Search

El fuzzing es una técnica de prueba automatizada que hace uso de mutaciones de entradas para ejecutar el software utilizando estas a fin de observar los valores de retorno y el estado externo del sistema; todo ello para identificar comportamientos no esperados. Por su simpleza y fácil automatización inicial, el fuzzing es una de las técnicas más populares para identificar vulnerabilidades en software en el mundo real. El uso de técnicas de fuzzing como parte del desarrollo de software en grandes compañías ha acelerado la evolución de las técnicas y mejorado las herramientas, como contrapartida muchos proyectos quedan huérfanos de sus desarrolladores originales, al ser captados por estas empresas y todas aquellas características con potencial uso comercial, son restringidas al ámbito privado o son dependientes de nubes propietarias. Esto supone una barrera inicial para nuevos desarrollos, una posible dependencia tecnológica de terceros y problemas de confidencialidad de los datos para adoptar modelos seguros de desarrollo o realizar investigaciones. Las investigaciones sobre fuzzing y las nuevas herramientas tienen en común partir desde cero o una base teórica y focalizarse en una característica o funcionalidad. Por todo lo anterior resulta valioso desarrollar un marco de trabajo común que de coherencia y continuidad de forma global abordando el fuzzing como un flujo con distintas fases, organizando todos los procesos implicados, incluyendo también aquellos con relación directa, de forma modular, abierta y agnóstica a las herramientas y técnicas. Con ello se potencia la reutilización y se elimina la dependencia a herramientas o casos de uso, a la vez que permiten sinergias con otros enfoques de seguridad en el software. El uso de una arquitectura desacoplada y escalable permite la Distribucion y paralelización de trabajos. Esta arquitectura es ideal para entornos de computación de alto rendimiento en adelante HPC ( high-performance computing por su traducción al inglés) o basados en cargas de trabajo. El código fuente y la documentación empleada para la prueba de concepto se encuentra disponible públicamente en GitHub.

International Conference on Industrial Engineering and Industrial Management (13th. 2019. Gijón)

As robotic systems spread, cybersecurity emerges as major concern. Currently most research autonomous systems are built using the ROS framework, along with other commercial software. ROS is a distributed framework where nodes publish information that other nodes consume. This model simplifies data communication but poses a major threat because a malicious process could easily interfere the communications, read private messages or even supersede nodes. In this paper we propose that ROS communications should be encrypted. We also measure how encryption affects its performance.We have used 3DES cyphering algorithm and we have evaluated the performance of the system, both from the computing and the communications point of view. Preliminary results show that symmetric ciphers using private keys impose significant delays

—Using information from RGBD sensors requires huge amount of processing. To use these sensors improves the robustness of algorithms for object perception, self-localization and, in general, all the capabilities to be performed by a robot to improve its autonomy. In most cases, these algorithms are not computationally feasible using single-thread implementations. This paper describes two multi thread strategies proposed for self localize a mobile robot in a known environment using information from a RGBD sensor. The experiments will show the benefits obtained when different numbers of threads are compared, using different approaches: a pool of threads and creation/destruction scheme. The work has been carried out on a Kobuki mobile robot in the environment of the RoCKiN competition, similar to RoboCup@home

La gestión de la tecnología en las universidades se enfrenta a un cambio de paradigma determinado por la evolución continúa de la tecnología y por las consecuencias que esta evolución impone en los ámbitos organizativos. Hemos de pasar de una visión centrada en la tecnología a una visión centrada en la oferta de servicios que satisfagan las necesidades de la comunidad universitaria alineada con la estrategia propia de cada universidad. Es necesario reflexionar sobre cuáles son los servicios ofertados y en qué condiciones se ofrecen a los diferentes colectivos de la comunidad universitaria. Este artículo describe los trabajos realizados en el seno del grupo de trabajo de CRUE-TIC en el ámbito de la elaboración de las cartas de servicios TIC universitarios, identificando el marco normativo al que está sujeta esta elaboración, la estructuración propuesta así como los riesgos y los beneficios derivados de su elaboración.

