The French National Research Institute for Agriculture, Food, and the Environment (INRAE) is a public research establishment under the dual authority of the Ministry of Agriculture and the Ministry of Research.
INRAE is recruiting researchers by open competition and offering permanent position.
It is a major player in research and innovation created on 1st of January 2020. INRAE is a research institute resulting from the merger of INRA and IRSTEA. It is a community of 12,000 people with more than 200 research units and 42 experimental units located throughout France.
The institute is among the world leaders in agricultural and food sciences, in plant and animal sciences, and is 11th in the world in ecology and environment. INRAE’s main goal is to be a key player in the transitions necessary to address major global challenges. In the face of the increase in population, climate change, scarcity of resources and decline in biodiversity, the institute develops solutions for multiperformance agriculture, high quality food and sustainable management of resources and ecosystems.
Work environment, missions and activities
The TSCF Research Unit at the INRAE Clermont-Ferrand Centre (https://www6.ara.inrae.fr/tscf/), has 60 agents. It develops new technologies for innovative agricultural equipment services, contributing to the ecological transition of agriculture. The unit is a member of the ImobS3 Labex (http://www.imobs3.uca.fr/index.php/fr/) and of the I-Site CAP 2025 (https://cap2025.fr/).
On the Unit teams, Romea (Robotics and Mobility for the Environment and Agriculture) is researching the development of robots that would operate in natural environments accurately, safely and repeatedly. The twenty-people team brings together multidisciplinary expertise to design perception and control algorithms, in order to provide robots with the versality required to carry out agricultural works, supporting the popularisation of agroecology principles. In particular, several robotic behaviours (such as trajectory or line tracking, target tracking, tools coordination, or the control of robots in formation...) have been developed within the framework of various collaborative projects. They made it possible to obtain generic results, in the field of control, data fusion, human / machine interaction and operational safety, applicable to different types of robots (modes of locomotion, size, mass).
These results have highlighted the need to improve, and even reconfigure, mobile robots’ behaviour, according to the task and the context. This would provide robots, in natural environments, with enhanced decision-making capabilities, in order to select and weight the most relevant perception and control approaches. The complexity of the interactions between the robot and its all-terrain environment makes it difficult to select and adjust deterministic control approaches. You will carry out researches in the field of AI aiming at increasing autonomy by endowing the robot with the capacity to decide on the types of perception and control algorithms to use depending on the situation. Such an adaptation is also understandable with respect to people interacting with the robot and thus includes the interpretation of human actions in order to increase the ergonomic robotic approaches for agriculture.
Some initial developments have shown the feasibility and relevance of using deep learning techniques to modify the parameters of low-speed perception / command algorithms. Your objective, in the short term, is to capitalise and extend this work, in order to be able to offer autonomous supervision tools, capable of selecting and managing the basic behaviours already developed and under development within the research team. Beyond the use of data provided by perception to feed control laws, your research work will aim to determine additional measures to increase performance, particularly with regards to the use of spatial data (humidity, weather, etc.), potentially available online, or via the use of enriched mapping, carried out during previous visits or from sensor networks.
In this sense, you will be fully part of the TSCF Unit project, whose objective is to develop integrated approaches for the autonomy, performance (agronomic and ecological), and safety of agricultural equipment. You will therefore help providing tools to democratise agroecology principles, whilst decreasing the workload and the hardship caused by agricultural work.
Training and skills
Candidates must have a PhD or equivalent.
A PhD in learning would be appreciated, as well as a significant experience in the field of robotics, preferably mobile.
Strong computer skills (programming languages, simulation software) and mathematics would be required, in order to develop algorithms making the robot adapt its behaviour depending on the context, with ad-hoc perception and control laws.
Curious and a team player are necessary qualities, with a keen practical sense and a strong interest for experimentation. Significant adaptability skills will be needed to immerse in current projects and lead the groups in which the team participates. We will expect the candidate to be dynamic and a driving force in proposing and contributing to building new projects and collaborations.
Candidates should have a good command of English and long-term international work experience. If you have not yet acquired this experience abroad, you will be strongly encouraged to do so after the first-year probationary period.
INRAE's life quality
By joining our teams, you benefit from:
- 30 days of annual leave + 15 days "Reduction of Working Time" (for a full time);
- parenting support: CESU childcare, leisure services;
- skills development systems: training, career advise;
- social support: advice and listening, social assistance and loans;
- holiday and leisure services: holiday vouchers, accommodation at preferential rates;
- sports and cultural activities;
- collective catering.