The Biometric Consortium Conference 19-21 September 2005 Arlington, Virginia USA
PDFPalm vein authentication technology and its applications (329KB / A4) This paper discusses the contactless palm vein authentication device that uses blood vessel patterns as a personal identifying
factor. The vein information is hard to duplicate since veins are internal to the human body. The palm vein authentication
technology offers a high level of accuracy, and delivers the following results: a false rejection rate (FRR) of 0.01%, and
a false acceptance rate (FAR) of 0.00008% or lower, based on Fujitsu research using the data of 140,000 palms. Several banks
in Japan have used the palm vein authentication technology for customer identification since July 2004. In addition, Fujitsu
has integrated the technology into the access control of electronic door lock systems. Fujitsu plans to further expand applications
for this technology by downsizing the sensor and improving the verification speed.
Fujitsu Robotics Technology
The 19th Annual Conference of the Robotics Society of Japan 18 - 20 September 2001 Tokyo, Japan
A biologically inspired design strategy for humanoid robot locomotion control and its simulation implementation is presented
in this paper. Firstly, the dynamics model of humanoid robot, biologically plausible spinal motor neural circuits, and virtual
muscular module are constructed. Then, the control strategy for adaptive bipedal locomotion is investigated, also the development
of the general-purpose robot simulation environment is discussed. This research shows that the locomotion control flexibility
and autonomy are achieved based on integration of biological foundations, computational neuroscience and robotics, and this
work also provides primary consideration for future engineering solution for both real robot and neurological disorder.
The 20th Annual Conference of the Robotics Society of Japan 2002 12 - 14 October 2002 Osaka, Japan
This article explores a biologically inspired approach to control the humanoid robot with many DOFs using Central Pattern
Generator (CPG) . The CPG is constructed by combination of groups of neural circuits that are modeled by recurrent neural
networks. The numerical perturbation method is used to guide the combination procedure for desired motion CPG in a step by
step manner. Validity of this approach is examined using HOAP-1, an open architecture humanoid platform. The operation and
development environment for neural control is also described in detail.
The 20th Annual Conference of the Robotics Society of Japan 2002 12 - 14 October 2002 Osaka, Japan
Recurrent neural network has been used in wide range of applications based on traditional programming language such as C.
However, when it comes to complex system, such as a humanoid robot, it is hard for these languages to generate the motion
pattern. In this paper, therefore, we present an RNN language, suitable for the programmer to reflect the biological process,
easy to implement, and it can fit well the learning process.
The First Asia International Symposium on Mechatronics(AISM 2004) 27 - 30 September 2004 Xi’an, China
Humanoid robots are expected to have variety of motions that enables good interaction with real human environment. Making
a program for generating several stable motions using the standard programming language such as C is not only time consuming
but also hard to understand and tune. For this, a suitable recurrent neural network language (RNN) inspired from neurobiology
has been developed. In this paper, a simple method of motion generation based on polynomials generated by RNN is presented.
All motions are generated using a basic RNN circuit of a first order polynomial. Using this method it is easy to generate
a complex motion of humanoid robot. Furthermore, Feedback controllers can be easily inserted in the RNN circuit of a motion
at any desired timing. Both rhythmic and non-rhythmic motion can be generated based on the same strategy. The effectiveness
of the proposed method is verified by experimental results.
