

Home > > 




Workshop & Tutorial
Registration Sheet 
SICEICCAS 2006 Workshop&Tutorial registration can be made by using the completing the separate registration form ( English or Korean) and sending it by mail or fax to the following address:
SICEICCAS 2006 Secretariat
Bucheon Techno Park 4011506, 193,
YakdaeDong, WonmiGu, BucheonCity, GyeonggiDo, 420734, Korea
Phone: +82322345801~5, Fax: +82322345807
Email: finance@icase.or.kr 

• Tutorial I 
Artificial Muscle Actuators and Its Robotic Applications 
• Time 

• Presentation 
English 
• Program 
 1th: Overview, Hyouk Ryeol Choi, Prof. Sungkyunkwan University
 2th: ElectroActive Paper Actuators, Jaehwan Kim, Inha University
 3th: Piezoelectric Actuators, Hoon Cheol Park, Kunkuk University
 4th: Robotic devices driven by soft actuators based on dielectric elastomer: Jungkwang Mok, Ph.d Sungkyunkwan University 
• Abstract 
The focus of this halfday tutorial is on the ElectroActive Polymer (EAP) Actuators and Sensors. The tutorial will cover the fundamental chemistry, physics, modeling, and demonstration of EAPs in robotic applications. Realizing that the properties of natural muscle are i) to produce large strain and moderate stress with a good bandwidth, ii) to show good efficiency, iii) and to perform for longcycle life, an enabling new technology, EAP actuators, and sensors based upon polymer science and engineering, is emerging to do the same job that natural muscles can do. EAPs are ideal for a variety of biologically inspired robotics applications. Electromechanical properties of EAPs can be controlled in response to an electric field. In particular, they are highly active actuators that show very large deformation. They can operate both in a humid and dry environment. In order to develop robust robotic devices actuated by EAP, it is necessary for engineers to understand their fundamental physics and chemistry.





• Tutorial II 
Haptic Interaction Control and Application 
• Time 

• Presentation 
English 
• Program 
1) Basics of haptic interaction control
2) Energy bounding algorithm
3) Damping Estimation and Multirate Control 
• Abstract 
Haptic interaction control has been a central issue for the last few decades since displaying transparently the intended virtual or real environments while guaranteeing contact stability is very difficult task. This tutorial will cover basics of haptic interaction control and will present details of the energy bounding algorithm that have been developed in the HumanMachineComputer Interface Lab, at Gwangju Institute of Science and Technology, Gwangju, Korea (Republic of).





• Tutorial III 
Introduction to Filtering Theory with Applications to Guidance, Navigation, and Control 
• Time 

• Presentation 
Korean 
• Program 
10:00 ~ 12:00: Lecture 1 (Kalman Filter Basics, Dr. Ick Ho Whang, ADD)
12:00 ~ 13:30: Lunch
13:30 ~ 15:30: Lecture 2 (Particle Filters and Tracking Applications, Prof. Taek Lyul Song, Hanyang University)
15:30 ~ 17:30: Lecture 3 (Robust Filters and Navigation Applications, Dr. Myeong Jong Yu, ADD) 
• Abstract 
The principal goal of this tutorial is to provide an introduction to the basic principle and applications of Kalman filter, particle filters, and robust filters to guidance, navigation, and control systems. Fundamental concept on filtering technique with detailed mathematical development will be introduced, so that one can build up solid background on the basics of Kalman filter as well as general filtering theory. Considering the importance of Kalman filtering in the practicing areas of guidance, navigation, and control, practical applications of the Kalman filter in real fields are also presented following the basic theory. The workshop will deliver highly useful knowledge and experience for graduate students working on related research, scientists of government institutes, and field engineers being involved with practical projects. The oneday tutorial consists of three parts. In the morning session, introduction and mathematical developments of the Kalman filter theory is scheduled. During the afternoon session, more advanced filters such as the particle filters and robust filters will be discussed. 




• Tutorial IV 
Advanced Learning Models and Applications 
• Time 
Full Day (6 hours) 
• Presentation 
Korean 


• Program 
10:00  11:50: Lecture 1: Latent Variable Models, Prof. Seungjin Choi, Postech
11:50  13:00: Lunch
13:00  14:50: Lecture 2: Support Vector Machine, Prof. Jooyoung Park, Korea
Unniversity
14:50  15:10: Coffee Break
15:10  17:00: Lecture 3: Bayesian Netowkrs: Prof. KyuBaek Hwang, Soongsil
University

• Abstract 
Lecture 1: Latent Variable Models : One of central problems in machine learning is that of density estimation, which involves constructing a model of a probability distribution, given a finite number of samples drawn from that distribution. A latent variable model is a powerful approach to probabilistic modeling, supplementing a set of observed (visible) variables with additional latent (hidden) variables. In this tutorial, I will introduce widelyused latent variable models, including linear generative models and mixture models. For linear generative models, I will first explain factor analysis where the goal is to seek a linear generative model with Gaussian factors which best models the covariance structure of data variables. Independent component analysis is a powerful spinoff of factor analysis, allowing nonGaussian factors in the model. I will also introduce an important family of latent variable models, that is known as mixture models, including mixture of Gaussians, mixture of factor analyzers, and mixture of experts. All these aforementioned latent variables models are parametric models where parameters are learned by maximum likelihood estimation. Expectation maximization (EM) is a powerful technique for learning parameters in the presence of latent variables, which will be also discussed. This tutorial focuses on basic concept and fundamental mathematical theory involving latent variable models and EM optimization, rather than any realistic applications, in order to give audience in robotics a taste of machine learning, stressing out that machine learning will be the best friend of robotics in near future.
Lecture 2: Support Vector Machine : With a great deal of recent theoretical and empirical successes, the support vector learning method has grown up as a viable tool in the area of intelligent systems. Among the important application areas for the support vector learning, we have SVC(support vector classification), SVR(support vector regression), and SVDD(support vector data description). In this tutorial, we will present fundamentals on SVC, SVR, and SVDD, together with related topics such as kernel PCA(principal component analysis) and RKHS(reproducing kernel Hilbert space) theory. After briefly presenting the above fundamentals, we will also introduce some recent results on the preimage problems and the kernelbased denoising methods.
Lecture 3: Bayesian Netowkrs : Bayesian networks are a kind of probabilistic graphical models that compactly represent the joint probability distribution over a set of random variables via a comprehensible DAG (directedacyclic graph) structure. A Bayesian network can be applied to both prediction and description tasks. Thus, Bayesian networks have been widely applied in various areas, spanning from robotics and speech recognition to medical diagnosis and bioinformatics. This tutorial will cover the basic building blocks for deploying Bayesian networks in realworld applications. In specific, various approaches to learning Bayesian networks from data are introduced. As an example application, DNA microarray data analysis using Bayesian networks is presented. In addition, a couple of advanced learning techniques for alleviating the smallsample problem are discussed.








