heterogeneous distribution) limits the use of this type of aerial vehicles, since they could not enter the different internal locations of the structure that are not easily accessible. Another of the limitations of this type of vehicles is their limited manipulation capacity while they are in the air.

The present research project focuses on this field. The project will explore the possibility of using robotic units that can move along these reticular structures in such a way that they can navigate through them with 6 degrees of freedom and traverse the reticular nodes present in them, regardless of their arrangement, layout and 3D configuration of the mesh. To address these inspection and / or maintenance tasks, this research project proposes the analysis, design and implementation of hybrid robots. They will consist of simple modules with few degrees of freedom, either with serial or parallel structure, designed in such a way that, when combined into hybrid robots, they can effectively navigate through these reticular structures despite all the challenging issues they present. In addition to analyzing these robots in depth, both from the kinematic and dynamic point of view, we propose to analyze and demonstrate their ability to navigate through such reticular workspaces, negotiating any possible arrangement of reticular nodes present in such structures.

Finally, it is essential to have a sufficiently precise model of the reticular structure in which these modular robots have to operate and to estimate efficiently their position and orientation in this environment. Considering the experience of the members of the research team in previous projects, the present project also proposes performing the reconstruction of these environments (three-dimensional grid structures), based on the fusion of the information provided by both range and visual sensors in a 360o field of perception around the robot. To achieve this objective, deep learning techniques will be used to efficiently process the high amount of data provided by the sensors.

Project PID2020-116418RB-I00 funded by MCIN/AEI/10.13039/501100011033.
Agencia Estatal de Investigación

Keywords: Hybrid robots, visual perception, sensor fusion, reticular structures

Head Researcher: L. Payá, O. Reinoso

PROMETEO2021

Title: Towards Further Integration of Intelligent Robots in Society: Navigate, Recognize and Manipulate

Funded by: GENERALITAT VALENCIANA

Duration: 01/2021 - 12/2024

Description:

In recent years, the number of robots used to perform tasks autonomously in multiple fields and sectors has gradually increased. Today, we can find robots performing repetitive tasks in controlled environments, addressing complex and sometimes dangerous tasks. However, having robots perform tasks in uncontrolled environments with the presence of objects and moving elements (such as people and other robots) and requiring the need to move between different points in the scene presents notable challenges that need to be addressed to enable greater integration of robots in such scenarios.

This research project aims to tackle activities within this scope in three specific lines: navigation, recognition, and manipulation, in order to advance the integration of robots and the performance of tasks in these environments. On one hand, it is necessary to consider the presence of humans in these social environments, as their possible movements and behavior will affect how robots should move and, ultimately, navigate within these scenarios. Additionally, there is a need to advance in the tasks of environment recognition, identifying the scenarios to make the localization of robots within them more robust and precise. Finally, the problem of object manipulation by these robots will be addressed, considering both the flexibility in shape and the deformability of these objects.

Project PROMETEO 075/2021 is funded by the Consellería de Innovación, Universidades, Ciencia y Sociedad Digital de la Generalitat Valenciana
Valencian Innovation Agency

Head Researcher: Oscar Reinoso

RETIC

Title: Planning of robotic movements in metallic structures

Funded by: Universidad Miguel Hernández de Elche

Duration: 01/01/2021 - 31/12/2022

Description:

Nowadays, we encounter three-dimensional metallic lattice structures in numerous artificial constructions, such as stadiums, high-voltage or telecommunications towers, airports, construction sites, pipeline networks in refineries, nuclear power plants, and aerospace constructions. These structures, composed of interconnected bars forming genuine metallic networks, require periodic inspection and maintenance to preserve their good condition and functionality and to prevent their structural stability from being compromised by deterioration. Examples of the required tasks include coating the metallic bars of the structure with protective paints to prevent corrosion, non-destructive inspection to detect possible cracks and welding defects, and tightening threaded joints, among others.

Traditionally, these tasks have been performed by human operators who, equipped with safety mechanisms such as harnesses, have to climb the structure and carry out the aforementioned operations. Despite the possible safety measures that can be adopted, performing these operations is dangerous for humans, who are subjected to significant safety and health risks. In order to avoid these dangers to human operators, the possibility of performing these hazardous tasks at height using robots (autonomous or teleoperated) has been pursued over the past three decades. In this project, the objective is to plan movements that a hybrid robot can perform so that it can navigate through these structures and pass through the structural nodes, attaching itself appropriately to carry out inspection and maintenance tasks.

