Post-doctoral offers
- Postdoc position - Diverse and constrained test cases generation for autonomous agricultural robots
Postdoc position - Diverse and constrained test cases generation for autonomous agricultural robots
Reference : UPR8001-JERGUI-003
Date of publication : 30 March 2023
Type of Contract : FTC Scientist
Contract Period : 12 months
Expected date of employment : 1 June 2023
Proportion of work : Full time
Remuneration : 3000 (gross salary)
Desired level of education : PhD
Missions
Field-testing is costly and time-consuming, hence, simulation-based testing is becoming more and more important to validate autonomous systems. Since autonomous systems can be deployed in diverse environments, a significant amount of diversified test cases has to be created. TAF (Testing Automation Framework) is a test generation tool we developed at LAAS to serve this purpose {https://www.laas.fr/projects/taf/}. It produces the test cases from a data model expressed in XML that specifies the virtual environments of interest, and generates diverse test cases by combining random sampling with the use of a solver (SMT). This first prototype is a proof of concept with strong limitations (in terms of expressiveness, performances, etc), but has already proved to be efficient in several industrial case-studies, and even been integrated in test case generation algorithms such as pair-wise testing.
The objective of this postdoctoral position is to extend this approach, to develop a complete loop: test case generation, test selection, execution of the test, analysis of the test, and based and the test results, be able to automatically launch a new test case generation. Such a complete loop could be based on heuristics-based approaches (e.g., genetic algorithms), or on data-based algorithms (e.g., machine learning).
This research is part of a french national project, GEOSUR, funded by the PIA4 Investment Program for the Future (Acceleration strategy "sustainable agricultural systems and agricultural equipments contributing to the ecological transition"). GEOSUR aims to develop multi-sensor geopositioning systems for outdoor agricultural robots, as well as methods and means of their certification.
One of the project workpackages is focusing on test case generation at two different levels : test cases for localisation functions (based on GNSS), and test cases at system level for complete robotic functions (e.g., geofencing). The proposed test case generation approach developed by the postdoc will be directly applied in theses two contexts. The postdoc will be also in charge of managing one task of the workpackage, interact with all the partners of the project, and develop new collaborations for further projects.
Activities
The successful candidate will contribute to the research developed in the team and will be involved in various research-related activities:
- co-advising of PhD and MSc students,
- participation to collaborative projects,
- preparation and submission of paper to international conferences and journals
- attendance to scientific events, presentation of the work and networking
- review of papers for conference and journals.
Moreover, the candidate will be encouraged to apply to academic positions. We commit to provide mentoring in the preparation of the applications during the postdoc.
Skills
Computer science, Soft skills
Work Context
About TSF team at LAAS-CNRS: TSF is a leading research team in the area of dependable and secure computing. The team has 30+ members, including CNRS researchers, faculty members, postdocs and PhD students. The research addresses a wide spectrum of computing systems (critical embedded systems, IoT, cloud services, telephony, web, social networks, energy distribution, …). It develops design and assessment methods against the threats faced by the systems, like physical faults, software development faults, or cyberattacks. The team members work in collaborative projects with academic as well as industrial partners. They are deeply involved in service activities for the international community, serving on the steering and organization committees of major dependability conferences (DSN, ISSRE, Safecomp), and on the editorial boards of international journals (IEEE Transactions on Reliability, Software Testing Verification & Reliability, Empirical Software Engineering).
The work will be supervised by Hélène Waeselynck and Jérémie Guiochet.
> Apply on CNRS Job Portal.
Application Deadline : 24 April 2023
Applications should contain a cover letter, curriculum vitae, and a list of publications. Additionally, please include your three most important papers. Your cover letter should discuss your motivation and qualification for the position. Up to two recommendation letters would also be appreciated.
Recruitment dates could be discussed, the position will be closed when a recruitment will be done.
