Pei-Hsin Kuo

dblp:164/8523 · DBLP profile ↗
← Back
1ranked-venue papers
1as first author
0since 2021 · last 2015
—ORCID · none

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 1 · 1 first-authorSystems, architecture and hardware · 1 · 1 first-author

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Artificial intelligence
1 paper
Robot manipulation · 100%

Topics — the 4 heaviest of 4, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Robotics › Robot manipulation
grasping
0.212015
Design of robotic fingers with human-like passive parallel compliance · ICRA 2015
Robotics › Robot manipulation › compliant manipulation
passive compliance
0.212015
Design of robotic fingers with human-like passive parallel compliance · ICRA 2015
Robotics › Robot manipulation
robotic hand design
0.212015
Design of robotic fingers with human-like passive parallel compliance · ICRA 2015
Robotics › Robot manipulation › cable-driven robot
tendon-driven manipulation
0.112015
Design of robotic fingers with human-like passive parallel compliance · ICRA 2015

Methods — techniques the papers use, named apart from their topics

motion capture · 0.2compliant joint optimization · 0.2
YearPublicationVenuePosition
2015 Design of robotic fingers with human-like passive parallel compliance
abstract
While human-like series passive compliance has been used in previous robotic hand designs, little attention has been paid to parallel passive compliance due to the lack of understanding of its importance in grasping and manipulation. In this paper, we present a novel design of compliant finger inspired by biomechanical features and functionality of human hands. We develop a human-like compact joint by optimizing the geometry of a compliant material and mechanical elements. The joint exhibits a passive double exponential torque matching human-like compliance. We implement the compliant joint into a robotic finger design with human-like tendon routings. We carry out a series of experiments on the finger design with an open-loop control strategy in grasping and manipulation. The results show that the fingers perform reliable grasping and manipulation without feedback. We validate the trajectory tracking with a motion capture system. The human-like compliant fingers follow the desired trajectories with small errors (less than 1 cm). The innovative finger design realizes the human-like hand passive properties and achieves human-like grasping capability.
Pei-Hsin Kuo, James DeBacker, Ashish D. Deshpande
ICRA1