Touch Perception with SOM, Growing Cell Structures and Growing Grids
Author
Summary, in English
We have implemented four bio-inspired selforganizing
haptic systems based on proprioception on a 12
d.o.f. anthropomorphic robot hand. The four systems differ in
the kind of self-organizing neural network used for clustering.
For the mapping of the explored objects, one system uses a Self-
Organizing Map (SOM), one uses a Growing Cell Structure
(GCS), one uses a Growing Cell Structure with Deletion of
Neurons (GCS-DN) and one uses a Growing Grid (GG). The
systems were trained and tested with 10 different objects
of different sizes from two different shape categories. The
generalization abilities of the systems were tested with 6 new
objects. The systems showed good performance with the objects
from both the training set as well as in the generalization
experiments, i.e. they mapped the objects according to shape
and size and discriminated individual objects. The GCS-DN
system managed to evolve disconnected networks representing
different clusters in the input space (small cylinders, large
cylinders, small blocks, large blocks), and the generalization
samples activated neurons in a proper subnetwork in all but
one case.
haptic systems based on proprioception on a 12
d.o.f. anthropomorphic robot hand. The four systems differ in
the kind of self-organizing neural network used for clustering.
For the mapping of the explored objects, one system uses a Self-
Organizing Map (SOM), one uses a Growing Cell Structure
(GCS), one uses a Growing Cell Structure with Deletion of
Neurons (GCS-DN) and one uses a Growing Grid (GG). The
systems were trained and tested with 10 different objects
of different sizes from two different shape categories. The
generalization abilities of the systems were tested with 6 new
objects. The systems showed good performance with the objects
from both the training set as well as in the generalization
experiments, i.e. they mapped the objects according to shape
and size and discriminated individual objects. The GCS-DN
system managed to evolve disconnected networks representing
different clusters in the input space (small cylinders, large
cylinders, small blocks, large blocks), and the generalization
samples activated neurons in a proper subnetwork in all but
one case.
Department/s
Publishing year
2008
Language
English
Pages
79-85
Document type
Conference paper
Topic
- Computer Vision and Robotics (Autonomous Systems)
Conference name
Towards Autonomous Robotic Systems 2008
Conference date
2008-09-01 - 2008-09-03
Conference place
Edinburgh, United Kingdom
Status
Published
Project
- Ikaros: An infrastructure for system level modelling of the brain
Research group
- Lund University Cognitive Science (LUCS)