PhD Position F/M Artificial intelligence for trajectory prediction in robotic teleoperation

Contract type : Fixed-term contract

Level of qualifications required : Graduate degree or equivalent

Fonction : PhD Position

Level of experience : Recently graduated

Context

Context

We are collaborating with the French Defense Innovation Agency (AID) to help teleoperating robots (mobile manipulators type). In this project, we use artificial intelligence to predict at each moment the trajectory that an expert would have followed in the current situation. We plan to display it as a suggestion to the operator and thus help them carry out their tasks.
 
 
 

 

Assignment

Objective

Our objective is to exploit artificial intelligence algorithms to facilitate the use of robots in direct tele-operation by non-experts. Our main idea is to use a set of demonstrations to guide piloting by non-experts. Guidance (the exploitation of expert suggestions) itself will be considered in different ways, in particular via visual suggestions or shared control.

Approach

This thesis focuses on the development of new artificial intelligence algorithms to predict the trajectories of experts as accurately as possible. In particular, we will be interested in:

  • evaluating the epistemic uncertainty of the prediction model
  • the exploitating the context (obstacles) and the constraints of robotics (kinematic constraints, dynamics, etc.) to improve the prediction
  • ensure the safety of suggested trajectories

Main activities

Main activities:
  • carry out a complete state of the art of the methods relevant to the project
  • design new artificial intelligence algorithms
  • implement algorithms in Pytorch test these algorithms in simulation then on the lab's Tiago++ robot
  • participate in the evaluation of the suggestion system (in collaboration with an engineer), using user studies

Skills

Technical skills and level required:
  • very good knowledge of machine learning algorithms, particularly supervised learning
  • very good knowledge of Python and the Pytorch library
  • knowledge of the basics of robotics will be useful (but not essential)
Languages: 
  • English is the main language of the team. 
  • French is not required.
 
 
 

 

Benefits package

  • Restauration subventionnée
  • Transports publics remboursés partiellement
  • Congés: 7 semaines de congés annuels + 10 jours de RTT (base temps plein) + possibilité d'autorisations d'absence exceptionnelle (ex : enfants malades, déménagement)
  • Possibilité de télétravail (après 6 mois d'ancienneté) et aménagement du temps de travail
  • Équipements professionnels à disposition (visioconférence, prêts de matériels informatiques, etc.)
  • Prestations sociales, culturelles et sportives (Association de gestion des œuvres sociales d'Inria)
  • Accès à la formation professionnelle
  • Sécurité sociale

Remuneration

2100€ brut/mois (1ère année)

2200€ brut/mois (2ème année)

2300€ brut/mois (3ème année)