Dr. Pham Cuong

Nanyang Technological University, Singapore
Personal webpage

Title of presentation: Motion planning and control with contacts and dynamics

Abstract: Robots climb and walk by making and breaking contacts with the environment. Efficient climbing and walking also make use of dynamics, as opposed to the quasi-static "robot-like" motions of old. Yet, planning and executing motions in presence of contacts and significant dynamics effects still constitute major challenges. In this talk, I will present our recent research in those topics. In particular, we developed a new algorithm to find time-optimal motions under kinodynamic constraints in milliseconds. We leveraged this algorithm to discover feasible (inherently dynamic) motions in situations where no quasi-static motion is possible. In terms of contacts, we developed robust, optimal, controllers to regulate the contacts between robots and environments whose physical properties (geometry, stiffness, friction) are unknown and diverse. Along the way, I will also present a number of complex tasks involving contacts and dynamics we have tackled in recent years: dynamic waiter, critically-fast pick-and-place with suction cups, automatic precision drilling (Airbus Shopfloor Challenge at ICRA 2016), autonomous assembly of an IKEA chair, large-scale 3D-printing by a team of mobile robots, etc. These complex tasks illustrate the need for building robust and scalable robotic systems that address multiple challenges, from precise localization, to motion planning, to control of contact forces. Videos of the demos can be found on our channel: https://www.youtube.com/c/CRIGroupRobotics


Short Bio: 

Cường was born in Hanoi, Vietnam and grew up in Vietnam and then in France. He is an alumnus of École Normale Supérieure, rue d’Ulm (France) and holds a Ph.D. in Neuroscience from Université Pierre et Marie Curie (France). He was a visiting researcher at the University of São Paulo (Brazil) in 2010, and a JSPS Fellow at the University of Tokyo (Japan) in 2011-2013. He joined NTU (Singapore) as an Assistant Professor in 2013. He was a recipient of the Best Paper Award at the conference Robotics: Science and Systems, 2012. He was the leader of Team CRI Group which won the second prize at the Airbus Shopfloor Challenge at ICRA 2016. His research has been featured on major international media, including The New York Times, The Guardian, The Economist, CNN, Science, Nature, etc.

Prof. Massimiliano Zecca

Loughborough University, UK
Personal webpage

Title of presentation: Sport is Medicine

Abstract: 

Physical exercises have been prescribed for good health since 600BC, and there is plenty of scientific evidence that exercise is effective to improve health outcomes. The healthcare scenario, however, is changing at an increasingly rapid pace: on one hand, the population is becoming older, with more than 16% of the world population expected to become over 65yo by 2050, due to a contemporary decrease of birth rate and increase of life expectancy (megatrend #1); on the other hand, more and more technology is entering our healthcare system and our daily lives (megatrend #2). Current healthcare systems are not sustainable, as both megatrends call for a more personalised and objective healthcare, to allow people to live longer, healthier lives, as well as to allow health professionals to be more efficient and proficient in their jobs, while at the same time reducing the costs for the society. To achieve this, there is the clear need for a contextual understanding of the activities (what is being done? when? where? how?) to be used to inform any subsequent plan. Our research is focused in particular on the observation and the analysis of the human being, which can be seen as an extreme and exquisite example of a robotic system, and on the development of the necessary tools to inform this understanding. Specifically, we aim at the objective quantification of the capabilities and skills in different situations, such as surgical training or rehabilitation, just to mention a few, and the application of these findings for developing more advanced healthcare systems. The healthcare sector, however, is highly regulated with very high barriers to entry, and as such it is always difficult to test innovative solutions. Sport can be considered the Petri Dish for technological innovation, allowing the exploration of several different ideas and solutions to identify the most promising ones which can be progressed further. This presentation will show a few current examples of these activities.

Short Bio:

Professor Massimiliano Zecca is Chair of Healthcare Technology and leader of the Wearable BioRobotics research team in the Wolfson School of Mechanical, Electrical and Manufacturing Engineering of Loughborough University. He is based in STI, the Sports Technology Institute of Loughborough University, and is a key member of the NCSEM, the National Centre for Sport and Exercise Medicine, both located in Loughborough. Before joining Loughborough University Prof. Zecca worked in Waseda University, Tokyo, Japan, from 2003 to 2013, as Associate Professor of Robotics, and in Scuola Superiore Sant’Anna, Pisa, Italy, from 1999 to 2003. Prof. Zecca’s main research interests focus on the development of wearable and portable, extremely small and very accurate bespoke sensors, together with the necessary data processing and analysis methodologies (artificial intelligence) to extract useful information from the raw data flow. The skilful combination of advanced hardware with advanced software makes it possible to make measurements in situations where it would otherwise be very difficult or impossible to measure. Current projects include the development of nearable measurement system for the objective assessment of exercise at home, the development of a real-time biomedical physiological sensing for first responders or exposed workers, and the development of a smart training system for surgeons.