Head Researcher: Oscar Reinoso Garcia

DECODED

Title: Decoding brain activity related to gait during exoskeleton-assisted walking

Funded by: European Union’s Horizon 2020 research and innovation programme, via an Open Call issued and executed under Project EUROBENCH

Duration: 01/04/2021 hasta 31/05/2022

Description: Lower-limb robotic exoskeletons have emerged as aids for over-ground, bipedal ambulation for individuals with motor limitations. The usability and clinical relevance of these robotics systems could be further enhanced by brain-machine interfaces (BMIs). Different approaches have been explored in the last decade to use BMIs based on EEG to interact with robotics exoskeletons. One of these approaches is based on detecting users’ motor imagery related to walk. In this regard, our group have developed different BMIs exploring the capabilities of using motor imagery for commanding exoskeletons. In addition, as the performance of current BMIs has to improve in order to command exoskeletons not only in clinic environments, but also at home or outdoors, our group is currently implementing a new BMI based on the combination of two paradigms: motor imagery and user’s attention during walking. Indeed, we have just published a paper showing some promising results using this new BMI. However, in this BMI, motor imagery is decoded only while users are walking through typical flat grounds and users’ attention is estimated from EEG.

In this proposal we will use several EUROBENCH scenarios to get data that will allow us: (1) to verify that the attention estimated from EEG by our algorithm is correlated with the attention provided by EUROBENCH while the users are walking wearing an exoskeleton; and (2) validate that the algorithm that we have developed to detect subjects’ motor imagery from users can be applied if they are walking through non-flat terrains. The EEG signals recorded using the EUROBENCH scenarios and the results provided by our algorithms (subjects’ motor imagery decoded and users’ attention estimated) will be incorporated into the EUROBENCH database. This information will be a powerful resource for researchers interested in controlling lower-limb exoskeletons from EEG signals to develop, test and compare their algorithms.

Head Researcher: José María Azorín Poveda

REKINE

Title: Reconstructing kinematics trajectories during walking from EEG signals

Funded by: European Union’s Horizon 2020 research and innovation programme, via an Open Call issued and executed under Project EUROBENCH

Duration: 01/04/2021 hasta 31/05/2022

Description: Lower-limb robotic exoskeletons have emerged as aids for over-ground, bipedal ambulation for individuals with motor limitations. The usability and clinical relevance of these robotics systems could be further enhanced by brain-machine interfaces (BMIs). Different approaches have been explored in the last decade to interact with robotics exoskeletons by means of BMIs based on EEG. One of the approaches explored is based on the decoding of kinematics trajectories during walking from EEG. Although walking is automatically based on reflexes governed at the spinal level, there are evidences that suggest that the motor cortex is particularly active during specific phases of the gait cycle. In addition, recent studies claim that EEG signals are directly related to the value of joint angles involved in human gait.

In this regard, our team has verified that it is possible to get a relation between lower- limb angles and EEG signals by using linear regression models. However, despite current efforts for reconstructing kinematics trajectories from EEG signals, more research is still needed to improve the performance of current decoding algorithms. Furthermore, there is a huge lack of EEG data available for researchers to develop, test and compare their algorithms. The main goal of this proposal is to register the EEG signals and the kinematics trajectories of lower-limbs of a high number of subjects during walking to: (1) integrate all these data into the EUROBENCH database; (2) improve our algorithm for reconstructing kinematics trajectories from EEG by using the recorded information; and (3) include in the EUROBENCH database the results of our decoding algorithm. This information will be a powerful resource for future researchers to develop, test and compare their algorithms.

Head Researcher: José María Azorín Poveda

OBRAINSITY

Title: OBRAINSITY - Nuevos enfoques terapéuticos frente a enfermedades metabólicas: modulación de la ingesta de alimentos y del balance energético mediante nutracéuticos y neurotecnología

Funded by: Conselleria de Innovación, Universidades, Ciencia y Sociedad Digital (Generalitat Valenciana) - Programa Prometeo para grupos de investigación de excelencia – PROMETEO 2021

Duration: 1/1/2021 hasta 31/12/2024

Description: OBRAINSITY - Nuevos enfoques terapéuticos frente a enfermedades metabólicas: modulación de la ingesta de alimentos y del balance energético mediante nutracéuticos y neurotecnología

Head Researcher: Vicente Micol Molina y María Herranz López

ModRet

Title: Recognition and modeling of lattice structures (ModRet)

Funded by: Universidad Miguel Hernández de Elche

Duration: 2 años

Description:

The project focuses on the creation of models of lattice structures. These types of structures are found in numerous constructions and require continuous maintenance. This maintenance can be automated using a mobile robot capable of moving through the structure. However, to undertake this task, the robot must have a model of the structure that allows it to know its position and plan the appropriate trajectory and sequence of movements to reach the target point. To create this model, the robot will collect information as it moves along the structure for the first time, using its equipped sensors (primarily omnidirectional vision systems).

Modeling these types of structures presents several differential aspects compared to other environments, such as their symmetry and the presence of repetitive visual structures, the wide variety of viewpoints from which they can be observed depending on the robot's trajectory, and the changes their appearance may undergo due to repairs carried out by the robot. Considering these characteristics, the model will be given a hierarchical structure, with a high-level layer containing information about the topology of the structure, and one or more low-level layers with data about the bars and nodes, such as their shape, width, planes that compose the bars, and node topology. Artificial intelligence and deep learning techniques will be used for scene description and extraction of relevant information. These tools will separate the information surrounding the structure and its conditions (such as lighting conditions) from the information of the lattice surrounding the robot (bars and nodes). Additionally, algorithms will be implemented for incremental model creation, updating it as the robot advances and captures new information about the structure.

