Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 13
Encontrada(s) 1 página(s)

RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

STEAM Approach to Autonomous Robotics Curriculum for High School Using the Robobo Robot

  • Bellas, Francisco
  • Mallo, Alma
  • Naya-Varela, M.
  • Souto, Daniel
  • Deibe Díaz, Álvaro
  • Prieto García, Abraham
  • Duro, Richard J.
This version of the conference paper has been accepted for publication, after peer review and is subject to Springer Nature’s AM terms of use (https://www.springernature.com/gp/open-science/policies/accepted-manuscript-terms), but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1007/978-3-030-26945-6_8., Included in: 'Robotics in Education: Current Research and Innovations' - Proceedings of the 10th International Conference on Robotics in Education (RiE 2019) held in Vienna, Austria, April 10–12, 2019., [Abstract]: Teaching robotics in secondary school is common nowadays, although with heterogeneous approaches in different countries, mainly in the specific technology that is used. Even with such lack of standardization, there are many common elements in these early stages of educational robotics, focused on basic assembling, simple sensing, and locomotion, which are a consequence of the simplicity of the robots that are used. In this paper, we aim to go one step ahead, and propose an approach of how the next stage in educational robotics should be. To this end, we analyze the current situation of this subject in reference to the robotics market and society, and then we propose a structure for the curriculum development. This approach is based on the use of the Robobo robot, as a clear example of the type of device that allows to perform such update of the subject, and on the use of a STEAM methodology, where a global view of how to face a robotics problem is presented., This work has been funded by the EU’s H2020 research programme under grant No 640891 (DREAM) and by the Xunta de Galicia under grant ED431C 2017/12., Xunta de Galicia; ED431C 2017/12
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

The Robobo Project: Bringing Educational Robotics Closer to Real-World Applications

  • Bellas, Francisco
  • Naya-Varela, M.
  • Varela, Gervasio
  • Llamas, Luis
  • Prieto García, Abraham
  • Becerra Permuy, Juan Carlos
  • Bautista, Moises
  • Duro, Richard J.
  • Faíña, Andrés
This version of the conference paper has been accepted for publication, after peer review and is subject to Springer Nature’s AM terms of use (https://www.springernature.com/gp/open-science/policies/accepted-manuscript-terms), but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1007/978-3-319-62875-2_20., [Abstract]: The Robobo Project is a STEM-based project that aims to bring educational robotics, in primary and high school, closer to real-world applications. It is based on the use of a smartphone-based robotic platform called Robobo, a very flexible programming environment, and a set of lessons to integrate them. The smartphone provides high-level hardware capabilities in terms of sensors, communications and processing capabilities that allow to create more practical and realistic lessons that exploit human-robot interaction, with a small investment. In this paper, we present the main elements of The Robobo Project in terms of hardware and software, and two illustrative educational projects that can be developed within it., This work has been partially funded by the EU’s H2020 research and innovation programme under grant agreement No 640891 (DREAM project) and by the Xunta de Galicia and redTEIC network (ED341D R2016/012)., Xunta de Galicia; ED341D R2016/012
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Simplifying the Creation and Management of Utility Models in Continuous Domains for Cognitive Robotics

  • Romero, Alejandro
  • Prieto García, Abraham
  • Bellas, Francisco
  • Duro, Richard J.
[Abstract] Establishing goal/sub-goal hierarchies in robotic motivational systems for open-ended learning situations and modelling this utility in a manner that is useful for robots is an open research problem, especially when the robots’ state-spaces are continuous and may present ambiguities. In these cases, directly obtaining value functions, and in particular, precise Artificial Neural Network based value functions, becomes very difficult. In this paper, this issue is addressed through a new type of coarse utility functions for the representation of motivation. The proposed approach can be used as an intermediate step in order to be able to produce more consistent data for the subsequent training of precise value functions when and where it becomes necessary. This type of coarse utility functions, called Separable Utility Regions (SUR), are based on the use of the variation of sensor values as clues to the position of goals in state space. Moreover, areas in the state-space must be established where there are correlations between the desired direction the system should follow in its state-space towards a goal, and the direction of variation of the values of a particular sensor. The main focus of this paper is on the process of creating sub-goal hierarchies that permit leading the system in a consistent manner towards goals, so that it can autonomously learn to achieve them whatever its starting state. To this end, an approach to sub-goal determination and chaining based on a recursive establishment of consolidated goal domains as new goals for new utility functions is described. The approach is tested on a real robotic system and the results are extensively analysed and discussed., Xunta de Galicia; ED341D R2016/012, Xunta de Galicia; ED431C 2017/12, This work has been partially funded by the EU's H2020 research and innovation programme under grant agreement No 640891 (DREAM project) and by the Xunta de Galicia and European Regional Development Funds under grants ED431C 2017/12 and redTEIC network (ED341D R2016/012).
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Open-ended learning: a conceptual framework based on representational redescription

