RASCALLI (Responsive Artificial Situated Cognitive Agents Living and Learning on the Internet) represent a growing class of cooperative agents that do not have a physical presence, but nevertheless are equipped with major ingredients of cognition including situated correlates of physical embodiment to become adaptive, cooperative and self improving in a certain environment (Internet) given certain tasks.
With RASCALLI we aim at artificial agents that are able to combine human and computer skills in such a way that both kinds of abilities can be optimally employed for the benefit of the human user.
RASCALLI is funded as a Specific Targeted Research Project under European Commission 6th FP with a budget around 1.6M euros. It started January 2006 and runs for 3 years. RASCALLI is coordinated by OFAI, Austria.
Contact: Atanas Kiryakov
Project Overview
The overall goal of the RASCALLI project is to develop an artificial cognitive system that allows human and computer skills to be combined in such a way that both abilities can be optimally employed for the benefit of the human user. We develop and implement a system platform and toolkit based on which responsive artificial situated cognitive agents, the RASCALLI, can be created and trained by the human user in order to perform certain tasks. Their cognitive system, knowledge and skills enable them to acquire and constantly improve their knowledge through the Web or through communication with people and other RASCALLI. To achieve this goal, RASCALLI have a built-in cognitive model and base knowledge about people, themes, Internet, time and communicat
The scientific objectives of the project concern the cognitive architectures used by Internet agents, in particular regarding memory and learning. There are a number of challenging technological objectives to be met:
- Cognitive architecture and modeling
- Perception and action
- Reasoning
- Learning
- Communication
- Platform inteion.gration and application development
- Evaluation
Ontotext’s Role
- How does symbolic reasoning interfere with DUAL?
- Could be two-layered approach, based on synchronization of two models
- Could be 100% DUAL-based
- What would be the scale of the data managed by:
- A single RASCALLA
- A server “hosting” multiple RASCALLI
- What KB visualization/editing/management tools are necessary?
- What Query modes are necessary for the KB?
- Will there be a RASCALLI software installed with the client?