The design and implementation of adaptive systems for accessing information is a sophisticated task. Different models have been proposed to build systems that adapt to the user reducing the complexity in the information browsing process, saving user time and offering personalized interfaces. The work described in this paper, named WAY-Z39.50, is an example of fuzzy adaptive system specially built for accessing digital libraries

Una de las aplicaciones habituales dentro de los sistemas multi-robot es la percepción distribuida. Este mecanismo de cooperación permite que cada robot sea capaz de modelar su entorno, más alla de lo que percibe a través de sus propios sensores, apoyandose en las observaciones de otros robots del equipo. Las técnicas probabilísticas de fusión sensorial pueden emplearse para combinar percepciones de varios robots y obtener una única estimación global. En este artículo se presentan dos aproximaciones al problema de la percepción distribuida de la pelota dentro del escenario de la RoboCup

This article presents a tele-assistance system based on augmented reality for elderly people that is integrated in a mobile platform. We propose the use of augmented reality for simplifying interaction with its users. The first prototype has been designed to help in medication control for ederly people. In this paper, both hardware and software architectures are described.The robotic platform is a slightly modified version of the Turtlebot platform. The software is based on ROS for the platform control, and in ArUco for the augmented reality interface. It also integrates other related systems in teleassistance such as VoIP, friendly user interface, etc.

In this article we want to discuss the skills required for human teleoperators of mobile robots. We show the classical problems related with teleoperation but focus our discussion in not specialized operators. We want to show how a proposal based on augmented reality interfaces can improve the performance of operators controlling the robot. We present the validation of our solution in two experiments: one in a controlled circuit and another one in a real environment. To carry out our experiments we use a low cost robotic surveillance platform

Using 3D computer simulations for training surgeons is not new. Using e-learning for improving students knowledge acquisition is not new. What we propose is to use 3D computer simulations in such a versatile way that those simulations could act as learning objects designed directly by those who own the experience we want to be transmitted. In order to achieve this goal, it is necessary to create a model in charge of communications between the learning objects and the simulation. This model ensures that, on the one hand, the simulation offers an interface to the learning process stable enough not to be affected by every small change. On the other hand, the model also ensures that the simulation offers an interface complete enough for adopting any change in the learning process. The key to solve this contradiction is to take the behavior of the simulation objects out of their control leaving in them just their very basic behavior. This paper presents the problem and the design proposed to solve it in a more detailed way

La predicción meteorológica es un problema clásico de la programación paralela. Muchos de los modelos matemáticos que se utilizan en meteorología para pronosticar el comportamiento de la atmósfera tienen implementaciones preparadas para ejecutarse en entornos de cálculo paralelo. La información obtenida después de ejecutar un modelo matemático de predicción meteorológica es necesario procesarla para poder visualizar los resultados. Sin embargo, no es fácil encontrar herramientas que permitan el procesado en paralelo de estas salidas. El presente trabajo plantea la posibilidad de dar un paso más y mejorar el rendimiento, utilizando el paradigma paralelo para procesar las salidas de un modelo de predicción numérica, en concreto, el modelo WRF (Weather Research and Forecasting)

Los últimos años se está detectando una bajada significativa en la matrículación de alumnos en las ingenierías en los países desarrollados. Esto nos ha hecho plantearnos la necesidad de fomentar las vocaciones científico-técnicas, para lo que hemos decidido aprovechar nuestra experiencia en el campo de la robótica. En concreto hemos organizado un campeonato de construcción de robots que denominamos RoboCampeones y que describimos en esta comunicación

This paper presents the object-oriented programing envir- onment for the AIBO robot, focusing in its concurrency model. Con- currency problems arise when programming a robot due to the various sensors and actuators that the programmers must manage. As this man- agement has some aspects of real time and communication, involves some coplexity. In order to deal with this complexity Sony has developed a framework for programming the AIBO Robot. The description of this API called OPEN-R is presented. Also we will discuss how the under- lying operating system, APERTOS, hides almost all the complexity of implement applications compounded of concurrent objects intercommu- nicated

