198documents trouvés
Learning from previous manipulation actions and planned results. DI3.10
D.SIDOBRE, X.BROQUERE, J.MAINPRICE, W.HE, J.CORTES, T.SIMEON, F.INGRAND, M.HERRB, J.MANHES, R.ALAMI
RIS, IDEA, I2C
Rapport de Contrat : ICT-FP7216239-DEXMART, Juillet 2012, 15p. , N° 12381
Diffusable
127722Vers une gestion des croyances pour la planification Homme - Robot
J. GUITTON, M.WARNIER, R.ALAMI
ONERA, RIS
Manifestation avec acte : Journées Francophones sur la Planification la Décision et l'Apprentissage pour la conduite de systèmes JFPDA 2012 7 du 22 mai au 23 mai 2012, Nancy (France), Mai 2012, 14p. , N° 12639
Lien : http://hal.inria.fr/hal-00736219
Diffusable
Plus d'informations
Résumé
Cet article présente une extension d'une approche de planification hiérarchique pour la gestion des problèmes multi-agents et, plus spécialement, pour les problèmes d'interaction Homme-Robot dans lesquels un robot et un humain doivent coopérer pour atteindre un but commun. La méthode proposée permet de raisonner et de planifier pour des agents qui ont des croyances différentes ou incomplètes. Elle s'appuie sur une nouvelle description des croyances des agents et sur un mécanisme permettant de produire et d'insérer des actions de communication dans le plan courant. Ces actions de communication ont pour fonction de transmettre des informations d'un agent à l'autre.
Human-Robot interaction in the MORSE simulator
S.LEMAIGNAN, G.ECHEVERRIA, M.KARG, J.MAINPRICE, A.KIRSCH, R.ALAMI
RIS, Munchen
Manifestation avec acte : ACM/IEEE International Conference on Human-Robot Interaction (HRI 2012), Boston (USA), 5-8 Mars 2012, 2p. , N° 12051
Lien : http://hal.archives-ouvertes.fr/hal-00667026
Diffusable
Plus d'informations
Abstract
Over the last two years, the Modular OpenRobots Simulation Engine (MORSE) project1 went from a simple extension plugged on the Blender's Game Engine to a full-fledged simulation environment for academic robotics. Driven by the requirements of several of its developers, tools dedicated to Human-Robot interaction simulation have taken a prominent place in the project. This late breaking report discusses some of the recent additions in this domain, including the immersive experience provided by the integration of the Kinect device as input controller. We also give an overview of the experiences we plan to complete in the coming months.
Roboscopie: A Theatre Performance for a Human and a Robot
S.LEMAIGNAN, M.GHARBI, J.MAINPRICE, M.HERRB, R.ALAMI
RIS, 2I
Manifestation avec acte : ACM/IEEE International Conference on Human-Robot Interaction (HRI 2012), Boston (USA), 5-8 Mars 2012, 1p. , N° 12054
Lien : http://hal.archives-ouvertes.fr/hal-00667021
Diffusable
Plus d'informations
Abstract
On the 14th of October 2011, we performed for a general public audience (over 300 persons) a 18 min long live theatre play, acted by professional actor Xavier Brossard and the LAAS/CNRS PR2 robot. The play was created and directed by Nicolas Darrot, a mixed-media artist from Paris. The PR2 has been programmed in a 2-months course, reusing several software components developed at LAAS/CNRS, including the 3D environment for situation assessment SPARK, the ontology-based knowledge base ORO and the natural-language processor Dialogs. This video abstract presents the storyline of the play, and underlines some of the significant outcome for the human-robot interaction community. The full-length version of the video, along with downloads of the open-source components, is available from www.laas.fr/roboscopie.
Grounding the interaction: anchoring situated discourse in everyday human-robot interaction
S.LEMAIGNAN, R.ROS ESPINOZA, E.A.SISBOT, R.ALAMI, M.BEETZ
RIS, Munchen
Rapport LAAS N°11743, DOI: 10.1007/s12369-011-0123-x, Février 2012, 20p.
Lien : http://hal.archives-ouvertes.fr/hal-00664546
Diffusable
Plus d'informations
Abstract
This paper presents how extraction, representation and use of symbolic knowledge from real-world perception and human-robot verbal and non-verbal in-teraction can actually enable a grounded and shared model of the world that is suitable for later high-level tasks such as dialogue understanding. We show how the anchoring process itself relies on the situated nature of human-robot interactions. We present an integrated approach, including a specialized symbolic knowledge representation system based on Description Logics, and case studies on several robotic platforms that demonstrate these cognitive capabilities.
What are you talking about? Grounding dialogue in a perspective-aware robotic architecture
S.LEMAIGNAN, R.ROS ESPINOZA, R.ALAMI, M.BEETZ
RIS, Munchen
Manifestation avec acte : IEEE International Symposium on Robot and Human Interactive Communication (Ro-MAN 2011), Atlanta (USA), 31 Juillet - 3 Aout 2011, pp.107-112 , N° 11735
Lien : http://hal.archives-ouvertes.fr/hal-00664548
Diffusable
Plus d'informations
Abstract
While key for human-robot interaction, natural language interpretation is a notoriously difficult task, especially because the interaction context is at the same time essential for dialogue understanding, difficult to build for machines, and depends on each speaker point of view. However, robots as embodied artifacts, can perceive their environment and interactors, and hence compute symbolic models from various perspectives. This allows in turn to build symbolic contexts for dialogues. In this paper, we introduce DIALOGS, a component for natural language interpretation that relies on these structured symbolic models of the world to ground verbal interaction.
Towards task understanding through multi-state visuo-spatial perspective taking for human-robot interaction
A.PANDEY, R.ALAMI
RIS
Manifestation avec acte : International Joint Conference on Artificial Intelligence (IJCAI'11), Barcelone (Espagne), 16-17 Juillet 2011, 6p. , N° 11637
Diffusable
125907Dialogue in situated environments: A symbolic approach to perspective-aware grounding, clarification and reasoning for robot
S.LEMAIGNAN, R.ROS ESPINOZA, R.ALAMI
RIS
Manifestation avec acte : Workshop on Grounding Human-Robot Dialog for Spatial Tasks, Los Angeles (USA), 1 Juillet 2011, 4p. , N° 11744
Lien : http://hal.archives-ouvertes.fr/hal-00667030
Diffusable
Plus d'informations
Abstract
Interacting with a robot in a shared space requires not only a shared model (i.e., environment entities must be described with the same symbols), but also a model of mutual knowledge: both the robot and the human need to figure out what the other knows, sees or can do in the environment to appropriately behave. We present here our efforts to let the robot grounds verbal interaction with a human in a physical, situated environment. We propose a knowledge-oriented architecture, where perceptions from different point of views (from the robot itself, from the human, etc.) are turned into symbolic facts that are stored in different cognitive models and reused in a newly designed module for dialogue grounding.
Planning and executing human-aware motions for human-robot interaction
J.MAINPRICE, X.BROQUERE, D.SIDOBRE, R.ALAMI, T.SIMEON
RIS
Rapport LAAS N°11318, Juin 2011, 7p.
Diffusable
124815Towards multi-state visuo-spatial reasoning based proactive human-robot interaction
A.PANDEY, M.ALI, M.WARNIER, R.ALAMI
RIS
Manifestation avec acte : International Conference on Advanced Robotics (ICAR 2011), Tallinn (Estonie), 20-23 Juin 2011, 7p. , N° 11636
Diffusable
125904