Head Researcher: L. Payá

ParallelRobots

Title: Design and study of computational torque regulators for traversing singularities in parallel robots

Funded by: CONSELLERIA DE INNOVACIÓN, UNIVERSIDADES, CIENCIA Y SOCIEDAD DIGITAL, Generalitat Valenciana

Duration: 01/01/2021-31/12/2021

Description:

Parallel robots control the movement of their end-effector or gripper through multiple kinematic chains connected in parallel, forming closed kinematic chains. This provides them with greater structural rigidity and dynamic performance, but it also limits their workspace and divides it into different regions separated by parallel-type singularities (also known as type 2 singularities) that do not exist in serial or open kinematic chain robots. When the robot crosses one of these singularities, it is not possible to control the movement of its end-effector in any arbitrary direction, requiring infinitely large actuation torques in the actuators. This makes it difficult to cross such singularities to fully utilize the robot's workspace.

In previous works, other researchers have avoided the divergence of actuation torques by designing the end-effector's trajectory so that, when crossing the singularity, the robot's dynamic model does not degenerate, satisfying a non-degeneration condition derived by other researchers in the past. The drawback is that the trajectory used to cross the singularity cannot be arbitrary; it must be designed to meet the mentioned non-degeneration condition.

In this project, we propose the design of new Computed-Torque Control laws that allow crossing the mentioned parallel singularities while avoiding the divergence of the actuation torques, so that they remain finite during the crossing of the singularity, and additionally avoiding the need to design the trajectory to achieve this, thus allowing arbitrary trajectories. To achieve this in the present project, we propose considering the small modeling errors that always occur when modeling the dynamics of the robot to be controlled. These small errors cause the tracking of the desired trajectory to be imperfect, which provides some margin to meet the non-degeneration condition simply by adjusting the proportional and derivative gains of the regulator, leaving the trajectory completely free. The proposed control will be tested in this project through simulation with example parallel robots, and also through testing on real parallel robots.

Project funded by the Department of Innovation, Universities, Science, and Digital Society of the Generalitat Valenciana.
Valencian Innovation Agency

Keywords: parallel robot, singularity, computational torque control

Head Researcher: Adrián Peidró

EMERG2020

Title: Scene Reconstruction from Omnidirectional Cameras Using Visual Appearance Techniques and Deep Learning

Funded by: Generalitat Valenciana

Duration: 01/2020 - 12/2020

Description:

Most of the existing algorithms that solve mapping and location problems stop working properly when the robot operates in an unstructured, complex and changing environment or when the robot can move with more than three degrees of freedom (DOF). ). In response to this challenge, the main research line of this project proposes the improvement and development of new mechanisms that allow efficient, robust and precise modeling of environments using vision systems. Specifically, the use of omnidirectional vision systems is proposed due to the large amount of information they provide at a relatively low cost. However, the use of these vision systems makes it necessary to consider the challenges of working with the images provided by this type of camera. In this sense, it is proposed to study in depth descriptors based on global appearance and make use of Deep Learning techniques.

The development of this project is developed through various objectives such as the analysis of the present algorithms for creating maps and location, comparison of the present global appearance algorithms and also, developing new location algorithms and / or appearance descriptors global based on Deep Learning. In order to improve the integration of the mobile robot in real work environments (Industry 4.0), in which they interact with people, characteristics that make it compatible with human perception will be incorporated into the map.

Keywords: Deep learning, scene reconstruction, localization, omnidirectional vision

Head Researcher: M. Ballesta

AICO2019

Title: Hierarchical model creation and robust localization of mobile robots in social environments

Funded by: Generalitat Valenciana

Duration: 01/01/2019 a 31/12/2020

Description: The project focuses on the field of map construction and localization using omnidirectional vision, advancing towards a hybrid topological-metric paradigm, which allows (a) the incremental construction of a semantic map as the robot explores the unknown environment and (b) the estimation of the robot's position and orientation with precision, with 6 degrees of freedom and at a reasonable computational cost. Additionally, to improve the integration of the mobile robot in real social environments, where it must interact with people, some features will be included in the model to make it compatible with human perception.

Thus, the proposal aims to go beyond the concept of multi-level hierarchical localization, adapting it to extensive and complex social environments, and including collaboration with users through high-level commands. This proposal is organized around two main lines of research:

- Line A: Incremental creation of hybrid metric-topological maps from the global appearan ce of a set of scenes.
- Line B: Construction of environment models that allow localization with 6 degrees of freedom from visual information.