This article describes two vision-based behaviors designed for an autonomous legged robot. These behaviors have been designed in a modular way in order to be able to integrate them in an architecture named DSH (Dynamic Schema Hierarchies), which is also briefly described. These behaviors have been tested in office indoor environments and experiments carried out are also described in this paper. The platform used in these experiments carried out are also described in theis paper. The platform used in these experiments has been the Sony AIBO robot. The developed behaviors provide the robot with the follow wall and follow person capabilities, using as main sensor the robot on-board camera

P. 708-715 This paper presents a visual based localization mechanism for a legged robot. Our proposal, fundamented on a probabilistic approach, uses a precompiled topological map where natural landmarks like doors or ceiling lights are recognized by the robot using its on-board camera. Experiments have been conducted using the AIBO Sony robotic dog showing that it is able to deal with noisy sensors like vision and to approximate world models representing indoor of ce environments. The two major contributions of this work are the use of this technique in legged robots, and the use of an active camera as the main sensor SI

Perception problem in robotics has been usually faced from the individual perspective, in this work we present preliminary results of a shared perception mechanism for a group of legged robots working is a dynamic scenario. The experiments has been conducted using a group of aiBo robots in the RoboCup environment. Each individual robot has its own perception of a common interesting feature, the ball, and they al together build a shared perception

En la liga de 4 patas de la Robocup, equipos de 4 robots AIBO autónomos se enfrentan entre si en partidos de fútbol. El objetivo de esta competición es presentar un entorno desafiante en que se han de resolver varios problemas relacionados con la robótica. En particular, la localización. Cada uno de los jugadores ha de estar localizado durante los partidos para que su comportamiento sea coherente. En este artículo proponemos un método de localización que combina técnicas de lógica difusa y filtros de Kalman para conseguir una localización más robusta, fiable y ligera

Este artículo presenta un ejemplo de cooperación borrosa entre un grupo de robots como una solución alternativa a los protocolos clásicos utilizados en las arquitecturas de cooperación entre robots. Para ello se ha procedido a integrar trabajos previos realizados en el Laboratorio de Agentes Inteligentes (LAI) sobre comportamientos borrosos y sobre arquitecturas de cooperación. Se han considerado tres tipos diferentes de protocolos borrosos y se han probado tanto en un simulador como sobre un robot real. Por último, se presenta la descripción de los experimentos realizados así como los resultados obtenidos

This paper presents the basic design and implementation of a goalkeeper made according to the regulations of the two-legged Standard Platform League of the RoboCup Federation. The paper describes the perceptive schemas created using the architecture of the TeamChaos-URJC team as well as the action schemes designed to create a minimal reactive goalie. This player was tested in the 2009 German Open international competition. The results obtained there are analyzed and the future works derived from that analysis are presented

Any device we want to be ab le connect to a global network should have an unique global identifier. The size of this identifier can be an unaceptable overhead for devices with limited resources (sensors, toys, disposable devices, microrobots, etc.), because conventional protocols use full addresses to transmit, process and store the data required for routing. The usual solution for such devices is to limit the address space to one or two bytes, but this sacrifices the global unicity of the identifiers. Another more drastic maesure is to without any routing at all

81 p. El software es uno de los principales componentes de los robots. En particular, opinamos que es el principal problema para la extensión de la robótica en nuestra vida diaria. Uno de los factores que creemos que puede ayudar a paliar este problema es el fenomeno del software libre, que ha crecido de manera extraordinaria en el campo de la robótica. En este artículo analizamos la situación del software libre en tres subáreas de la robótica. industria, enseñanza e investigación. Las herramientas libres han sido muy populares entre la comunidad docente e investigadora en el campo de la robótica. Incluso compañías cuyo principal modelo de negocio es la venta de robots, han creído conveniente compartir el software con el fin de promover comunidades alrededor de sus productos

