Filters








10,723 Hits in 3.3 sec

Semantic-Based Explainable AI: Leveraging Semantic Scene Graphs and Pairwise Ranking to Explain Robot Failures [article]

Devleena Das, Sonia Chernova
2021 arXiv   pre-print
Our framework autonomously captures the semantic information in a scene to produce semantically descriptive explanations for everyday users.  ...  Existing natural language explanations hand-annotate contextual information from an environment to help everyday people understand robot failures.  ...  Within the robotics community, scene graphs have been utilized for scene analysis and goal-directed manipulation.  ... 
arXiv:2108.03554v1 fatcat:xv6a3mkenfe4jf35ph2fqht5by

Commonsense Scene Semantics for Cognitive Robotics: Towards Grounding Embodied Visuo-Locomotive Interactions

Jakob Suchan, Mehul Bhatt
2017 2017 IEEE International Conference on Computer Vision Workshops (ICCVW)  
We present a commonsense, qualitative model for the semantic grounding of embodied visuo-spatial and locomotive interactions.  ...  The key contribution is an integrative methodology combining low-level visual processing with high-level, human-centred representations of space and motion rooted in artificial intelligence.  ...  We also acknowledge the support of Omar Moussa, Thomas Hudkovic, and Vijayanta Jain in preparation of parts of the overall activity dataset.  ... 
doi:10.1109/iccvw.2017.93 dblp:conf/iccvw/SuchanB17 fatcat:y6hjq7mtjfgxvfg4bcuhzpb73y

Special Issue on Assistive Computer Vision and Robotics - ``Assistive Solutions for Mobility, Communication and HMI''

Giovanni Maria Farinella, Takeo Kanade, Marco Leo, Gerard G. Medioni, Mohan Trivedi
2016 Computer Vision and Image Understanding  
, feature extraction, tracking, 3D morphometric analysis.  ...  Assistive technologies provide a set of advanced tools that can improve the quality of life not only for impaired people, patients and elderly but also for healthy people struggling with everyday actions  ... 
doi:10.1016/j.cviu.2016.05.014 fatcat:ek3uupvcvvfqdh6u6chla56w3q

Commonsense Scene Semantics for Cognitive Robotics: Towards Grounding Embodied Visuo-Locomotive Interactions [article]

Jakob Suchan, Mehul Bhatt
2017 arXiv   pre-print
We present a commonsense, qualitative model for the semantic grounding of embodied visuo-spatial and locomotive interactions.  ...  The key contribution is an integrative methodology combining low-level visual processing with high-level, human-centred representations of space and motion rooted in artificial intelligence.  ...  We also acknowledge the support of Omar Moussa, Thomas Hudkovic, and Vijayanta Jain in preparation of parts of the overall activity dataset.  ... 
arXiv:1709.05293v1 fatcat:5ll7cn2s6bahpfcjjiuxs3hrfi

Empathy

Brian K. Mok, Stephen Yang, David Sirkin, Wendy Ju
2014 Proceedings of the 2014 ACM/IEEE international conference on Human-robot interaction - HRI '14  
The role of human-robot interaction is becoming more important as everyday robotic devices begin to permeate into our lives.  ...  In this study, we video-prototyped a user's interactions with a set of robotic drawers. The user and robot each displayed one of five emotional states -angry, happy, indifferent, sad, and timid.  ...  INTRODUCTION Autonomous robots have begun to permeate into various facets of our everyday lives.  ... 
doi:10.1145/2559636.2563720 dblp:conf/hri/MokYSJ14 fatcat:padmzyocsvcmnpi7awu6zfeuvu

Special issue on Assistive Computer Vision and Robotics - Part I

Giovanni Maria Farinella, Takeo Kanade, Marco Leo, Gerard G. Medioni, Mohan Trivedi
2016 Computer Vision and Image Understanding  
Wang et al. provides a method for the characterization of everyday activities from egocentric images.  ...  From the trajectory of the fingertip, the written character is localised and recognised simultaneously. The paper "Geodesic pixel neighborhoods for 2D and 3D scene understanding" by V.  ... 
doi:10.1016/j.cviu.2016.05.010 fatcat:tiiosvi5lbagnecmyekiz2p57m

RoboSherlock: Cognition-enabled Robot Perception for Everyday Manipulation Tasks [article]

Ferenc Bálint-Benczédi, Jan-Hendrik Worch and Daniel Nyga and Nico Blodow and Patrick Mania and Zoltán-Csaba Márton and Michael Beetz
2019 arXiv   pre-print
We present RoboSherlock, a knowledge-enabled cognitive perception systems for mobile robots performing human-scale everyday manipulation tasks.  ...  We demonstrate the potential of the proposed framework through feasibility studies of systems for real-world scene perception that have been built on top of the framework.  ...  Perception for Everyday Manipulation tasks Everyday robot manipulation tasks usually take a considerable amount of time to execute, are in some sense repetitive in their nature and require interaction  ... 
arXiv:1911.10079v1 fatcat:hnude4inmfcs5ncfwgjclkftam

