Post-doctoral research visit f - m in learning robotic skills with foundation models imitation learning and robot learning h/f

A propos d'Inria

Inria est l'institut national de recherche dédié aux sciences et technologies du numérique. Il emploie 2600 personnes. Ses 215 équipes-projets agiles, en général communes avec des partenaires académiques, impliquent plus de 3900 scientifiques pour relever les défis du numérique, souvent à l'interface d'autres disciplines. L'institut fait appel à de nombreux talents dans plus d'une quarantaine de métiers différents. 900 personnels d'appui à la recherche et à l'innovation contribuent à faire émerger et grandir des projets scientifiques ou entrepreneuriaux qui impactent le monde. Inria travaille avec de nombreuses entreprises et a accompagné la création de plus de 200 start-up. L'institut s'eorce ainsi de répondre aux enjeux de la transformation numérique de la science, de la société et de l'économie. Post-Doctoral Research Visit F/M in learning robotic skills with foundation models, imitation learning and robot learning
Le descriptif de l'offre ci-dessous est en Anglais
Type de contrat : CDD

Contrat renouvelable : Oui

Niveau de diplôme exigé : Thèse ou équivalent

Fonction : Post-Doctorant

Contexte et atouts du poste

This position is funded by the euROBIN Europeanproject (European Network of Excellence in ROBotics and AI), which involves 32 partners in Europe.

Our team is participating in one of the challenges of the project, so called "Personal Robotics challenge" where we want to develop the skills that robots need to helps humans in their tasks, such as opening doors, carrying small to medium heavy objects, navigate in a human environment, manipulate small objects, understanding natural language instructions and reasoning about possible plans. We will BE tackling the problem with two approaches : 1) teleoperation and imitation learning, i.e., showing to the robots how to solve the tasks, and acquiring demonstrations to train machine learning models; 2) generative AI.

The positionmay involve regular travels to the European partners of the project, in particular to Munich (DLR) and Karlsruhe (KIT), as well as participating in"hackatons" with the partners to implement and compare concrete ideas, and robotics competitions. In particular, two robotics demonstrations will take place in 2026 in Bruxellesand Wien (ICRA 2026).

Therecruted postdoc should stayuntil the end of the project (december 2026) and participate in the team's projects and activities. Extension of the contract is possible, on other similar projects of the team.

Mission confiée

The overall objective is todevelop research about teleoperation of human-like robots, whole-body teleoperation, imitation learning, andgenerative models for skills executionin concrete cases : whole-body manipulation, multi-contact motions, use of tools, manipulating objects with unknown weight, opening doors, shared autonomy The exact research topic will depend on the interest and the skills of the recruited researcher.

Most of the work will target the Tiago++ robot (2 arms + torso + wheeled base), but, when IT is relevant, we will extend IT to humanoid robots (Talos and G1). The codewill BE tested as often as possible on the real platforms.

The recruited person will BE in connection withSerena Ivaldi and Jean-Baptiste Mouret. The post-doctoral researcher will also help supervise the team's students working on robot learning and control.

Principales activités

The main objective is to develop and publish new algorithms that help to fulfillthe objectives of the euROBIN project. The post-doctoral researcher will BE actively involved in the day-to-day management of the tasks of Inria, present the work to the other partners, and perform experiments with the robots. He/she will also participate with the Inria team to robotics competitions and hackathons organized by the euROBIN project, and demonstrations of the robots' skills at the European Parliament and ICRA 2026.

Compétences

Ideal skills :whole-body control, C++ programming, machine learning, reinforcement learning, diffusion models, VLM/LLM

Required : good programming proficiency in Python or C++, knowledge of robotics (kinematics, dynamics, etc.) and machine learning.

Very good knowledge of English is a strong requirement (many interactions with the European partners).

Technical skills and knowledge :
- Whole-body control
- Machine learning methods
- Generative AI methods (diffusion, VLM, LLM)
- Python and C++ programming
- ROS middleware and associated tools (Rviz, MoveIt !, etc.)
- Linux and RTOS
- Code versioning and continuous integration (git)

Required soft skills :
- Rigour and intellectual honesty
- Curiosity and desire to learn
- Analytical mindset and abstraction skills
- Practical mindset and ability to develop robust and reliable solutions
- Autonomy and organizational skills
- Desire to work well
- Not afraid of challenging projects
- Love working in a multi-cultural environment
- Team player
- Good communication skills at work, and ability to report progress

Avantages
- Subsidized meals
- Partial reimbursement of public transport costs
- Leave : 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
- Possibility of teleworking (after 6 months of employment) and flexible organization of working hours
- Professional equipment available (videoconferencing, loan of computer equipment, etc.)
- Social, cultural and sports events and activities
- Access to vocational training
- Social security coverage

Rémunération

2788 € gross/month