Abstract

The key note presentation will go over megatrend on recent developments on self-driving car industry. It begins from a brief history of vehicle automation to five different levels of autonomy and their killer applications. The second part of the talk consists of perspectives on new automotive sensors (i.e., radar, camera, and lidar) and new algorithm development based on those sensors. The last part of the talk will be about personal journey on my startup, Phantom AI. The story is on why I started the startup and how I managed the first two years and finally how we are surviving!

Biography

Dr. Hyunggi Cho is currently the CEO and Co-Founder of Phantom AI, Inc. a start-up located in San Francisco, California. Phantom AI is a self-driving technology partner for Tier1s and OEMs, producing software for autonomous vehicles. Prior to his time at Phantom AI, Hyunggi was a Senior Control Engineer at Tesla Motors, focused on Autopilot R&D for Tesla Motors. He worked on several key aspects of perception for Tesla's Autopilot system including sensor fusion S/W framework (i.e., sensor logging, playback, and visualization), computer vision, and localization and mapping. Prior to his time at Tesla, Dr. Cho was a PhD Candidate at Carnegie Mellon University, where he focused on autonomous driving. His previous roles include Embedded Linux kernel programmer at AL Tech (April 2004 - May 2005); Real-Time Software Programmer (August 2002 - March 2004). He holds a B.S. in Control Measurement from Sun Moon University, a Master of Science in Localization in Wireless Sensor Work from Yonsei University, a Master of Science in Robotics from Carnegie Mellon University (2010), and a PhD in Autonomous Driving from Carnegie Mellon University (2014).

Abstract

In this talk, I’d like to engage our community to question whether robots need socio-emotive intelligence. To answer this question though, we need to first think about a new dimension of evaluating AI algorithms and systems that we build - measuring their impact on people’s lives in the real-world contexts. I will highlight a number of provocative research findings from our recent long-term deployment of social robots in schools, homes, and older adult living communities. We employ an affective reinforcement learning approach to personalize robot’s actions to modulate each user’s engagement and maximize the interaction benefit. The robot observes users’ verbal and nonverbal affective cues to understand the user state and to receive feedback on its actions. Our results show that the interaction with a robot companion influences users’ beliefs, learning, and how they interact with others. The affective personalization boosts these effects and helps sustain long-term engagement. During our deployment studies, we observed that people treat and interact with artificial agents as social partners and catalysts. We also learned that the effect of the interaction strongly correlates to the social relational bonding the user has built with the robot. So, to answer the question “does a robot need socio-emotive intelligence,” I argue that we should only draw conclusions based on what impact it has on the people living with it - is it helping us flourish in the direction that we want to thrive?

Biography

Hae Won Park is a Research Scientist at MIT Media Lab and a Principal Investigator of the Social Robot Companions Program. Her research focuses on socio-emotive AI and personalization of social robots that support long-term interaction and relationship between users and their robot companions. Her work spans a range of applications including education for young children and wellbeing benefits for older adults. Her research has been published at top robotics and AI venues and has received awards for best paper (HRI 2017), innovative robot applications (ICRA 2013), and pecha-kucha presentation (ICRA 2014). Hae Won received her PhD from Georgia Tech in 2014, at which time she also co-founded Zyrobotics, an assistive education robotics startup that was recognized as the best 2015 US robotics startup by Robohub and was the finalist of the Intel Innovation Award.

Abstract

Intuitive Surgical Inc.’s da Vinci Surgical System is a leading robotic technology in the global market today. Approved by the FDA in 2000, it can be used in cardiac, thoracic, colorectal, general, head and neck, gynecology and urology surgeries. It took several years for Tianjin University, based in China, to develop a minimally invasive surgical robot system called the Micro Hand S. From 2014 to 2015, the system went through human clinical trials, operating on patients in need of laparoscopic surgery. With positive results and no technical problems or complications encountered, the Micro Hand S has the potential to be a safe and effective system for surgeries in the future. Surgeons in China are required to go through extensive training before they are able to use the surgical robot in operations. Hong Kong is a leading location in Asia where many robotic surgeries have been performed. In 2012, Hong Kong acquired the first Robotic Interactive Orthopedic (RIO) system in Asia from MAKO Surgical Corporation (acquired by Stryker Corp.). The RIO system is mainly used for partial knee replacement surgeries, but can potentially be used for hip, ligament, and spinal surgeries as well. The RIO system enables the surgeon to hold and guide the robotic arm during the surgery, rather than operate it remotely on a console. Not only can surgeons perform more difficult surgeries with the RIO system, but they can also sometimes do it with less experience.

