Name
Abstract | ||
|---|---|---|
This paper investigates the processes used by an evolved, embodied simulated agent to adapt to large disruptive changes in its sensor morphology, whilst maintaining performance in a phototaxis task. By avoiding the imposition of separate mechanisms for the fast sensorimotor dynamics and the relatively slow adaptive processes, we are able to comment on the forms of adaptivity which emerge within our Evolutionary Robotics framework. This brings about interesting notions regarding the relationship between different timescales. We examine the dynamics of the network and find different reactive behaviours depending on the agent's current sensor configuration, but are only able to begin to explain the dynamics of the transitions between these states with reference to variables which exist in the agent's environment, as well as within its neural network 'brain'. |
Year | DOI | Venue |
|---|---|---|
2007 | 10.1007/978-3-540-74913-4_21 | ECAL |
Keywords | Field | DocType |
simulated agent,sensor morphology,neural network,different reactive,evolutionary robotics framework,current sensor configuration,interesting notion,different timescales,adaptive process,fast sensorimotor dynamic | Evolutionary robotics,Computer science,Embodied cognition,Artificial intelligence,Current sensor,Artificial neural network,Phototaxis,Machine learning | Conference |
Volume | ISSN | Citations |
4648 | 0302-9743 | 6 |
PageRank | References | Authors |
1.04 | 5 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Peter Fine | 1 | 14 | 3.33 |
| Ezequiel A. Di Paolo | 2 | 428 | 47.42 |
| Eduardo Izquierdo | 3 | 46 | 7.91 |