[robotics-worldwide] Call for Participation - ICAR'09 Workshop on Robust and Legible Manipulation in Human Environments

Freek Stulp stulp at cs.tum.edu
Mon May 18 06:33:42 PDT 2009



ICAR'09 Workshop on Robust and Legible Manipulation in Human Environments


The full-day workshop "Robust and Legible Manipulation in Human Environments"
will be held during the 14th International Conference on Advanced Robotics 
(ICAR 2009) in Munich, Germany, on June 23, 2009.



09:15 -- 09:45 Introduction
09:45 -- 10:30 Gordon Cheng - Technische Universitat München
10:30 -- 11:00 Coffee Break
11:00 -- 11:45 Tim Guhl - KUKA Roboter GmbH
11:45 -- 12:30 Andreas Pott - Fraunhofer Institut für Produktionstechnik und
                              Automatisierung IPA
12:30 -- 14:00 Lunch Break
14:00 -- 14:45 Radu Rusu - Willow Garage / Technische Universitat München
14:45 -- 15:30 Michael Beetz - Technische Universitat München
15:30 -- 16:00 Coffee Break
16:00 -- 18:00 Panel Discussion

Robotics in human environments, manipulation, mobile manipulation,
unstructured environments, humanoid robots, intention recognition

Although robots are currently faster, stronger, and more accurate than
humans, they are still far from achieving human-like performance when
manipulating objects. The main reason is that the brain as a motion
controller is far superior over robotic controllers in terms of
flexibility, autonomous learning abilities, and reliability. In the long
run, such characteristics are necessary requirements for robots too; as,
for instance, needed in elderly care. With a steadily increasing
percentage of elderly people, and therefore the increased prevalence of
chronic diseases and disabilities, there is great potential for such
robots to help where human resources are insufficient.

In order to achieve robots that have human-like manipulation
performance, the computational aspects of everyday manipulation tasks
need to be well-understood, and requires the thorough study of the
interaction of perceptual, learning, reasoning, planning, and control
mechanisms. The challenges to be met include cooperation with humans,
uncertainty in both task and environments, real-time action
requirements, and the use of tools. The challenges cannot be met by
merely improving the software engineering and programming techniques.
Rather the systems need built-in capabilities to deal with these
challenges. Looking at natural intelligent systems, the most promising
approach for handling them is to equip the systems with more powerful
cognitive mechanisms. Interesting topics for discussion might be: Which
aspects of human environments should robots know before being deployed,
and which aspects should it acquire during operation through modeling
and learning? Which role should imitation play?

Another aspect of robots in human environments we want to address is
legibility of robot behavior, i.e. how well humans can interpret a
robot's intentions. For humans to interact naturally with robot, it is
not an absolute necessity to have robots with the exact same morphology
as humans. This might even have the contrary effect, known as the
'uncanny valley'. Rather, natural interaction depends on a robot's
-behavior-, which should be predictable, consistent, efficient and
goal-directed. In this context, we will address questions such as: How
much should/must robot behavior mimic that of humans? Should robots
mimic all idiosyncrasies of humans? Which rules of politeness should
robots respect, and how can such rules be represented? Does (near)
optimal behavior facilitate the interpretation of intentions by others?

The goal of the proposed workshop is to make progress towards closing
the gap between human and robot manipulation in uncertain environments
inhabited by humans. We will do this by considering application domains
that are too complex for current robotic system, such as a kitchen robot
that can set the table, or a robot that assists caretakers in elderly homes.

Freek Stulp, Technische Universitat München, Garching, Germany
Michael Beetz, Technische Universitat München, Garching, Germany
Jan Paulus, Bonn-Rhein-Sieg University of Applied Science, Germany


More information about the robotics-worldwide mailing list