Can we build Baymax? Humanoids 2020

Objectives

We are excited to announce our 6th Can we build Baymax? workshop! This workshop will be on topics related to 'Superhuman Abilities in Current Humanoids.' Since the first workshop was organized in 2015, our series has taken place at the IEEE-RAS International Conference on Humanoid Robots (Humanoids 2020) every year. Baymax is a humanoid character in the Disney feature animation “Big Hero 6.” It is a healthcare robot with an inflatable body, capable of walking, bumping into surrounding objects, learning motions and physically interacting with people. However, in the real world, it is not easy to build such a robot. In the previous workshops, we have discussed topics on soft robot mechanisms, sensors, control, fail-safety, learning and social interaction of humanoid robots. As a continuation of the discussion, this workshop will bring together researchers looking for superhuman abilities in current humanoid robot technology. In particular, we will tackle challenges in superhuman sensors, actuators and processors, dynamic robots such as robot athletes, gymnasts and entertainers, size-scaled humanoid robots, powerful exoskeleton/prosthesis, and superhuman perception and intelligence.

We invite you to contribute and to participate in this workshop.

The workshop's topics include, but are not limited to:

Superhuman sensors, actuators and processors
Robot athletes, gymnasts and entertainers
Giant robots
Powerful exoskeletons and prostheses
Superhuman perception and intelligence

Speakers:

Gordon Cheng, Technical University of Munich, Germany
Dennis Hong, University of California, Los Angeles (UCLA), USA
Masatoshi Ishikawa, University of Tokyo, Japan
Oussama Khatib, Stanford University, USA
Scott Kuindersma, Boston Dynamics, USA
Naveen Kuppuswamy, Toyota Research Institute (TRI), USA
Jerry Pratt, Institute for Human & Machine Cognition (IHMC), USA
Nikos Tsagarakis, Italian Institute of Technology (IIT), Italy

Previous Workshops:

Workshop Schedule

05:20	08:20	14:20	21:20
Chris Atkeson, Carnegie Mellon University (CMU), USA Welcome and Introduction
05:30	08:30	14:30	21:30
Masatoshi Ishikawa, University of Tokyo, Japan Super Sensing and Manipulation for Dynamic Intelligent Robots - We can build a robot too fast to see High-speed vision or high-speed image processing can be implemented by using parallel processing vision chips and opens new applications in robotics and related research fields. We developed a pixel-wise fully parallel processing vision chip and a stacked CMOS vision chip which has a layer of a high-speed CMOS imager and a layer of a column parallel processing element array (1,304 PEs). Those chips can carry out high-speed image processing at 1,000 fps with low latency in the chips. As the video rate is not enough for controlling dynamics of intelligent robots, such high-speed vision is a key technology for realizing high-speed and low latency intelligent robots based on visual feedback. In this talk, high-speed vision devices and systems, hierarchical parallel processing architecture for intelligent robots, high-speed robots controlled by high-speed vision such as throwing and batting robots, a dexterous hand, a bipedal running robot, and game playing robots will be shown. In addition, demonstrations of dynamic projection mapping will be shown as examples of interactive reality with robots. Abstract
06:00	09:00	15:00	22:00
Gordon Cheng, Technical University of Munich (TUM), Germany Enabling superhuman sensation and action After developing high-performance humanoid robots for 20 years, yet still, there is more to be done. Here I will give an overview of past systems and present a peek at the future. Abstract
06:30	09:30	15:30	22:30
Nikos Tsagarakis, Italian Institute of Technology (IIT), Italy Development of Human Compatible Physical Performance Robots The talk will provide an introduction of the humanoids platforms developed within the Humanoid and Human Mechatronics Lab at IIT, introducing their mechatronics and actuation design approaches towards systems that can demonstrate high physical capabilities and sturdiness. The application of these design principles into the development of compliant and torque control joints and the overall design implementation of these humanoid or semi-humanoid robots and their control tools will be demonstrated in highly demanding physical tasks. Finally, design principles targeting to improve the energetic economy of forthcoming prototypes will be also presented. Abstract
07:00	09:00	16:00	23:00
Naveen Kuppuswamy, Toyota Research Institute (TRI), USA Super-Support: Towards soft, caring and collaborative robots
07:30	10:30	16:30	23:30
Discussion (20 min)
07:50	10:50	16:50	23:50
Break (10 min)
08:00	11:00	17:00	24:00
Scott Kuindersma, Boston Dynamics, USA The Art and Engineering Behind a Humanoid Dance Routine
08:30	11:30	17:30	00:30
Jerry Pratt, Institute for Human & Machine Cognition (IHMC), USA Challenges and some progress towards achieving human level range of motion, torque, speed, mass, volume, and force fidelity in a humanoid robot
09:00	12:00	18:00	01:00
Dennis Hong, University of California, Los Angeles (UCLA), USA Our Three Approaches Towards Building Superhuman Humanoids In our lab RoMeLa, the Robotics and Mechanisms Laboratory at UCLA, we have built robots with all different shapes, sizes and morphologies, including a dozen successful humanoid robots. Our humanoid robots we have developed can walk but barely run, and can do only very simple manipulation tasks. None of them are even close to the capabilities of what we humans naturally possess. Our ultimate goal is to build robots that can help people in tasks that humans cannot do due to the speed, strength, skills required that exceeds what we humans can do. Superhuman abilities in humanoids will enable them to be used at dangerous disasters sites and to rescue lives. If this sounds like a superhero movie, then you have it right. But how can we build such a robot when our robots can only barely mimic the capabilities our abilities? In this talk we present our three approaches we are taking towards building a humanoid robot with superhuman abilities using specific examples of robots developed at RoMeLa, including CHARLI, BALLU, ALPHRED, NABi, THOR, etc. and also provide a sneak peak of our newest next generation humanoid robot ARTEMIS. Abstract
09:30	12:30	18:30	01:30
Oussama Khatib, Stanford University, USA The Era of Human‐Robot Collaboration: Deep Sea Exploration The promise of oceanic discovery has intrigued scientists and explorers, whether to study underwater ecology and climate change, or to uncover natural resources and historic secrets buried deep at archaeological sites. This quest to explore the oceans requires expert human access, but much of the oceans is inaccessible to humans. Reaching these depths is imperative for understanding the ecology, maintaining, and repairing underwater structures, and working in archaeological sites over this immensely unknown part of our planet. This challenge demands human‐level abilities at depths where humans cannot or should not be. Ocean One was conceived to create a robotic diver with a high degree of autonomy for physical interaction with the environment while connected to a human expert through an intuitive interface. The human expert instructs the robot through high‐level cognitive guidance and can intervene at any level of the operation through a high‐bandwidth sensory‐rich visual and haptic interface. The robot was deployed in an expedition in the Mediterranean to Louis XIV’s flagship Lune, lying off the coast of Toulon at ninety‐one meters. Ocean One’s ability to distance humans physically from dangerous and unreachable spaces while connecting their skills, intuition, and experience to the task promises to fundamentally alter remote work. Ocean One’s achievement has shown how human‐robot collaboration induced synergy can expand our abilities to reach new resources, build and maintain infrastructure, and perform disaster prevention and recovery operations ‐ be it deep in oceans and mines, at mountain tops, or in space. Abstract
10:00	13:00	19:00	02:00
Discussion (30 min)
10:30	13:30	19:30	02:30
Workshop Wrap-up

