Towards Autonomous Robot Control via Self-Adapting Recurrent Networks

• In this paper a higher-order recurrent connectionist architecture is used for learning adaptive behaviour in an autonomous robot. This architecture consists of two sub-networks in a master-slave relationship: a function network for the coupling between sensory inputs and motor outputs, and a context network, which dynamically adapts the sensory input weights in order to allow a flexible, context-dependent mapping from percepts to actions. The capabilities of this architecture are demonstrated in a number of action selection experiments with a simulated Khepera robot, and it is argued that the general approach of generically dividing the overall control task between sequentially cascaded context and function learning offers a powerful mechanism for autonomous long- and short-term adaptation of behaviour

Ämnesord

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

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

Nyckelord

autonomy

complex behaviour

recurrent connectionist networks

subsumption architecture

Computer and systems science

Data- och systemvetenskap

Publikations- och innehållstyp

vet (ämneskategori)

rap (ämneskategori)