Jérémie Guiochet

Jérémie Guiochet
French National Centre for Scientific Research | CNRS · Laboratory for Analysis and Architecture of Systems (LAAS)

Professor

About

82
Publications
71,352
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,391
Citations
Introduction
Jérémie Guiochet currently works at the LAAS - CNRS, University of Toulouse. Jérémie does research in Safety Engineering, Dependability, Risk Management, and Safety Critical Autonomous Systems Most of my plublications can be downloaded from my web page: http://homepages.laas.fr/guiochet
Additional affiliations
September 2004 - present
Paul Sabatier University - Toulouse III
Position
  • Professor (Associate)
Description
  • Research at LAAS-CNRS, Toulouse, France
September 2002 - September 2004
Université Toulouse  II - Jean Jaurès
Position
  • Lecturer
September 1999 - June 2003
Institut National des Sciences Appliquées de Toulouse
Position
  • Lecturer
Education
September 1999 - September 2003
Institut National des Sciences Appliquées de Toulouse
Field of study
  • Computer science & robotics
September 1998 - July 1999
Paul Sabatier University - Toulouse III
Field of study
  • Embedded Systems
September 1995 - July 1998

Publications

Publications (82)
Conference Paper
Testing perception functions for safety-critical autonomous systems is a crucial task. The reason is that accurate ML models applied in computer vision tasks still fail in scenarios where humans perform well. Out-of-distribution (OOD) images are usually a source of such failures. For this reason, literature usually applies data augmentation techniq...
Preprint
With the increasing use of Machine Learning (ML) in critical autonomous systems, runtime monitors have been developed to detect prediction errors and keep the system in a safe state during operations. Monitors have been proposed for different applications involving diverse perception tasks and ML models, and specific evaluation procedures and metri...
Preprint
Full-text available
To certify UAV operations in populated areas, risk mitigation strategies -- such as Emergency Landing (EL) -- must be in place to account for potential failures. EL aims at reducing ground risk by finding safe landing areas using on-board sensors. The first contribution of this paper is to present a new EL approach, in line with safety requirements...
Preprint
Full-text available
High-accurate machine learning (ML) image classifiers cannot guarantee that they will not fail at operation. Thus, their deployment in safety-critical applications such as autonomous vehicles is still an open issue. The use of fault tolerance mechanisms such as safety monitors is a promising direction to keep the system in a safe state despite erro...
Chapter
Full-text available
Structured safety argument based on graphical representations such as GSN (Goal Structuring Notation) are used to justify the certification of critical systems. However, such approaches do not deal with uncertainties that might affect the merits of arguments. In the recent past, some authors proposed to model the confidence in such arguments using...
Preprint
Full-text available
Unmanned Aerial Vehicles (UAVs) have the potential to be used for many applications in urban environments. However, allowing UAVs to fly above densely populated areas raises concerns regarding safety. One of the main safety issues is the possibility for a failure to cause the loss of navigation capabilities, which can result in the UAV falling/land...
Chapter
In this paper, we present an approach to test underwater robots with a mission perspective. We propose five classes of oracle mission properties, used to perform test verification and evaluation: mission phases, time, energy, safety and localization. We study how these properties can be used, using data from the generated logs and analyzing the set...
Chapter
Full-text available
Structured safety arguments are widely applied in critical systems to demonstrate their safety and other attributes. Graphical formalisms such as Goal Structuring Notation (GSN) are used to represent these argument structures. However, they do not take into account the uncertainty that may exist in parts of these arguments. To address this issue, s...
Conference Paper
Full-text available
In this paper, we present an approach to test underwater robots with a mission perspective. We propose five classes of oracle mission properties, used to perform test verification and evaluation: mission phases, time, energy, safety and localization. We study how these properties can be used, using data from the generated logs and analyzing the set...
Conference Paper
Full-text available
Structured safety arguments are widely applied in critical systems to demonstrate their safety and other attributes. Graphical formalisms such as Goal Structuring Notation (GSN) are used to represent these argument structures. However, they do not take into account the uncertainty that may exist in parts of these arguments. To address this issue, s...
Article
Full-text available
Testing autonomous robots typically requires expensive test campaigns in the field. To alleviate them, a promising approach is to perform intensive tests in virtual environments. This paper presents an industrial case study on the feasibility and effectiveness of such an approach. The subject system is Oz, an agriculture robot for autonomous weedin...
Conference Paper
Full-text available
Testing autonomous robots requires test campaigns in the field that could be expensive, risky for the system and its environment, or even impossible to set up. To cope with these limits, an expanding approach is to perform tests in virtual environments using simulators. Due to the non-determinism of the robot control and simulation execution, a tes...
Article
Full-text available
Please cite this article as: J. Friginal , S. Gambs, J. Guiochet, M.-O. Killijian, Towards privacy-driven design of a dynamic carpooling system, Pervasive and Mobile Computing (2014), http://dx. Abstract Dynamic carpooling (also known as instant or ad-hoc ridesharing) is a service that arranges one-time shared rides on very short notice. This type...
