Evolution of visually-guided approach behaviour in recurrent artificial neural network robot controllers

• Analysis of internal structures of embodied and situated agents may provide insights into the mechanisms underlying adaptive behaviour. This paper is concerned with the evolution and analysis of visually-guided approach behaviour in a simulated robotic agent controlled by a recurrent artificial neural network, whose connection weights have been evolved using evolutionary algorithms. Analysis of the evolved behaviours and their network-internal mechanisms reveals a behavioural structure and organization resembling a Brooksian subsumption architecture. The task decomposition, as well as the resulting individual behaviours and their integration, however, are realized as network-internal state space dynamics, evolved in the course of agent-environment interaction, i.e. with a minimum of designer intervention.

• Annotation: In Pfeifer, Blumberg, Meyer, and Wilson (Eds.) From animals to animats 5-Proceedings of the Fifth International Conference on Simulation of Adaptive Behavior. Cambridge, MA: MIT Press.

Subject headings

NATURVETENSKAP  -- Data- och informationsvetenskap -- Systemvetenskap, informationssystem och informatik (hsv//swe)

NATURAL SCIENCES  -- Computer and Information Sciences -- Information Systems (hsv//eng)

Keyword

Evolutionary robotics

visually-guided behaviour

recurrent artificial neural networks

subsumption architectures

Computer and systems science

Data- och systemvetenskap

Publication and Content Type

vet (subject category)

rap (subject category)