Eye in hand: Towards GPU accelerated online grasp planning based on pointclouds from in-hand sensor

Resource type
Conference
Author(s)
Hermann, Andreas and Mauch, Felix and Klemm, Sebastian and Roennau, Arne and Dillmann, Ruediger
Year
2016
Volume
16
Month
Nov
Address
Cancun, Mexico
Book title
Humanoid Robots (Humanoids), 2016 IEEE-RAS 16th International Conference on
Organization
IEEE
Abstract
This work proposes the usage of in-hand depth cameras in combination with GPU-based collision detection algorithms to realize robotics grasp planning for unknown objects on the fly. Based on pointcloud data captured during an exploratory hand motion we evaluate and optimize grasps with a hybrid Particle Swarm Optimization process. The approach maximizes the contact surface while examining various grasp poses and allows a precise and model-free manipulation of arbitrary objects. Targeted end-effectors are anthropomatic multi-fingered hands with complex kinematics and geometries.
DOI
10.1109/HUMANOIDS.2016.7803394
Research focus
Service Robotics and Mobile Manipulation
Download .bib
Download .bib
Published by