>>

PhD proposal Neurocybernetics team

The NeuroCybernetics Team of ETIS Laboratory University of Cergy-Pontoise, France, is looking for one outstanding and enthusiastic PhD Candidate to work in the area of NeuroCognitive Robotics for 3-years.

Subject

As part of this thesis we want to develop for a robot a neural architecture constituted of the motor cortex, the parietal cortex and the basal ganglia for learning simple prehensive tasks (e.g. pick and drop) and for thinking spatially relative to different reference frames (eye, hand, objet orientation). The model will be tested on our humanoid robot TINO using visual, tactile and proprioceptive information.

  • Neural Model for Spatial Coordinate Transformation
  • Habit Learning and Action Generalization/Selection & Serialization
  • Learning of a Body Schema from Visuo-, Tactile-, and Proprioceptive Integration

Requirements

The successful applicant is expected to have a strong background in computer sciences or mechanical engineering or electronic engineering or equivalent.

The ideal candidate has also some of the desired qualifications/skills:

  • experience in artificial neural networks or neurocomputational model of the brain.
  • robotics, machine learning and C programming
  • strong proactive attitude and problem solving capabilities
  • team working

Contacts

Interested applicants should be sent by replying to this email to philippe.gaussier@ensea.fr, alexandre.pitti@u-cergy.fr until 24 May 2017 and should include:

  • a detailed CV;
  • a brief statement about research interests and motivation to join the project, and
  • the name and contact of 2 references.

References

De Rengervé, A., Andry, P., & Gaussier, P. (2015). Online learning and control of attraction ponds for the development of sensorimotor control strategies. Cybernetics, 109 (2), 255-274.

Mahé, S., Braud, R. Gaussier, P., Quoy, M. and Pitti, A. (2015). Exploit the gain modulation mechanism in the application of parieto-motor neurons to visuomotor transformations and to the incorporated simulation. Neural networks, 62: 102-111.

Pitti A., Gaussier P. & Quoy M. (2017) Incremental optimization of free energy for recurrent neural networks (INFERNO). PLoS ONE 12 (3): e0173684. Doi: 10.1371 / journal.pone.0173684

Go back