2,852 Hits in 5.3 sec

Exploiting Deep Semantics and Compositionality of Natural Language for Human-Robot-Interaction [article]

Manfred Eppe, Sean Trott, Jerome Feldman
2016 arXiv   pre-print
We implement our NLU framework as a ROS package and present proof-of-concept scenarios with different robots, as well as a survey on the state of the art.  ...  Using ECG, robots are able to solve fine-grained reference resolution problems and other issues related to deep semantics and compositionality of natural language.  ...  These capture modalities, spatial relations, temporal expressions, actions, etc.  ... 
arXiv:1604.06721v1 fatcat:n6zfaafncrb35dhrx4vgpei7qa

Integration of Action and Language Knowledge: A Roadmap for Developmental Robotics

Angelo Cangelosi, Giorgio Metta, Gerhard Sagerer, Stefano Nolfi, Chrystopher Nehaniv, Kerstin Fischer, Jun Tani, Tony Belpaeme, Giulio Sandini, Francesco Nori, Luciano Fadiga, Britta Wrede (+5 others)
2010 IEEE Transactions on Autonomous Mental Development  
These milestones provide a possible set of cognitive robotics goals and test-scenarios, thus acting as a research roadmap for future work on cognitive developmental robotics.  ...  This position paper proposes that the study of embodied cognitive agents, such as humanoid robots, can advance our understanding of the cognitive development of complex sensorimotor, linguistic and social  ...  In particular, we wish to thank the following people for comments and contributions to some of the sections in the paper: Davide Marocco, Francesco Nori, Vadim Tikhanoff, Alessandra Sciutti, Arjan Gijsberts  ... 
doi:10.1109/tamd.2010.2053034 fatcat:bqi276njyvcw5dkrd2bqv6hlwe

Anchoring by Imitation Learning in Conceptual Spaces [chapter]

Antonio Chella, Haris Dindo, Ignazio Infantino
2005 Lecture Notes in Computer Science  
, and in a topdown approach, in order to anchor the symbolical representations to the perceptual activities of the robotic system.  ...  In order to have a robotic system able to effectively learn by imitation, and not merely reproduce the movements of a human teacher, the system should have the capabilities of deeply understanding the  ...  Acknowledgments This research is partially supported by MIUR (Italian Ministry of Education, University and Research) under project RoboCare ("A Multi-Agent System with Intelligent Fixed and Mobile Robotic  ... 
doi:10.1007/11558590_50 fatcat:ezlmujyd75edpbtel5aqnuwulm

Towards an Indexical Model of Situated Language Comprehension for Cognitive Agents in Physical Worlds [article]

Shiwali Mohan, Aaron Mininger, John Laird
2016 arXiv   pre-print
of beliefs, knowledge, and experience external to the linguistic system.  ...  The model is being used to support linguistic interactions in Rosie, an agent implemented in Soar that learns from instruction.  ...  The authors thank Edwin Olson and the APRIL lab at the University of Michigan, Ann Arbor, for the design and implementation of the robot including its perception and actuation algorithms.  ... 
arXiv:1604.02509v1 fatcat:5njqud7p2rhmvmjbpyfhzzcahq

Grounded Situation Models for Robots: Where words and percepts meet

Nikolaos Mavridis, Deb Roy
2006 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems  
The robot updates beliefs (held in the GSM) about its physical environment, the human user, and itself, based on a mixture of linguistic, visual and proprioceptive evidence.  ...  It is impossible to directly apply these approaches in any principled way to endow robots with linguistic skills since the underlying theories of semantics in symbol-based NLP provide no appropriate "hooks  ...  Layer 3 (L3) maintains discrete, categorical encodings of properties, suited for interfaces with natural language. Consider the scenario of asking the robot where an object is.  ... 
doi:10.1109/iros.2006.282258 dblp:conf/iros/MavridisR06a fatcat:b2bctlxjjvg7vd62daryduxg5a

Grounding Dynamic Spatial Relations for Embodied (Robot) Interaction [chapter]

Michael Spranger, Jakob Suchan, Mehul Bhatt, Manfred Eppe
2014 Lecture Notes in Computer Science  
This paper presents a computational model of the processing of dynamic spatial relations occurring in an embodied robotic interaction setup.  ...  A complete system is introduced that allows autonomous robots to produce and interpret dynamic spatial phrases (in English) given an environment of moving objects.  ...  Static spatial relations are interesting but they only cover a particular subdomain of spatial relations namely relations that do not encode temporal qualities.  ... 
doi:10.1007/978-3-319-13560-1_83 fatcat:dbvnifa2fnhxfcmzgv2leoxzwu

Grounding Dynamic Spatial Relations for Embodied (Robot) Interaction [article]

Michael Spranger and Jakob Suchan and Mehul Bhatt and Manfred Eppe
2016 arXiv   pre-print
This paper presents a computational model of the processing of dynamic spatial relations occurring in an embodied robotic interaction setup.  ...  A complete system is introduced that allows autonomous robots to produce and interpret dynamic spatial phrases (in English) given an environment of moving objects.  ...  Static spatial relations are interesting but they only cover a particular subdomain of spatial relations namely relations that do not encode temporal qualities.  ... 
arXiv:1607.07565v1 fatcat:jkx4xmxv5jcphlewdovo3ul2sq