  • Doncieux, Stephane
  • Filliat, David
  • Díaz-Rodríguez, Natalia
  • Hospedales, Timothy
  • Duro, Richard J.
  • Coninx, Alexandre
  • Roijers, Diederik M.
  • Benoît, Girard
  • Perrin, Nicolas
  • Sigaud, Oliver
[Abstract]: Reinforcement learning (RL) aims at building a policy that maximizes a task-related reward within a given domain. When the domain is known, i.e., when its states, actions and reward are defined, Markov Decision Processes (MDPs) provide a convenient theoretical framework to formalize RL. But in an open-ended learning process, an agent or robot must solve an unbounded sequence of tasks that are not known in advance and the corresponding MDPs cannot be built at design time. This defines the main challenges of open-ended learning: how can the agent learn how to behave appropriately when the adequate states, actions and rewards representations are not given? In this paper, we propose a conceptual framework to address this question. We assume an agent endowed with low-level perception and action capabilities. This agent receives an external reward when it faces a task. It must discover the state and action representations that will let it cast the tasks as MDPs in order to solve them by RL. The relevance of the action or state representation is critical for the agent to learn efficiently. Considering that the agent starts with a low level, task-agnostic state and action spaces based on its low-level perception and action capabilities, we describe open-ended learning as the challenge of building the adequate representation of states and actions, i.e., of redescribing available representations. We suggest an iterative approach to this problem based on several successive Representational Redescription processes, and highlight the corresponding challenges in which intrinsic motivations play a key role.
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

A versatile robotic platform for educational interaction

  • Naya-Varela, M.
  • Varela, Gervasio
  • Llamas, Luis
  • Bautista, Moises
  • Becerra Permuy, Juan Carlos
  • Bellas, Francisco
This version of the paper has been accepted for publication. The final published paper is available online at: https://doi.org/10.1109/IDAACS.2017.8095065., Included in: 2017 9th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS), Bucharest, Romania, 21-23 September 2017., [Abstract]: This paper describes a new educational robot called ROBOBO which was developed in order to provide an engaging and natural interactive experience with children. The objective is to motivate children to explore and cooperate with the robots while they learn concepts and abilities related to STEM education (Science, Technology, Engineering and Mathematics). The robot and the educational approach has been tested in different school environments corresponding to different educational levels with very successful results., This work has been partially funded by the EU’s H2020 research and innovation programme under grant agreement No 640891 (DREAM project) and by the Xunta de Galicia and redTEIC network (ED341D R2016/012)., Xunta de Galicia; ED341D R2016/012
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Embodied evolution in collective robotics: A review

  • Prieto García, Abraham
  • Bredeche, Nicolas
  • Haasdijk, Evert
[Abstract]: This article provides an overview of evolutionary robotics techniques applied to online distributed evolution for robot collectives, namely, embodied evolution. It provides a definition of embodied evolution as well as a thorough description of the underlying concepts and mechanisms. This article also presents a comprehensive summary of research published in the field since its inception around the year 2000, providing various perspectives to identify the major trends. In particular, we identify a shift from considering embodied evolution as a parallel search method within small robot collectives (fewer than 10 robots) to embodied evolution as an online distributed learning method for designing collective behaviors in swarm-like collectives. This article concludes with a discussion of applications and open questions, providing a milestone for past and an inspiration for future research.
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Introducing Separable Utility Regions in a Motivational Engine for Cognitive Developmental Robotics

