- Offer Profile
- What are the basic building
blocks of cognition and learning? How can we endow robots with some social
competence, to make them acceptable as assistants to humans? How can
machines communicate smoothly and on semantic levels with humans? Such
important yet unsolved persistent research questions have been guiding
Bielefeld researchers in the key area of Interactive Intelligent Systems for
The "Research Institute for Cognition and Robotics - CoR-Lab"
What does CoR-Lab offer ?
In order to face the enormous challenges that these
question imply for robotics, the „Research Institute for Cognition and
Robotics (CoR-Lab)“ was founded at the Bielefeld University in July 2007
under main participation of the research groups Neuroinformatics (Prof. Dr.
H. Ritter, Prof. Dr. J. J. Steil) and Applied Computer Science (Prof. Dr. G.
Sagerer), with support by the ministry of Innovation, Science, Research and
Technology of North Rhine-Westphalia and in a strategic partnership with the
industrial partner Honda Research Institute Europe GmbH (HRI-EU). In this
ongoing partnership, HRI-EU contributed two ASIMO robots for research
projects in a joint graduate school from 2007-2012. The special relationship
between Honda and CoR-Lab has been renewed in 2012 for further four years
and continues with new research projects in robotics, machine learning and
- Talks and presentations on cognitive and learning technology
- Training of highly-qualified personnel
- Cooperative FuE projects in research and teaching
- Information exchange
- Cooperation in individual measures
- Contact for students projects
The participating research groups in CoR-Lab are widely known for their work
in artificial cognition, computer vision, neural networks and machine
learning, and human-robot interaction. They are in command of a unique
wealth of robot platforms including two humanoid iCub robots, several Nao
robots, anthropomorphic robot hand, Kuka LWR compliant arms, a bionic
handling assistant, and further service robots.
The acquisition of competencies in these wide fields of intelligent systems
technology since its inauguration in 2007, and its growing focus on applied
research enables CoR-Lab to serve more and more as a center for the transfer
of advanced intelligence technology from fundamental research towards
industrial application in the region Ostwestfalen-Lippe. Through joint
projects with regional industry partners it supports the domestic
medium-sized economy by organizing transfer of excellent research, e.g. in a
transfer chain reaching from the Bielefeld Center of Excellence in Cognitive
Interaction Technology CITEC through CoR-Lab to application partners. With
this aim, CoR-Lab also takes the lead for Bielefeld University’s
contribution to the BMBF Spitzencluster it’s-owl (Intelligent Technical
- Add Intelligence to Machines.
High-tech for tomorrow’s markets. A technology network encompassing
economy and science about to set world standards for intelligent products
and production systems is growing in OstWestfalenLippe. The cluster
Intelligent Technical Systems OstWestfalenLippe – in short, it’s OWL –
is regarded as a pioneer for Industry 4.0 and makes important contributions
to Germany’s competitiveness as an industry location. Having been awarded in
the Leading- Edge Cluster Competition of the Federal Ministry of Education
and Research, is a seal of quality for it’s OWL.
174 companies, research institutes and organizations cooperate within
the it’s OWL network. In a joint effort of economy and science they approach
the innovation leap from mechatronics towards Intelligent Technical Systems.
World market leaders in the fields of mechanical engineering, electrical and
automotive supply industries collaborate with top-level research institutes.
45 projects with a total budget of 100 million Euro will develop
technologies for new generation products and production systems – ranging
from automation and drive solutions to machines, vehicles, household
appliances to Smart Grids and networking production plants.
The Federal Ministry of Education and Research sustains these activities
with 40 million Euro.
The technology platform will be made usable for numerous producing
companies. This is a strong impulse for growth and employment in the
Resulting from a joint effort of engineering sciences and informatics
Intelligent Technical Systems
Intelligent Technical Systems
- interact with the environment and
adapt autonomously (adaptive),
- cope with unexpected situations in a dynamic surrounding (robust),
- anticipate the effects of diverse influences on the basis of
experiential knowledge (anticipatory),
- and consider individual user behavior (user-friendly).
