Open AccessWrist-driven passive grasping: interaction-based trajectory adaption with a compliant anthropomorphic hand
Author(s) -
Kieran Gilday,
Josie Hughes,
Fumiya Iida
Publication year - 2021
Publication title -
bioinspiration and biomimetics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.905
H-Index - 69
eISSN - 1748-3190
pISSN - 1748-3182
DOI - 10.1088/1748-3190/abe345
Subject(s) - wrist , trajectory , computer science , object (grammar) , degrees of freedom (physics and chemistry) , exploit , artificial intelligence , simulation , task (project management) , robot , computer vision , engineering , medicine , physics , computer security , systems engineering , quantum mechanics , astronomy , radiology
The structure of the human musculo-skeletal systems shows complex passive dynamic properties, critical for adaptive grasping and motions. Through wrist and arm actuation, these passive dynamic properties can be exploited to achieve nuanced and diverse environment interactions. We have developed a passive anthropomorphic robot hand that shows complex passive dynamics. We require arm/wrist control with the ability to exploit these. Due to the soft hand structures and high degrees of freedom during passive-object interactions, bespoke generation of wrist trajectories is challenging. We propose a new approach, which takes existing wrist trajectories and adapts them to changes in the environment, through analysis and classification of the interactions. By analysing the interactions between the passive hand and object, the required wrist motions to achieve them can be mapped back to control of the hand. This allows the creation of trajectories which are parameterized by object size or task. This approach shows up to 86% improvement in grasping success rate with a passive hand for object size changes up to ±50%.