Dr. Hanafiah Yussof

Universiti Teknologi MARA (UiTM), Malaysia
Personal webpage

Title of presentation: Pioneering Service Robotics Industry in Malaysia:
Development of Humanoid Robot ADAM

Abstract: Service Robots is defined as robot that performs useful tasks for humans or equipment excluding industrial automation applications. The service robotics industry is emerging, categorized into personal/domestic use and professional use, a high growth is expected in service robotics segment due to technological advancements and growing adoption in diverse industries. The total market size of service robotics in global robotics technology market is expected to reach USD82.7Billion by year 2020. The service robotics annual growth is also expected to reach up to 25% compared to 15% for industrial robotics. With the positive growth in global robotics business together with the growing numbers of service robots employing AI and Machine Learning solutions, we will soon be seeing robots of all shapes and sizes making their first forays into our everyday lives. Robopreneur Sdn Bhd is a local Malaysian robotics company focusing on service robotics industry. Established in 2015 as a spin-off company of UiTM, Robopreneur is creating values in Malaysia robotic business ecosystem providing service robotics development and solutions for professional use, healthcare applications and business services. In 2018, the company is taking a bold step by pioneering the development of first Malaysian made humanoid robot ADAM (Advanced Development Autonomous Machine). Funded by the Ministry of Finance Malaysia, the first stage of ADAM project is focusing on the development of upper trunk humanoid with full body motion, vision and speech capabilities. ADAM is consists of 12 DOFs at the arm, shoulder and neck, with additional 10 DOFs from 10 fingers on both arms connected to 10 micro motors to move the fingers. ADAM is embedded with dual-stereo camera which connected to vision system with face detection algorithm. For speech recognition, the robot is using Mary-speech Engine with autonomous dialog using AIML Chatbot Engine (similar with Sophia robot system). The speech database was programmed on-board at the robot processor. By completing the development objective in the first stage of the project, Robopreneur has started commercializing ADAM as prototype humanoid robot platform for research purpose. Moving forward, further development on ADAM project is aiming on a fully functional biped humanoid robot for commercial use by year 2023.

Short Bio:

Dr. Hanafiah Yussof is the Founder, Board of Director and Group Chief Executive Officer of Robopreneur Sdn Bhd. Dr. Hanafiah holds PhD in Information Science from Nagoya University Japan specializing in humanoid robot. Dr. Hanafiah extended his research in humanoid robotics by developing tele-rehabilitation system employing humanoid robot in Autism rehabilitation. Holding permanent position as Associate Professor at the Faculty of Mechanical Engineering, Universiti Teknologi MARA (UiTM), Dr. Hanafiah venture into business by establishing Robopreneur Sdn Bhd in 2015 to commercialize his research products and explore service robotics business. Recognized as the pioneer in Service Robotics Industry in Malaysia by the Malaysia Investment Development Authority (MIDA), Robopreneur features a solid foundation in industrial R&D specializing in developing service robots and Artificial Intelligent (AI) solutions, with team of local talents at the new office setup in Cyberjaya. The company is currently undergoing several projects including development of first Malaysian made Humanoid Robot; a project funded by the Ministry of Finance Malaysia. The company is also venturing into AI solutions, Additive Manufacturing and Smart Manufacturing as technology solutions provider for Malaysia 4th Industry Revolution Policy (Industry 4Ward). With strong business corporate management, leadership and deep technical knowledge in robotics, Dr. Hanafiah believes that Robopreneur will become a world-class robotics company and making Malaysia as one of the producer and exporter of service robots to the world. Dr. Hanafiah also holds prominent position in robotics professional community. He was the Chairman of IEEE Robotics and Automation Society (RAS) Malaysia Chapter from 2013 until 2015, Editors in several high-impact journals and well known among robotics scientists and researchers. He also serves as Visiting Professors at University of Toyama Japan, and Visiting Researcher at Nagoya University and Hosei University Japan. Dr. Hanafiah have received several national and international awards such as ASME Best Mechatronics Paper Award and Nagoya University Award for Contribution to International Exchange between Japan and Malaysia.

