POST-DOCTORAL POSITION - Mobile robot learning with minimal supervision

In the framework of the research project “Innovative systems and services for transport and production” IDEX/I-SITE CAP 20-25 (Challenge 2) and the LabEx IMobS3, and thanks to a FrenchTech chair program, a postdoctoral position is proposed for highly motivated candidates interested in computer vision and mobile robots.

Subject
Mobile robot learning with minimal supervision

Context of the project
This postdoc is funded through the FrenchTech/I-SITE CAP 20-25 Chaire d’Excellence program. The candidate will be joining the Image, Perception Systems and Robotics group of Institute Pascal which has long experience in computer vision and mobile robots. This research will be conducted in the context of an ongoing collaboration between Institut Pascal and Prof. Jochen Triesch from the Frankfurt Institute for Advanced Studies (FIAS).

Scientific project and objectives
In recent years, the combination of reinforcement learning and deep neural networks has lead to impressive results such as computers outperforming humans in certain games (Mnih et al., 2015, Silver et al., 2016) and it has shown promising results in robotic tasks when some priors are available (Lilicrap et al. 2015, Finn et al. 2016). However, learning complex tasks for mobile manipulation robots without strong priors remains a challenge since only very specific behaviors may lead to any rewards. Discovering these behaviors by exploring the consequences of random movements is extremely improbable. This suggests that the learning process cannot rely on random exploration but must be structured intelligently.

We have recently proposed a new deep reinforcement learning framework to address this problem in the context of learning visuomotor tasks (de La Bourdonnaye et al. 2017, 2018). We have considered an object reaching task on a robotic platform comprising an active binocular vision system and a robot arm. The main contribution of this framework was to demonstrate stage-wise sensorimotor learning using only miminal supervision. In particular, no forward/inverse kinematics, pre-trained visual modules, expert knowledge, nor calibration parameters were used. Nevertheless, by following a stage-wise learning regime, where difficult skills are learned on top of simpler ones, the complex object touching skill was learned quickly. In this project, we propose to extend this framework of learning with minimal supervision to the context of mobile robots. The goal is to develop learning algorithms for mobile robots allowing them to autonomously learn how to approach, follow, and manipulate objects without prior knowledge of their kinematics or dynamics or any pre-trained visual modules.

Requirements

  • PhD in Computer Science, Machine Learning, Robotics or other relevant subject
  • Experience with (deep) Reinforcement Learning and/or Computer Vision are highly desirable
  • Strong programming skills (C/C++, Python)
  • Solid analytical ability
  • Good spoken and written English
  • High motivation

References
De La Bourdonnaye, F., Teulière, C., Chateau, T., & Triesch, J. (2017, May). Learning of binocular fixations using anomaly detection with deep reinforcement learning. In IJCNN 2017 (pp. 760-767).

De La Bourdonnaye, F., Teulière, C., Triesch, J., & Chateau, T. (2018). Stage-wise learning of reaching using little prior knowledge. Frontiers in Robotics and AI, 5.

Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., … & Petersen, S. (2015). Human-level control through deep reinforcement learning. Nature, 518(7540), 529.

Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., Van Den Driessche, G., … & Dieleman, S. (2016). Mastering the game of Go with deep neural networks and tree search. Nature, 529(7587)

Lillicrap, T. P., Hunt, J. J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., … & Wierstra, D. (2015). Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971

Finn, C., Tan, X. Y., Duan, Y., Darrell, T., Levine, S., & Abbeel, P. (2016, May). Deep spatial autoencoders for visuomotor learning. In ICRA 2016.

Contacts
Advisors
:

  • Prof. Jochen Triesch (Frankfurt Institute for Advanced Studies)
  • Dr. Céline Teulière (Institut Pascal, UCA)
  • Prof. Thierry Chateau (Institut Pascal, UCA)

Offer: One year contract, starting date in Fall 2019

Research Group: Institut Pascal

University: Université Clermont Auvergne (UCA) – Clermont Ferrand - France

Contact: celine.teuliere@uca.fr


Mehr über den Arbeitgeber

Unternehmen

LabEx IMobS3

Orte

Kategorien

Bewerbungsfrist

2019-05-31


Bewerben

Schicken Sie mir die Anzeige



Mehr über den Arbeitgeber

Unternehmen

LabEx IMobS3

Orte

Kategorien

Bewerbungsfrist

2019-05-31


Bewerben

Schicken Sie mir die Anzeige