Filters








52,205 Hits in 8.3 sec

Category-Association Based Similarity Matching for Novel Object Pick-and-Place Task [article]

Hao Chen, Takuya Kiyokawa, Weiwei Wan, Kensuke Harada
2022 arXiv   pre-print
To break through this drawback of learning-based approaches, we introduce a new perspective of similarity matching between novel objects and a known database based on category-association to achieve pick-and-place  ...  Robotic pick-and-place has been researched for a long time to cope with uncertainty of novel objects and changeable environments.  ...  Yoshiaki Ando and Dr. Floris Erich of AIST for helping creation of the database with a 3D shape measurement system of AIST.  ... 
arXiv:2201.08177v1 fatcat:a2rnq5zhgfcubbbxeyfky6tuea

Late talkers show no shape bias in a novel name extension task

Susan S. Jones
2003 Developmental Science  
The implications of the results both for the role of attentional biases in object name learning and for the etiology of some late talking are discussed.  ...  Twelve 2-to 3year-old 'late talkers' -children whose total vocabularies rank below the 30th percentile for their age -were compared with age-matched children with larger vocabularies in a novel object  ...  There were two test trials for each novel object category. One of the test objects on each trial was a Similar object. The other two objects were highly Dissimilar objects.  ... 
doi:10.1111/1467-7687.00304 fatcat:3eznwpw3nfektg4zwzlqqzzvli

Robotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matching [article]

Andy Zeng, Shuran Song, Kuan-Ting Yu, Elliott Donlon, Francois R. Hogan, Maria Bauza, Daolin Ma, Orion Taylor, Melody Liu, Eudald Romo, Nima Fazeli, Ferran Alet (+9 others)
2020 arXiv   pre-print
This paper presents a robotic pick-and-place system that is capable of grasping and recognizing both known and novel objects in cluttered environments.  ...  The key new feature of the system is that it handles a wide range of object categories without needing any task-specific training data for novel objects.  ...  /1539099), NVIDIA, and Facebook for hardware, technical, and financial support.  ... 
arXiv:1710.01330v5 fatcat:yyytldcvnfbvnailib366awsg4

Robotic pick-and-place of novel objects in clutter with multi-affordance grasping and cross-domain image matching

Andy Zeng, Shuran Song, Kuan-Ting Yu, Elliott Donlon, Francois R. Hogan, Maria Bauza, Daolin Ma, Orion Taylor, Melody Liu, Eudald Romo, Nima Fazeli, Ferran Alet (+9 others)
2019 The international journal of robotics research  
This article presents a robotic pick-and-place system that is capable of grasping and recognizing both known and novel objects in cluttered environments.  ...  The key new feature of the system is that it handles a wide range of object categories without needing any task-specific training data for novel objects.  ...  Acknowledgements The authors would like to thank the MIT-Princeton ARC team members for their contributions to this project and ABB Robotics, Mathworks, Intel, Google, NVIDIA, and Facebook for hardware  ... 
doi:10.1177/0278364919868017 fatcat:tjzvct4y7rfnfiqk5bhlegpiwi

Are preschoolers' renamings intentional category violations?

Eve Mendelsohn, Susan Robinson, Howard Gardner, Ellen Winner
1984 Developmental Psychology  
There are two ways in which objects are conventionally grouped-by taxonomic category and by association.  ...  For each item, three visual matches were constructed, one based on color, a second based on shape, and a third based on color and shape combined.  ... 
doi:10.1037/0012-1649.20.2.187 fatcat:am7lqlzjcze3zikef7m5g4v36y

They call it like they see it: spontaneous naming and attention to shape

Larissa K. Samuelson, Linda B. Smith
2005 Developmental Science  
Results indicate that object shape plays an important role in both spontaneous productions and novel noun generalization, but contrary to current hypotheses, children may name objects by shape from the  ...  Experiment 2 examines the relation between spontaneous productions, name generalizations in a structured task, and vocabulary development in a group of children between 17 and 24 months of age (mean 21  ...  The authors wish to thank Amber Cox, Char Wozniak and Jessica Horst for their help with data collection and coding.  ... 
doi:10.1111/j.1467-7687.2005.00405.x pmid:15720376 fatcat:offmkmbp2rdkxftaexo3boo4li

The role of inhibition in moving beyond perceptually focused noun extensions

Simon Snape, Andrea Krott
2017 First language  
Another object was from the same category as the standard (= taxonomic match) but differed from it in terms of shape, and the third object was from a different category, but was similar in shape to the  ...  She asked 3-to 5-year-olds to categorise objects first by perceptual similarity and then by taxonomic category membership, or vice versa.  ... 
doi:10.1177/0142723717737195 fatcat:jl6ih7wwdjhvrbuzmin4f4jp4m

Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation [article]

Anthony Simeonov, Yilun Du, Andrea Tagliasacchi, Joshua B. Tenenbaum, Alberto Rodriguez, Pulkit Agrawal, Vincent Sitzmann
2021 arXiv   pre-print
We employ this representation for object manipulation, where given a task demonstration, we want to repeat the same task on a new object instance from the same category.  ...  We propose to achieve this objective by searching (via optimization) for the pose whose descriptor matches that observed in the demonstration.  ...  Using this novel formulation, we propose a system that can imitate pick-and-place tasks for a category of objects from only a small handful of demonstrations.  ... 
arXiv:2112.05124v1 fatcat:p5jxy4iipva5djuxgrhpxwmo7e

