The Robotics Institute
Search the site
RI | Publications | Grasp Synthesis from Example: Tuning the Example to a Task or Object

Text only version of this site

Grasp Synthesis from Example: Tuning the Example to a Task or Object
N. Pollard and A. Wolf
Multi-point Interaction with Real and Virtual Objects, Federico Barbagli, Domenico Prattichizzo, and Kenneth Salisbury, ed., Springer Tracts in Advanced Robotics, 2005, pp. 77-90.

Jump to: Download | Abstract | Notes | Text Reference | BibTeX Reference

Download [Help]

Adobe portable document format (pdf) [651 KB]

Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract

Many approaches to grasp synthesis do not scale well as the desired number of contacts is increased. In previous work, we have presented a technique that makes use of an example grasp to make synthesis tractable for grasps having larger numbers of contacts. However, an interesting side effect of this approach is that results can pick up quirks that are present in the example, some of which may be undesirable. We are beginning to explore techniques to tune an example grasp for a specific collection of task wrenches and to a given object geometry. This paper presents preliminary results.

Notes

Sponsor: NSF
Grant ID: CCF-0343161

Number of pages: 16

Text Reference

N. Pollard and A. Wolf, "Grasp Synthesis from Example: Tuning the Example to a Task or Object," Multi-point Interaction with Real and Virtual Objects, Federico Barbagli, Domenico Prattichizzo, and Kenneth Salisbury, ed., Springer Tracts in Advanced Robotics, 2005, pp. 77-90.

BibTeX Reference

@incollection{Pollard_2005_5397,
   author = "Nancy Pollard and Alon Wolf",
   editor = "Federico Barbagli, Domenico Prattichizzo, and Kenneth Salisbury",
   title = "Grasp Synthesis from Example: Tuning the Example to a Task or Object",
   booktitle = "Multi-point Interaction with Real and Virtual Objects",
   pages = "77-90",
   publisher = "Springer Tracts in Advanced Robotics",
   year = "2005"
}


The Robotics Institute is part of the School of Computer Science, Carnegie Mellon University.
For updates and comments, please see these instructions.
This page maintained by robotwebmaster@ri.cmu.edu