Filters








283 Hits in 8.1 sec

Grasp affordances from multi-fingered tactile exploration using dynamic potential fields

Alexander Bierbaum, Matthias Rambow, Tamim Asfour, Rudiger Dillmann
2009 2009 9th IEEE-RAS International Conference on Humanoid Robots  
In this paper, we address the problem of tactile exploration and subsequent extraction of grasp hypotheses for unknown objects with a multi-fingered anthropomorphic robot hand.  ...  In the subsequent feature extraction, faces found in the object model are considered to generate grasp affordances.  ...  ACKNOWLEDGEMENT The work described in this paper was conducted within the EU Cognitive Systems projects PACO-PLUS (FP6-027657) and GRASP (FP7-215821) funded by the European Commission.  ... 
doi:10.1109/ichr.2009.5379581 dblp:conf/humanoids/BierbaumR09 fatcat:632u37uy2bdtnjatp7pt5oyzb4

Developing haptic and visual perceptual categories for reaching and grasping with a humanoid robot

Jefferson Coelho, Justus Piater, Roderic Grupen
2001 Robotics and Autonomous Systems  
We are studying humanoid robots in order to apply insight derived from neuroscience, neurology, and developmental psychology to the design of advanced robot architectures.  ...  Our example shows how exploratory grasping behavior using a dextrous robot hand can lead to candidate grasps of varying quality and illustrates a learning mechanism that reliably selects high quality grasps  ...  The von Mises distribution can be regarded as a circular equivalent of the linear Gaussian distribution, and has the probability density function [22] Acknowledgments This work was supported in part  ... 
doi:10.1016/s0921-8890(01)00158-0 fatcat:kmzbwt544rdkbiwfq45kqsadji

Object Detection Recognition and Robot Grasping Based on Machine Learning: A Survey

Qiang Bai, Shaobo Li, Jing Yang, Qisong Song, Zhiang Li, Xingxing Zhang
2020 IEEE Access  
A reasonable grasping strategy and grasping points are the basic requirements for the robot to grasp the target based on vision, and they correspond to the nondeformable object and the deformable object  ...  [63] presented a real-time method for visual categorization to achieve robot grasping.  ... 
doi:10.1109/access.2020.3028740 fatcat:de4euqnb4ngsbclfob5izyeaxa

Sensors for Robotic Hands: A Survey of State of the Art

Artur Saudabayev, Huseyin Atakan Varol
2015 IEEE Access  
In this paper, our goal is to provide a comprehensive survey of the sensors for artificial hands.  ...  We also cover the sensors developed for robot hand usage in each era.  ...  A lot of effort was focused on operation in uncertain conditions. In [118] , researchers developed a grasping strategy for unknown objects based on human grasping reflex.  ... 
doi:10.1109/access.2015.2482543 fatcat:nuogqh23mzecfmr7llvb4o4me4

Predictive Control-Based Completeness Analysis and Global Calibration of Robot Vision Features

Jingjing Lou, Akshi Kumar
2021 Computational Intelligence and Neuroscience  
This paper provides an in-depth study and analysis of robot vision features for predictive control and a global calibration of their feature completeness.  ...  To address the problems of singular values, local minima, and insufficient robustness in the traditional scale-free vision servo algorithm, a new scale-free vision servo method is proposed to construct  ...  FG2020196 and FG2020197), the second batch of teaching reform research projects in the 13th Five-Year Plan of Zhejiang Higher Education, China (Grant no. jg20190878), and the Public Welfare Science and  ... 
doi:10.1155/2021/7241659 pmid:34925495 pmcid:PMC8677366 fatcat:ripbxkqbq5ehbpsddeup6koiwm

Towards intelligent social robots: Current advances in cognitive robotics

Amir Aly, Sascha Griffiths, Francesca Stramandinoli
2017 Cognitive Systems Research  
The integration of multisensory information plays a crucial role in autonomous robotics.  ...  Experiments on a dataset of 10 full-body actions show that our architecture is able to learn action-word mappings without the need of segmenting training samples for ground-truth labelling.  ...  Willow Garage created this database to provide, for each 3D surface 3 model of the objects in the database, a large number of grasp points that are specific to a PR2 robot and its gripper.  ... 
doi:10.1016/j.cogsys.2016.11.005 fatcat:ptmokg2tbrdblgwhnkbclxecri

Synthesizing Diverse and Physically Stable Grasps with Arbitrary Hand Structures using Differentiable Force Closure Estimator [article]

Tengyu Liu, Zeyu Liu, Ziyuan Jiao, Yixin Zhu, Song-Chun Zhu
2021 arXiv   pre-print
Although force closure has commonly served as a measure of grasp quality, it has not been widely adopted as an optimization objective for grasp synthesis primarily due to its high computational complexity  ...  Existing grasp synthesis methods are either analytical or data-driven. The former one is oftentimes limited to specific application scope.  ...  When the vertices are sparse, or the object has a pointy part, it is possible for the object to penetrate the hand without being detected.  ... 
arXiv:2104.09194v3 fatcat:ygpfwosnj5bqvm7xw7lj7s6g64

