13,243 Hits in 5.3 sec

CAGE: Context-Aware Grasping Engine [article]

Weiyu Liu, Angel Daruna, Sonia Chernova
2020 arXiv   pre-print
reasoning patterns.  ...  Semantic grasping is the problem of selecting stable grasps that are functionally suitable for specific object manipulation tasks.  ...  RELATED WORK Below we discuss previous approaches to semantic grasping along with related works in affordance and material detection. A.  ... 
arXiv:1909.11142v3 fatcat:7rzvegkvqjha5pht5usvmqerri

Identifying relevant feature-action associations for grasping unmodelled objects

Mikkel Tang Thomsen, Dirk Kraft, Norbert Krüger
2015 Paladyn: Journal of Behavioral Robotics  
We apply our method in a simulated environment on three different object sets for the case of grasp affordance learning.  ...  In this paper, we present a method for learning action affordances based on basic visual features, which can vary in their granularity, order of combination and semantic content.  ...  A third reason for addressing grasping is that there exists already relevant related prior work: In [4] (see Fig. 2 ), grasp affordances have been manually designed as first and second order relations  ... 
doi:10.1515/pjbr-2015-0006 fatcat:ey4r4nq3rrelvgytzxiairtj7u

Visual Affordance and Function Understanding: A Survey [article]

Mohammed Hassanin, Salman Khan, Murat Tahtali
2018 arXiv   pre-print
Specifically, we discuss sub-problems such as affordance detection, categorization, segmentation and high-level reasoning.  ...  The survey also provides necessary background to the problem, sheds light on its significance and highlights the existing challenges for affordance and functionality learning.  ...  Then the robot learned the model of grasping and used affordances through imitation and self observation.  ... 
arXiv:1807.06775v1 fatcat:kl7miygnizdinpovqnzfdhwokq

Affordance-Aware Handovers with Human Arm Mobility Constraints [article]

Paola Ardón, Maria E. Cabrera, Èric Pairet, Ronald P. A. Petrick, Subramanian Ramamoorthy, Katrin S. Lohan, Maya Cakmak
2021 arXiv   pre-print
We encapsulate these preferences in a statistical relational model (SRL) that is able to reason about the most suitable handover configuration given a receiver's arm mobility and upcoming task.  ...  This also ensures that the robot grasps consider the context of the user's upcoming task, i.e., the usage of the object.  ...  To assess the learned model, we start by analysing the differences in robot grasps resulting from reasoning about grasp affordances with [21] versus our proposal in Section III for handover.  ... 
arXiv:2010.15436v2 fatcat:6fqr6eaubneptetfmeqlgx22cu

Same Object, Different Grasps: Data and Semantic Knowledge for Task-Oriented Grasping [article]

Adithyavairavan Murali, Weiyu Liu, Kenneth Marino, Sonia Chernova, Abhinav Gupta
2020 arXiv   pre-print
Despite the enormous progress and generalization in robotic grasping in recent years, existing methods have yet to scale and generalize task-oriented grasping to the same extent.  ...  Our framework shows a significant improvement of around 12% on held-out settings compared to baseline methods which do not use semantics.  ...  [20] leveraged probabilistic logic languages to reason about grasp regions affording different tasks through semantic relations.  ... 
arXiv:2011.06431v2 fatcat:52zg6zdzxrapjbxod5j6tlfkbm

Intention-Related Natural Language Grounding via Object Affordance Detection and Intention Semantic Extraction

Jinpeng Mi, Hongzhuo Liang, Nikolaos Katsakis, Song Tang, Qingdu Li, Changshui Zhang, Jianwei Zhang
2020 Frontiers in Neurorobotics  
Finally, we ground intention-related natural language queries by integrating the detected object affordances with the extracted intention semantics.  ...  Moreover, we introduce an intention semantic extraction module to extract intention semantics from intention-related natural language queries.  ...  AUTHOR CONTRIBUTIONS JM designed the study, wrote the initial draft of the manuscript, trained the object affordance detection network, completed the intention-related natural language grounding architecture  ... 
doi:10.3389/fnbot.2020.00026 pmid:32477091 pmcid:PMC7238763 fatcat:gjdtium6vzapnov7c7cn5x4gae

High-level Reasoning and Low-level Learning for Grasping: A Probabilistic Logic Pipeline [article]

Laura Antanas, Plinio Moreno, Marion Neumann, Rui Pimentel de Figueiredo, Kristian Kersting, José Santos-Victor, Luc De Raedt
2014 arXiv   pre-print
Further, a mapping is learned from part-related visual features to good grasping points.  ...  Specifically, we introduce a new probabilistic logic module to first semantically reason about pre-grasp configurations with respect to the intended tasks.  ...  All of these approaches successfully intertwine relational reasoning and learning in robotics.  ... 
arXiv:1411.1108v1 fatcat:kyvnzpttj5gxbfg3n4qmuwouxe

