ICCAS-SICE 2009

Abstract:

Humanoid robot is a machine which is built to look alike human and to move like a human. That means humanoid robot should satisfy two major aspects: anthropomorphism (looks alike a human) and functionality (moves like a human). The tutorial will present what are the main challenges to achieve these goals and how can we attack the problems by introducing the development outline of Hubo, the first Korean humanoid robot.

The full size humanoid robot with height of around 1.5m is quit differ from the toy size small ones in many aspects. It should have very stable and well designed structure with little uncertainties. It must strong enough to move its body weight but not so heavy to minimize the torques to drive the body parts. All the electrical parts and sensors must be compact to be fit in the enclosure of the body. We designed such kind of parts including force/torque sensors, inertia sensors and all the driver circuits, internal decentralized control architecture and hardware. Another important task is design walk algorithm. Walking algorithm is composed with two parts: off-line gait pattern design and real time stabilization control. Gait pattern design is to find a periodic function for each joint of leg such that humanoid robot is to walk with desired velocity keeping certain level of stability. We suggested a simple function connected with cubic spline and sine functions with minimal number of parameters. This approach simplifies the parameter adjustment procedure. Play back of gait pattern found from the former process, however, does not guarantee the robot walks in real practice since there are number of uncertainties involved in real situation. The uncertainties include ground inclination, friction, un-modeled vibration of the body. The stabilization algorithm should deal with such kind of problems. Hubofs walk algorithm has 8 levels of hierarchical control architecture to cope with the general circumstances in walking environment. The general issues including mentioned above will be presented at the speech.

Brief-biography:

1977. 2 B.S. in Mechanical Engineering, Yonsei University, Seoul, Korea
1979. 2 M.S. in Mechanical Engineering, Yonsei University, Seoul, Korea
1985. 10 Ph.D. in Mechanical Engineering, U.C. Berkeley, USA
1985. 10 ? present Professor of Mechanical Engineering, KAIST

Abstract:

Visual surveillance in a dynamic environment has drawn a great deal of attention nowadays. It spans a wide research spectrum, such as for access control, human or vehicle detection and identification, detection of anomalous behaviors, crowd statistics or congestion analysis, human-machine interaction in an intelligent space, etc. Since the field of view of one camera is limited, a camera platform is usually equipped with degrees of freedom to extend its observing range. In order to construct a wide-area surveillance system economically, a camera must be utilized to track multiple targets within its limited field of view. With the growing of computational power and advances of tracking theory, now we can monitor gradually more targets with a single camera simultaneously.
Many problems in science require estimation of the state of a system that changes over time using a sequence of noisy measurements made on the system. Bayesian filter provides a rigorous general framework for dynamic state estimation problems. Visual tracking is also one kind of this problem. The sensed sequence of 2D image data, which may lose some 3D information and is usually noisy, includes the target, similar objects, and cluttered background, etc. Here, the visual tracker is proposed to overcome the challenging tracking problems and result in successful multi-target tracking when the objects interact in a group.
On the other hand, there is another issue called multi-camera cooperation which attracts increasing attention lately. The overall surveillance capability of the entire set of cameras will not be effectively utilized with poor cooperations, and tracking of some targets will be rather vulnerable. Through the designed strategies of camera task assignment and camera action selection, the distributed camera agents will tightly collaborate with one another. Integrating the multi-target tracking technique and multi-camera cooperative methodology, the prospect of seamless tracking can be realized stage by stage. One can show that, after the overall system is equipped with the former capability, then we can develop a powerful wide-area surveillance system with near real-time performance.

Brief-biography:

Li-Chen Fu received the B.S. degree from National Taiwan University, Taipei, Taiwan, R.O.C., in 1981, and the M.S. and Ph.D. degrees from the University of California, Berkeley, in 1985 and 1987, respectively. Since 1987, he has been a member of the faculty, and is currently a Professor in the Department of Electrical Engineering and Department of Computer Science and Information Engineering, National Taiwan University. During 2005/8-2008/7, he was appointed Secretary General of the University, and since the end of year 2006 he was promoted to life-time Distinguished Professor of the university due to his extraordinary achievements. His current research interests include robotics, FMS scheduling, shop floor control, home automation, visual detection and tracking, e-commerce, and control theory and applications. He has been the Associate Editor of Automatica, and since year 1999 he became the Editor-in-Chief of the Asian Journal of Control. Prof. Fu has been very active in both IEEE Robotics and Automation Society (RAS) and IEEE Control Systems Society (CSS). From 2004 to 2005, he served as an AdCom Member of the IEEE RAS, and member of International Affairs Committee of IEEE CSS. Besides, he has served as Program Chair of the IEEE International Conference on Robotics and Automation (ICRA) sponsored by RAS in 2003 and the Program Chair of the IEEE International Conference on Control Applications (CCA) sponsored by CSS in 2004. Due to his numerous recognitions received domestically and internationally, he was awarded the prestigious honor as IEEE Fellow in year 2004.