P. 475-483 This paper presents an architecture for the control of autonomus agents that allows explicit cooperation among them. The structure of the software agents controlling the robots is based an a general purpose multi-agent architecture based on a two level approach. One level is composed of reactive skills capable of archieving simple actions by their own. The other is based an an agenda used as an opportunistic planning mechanism to compound, activate and coordinate the basic skills. This agenda handles actions both from the internal goals of the robot or from other robots. This paper describes the work already accomplished, as well as the issues arising from the implementation of the architecture and its use the RoboCup domain SI

Digital libraries and OPACs are offering an enormous collection of information resources which can be accessed through Internet by quite different users thanks to the existence of standard protocols for information retrieval such as Z39.50. However, some users may find difficult to get the items they are looking for in such a huge bulk of heterogeneous resources since they have to know where and how they have to search for. Thus, one of the main reasons for the disregard of the Z39.50 service has traditionally been the absence of appropriate interfaces and the cost of making alternative searches. WAY-Z39.50 tries to help spreading the use of these servers by providing easy web access to them, as well as, by facilitating the access to multiple servers at once. The prototype described implements the WAY general model based on an agent-based architecture that provides adaptive searching in different servers through an adaptive interface

A new methodological approach to solve the problem of integrating different behaviors in autonomous robots is developed in this paper. It relies on the succesful integration of several fuzzy relational algorithms (Zadeh73), each one specialized in a different task. The whole system is based on a continiously act on sensor data (reactive) approach. The problem is how to got an intelligent behavior from low level reactive controllers. Our assumption is that we can obtain adecuate response to unkown external situations from the fusion of basic actions

Mobile robots need to be able to communicate among them, and with other hosts participating in a given task. Traditional wired networks are obviously not suitable for mobile robots. Current wireless networks are usually based on a fixed network infrastructure (base stations) to route packets. The best alternative for mobile robots are Ad-Hoc networks, which are wireless networks that do not need a fixed infrastructure. This paper describes PERA, an adaptation of an adhoc routing protocol that runs on Eyebot mobile robots. By using PERA, a robot can send messages to other robots or hosts that are not directly reachable through its radio antenna, by routing messages through intermediate mobile robots. The design, implementation and lessons learned in the initial tests of PERA are presented in this paper

P. 287-297 Different models have been proposed to build systems that adapt to the user reducing the complexity in the information browsing process, saving user time and offering personalised interfaces. The work described in this paper, named Way-Z39.50, is an example of adaptive system specially built for accessing digital libraries. A fuzzy decision mechanism is used to implement the adaptation of both the user interface and the information searching process. This paper describes how this system has been designed and implemented, focusing on its fuzzy-based components. Finally, it also briefly discusses the advantages of using fuzzy logic to implement adaptability of the user interface and the searching process SI

En la Inteligencia Artificial, desde sus orígenes, han existido dos corrientes básicas, la simbólica y la subsimbólica. Estas dos aproximaciones han tenido gran influencia también en la robótica. En este artículo queremos presentar un enfoque menos conocido, el de la etología, y en concreto su aplicación a la generación de comportamiento autónomo en robots móviles. Para ello presentamos los fundamentos de la "Jerarquía Dinámica de Esquemas", una arquitectura para el control de robots móviles, basada en la composición de unidades simples denominadas "esquemas" siguiendo las teorías etológicas de Arbib. Igualmente se presentan experimentos preliminares que validan esta aproximación y se discute su viabilidad y se presentan los trabajos previstos para continuar investigando en esta línea

This paper is concerned with the learning of basic behaviors in autonomous robots. In this way, we present a method for the adaptation of basic reactive behaviors implemented as fuzzy controllers applying a genetic algorithm to the evolution of the fuzzy rule system. In this sense, we show our experiments in the evolution of control rules based on symbolic concepts represented as linguistic labels. The rules will be formulated in a fuzzy way and in order to test the rules obtained in each generation of the genetic algorithm a real robot has been used. The individual with the best performance is chosen to generate a new population: the elite strategy. All the new individuals were tested in the same real environment. In conclusion, the individuals of the last generation offer a set of rules that provides better performance than the ones designed by a non-expert designer