Prof. Fujimoto Yasutaka

Division of Intelligent Systems Engineering, Faculty of Engineering, Yokohama National University
Personal webpage

Title of presentation: Highly Backdrivable Actuators for Human-Machine Collaboration

Abstract: The talk will be on a new development of bilateral drive gears that can be easily driven by load side shaft. For safety purposes, cooperative robots are installed with an actuator composed of a low power servo motor, a reduction gearbox, and a torque sensor. When cooperative robots contact humans or the environment, they must detect the contact force with a force sensor, a touch sensor, or joint-torque sensors. Exoskeletons enclosing geared motors, hydraulic actuators, or pneumatic actuators are also developed for assistive applications. For detecting the torque from outside, some sensors are needed. Equipping these sensors increase the cost and size of the application, but can be avoided under sufficient backdrivability of the actuator. To this end, we propose a method that maximizes the power transmission efficiency of a compound planetary reduction gear and develop prototypes of the backdrivable reduction gearbox called the bilateral drive gear. The forward and backward driving efficiencies of the prototype gearbox are around 90% and the reversedrive starting torque is less than 0.05N.m. We also confirmed that prototype gearboxes with different gear ratios are easily backdrivable by hand.

Short Bio:

Yasutaka Fujimoto (S’93-M’98-SM’11) received the B.E., M.E., and Ph.D. degrees in electrical engineering from Yokohama National University, Yokohama, Japan, in 1993, 1995, and 1998, respectively. In 1998 he joined Keio University, Yokohama, Japan as a research associate. Since 1999, he has been with the Department of Electrical and Computer Engineering, Yokohama National University, Japan, where he is currently a full professor. His research interests include motion control and actuators. In 1995, he published a work on three-dimensional robotic dynamic simulator and control considering a floating base link and physical interaction between robot and environment. He also contributed to development and control of helically-shaped direct-drive actuators with high-thrust force density and high-backdrivability. He received Inose Young Researcher’s Award in 1994, IEE-Japan Excellent Presentation Award in 2001, 2003, and 2005, JEMA/NECA SCF2009 Executive Committee Chairman Award in 2009, IECON2010 First Prize Paper Award of the IEEE-IES Electrical Machines Technical Committee, and IEEE ECCE2016 Best Paper Award. He is an IEEE-IES AdCom Member, an Associate Editor of IEEE Transactions on Industrial Electronics, a Program Chair of IEEE AMC2014, IEEE AMC2018, and a General Co-chair of IEEE ICM2019.

Prof. Feng Gao

School of Mechanical Engineering, Shanghai Jiao Tong University
Personal webpage

Title of presentation: Design and Control of 6-Legged Robots with Parallel or Hybrid Mechanisms for Applications

AbstractResearch on the walking robots has been one of key topics in robotics for a long time. In recent years, many legged robots were developed in the world, which of them achieved great progress and received much attention from the robotic field. The most important challenging issues are the design and human robot Interaction control of the legged robots. This speech will introduce our research on both mechanism design and real time control of the6-legged robots for applications, whichinclude the following issues: design process of type synthesis for legged robots with parallel or hybrid mechanismsdesign of the unit composed of motor, reducer, encoder and torque sensor for legged robots; real-time operating system for legged robots, walking based on force sensing, obstacle avoidance with both vision and F/T sensor, walking upstairs by vision, human-robot interactive assembly based on F/T sensor, locked door opening based on F/T sensor for legged robots, fire-fighting and so on.

Short Bio:

Feng Gao is a Chair Professor at the Shanghai Jiao Tong University. He earned his Ph.D. in mechanical engineering at Beijing University of Aeronautics and Astronautics in 1991, and his Master in Mechanical Engineering at Northeast Heavy Machinery Institute in 1982. From 1995 to 1997, he was a postdoctoral research associate in the School of Engineering Science at Simon Fraser University. He was a full professor at Yanshan University from 1995 to 1999. He served first as Vice President and then as President of Hebei University of Technology from 2000 to 2004. He served as the director of the State Key Laboratory of Mechanical Systems and Vibration at Shanghai Jiao Tong University from 2008 to 2013. Since 2004, he has been a full professor at Shanghai Jiao Tong University. He has been serving as an Associate Editor of Mechanism and Machine Theory since 2008 and the ASME Journal of Mechanical Design since 2012, and theGeneral Memberof the ASME Mechanisms and Robotics Committee since 2012. He gave the Keynote Speeches on the conferences of the ASME 2012 and IFToMM 2015, respectively. He won the 2013 China National Natural Science Award because of his contributions in parallel mechanism designand the 8 items of awards from the provincial science and technology invention prizes in China.And he won the ASME Leonardo Da Vinci Award for his invention of parallel manipulators in USA in 2014. He has been granted 120 patents and has published 3 research books on mechanisms and robotics, as well as 120 papers in international journals.