| The 2010 edition of AT-EQUAL was held in Iasi, Romania, July 12-18. With four conferences and one summer school
|
| Recent newspaper coverage related to AT-EQUAL events in Iasi
|
as@adrianstoica.com
+1 626 USA LAB1 |
|
| Scientific contributions |
Selected contributions,
from over 100 papers and 10+ Keynotes/Plenary Talks
(at
conferences in US, Australia, UK, China, Korea, Japan)
In Adaptive, Learning, and Evolvable Systems
Reconfigurable
VLSI Architectures for Evolvable
Hardware: From Experimental Field Programmable Transistor Arrays to Evolution-Oriented Chips (2001)
Polymorphic
Electronics (2001)
In Robotics
Stoica, A. Evolving
creatures that can learn by imitation: apprentice behavior and its role
in
robot motor learning. Int. Conf on autonomous robots and artificial
life
PERAC'94 - From perception to action, EPFL, Lausanne, Switzerland, 7-9
September, 440-443,1994
PhD
Thesis (1995), Motion Learning by Robot
Apprentices: A Fuzzy neural Approach, Victoria
University of Technology, Melbourne,
Australia
- hardcopy can be obtained from the University) (177 pages plus
robot programming code (C/Matlab)) The
earliest work on anthropomorhic/humanoid robot learning by
imitation (to my knowledge so far:-), partly published in
Conf papers 6-10 above)
Abstract:
Futuristic scenarios feature anthropomorhic robots
cooperating with humans in daily activities. Efficient cooperation
requires new techniques for facilitating man-robot skill transfer.
Instead of programming, it is far easier for a human to demonstrate the
task, showing the robot the movements it needs to perform. This thesis
presents an approach on how robots can learn the visuo-motor
coordination of their arms and how they can imitate arm movements, in
order to acquire motor skills from human instructors. It is argued that
in skill acquisition that involves arm movements, eye-hand coordination
is not sufficient and eye-arm coordination must be developed. A method
which allows the robot to learn how to move its arm while watching the
human arm is proposed. The robot moves its arm to randomly chosen
positions and the human places its arm in similar positions, imitating
the robot. Thus the robot can make associations between images of the
human arm and commands given to its own arm. Previous research on
neural models has offered promissing results in the learning of
visuo-motor coordination, while fuzzy techniques have been successful
in coping with the imprecisely defined concepts used in linguistic
instruction and reasoning. The fuzzy neuron is one of the many possible
neuro-fuzzy hybdrids, which attempt to benefit from the synergism of
qualities of neural and fuzzy models. The first part of this thesis
attempts toprovide a unified framework for modelling and implementing
systems by using fuzzy neural networks. In particular, two new types of
fuzzy neurons are proposed and analysed: the fundamental fuzzy neuron
and the fuzzy neuron with shared weights. The fuzzy neural structures
analysed in the first part of the thesis are used in the second part
for robot learning and control. It is shown that fuzzy neural networks
can be used for learning visuo-motor models, and provide certain
advantages over classic neural networks. The main advantage is the
transparency of the fuzzy neural models. As the rbot used for tests is
anthropomorphic only in a planar appearance, human imitation is
demonstrated for 2D, while for 3D the robot imitates a second,
identically built robot.
Robot fostering techniques for sensory-motor development
of humanoid robots (2001)
Humanoids
for Lunar and Planetary Surface Operations (2005)
From Bionics and Wetware to Cyborgs and Transhumans
FBIT 2007
Keynote
Robotic scaffolds for tissue engineering and organ growth (2009)
In Security
Biometric
Inverse Problems (book, 2005)
Towards Recognition of Humans and their Behaviors from Space and Airborne Platforms:Extracting
the Information in the Dynamics of Human Shadows(2008)
|
|
|
|