Some of the most succesful products in the market of robots for edutainment have made manufactures realize that software for controlling the robots is one of the key elements of the success. Some of them have also conclude that libre software is the best way to produce, maintain and distribute their software. This paper will summarize the fundamentals of the libre software model and their benefits for the edutainment robot market as well as some examples of companies currently supporting it

Systems that must plan, act, and probably learn using a rational, flexible behavior in real time present a challenge to current integrated schemas of planning and acting. Classical planning is still far from solving problems on such short time as needed in dynamic domains, such as Robosoccer, even with new approaches such as graph-based techniques. Reactive systems on the other hand, are hard to configure and do not work well when high level flexible reasoning is required.This paper presents an opportunistic planning-acting schema based on our model named ABC2. The primary goal of the modeli s to composep re-defined skills in an opportunistic way to achieve and intelligent behavior for robots working autonomously

Los robots están apareciendo en nuestra vida. Hace algún tiempo llegaron a las cadenas de montaje, pero hoy están llegando a nuestras casas. Lo están haciendo para una utilidad inesperada, la de hacer compañía a los humanos. Así, los primeros robots que nos vamos a encontrar en nuestra vida diaria serán las mascotas electrónicas, nuestros hijos los encontrarán en sus juguetes. Una de las caracteríssticas principales de estos robots precisamente es que están diseñados para interactuar con las personas, su finalidad es precisamente esa, relacionarse con los humanos. Por tanto, comienza a vislumbrarse un nuevo campo dentro de la interacción entre las personas y los computadores. En este artículo intentamos dar una visión general a las diferentes formas de interactuar con los robots, presentando sus características principales y proponiendo una clasificación de los mismos con el objetivo de divulgar este campo entre los investigadores preocupados por la interacción entre los ordenadores y sus usuarios

This paper describes a teleoperator system developed for the EyeBot robot under a client-server architecture. The teleoperator is made up of two different programs: a server, running on robot’s microprocessor, and a client running on a PC. They talk to each other through a serial connection following an specific protocol. The server gathers sensor information required by the client, sends it and executes movement commands. The client asks for sensor data to the server on behalf of the human operator and sends motion orders. It also shows her a graphical interface, so she can see the values from all robot sensors and she can request different movements to its motors and servomotors

P. 269-279 The main goal of this paper is to present the advantages that the new generation of mobile robot simulators has given to the teaching of robotics to computer science students. We present some of their features, as well as some experiences of their uso in two Spanish universities. These experiences have taken place at different courses, both at graduate and undergraduate levels. We also discuss about those experiences and introduce how we envision teachng in this frekl. SI

P. 902-913 This paper proposes a behavior based architecture for robot control which uses dynamic hierarchies of small schemas to generate autonomous behavior. Each schema is a ow of execution with a target, can be turned on and o , and has several parameters which tune its behavior. Low level schemas are woken up and modulated by upper level schemas, forming a hierarchy for a given behavior. At any time there are several awake schemas per level, running concurrently, but only one of them is activated by environment perception. When none or more than one schema wants to be activated then upper level schema is called for arbitration. This paper also describes an implementation of the architecture and its use on a real robot

220 p. "Sobre software libre" reune casi una treintena de ensayos sobre temas de candente actualidad relacionados con el software libre (del cual Linux es su ex- ponente más conocido). Los ensayos que el lector encontrará están divididos en bloques temáticos que van desde la propiedad intelectual o las cuestiones económicas y sociales de este modelo hasta su uso en la educación y las administraciones publicas, pasando por alguno que repasa la historia del software libre en los ultimos años y los problemas que tiene que enfocar en un futuro próximo como es el caso de las patentes de programación. La obra incluye además una serie de artículos calificados como seminales dentro del mundo del software libre y firmados por Richard Stallman, uno de los grandes gurus del movimiento del software libre. Este es un libro pensado para un publico objetivo muy amplio, no especificamente informáticos, sino también abogados, economistas, universitarios en general. Esto es así, porque la naturaleza de los contenidos, aunque técnica, está prin- cipalmente orientada en dar a conocer la vertiente más filosófica, sociológica y pragmática del software libre. En la actualidad no existe ninguna edición en nuestro idioma que permita a las personas interesadas (sobre todo las que no tienen una formación informática más allá de nivel de usuario) introducirse en la naturaleza y la filosofía del software libre, aún cuando esta temática está ganando en peso dentro y fuera del campo de la informática. Esta obra ha sido concebida en su mayor parte por un activo grupo de profesores de la Universidad Rey Juan Carlos de Madrid, uno de los grupos pioneros en la adopción y difusión del software libre en España

