Dept. of Automation & Computer-Aided Engineering
The Chinese University of Hong Kong
Freitag, 15.02.2002, 11 Uhr c.t., M6-114
For over a few decades, people have come from a long way to develop
intelligent machines with various schemes of machine intelligence. To
build an intelligent machine, the central problems is to abstract
intelligence and implant the intelligence to machines so as to allow
them to make a right decision (the cognition problem), and to sense
the world (the perception problem), and to response with actions (the
manipulation problem). The question is where the intelligence comes
from. In this talk, we will overview an approach that the author has
been working on for many years with his students and colleagues in
both Carnegie Mellon University and The Chinese University of Hong
Kong. We developed methodologies for modeling and transferring a class
of human intelligence, i.e., human control strategies in response to
real-time inputs. We will discuss the architectures, practice,
pitfalls, and perspective in relation to the following work: (1) how
we can efficiently model human control strategy in continuous and
discontinuous real-time inputs, (2) whether we need to validate the
learned models, (3) how about evaluation of the quality and
performance of the human skills associated in the model, (4) what
human skills can be transferred to another person, or to a robot, (5)
why we need to model the human skill in handling dynamically stable
systems, and (6) what sensing inputs should be selected for meaningful
models.
Bio
Yangsheng Xu received a PhD from the University of Pennsylvania in
Robotics. He is currently Professor and Chairman of Department of
Automation and Computer-aided Engineering at the Chinese University of
Hong Kong (CUHK). Before joining CUHK, he was a faculty member at the
Robotics Institute, Carnegie Mellon University where, with his
colleagues and students, he established the Space Robotics Laboratory
which was considered as the world first laboratory equipped with a
zero-gravity environment, space station model, and a ground-base
real-time control station. He designed and built over 10 robot
systems including Self-Mobile Space Manipulator, Single-Wheel,
Gyroscopically Stabilized Robot, Detachable Mobile Manipulator, and
Free-Floating Underactuated Robot. He has also made contributions to
abstracting human control strategy and implementing it in various
autonomous systems. Recently he has been working on microsystems,
wearable robots, and dynamically stable systems. He has published over
180 papers, from over 40 projects funded by both government and
industries, as a principle investigator. He has served as Associate
Editor of IEEE Transactions in Robotics and Automation, as President
of Hong Kong Joint Chapter of RACS, as Chairman of several IEEE
conferences, and keynote speaker in eight conferences. He has also
served on various advisory boards or panels in government and
industries in US, Japan, Korea, Hong Kong, the mainland China and
United Nations. He is a Fellow of HKIE and Academician of Euroasia
Acadamy of Sciences.