Keywords: Mobile robot; omnidirectional vision; hybrid map; hierarchical localization; social environments

Head Researcher: L. Payá

Emergentes desarrollo BCI rehabilitación

Title: Desarrollo de nuevas interfaces cerebro-máquina para la rehabilitación de miembro inferior

Funded by: CONSELLERIA DE INNOVACIÓN, UNIVERSIDADES, CIENCIA Y SOCIEDAD DIGITAL

Duration: 01/01/2019 - 31/03/2021

Description: La apoplejía o el accidente cerebrovascular (ACV) y la lesión medular son algunas de las causas que ocasionan trastornos motores en personas debido al daño asociado al sistema nervioso. Dicho daño conlleva un considerable descenso en su calidad de vida, ya que las lesiones ocasionadas suelen interrumpir las vías sensoriales y motoras, conduciendo a una marcha patológica permanente y a un deterioro de la deambulación independiente. Recientemente, han aparecido diversos exoesqueletos robóticos con el fin de ser utilizados en terapias de rehabilitación. El uso de este tipo de dispositivos asociados a interfaces cerebro-máquina (BMI), que decodifican las señales electroencefalográficas (EEG) del paciente para interpretar los comandos de movimiento, puede mejorar la neuroplasticidad neuronal en las terapias de rehabilitación. En este aspecto, el grupo de investigación del Dr. Contreras-Vidal (Universidad de Houston, Texas E.E.U.U) en colaboración con el grupo de Neuro-Rehabilitación del Instituto Cajal del Dr. Pons en España, realizaron un primer estudio clínico sobre el uso de este tipo de robots durante la rehabilitación de la marcha de pacientes de ACV, demostrando su viabilidad en rehabilitación. Sin embargo, todavía existen dos inconvenientes para su aplicación de forma extendida. En primer lugar, es preciso que los algoritmos de control mejoren su precisión, lo que aboga por desarrollar nuevos algoritmos que permitan BMIs más robustas y fiables. En segundo lugar, dichos dispositivos robóticos tienen un alto coste económico, desde unos 70.000€ hasta 200.000€ según modelo y propiedades, lo que dificulta su implantación, siendo necesario la búsqueda de alternativas de inferior coste.

El objeto de la investigación es implementar un nuevo tipo de BMI híbrida para la rehabilitación de la marcha que presente una mayor precisión gracias a la combinación de dos tipos de paradigmas: imaginación motora de la marcha y niveles de atención. Adicionalmente, se evaluará si los resultados de la BMI desarrollada, vienen influidos por el tipo de dispositivo actuador asociado. De este modo, se comparará la viabilidad de la sustitución de BMIs asociadas a exoesqueletos robóticos por entornos de VR en combinación con cintas andadoras.
Para la primera aproximación se aprovechará la estancia concedida al IP de este proyecto mediante una beca Castillejo en la Universidad de Houston. En la misma, se podrá tener acceso a los exoesqueletos que dispone el Dr. Contreras-Vidal. Ejemplos de los posibles exoesqueletos a utilizar son el H2 de Technaid S.L., el Rex de Bionics Ltd. y el Hank de Gogoa.
Para la segunda aproximación, se utilizará un equipo de realidad virtual (HTC Vive) en combinación con una cinta andadora Proform, como alternativa de bajo costo. En ambos casos se utilizarán equipos de registro de la señal EEG para decodificar las intenciones motoras.

Head Researcher: Mario Ortiz García

WALK - Controlling lower-limb exoskeletons by means of brain-machine interfaces to assist people with walking disabilities

Title: WALK – Control de exoesqueletos de miembro inferior mediante interfaces cerebro-máquina para asistir a personas con problemas de marcha

Funded by: Ministerio de Ciencia, Innovación y Universidades

Duration: 1/01/2019 - 30/09/2022

Description:

Stroke and Spinal Cord Injury (SCI) are two of the major motor disorders due to damage in the human nervous system leading to physical impairment in Western society. These conditions will in general disrupt sensory and motor pathways that in turn lead to permanent pathological gait, resulting in impaired independent ambulation. Walking incorrectly creates a stigma and makes patients more susceptible to injury, affecting quality of life. Ambulation after trauma has long been a research topic, but more progress is needed.

With recent advances in robotic technologies, lower-limb robotic exoskeletons have emerged as aids for over-ground, bipedal ambulation for individuals with motor limitations. Interfaces between robotic exoskeletons and users are often implemented via a combination of mechanical and electrical devices. However, these interfaces are not what humans naturally use. The usability and clinical relevance of these robotics systems could be further enhanced by brain-machine interfaces (BMIs). BMIs bypass motor systems of any kind. BMIs make context-based decisions from recordings of the users brain activity, thus allowing direct and voluntary operation of the devices beyond users diminished physical capabilities. Although the feasibility of using BMIs to control lower-limb exoskeletons has been demonstrated, important challenges have to be still addressed to deploy these systems as assistive devices in the clinic and at home: (1) Robust BMIs with better performances have to be developed to send safely basic commands (walk and stop) to exoskeletons; (2) BMIs for turning left/right exoskeletons, increasing/decreasing their speed, or stopping them if unexpected obstacles appear have to be implemented for providing more capabilities to these systems; (3) Training schemes to reduce the number of training sessions required to use BMIs, and to reach higher performances have to be developed; and (4) More clinical studies have to be carried out to validate the health benefits of using these systems. All these challenges will be addressed in the WALK project.

