Martijn.Zeestraten's picture





Istituto Italiano di Tecnologia

My Bio: 

Martijn Zeestraten is an Early Stage Researcher (ESR) within the SMART-E project. He is employed at Istituto Italiano di Tecnologia (IIT), Genova Italy.

Before starting his Ph.D, Martijn studied Mechanical Engineering with at Delft University of Technology (TU Delft). There he specialized in Bio-mechanical robotics, and graduated cum laude in 2013. He obtained his Bachelor Degree from the TH-Rijswijk in 2011.

As a student Martijn worked in the technical industry in the Netherlands. The SMART-E program provides him the opportunity to maintain a link between academia and industrial applications. 


What I do in Smart-E: 

ESR13: Dexterous teleoperation for a compliant robot within unstructured spaces

Within the project I work on the development of a semi-autonomous tele-operation system. I focus on developing methods that are able to learn semi-autonomous behavior. This is achieved by learning a model of Environmental conditions, Human Input and desired actions. Programming by Demonstration (PbD) is an ideal learning technique to learn such models, especially for industrial environments. Using PbD, human operators can train the system by providing a number of examples of the desired behavior. This provides a fast programming method which does not require expert programmers. 



  1. M J A Zeestraten, I Havoutis, J Silverio, S Calinon and D G Caldwell. An Approach for Imitation Learning on Riemannian Manifolds. IEEE Robotics and Automation Letters (RA-L), January 2017. PDF
  2. M J A Zeestraten, A Pereira, M Althoff and S Calinon. Online motion synthesis with minimal intervention control and formal safety guarantees. In Proc. IEEE Intl Conf. on Systems, Man, and Cybernetics. October 2016, . PDF
  3. M Zeestraten, S Calinon and D G Caldwell. Variable Duration Movement Encoding with Minimal Intervention Control. May 2016, 497–503. PDF 

First Name: 


Last Name: 



Member for
2 years 6 months