DSR in one of the best known protocols for datagram routing in ad-hoc networks. It uses source routing, soeach datagram must carry the addresses of all the machines in its path. Under some circunstances, specially with the use of IPv6, headers size can become very big. In this paper we propose ADSR protocol, a modification of DSR that drastically reduces its headers size by using abbreviated addresses for the routing. This mechanism can lead to two different nodes having the same address, fact that we coll a collision and analyce in this work. We will also show some results about this protocol performance obtained by simulations implemented using the ns-2 network simulator

Research on Mobile robotics is in our opinion more focused on generating autonomous behaviors than on the development of basic technologies (locomotion, localization, navigation, etc.). However, this issue is really a complex problem where many technologies converge: artificial perception, electronics, even philosophy and there are no general theories generally accepted in the research community. Historically, Cybernetics was the first subjacent theory, then artificial intelligence techniques were the dominant paradigm used to try the solve the problem, in the 90s the focus turned to biology based systems, nowadays ethology has emerged again as the most promising theories to generate autonomous behavior. In this paper we want to present the most relevant concepts borrowed from ethology that have been successfully used in mobile robotics, such as the use of ethograms in robotic pets or the ideas of schemes, or the use of fixed actions patterns to implement reactivity

Una de las habilidades fundamentales que debe poseer un robot para definirse como autónomo es la de autolocalizarse en un entorno dado. En este artículo abordaremos el problema de la localización aplicando técnicas probabilísticas combinando representaciones topológicas y métricas sobre un terreno acotado como es el campo de fútbol de la RoboCup. El artículo presenta también el funcionamiento y resultados obtenidos sobre un conjunto de pruebas simuladas y reales utilizando el humanoide Nao

In this article we propose a dynamic role exchange algorithm for mobile robots. The heuristics used to alternate among the different roles is based on utility functions. We have utilize the Sony Aibo ERS-7 for testing our design and implementation. The RoboCup 4-legged competition environment has been chosen for proving our work

Reinforcement learning har proven to be very successful for finding optimal policies on uncertian and/or dynamic domains. One of the problems on using such techniques appears with large state and action spaces. This problem appears very frequently given that most information in the type of tasks to which these techniques have been applied is continuous. In the paper, we describe a new mechanism for solving the states generalization problem in reinforcement learning algorithms, the VQQL technique

Position estimation is one of the classic problems in mobile robotics. The goal of this paper is to compare two probabilistic localization methods based on local vision for a mobile robot. The experimental set up is based on the Aibo league of the RoboCup, where the robotic dogs major sensor is the on-board camera. Two localization algorithms, Bayesian and Montecarlo (MCL), have been implemented and compared, and their behaviour studied in several situations using a simulator

En este artículo presentamos jdec, una implementación de la arquitectura basada en comportamientos Jerarquía Dinámica de Esquemas. Esta plataforma usa esquemas como unidad básica para la programación de aplicaciones con robots. Estos esquemas se combinan en jerarquías dinámicas para desarrollar comportamientos y en jdec se han implementado como hebras. La plataforma se ha probado en distintos robots reales con aplicaciones de navegación visual, de localización y navegación híbrida en interiores. Además, proporciona una capa de abstracción del hardware, ejecución distribuida, e interfaz gráfica para depuración así como una colección de esquemas ya realizados para componer nuevas aplicaciones

