Authors:
Nicolas Verstaevel
1
;
Christine Régis
2
;
Valérian Guivarch
2
;
Marie-Pierre Gleizes
2
and
Fabrice Robert
3
Affiliations:
1
Université Paul Sabatier and Sogeti High Tech, France
;
2
Université Paul Sabatier, France
;
3
Sogeti High Tech, France
Keyword(s):
Ambient Intelligence, Self-Organizing Systems, Machine Learning, Adaptive Multi-Agent Systems, Robot and Multi-Robot Systems.
Related
Ontology
Subjects/Areas/Topics:
Agents
;
Ambient Intelligence
;
Artificial Intelligence
;
Artificial Intelligence and Decision Support Systems
;
Computational Intelligence
;
Distributed and Mobile Software Systems
;
Enterprise Information Systems
;
Evolutionary Computing
;
Knowledge Discovery and Information Retrieval
;
Knowledge Engineering and Ontology Development
;
Knowledge-Based Systems
;
Machine Learning
;
Multi-Agent Systems
;
Robot and Multi-Robot Systems
;
Self Organizing Systems
;
Soft Computing
;
Software Engineering
;
Symbolic Systems
Abstract:
Our work focuses on Extreme Sensitive Robotic that is on multi-robot applications that are in strong interaction with humans and their integration in a highly connected world. Because human-robots interactions have to be as natural as possible, we propose an approach where robots Learn from Demonstrations, memorize contexts of learning and self-organize their parts to adapt themselves to new contexts. To deal with Extreme Sensitive Robotic, we propose to use both an Adaptive Multi-Agent System (AMAS) approach and a Context-Learning pattern in order to build a multi-agent system ALEX (Adaptive Learner by Experiments) for contextual learning from demonstrations.