- help creating new functionalities of
products and production systems and provide easier handling for users,
- improve development, installation, maintenance, and life cycle
- improve reliability, safety, and availability,
- provide for a more efficient use of resources like energy and materials,
- and allow for individualized and changeable production processes.
FlexIRob - Motion Learning At Your Fingertips
- Enabling robots to become co-workers that collaborate
with humans efficiently and in safely is a major goal of current robotics
research. At Bielefeld University's CoR-Lab, researchers use learning and
interaction technology for control of compliant robots such as the KUKA
Lightweight Robot (LWR) to realize such human-robot interaction. Research
results are continuously integrated in the showcase robotic system
“FlexIRob” providing a testbed for flexible robotic co-worker and advanced
human-robot collaboration scenarios.
In its current setup, FlexIRob allows to teach a redundant robot various
Nullspace constraints in different areas of the workspace. Users with no
particular robotics knowledge can perform this task in physical interaction
with the compliant robot, for example to reconfigure of a working cell
environment. After a short training phase, the learned adaptive mapping
solves the inverse kinematics problem of the robot. It is embedded in the
motion controller of the system, hence allowing for execution of arbitrary
motions in task space, respecting the learned Nullspace constraints. This is
a large step towards our vision of a flexible robotic coworker system,
because it avoids the complex manual programming that standard methods for
this task have previously required.
AMARSi - Adaptive Modular Architectures for Rich Motor
- AMARSi is a EU-funded research project in the Seventh
Framework Programme. The project is a large scale integration project hosted
in the category Information and Communication Technologies , unit E5:
Cognitive Systems, Interaction and Robotics .
Motor skills of humans and animals are still utterly astonishing when
compared to robots. AMARSi aims at a qualitative jump in robotic motor
skills towards biological richness. AMARSi' objective: the experimentation
and demonstration of rich motor skills on the iCub humanoid robot and on the
quadruped Oncilla. Rich motor skills in robots will have a tremendous impact
on our society. Dexterous and skillful motion in robots will make them more
suitable for a large number of tasks. The compliant and natural movements
will make them blend into everyday routines, safe and psychologically
Research in AMARSi focuses on three main areas: biology, robotics and
software methods. Seven research subjects (or Work Packages) are tightly
- Human Motor Primitives - Work Package 1
- Compliant Systems - Work Package 2
- Morphological Computation - Work Package 3
- Adaptive Modules - Work Package 4
- Learning - Work Package 5
- Architectures - Work package 6
- Robotic Experimentation - Work package 7
- Dissemination and Training - Work package 8
- Management and Coordination - Work package 9
Cognitive Robotics and Learning
- The research group is organized at the border of machine
learning, cognition and human-robot interaction. The ultimate goal is to
enable interactive learning in human-machine cooperation. The research group
investigates efficient and life-long learning methods for behavior
generation, motor learning and visual object recognition to maximize the
autonomy and adaptability of robotic systems. In particular, imitation
learning and bootstrapping processes are central research areas. Application
areas of this research group comprise behavior learning and generation for
ASIMO, iCub, the light-weight KUKA LWR robot arm and other robots, visual
online learning for object recognition, and autonomous learning approaches
to generate complex time series including audio and video signals.
Main methodological foci are neural learning methods, in particular
recurrent reservoir networks, and the transfer of other machine learning
approaches to interactive scenarios, which require high computational
efficiency and online-learning capabilities. Of particular interest in this
domain are generative approaches to allow for behavior generation along with
classification or prediction. Important methodological aspects of generative
models are covered by the projects "ALEGRO" and "Theory of generative
The projects "Neural Learning of Flexible Full Body Motion" and
"Goal-directed Imitation Learning from Humans" pursue the autonomous
bootstrapping of motor control and skill acquisition by imitation learning.
Central goal is to understand cognitive and developmental aspects related to
motor learning and learning by imitation. The research group follows a
synthetic approach to tackle important questions in this context by
implementing computational models of these processes.
