15 May 2024
Job Information
- Organisation/Company
CNRS- Department
Laboratoire d'analyse et d'architecture des systèmes- Research Field
Engineering
Computer science
Mathematics- Researcher Profile
First Stage Researcher (R1)- Country
France- Application Deadline
4 Jun 2024 - 23:59 (UTC)- Type of Contract
Temporary- Job Status
Full-time- Hours Per Week
35- Offer Starting Date
2 Sep 2024- Is the job funded through the EU Research Framework Programme?
Not funded by an EU programme- Is the Job related to staff position within a Research Infrastructure?
No
Offer Description
This Doctoral thesis is part of the NINSAR project (New ItiNerarieS for Agroecology using cooperative Robots), funded by the Agroecology and ICT PEPR (Priority Research Program and Equipment) and bringing together 17 French laboratories in Agroecology and Robotics.
The objective of the NINSAR project is to define new agroecological itineraries (new cultural practices, respectful of the environment and the soil, without chemicals), and to embody them in the collaborative execution of missions by a fleet of mobile outdoor robots.
The thesis will take place at LAAS-CNRS, Toulouse, from September 2024. The Institut Pascal (Clermont-Ferrand) and XLim (Limoges) laboratories will contribute to the supervision. Mobility is to be expected at the AgroTechnopole (INRAE Montoldre).
A function required for the collaborative execution of missions by a fleet of outdoor mobile agricultural robots concerns localization, including in the absence of GNSS signals: given a map of the environment (for instance, built up with natural landmarks), the robots localize themselves in an individual or concerted manner, e.g., by sharing their perception of common landmarks and/or by exploiting the fact that they perceive each other; when the map is no longer trustworthy, they establish a new one by running an individual or collaborative SLAM (Simultaneous Localization and Mapping).
A fleet of terrestrial robots in considered, equipped with proprioception and exteroceptive perception modalities, some of which can be controlled. The objective of the thesis is to develop opportunistic or active, individual or collaborative, localization and SLAM approaches, making it possible to overcome the scientific issues raised by the agricultural context: complexity and variability of natural environments, high level of precision and confidence required. in a wide range of situations, etc. Some methodological aspects addressed in the research team will be incorporated: modeling and inference in causal Bayesian networks; definition of (“greedy” vs “N-step-ahead”) policies enabling the optimization of an information-based criterion and operating in real time; joint learning of latent representation and optimal policy (prediction of agents and control of sensory modalities); etc.
The developed schemes will be systematically validated in simulation, then implemented on a fleet of robots hosted at the AgroTechnopole (INRAE Montoldre).
The innovative and multidisciplinary nature requires strong skills in all of the following disciplines: robotics, probabilistic modeling and inference, large-scale software development (software development infrastructures, etc.), perception, control, machine learning.
Requirements
- Research Field
- Engineering
- Education Level
- PhD or equivalent
- Research Field
- Computer science
- Education Level
- PhD or equivalent
- Research Field
- Mathematics
- Education Level
- PhD or equivalent
- Languages
- FRENCH
- Level
- Basic
- Research Field
- Engineering
- Years of Research Experience
- None
- Research Field
- Computer science
- Years of Research Experience
- None
- Research Field
- Mathematics
- Years of Research Experience
- None
Additional Information
Additional comments
Profile sought: Master's degree in Research (or equivalent), with proven skills in all of the following disciplines: robotics, probabilistic modeling and inference, large-scale software development (software development infrastructures, etc.), perception, control, machine learning. Other qualities sought: high motivation, autonomy, rigor, proactiveness, openness to multidisciplinary approaches, good oral/written communication in English.
The Curriculum Vitae file must also include: Master's transcripts, an example of written production (report, article, Master's thesis, etc.), if possible at least one letter of recommendation or reference. The cover letter must describe the candidate's interest in the position.
- Website for additional job details
https://emploi.cnrs.fr/Offres/Doctorant/UPR8001-PATDAN-006/Default.aspx
Work Location(s)
- Number of offers available
- 1
- Company/Institute
- Laboratoire d'analyse et d'architecture des systèmes
- Country
- France
- City
- TOULOUSE
- Geofield
Where to apply
- Website
https://emploi.cnrs.fr/Candidat/Offre/UPR8001-PATDAN-006/Candidater.aspx
Contact
- City
TOULOUSE- Website
http://www.laas.fr
STATUS: EXPIRED