Engineer or doctor in electronics and embedded systems M/F: Study and realization of a connected sole device allowing the measurement of a biomechanical index for walking stability analysis
Duration of the contract: 24 months
Date of hiring: from March 2023 (flexibility can be granted depending on the availability of the candidate)
Contacts/advisors: Eric Campo, eric.campo@laas.fr, Phone: +33561337961 ; Damien Brulin, dbrulin@laas.fr, Phone: +33561336951
MISSIONS
Postural balance is an essential sensorimotor function that is ensured by a particular position of the body segments in relation to each other at a given time. To ensure balanced walking, the body relies on orientation and stabilisation. Disruption of any of these properties can create a loss of postural reference and thus instability and can lead to a fall. Thus, the understanding and measurement of locomotion indicators (posture, balance) would make it possible to offer better support and monitoring of people to adapte and optimise rehabilitation or even risk prevention.
A team of researchers from the LAAS-CNRS and the IBHGC has initiated a study to propose concrete metrics to quantify instability during locomotion by combining complementary biomechanical and robotic approaches. The work entrusted to the recruited person will concern the study of a connected device that will take the form of an instrumented insole whose measurement accuracy will be evaluated in real time and whose proof of concept will be validated.
More specifically, the aim will be to design a portable prototype capable of acquiring the input data required to calculate the metrics under acceptability constraints for clinicians and users. The electronics will be based on an architecture composed of sensors distributed at strategic locations on the foot, a processor for the capture and first-level data processing, a BLE-type radio frequency communication and a rechargeable battery. The study of the integration of these microelectronic components will be necessary in order to ensure an optimal comfort allowing to eliminate any possible bias during the wearing of the sole and the capture of the measurements during the experiments.
This work will be done in collaboration with a PhD student who will be recruited in the field of biomechanics within the S4M team and GEPETTO team at LAAS-CNRS.
ACTIVITIES
- Define the specifications of the device (choice of components, integration architecture, measurement functions, indices, precision, frequency, etc.). These specifications will be based on a state of the art of the literature on balance and posture measurement devices.
- Design specific insoles: a first light structure removable prototype on a shoe (orthesis), a second prototype integrated in a comfort insole including sensors at strategic points of plantar pressure. This design will be able to take advantage of the previous work of the research teams involved in the project.
- To carry out the electronic integration of the sensors and a first algorithm for real-time measurements.
- Evaluate the sole in comparison with the force plate data (calibration process, characterisation of hysteresis, etc.) and the synchronisation of the data with the sensors.
- Evaluate the accuracy and performance of the device (distinction between stable and unstable walking) from data collected on a treadmill, by volunteers, in comparison with a reference device of the motion capture type
SKILLS
- Post-doc in electronics/instrumentation or Engineer with a background in electronics and embedded systems
- Skills in electronics, embedded systems, instrumentation, integration, embedded computing optimization
- Enthusiastic and enterprising with a sense of results, teamwork, rigorous, serious and autonomous
- Ability to work orally and in writing in French and English
References
[1] Massion J. Postural control system. Curr Opin Neurobiol 1994 ; 4 : 877–87.
[2] Winter D. Human balance and posture control during standing and walking. Gait Posture 1995 ; 3 : 193–214.
[3] Bailly FF, Carpentier J, Pinet B, Souères P, Watier B, Soueres P, et al. A Mechanical Descriptor of Human Locomotion and its Application to Multi-Contact Walking in Humanoids. Proc. IEEE RAS EMBS Int. Conf. Biomed. Robot. Biomechatronics. 2018.
[4] Pickle NT, Shearin SM, Fey NP. Dynamic neural network approach to targeted balance assessment of individuals with and without neurological disease during non-steady-state locomotion. 2019;8:1–9.
[5] Piau A, Charlon Y, Campo E, Vellas B, Nourhashemi F. A Smart Insole to Promote Healthy Aging for Frail Elderly Individuals: Specifications, Design, and Preliminary Results. JMIR Rehabil. Assist. Technol. 2015.
[6] Charlon Y, Campo E, Brulin D. Design and evaluation of a smart insole: Application for continuous monitoring of frail people at home. Expert Syst. Appl. 2018;95:57–71.
Read and apply on CNRS Job Portal.