Taiwan has the most surgical robots in Asia relative to its population. While there are benefits to robotic surgery as discussed earlier, many hospitals in Taiwan are being criticized for recommending expensive robot-assisted surgeries when traditional surgeries would have sufficed. In Japan, the government is currently collaborating with five universities and 14 companies to develop a robotic surgery system that allows doctors to operate with more precision and accuracy, as well as simultaneously monitor MRI readings and data from other devices. In 2015, Japanese researchers revealed EMARO, an air-powered endoscopic robot that gives surgeons hands-free control and enhances visualization inside a patient’s body with three movable cameras. It is expected to be marketed to hospitals and universities in Japan in the fall of 2016 and be available overseas within the next few years. Like many other Asian countries, Korea is adapting surgical robots for healthcare, too. Robotic surgery training is not required in Korea and has sometimes led to adverse events that possibly could have been avoided. A training center was therefore opened in 2008 at a Korean hospital for surgeons to gain experience and practice the skills necessary to operate surgical robots. Inspired by the renowned da Vinci system, the Meere Company in Korea has been developing the new Revo-i system since 2007. Revo-i is a robot for laparoscopic surgeries that will be used to treat cancer. It is undergoing human testing this year and is estimated to cost a third of the price of the da Vinci system.

Biography

Dr. Koon Ho Rha is Professor of Urology and Robotic and Minimally Invasive Surgery Center. He received both his premedicine education magna cum laude and his M.D. degree from the Yonsei University, Seoul. Dr. Rha was trained during his urological rotating residency training at the Mayo Clinic in Minnesota. He underwent fellowship training in minimally invasive and laparoscopic surgery at the Johns Hopkins Medical Institution as Engineering and Urology endowed fellow, and served as visiting Assistant Professor in Urology at the Johns Hopkins University School of Medicine. During his stay, he also completed “Business in Medicine” a 1-year MBA program at the School of Business Administration and Education.

Prior to his return to Yonsei in 2003, Dr. Rha obtained extensive experience in minimally invasive and laparoscopic surgery at Yonsei University and co-invented a novel surgical procedure “Video-Assisted Minilaparotomy Surgery (VAMS)”, which is now commercially available through Thompson Surgical, Inc. Later at Johns Hopkins, he continued his interests in the field of minimally invasive surgery/laparoscopy, and conducted further scientific studies with Dr. Louis R. Kavoussi, the leading pioneer on laparoscopic and robotic surgery. Dr. Rha set up the robotic surgery program at Yonsei University in 2005 which now became the most successful robotic program in the world with more than 21,000 cases. During last 10 years, Dr. Rha has performed the most robotic urological cases in Asia with more than 3000 cases of robotic cases including some 2500 cases of robotic prostatectomies. With cumulative experiences, Dr. Rha’s team developed world’s first robotic approaches of nephroureterectomies and single-incision partial nephrectomies. He has given more than 500 lectures on robotic surgery. He also performed live surgery or proctored more than 60 occasions, including US, France, Italy, Czech Republic, China, Japan, Taiwan, Singapore, Hong Kong, Saudi Arabia, Thailand and Malaysia. With interest in developing surgical robotic platform and devices, Dr. Rha lead the development Korean surgical (Revo-I, MeereCompany) since 2007 and successfully finished first human trial on robotic prostatectomy in 2017.

Dr. Rha has more than 280 peer-reviewed scientific publications on minimally invasive urological surgery. He is the Immediate Past-President of Korean Endourological Society served as past president of Engineering and Urology Society and member of the American Urological Association, American College of Surgeons, Endourological Society, and Society of Laparoendoscopic Surgeons. Dr. Rha will host Video Urology and East Asia Endourology Conference in June 2019 in Seoul.

CURRICULUM VITAE : Koon Ho RHA, M.D., FACS, Ph.D.