  • Prieto García, Abraham
  • Romero, Alejandro
  • Bellas, Francisco
  • Duro, Richard J.
[Abstract] Cognitive Developmental Robotics relies on lifelong open-ended learning processes, where mechanisms are needed to allow the robot to self-discover and self-select goals as well as to self-define its state space evaluation with regards to them. Thus, this paper addresses the problem of finding and using goals in continuous state spaces and automatically obtaining sub-goal hierarchies that allow autonomous development. In particular, the main purpose of this paper is to propose a new approach to the creation of utility models based on the concept of separable utility regions (SURs), which reduce the complexity of standard value function like utility models. These regions exhibit a correlation between the expected utility and the response of one sensor of the robot. Once they are discovered, the evaluation of the candidate states is only based on the changes of one sensor, which provides a strong independence from noise or dynamism in the utility models. A non-static variation of the classical collect-a-ball scenario and a robot gathering problem were used to test this approach in simulation and on real robots in order to identify goals and sub-goals in an autonomous way. The results confirm the good response of the method as a highly promising approach towards autonomous learning of continuous domains in cognitive robotics., This work has been partially funded by the EU’s H2020 research and innovation programme under grant agreement No 640891 (DREAM project) and by the Xunta de Galicia and European Regional Development Funds under grants ED431C 2017/12 and redTEIC network (ED341D R2016/012)., Xunta de Galicia; ED431C 2017/12, Xunta de Galicia; ED341D R2016/012
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Studying How Innate Motivations Can Drive Skill Acquisition in Cognitive Robots

  • Romero, Alejandro
  • Bellas, Francisco
  • Becerra Permuy, José Antonio
  • Duro, Richard J.
This article belongs to the Proceedings of XoveTIC Conference, Abstract: In this paper, we address the problem of how to bootstrap a cognitive architecture to opportunistically start learning skills in domains where multiple skills can be learned at the same time. To this end, taking inspiration from a series of computational models of the use of motivations in infants, we propose an approach that leverages two types of cognitive motivations: exploratory and proficiency based, the latter modulated by the concept of interestingness as an implementation of attentional mechanisms. This approach is tested in an illustrative experiment with a real robot., Xunta de Galicia; ED431C 2017/12, Ministerio de Economía y Competitividad; TIN2015-63646-C5-1-R
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Motivational Engine and Long-Term Memory Coupling Within a Cognitive Architecture for Lifelong Open-Ended Learning

  • Becerra Permuy, José Antonio
  • Romero, Alejandro
  • Bellas, Francisco
  • Duro, Richard J.
Manuscrito aceptado, [Abstract] This paper considers a cognitive architecture that revolves around a network memory based Long-Term Memory and how it can lead to a working lifelong learning system that can deal with open-ended learning. It focuses on the mutual interaction between the Motivational Engine and the Long-Term Memory and, in particular, on autonomously producing high-level utility representations in order to allow for development. Thus, the main point is to study how this architecture allows to start from primitive policies and models operating over continuous and large state/action spaces and progressively move towards higher level structures defined over smaller and discrete state/action spaces. This progression is demonstrated in a series of experiments carried out on a real robotic setup that involves different contexts, both in terms of domains (worlds) and tasks (goals)., This work has been partially funded by the EU's H2020 research programme under grant No 640891 (DREAM) as well as by the Xunta de Galicia and the European Regional Development Funds under grant ED431C 2017/12 and the Spanish Science and Education Ministry through grant RTI2018-101114-B-I00 and the FPU grant of Alejandro Romero. Centro de Investigación de Galicia "CITIC", funded by Xunta de Galicia and the European Union (European Regional Development Fund- Galicia 2014-2020 Program), by grant ED431G 2019/01., Xunta de Galicia; ED431C 2017/12, Xunta de Galicia; ED431G 2019/01
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Perceptual Generalization and Context in a Network MemoryInspired Long-Term Memory for Artificial Cognition

  • Duro, Richard J.
  • Becerra Permuy, José Antonio
  • Monroy Camafreita, Juan
  • Bellas, Francisco
Abstract: In the framework of open-ended learning cognitive architectures for robots, this paper deals with thedesign of a Long-Term Memory (LTM) structure that can accommodate the progressive acquisition ofexperience-based decision capabilities, or what different authors call “automation” of what is learnt, asa complementary system to more common prospective functions. The LTM proposed here provides fora relational storage of knowledge nuggets given the form of artificial neural networks (ANNs) that isrepresentative of the contexts in which they are relevant in a configural associative structure. It alsoaddresses the problem of continuous perceptual spaces and the task- and context-related generalizationor categorization of perceptions in an autonomous manner within the embodied sensorimotor apparatusof the robot. These issues are analyzed and a solution is proposed through the introduction of two newtypes of knowledge nuggets: P-nodes representing perceptual classes and C-nodes representing contexts.The approach is studied and its performance evaluated through its implementation and application to areal robotic experiment, Xunta de Galicia; ED431C 2017/12, Xunta de Galicia; ED341D R2016/012
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Motivation as a Tool for Designing Lifelong Learning Robots

