Researcher on Deep and Reinforcement Learning for Robotics

Starting Date: February 1st, 2020.
Funding: The H2020 ICT SPRING Project
Contact Point
: Xavier Alameda-Pineda
Duration: From 2 and up to 4 years.
To applyhttps://jobs.inria.fr/public/classic/fr/offres/2019-02083

General Context: SPRING – Socially Pertinent Robots in Gerontological Healthcare – is a 4-year R&D project fully funded by the European Comission under the H2020 framework. SPRING aims to develop socially assistive robots with the capacity of performing multi-person interactions and open-domain dialogue. The scientific objective of SPRING is to develop a novel paradigm and novel concept of socially-aware robots, and to conceive innovative methods and algorithms for computer vision, audio processing, sensor-based control, and spoken dialog systems based on modern statistical- and deep-learning to ground the required social robot skills. The technological objective of SPRING is to create and launch a brand new generation of robots that are flexible enough to adapt to the needs of the users, and not the other way around. The experimental objective of SPRING is twofold: to validate the technology based on HRI experiments in a gerontology hospital, and to assess its acceptability by patients and medical staff.

The project is coordinated by the Perception team at Inria Grenoble and gathers academic and industrial partners in France (Inria, ERM Automatismes Industriels, Assistance Public Hôpitaux de Paris), Italy (Università degli Study di Trento), Czech Republic (České Vysoké Učenı́ Technické v Praze), UK (Heriot-Watt University), Israel (Bar-Ilan University), and Spain (PAL Robotics). Frequent travel to visit partners is required (up to 5 times a year).

Mission: The Perception team offers a senior postdoc position to work in the field of multimodal learning for human robot interaction. More precisely, the objective is to learn robot behavior in human-robot interaction scenarios based on robot-motor feedback and on visual and audio data gathered with cameras and microphones mounted onto a robotic head. Emphasis will be put on learning social interactions between the robot and a group of people and on developing novel methodological concepts and practical solutions based on deep and reinforcement learning.

Main Activities:

  • Conceive new learning methods, models and algorithms suitable for the role of Inria in the SPRING consortium.
  • Keep updated with the state-of-the-art and inform the SPRING team about relevant publications.
  • Daily supervision of the development of software prototypes, experimental validation and publication writing.

Sought Expertise: The candidates should have strong expertise and a very good publication record in at least two out of the following topics: machine learning, computer vision, audio signal processing. Moreover, they should have excellent written- and oral scientific communication skills. Senior postdoc candidates (2-3 years of experience after the PhD) will be preferred but junior postdoc candidates (0-1 year of experience) with strong CVs are encouraged to apply as well. The recruited researcher will work in close collaboration with the Perception team members (two senior researchers, 4-5 PhD students and three development engineers) and with the SPRING partners.