Prof. Toshio Fukuda ( Keynote Speaker)

IEEE President 2020

Foreign Member of Chinese Academy of Sciences

IEEE Fellow (1995- ). SICE Fellow (1995- ), JSME Fellow (2002- ), RSJ Fellow (2004- ), VRSJ Fellow (2011-), Member of Science Council of Japan (2008- ), Honorary Doctor of Aalto University School of Science and Technology (2010)

Meijo University,Japan / Beijing Institute of Technology, China

Speech Title: Multi-Locomotion Robotic System

Abstract: The monkey type of robot has many different locomotion modes, such as brachiation mode, swinging from branch to branch, biped mode, walking like humanoid, 4 leg mode, walking like animals, ladder mode, climbing up and descending ladders and others. This multi-locomotion robot (MLR) is studied how to make the locomotion stable and how to use and select the various locomotion modes. There are two methods for controlling the stable locomotion: The learning control method and the task oriented model based control.
For the learning control methods, soft computing, reinforcement learning, neuro computing, and AI approach are applied for making the locomotion modes stable. For the task oriented model based control, Passive Dynamic Autonomous Control (PDAC) will be shown how the biped robot can make stable locomotion and then furthermore, applied for the quad locomotion mode and ladder climbing.
Depending on the environment situations, the robot can select and adjust the best locomotion methods from biped mode to quad locomotion and vice versa. The robot stability can be augmented and improved by swinging the robot arms and using canes.
Overall, the multi-locomotion robot (MLR) control methods show the more varieties of the stable locomotion for the robot.






Prof. Dan Zhang ( Keynote Speaker)

Fellow of the Canadian Academy of Engineering (CAE)

Fellow of the Engineering Institute of Canada (EIC)

Fellow of American Society of Mechanical Engineers (ASME)

Fellow of Canadian Society for Mechanical Engineering (CSME)

York University, Canada


Speech Title: Performance Improvement of Robotic Systems for Manufacturing

Abstract: There has been increasing in developing enviromentally-benign manufacturing technologies, robots, etc. This is considered a significant step in achieving sustainable development. Sustainability of a manufacturing system becomes critical technology that enables manufacturing companies to reduce production costs and improve their global competitiveness. System sustainability can be achieved by reconfiguration and decentralization, whose system configurations are evolved with the changes of design requirements and dynamic environment. The modular construction of parallel robotic machines allows them to be used as a class of reconfigurable machine tools. Nevertheless, parallel robotic machines as contemporary manufacturing robotic systems often have difficulty meeting the highly increased workplace demands on (1) operational accuracy, (2) operational load capacity, (3) task adaptability, and (4) reliability. For example, according to some large robot/robotic machine tool manufacturers and manufacturing robot user, i.e., ABB Robotics, Ingersoll Machine Tools Inc. and ATS Automation Tooling Systems Inc., the current robotic systems for high speed machining often fail due to thermal effects, which fatally distort the accuracy of the systems. According to the International Federation of Robotics (IFR), more than 60% of industry robots operating in the manufacturing industry are articulated robots (i.e., serial robots), or robots that can only allow material handling, but not material fabrication.

In this talk, the rational of using parallel robotic machines for green and sustainable manufacturing is discussed and explained. A comparative study is carried out on some successful parallel robotic machines and conventional machine tools. Meanwhile, the latest research activities of parallel manipulators in the Laboratory of Robotics and Automation of UOIT are introduced, they are: parallel robotic machines, reconfigurable/green robotic manipulators, web-based remote manipulation as well as the applications of parallel manipulators in micro-motion device, MEMS (parallel robot based sensors), wearable power assist hip exoskeleton, and rescue robot.