The WALK project will go beyond the current state-of-the-art by developing more robust BMIs with higher performances not only able to control the exoskeletons for walking and stopping safely, but also to send them commands for turning left/right, increasing/decreasing their speed, or stopping them if unexpected obstacles appear. To improve the performance of the new BMIs and reduce the number of training sessions, new training strategies based on transcranial direct current stimulation (tDCS) and virtual reality will be developed. Furthermore, the project will demonstrate how the use lower-limb exoskeletons commanded by BMIs could have health benefits for SCI people, particularly with respect to pain, spasticity and autonomic activity.

Thus, the WALK project will allow people with locomotion difficulties to command lower-limb robotic exoskeletons by means of BMIs in order to provide them walking assistance in the clinic and at home. This will contribute that neurologically injured patients have higher activity at home and participation in society.

Head Researcher: José María Azorín Poveda

BinaryRobot

Title: Design and development of a hybrid structure robot with binary-operated hydraulic actuators.

Funded by: Generalitat Valenciana

Duration: Del 01/01/2018 al 31/12/2019

Description:

Steel structures require inspection, maintenance, and repair tasks to ensure their proper functioning, stability, structural integrity, longevity, and aesthetic quality. Such structures are present in numerous constructions such as bridges, ports, airports, telecommunications towers, stadiums, power lines, power plants, and industrial plants, as well as forming part of the framework of most buildings. Typically, the maintenance tasks for these vertical structures are performed by human operators who must climb the structures to carry out these tasks, subjecting them to serious risks, including falling from considerable heights or electrocution. To avoid exposing human operators to such risks, for the past couple of decades, numerous researchers worldwide have been studying the possibility of using climbing robots to perform these dangerous tasks at height.

The main objective we propose in this project is to develop a new articulated climbing robot for the exploration and maintenance of vertical steel structures, with the ability to move in three-dimensional space. The main innovation of the robot to be developed in this project, compared to other climbing robots developed to date, is that the proposed robot will have binary actuation (all-or-nothing actuators), which greatly simplifies the planning and control of its movements. Additionally, the robot to be developed will have a moderately high degree of kinematic redundancy (between 10 and 12 degrees of freedom), allowing it to enjoy sufficiently high mobility to explore three-dimensional structures despite having only binary actuators. In this way, by combining binary actuation and kinematic redundancy, we aim to achieve a balance between simplicity and freedom of movement, thereby addressing the main complexity issues that currently prevent climbing robots from being used more extensively.

Keywords: climbing robot, binary operation

Head Researcher: M. Ballesta

OMMNI-SLAM

Title: Map Building by Means of Appearance Visual Systems for Robot Navigation

Funded by: CICYT Ministerio de Ciencia e Innovación

Duration: 01/01/2017 al 31/12/2019

Description: In order to be truly autonomous, a mobile robot should be capable of navigating through any kind of environment while carrying out a task. In order to do that it is considered necessary that the robot possesses the ability to create a model of its workspace that allows to estimate its position inside it and navigate along a trajectory.

Map building and navigation is currently a very active research area, in which a large number of researchers focus on and where very different approaches have emerged based on diverse algorithms and using various kind of sensorial information. To the present days, most of the efforts have been focusing on construction of models of the environment based on a set of significant points extracted from it without considering the global appearance of the scene.

Considering the concepts posed above, we propose the improvement and development of new mechanisms that allow an efficient, robust and precise modelling of the environment by making use of omnidirectional vision systems. The research group has experience in the mentioned areas and during the last years has developed different approaches in the areas of map building, localization, exploration and SLAM by means of information gathered by different kind of vision systems installed on the robots. In order to carry out these approaches, an extensive study of the different description methods has been performed, both based on the extraction of significant points and local descriptors and also those methods based on the global appearance of the image, with remarkable results.

Keywords: Mobile robots, autonomous navigation, computer vision, omnidirectional systems

Head Researcher: L. Payá, O. Reinoso

REASISTE

Title: Red Iberoamericana de rehabilitación y asistencia de pacientes con daño neurológico mediante exoesqueletos robóticos de bajo coste.

Funded by: Programa Iberoamericano de Ciencia y Tecnología para el Desarrollo (CYTED)

Duration: 1/01/2016 hasta 31/12/2019

Description: Patients with neurological damage are a very disadvantaged group in Latin America that has not been dedicated to a coordinated transnational and multidisciplinary effort of clinical centers, research centers, universities and companies. Neurological damage is one of the main causes of disability, with the number of people with disabilities in Ibero-America exceeding 72 million (affecting approximately 11% of the total population of Ibero-America). The main objective of Reasiste is to establish a broad working forum to enable and facilitate cooperation and the exchange of knowledge among stakeholders from Ibero-America working in the field of rehabilitation and care of patients with neurological damage. The network is articulated around the development of one or several robotic exoskeletons (ERs) to improve the rehabilitation and assistance of patients with neurological damage. Thereby, once the network is completed, several ERs will be available that can be used by clinical centers in rehabilitation therapies and assistance to patients with neurological damage. Although the people who will benefit first from the developments of this network are the group of patients with neurological damage, the ERs of the network could be used to improve the health of patients with other pathologies, such as, for example, patients with poliomyelitis or botulism.