116 p. El comportamiento de un robot autónomo viene determinado por el programa que gobierna sus actuaciones. La creación de programas para robots debe cumplir con ciertos requisitos específicos frente a la programación en otros entornos más tradicionales, como el ordenador personal. En este artículo planteamos que el software de los robots se estructura actualmente en tres niveles: sistema operativo, plataforma de desarrollo y aplicaciones concretas. En los últimos años, han surgido con fuerza plataformas de desarrollo con la idea de facilitar la construcción incremental de estas aplicaciones robóticas. Más allá del acceso básico a los sensores y actuadores, las plataformas suelen proporcionar un modelo para la organización del código y bibliotecas con funcionalidades comunes. En este artículo se identifican y analizan esos tres niveles, describiendo desde esta perspectiva los entornos de desarrollo de los robots reales más extendidos, y las tendencias más recientes

This paper deals with the decision making process, using fuzzy information, in a distributed environment. In order to deal with the complexity of this problem we have used the agent model approach. In this way we have apply this model to the problem of transportation in a non-centralized environment. The internal decosion process inside each agent is archieved through a fuzzy reasoning system

Determining the 3D location of a moving object, and tracking it from a sequence of different camera images is a classical but still challenging problem. In our approach neither explicit triangulation, nor precise motion model are used; only the colour of the object to be tracked is required. We use a particle filter, where the observation model we have developed avoids the colour filtering of the entire image. Preliminary experiments are presented and lessons learned are commented. The approach easily scales to several cameras and new sensor cues

This article exposes the localization issues faced during the implementation of a humanoid goalkeeper to take part in the RoboCup SPL standardized soccer robot competition. For this task, we have used BICA, a state-driven, component-based architecture created by our counterparts in the URJC, to allow a much easier behavior design process. The use of BICA let us choose different self-localization methods in configuration time, and the possibility of using none in running time if some type of error appears

P. 31-32 One of the major scientific contributions of CompCog has been to provide a unified system to collate research methods and results across various animal species, including humans, and also artificial creatures (robots). The systematic collection of data produced by different research groups would enhance the study of social cognition in an operationally comparative way. In the project an on-line video tagging system has been developed. Another contribution has been the use of mobile robots to test the abilities of ethologists SI

Visual attention is a natural tool which allows animals to locate relevant objects or areas in a given scene, discarding the rest of elements present and thus reducing the amount of information to deal with. In this paper we present the design an implementation of a visual attention mechanism based on a saliency map and its implementation in the Nao humanoid. This control mechanism is applied to solve one of the challenges proposed in the RoboCup competition named ”any-ball”. The results obtained are analysed and future works derived from that analysis are presented

The main goal of the project described in this paper is to create a security system using autonomous surveillance robots that use SODAR-like detection system sensors, working with acoustic signals in air environment and navigation base on Geographic Information System and Markov's models. The surveillance system based on SONAR provides great information from the environment, even lets you see behind objects (rebounds effects) whose manipulation offers a great added value to surveillance The guide system will implement in one hand a local navigation module directed to avoid obstacles based on classical techniques and using the new SODAR sensor. On the other hand a global navigation module will be implemented using preset trajectories and gradient techniques and an auto-location system. One of the greatest challenges obtained is the definition of the VIGICOPVar variable that defines, depending on the environment and safety parameters, the probability of intrusion. Surveillance experts of GRUPO NORTE (multinational company with security expertise of more than 38 years) have worked In the definition and validation of the model. The monitoring robots will be controlled in a centralized way from an alarm center from where you can manage all information relating to intrusion detected. VIGICOP is the low cost surveillance robot which provides new/full information interactive surveillance information

Attention mechanism can be used both for reducing the amount of perceptual information to be processed and for restricting all available actions to only those useful for a given scenario. Information reduction improves performance and action restriction allows for a more precise interaction with our environment. In this paper we present the design of an attention control mechanism based on a saliency map and its implementation in the SPL's Nao robot. The results obtained are analysed and future works derived from that analysis are presented