GNOSYS
1. PARTNERS
|
List of Participants |
||||||
|
Partic.Role* |
Partic.
no. |
Participant
name |
Participant
short name |
Country |
Date
enter project** |
Date
exit project** |
|
CO |
1 |
King’s College London |
KCL |
|
Month 1 |
Month 36 |
|
CR |
2 |
ZENON |
ZENON |
GR |
Month 1 |
Month 36 |
|
CR |
3 |
Foundation of Research and
Technology - |
|
GR |
Month 1 |
Month 36 |
|
CR |
4 |
Eberhard_Karls-Inversitat |
UTUB |
DE |
Month 1 |
Month 36 |
|
CR |
5 |
Universita di Genova,
Dipartimento di Informatica, Sistemistica, Telematica |
UGDIST |
IT |
Month 1 |
Month 36 |
*CO = Coordinator
CR = Contractor
The project will develop and validate a conceptual architecture for Cognitive Agents. The architecture will integrate the cycle of perception-knowledge acquisition-abstraction-reasoning-action generation. Special focus will be given to the abstraction architecture. The concept system is the representation of the knowledge that the agent possesses of its environment and itself. Objects, relations, goals, context information, and solution strategies are considered as knowledge about a situation. The abstraction mechanism is responsible for creating and organising a hierarchy of concepts while the reasoning process operates on the concept system in order to make inferences for virtual actions and select the one that will realise the greatest reward. The architecture will include attention control as a means of handling complexity, prioritising responses, detecting novelty and creating new goals. Both sensory and motor attention will be used. A goals-oriented computational model will allow the fusion together of user tasks with tasks originating from the agent. A goals generation system will enable the agent to produce its own goals. Reinforcement learning will provide the means by which the agent learns solution strategies for the satisfaction of a goal. The loop closes by having new actions modifying the current knowledge through perception.
The architecture will be implemented in a robotics application, namely of robot navigation in unknown outdoors environment but it will be in no way specific to this domain. Major requirements include survival, fast response and user-goal satisfaction. The robotic agent will learn about its own environment before becoming able to satisfy successfully any user goal. The process of retraining prior to becoming service-able will be re-iterated in a new environment. Different outdoors environments will be used for testing purposes. The evaluation process will examine the generality, performance, accuracy, scalability and robustness of the architecture.