Article
Full-text available
Safety arguments, also called safety cases, are commonly used to demonstrate that adequate efforts have been made to achieve safety goals. Assessing the confidence of such arguments and decision-making is usually done manually and is heavily dependent on subjective expertise. Therefore, there is an urgent need for an approach that can assess confid...
Article
Full-text available
Railway standard EN50129 clarifies the safety acceptance conditions of safety-related electronic systems for signalling. It requires using a structured argumentation, named Safety Case, to present the fulfilment of these conditions. As guidance for building the Safety Case, this standard provides the structure of high-level safety objectives and th...
Conference Paper
Full-text available
Confidence in safety critical systems is often justified by safety arguments. The excessive complexity of systems nowadays introduces more uncertainties for the arguments reviewing. This paper proposes a framework to support the argumentation assessment based on experts’ decision and confidence in the decision for the lowest level claims of the arg...
Article
Full-text available
Developing advanced robotics applications is now facing the safety issue for users, the environment, and the robot itself, which is a main limitation for their deployment in real life. This safety could be justified by the use of dependability techniques as it is done in other safety-critical applications. However, due to specific robotic propertie...
Conference Paper
Full-text available
Safety-critical autonomous systems, like robots working in collaboration with humans, are about to be used in diverse environments such as industry but also public spaces or hospitals. Those systems evolve in complex and dynamic environments and are exposed to a wide variety of hazards. Several techniques may be used to ensure that their misbehavio...
Article
Full-text available
Safety-critical systems with decisional abilities, such as autonomous robots, are about to enter our everyday life. Nevertheless, confidence in their behavior is still limited, particularly regarding safety. Considering the variety of hazards that can affect these systems, many techniques might be used to increase their safety. Among them, active s...
Conference Paper
Full-text available
Structured arguments are commonly used to communicate to stakeholders that safety, security or other attributes of a system are achieved. Due to the growing complexity of systems, more uncertainties appear and the confidence in arguments tends to be less justifiable by reviewing. In this paper, we propose a quantitative method to assess the confide...
Conference Paper
Full-text available
Software applications dependability is frequently assessed through degrees of constraints imposed on development activities. The statement of achieving these constraints are documented in safety arguments, often known as safety cases. However, such approach raises several questions. How ensuring that these objectives are actually effective and meet...
Article
Full-text available
New safety critical systems are about to appear in our everyday life: advanced robots able to interact with humans and perform tasks at home, in hospitals, or at work. A hazardous behavior of those systems, induced by failures or extreme environment conditions, may lead to catastrophic consequences. Well-known risk analysis methods used in other cr...
Book
This book constitutes the refereed proceedings of four workshops co-located with SAFECOMP 2016, the 35th International Conference on Computer Safety, Reliability, and Security, held in Trondheim, Norway, in September 2016. The 30 revised full papers presented together with 4 short and 5 invited papers were carefully reviewed and selected from numer...
Book
This book constitutes the refereed proceedings of the 35th International Conference on Computer Safety, Reliability, and Security, SAFECOMP 2016, held in Trondheim, Norway, in September 2016. The 24 revised full papers presented were carefully reviewed and selected from 71 submissions. The papers are organized in topical sections on fault injection...
Conference Paper
Full-text available
Building a safety case is a common approach to make expert judgement explicit about safety of a system. The issue of confidence in such argumentation is still an open research field. Providing quantitative estimation of confidence is an interesting approach to manage complexity of arguments. This paper explores the main current approaches, and prop...
Article
Full-text available
Ensuring that safety requirements are respected is a critical issue for the deployment of hazardous and complex reactive systems. We consider a separate safety channel, called a monitor, that is able to partially observe the system and to trigger safety-ensuring actuations. We address the issue of correctly specifying such a monitor with respect to...
Article
Full-text available
Dynamic carpooling (also known as instant or ad-hoc ridesharing) is a service that arranges one-time shared rides on very short notice. This type of carpooling generally makes use of three recent technological advances: (i) Navigation devices to determine a driver’s route and arrange the shared ride; (ii) smartphones for a traveller to request a ri...
Conference Paper
Full-text available
Mobiquitous systems are gaining more and more weight in our daily lives. They are becoming a reality from our home and work to our leisure. The use of Location-Based Services (LBS) in these systems is increasingly demanded by users. Yet, while on one hand they enable people to be more "connected", on the other hand, they may expose people to seriou...
Conference Paper
Full-text available
Autonomous systems operating in the vicinity of humans are critical in that they potentially harm humans. As the complexity of autonomous system software makes the zero-fault objective hardly attainable, we adopt a fault-tolerance approach. We consider a separate safety channel, called a monitor, that is able to partially observe the system and to...