  • Romero, Alejandro
  • Bellas, Francisco
  • Becerra Permuy, José Antonio
  • Duro, Richard J.
[Abstract] Designing robots has usually implied knowing beforehand the tasks to be carried out and in what domains. However, in the case of fully autonomous robots this is not possible. Autonomous robots need to operate in an open-ended manner, that is, deciding on the most interesting goals to achieve in domains that are not known at design time. This obviously poses a challenge from the point of view of designing the robot control structure. In particular, the main question that arises is how to endow the robot with a designer defined purpose and with means to translate that purpose into operational decisions without any knowledge of what situations the robot will find itself in. In this paper, we provide a formalization of motivation from an engineering perspective that allows for the structured design of purposeful robots. This formalization is based on a definition of the concepts of robot needs and drives, which are related through experience to the appropriate goals in specific domains. To illustrate the process, a motivational system to guide the operation of a real robot is constructed using this approach. A series of experiments carried out over it are discussed providing some insights on the design of purposeful motivated operation., This work was partially funded by the EU’s H2020 research programme (grant No 640891 DREAM), Ministerio de Ciencia, Innovación y Universidades of Spain/FEDER (grant RTI2018-101114-B-I00), Xunta de Galicia and FEDER (grant ED431C 2017/12), and by the Spanish Ministry of Education, Culture and Sports through the FPU grant of Alejandro Romero, Xunta de Galicia; ED431C 2017/12
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Behavioural Specialisation in Embodied Evolutionary Robotics: Why so Difficult?

  • Montanier, Jean-Marc
  • Carrignon, Simon
  • Bredeche, Nicolas
Embodied evolutionary robotics is an on-line distributed learning method used in collective robotics where robots are facing open environments. This paper focuses on learning behavioral specialization, as defined by robots being able to demonstrate different kind of behaviors at the same time (e.g., division of labor). Using a foraging task with two resources available in limited quantities, we show that behavioral specialization is unlikely to evolve in the general case, unless very specific conditions are met regarding interactions between robots (a very sparse communication network is required) and the expected outcome of specialization (specialization into groups of similar sizes is easier to achieve). We also show that the population size (the larger the better) as well as the selection scheme used (favoring exploration over exploitation) both play important – though not always mandatory – roles. This research sheds light on why existing embodied evolution algorithms are limited with respect to learning efficient division of labor in the general case, i.e., where it is not possible to guess before deployment if behavioral specialization is required or not, and gives directions to overcome current limitations., This work is supported by the European Unions Horizon 2020 research and innovation programme under grant agreement No 640891, and the ERC Advanced Grant EPNet (340828). Part of the experiments presented in this paper were carried out using the Grid’5000 experimental testbed, being developed under the INRIA ALADDIN development action with support from CNRS, RENATER, and several Universities as well as other funding bodies (see https://www.grid5000.fr). The other parts of the simulations have been done in the supercomputer MareNostrum at Barcelona Supercomputing Center – Centro Nacional de Supercomputacion (The Spanish National Supercomputing Center)., Peer Reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Behavioural Specialisation in Embodied Evolutionary Robotics: Why so Difficult?

  • Montanier, Jean-Marc
  • Carrignon, Simon
  • Bredeche, Nicolas
Embodied evolutionary robotics is an on-line distributed learning method used in collective robotics where robots are facing open environments. This paper focuses on learning behavioral specialization, as defined by robots being able to demonstrate different kind of behaviors at the same time (e.g., division of labor). Using a foraging task with two resources available in limited quantities, we show that behavioral specialization is unlikely to evolve in the general case, unless very specific conditions are met regarding interactions between robots (a very sparse communication network is required) and the expected outcome of specialization (specialization into groups of similar sizes is easier to achieve). We also show that the population size (the larger the better) as well as the selection scheme used (favoring exploration over exploitation) both play important – though not always mandatory – roles. This research sheds light on why existing embodied evolution algorithms are limited with respect to learning efficient division of labor in the general case, i.e., where it is not possible to guess before deployment if behavioral specialization is required or not, and gives directions to overcome current limitations., This work is supported by the European Unions Horizon 2020 research and innovation programme under grant agreement No 640891, and the ERC Advanced Grant EPNet (340828). Part of the experiments presented in this paper were carried out using the Grid’5000 experimental testbed, being developed under the INRIA ALADDIN development action with support from CNRS, RENATER, and several Universities as well as other funding bodies (see https://www.grid5000.fr). The other parts of the simulations have been done in the supercomputer MareNostrum at Barcelona Supercomputing Center – Centro Nacional de Supercomputacion (The Spanish National Supercomputing Center)., Peer Reviewed, Postprint (published version)