Prof. Wei Gao ( Keynote Speaker)

University of New South Wales (Sydney), Australia


Speech Title: New Era of Civil Engineering: When It Meets Artificial Intelligence

Abstract: Artificial Intelligence (AI) provides wide applications in current society, including predicting, classifying, and solving both social and scientific problems. Civil Engineering (CE), as one of the most mature engineering disciplines, is covering various aspects from the design, construction to the maintenance of the built environment. Generally, CE provides ample practical scope for abilities of AI; in turn, AI improves the quality of human life and originate novel approaches to solving engineering problems. For instance, the structural response analysis and reliability assessment incorporated with AI, also named as data-driven structural analysis, directly applies the data to derive the relationship between the variables and responses, and further establishes surrogate model to reflect this mathematical relationship implicitly involving the complex constitutive relationship. Data-driven analysis method partially avoids the challenge from physics and shares the benefits of self-adaption, self-optimization, and self-correction. In this study, practically significant investigations are conducted to demonstrate the sparks ignited by the new era of civil engineering which is the integration of CE and AI.



Prof. Kenji Suzuki (Keynote Speaker)

Senior Member, Institute of Electrical and Electronics Engineers (IEEE)

Member, American Association for the Advancement of Science (AAAS)

Member, American Association of Physicists in Medicine (AAPM)

Tokyo Institute of Technology, Japan


Speech Title: AI Doctor and Smart Medical Imaging with Deep Learning

Abstract: It is said that artificial intelligence driven by deep learning would make the 4th Industrial Revolution. Deep leaning becomes one of the most active areas of research in computer vision, pattern recognition, and imaging fields, because “learning from examples or data” is crucial to handling a large amount of data (“big data”) coming from informatics and imaging systems. Deep learning is a versatile, powerful framework that can acquire image-processing and analysis functions through training with image examples; and it is an end-to-end machine-learning model that enables a direct mapping from raw input data to desired outputs, eliminating the need for handcrafted features in conventional feature-based machine learning. I invented ones of the earliest deep-learning models for image processing, semantic segmentation, object enhancement, and classification of patterns in medical imaging. I have been actively studying on deep learning in medical imaging in the past 23 years. In this talk, AI-aided diagnosis and smart medical imaging with deep learning are introduced, including 1) computer-aided diagnosis for lung cancer in CT, 2) distinction between benign and malignant lung nodules in CT, 3) polyp detection and classification in CT colonography, 4) separation of bones from soft tissue in chest radiographs, and 5) radiation dose reduction in CT and mammography.




Prof. Jinsong Bao ( Invited Speaker)

Donghua University, China


Speech Title: Data Intelligence: Enpowering Digital Twin Manufacturing

Abstract: Today, increased computing power and connectivity are making it possible to virtualize manufacturing process in life-cycle by creating and maintaining a digital “mirror”, or digital twin. The ultimate vision for the digital twin manufacturing is to create, test and build whole manufacturing processes in a virtual environment, where it predicts the performance of workshop or factory by its digital twin through sensors so that the digital twin contains all the information that we could have by inspecting the physical build. Data intelligence connects, aggregates, and anonymizes data. Data intelligence help us insight to manufacturing, including efficiency and quality. The presentation will introduce the framework of Digital twin manufacturing, the state of the art in data intelligence, data-driven methods and use cases.



Prof. Lingfei Kong( Invited Speaker)

Xi'an University of Technology, China

Speech Title:Control energy optimality for multi-input planar cable-driven parallel robot

Abstract: Cable-driven parallel robots (CDPR) create a significant potential for use in large-scale applications, such as high-speed automated warehousing, sports stadiums and five hundred meters aperture spherical radius telescope etc.. Consequently, their movement speed and accuracy are critical to the quality and productivity of the working process. Moreover, they account for a significant portion of the energy consumption in the long-range motion process. In this talk, a novel control allocation frame is proposed for energy optimality of multi-input CDPR. Instead of the real-time optimization problem, the proposed approach introduces an implementable proxy to accurately measure the deviation of the controlled system from the energy optimal subspace. Then, the energy optimality is converted to a regulation problem solved by a standard H∞ approach. The proposed controller is shown to have significant benefit both in simulation and experimentally at the energy efficiency of CDPR.





AIACT Past Speakers

Prof. Dan Zhang
Prof. Songyi Dian
Prof. Makoto Kaneko
Prof. ZhiDong Wang
Prof. Wei Dong
York University, Canada
Sichuan University, China
Osaka University, Japan
Chiba Institute of Technology, Japan
Harbin Institute of Technology, China