Evaluating the Quality of Non-Prehensile Balancing Grasps
Paper in 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.


Task analysis


Predictive models





Robert Krug

Royal Institute of Technology (KTH)

Yasemin Bekiroglu

Vicarious AI

Danica Kragic

Royal Institute of Technology (KTH)

Maximo Roa

German Aerospace Center (DLR)

2018 IEEE International Conference on Robotics and Automation (ICRA)

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


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

Subject Categories

Biomedical Laboratory Science/Technology

Bioinformatics (Computational Biology)




More information

Latest update

6/3/2022 8