2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422)
DOI: 10.1109/robot.2003.1241860
|View full text |Cite
|
Sign up to set email alerts
|

Automatic grasp planning using shape primitives

Abstract: Abstract-Automatic grasp planning for robotic hands is a difficult problem because of the huge number of possible hand configurations. However, humans simplify the problem by choosing an appropriate prehensile posture appropriate for the object and task to be performed. By modeling an object as a set of shape primitives, such as spheres, cylinders, cones and boxes, we can use a set of NI-to generate a set of grasp starting positions and pregrasp shapes that can then be tested on the object model. Each grasp is… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
380
0
7

Publication Types

Select...
5
3
1

Relationship

0
9

Authors

Journals

citations
Cited by 565 publications
(387 citation statements)
references
References 13 publications
0
380
0
7
Order By: Relevance
“…In [27,28,29], objects are represented as basic shape primitives and then associated with predefined grasp primitives. In [30], a support vector machine (SVM) is used to learn the grasp quality manifold for a specific hand and simple object shapes.…”
Section: Related Workmentioning
confidence: 99%
“…In [27,28,29], objects are represented as basic shape primitives and then associated with predefined grasp primitives. In [30], a support vector machine (SVM) is used to learn the grasp quality manifold for a specific hand and simple object shapes.…”
Section: Related Workmentioning
confidence: 99%
“…Some works do this by matching hand pre-grasp postures to prototypical geometric shapes (Miller et al, 2003;Eppner and Brock, 2013). Others learn the mapping of hand-object shape match from real data (Lenz et al, 2013).…”
Section: Interactions Between Hand and Objectmentioning
confidence: 99%
“…Instead of directly searching the high dimensional configuration space of robotic hands, this space can be reduced by generating a set of grasp starting positions, hand preshapes [15] or eigengrasps [2] that can then be tested on the object model. Such approaches reduce the dimensionality of the hand configuration space, but doing so implies a corresponding reduction in the accessible hand postures.…”
Section: Related Workmentioning
confidence: 99%
“…Its quality measurement module computes the grasp quality according to all the contacts between the hand and the object, in the form described by Ferrari and Canny [7]. A grasp planning module for primitive shapes, i.e cylinder, sphere, cuboid and cone, is available, allowing users to easily generate grasps [15]. To sample grasps for objects with complex shapes, we alter the module and generate grasps as follows.…”
Section: A Grasp Generation Given the Hand Kinematicsmentioning
confidence: 99%