European Commission logo
français français
CORDIS - Résultats de la recherche de l’UE

Cognitive systems using perception-action learning


Central topics of the COSPAL project are a new system architecture and new learning strategies for artificial cognitive systems (ACSs). The novelty of the approach lies in the interaction of continuous and symbolic perception and action, which results in robust and stable motor and sensorial capabilities of the system and allows a purposive behaviour. Moreover, the system is able to extend itself through exploration of the environment and has therefore the potential to solve problems of a large range of complexity levels.

The new learning strategy is based on the assumption that perception is shaped by incremental (online) learning of percept-action mappings and by introducing rules at an appropriate level of tasks. The necessary system structure to achieve this goal is a multi-level network consisting of different layers, using new kinds of networks and a new type of information representation, the channel representation, whose locality property allow a fast convergence in learning. In the demonstrator of the COSPAL project we will show that after an initial bootstrapping phase such a system can autonomously solve shape-sorter puzzles of various kinds.

The investigation of the sketched design requires the following tasks to be addressed by the COSPAL project:
- mimicking human movements to achieve an optimal manipulator control,
- investigation of heterogeneous and homogeneous multi-level network structures for associating percepts and actions,
- development of methods for incremental learning,
- development of methods for reinforcing context dependent purposes to the network after the bootstrapping phase,
- investigation of interfaces between associative networks and symbolic layers, and
- development of suitable symbolic methods for supervising network states.

We expect the COSPAL ACS design being capable of forming sufficiently complex models of the environment to perform autonomous actions, which would lead to fundamental progress in the field.

Appel à propositions

Data not available


Contribution de l’UE
Aucune donnée

Voir sur la carte

Coût total
Aucune donnée

Participants (3)