2016
DOI: 10.1109/lra.2016.2517209
|View full text |Cite
|
Sign up to set email alerts
|

Benchmarking the Grasping Capabilities of the iCub Hand With the YCB Object and Model Set

Abstract: The paper reports an evaluation of the iCub grasping capabilities, performed using the YCB Object and Model Set. The goal is to understand what kind of objects the iCub dexterous hand can grasp, and with what degree of robustness and flexibility, given the best possible control strategy. Therefore, the robot fingers are directly controlled by a human expert using a dataglove: in other words, the human brain is employed as the best possible controller. Through this technique, we provide a baseline for researche… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
7
0

Year Published

2017
2017
2023
2023

Publication Types

Select...
4
2

Relationship

0
6

Authors

Journals

citations
Cited by 11 publications
(7 citation statements)
references
References 19 publications
(21 reference statements)
0
7
0
Order By: Relevance
“…In addition, it also includes the research history and research results of computer simulation painting technology and multitouch technology. 21 In the research based on rigid palm dexterous hand grasping, scholars generally focus on how to use arm motion planning to move the end effector, namely the rigid palm, to a specified position, and finally complete the grasping action through finger movements. For traditional mechanical dexterous hands, its flexibility is reflected in how to improve the layout of the fingers and increase the extra freedom of the fingers.…”
Section: Discussionmentioning
confidence: 99%
“…In addition, it also includes the research history and research results of computer simulation painting technology and multitouch technology. 21 In the research based on rigid palm dexterous hand grasping, scholars generally focus on how to use arm motion planning to move the end effector, namely the rigid palm, to a specified position, and finally complete the grasping action through finger movements. For traditional mechanical dexterous hands, its flexibility is reflected in how to improve the layout of the fingers and increase the extra freedom of the fingers.…”
Section: Discussionmentioning
confidence: 99%
“…With reference to the adaptive grasping action of the human hand, the multi-joint pneumatic hand is provided with an appropriate amount of air pressure for the grasping behaviour of the fingers to undergo active adaptive deformation. The YCB (Yale -CMU -Berkeley) set of grasped items [5] is selected as the object to be grasped for the experiment, and can be divided into four main categories: food, kitchenware, tools and shapes. Figure 5 illustrates the grasping performance of a representative number of objects.…”
Section: Grasping Performance Testsmentioning
confidence: 99%
“…In recent years, rigid manipulators have achieved good functionality by introducing many elements such as motors, linkages, gears and springs [2][3][4], but at the same time greatly increasing the sophistication of structures. Although the rigid robotic hands are precise and responsive, they may cause irreparable damage when gripping fragile things [5]. Due to the softness of its material, the soft hand has a unique advantage in terms of compliance and toughness, not only it can grasp different kinds of objects, but also it will hardly be damaged when it is extruded and collided with by outside [6][7][8].…”
Section: Introductionmentioning
confidence: 99%
“…Grasping Benchmark 4: extended GAB. An extension to the standard GAB was proposed by Jamone et al 47 to include three more categories of objects: Cubic, Cylindrical, and Complex. The addition of further objects provides more information about the types of object graspable by the T-MO.…”
Section: Grasping Benchmarksmentioning
confidence: 99%
“…Extended Scoring of the Tactile Model O Hand in the Basic Gripper AssessmentBenchmark as Proposed by Jamone et al47 …”
mentioning
confidence: 99%