Get Your Facts Right: Preschoolers Systematically Extend Both Object Names and Category-Relevant Facts

Amanda K. Holland, Emily Mather, Andrew Simpson, Kevin J. Riggs
2016 Frontiers in Psychology  
We explicitly contrast facts varying in category relevance, and test for extension using two different tasks.  ...  Three-to four-year-olds (N = 61) were provided with one of three types of information about a single novel object: a category-relevant fact ('it's from a place called Modi'), a category-irrelevant fact  ...  ACKNOWLEDGMENTS We would like to thank the children, parents and staff at St Margaret's Nursery School in North London for all their help in collecting the data for this study.  ... 
doi:10.3389/fpsyg.2016.01064 pmid:27486414 pmcid:PMC4949258 fatcat:5calfo2dujc3pac7xj5kdgc3pq

Statistical regularities in vocabulary guide language acquisition in connectionist models and 15-20-month-olds

Larissa K. Samuelson
2002 Developmental Psychology  
A second simulation suggested this overgeneralization is due to the dominance of names for shape-based categories in the early noun vocabulary.  ...  This research tested the hypothesis that young children's bias to generalize names for solid objects by shape is the product of statistical regularities among nouns in the early productive vocabulary.  ...  Thanks go to Rich Shiffrin, Susan Jones and Mike Gasser for their thoughtful discussions of the experiments and simulations and for their encouragement of the research.  ... 
doi:10.1037//0012-1649.38.6.1016 pmid:12428712 fatcat:fzk7wiysbrcm3p5aeblfgh7kvy

Statistical regularities in vocabulary guide language acquisition in connectionist models and 15-20-month-olds

Larissa K. Samuelson
2002 Developmental Psychology  
A second simulation suggested this overgeneralization is due to the dominance of names for shape-based categories in the early noun vocabulary.  ...  This research tested the hypothesis that young children's bias to generalize names for solid objects by shape is the product of statistical regularities among nouns in the early productive vocabulary.  ...  Thanks go to Rich Shiffrin, Susan Jones and Mike Gasser for their thoughtful discussions of the experiments and simulations and for their encouragement of the research.  ... 
doi:10.1037/0012-1649.38.6.1016 fatcat:46mz5u7nkfakpm2rrimxir72k4

kPAM: KeyPoint Affordances for Category-Level Robotic Manipulation [article]

Lucas Manuelli, Wei Gao, Peter Florence, Russ Tedrake
2019 arXiv   pre-print
Extensive hardware experiments demonstrate our method can reliably accomplish tasks with never-before seen objects in a category, such as placing shoes and mugs with significant shape variation into category  ...  Hence we propose a novel formulation of category-level manipulation that uses semantic 3D keypoints as the object representation.  ...  Robotic pick-and-place of novel objects in clutter with multi-affordance grasping and cross-domain image matching.  ... 
arXiv:1903.06684v2 fatcat:gaghpp3ukjg7xad3u35yplur24

The Effect of Learned Perceptual Associations on Visuomotor Programming Varies with Kinematic Demands

Angela M. Haffenden, Melvyn A. Goodale
2000 Journal of Cognitive Neuroscience  
greater in form-matching tasks than in color-matching tasks, indicating a greater role for semantic associations with form than with color.  ...  Of course, we could equally well pick up these two objects for other reasons: to put the glass in the dish rack, for example, our fingers would no longer have to be placed around the sides of the cup in  ... 
doi:10.1162/08989290051137495 pmid:11177416 fatcat:ctqxrk7n2fhojmjfupx7qvtwty

Coordination of Caregiver Naming and Children's Exploration of Solid Objects and Nonsolid Substances

Lynn K. Perry, Stephanie A. Custode, Regina M. Fasano, Brittney M. Gonzalez, Adriana M. Valtierra
2022 Frontiers in Psychology  
Together these findings, though exploratory, suggest the coordination of caregiver-child play can shape what children remember about novel word-object associations for solid objects, but not nonsolid substances  ...  When a caregiver names objects dominating a child's view, the association between object and name is unambiguous and children are more likely to learn the object's name.  ...  ACKNOWLEDGMENTS We thank families for their participation and the members of the Object and Word Learning Lab for their help with data collection and coding.  ... 
doi:10.3389/fpsyg.2022.945664 pmid:35865677 pmcid:PMC9294728 fatcat:yjbz2j7trzfvdbiquwarvlhhfq

Tracking Multiple Statistics: Simultaneous Learning of Object Names and Categories in English and Mandarin Speakers

Chi-hsin Chen, Lisa Gershkoff-Stowe, Chih-Yi Wu, Hintat Cheung, Chen Yu
2016 Cognitive Science  
Experiment 1 used a cross-situational learning paradigm to test whether English speakers were able to use co-occurrences to learn word-toobject mappings and concurrently form object categories based on  ...  , were able to learn words and form object categories when trained with the same type of structures.  ...  Acknowledgments This research was supported by National Institute of Health Grant (R01HD056029) and National Science Foundation Grant (BCS 0544995) to Chen Yu, and National Science Council Grant (NSC96  ... 
doi:10.1111/cogs.12417 pmid:27671780 pmcid:PMC5366274 fatcat:llw7nfmnzvewjlfnrntoncgoxy
« Previous Showing results 1 — 15 out of 52,205 results