Sökning: onr:"swepub:oai:DiVA.org:his-1246" >
Towards Autonomous ...
Towards Autonomous Robot Control via Self-Adapting Recurrent Networks
-
- Ziemke, Tom (författare)
- Högskolan i Skövde,Institutionen för datavetenskap,Neural Computing Group, Dept. of Computer Science, University of Sheffield, UK,The Connectionist Research Group
-
(creator_code:org_t)
- Skövde : University of Skövde, 1996
- Engelska.
-
Serie: IDA Technical Reports ; HS-IDA-TR-96-009
- Relaterad länk:
-
https://citeseerx.is...
-
visa fler...
-
https://urn.kb.se/re...
-
visa färre...
Abstract
Ämnesord
Stäng
- 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)