Connectionists: postdoc position in explorative motor learning at CoR-Lab, Bielefeld University

[Robert Haschke]

CoR-Lab at Bielefeld University invites applications from outstanding
Postdocs in the area of autonomous explorative motor learning

The successful candidate has a strong background in at least two of the
areas visual servoing, dynamical systems and control, and machine
learning. The research project will cover dimension reduction methods,
development of adaptive vision-based controllers, their evaluation in
physics-based simulations and on real robot hands, and the development
of explorative learning strategies. The candidate should be able to
autonomously acquaint oneself with new research topics, supervise
undergraduate students, and integrate into the existing team.

Research topic
Humans gradually increase their manual competence by active exploration
of the manipulation capabilities of their fingers. As compared to
learning from sensory data, active learning incorporates the exploration
into the skill acquisition process.
The project targets to research such active learning paradigms, and to
apply them to real-world scenarios such as object-in-hand-manipulation
with dexterous robot hands. One interesting example is to learn to
rotate a cube so that certain faces become visible one after the other.
The learning scheme should exploit multimodal perception, such as joint
angle sensors, tactile sensors in the fingertips, and visual
information, and integrate these cues with the movement control scheme
of a dexterous 20 DOF Shadow Robot Hand. A major goal of the project
would be to implement a vertical slice of explorative skills, ranging
from learning low level finger control (extending eye-hand to eye-finger
coordination) to realizing desired movement skills of an object held in
the hand.
Generic insights should be gained about how proprioceptive, visual, and
haptic information has to be combined to drive the exploration process
and about suitable principles for shaping the exploration. This will
touch the research areas of reinforcement learning, active learning
driven by information maximization, or imitation of previously learnt
episodes.

Research environment
The CoR-Lab has been established at Bielefeld University, Germany, as a
research centre for intelligent systems and human-machine interaction.
The CoR-Lab forms a strategic partnership between Bielefeld University
and the Honda Research Institute Europe GmbH, Germany. It pursues
fundamental research in the field of cognitive robots and intelligent
systems. A particular focus of the CoR-Lab is the interdisciplinary
integration of expertise in engineering, computer science, brain
science, and cognitive sciences, including the humanities and social
sciences.
The Graduate School that is associated with the CoR-Lab provides an
exciting and stimulating environment for 20 enthusiastic and creative
PhDs and Postdocs, allowing them to pursue research in international
teams in close collaboration with an industrial research institute.

Scholarship
The CoR-Lab offers a three-year scholarship to pursue the research goals
of the project.

For more information please see:
http://www.cor-lab.de/corlab/html/graduate_school/index.php

A complete application should include certificates and transcripts of
records of the completed course of studies, a detailed curriculum vitae,
a cover letter providing information about the qualification for this
project, your past and future research interests including your research
projects in related areas, as well as your motivation to do research in
the Graduate School.
Please send your application until 31 October 2008 (preferably in PDF
format) to the Managing Director of the Graduate School:

Bielefeld University
CoR-Lab Graduate School
Dr. Carola Haumann
33594 Bielefeld
Germany

email: chaumann at cor-lab.uni-bielefeld.de