DRAMA, a connectionist architecture for control and learning in autonomous robots

Billard, Aude and Hayes, Gillian (1999) DRAMA, a connectionist architecture for control and learning in autonomous robots. [Journal (Paginated)]

Full text available as:

[img] Postscript


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.

Item Type:Journal (Paginated)
Keywords:Time-delay recurrent neural network, Hebbian learning, on-line robot learning, autonomous robot, unsupervised learning, spatio-temporal correlations, time series, communication.
Subjects:Computer Science > Artificial Intelligence
Computer Science > Neural Nets
Computer Science > Robotics
Computer Science > Robotics
ID Code:535
Deposited By: Billard, Aude
Deposited On:09 Apr 1999
Last Modified:11 Mar 2011 08:54


Repository Staff Only: item control page