The book "Exoesqueletos Robóticos para Rehabilitación y Asistencia de Pacientes con Daño Neurológico | Experiencias y Posibilidades en Iberoamérica", the workshop: «Experiences and advances in technologies for rehabilitation and functional compensation in Iberoamerica, with a focus on Wearable Robotics» within ICNR 2016 and the Curso Introducción a los exoesqueletos robóticos de miembro inferior are some of the activities and materials that Reasiste has produced.

Head Researcher: José María Azorín Poveda

ASSOCIATE

Title: Decodificación y estimulación de actividad cerebral sensorial y motora para permitir potenciación a largo plazo mediante estimulación Hebbiana y estimulación asociativa pareada durante la rehabilitación de la marcha.

Funded by: Ministerio de Economía y Competitividad

Duration: 1/01/2015 hasta 31/12/2019

Description: Cerebral vascular accident (CVA, Stroke) and Spinal cord injury (SCI) are two of the major motor disorders due to damage in the human nervous system leading to physical impairment in Western society. These conditions will in general disrupt sensory and motor pathways that in turn lead to permanent pathological gait, resulting in impaired independent ambulation.

Walking incorrectly creates a stigma and makes patients more susceptible to injury, affecting quality of life. Most advanced robotic treatments to rehabilitate walking function in neurological patients could specifically target the neuronal changes that may contribute to skill acquisition and recovery. Afferent-generated feedback can be applied in these interventions in association to motor planning at brain level.

The first objective of the project is to validate the effectiveness of a novel intervention to promote motor control re-learning in neurological patients by means of an associated use of motor planning at brain level, sensory stimulation at cortical level and afferent feedback provided with a wearable lower extremity exoskeleton.
On the other hand, lower extremity exoskeletons as assistive technologies have been mostly applied in chronic SCI patients as temporary alternative to wheelchairs. Such systems are still not ready for real everyday use in community settings and to maintain neuromusculoskeletal health below the level of the injury. This situation is due basically to the limited flexibility of mechanical and control structures to manage the interactions with musculoskeletal system and human gait dynamics, respectively.

The second objective of the project is to validate the effectiveness of a novel lower extremity wearable exoskeleton with embodied intelligence and enhanced self-learning characteristics in the assistance to locomotion in complete and incomplete SCI in terms of reduced learning periods, improved adaptation and more versatile and dextrous operation.

Head Researcher: José María Azorín Poveda

BioMot

Title: Smart Wearable Robots with Bioinspired Sensory-Motor Skills · BioMot

Funded by: VII Programa Marco Comisión Europea

Duration: 1/10/2013 hasta 1/10/2016

Description: Wearable robots (WR) are person-oriented devices, usually in the form of exoskeletons. These devices are worn by human operators to enhance or support a daily function, such as walking. WRs find applications in the enhancement of intact operators or in clinical environments, e.g. rehabilitation of gait function in neurologically injured patients. Most advanced WRs for human locomotion still fail to provide the real-time adaptability and flexibility presented by humans when confronted with natural perturbations, due to voluntary control or environmental constraints. Current WRs are extra body structures inducing fixed motion patterns on its user.

Aim
The aim of the BioMot project is to improve the efficiency in the management of human-robot interaction in overground gait exoskeletons by means of mixture of bioinspired control, actuation and learning approaches. Our aim is to show how the embodiment of bioinspired and architectural mechanisms can allow a user to conveniently alter the behaviour of WRs for walking.

Final Goal
The final goal of the project is to deliver novel ambulatory wearable exoskeleton technology that exploits neuronal control and learning mechanisms and provides a) more energy efficient cooperative (human-robot) performance, and b) adaptive assistance based on the user’s residual and voluntary action.

Approach
BioMot’s exoskeletons apply adaptive assistance as a function of real-time estimation of human effort provided by a detailed neuromusculoskeletal model that computes neuromuscular activity (surface electromyography, EMG) to predict joint moments and hence prescribe the exoskeleton function. Gait detection algorithms based on human performance (brain signals, EEG) and embedded sensors (kinematic and kinetic) are developed for decision making, handling transitions or volitional changes in the task (such as gait speed). Local reflex-based joint controllers are designed to allow for automatic adaptation when confronting changes in the interaction. At the physical level, intrinsically compliant actuators are developed to exploit natural dynamics of movement, orchestrated by the control system for economy and stability. A global learning scheme modules joint compliance as a function of gait efficiency and semantic signals infered from user demand.

