Sensors are multiplying on machines, networks and living things. From the data produced and the symptoms observed as well as from verifications and tests, diagnosis aims to estimate the internal state of a “system” and to identify the nature and the cause of a failure, an anomaly or an illness. There are two main paradigms in the field of automatic diagnosis: model-based diagnosis and data-driven diagnosis.

This chair aims to analyze the transformations performed by model based and by data based diagnosis methods, deriving mutual benefits, and integrating them closely.

The first objective is to highlight and understand the correspondences that may exist between them and how they could synergize each other. 

The second objective is to be able to abstract up data classifiers and map them to symbolic or analytical models suitable for diagnosis reasoning, gaining better explainability and acceptability. 

Integration within ANITI program

This chair is anchored in the ANITI “Collaborative AI” research program as diagnosis, including in the broadest sense monitoring, anomaly detection, fault isolation and identification, prognosis and health management, is a task for which integrated human/AI systems show better performance. 

This chair contributes to several ANITI themes, in particular “Data & Anomalies”, “Explainability” and “Automated reasoning and decision making”.

Industrial partnership: Vitesco Technologies, Carl Levreau, CNES, ATOS, AIRBUS. The Application Areas defined by ANITI that are targeted by this chair are Transport/Mobility and Industry 4.0.

Education Topics: Logic theory of model-based diagnosisDiagnosis and diagnosability of discrete event systems,Fault indicators generation via structural analysis, Machine learning for diagnosis and supervision, Prognosis and Health ManagementBridging control and artificial intelligence theories for diagnosisEthics and integrity in science.

AI dissemination activities to the general publicPopularization talksMeetings in high schools, Female high school student’s awareness of AIAI-based escape game.

Projects of the chair

Programmes : IA acceptable, certifiable & collaborative
Thèmes : Raisonnement automatique et décision, explicabilité, données et anomalies

Porteur :
Louise Travé-Messuyes, DR CNRS, LAAS

Equipe de recherche :

Elodie Chanthery, co-chair, Assistant professor, LAAS-CNRS, INSA, Toulouse

Xavier Pucel, co-chair, Research engineer, ONERA, Toulouse 

Nathalie Barbosa Roa, co-chair, Data scientist and Big Data engineer, Vitesco Technologies, Toulouse

Audine Subias, Assistant professor, LAAS-CNRS, INSA, Toulouse

Yannick Pencolé, Research fellow CNRS, LAAS-CNRS, Toulouse 

Marie-Véronique Le Lann, Professor, LAAS-CNRS, INSA, Toulouse

Adrien Dorise, PhD student, LAAS-CNRS, CNES, Toulouse

Kevin Ducharlet, PhD student, LAAS-CNRS, Carl Levreau, Toulouse

Le Toan Duong, PhD student, LAAS-CNRS, Vitesco Technologies, Toulouse

Louis Goupil, PhD student, LAAS-CNRS, ATOS, Toulouse

Edgar Sepulveda, PhD student, LAAS-CNRS, Quantom, Toulouse

Alexandre Gaffet, PhD student, LAAS-CNRS, Vitesco Technologies, Toulouse

Amaury Vignolles, PhD student, LAAS-CNRS, Toulouse

Contact
louise@laas.fr

Site
http://homepages.laas.fr/louise