Combining arm and hand metrics for sensible grasp selection

Ana Huaman Quispe, Hani Ben Amor, Henrik I. Christensen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper we propose an approach to robot grasp prioritization based on a combined arm-and-hand metric. Most traditional approaches evaluate grasps based on hand-centric metrics such as force-closure, finger spread, contact surface area and similar measures. While these are certainly important factors to predict the robustness of a grasp, they do not carry information on the feasibility of the reaching action needed to execute the grasp. Based on our observations of physical pick-up experiments, we suggest that the execution success of a pick-up task is partially dependant on the easiness of the reaching movement. We present our metric, which combines 2 measures involving arm-kinematics and an existing hand heuristic metric. Results of simulated as well as physical experiments in our robot, Crichton, are presented.

Original languageEnglish (US)
Title of host publication2016 IEEE International Conference on Automation Science and Engineering, CASE 2016
PublisherIEEE Computer Society
Pages1170-1176
Number of pages7
Volume2016-November
ISBN (Electronic)9781509024094
DOIs
StatePublished - Nov 14 2016
Externally publishedYes
Event2016 IEEE International Conference on Automation Science and Engineering, CASE 2016 - Fort Worth, United States
Duration: Aug 21 2016Aug 24 2016

Other

Other2016 IEEE International Conference on Automation Science and Engineering, CASE 2016
CountryUnited States
CityFort Worth
Period8/21/168/24/16

Fingerprint

Robots
Kinematics
Experiments

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Quispe, A. H., Ben Amor, H., & Christensen, H. I. (2016). Combining arm and hand metrics for sensible grasp selection. In 2016 IEEE International Conference on Automation Science and Engineering, CASE 2016 (Vol. 2016-November, pp. 1170-1176). [7743537] IEEE Computer Society. https://doi.org/10.1109/COASE.2016.7743537

Combining arm and hand metrics for sensible grasp selection. / Quispe, Ana Huaman; Ben Amor, Hani; Christensen, Henrik I.

2016 IEEE International Conference on Automation Science and Engineering, CASE 2016. Vol. 2016-November IEEE Computer Society, 2016. p. 1170-1176 7743537.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Quispe, AH, Ben Amor, H & Christensen, HI 2016, Combining arm and hand metrics for sensible grasp selection. in 2016 IEEE International Conference on Automation Science and Engineering, CASE 2016. vol. 2016-November, 7743537, IEEE Computer Society, pp. 1170-1176, 2016 IEEE International Conference on Automation Science and Engineering, CASE 2016, Fort Worth, United States, 8/21/16. https://doi.org/10.1109/COASE.2016.7743537
Quispe AH, Ben Amor H, Christensen HI. Combining arm and hand metrics for sensible grasp selection. In 2016 IEEE International Conference on Automation Science and Engineering, CASE 2016. Vol. 2016-November. IEEE Computer Society. 2016. p. 1170-1176. 7743537 https://doi.org/10.1109/COASE.2016.7743537
Quispe, Ana Huaman ; Ben Amor, Hani ; Christensen, Henrik I. / Combining arm and hand metrics for sensible grasp selection. 2016 IEEE International Conference on Automation Science and Engineering, CASE 2016. Vol. 2016-November IEEE Computer Society, 2016. pp. 1170-1176
@inproceedings{ee1104680eae485f8da9de7ab72200b3,
title = "Combining arm and hand metrics for sensible grasp selection",
abstract = "In this paper we propose an approach to robot grasp prioritization based on a combined arm-and-hand metric. Most traditional approaches evaluate grasps based on hand-centric metrics such as force-closure, finger spread, contact surface area and similar measures. While these are certainly important factors to predict the robustness of a grasp, they do not carry information on the feasibility of the reaching action needed to execute the grasp. Based on our observations of physical pick-up experiments, we suggest that the execution success of a pick-up task is partially dependant on the easiness of the reaching movement. We present our metric, which combines 2 measures involving arm-kinematics and an existing hand heuristic metric. Results of simulated as well as physical experiments in our robot, Crichton, are presented.",
author = "Quispe, {Ana Huaman} and {Ben Amor}, Hani and Christensen, {Henrik I.}",
year = "2016",
month = "11",
day = "14",
doi = "10.1109/COASE.2016.7743537",
language = "English (US)",
volume = "2016-November",
pages = "1170--1176",
booktitle = "2016 IEEE International Conference on Automation Science and Engineering, CASE 2016",
publisher = "IEEE Computer Society",
address = "United States",

}

TY - GEN

T1 - Combining arm and hand metrics for sensible grasp selection

AU - Quispe, Ana Huaman

AU - Ben Amor, Hani

AU - Christensen, Henrik I.

PY - 2016/11/14

Y1 - 2016/11/14

N2 - In this paper we propose an approach to robot grasp prioritization based on a combined arm-and-hand metric. Most traditional approaches evaluate grasps based on hand-centric metrics such as force-closure, finger spread, contact surface area and similar measures. While these are certainly important factors to predict the robustness of a grasp, they do not carry information on the feasibility of the reaching action needed to execute the grasp. Based on our observations of physical pick-up experiments, we suggest that the execution success of a pick-up task is partially dependant on the easiness of the reaching movement. We present our metric, which combines 2 measures involving arm-kinematics and an existing hand heuristic metric. Results of simulated as well as physical experiments in our robot, Crichton, are presented.

AB - In this paper we propose an approach to robot grasp prioritization based on a combined arm-and-hand metric. Most traditional approaches evaluate grasps based on hand-centric metrics such as force-closure, finger spread, contact surface area and similar measures. While these are certainly important factors to predict the robustness of a grasp, they do not carry information on the feasibility of the reaching action needed to execute the grasp. Based on our observations of physical pick-up experiments, we suggest that the execution success of a pick-up task is partially dependant on the easiness of the reaching movement. We present our metric, which combines 2 measures involving arm-kinematics and an existing hand heuristic metric. Results of simulated as well as physical experiments in our robot, Crichton, are presented.

UR - http://www.scopus.com/inward/record.url?scp=85000916282&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85000916282&partnerID=8YFLogxK

U2 - 10.1109/COASE.2016.7743537

DO - 10.1109/COASE.2016.7743537

M3 - Conference contribution

VL - 2016-November

SP - 1170

EP - 1176

BT - 2016 IEEE International Conference on Automation Science and Engineering, CASE 2016

PB - IEEE Computer Society

ER -