Towards Grasping with Spiking Neural Networks for Anthropomorphic Robot Hands

Resource type
Conference
Author(s)
Tieck, J. Camilo Vasquez and Donat, Heiko and Kaiser, Jacques and Peric, Igor and Ulbrich, Stefan and Roennau, Arne and Zöllner, Marius and Dillmann, Rüdiger
Year
2017
Pages
43--51
Publisher
Springer International Publishing
Address
Cham
ISBN
978-3-319-68600-4
Book title
Artificial Neural Networks and Machine Learning -- ICANN 2017
Editor
Lintas, Alessandra and Rovetta, Stefano and Verschure, Paul F.M.J. and Villa, Alessandro E.P.
Abstract
Representation and execution of movement in biology is an active field of research relevant to neurorobotics. Humans can remember grasp motions and modify them during execution based on the shape and the intended interaction with objects. We present a hierarchical spiking neural network with a biologically inspired architecture for representing different grasp motions. We demonstrate the ability of our network to learn from human demonstration using synaptic plasticity on two different exemplary grasp types (pinch and cylinder). We evaluate the performance of the network in simulation and on a real anthropomorphic robotic hand. The network exposes the ability of learning finger coordination and synergies between joints that can be used for grasping.
DOI
10.1007/978-3-319-68600-4_6
Download .bib
Download .bib
Published by
Arne Rönnau