Advanced

Recognizing Texture and Hardness by Touch

Johnsson, Magnus LU and Balkenius, Christian LU (2008) IROS 2008 p.482-487
Abstract
We have experimented with different neural network

based architectures for bio-inspired self-organizing texture

and hardness perception systems. 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.We have implemented and successfully tested

both monomodal systems for texture and hardness perception

and multimodal systems that merge texture and hardness data

into one representation. All systems were trained and tested

with multiple samples gained from the exploration of a set of 4

soft and 4 hard objects of different materials. The monomodal

... (More)
We have experimented with different neural network

based architectures for bio-inspired self-organizing texture

and hardness perception systems. 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.We have implemented and successfully tested

both monomodal systems for texture and hardness perception

and multimodal systems that merge texture and hardness data

into one representation. All systems were trained and tested

with multiple samples gained from the exploration of a set of 4

soft and 4 hard objects of different materials. The monomodal

texture system was good at mapping individual objects in

a sensible way, the hardness systems was good at mapping

individual objects and in addition dividing the objects into

categories of hard and soft objects. The multimodal system was

successful in merging the two modalities into a representation

that performed at least as good as the best recognizer of

individual objects, i.e. the texture system, and at the same time

categorizing the objects into hard and soft. (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
IROS 2008
external identifiers
  • Scopus:69549090016
language
English
LU publication?
yes
id
f05cd381-9b13-4c23-9478-45a8b1274683 (old id 1288041)
date added to LUP
2009-01-30 09:41:15
date last changed
2016-10-13 05:02:45
@misc{f05cd381-9b13-4c23-9478-45a8b1274683,
  abstract     = {We have experimented with different neural network<br/><br>
based architectures for bio-inspired self-organizing texture<br/><br>
and hardness perception systems. To this end we have<br/><br>
developed a microphone based texture sensor and a hardness<br/><br>
sensor that measures the compression of the material at a<br/><br>
constant pressure.We have implemented and successfully tested<br/><br>
both monomodal systems for texture and hardness perception<br/><br>
and multimodal systems that merge texture and hardness data<br/><br>
into one representation. All systems were trained and tested<br/><br>
with multiple samples gained from the exploration of a set of 4<br/><br>
soft and 4 hard objects of different materials. The monomodal<br/><br>
texture system was good at mapping individual objects in<br/><br>
a sensible way, the hardness systems was good at mapping<br/><br>
individual objects and in addition dividing the objects into<br/><br>
categories of hard and soft objects. The multimodal system was<br/><br>
successful in merging the two modalities into a representation<br/><br>
that performed at least as good as the best recognizer of<br/><br>
individual objects, i.e. the texture system, and at the same time<br/><br>
categorizing the objects into hard and soft.},
  author       = {Johnsson, Magnus and Balkenius, Christian},
  language     = {eng},
  pages        = {482--487},
  title        = {Recognizing Texture and Hardness by Touch},
  year         = {2008},
}