Combining perception and knowledge processing for everyday manipulation

D Pangercic, M Tenorth, D Jain, M Beetz
2010 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems  
and scenes and to infer answers to complex queries that require the combination of perception and knowledge processing.  ...  Key features of K-COPMAN are that it can make a robot environment-aware and that it supports goal-directed as well as passive perceptual processing.  ...  INTRODUCTION Autonomous robots performing everyday manipulation tasks have to make many decisions that require the combination of perception and knowledge processing.  ... 
doi:10.1109/iros.2010.5651006 dblp:conf/iros/PangercicTJB10 fatcat:btzdhydhtfdlhmfmostcj5uq5i

Humanoid Cognitive Robots

Rüdiger Dillmann, Regine Becher, Peter Steinhaus
2005 Journal of the Robotics Society of Japan  
Acknowledgements The work of the  ...  It serves the robot to identify important objects in a static scene and to allow a closer analysis of the identified objects.  ...  , in particular a microphone array for a spatial analysis of the acoustic scene and a colour stereo camera system.  ... 
doi:10.7210/jrsj.23.517 fatcat:x4ft3by6tncm3oa5znqrsuuyau

The role of culture in comics of the quotidian

Frank Bramlett
2015 Journal of Graphic Novels and Comics  
The analysis points to the conclusion that the culture of the world inside comics must be accounted for in most any attempt to understand the quotidian in comics.  ...  This is also found in studies of literature, art and economics. The premise of the quotidian, however, must be examined through a lens of culture.  ...  Thanks to Julie Pelton for pointing me toward Swidler's work on culture. 1 appreciate the very helpful comments of Nina Mickwitz on notions of the everyday, though any errors remain mine.  ... 
doi:10.1080/21504857.2014.1002853 fatcat:otbvyxinkzca7hilb2mmfkoeje

TrimBot2020: an outdoor robot for automatic gardening [article]

Nicola Strisciuglio, Radim Tylecek, Michael Blaich, Nicolai Petkov, Peter Bieber, Jochen Hemming, Eldert van Henten, Torsten Sattler, Marc Pollefeys, Theo Gevers, Thomas Brox, Robert B. Fisher
2018 arXiv   pre-print
Robots are increasingly present in modern industry and also in everyday life.  ...  Autonomous lawn mowers are succesful market applications of gardening robotics.  ...  For instance, analysis of color images gives information about the type of of objects (e.g. bushes, roses, trees, hedges, etc.) present in the scene.  ... 
arXiv:1804.01792v2 fatcat:z444vmgoxzbebl4iawy6dop6m4

Eccentricity edge-graphs from HDR images for object recognition by humanoid robots

D. Gonzalez-Aguirre, T. Asfour, R. Dillmann
2010 2010 10th IEEE-RAS International Conference on Humanoid Robots  
Experimental evaluation with the humanoid robot ARMAR-III is presented.  ...  The approach acquires accurate high dynamic range images to properly capture complex heterogeneously lighted scenes.  ...  Avoiding the ubiquitous high-contrast image-content in everyday humanoid robot applications is not plausible.  ... 
doi:10.1109/ichr.2010.5686336 dblp:conf/humanoids/Gonzalez-AguirreAD10 fatcat:f6deefcnqzb3rmfbzefia3pmdq

Editorial: Computational Approaches for Human-Human and Human-Robot Social Interactions

Cigdem Beyan, Vittorio Murino, Gentiane Venture, Agnieszka Wykowska
2020 Frontiers in Robotics and AI  
Lammers et al. present a dataset of everyday actions expressing various emotions.  ...  Automatized detection and analysis of non-verbal social signals can be of particular relevance not only to human-human interaction (HHI) but also in human-robot interaction (HRI).  ... 
doi:10.3389/frobt.2020.00055 pmid:33501223 pmcid:PMC7805690 fatcat:ewd7twmq5zamzapnxazm5sfpci

Social behavior recognition using body posture and head pose for human-robot interaction

Andre Gaschler, Soren Jentzsch, Manuel Giuliani, Kerstin Huth, Jan de Ruiter, Alois Knoll
2012 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems  
Robots that interact with humans in everyday situations, need to be able to interpret the nonverbal social cues of their human interaction partners.  ...  With this model, the bartender robot of the project JAMES can recognize typical social behaviors of human customers.  ...  Fig. 5 shows two scenes with labeled and recognized states in comparison; one of a participant in a group, one of a single participant interacting with the robot.  ... 
doi:10.1109/iros.2012.6385460 dblp:conf/iros/GaschlerJGHRK12 fatcat:7pecsokjyne75am6atcd7vxooe

Cognitive Interpretation of Everyday Activities: Toward Perceptual Narrative Based Visuo-Spatial Scene Interpretation [article]

Mehul Bhatt, Jakob Suchan, Carl Schultz
2013 arXiv   pre-print
ACM Classification: I.2 Artificial Intelligence: I.2.0 General -- Cognitive Simulation, I.2.4 Knowledge Representation Formalisms and Methods, I.2.10 Vision and Scene Understanding: Architecture and control  ...  structures, Motion, Perceptual reasoning, Shape, Video analysis General keywords: cognitive systems; human-computer interaction; spatial cognition and computation; commonsense reasoning; spatial and temporal  ...  ., logistical processes, activities of everyday living) of the environment being modelled.  ... 
arXiv:1306.5308v1 fatcat:jxqphtmqrjaz3i77dvgeiklwoq
« Previous Showing results 1 — 15 out of 10,723 results