Accéder directement au contenu

Jérémie Guiochet

4
Documents
Identifiants chercheurs

Présentation

Jérémie Guiochet is professor in computer science at University of Toulouse. His research activities take place at LAAS-CNRS. He received an Engineer degree in electronics and computer sciences at ENSEIRB, and a Ph.D. in 2003 from the INSA, Toulouse, France. He provides courses in Computer Science, Industrial Computing, Dependabilty and Risk Management. His research work is conducted in the LAAS-CNRS in the dependable computing and fault tolerance group (TSF) and relates to safety assessment, fault removal and tolerance in safety critical autonomous systems. <http://homepages.laas.fr/guiochet/> #### Risk analysis and safety argumentation for autonomous systems We investigate which system behavior models and human-system interaction models are appropriate for early risk analysis of autonomously-adapting systems (mostly robotics system). We particularly focus on modeling languages like UML associated with risk analysis methods. See [HAZOP-UML](https://www.laas.fr/projects/HAZOPUML/) page. We also also investigate how uncertainties could be modeled and managed in a develomment process or an safety argumentation (safety case), integrating formal probabilistic models as Markov and Bayesian networks, or belief theory. Other LAAS researchers :[Mohamed Kaaniche](http://homepages.laas.fr/kaaniche/), [David Powell](http://homepages.laas.fr/dpowell/), [Gilles Motet](http://homepages.laas.fr/gmotet) #### Defenses and tests for autonomous systems The counterpart of autonomous adaptation is the confidence that can be placed on the underlying mechanisms. In particular: a) what defenses can be provided as countermeasures against the threats introduced by autonomous adaptation? Our research on this theme focus on the safety of autonomous robot systems based on the use of safety monitors. See [SMOF](https://www.laas.fr/projects/smof) page. b) how to perform tests of autonomous systems, considering the infinate entry set, and that running hazardous scenarios is not possible ? We develop a method based on testing autonomous system in virtual words. Other LAAS researchers: [Hélène Waeselynck](http://homepages.laas.fr/waeselyn/), [David Powell](http://homepages.laas.fr/dpowell/), [Marc-Olivier Killijian](http://homepages.laas.fr/mkilliji/index.html), [Jean Arlat](http://homepages.laas.fr/arlat/), [Matthieu Roy](http://homepages.laas.fr/mroy/), [Felix Ingrand](http://homepages.laas.fr/felix), [Simon Lacroix](http://homepages.laas.fr/lacroix) #### Geo-Privacy risk analysis Specific methods and risk criteria should be developped to analyse risks in the geoprivacy domain. We particularly focus on methods for integrating quantitative estimation (coming from provable security) to qualitative analysis. Other LAAS researchers :[Marc-Olivier Killijian](http://homepages.laas.fr/mkilliji/index.html)

Publications

kevin-delmas
Image document

Out-Of-Distribution Detection Is Not All You Need

Joris Guérin , Kevin Delmas , Raul Sena Ferreira , Jérémie Guiochet
The 37th AAAI conference on artificial intelligence (2023), Feb 2023, Washington DC, United States
Communication dans un congrès hal-03870531v2
Image document

Unifying Evaluation of Machine Learning Safety Monitors

Joris Guérin , Raul Sena Ferreira , Kevin Delmas , Jérémie Guiochet
33rd IEEE International Symposium on Software Reliability Engineering (ISSRE 2022), Oct 2022, Charlotte, United States. ⟨10.1109/ISSRE55969.2022.00047⟩
Communication dans un congrès hal-03765273v1
Image document

Evaluation of Runtime Monitoring for UAV Emergency Landing

Joris Guerin , Kevin Delmas , Jérémie Guiochet
International Conference on Robotics and Automation (ICRA), May 2022, Philadelphia, United States
Communication dans un congrès hal-03600856v1
Image document

Certifying Emergency Landing for Safe Urban UAV

Joris Guérin , Kevin Delmas , Jérémie Guiochet
7th International Workshop on Safety and Security of Intelligent Vehicles (SSIV 2021) at IEEE/IFIP Intern. Conf. on Dependable Systems and Networks (DSN), Jun 2021, Taipei (virtual), Taiwan. ⟨10.1109/DSN-W52860.2021.00020⟩
Communication dans un congrès hal-03213534v1