Suchergebnisse

Generating complex, human-like behavior in a humanoid robot like the iCub requires the integration of a wide range of open source components and a scalable cognitive architecture. Hence, we present the iCub-HRI library which provides convenience wrappers for components related to perception (object recognition, agent tracking, speech recognition, and touch detection), object manipulation (basic and complex motor actions), and social interaction (speech synthesis and joint attention) exposed as a C++ library with bindings for Java (allowing to use iCub-HRI within Matlab) and Python. In addition to previously integrated components, the library allows for simple extension to new components and rapid prototyping by adapting to changes in interfaces between components. We also provide a set of modules which make use of the library, such as a high-level knowledge acquisition module and an action recognition module. The proposed architecture has been successfully employed for a complex human–robot interaction scenario involving the acquisition of language capabilities, execution of goal-oriented behavior and expression of a verbal narrative of the robot's experience in the world. Accompanying this paper is a tutorial which allows a subset of this interaction to be reproduced. The architecture is aimed at researchers familiarizing themselves with the iCub ecosystem, as well as expert users, and we expect the library to be widely used in the iCub community. ; The research leading to these results has received funding under the European Union's Seventh Framework Programme (FP/2007-2013)/ERC Grant Agreement n. FP7-ICT-612139 (WYSIWYD—What You Say Is What You Did) and FP7-ICT-270490 (EFAA—The Experimental Functional Android Assistant). PN was supported by a Marie Curie Early Stage Researcher Fellowship (H2020-MSCA-ITA, SECURE 642667). PV was supported by the ERC advanced grant 341196 (cDAC—Role of Consciousness in Adaptive Behavior).

In this paper, we present a novel methodology to obtain imitative and innovative postural movements in a humanoid based on human demonstrations in a different kinematic scale. We collected motion data from a group of human participants standing up from a chair. Modeling the human as an actuated 3-link kinematic chain, and by defining a multi-objective reward function of zero moment point and joint torques to represent the stability and effort, we computed reward profiles for each demonstration. Since individual reward profiles show variability across demonstrating trials, the underlying state transition probabilities were modeled using a Markov chain. Based on the argument that the reward profiles of the robot should show the same temporal structure of those of the human, we used differential evolution to compute a trajectory that fits all humanoid constraints and minimizes the difference between the robot reward profile and the predicted profile if the robot imitates the human. Therefore, robotic imitation involves developing a policy that results in a temporal reward structure, matching that of a group of human demonstrators across an array of demonstrations. Skill innovation was achieved by optimizing a signed reward error after imitation was achieved. Experimental results using the humanoid HOAP-3 are shown. ; The research leading to these results has received funding from the ARCADIA project DPI2010-21047-C02-01, funded by CICYT project grant on behalf of Spanish Ministry of Economy and Competitiveness and from the RoboCity2030-II-CM project (S2009/DPI-1559), funded by Programas de Actividades I+D en la Comunidad de Madrid and co-funded by Structural Funds of the EU. ; Publicado

Purpose
– The purpose of this paper is to identify ways teachers might employ a robot to achieve learning objectives with pupils with intellectual disabilities and potential outcome measures.


Design/methodology/approach
– A series of five case studies where teacher-pupil dyads were observed during five planned video-recorded sessions with a humanoid robot. Engagement was rated in a classroom setting and during the last session with the robot. Video recordings were analysed for duration of engagement, teacher assistance and number of goals achieved.


Findings
– Teachers identified a wide range of learning objectives ranging from an appreciation of cause and effect to improving the pupil's sense of direction. The robot's role could be to reward behaviour, provide cues or provide an active element to learning. Rated engagement was significantly higher with the robot than in the classroom.


Research limitations/implications
– A robot with a range of functions that allowed it to be engaging and motivating for the wide range of pupils in special education would be expensive and require teachers to learn how to use it. The findings identify ways to provide evidence that this expenditure of time and money is worthwhile.


Originality/value
– There is almost no research teachers can refer to on using robots to support learning in children with intellectual disabilities. This paper is therefore of value for researchers who wish to investigate using robots to educate children with intellectual disabilities, as it can provide vital information to aid study design.

Source of fascination and distrust, the humanoid robot, machine endowed with an artificial intelligence and created on the human model, concretizes ancestral dreams, with the ambition to equal or even exceed its model and creator. And while it becomes a reality, being an integral part of our daily lives and taking different forms, the birth of the robot is closely linked to that of the cinema, which seizes very early the figure : how then to characterize the link which unites the two, and what are the specificities of the art and cinematographic medium in its representations ? In order to understand what underlies the representation of the robot in cinema, its specificities, its stakes, and what it says today about the biological, political and social human, this work proposes to return to the golden age of the humanoid robot in cinema located in the late twentieth century in order to analyze its metamorphoses in the digital age. The humanoid robot sends its image back to man, and becomes in the cinema a revealing reflection of the tensions and crises that the Western society is experiencing and the status of the cinematographic image that becomes a reflection of the ambivalent relationship that we have with our creation and our own image. At the crossroads of different approaches, this dissertation attempts to describe and decipher the confusion and turmoil inherent in the representation of the humanoid robot, its avatars and its interactions with humans, and the upheaval linked to the arrival of digital technologies and big data. ; Source de fascination et de méfiance, le robot humanoïde, machine dotée d'une intelligente artificielle et créée sur le modèle humain, concrétise des rêves ancestraux, avec pour ambition d'égaler voire dépasser son modèle et créateur. Et tandis qu'il devient une réalité, faisant partie intégrante de nos vies quotidienne et revêtant différents formes, la naissance du robot est étroitement liée à celle du cinéma, qui s'empare très tôt de la figure : comment alors caractériser le lien qui unit les deux, et quelles sont les spécificités de l'art et médium cinématographique dans ses représentations ? Afin de comprendre ce qui sous-tend la représentation du robot au cinéma, ses spécificités, ses enjeux, et ce qu'elle dit aujourd'hui de l'humain biologique, et politique et social, ce travail propose de revenir sur l'âge d'or du robot humanoïde au cinéma situé dans la fin du XXe siècle afin d'analyser ses métamorphoses à l'ère numérique. Le robot humanoïde renvoie son image à l'homme, et devient au cinéma un reflet révélateur des tensions et crises que connaissent l'Occident et le statut de l'image cinématographique qui devient le reflet des rapports ambivalents que nous entretenons avec notre création et notre propre image. À la croisée de différentes approches, ce mémoire tente de décrire et décrypter la confusion et le trouble inhérents à la représentation du robot humanoïde, ses avatars et ses interactions avec l'humain, et le bouleversement lié à l'arrivée des technologies numériques et des big data .