The research group also contributes neural learning methods and robotic
experimentation to the FP7-IP large scale project AMARSi -- Adaptive Modular
Architectures for Rich Motor Skills, which is coordinated by Prof. Steil.
Cognitive Systems Engineering
- Cognitive robotics is an experimental research activity
that combines research efforts in mechatronics, informatics and the
cognitive sciences. Creating cognitive robots requires building systems that
can adapt their behavior to environments that are complex, rapidly changing,
and that cannot be completely modeled in preface. Nowadays, many of the
resulting challenges can be successfully addressed on the level of
individual algorithms or by advanced robotics hardware tuned for specific
In order to provide an avenue for robotic systems to become useful in
every-day human settings and as a prerequisite for entering the consumer
market, these attributes must be ensured on a system level that encompasses
the web of skills advanced robots must be capable of. The aim of the
cognitive systems engineering group is to investigate software architectures
and engineering principles that allow to efficiently integrate, implement
and bring together this web of different skills in order to build complex
cognitive robotic systems.
A fundamental prerequisite for mastering the (technical) integration of
complex robotics systems is the availability and in-depth understanding of
robotics middleware technology. For this reason and despite the availability
of frameworks such as ROS, we decided to further develop a custom, but very
light-weight and open robotics middleware termed RSB. This so called
Robotics Service Bus (RSB) is an efficient message-oriented, event-driven
middleware aiming at scalable integration of robotics systems in
heterogeneous environments. It is fully open source and available for
various operating system, featuring implementations for a number of popular
programming languages. Due to our involvement in the HUMAVIPS EU project,
specific platform support will be made available for the NAO humanoid robot
at the HUMAVIPS Open Portal page. Please find more information and a
comparison to ROS concepts at the corresponding project website.
- When taking the reasoning of current robotic research
seriously we have to face the possibility that in the future humans and
robots will live together in a shared environment and form a hybrid society
of natural and artificial agents. We can thus expect to see more and more
humans interacting with robots. This vision opens new research questions and
opportunities that we want to tackle in the research group „Hybrid Society“.
On the one hand, robots will be able to profit from interactions with
humans. As humans are experts when it comes to understanding and handling
tasks in the real world, they are a valuable source of information for
robots. But how can robots make use of this information? In our group we
target at enabling robots to be tutored by humans. Research has shown that
adults provide specifically designed input to infants in tutoring
situations. We expect to see similar behavior in human-robot tutoring
situations provided that the robot displays a certain degree of social
behavior. Based on such behavior we are currently determining ways for the
robot to understand the meaning of a demonstrated action and to detect when
an action is being demonstrated in order to be learned by the robot.
On the other hand, the main goal for robots is to help humans and support
them in their daily activities. However, in order for robots to be really
helpful they not only must be able to learn and carry out tasks and actions.
They must also display socially acceptable behavior and be understandable
and predictable for their interaction partners. This entails not only to the
propositional content of an interaction as modelled by a dialog management
component, which enables to build a common ground of shared information
between the user and the robot. Also, the robot should be able to take the
affective components of an interaction into account by reading the human’s
emotional expressions and by producing appropriate emotional signals. We
suppose that such an alignment of emotional behavior will make interaction
with the robot not only more satisfying but also more efficient.
- Transfer and cooperative offers for enterprises
The next generation of intelligent robots will be used as assistants in the
industrial range and will bring along own knowledge and abilities, which
will allow them to act autonomously. The vision is a custom-made, industrial
solution for enterprises with a maximum of variability, simple handling and
This vision poses new challenges for man-machine cooperation and
communication like security in interaction, and needs increased robustness,
efficiency, accuracy and economy.
CoR-Lab aims to enhance the respective potential of learning and cognitive
technology in the region East-Westphalia and Lippe (OWL) by cooperation with
regional industry and offers to help enterprises increasing their
competitive ability in this upcoming field of high-technology through joint
workshops, FuE projects, and networking. The training of highly-qualified
engineers in CoR-Lab's Graduate School also contributes to the innovative
strength and the economic development of the region.