Advanced

Neural network models of haptic shape perception

Johnsson, Magnus LU and Balkenius, Christian LU (2007) In Robotics and Autonomous Systems 55(9). p.720-727
Abstract
Three different models of tactile shape perception inspired by the human haptic system were tested using an 8 d.o.f. robot hand with 45 tactile sensors. One model is based on the tensor product of different proprioceptive and tactile signals and a self-organizing map (SOM). The two other models replace the tensor product operation with a novel self-organizing neural network, the Tensor-Multiple Peak Self-Organizing Map (T-MPSOM). The two T-MPSOM models differ in the procedure employed to calculate the neural activation. The computational models were trained and tested with a set of objects consisting of hard spheres, blocks and cylinders. All the models learned to map different shapes to different areas of the SOM, and the tensor product... (More)
Three different models of tactile shape perception inspired by the human haptic system were tested using an 8 d.o.f. robot hand with 45 tactile sensors. One model is based on the tensor product of different proprioceptive and tactile signals and a self-organizing map (SOM). The two other models replace the tensor product operation with a novel self-organizing neural network, the Tensor-Multiple Peak Self-Organizing Map (T-MPSOM). The two T-MPSOM models differ in the procedure employed to calculate the neural activation. The computational models were trained and tested with a set of objects consisting of hard spheres, blocks and cylinders. All the models learned to map different shapes to different areas of the SOM, and the tensor product model as well as one of the T-MPSOM models also learned to discriminate individual test objects. (c) 2007 Elsevier B.V. All rights reserved. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
robotic hand, tensor product, haptic perception, self-organizing map
in
Robotics and Autonomous Systems
volume
55
issue
9
pages
720 - 727
publisher
Elsevier
external identifiers
  • wos:000249771900009
  • scopus:34548029725
ISSN
0921-8890
DOI
10.1016/j.robot.2007.05.003
language
English
LU publication?
yes
id
02be64a9-3154-48f8-8957-7203e3698e91 (old id 655858)
date added to LUP
2007-12-13 13:52:42
date last changed
2017-01-01 06:57:40
@article{02be64a9-3154-48f8-8957-7203e3698e91,
  abstract     = {Three different models of tactile shape perception inspired by the human haptic system were tested using an 8 d.o.f. robot hand with 45 tactile sensors. One model is based on the tensor product of different proprioceptive and tactile signals and a self-organizing map (SOM). The two other models replace the tensor product operation with a novel self-organizing neural network, the Tensor-Multiple Peak Self-Organizing Map (T-MPSOM). The two T-MPSOM models differ in the procedure employed to calculate the neural activation. The computational models were trained and tested with a set of objects consisting of hard spheres, blocks and cylinders. All the models learned to map different shapes to different areas of the SOM, and the tensor product model as well as one of the T-MPSOM models also learned to discriminate individual test objects. (c) 2007 Elsevier B.V. All rights reserved.},
  author       = {Johnsson, Magnus and Balkenius, Christian},
  issn         = {0921-8890},
  keyword      = {robotic hand,tensor product,haptic perception,self-organizing map},
  language     = {eng},
  number       = {9},
  pages        = {720--727},
  publisher    = {Elsevier},
  series       = {Robotics and Autonomous Systems},
  title        = {Neural network models of haptic shape perception},
  url          = {http://dx.doi.org/10.1016/j.robot.2007.05.003},
  volume       = {55},
  year         = {2007},
}