A survey of knowledge representation in service robotics

David Paulius, Yu Sun
2019 Robotics and Autonomous Systems  
in recent years, such as machine learning, deep learning, probabilistic modelling, and semantic graphical structures.  ...  and retrieval, and the intertwining of perception/vision and machine learning techniques.  ...  relations (i.e. where the object's affordance depends on the sub-activity it is involved in), 2) affordance-affordance relation (i.e. where one can infer the affordance(s) of a single object based on  ... 
doi:10.1016/j.robot.2019.03.005 fatcat:yc6zheqqdvfixdvcr7elyvlkgq

Recognizing Object Affordances to Support Scene Reasoning for Manipulation Tasks [article]

Fu-Jen Chu, Ruinian Xu, Chao Tang, Patricio A. Vela
2020 arXiv   pre-print
Secondly, a self-attention mechanism trained to interpret each proposal learns to capture rich contextual dependencies through the region.  ...  Thus, integrating affordance-based reasoning into symbolic action plannning pipelines would enhance the flexibility of robot manipulation.  ...  Affordances should also serve as shareable features with semantic meaning whose use could benefit feature learning for object instances.  ... 
arXiv:1909.05770v2 fatcat:qzinrh63srg2pdhfuu42liiqlm

Affordances in Psychology, Neuroscience, and Robotics: A Survey

Lorenzo Jamone, Emre Ugur, Angelo Cangelosi, Luciano Fadiga, Alexandre Bernardino, Justus Piater, Jose Santos-Victor
2018 IEEE Transactions on Cognitive and Developmental Systems  
Index Terms-Affordances, ecological perception, cognitive system and development, embodied cognition, robots with development and learning skills.  ...  In this paper we offer a multidisciplinary perspective on the notion of affordances: we first discuss the main definitions and formalizations of the affordance theory, then we report the most significant  ...  to construct a detailed model of the world or to perform semantic reasoning.  ... 
doi:10.1109/tcds.2016.2594134 fatcat:hnjyazd4urc3thfnhsyvmwlnsu

Learning to Act Properly: Predicting and Explaining Affordances from Images [article]

Ching-Yao Chuang, Jiaman Li, Antonio Torralba, Sanja Fidler
2018 arXiv   pre-print
We address the problem of affordance reasoning in diverse scenes that appear in the real world. Affordances relate the agent's actions to their effects when taken on the surrounding objects.  ...  We collect a new dataset that builds upon ADE20k, referred to as ADE-Affordance, which contains annotations enabling such rich visual reasoning.  ...  Related Work We review works most related to ours, focusing on affordances, visual reasoning, and captioning. Affordance Reasoning.  ... 
arXiv:1712.07576v2 fatcat:tfmifkjzlndnjnobskksacjy5u

Learning to Act Properly: Predicting and Explaining Affordances from Images

Ching-Yao Chuang, Jiaman Li, Antonio Torralba, Sanja Fidler
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
Related Work We review works most related to ours, focusing on affordances, visual reasoning, and captioning. Affordance Reasoning.  ...  Reasoning about the affordances thus requires both, understanding the semantic classes of all objects in the scene, as well as their spatial relations.  ... 
doi:10.1109/cvpr.2018.00108 dblp:conf/cvpr/ChuangL0F18 fatcat:zjzjedxb2vgzvpxnqpned4eteq


2009 International Journal of Humanoid Robotics  
This vision system is firstly targeted at the interaction with the world through recognition and grasping of objects and secondly at being an interface for the reasoning and planning module to the real  ...  The perception-action cycle is connected to the reasoning system based on the idea of affordances.  ...  Acknowledgments This work was supported by EU through the projects PACO-PLUS, IST-FP6-IP-027657 and GRASP, IST-FP7-IP-215821.  ... 
doi:10.1142/s0219843609001796 fatcat:ns4e6dn7i5fp3pzhozutfxccsy

Semantic grasping: planning task-specific stable robotic grasps

Hao Dang, Peter K. Allen
2014 Autonomous Robots  
We introduce a semantic affordance map, which relates local geometry to a set of predefined semantic grasps that are appropriate to different tasks.  ...  We show experiments planning semantic grasps on everyday objects and applying these grasps with a physical robot.  ...  To this end, we introduce a semantic affordance map which relates partial geometry features to semantic grasps and records grasp related information.  ... 
doi:10.1007/s10514-014-9391-2 fatcat:bdazzjdkdrd2flle33ckr6stpm

Action semantics: A unifying conceptual framework for the selective use of multimodal and modality-specific object knowledge

Michiel van Elk, Hein van Schie, Harold Bekkering
2014 Physics of Life Reviews  
We show that research in each of these domains is characterized by similar discussions regarding (1) the role of object affordances, (2) the relation between goals and means in object use and (3) the functional  ...  and neural organization of action semantics.  ...  Means-end reasoning In addition to being able to grasp an object correctly, infants have to learn about the functional use of objects as well (e.g. knowing that a key is used to open a door).  ... 
doi:10.1016/j.plrev.2013.11.005 pmid:24461373 fatcat:5cjhg6hy3nff5auhic4fnw27uq
« Previous Showing results 1 — 15 out of 13,243 results