Speakers

Gordon Cheng, Technical University of Munich, Germany
Dennis Hong, University of California, Los Angeles (UCLA), USA
Masatoshi Ishikawa, University of Tokyo, Japan
Oussama Khatib, Stanford University, USA
Scott Kuindersma, Boston Dynamics, USA
Naveen Kuppuswamy, Toyota Research Institute (TRI), USA
Jerry Pratt, Institute for Human & Machine Cognition (IHMC), USA
Nikos Tsagarakis, Italian Institute of Technology (IIT), Italy

Gordon Cheng
Technical University of Munich

Gordon Cheng holds the Chair of Cognitive Systems with regular teaching activities and lectures. He is Founder and Director of Institute for Cognitive Systems, Faculty of Electrical and Computer Engineering at Technical University of Munich, Munich/Germany. He is also the coordinator of the CoC for Neuro-Engineering - Center of Competence Neuro-Engineering in the Department of Electrical and Computer Engineering.

Formerly, he was the Head of the Department of Humanoid Robotics and Computational Neuroscience, ATR Computational Neuroscience Laboratories, Kyoto, Japan. He was the Group Leader for the newly initiated JST International Cooperative Research Project (ICORP), Computational Brain. He has also been designated as a Project Leader/Research Expert for National Institute of Information and Communications Technology (NICT) of Japan. He is also involved (as an adviser and as an associated partner) in a number of major European Union Projects.

Over the past ten years Gordon Cheng has been the co-inventor of approximately 20 patents and is the author of approximately 250 technical publications, proceedings, editorials and book chapters.

Institute for Cognitive Systems (ICS)

Dennis Hong
University of California, Los Angeles (UCLA)

Dr. Dennis Hong, a TED alumnus, is a Professor and the Founding Director of RoMeLa (Robotics & Mechanisms Laboratory) of the Mechanical & Aerospace Engineering Department at UCLA. His research focuses on robot locomotion and manipulation, autonomous vehicles and humanoid robots. He is the inventor of a number of novel robots and mechanisms, including the ‘whole skin locomotion’ for mobile robots inspired by how amoeba move, a unique three-legged waking robot STriDER, an air-powered robotic hand RAPHaEL, and the world’s first car that can be driven by the blind. His work has been featured on numerous national and international media. Washington Post magazine called Dr. Hong “the Leonardo da Vinci of robots.”