Source of fascination and distrust, the humanoid robot, machine endowed with an artificial intelligence and created on the human model, concretizes ancestral dreams, with the ambition to equal or even exceed its model and creator. And while it becomes a reality, being an integral part of our daily lives and taking different forms, the birth of the robot is closely linked to that of the cinema, which seizes very early the figure : how then to characterize the link which unites the two, and what are the specificities of the art and cinematographic medium in its representations ? In order to understand what underlies the representation of the robot in cinema, its specificities, its stakes, and what it says today about the biological, political and social human, this work proposes to return to the golden age of the humanoid robot in cinema located in the late twentieth century in order to analyze its metamorphoses in the digital age. The humanoid robot sends its image back to man, and becomes in the cinema a revealing reflection of the tensions and crises that the Western society is experiencing and the status of the cinematographic image that becomes a reflection of the ambivalent relationship that we have with our creation and our own image. At the crossroads of different approaches, this dissertation attempts to describe and decipher the confusion and turmoil inherent in the representation of the humanoid robot, its avatars and its interactions with humans, and the upheaval linked to the arrival of digital technologies and big data. ; Source de fascination et de méfiance, le robot humanoïde, machine dotée d'une intelligente artificielle et créée sur le modèle humain, concrétise des rêves ancestraux, avec pour ambition d'égaler voire dépasser son modèle et créateur. Et tandis qu'il devient une réalité, faisant partie intégrante de nos vies quotidienne et revêtant différents formes, la naissance du robot est étroitement liée à celle du cinéma, qui s'empare très tôt de la figure : comment alors caractériser le lien qui unit les deux, et quelles sont les spécificités de l'art et médium cinématographique dans ses représentations ? Afin de comprendre ce qui sous-tend la représentation du robot au cinéma, ses spécificités, ses enjeux, et ce qu'elle dit aujourd'hui de l'humain biologique, et politique et social, ce travail propose de revenir sur l'âge d'or du robot humanoïde au cinéma situé dans la fin du XXe siècle afin d'analyser ses métamorphoses à l'ère numérique. Le robot humanoïde renvoie son image à l'homme, et devient au cinéma un reflet révélateur des tensions et crises que connaissent l'Occident et le statut de l'image cinématographique qui devient le reflet des rapports ambivalents que nous entretenons avec notre création et notre propre image. À la croisée de différentes approches, ce mémoire tente de décrire et décrypter la confusion et le trouble inhérents à la représentation du robot humanoïde, ses avatars et ses interactions avec l'humain, et le bouleversement lié à l'arrivée des technologies numériques et des big data .

En este artículo se presenta el desarrollo e implementación de un sistema de captura de movimiento antropomórfico mediante técnicas de visión de máquina basado en el dispositivo Kinect, con el fin de realizar el control de movimiento imitativo de un agente robótico Bioloid en el Grupo de Aplicaciones Virtuales (GAV) del Programa de Ingeniería en Mecatrónica de la Universidad Militar Nueva Granada (UMNG). Dados los múltiples grados de libertad de un brazo humano, se busca simplificar una interfaz de control que permita replicar los movimientos de este en un robot humanoide. En este artículo se presentan las técnicas usadas para mejorar el nivel de precisión de los datos entregados por el Kinect y los métodos personalizados de transmisión y codificación de las órdenes enviadas al robot. Los resultados obtenidos derivan en un sistema que cumple con las exigencias básicas de estabilidad, precisión y velocidad de repuesta en la imitación ; This paper presents the development and implementation of an anthropomorphic motion capture system through machine vision based on the Kinect device in order to achieve the imitative motion control of a Bioloid robotic agent of the GAV research group from the Mecatronics Engineering program at UMNG. We present the techniques used to improve data precision delivered by Kinect, as well as custom methods of transmission and coding of commands sent to the robot. Results derive in a system that meets the basic requirements of stability, accuracy and speed of imitation response

The article focuses on the analysis of subjective conditions for the integration of humans with humanoid robots. By interacting with each other, these units create hybrid systems that deserve to be called positive, as interactions with technological artifacts contribute to increasing the optimal functioning of users. An online survey-based study with 364 respondents was conducted that tested the relationship between anthropocentric beliefs of individuals, attitudes towards, and interactions with humanoid robots. It was found that this relationship is positive and is mediated by the aspects of fear of artificial intelligence (AI) related to the perception of AI-driven agents as scary and intimidating and by anxiety caused by the fear of their strong expansion (e.g., in the labor market). The significant strength of the relationship is an important clue for people designing hybrid systems (e.g., in the workplace), especially in conservative societies whose representatives are sensitive to the position humans in the hierarchy of entities.