Belief modelling for situation awareness in human-robot interaction

Pierre Lison, Carsten Ehrler, Geert-Jan M. Kruijff
2010 19th International Symposium in Robot and Human Interactive Communication  
To interact naturally with humans, robots need to be aware of their own surroundings. This awareness is usually encoded in some implicit or explicit representation of the situated context.  ...  In this paper, we present a new framework for constructing rich belief models of the robot's environment.  ...  The probability of these correlations are encoded in a Markov Logic Network.  ... 
doi:10.1109/roman.2010.5598723 dblp:conf/ro-man/LisonEK10 fatcat:ou7d6kp4svgwjpawpn7ls3ruwu

Learning to Use Narrative Function Words for the Organization and Communication of Experience

Gregoire Pointeau, Solène Mirliaz, Anne-Laure Mealier, Peter Ford Dominey
2021 Frontiers in Psychology  
Narrative sentences describe events, and they also define temporal and causal relations between events.  ...  narrative practice in human-robot interaction.  ...  ACKNOWLEDGMENTS We thank Théophile Peyraud for help in collecting data on use of narrative function words.  ... 
doi:10.3389/fpsyg.2021.591703 pmid:33762991 pmcid:PMC7982915 fatcat:v7l2tdpqqfc6bhvkyxsgikcnbi

Memory and mental time travel in humans and social robots

Tony J. Prescott, Daniel Camilleri, Uriel Martinez-Hernandez, Andreas Damianou, Neil D. Lawrence
2019 Philosophical Transactions of the Royal Society of London. Biological Sciences  
the deployment of this system for human-robot interaction.  ...  Using computational models, embedded in humanoid robots, we are seeking to test the sufficiency of this theoretical account and to evaluate the usefulness of brain-inspired memory systems for social robots  ...  at the University of Sheffield who have helped us to develop memory systems for the iCub, particularly Luke Boorman, Harry Jackson and Matthew Evans.  ... 
doi:10.1098/rstb.2018.0025 pmid:30852998 pmcid:PMC6452248 fatcat:oxnpgecavfbupnn4f5tjyou2g4

Multimodal Semantic Simulations of Linguistically Underspecified Motion Events [article]

Nikhil Krishnaswamy, James Pustejovsky
2016 arXiv   pre-print
In this paper, we describe a system for generating three-dimensional visual simulations of natural language motion expressions.  ...  This paper outlines technical considerations and discusses implementing the aforementioned semantic models into such a system.  ...  Given any object pair, the system can pinpoint the set of RCC relations applying to them in the current state.  ... 
arXiv:1610.00602v1 fatcat:vyjavjwe6rd4zlw3qbjxpl75k4

Linking language with embodied and teleological representations of action for humanoid cognition

2010 Frontiers in Neurorobotics  
We developed a perceptual system that extracts patterns of spatio-temporal visual properties in order to encode actions in terms of these patterns.  ...  cognItIve system ArchItecture We developed a cognitive system architecture to respond to the requirements implied in Section "Experimental Scenarios," guided by knowledge of the cognitive linguistic mechanism  ...  Conflict of Interest Statement: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest  ... 
doi:10.3389/fnbot.2010.00008 pmid:20577629 pmcid:PMC2889716 fatcat:ztiqxbd4wve65cyjaojdfl3iqm

Temporal-Logic-Based Reactive Mission and Motion Planning

H. Kress-Gazit, G.E. Fainekos, G.J. Pappas
2009 IEEE Transactions on robotics  
As one robot is part of the environment of another robot, our sensor-based framework very naturally captures multirobot specifications in a decentralized manner.  ...  The desired task specifications, which are expressed in a fragment of linear temporal logic (LTL), can capture complex robot behaviors such as search and rescue, coverage, and collision avoidance.  ...  In the hybrid systems community, several researchers have explored the use of temporal and modal logic for the design of controllers.  ... 
doi:10.1109/tro.2009.2030225 fatcat:a44ttvnj5fci3dx66hyb4nqpqy

Episodes, events, and models

Sangeet S. Khemlani, Anthony M. Harrison, J. Gregory Trafton
2015 Frontiers in Human Neuroscience  
The theory is the first unified computational account of event segmentation and temporal inference.  ...  We describe a computational implementation of the theory, as well as a robotic extension of the theory that demonstrates the processes of online event segmentation and event model construction.  ...  By age 3, children understand the temporal order of actions and their relations to one another in a sequence of conceptually related events (Nelson and Gruendel, 1986) .  ... 
doi:10.3389/fnhum.2015.00590 pmid:26578934 pmcid:PMC4621428 fatcat:tce2h7ha4nd75aflq3thbotaly

Grounding action words in the sensorimotor interaction with the world: experiments with a simulated iCub humanoid robot

Davide Marocco
2010 Frontiers in Neurorobotics  
The control system of the robot is an artificial neural network trained to manipulate an object through a Back-Propagation-Through-Time algorithm.  ...  This paper presents a cognitive robotics model for the study of the embodied representation of action words.  ...  point of view (see also Tikhanoff et al., 2008) .  ... 
doi:10.3389/fnbot.2010.00007 pmid:20725503 pmcid:PMC2901088 fatcat:5xutivxaozdofo5ssbxykwqtdq
« Previous Showing results 1 — 15 out of 2,852 results