Preprints available

[Aude Billard]

The following paper "DRAMA, a connectionist architecture for control
and learning in autonomous robots" is to appear in Adaptive Behaviour
Journal, vol. 7:1 (January 1999). 

A preprint of the paper is available at the site:
http://www.dai.ed.ac.uk/daidb/people/homes/audeb/publication.html

This paper reports on the development of a novel connectionist
architecture used for on-line learning of spatio-temporal regularities
and time series in discrete sequences of inputs of an autonomous
mobile robot. An on-line version of my PhD thesis, of which the paper
reports some aspects, will soon be available.

I am very grateful for any  comments.

Thank you for transmitting the message.

Aude Billard


=================================================================

  DRAMA, a connectionist architecture for control and learning in
  autonomous robots, Billard A. and Hayes G. (1998), In 
  Adaptive Behaviour Journal, vol. 7:1.


  This work proposes a connectionist architecture, DRAMA, for dynamic
  control and learning of autonomous robots. DRAMA stands for
  dynamical recurrent associative memory architecture. It is a 
  time-delay recurrent neural network, using Hebbian update rules. It
  allows learning of spatio-temporal regularities and time series in
  discrete sequences of inputs, in the face of an important amount of
  noise.  The first part of this paper gives the mathematical
  description of the architecture and analyses theoretically and
  through numerical simulations its performance. The second part of
  this paper reports on the implementation of DRAMA in simulated and
  physical robotic experiments. Training and rehearsal of the DRAMA
  architecture is computationally fast and inexpensive, which makes the
  model particularly suitable for controlling
  `computationally-challenged' robots. In the experiments, we use a
  basic hardware system with very limited computational capability and
  show that our robot can carry out real time computation and on-line
  learning of relatively complex cognitive tasks. In these
  experiments, two autonomous robots wander randomly in a fixed
  environment, collecting information about its elements. By mutually
  associating information of their sensors and actuators, they learn
  about physical regularities underlying their experience of varying
  stimuli.  The agents learn also from their mutual interactions. We
  use a teacher-learner scenario, based on mutual following of the two
  agents, to enable transmission of a vocabulary from one robot to the
  other.

Keywords: Time-delay recurrent neural network; Hebbian
  learning; spatio-temporal associations; unsupervised dynamical
  learning; autonomous robots.