Abstract:

Development of new methods for describing 3D shapes is an important topic in object recognition, model-based manipulation, and digital geometry processing. In the early days of computer vision, an object is usually modeled with global representations such as constructive solid geometry, generalized cylinders, or deformed superquadrics. Recently, more sophisticated representations such as shape distributions are developed, which allow for matching of objects under general similarity metrics. One drawback of such global schemes is that they are not suitable for matching with scenes where the target objects are only partially visible due to occlusion or limited view fields. In the talk, I will report our efforts in combining global and local representations to develop efficient methods for the partial object matching and analysis. The topics include a new shape representation scheme which uses a probabilistic bag-of-words model, a shape matching algorithm based on a dimension amnesic pyramid match kernel, and a shape space approach to animation of 3D human faces.

Brief-biography:

Hongbin Zha received Ph.D. degree in electrical engineering from Kyushu University, Japan, in 1990. After working as a Research Associate in Kyushu Institute of Technology, Japan, he joined Kyushu University in 1991 as an Associate Professor. He was also a Visiting Professor in Centre for Vision, Speech and Signal Processing, Surrey University, UK, in 1999. Since 2000, he has been a Professor at Key Laboratory on Machine Perception (MOE), Peking University, China. His research interests include computer vision, 3D geometric modeling, and virtual reality. He has over 200 technical publications in journals, books and international conference proceedings. He received the Franklin V. Taylor Award from IEEE SMC Society in 1999. He also served as Special Issue Guest Editors for IEEE Trans. SMC, Trans. IEICE, The Visual Computer, and is PC Chairs or Co-Chairs for IEEE ROBIOf06, VSMMf06, ACCVf07, and ACCVf09. He is a Member of IEEE Computer Society.

Abstract:

In this talk, an overview of the project is introduced that is fully supported by a Grant-in-Aid Creative Scientific Research 2007-2011 funded by the Ministry of Education, Culture, Sports, Science and Technology. In this project, we focus on the design issues of the mutual and inseparable relationships between the external environment and the internal of the agent that is an actor, an observer, a cognizer, and an interpreter. For this purpose, we introduce the subject of "semiosis", which is any form of activity, conduct, or process that involves signs, including the production of meaning. By mingling technologies with semiotics, we jointly approach to the common design issues varying from how organisms make predictions about, and adapt to, their semiotic niche in the world, and to an aspect of the wider systems including architects, embodied robots, product innovation and human-machine and/or human social interactions. Semiotic technology offers us an indispensable tool for the creation of a truly sustainable society and human-oriented technology, and our project enables a paradigm shift from conventional "design for manufacture" to novel "design for nurture".

Brief-biography:

Tetsuo Sawaragi was born in 1957 and is now a professor at the Dept. of Mechanical Engineering and Science, Graduate School of Engineering, Kyoto University, Japan. He received his B.S., M.S. and Ph.D. degrees in Systems Engineering from Kyoto University in 1981, 1983 and 1988, respectively. From 1986 to 1994, he was a research associate at the Department of Precision Mechanics, Faculty of Engineering, Kyoto University, wherein he was an associate professor and a professor in 1994 and 2002, respectively. In 2005 he was in the current department as a professor, and is presently a director of Center for Global Leadership Engineering Education (CGLEE) of Kyoto University. From 1991 to 1992, he was a visiting scholar at Dept. of Engineering-Economic Systems, Stanford University, USA. He has been engaged in the researches on Systems Engineering, Cognitive Science and Artificial Intelligence, particularly in the development of human-machine collaborative systems, modeling the transfer of human cognitive skills into machines. He was a chair of IEEE SMC Japan Chapter and a board member of the Institute of Systems, Control and Information Engineers, Human Interface Society and Japan Society for Fuzzy Theory and Systems. He was a project leader of the 21st Century COE Program "Center of Excellence for Research and Education on Complex Functional Mechanical Systems" of Kyoto University, and is currently a principal investigator of the Grant-in-Aid Creative Scientific Research 2007-2011 (19GS0208) on "Design Theory for Dynamical Systems with Semiosis" that is funded by the Ministry of Education, Culture, Sports, Science and Technology and is ongoing mainly at Kyoto University. Presently he is a president of Human Interface Society.