Sylvain Calinon

Curriculum Vitae






Contact / Links


Sylvain Calinon

Sylvain Calinon

I'm a Researcher at the Idiap Research Institute since May 2014, with research interests covering robot learning and human-robot interaction. I am also a Lecturer at the Ecole Polytechnique Federale de Lausanne (EPFL), an External Collaborator at the Department of Advanced Robotics (ADVR), Italian Institute of Technology (IIT), and a Visiting Researcher at the Learning Algorithms and Systems Laboratory (LASA), EPFL. From 2009 to 2014, I was a Team Leader at ADVR-IIT. From 2007 to 2009, I was a Postdoc at LASA-EPFL. I hold a PhD from EPFL (2007), awarded by the Robotdalen Scientific Award, ABB Award and EPFL-Press Distinction. I'm the author of 60 publications and a book in the field of robot learning by imitation and exploration, with recognition including IEEE Ro-Man'2007 Best Paper Award, IEEE-RAS Humanoids'2009 Best Paper Award Finalist and IEEE/RSJ IROS'2013 CoTeSys Best Paper Award Finalist. European Projects I have been involved in include STIFF-FLOP, PANDORA, SAPHARI, AMARSI, ROBOT@CWE, FEELIX GROWING and COGNIRON.

My work focuses on human-centric applications using robotics technologies. I am interested in innovative applications bringing end-users closer to the robots, which solicit tight links between learning, planning and control strategies (e.g., transfer of skills from demonstrations and further self-refinement by stochastic optimization). I take the perspective that the robots' actuation capability must be enriched with haptics information and bidirectional interfaces to anticipate the users' behaviors and generate safe and natural movements in confined spaces. In my research, I explore the use of statistical machine learning and dynamical systems to develop adaptive and compact representations of skills that can be shared by different learning approaches.

Upcoming or recent invited talks


PI Symposium (Posthuman and Digital Art), Monthey, Switzerland, see also the article in Le Nouvelliste (in French) of 19/11/2014.


Intl Conf. on Ubiquitous Robots and Ambient Intelligence (URAI), Kuala Lumpur, Malaysia.


Nipconf'2014, SwissTech Convention Center, Lausanne, Switzerland.


Workshop on Compliant Manipulation: Challenges in Learning and Control, IROS'2014, Chicago, USA.


Demonstrations of learning by interaction applications with the Baxter robot, TEDx Martigny.

Latest news and Updates


We recently acquired a Baxter robot for the Robot Learning & Interaction Group at Idiap, see the short video report from Canal 9 (in French).


Tohid Alizadeh and Davide De Tommaso successfully defended their PhD Theses and obtained the PhD Degree today. Congrats Doctors!


New paper "A task-parameterized probabilistic model with minimal intervention control" to be presented at ICRA'2014.


New paper "Null space redundancy learning for a flexible surgical robot" to be presented at ICRA'2014.


New paper "Learning from demonstrations with partially observable task parameters" to be presented at ICRA'2014.