The Machine Learning & Robotics group at TU Berlin is inviting
applications for a PhD studentship. The position is financed from a
cooperative project with the CoR-Lab Bielefeld and the Honda Research
Institute (Offenbach), in particular with their ASIMO robotics lab. The
project is about grasping using tactile and visual feedback and
involves a realization on a robotics platform with a 7 DoF Schunk arm
and a dexterous 3 finger Schunk hand. We aim to apply Machine Learning
methods in this context, in particular probabilistic inference methods
for the integration of goals, constraints and uncertain information on
multiple sensor and motor representations, and learning of prototypes
and representations. The position is based in Berlin but includes the
unique chance to visit the Honda and Bielefeld lab for one or two months
per year and actively transfer the developed methods. Applicants should
have experience in one of the fields of robotics, control, or Machine
Learning, and great interest in the combination of theoretical methods
and robotic applications.