Conference Paper
Full-text available
The aim of robustness testing is to characterize the behavior of a system in the presence of erroneous or stressful input conditions. It is a well-established approach in the dependability community, which has a long tradition of testing based on fault injection. However, a recurring problem is the insufficient documentation of experiments, which m...
Article
Full-text available
Robotic systems have to cope with various execution environments while guaranteeing safety, and in particular when they interact with humans during rehabilitation tasks. These systems are often critical since their failure can lead to human injury or even death. However, such systems are difficult to validate due to their high complexity and the fa...
Article
Full-text available
La théorie du contrôle par supervision (Supervisory Control Theory, SCT), ou synthèse de superviseur, a été inventée en 1987 par P.Ramadge et W.M.Wonham. La SCT s'appuie sur la théorie des langages, et a recours aux machines à état. Elle vise à synthétiser un superviseur correct par construction, qui veille à ce que le comportement d'un système à é...
Book
This book constitutes the refereed proceedings of the 32nd International Conference on Computer Safety, Reliability, and Security, SAFECOMP 2013, held in Toulouse, France, in September 2013. The 20 revised full papers presented together with 5 practical experience reports were carefully reviewed and selected from more than 88 submissions. The paper...
Conference Paper
Full-text available
A systematic process for eliciting safety trigger conditions is presented. Starting from a risk analysis of the monitored system, critical transitions to catastrophic system states are identified and handled in order to specify safety margins on them. The conditions for existence of such safety margins are given and an alternative solution is propo...
Conference Paper
Full-text available
— Considering the new threats in medical robotics due to increasing complexity and autonomy, and the absence of dedicated standards, we present in this paper how we carried safety analyses for a rehabilitation robot. We combine several standards and research works for a safe design and to construct a safety case for regulatory bodies. We point out...
Conference Paper
Full-text available
We present the AMORES project, which aims to provide an architecture for the provision of privacy preserving and resilient collaborative services in "mobiquitous" (i.e., mobile and ubiquitous) systems. The project is built around three use-cases from the area of public transportation: (1) dynamic carpooling, (2) real-time computation of multimodal...
Article
This paper aims to present the MIRAS project: a multimodal interactive robot developed to provide assistance in strolling for people suffering from locomotion troubles. The first part of this paper summarizes goals and expected impacts of the project. Each work package is then detailed: description of use-cases and associated multimodal functions,...
Conference Paper
Full-text available
Safety is now a major concern in many computer based systems and more particularly for autonomous systems such as service robots in physical contact with humans. The traditional approach to analyze the safety of such systems is to use risk assessment methods based on models of system structure, or system behavior. Unfortunately, such models are har...
Conference Paper
Full-text available
Safety is a major concern for robots that interact physically with humans. We propose a risk analysis method based on deviation analysis of system usage scenarios that allows the identification of major risks. Scenarios are described with the common Unified Modeling Language (UML), and risk analysis is performed with the guideword-based collaborati...
Article
Full-text available
Les systèmes informatiques réalisent des tâches de plus en plus complexes, dont certaines peuvent mettre l’humain en danger. L’inévitable présence de fautes résiduelles de développement, de fautes physiques ou d’interaction activées pendant la vie opérationnelle, conduit à l’utilisation de systèmes indépendants de surveillance de la sécurité pour p...
Article
Full-text available
Robotic systems have to carry out more and more complex tasks, including ones where humans can be endangered. Residual design faults in such systems, as well as the inevitability of physical faults and interac- tion faults during operation, motivate the use of safety monitors to prevent catastrophic failures. In this paper, we consider the design o...
Conference Paper
Full-text available
Autonomous robots offer alluring perspectives in numerous application domains: space rovers, satellites, medical assistants, tour guides, etc. However, a severe lack of trust in their dependability greatly reduces their possible usage. In particular, autonomous systems make extensive use of decisional mechanisms that are able to take complex and ad...
Article
Full-text available
L'utilisation de systèmes robotiques dans le domaine médical,initiée il y a quelques années, pose le problème de la sécurité ausein d'un environnement où l'homme est très présent. La complexitéde tels systèmes et le transfert de responsabilités du chirurgienvers le robot conduisent les concepteurs à intégrer dans leursétudes des exigences de sûreté...
Conference Paper
Full-text available
Planners are central to the notion of complex autonomous systems. They provide the flexibility that autonomous systems need to be able to operate unattended in an unknown and dynamically-changing environment. However, they are notoriously hard to validate. This paper reports an investigation of how redundant, diversified models can be used as a com...
Article
Full-text available
L' objectif de cet article est de présenter un profil UML permettant la construction de composants logiciels multivues. Un composant multivues est une extension de la notion de composant UML permettant de stocker et restituer de l' information en fonction du profil de l' utilisateur (point de vue), et offrant la possibilité de changement dynamique...