Simultaneous capture and localization of human movements based on humanoid kinematics

embarrassedlopsidedΤεχνίτη Νοημοσύνη και Ρομποτική

14 Νοε 2013 (πριν από 3 χρόνια και 10 μήνες)

81 εμφανίσεις

Simultaneous capture and localization of human movements based
on humanoid kinematics



Professor I
-
Ming Chen

School of Mechanical and
Aerospace

Engineering

Nanyang Technological University

Singapore


ABSTRACT


We

introduces a method called SLAC (Simultane
ous Localization And Capture) to track the spatial
location of a human using wearable inertia sensors without additional external assistive global sensing
device (e.g., camera, ultrasound, IR, etc.) The method uses multiple wearable inertia sensors to
dete
rmine the orientation of the body segments and lower limb joint motions. At the same time, based
on human kinematics and locomotion phase detection, the spatial position and trajectory of a
reference point on the body can be determined. Preliminary experim
ental study has shown that the
position error of SLAC can be controlled within 10 to 15 cm for a person to
walk

around a
2.8m by
3m rectangle on the floor

and climb up and down stairs
about 4m in length and 2m in height (or about
2% error of the total dist
ance travelled).
A
benchmark study on the accuracy of SLAC was carried out
using

the camera
-
based M
otion
A
nalysis
®

system
. The localization data obtained from SLAC tally
well with that from the commercial system. The positioning accuracy obtained from SLAC

is at least
an order of magnitude less than the GPS. Since the sensors can be worn on the human at any time and
any place, this method has no restriction to indoor and outdoor applications and is complimentary to
GPS applications.


Speaker:


Prof. Chen,
Fellow

of IEEE,
Fellow

of ASME, and
General Chairman

of IEEE International
Conference on Robotics and Automation (ICRA) 2017, Singapore, is a world renowned roboticist
with contributions in modular robotics, actuation design and wearable mechatronics. For
the past 10
years,
he had received funding of > S$10

million in the related areas as PI. He is currently Director of
Intelligent Systems Centre, which is co
-
funded by NTU and ST Engineering. He received the B. S.
degree from National Taiwan University in 1
986, and M. S. and Ph. D. degrees from California
Institute of Technology, Pasadena, CA in 1989 and 1994 respectively. His research interests are in
wearable sensors, human
-
robot interaction, reconfigurable automation, parallel kinematics machines
(PKM), b
iomorphic underwater robots, and smart material based actuators. Dr. Chen has published
more than 260 papers in refereed international journals and conferences as well as book chapters. He
has been serving on the editorial boards of IEEE Transactions on Ro
botics, IEEE/ASME Transactions
on Mechatronics, Mechanism and Machine Theory, and Robotica.

Modularity and reconfiguration for intelligent and biomimetic
robotic system design


Professor I
-
Ming Chen

School of Mechanical and
Aerospace

Engineering

Nanyang T
echnological University

Singapore


ABSTRACT


Modularization is a necessary step to realize a system that can change its configuration. The system
configuration may refer to as the structure and the appearance of the system, for example, toys
systems formed

by the LEGO bricks, or internal components and components that cannot be seen
from the outside, like memory card and CPU unit in a personal computer. In product design,
modularity issue has been addressed though product architecture. It is known that a mo
dular product
should have two major characteristics: 1) a one
-
to
-
one mapping from functional elements in the
function structure to the physical components of the product, and 2) decoupled interfaces between the
components of different modules. For a modula
rly designed robotic system, these two features of
modular products apply as well. In this talk, I will introduce a number of robotics/automation systems
built in our laboratory based on modularity and reconfiguration concept. The systems range from
indust
rial type reconfigurable automation systems that utilize standardized actuators and linking
components to form robots with serial and parallel architectures of different degrees of freedom to
micro/nano manipulation systems based on flexure parallel mechan
isms, and biomimetic underwater
robots. The science behind these modular robot systems varies. We have developed “Plug
-
n
-
play”
Local Product
-
of
-
Exponential models for simulation and control of reconfiguration automation
systems; selective
-
actuation design
principles for macro and micro scale parallel manipulation
systems. This talk will be concluded with our aspect of future development on the modularity and
reconfiguration of
intelligent
robotic systems for biomedical and nanotechnology.


Speaker:


Prof.
Chen,
Fellow

of IEEE,
Fellow

of ASME, and
General Chairman

of IEEE International
Conference on Robotics and Automation (ICRA) 2017, Singapore, is a world renowned roboticist
with contributions in modular robotics, actuation design and wearable mechatronics
. For the past 10
years,
he had received funding of > S$10

million in the related areas as PI. He is currently Director of
Intelligent Systems Centre, which is co
-
funded by NTU and ST Engineering. He received the B. S.
degree from National Taiwan Universit
y in 1986, and M. S. and Ph. D. degrees from California
Institute of Technology, Pasadena, CA in 1989 and 1994 respectively. His research interests are in
wearable sensors, human
-
robot interaction, reconfigurable automation, parallel kinematics machines
(P
KM), biomorphic underwater robots, and smart material based actuators. Dr. Chen has published
more than 260 papers in refereed international journals and conferences as well as book chapters. He
has been serving on the editorial boards of IEEE Transactions

on Robotics, IEEE/ASME Transactions
on Mechatronics, Mechanism and Machine Theory, and Robotica.