EDUCATION
2016 Harvard School of Public Health “Healthcare Executives Leadership Strategies”
2015 Yonsei University School of Public Health “Globalization of Healthcare”
2010 Harvard School of Public Health “Leadership in Academic Medicine”
2002-2003 Johns Hopkins University, School of Business/Medicine
: “Business in Medicine” Certificate Program”, Baltimore, MD, USA
(courses in managed care, accounting, health care finance, and leadership)
1993-1999 Yonsei University, Graduate School, Seoul, Korea; PhD
1988-1992 Yonsei University, Seoul, Korea; MD (Graduated with Honors)
1980-1984 South Pasadena High School, South Pasadena, CA, USA

POSTDOCTORAL TRAINING
2002-2003 Society for Urology and Engineering Fellow
Johns Hopkins Hospital, Baltimore, Maryland, USA
1995 Visiting Resident; Urology, Mayo Clinic, Rochester, Minnesota, USA
1993-1997 Resident, Urology, Severance Hospital, Yonsei University, Seoul, Korea

HOSPITAL/ACADEMIC APPOINTMENTS
2016.11- present : Chief Strategy Officer, Yonsei University Health System
2014.9. – 2016.8 : Chief Operating Officer, Severance Hospital, Yonsei University
2012.9 – 2014.8 : Associate Dean, Academic Affairs, Yonsei University
2002.4. – present: Professor; Department of Urology, Yonsei University
1998 - present: Consultant in Urology, 121 General Hospital; US Army, Seoul, Korea
2002 - 2003 Faculty (Visiting Assistant Professor); Johns Hopkins University, USA
2000 - 2002.3.: Instructor in Urology, Yonsei University, College of Medicine
1998 - 2000: Urologist in Chief, Capital Armed Forced Hospital, Seoul, Korea

CERTIFICATION AND LICENSURE
2003 DaVinci Certification 2003 Zeus Certification
1997 Korean Board of Urology (#1108)
1992 ECFGM Certification (#0-457-651-8)

PATENTS
Rha KH and Yang SC. (2002), “Surgical instruments and method for creating anatomic working space in minilaparotomy procedure”, US Patent No. 6,878,110

MEMBERSHIP IN PROFESSIONAL SOCIETIES
Fellow, American College of Surgeons (FACS)
Past President, Engineering and Urology Society, USA
Associate Editor, KJU, J Endourology, BJU Int, J Robotic Surgery
Expert, International Healthcare Subject Matter Experts (US Department of Army)

SCI PEER-REVIEWED SCI PUBLICATIONS (300)
CLINCIAL EXPERIENCE : 3000 robotic cases (2500 prostatectomies)
Live Surgery/Proctorship in 14 different countries including USA, France, Italy
First Korean Robot (REVO-i) Prostatectomy (2016.9)

Abstract

Human hands and arms have the inherent safety and remarkable performance. They can precisely manipulate small objects in the submillimeter scale and also lift the entire human body weight. Moreover, they can safely interact with others at high speeds and compliantly absorb impact and overload. Recently, aiming at providing safe human-robot interaction capability, various collaborative robots (cobots) have been introduced in the market. However, most of these robots based on the traditional robotic components and mechanisms are no match for aforementioned human performances and properties. Many biomimetic and bioinspired robots are now being tried, mostly focusing on achieving human-level safety and compliance rather than payload and precision. In this presentation, the essential principles of the biomechanics of human hands and arms causing the aforementioned differences are introduced. Instead of mimicking the anatomical shapes, the principles are adopted from the level of fundamental components. Our recent results of the efforts to merge these biomechanical principles and mechanical advantages, including the fast and safe manipulator AMBIDEX and the robust and dexterous hand FLLEX hand, are presented.

Biography

Yong-Jae Kim received the M.S. and Ph.D. degrees in electrical engineering and computer science from Korea Advanced Institute of Science and Technology, Daejeon, South Korea, in 1998 and 2003, respectively. He was a Research Staff Member with Samsung Advanced Institute of Technology, South Korea. He is currently an Associate Professor with Korea University of Technology and Education, Cheonan, South Korea. His research interests include electromechanical design and control of safe manipulators, bioinspired robotic hands, soft-wearable robots, surgical robots, and humanoid robots for physical human–machine interaction. He recently received the 1st prize of IROS2018 Fan Robotic Challenge, and the manipulator AMBIDEX developed with the support of NAVER Labs Co. received Innovation Award of CES2019

Abstract

The horticulture industry faces increasing pressure as demands for high-quality food and competitive productivity grow. To cater for these requirements, better pollination and harvesting systems can be used. The University of Auckland CARES developed an multi-purpose orchard robot system that performs pollination and fruit harvesting for kiwi and apple plants. In this talk, we share our experience to make this robot works in real environment.

