PhD position in robot learning from demonstration (deadline: Jan 31, 2020)

The Robot Learning & Interaction Group at the Idiap Research Institute in Switzerland has an open PhD position within the CODIMAN project (cobotics, digital skills and the re-humanization of the workplace), in collaboration with the Bern University of Applied Sciences (BFH). The research will be supervised by Dr Sylvain Calinon in the Robot Learning & Interaction group at Idiap, and will be achieved in tight collaboration with Prof. Sarah Dégallier Rochat at the Human-Centered Engineering Institute (HuCE) of BFH.

The CODIMAN project will develop cobotic solutions to allow for true human-robot collaboration in industrial settings. We will examine how to support the implementation and acceptance of new technologies in partial automation and human-machine interactions. The project will address questions such as: what kind of interfaces are needed to facilitate intuitive machine operation and flexible reprogramming?, how to transfer complex manipulation skills by imitation?, which continuous education is needed to prepare workers for cobotics and improve productivity?, and how to foster social acceptance and promote a successful integration?

Besides generating guidelines, the project will also deliver a platform for intuitive human-machine interaction that will provide a basis to acquire the necessary skills. To achieve these goals, the project is interdisciplinary, combining expertise in robotics and social sciences, by working together and in close interaction with the workers. Our industrial partners will let us build technological solutions that are centered on the workers' needs. The detailed research aspects of CODIMAN investigated at Idiap are described below.

Research aspects of CODIMAN investigated at Idiap

In CODIMAN, we plan to rely on the expertise available at Idiap and BFH in learning from demonstration and movement primitives representations. We will:

PhD position at Idiap/EPFL

The selected PhD candidate should hold a Master degree in engineering, computer science, physics or applied mathematics, with a background in linear algebra, signal processing, programming, control and/or machine learning. The PhD position is for 4 years, provided successful progress, and should lead to a dissertation. The selected candidate will become a doctoral student at EPFL (after hiring, s/he will submit his/her application to the Doctoral School at EPFL). Annual gross salary ranges from 47,000 CHF (first year) to 50,000 CHF (last year).

Link for application: http://www.idiap.ch/education-and-jobs/job-10278
Application deadline: January 31, 2020.

Idiap is an independent not-for-profit research institute, affiliated with the Ecole Polytechnique Fédérale de Lausanne (EPFL). It is located in the town of Martigny in Valais, a scenic region in the south of Switzerland, surrounded by the highest mountains of Europe, and offering exceptional quality of life, exciting recreational activities, including hiking, climbing and skiing, as well as varied cultural activities. It is within proximity to Lausanne and Geneva.

Idiap offers excellent salaries and conditions at all levels in a young, high-quality, dynamic, and multicultural environment. Although Idiap is located in the French part of Switzerland, English is the official working language. Free French lessons are also provided on a complimentary basis. Idiap is an equal opportunity employer and is actively involved in the "Advancement of Women in Science" European initiative. The Institute seeks to maintain a principle of open competition (on the basis of merit) to appoint the best candidate, provides equal opportunity for all candidates, and equally encourage both genders to apply.

Other open positions

The Robot Learning & Interaction Group at the Idiap Research Institute is regulary searching for excellent PhD and Postdoc researchers. If your research interests fit with our research activities and you are a motivated and outstanding researcher/student, feel free to contact me by email.

PhD candidates should hold a Master degree in engineering, computer science, physics or applied mathematics, with a background in linear algebra, statistics, optimization, signal processing, control and programming. PhD positions are for 4 years, provided successful progress, and should lead to a dissertation. The selected candidates will become doctoral students at EPFL (after hiring, they will submit their applications to the Doctoral School at EPFL). Annual gross salary ranges from 47,000 CHF (first year) to 50,000 CHF (last year).

Postdoc candidates should hold a PhD degree in computer science, engineering, physics or applied mathematics, with a background in linear algebra, statistics, optimization, signal processing, control and programming. The Postdoc position is from one to two years. Annual gross salary is 80,000 CHF. Part time employment is possible if desired.

The research in the Robot Learning & Interaction Group span several disciplines at the crossroad of machine learning, statistics, optimal control, differential geometry, human motion sciences and user interfaces. Specific examples of techniques we have been using include hidden Markov models (HMM), Gaussian process regression (GPR), model predictive control (MPC), Riemannian geometry and tensor methods. Our group is small, which facilitates both the collaboration within the group and the visibility of each person's research. We are particularly interested in the challenge of learning/transferring skills from fewer trials or demonstrations than what is currently achieved. Related topics include transfer learning, active learning, and the use of model priors that are valid for a wide range of skills.

Who do I seek?

Our research activities span several branches of science, and there is consequently no specific educational background sought for these positions. The ideal candidate should have strong expertise in one or a subset of the research topics described above. Other areas of research extending our current lines of research are also welcome for outstanding candidates: if you are a great candidate, we will adapt the project to you!

The ideal candidate is enthusiastic, creative, curious and motivated to do research with both theory and practice. I expect strong mathematical skills (in particular, in linear algebra, machine learning or optimization) and strong coding skills (C++, Python or Matlab).

It is important that you take the time to prepare a cover letter (max 2 pages) to explain how your background fit with our research activities (see the short description of our research and our latest publications). We receive many applications (usually over a hundred for each open position) and a good cover letter can be decisive to be shortlisted.

When preparing your CV, do not assume I know everything you know! In particular, for PhD positions, I am generally not aware of university rankings or grading systems. when available, relative ranking can then be more informative, such as average grade or ranks in the class. I may otherwise not necessarily be able to gauge how good you are from your grades or your university. If you are applying for a PhD position, you may not have experience with research, but you will most likely have done project work, so tell me about the projects you liked the most!

What is Idiap?

Idiap is an independent not-for-profit research institute, affiliated with the Ecole Polytechnique Fédérale de Lausanne (EPFL). It is located in the town of Martigny in Valais, a scenic region in the south of Switzerland, surrounded by the highest mountains of Europe, and offering exceptional quality of life, exciting recreational activities, including hiking, climbing and skiing, as well as varied cultural activities. It is within proximity to Lausanne and Geneva.

The pdf copy of our annual reports is the best way to know more about Idiap.

Idiap offers excellent salaries and conditions at all levels in a young, high-quality, dynamic, and multicultural environment. Although Idiap is located in the French part of Switzerland, English is the official working language. Free French lessons are also provided on a complimentary basis. Idiap is an equal opportunity employer and is actively involved in the "Advancement of Women in Science" European initiative. The Institute seeks to maintain a principle of open competition (on the basis of merit) to appoint the best candidate, provides equal opportunity for all candidates, and equally encourage both genders to apply.

For frequently asked questions (FAQs) about living in Switzerland, you can visit http://www.idiap.ch/en/faq.