Advanced

Associating SOM Representations of Haptic Submodalities

Johnsson, Magnus LU and Balkenius, Christian LU (2008) Towards Autonomous Robotic Systems 2008 p.124-129
Abstract
We have experimented with a bio-inspired selforganizing

texture and hardness perception system which

automatically learns to associate the representations of the two

submodalities with each other. To this end we have developed

a microphone based texture sensor and a hardness sensor that

measures the compression of the material at a constant pressure.

The system is based on a novel variant of the Self-Organizing

Map (SOM), called Associative Self-Organizing Map (A-SOM).

The A-SOM both develops a representation of its input space

and learns to associate this with the activity in an external SOM

or A-SOM. The system was trained and tested with... (More)
We have experimented with a bio-inspired selforganizing

texture and hardness perception system which

automatically learns to associate the representations of the two

submodalities with each other. To this end we have developed

a microphone based texture sensor and a hardness sensor that

measures the compression of the material at a constant pressure.

The system is based on a novel variant of the Self-Organizing

Map (SOM), called Associative Self-Organizing Map (A-SOM).

The A-SOM both develops a representation of its input space

and learns to associate this with the activity in an external SOM

or A-SOM. The system was trained and tested with multiple

samples gained from the exploration of a set of 4 soft and 4 hard

objects of different materials with varying textural properties.

The system successfully found representations of the texture

and hardness submodalities and also learned to associate these

with each other. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to conference
publication status
published
subject
pages
6 pages
conference name
Towards Autonomous Robotic Systems 2008
language
English
LU publication?
yes
id
7a80fc23-f36d-4c39-b23f-c9d9144fc92d (old id 1288037)
date added to LUP
2009-01-30 09:31:19
date last changed
2016-04-16 11:53:05
@misc{7a80fc23-f36d-4c39-b23f-c9d9144fc92d,
  abstract     = {We have experimented with a bio-inspired selforganizing<br/><br>
texture and hardness perception system which<br/><br>
automatically learns to associate the representations of the two<br/><br>
submodalities with each other. To this end we have developed<br/><br>
a microphone based texture sensor and a hardness sensor that<br/><br>
measures the compression of the material at a constant pressure.<br/><br>
The system is based on a novel variant of the Self-Organizing<br/><br>
Map (SOM), called Associative Self-Organizing Map (A-SOM).<br/><br>
The A-SOM both develops a representation of its input space<br/><br>
and learns to associate this with the activity in an external SOM<br/><br>
or A-SOM. The system was trained and tested with multiple<br/><br>
samples gained from the exploration of a set of 4 soft and 4 hard<br/><br>
objects of different materials with varying textural properties.<br/><br>
The system successfully found representations of the texture<br/><br>
and hardness submodalities and also learned to associate these<br/><br>
with each other.},
  author       = {Johnsson, Magnus and Balkenius, Christian},
  language     = {eng},
  pages        = {124--129},
  title        = {Associating SOM Representations of Haptic Submodalities},
  year         = {2008},
}