Invited Talk I
“Model-based Development for Robotics with MATLAB/Simulink’s ROS Toolbox”
Thanacha Choopojcharoen
- Adjunct Faculty: Institute of Field Robotics FIBO, KMUTT
- Co-founder & Research Director : CoXsys Robotics
- Academic Affair Director: Thai Automation & Robotics Association (TARA)
Abstract
Due to its multi-domain nature and complexity, the development of algorithms for robotics systems requires extensive verification and validation to ensure performance and safety. A model-based approach allows the developers to simulate multi-domain dynamics and validate control algorithms without the risk of potential problems from building an untested physical prototype. A versatile graphical software platform known as Simulink is utilized in order to simulate vehicle dynamics and camera’s view in a virtual environment. The focus of our research is to design, implement, and validate a control algorithm for a robotics system in a controlled environment.
Invited Talk II
“Deep Learning Accelerator for Intelligent Computer Vision Systems”
Assoc. Prof. Dr. Hiroki Nakahara
- CEO/Co-Founder, Tokyo Artisan Intelligence (TAI), JP
- Associate professor, Tokyo Institute of Technology, JP
Biography
HIROKI NAKAHARA received the B.E., M.E., and Ph.D. degrees in computer science from Kyushu Institute of Technology, Fukuoka, Japan, in 2003, 2005, and 2007, respectively. He has held research/faculty positions at Kyushu Institute of Technology, Iizuka, Japan, Kagoshima University, Kagoshima, Japan, and Ehime University, Ehime, Japan. Now, he is an associate professor at Tokyo Institute of Technology, Japan and CEO/CRO/Co-Founder at Tokyo Artisan Intelligence Corp., Japan. He is a member of the IEEE, the ACM, and the IEICE.
Abstract
Convolutional neural networks (CNNs) are primarily a cascaded set of pattern recognition filters, which are trained by big data. It enables us to solve complex problems of computer vision applications, such as object recognition, segmentation, a pose estimation, toward more complex tasks. Since these vision applications require more accuracy and smart, modern CNNs contain millions of floating-point parameters and need billions of floating-point operations. Furthermore, recent CNNs tend to be massive by AI researchers. However, there is a big gap between the required computation power with available resources. Therefore, we must consider a low-power, cost, and real-time computation. Thus, deep learning accelerator research becomes still more important. In this talk, I will introduce optimization techniques for the CNN hardware accelerator and how to design a high performance per power efficiency for a surveillance camera system. Especially, I focus on customized hardware, which is a field-programmable gate array (FPGA) based on one. Next, I will apply more complex CNN to more intelligent work. Finally, I will discuss the platform which should be adopted, and share future research topics.