Innovations
A cognitive system for a wearable gait exoskeleton that assists overgound human walking. The cognitive system processes biomechanical and electrophysiological signals to adaptively assist the human movement based on the user’s contribution and performance. The wearable 6 DoF exoskeleton assists hip, knee and ankle movements with compliant actuators that can be transparent to the user and store and release energy. BioMot’s assistive exoskeleton flexible built-in intelligence in its artificial brain and muscles allows to exploit the natural dynamics of overground walking. As a wearable robotic trainer for gait disorders, BioMot uniquely provides overground gait training, promoting the patient effort to induce recovery, and assists as needed the patient during performance of the exercises. The training sessions enabled by BioMot trainer will go beyond common available protocols, including variations of speed, turning and improved negotiation with transitions.

Head Researcher: I.P.: José María Azorín Poveda Coordinador:Juan C. Moreno, CSIC

Iberada

Title: Iberada - Red Iberoamericana para el estudio y desarrollo de aplicaciones TIC basadas en interfaces adaptadas a personas con discapacidad.

Funded by: Programa Iberoamericano de Ciencia y Tecnología para el Desarrollo (CYTED)

Duration: 1/01/2012 hasta 31/12/2015

Description: Access to information and communication technologies (ICT) presents serious difficulties for people with disabilities or elder who have perception, motor or intellectual severe limitations. Different interfaces have been developed to alleviate these barriers, for example in voice recognition, eye tracking or brain-computer interaction. The aim is to improve both the control of personal devices (prostheses, wheelchairs …) and access to knowledge through the Internet, reducing the «digital divide» by enabling them to use the computer and ICT.

The main goal of Iberada is to establish a broad working forum to enable and facilitate cooperation and the exchange of knowledge between different Ibero-American research groups whose work focuses on Assistive Technologies with the development of applications based on interfaces adapted to people with disabilities, combining the isolated efforts of these groups. It is intended to coordinate actions of study, training, parallel developments (design, implementation and experimentation), mobility and scientific interaction. The medium term goal is to strengthen this important emerging sector in Ibero-America and to project technological solutions to the market, with the aim of achieving greater autonomy in the daily activities of people with serious deficiencies through computer access. manipulation, mobility, interaction-communication and cognition, for a better quality of life and more full integration into society.

Head Researcher: José María Azorín Poveda

Brain2Motion

Title: Brain2Motion - Desarrollo de una Interfaz Multimodal Cerebro-Neural para el Control de un Sistema Robótico Híbrido Exoesqueleto - Neuroprótesis de Miembro Superior.

Funded by: Ministerio de Economía y Competitividad

Duration: 1/01/2012 hasta 31/12/2014

Description: Exoskeletal robots (ERs) are person-oriented robots that supplement the function of a limb or replace it completely. A possible alternative to ERs are Motor Neuro-Prostheses (MNP) based on Functional Electrical Stimulation (FES). Both ERs and MNPs are technologies that seek to restore or substitute motor function. MNPs constitute an approach to restoring function by means of artificially controlling human muscles or muscle nerves with FES. ERs use volitional commands for controlling the application of controlled forces to drive paralyzed or weak limbs.

The main goal of BRAIN2MOTION project is to develop a new hybrid ER-MNP for the upper limb interfaced to the users by means of non-invasive multimodal brain-neural computer interfaces (BNCIs). The robotic hybrid system will combine a light and kinematically compatible ER, and a textile-based surface MNP. In this combined ER-MNP, hardware and control strategies will be developed to combine the action of the ER and MNP while preserving motor latent capabilities of the user. A spontaneous non- invasive EEG-based Brain-Computer Interface (BCI) and an electrooculography (EOG) interface will compose the multimodal BNCI. The BCI will differentiate more than three mental tasks. This will be achieved incorporating new adaptive classifiers into the BCI. Learning strategies will be developed in order to improve the performance and versatility of the BCI. Control strategies combining EEG and EOG signals will be developed to control the ER-MNP.

The hybrid ER-MNP controlled by the BNCI will be used to perform reaching and grasping operations. The system will be validated with patients suffering from neurological conditions leading to severe motor disorders, in particular cerebrovascular accident (CVA).

Head Researcher: José María Azorín Poveda

RemoteRoboticsLab

Title: Convenio de Colaboración para el desarrollo del proyecto "Hacia la formación práctica ubicua y digital en robótica mediante laboratorios remotos”

Funded by: Centro de Inteligencia Digital de la Provincia de Alicante (CENID)

Duration: 6 meses (abril 2022 - octubre 2022)

Description: Este proyecto pretende desarrollar un laboratorio remoto, que consiste en una plataforma ciberfísica que permite al estudiantado de carreras técnicas conectarse a robots de forma remota, para hacer prácticas de laboratorio y experimentos con dichos robots, a través de Internet. Esto permitirá dotar al estudiantado de mayor flexibilidad espacial y temporal, permitiéndoles hacer prácticas de laboratorio de forma ubicua, sin limitarlos a tener que desplazarse a un laboratorio físico para realizar las prácticas únicamente en las horas en las que el acceso a dicho laboratorio está habilitado. El estudiantado se conectará a los robots reales a través de un servidor web y, a través de una interfaz, podrá comandar movimientos o experimentos para realizar con los robots remotos. El movimiento de los robots se mostrará a través de una webcam en tiempo real, y también se devolverá información relativa a los resultados del experimento remoto, información que será captada mediante sensores de posición, velocidad, y fuerza, colocados en el robot real. Los robots remotos que se implementarán para hacer prácticas a distancia serán de tipo paralelo o de cadena cinemática cerrada, ya que éstos disponen de mayor riqueza que los robots tradicionales de cadena cinemática serie, a la hora de ser estudiados en asignaturas de control y robótica.

