Cooperative agents to track learner’s cognitive gap

Abstract

This paper presents the earlier results of the CMOS project including an embedded multi-agents ITS to efficiently help the learner faced with troubleshooting maintenance tasks. This environment carry on dedicated responses for aeronautical training sessions according to a three-step principle: first «introduce», next «convince» and at least «get to do». We emphasize on two main characteristics: a real-time full simulation of the technical domain, and it works with an tutoring multi-agents architecture, ASITS. ASITS is supplied with reactive and cognitive agents to track the learner performance, detect inherent negative effects (the learner’s "cognitive gaps"), and as a feedback issue, to identify some deficiencies that current training simulator lack. Therefore, as measuring gap values with quantitative rules keeps sometimes hazardous, the concept of simulation has to be extended to a Qualitative Simulation approach.