Conceptual Preview of the AI and Image Analytics Methodologies in Robotics

Sathyanarayanan P.S.V
2020 International Journal of Engineering Research and Advanced Technology  
When AI is to be utilized for the machine-human level interactions, the user recognition and the intended interaction becomes a mandatorily important task which needs more attention towards the image analytics  ...  Majorly, the image processing operations taking up the facial/emotion recognition is discussed in a brief preview in this paper with reference to the utilized methodologies.  ...  They prove grasping specific points on an object across potentially deformed object setups, and showing how to transfer specific grasps through entities in a class utilizing class particular descriptors  ... 
doi:10.31695/ijerat.2020.3610 fatcat:4fkxybzbtne7tiyzxfsma6qzam

Review of Deep Reinforcement Learning-based Object Grasping: Techniques, Open Challenges and Recommendations

Marwan Qaid Mohammed, Kwek Lee Chung, Chua Shing Chyi
2020 IEEE Access  
Object grasping requires detection systems, methods and tools to facilitate efficient and fast agent training.  ...  This review refers to all relevant articles on deep reinforcement learning-based object manipulation and solutions. The object grasping issue is a major manipulation challenge.  ...  In [102] , a method based on partial point cloud observations was implemented to plan 6-DoF grasps for the target object in a cluttered environment.  ... 
doi:10.1109/access.2020.3027923 fatcat:44xyylmy7fhirjept76wm6uaeq

Multi-Fingered Robotic Grasping: A Primer [article]

Stefano Carpin, Shuo Liu, Joe Falco, Karl Van Wyk
2016 arXiv   pre-print
Next, we present an overview of various grasp planning algorithms with the objective of illustrating different approaches to solve this problem. Finally, we discuss grasp performance benchmarking.  ...  This technical report presents an introduction to different aspects of multi-fingered robot grasping.  ...  If the SVM classifiesĜ as a good grasp, the robot tries lifting the object, otherwise it tries a different grasp. The method is validated using a Barrett Hand with a good performance.  ... 
arXiv:1607.06620v1 fatcat:7ti5wexponcxpaxydbj5hkof7y

Self-Supervised Damage-Avoiding Manipulation Strategy Optimization via Mental Simulation [article]

Tobias Fromm
2017 arXiv   pre-print
The presented approach consists of a planning method that determines the optimal sequence to manipulate a number of objects in a scene with respect to possible damage by simulating interaction and hence  ...  However, we propose to take into account any unintended motion of objects in the scene and to learn manipulation strategies in a self-supervised way which minimize the potential damage.  ...  Now imagine a scenario with a robot for which grasping object A is easier than grasping object B in a specific scene because of • limited workspace due to manipulator size, position on the robot base and  ... 
arXiv:1712.07452v1 fatcat:n366fugsmbctxhqm2q6vc6musa

Manipulation in Human Environments

Aaron Edsinger, Charles Kemp
2006 2006 6th IEEE-RAS International Conference on Humanoid Robots  
We describe the design of a humanoid robot named Domo, develop methods that allow Domo to assist a person in everyday tasks, and discuss general strategies for building robots that work alongside people  ...  Human environments present special challenges for robot manipulation. They are often dynamic, difficult to predict, and beyond the control of a robot engineer.  ...  On a robot, the grasp aperture can be used to estimate the size of an unknown, grasped object.  ... 
doi:10.1109/ichr.2006.321370 dblp:conf/humanoids/EdsingerK06 fatcat:i5tunfqrrfdenh6k2vos5mhsby

A 3-stage Machine Learning-based Novel Object Grasping Methodology

Jacques Janse Van Vuuren, Liqiong Tang, Ibrahim Al-Bahadly, Khalid Mahmood Arif
2020 IEEE Access  
For unknown objects, this equates to a 10% improvement relative to other similar methodologies.  ...  To overcome human bias, objective measures of grasp performance are established that comprehensively measure the error introduced by the grasp trial itself.  ...  A scoring network is then used to rank these locations and decide on the final grasping position.  ... 
doi:10.1109/access.2020.2987341 fatcat:7gju7hgjwjbr7l3sl6txpd5u4y

Grasp type revisited: A modern perspective on a classical feature for vision

Yezhou Yang, Cornelia Fermuller, Yi Li, Yiannis Aloimonos
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Experiments on a public static scene hand data set validate good performance of the presented method.  ...  Experiments on both tasks demonstrate the usefulness of grasp type as a cognitive feature for computer vision.  ...  Knowledge about how to grasp the object is necessary so the robot can arrange its effectors. For example, consider a humanoid with one parallel gripper and one vacuum gripper.  ... 
doi:10.1109/cvpr.2015.7298637 dblp:conf/cvpr/YangFLA15 fatcat:3oliktk3jfai7hrhdjwyfnbbxy

Analysis of human–robot interaction at the DARPA Robotics Challenge Finals

Adam Norton, Willard Ober, Lisa Baraniecki, Eric McCann, Jean Scholtz, David Shane, Anna Skinner, Robert Watson, Holly Yanco
2017 The international journal of robotics research  
A set of guidelines for designing HRI with remote, semi-autonomous humanoid robots is proposed based on these results.  ...  All competition teams were responsible for developing their own interaction method to control their robot.  ...  Many thanks to all of the staff members of the DARPA Robotics Challenge for their assistance on-site.  ... 
doi:10.1177/0278364916688254 fatcat:iibefk6q35bz7ljrvz7i5a65sa
« Previous Showing results 1 — 15 out of 283 results