Las actividades que abarcará este proyecto serán las siguientes cuatro: 1) construcción de dos robots paralelos con los que el estudiantado pueda realizar prácticas y experimentos a través de internet, 2) implementación del servidor web que gestione las reservas y el acceso remoto de los robots por parte del estudiantado, 3) la programación de interfaces gráficas de usuario que permitan al estudiantado comandar órdenes y experimentos a la vez que se observa el movimiento del robot en tiempo real a través de una webcam, y 4) diseño de prácticas y experimentos didácticos a realizar con la ayuda del laboratorio remoto desarrollado. El principal resultado esperado de este proyecto es la materialización del mencionado laboratorio remoto, que permitirá flexibilizar la realización ubicua de prácticas con robots reales a distancia, haciendo uso de las tecnologías digitales al servicio de la enseñanza y el aprendizaje.

Keywords: Robot paralelo, laboratorio remoto, prácticas de laboratorio, identificación, control

Head Researcher: Adrián Peidró

Tonalidad de Pieles

Title: Desarrollo de un software para la detección y medición de los diferentes tonos de piel

Funded by: PIES CUADRADOS LEATHER S.L.

Duration: 2019 - 2020

Description: El objetivo de esta propuesta es el estudio, desarrollo e implementación de un sistema de clasificación mediante visión por computador de la tonalidad de piezas de cuero teñido atendiendo a la apariencia visual del tono de la piel.

La medida de color y clasificación de grandes piezas de cuero teñido para obtener una producción uniforme en la industria del calzado, es un problema técnico no resuelto debido a las dificultades impuestas por la alta variabilidad espacial de la tonalidad y de la textura de la misma. En la percepción visual de la tonalidad de un producto influyen múltiples factores: iluminación, propiedades de absorción del material y la respuesta del sensor utilizado. Cada uno de estos factores está sujeto a variación tanto espacial como temporal. Los trabajos en el campo de la percepción de color han dado lugar a una conjunto de modelos y herramientas para definir de forma univoca el color puntual respecto a unas referencias espectrales, pero la medida y percepción de diferencias de tonalidad en materiales no uniformes, aplicados a la producción de elementos con múltiples piezas donde la compatibilidad de la apariencia visual es determinante, es un problema mucho más complejo y sujeto todavía a estudio.

Sobre esta base, se propone el estudio y desarrollo de los diferentes aspectos y tecnologías aplicados a la clasificación de la tonalidad de pieles. Se propone la necesidad del estudio e implementación de descriptores de color uniformes que permitan la medida de distancia de apariencia visual de forma robusta. El estudio de técnicas de calibración y corrección de color que permita observar las variaciones espaciales y temporales del sistema de captación y de iluminación. Adicionalmente se propone el estudio de descriptores texturales aplicables a imágenes en color y que tengan en cuenta no solo la tonalidad puntual sino la variabilidad espacial del mismo debido a la textura del material. Se diseñarán y analizarán técnicas de clasificación y reconocimiento de patrones que permitan establecer reglas de decisión robustas. Por último se implementarán los resultados obtenidos en un sistema industrial de clasificación de pieles mediante visión por computador.

Head Researcher: O. Reinoso

Ingeniería Industrial, Automatización de Maquinaria Industrial y Robótica

Title: Contrato de asesoramiento técnico y científico en el ámbito de la Ingeniería Industrial, Automatización de Maquinaria Industrial y Robótica

Funded by: SIMPLICITYWORKS EUROPE SL

Duration: 2019 - 6 meses

Description: Contrato de asesoramiento técnico y científico en el ámbito de la Ingeniería Industrial, Automatización de Maquinaria Industrial y Robótica

Keywords: Asesoramiento

Head Researcher: Carlos Pérez Vidal

Desarrollo de un nuevo procedimiento para incrementar el nivel de pegado de polímeros inyectados en molde cerrado

Title: Contrato para la realización del proyecto "Desarrollo de un nuevo procedimiento para incrementar el nivel de pegado de polímeros inyectados en molde cerrado"

Funded by: SIMPLICITYWORKS EUROPE SL

Duration: 2018 - 2 años

Description: Desarrollo de un nuevo procedimiento para incrementar el nivel de pegado de polímeros inyectados en molde cerrado

Keywords: Moldes, polímeros, pegado

Head Researcher: Carlos Pérez Vidal