Evaluating the Quality of Non-Prehensile Balancing Grasps
Paper i proceeding, 2018

Assessing grasp quality and, subsequently, predicting grasp success is useful for avoiding failures in many autonomous robotic applications. In addition, interest in nonprehensile grasping and manipulation has been growing as it offers the potential for a large increase in dexterity. However, while force-closure grasping has been the subject of intense study for many years, few existing works have considered quality metrics for non-prehensile grasps. Furthermore, no studies exist to validate them in practice. In this work we use a real-world data set of non-prehensile balancing grasps and use it to experimentally validate a wrench-based quality metric by means of its grasp success prediction capability. The overall accuracy of up to 84 % is encouraging and in line with existing results for force-closure grasps.

Friction

Task analysis

Robots

Predictive models

Measurement

Grasping

Force

Författare

Robert Krug

Kungliga Tekniska Högskolan (KTH)

Yasemin Bekiroglu

Vicarious AI

Danica Kragic

Kungliga Tekniska Högskolan (KTH)

Maximo Roa

Deutsches Zentrums für Luft- und Raumfahrt (DLR)

2018 IEEE International Conference on Robotics and Automation (ICRA)

2577-087X (ISSN) 2577-087X (eISSN)

4215-4215

IEEE International Conference on Robotics and Automation (ICRA)
Brisbane, Australia,

Ämneskategorier

Biomedicinsk laboratorievetenskap/teknologi

Bioinformatik (beräkningsbiologi)

Robotteknik och automation

DOI

10.1109/ICRA.2018.8461078

Mer information

Senast uppdaterat

2022-06-03