Biography

Ho Seok AHN is a senior lecturer, which is equivalent to Associate Professor at major universities abroad, at the Department of Electrical, Computer and Software Engineering, University of Auckland, New Zealand, since 2015. He received his B.S. degree in Information and Communication Engineering from Sungkyunkwan University, Republic of Korea, and his Ph.D. degree in Electrical Engineering and Computer science from Seoul National University, Republic of Korea, in 2005 and 2010, respectively. He was a senior researcher at Korea Institute of Industrial Technology (KITECH), Republic of Korea, from 2010 to 2012. He was a research scientist at Advanced Telecommunications Research Institute International (ATR), Japan, from 2012 to 2013. He was a postdoctoral researcher at the University of Auckland, New Zealand, from 2013 to 2015. His research interests include social robots, healthcare robots, and agricultural robots working in real-world

Abstract

Surgical robotics field is one of the important technology to achieve minimally invasive surgery. The robotics itself is advancing and more role is becoming sophisticated manner with surrounding information technologies using IoT in the operating room. Reliable and concrete medical information are utilized for predicting functional prognosis or survival prognosis with AI(Artificial Intelligence)/BI(Business Intelligence) methods. In this presentation, our current research projects including Smart Cyber Operating Theater (SCOT^®), Clinical Information Analyser, and MRLink middleware architecture for master-slave surgical robots toward smart surgery.

Biography

He received Ph.D. from the University of Tokyo on March, 1999, and become Lecturer, Dept. of Biotechnology, Tokyo Denki University from 2000-2005. From 2005, he moved as an Associate Professor, Dept. of Mechano-Informatics, Graduate School of Information Science and Technology, the University of Tokyo. From 2014, he became the current position.

He received several honors/ awards including Ogino award, Japan Society of Medical and Biomedical Engineering (2000), JSCAS Young Investigator Award (Hitachi Medico Prize), Gold prize (2006), Good Design Award (2016 as a co-researcher), Japan Innovation Award (2018 as a co-researcher)

Abstract

With recent introduction of affordable sensor and actuator hardware, as well as a huge increase in computing power, the wide adoption of intelligent robots is finally becoming a reality. Such a movement is greatly accelerated by recent robotic competitions, which requires a general, self-contained robot system that can autonomously work in uncontrolled environments. In this talk, we present how we build a modular, general purpose robotic software framework from simple and efficient software modules, and how the software framework has been successfully used for two recent international home service robotics competitions, the RoboCup@Home and World Robot Summit.

Biography

Seung-Joon Yi is an assistant professor in the Department of Electrical Engineering at the Pusan National University. He received his B.S. in electrical engineering and Ph.D. in machine learning from Seoul National University, and worked at the University of Pennsylvania as a visiting scholar and a postdoctoral researcher. Before joining PNU, he was a researcher at Naver Labs. His main research interest is leveraging machine learning approaches to build more intelligent robotic systems.

Abstract

Nowadays collaborative robots are believed to bring a next gold era in the industrial robot market. In particular, small and medium-sized manufacturers are definitely one of those who get benefits from cobot-based automation. In this talk I’d like to share our experience in developing the new cobot, Indy, to open a low-cost industrial cobot market. Particularly I will focus on how robotics control algorithms can help us to implement a very robust collision detection capability and a stable direct teaching based on impedance control, and how deep learning algorithms improves the control performance and paves the new way to a very robust low-cost vision system for cobot domains.

Biography

2013~ present: Founder and CEO of Neuromeka
2014~present: Adjunct professor in ME, POSTECH
2007~2012: CTO in SimLab
2000~2001: Visiting scholar in Hiroshima University (Japan)
1994~1999: Ph.D in Robotics Lab, ME, POSTECH
1992~1994: M.S. in Robotics Lab, ME, POSTECH
1988~1992: B.S. in ME, POSTECH