Dr. Hong has been named to Popular Science’s 8th annual “Brilliant 10”, honoring top scientists younger than 40 years of age from across the United States, “Forward Under 40” by the University of Wisconsin-Madison Alumni Association, and also honored as “Top 40 Under 40” alumni by Purdue University. Hong’s other past awards include the National Science Foundation’s CAREER award, the SAE International’s Ralph R. Teetor Educational Award, and the ASME Freudenstein / GM Young Investigator Award to name a few. Dr. Hong also actively leads student teams for various international robotics and design competitions winning numerous top prizes including the DARPA Urban Challenge where they won third place and the $500,000 prize, and the RoboCup, the international autonomous robot soccer competition where his team won First Place in both the Kid-Size and Adult-Size Humanoid divisions and brought the Louis Vuitton Cup Best Humanoid Award to the United States for the very first time.

Dr. Hong received his B.S. degree in Mechanical Engineering from the University of Wisconsin-Madison (1994), his M.S. and Ph.D. degrees in Mechanical Engineering from Purdue University (1999, 2002).

He is also a serious gourmet chef and a magician performing annual charity magic shows and lectures on the science of magic.

The Robotics & Mechanisms Laboratory (RoMeLa)

Masatoshi Ishikawa
University of Tokyo

Masatoshi ISHIKAWA received the B.E., M.E. and Dr. Eng. degrees in mathematical engineering and information physics in 1977, 1979 and 1988, respectively, from the University of Tokyo. He was a researcher at Industrial Products Research Institute, Tsukuba, Japan, from 1979 to 1989. He moved to the University of Tokyo as an associate professor in 1989. He was a professor of information physics at University of Tokyo from 1999 to 2020. He was an executive adviser to the president, a vice-president and an executive vice-president of the University of Tokyo, from 2002 to 2004, from 2004 to 2005, and from 2005 to 2006, respectively. He is a project professor at the Data Science Division, Information Technology Center, University of Tokyo from 2020. His current research interests include high-speed vision, sensor fusion, high-speed intelligent robots, visual feedback, dynamic intelligent systems, and dynamic interaction.

Ishikawa Group Laboratory

Ishikawa Group YouTube Channel

Oussama Khatib
Stanford University

Oussama Khatib received his PhD from Sup’Aero, Toulouse, France, in 1980. He is Professor of Computer Science and Director of the Robotics Laboratory at Stanford University. His research focuses on methodologies and technologies in human-centered robotics, haptic interactions, artificial intelligence, human motion synthesis and animation. He is President of the International Foundation of Robotics Research (IFRR) and a Fellow of the Institute of Electrical and Electronic Engineers (IEEE). He is Editor of the Springer Tracts in Advanced Robotics (STAR) series, and the Springer Handbook of Robotics, awarded the American Publishers Award for Excellence in Physical Sciences and Mathematics. He is recipient of the IEEE Robotics and Automation (IEEE/RAS) Pioneering Award (for his fundamental contributions in robotics research, visionary leadership and life-long commitment to the field), the IEEE/RAS George Saridis Leadership Award, the Distinguished Service Award, the Japan Robot Association (JARA) Award, the Rudolf Kalman Award, and the IEEE Technical Field Award. Professor Khatib is a member of the National Academy of Engineering.

Stanford Robotics Lab

Scott Kuindersma
Boston Dynamics

Scott Kuindersma is a Research Scientist and the Atlas team lead at Boston Dynamics. Previously he was an Assistant Professor of Engineering and Computer Science at Harvard University and a postdoc in the Robot Locomotion Group at MIT. His work is focused on deploying optimization algorithms to produce high-performance behaviors in mobile robots.

Boston Dynamics

Naveen Kuppuswamy
Toyota Research Institute (TRI)

Naveen Kuppuswamy is a Senior Research Scientist and Tactile Perception and Control Lead in the Dextrous Manipulation department. Naveen holds several years of academic and industry experience in working on themes of tactile sensing, soft robotics and robot controls on a wide variety of platforms. He is currently leading a research effort in expanding the scope and robustness of domestic manipulation by exploiting softness and tactile perception within the control - a recent outcome of this effort has been the development of perception and control algorithms and modelling techniques for the TRI "Soft-bubble" sensor and gripper systems.

Dr. Kuppuswamy received a Bachelor of Engineering at Anna University, Chennai, India in 2005, MS in Electrical Engineering at the Korea Advanced Institute for Science and Technology (KAIST), Daejon, South Korea in 2007 and a PhD in Artificial Intelligence at the University of Zurich, Switzerland in 2014 under a Marie Curie Fellowship. Since graduation, he has also spent some time as a Postdoctoral Researcher at the Italian Institute of Technology, Genova, Italy, between 2014 and 2016 and as a Visiting Scientist with the Robotics and Perception Group at the University of Zurich between 2016 and 2017. His research and experience has covered diverse themes in robotics such as cognitive control architectures, modelling and control of wheeled mobile robots, tendon-driven underwater soft robots, tactile perception for humanoids, quadrotor trajectory optimization, educational robots and in human movement modelling and robot-human physical interaction and has authored several publications in leading peer-reviewed journals and conferences. He is also keenly interested in STEM education of under-represented communities around the world. His research has been recognized through awards such as the 2019 Best Paper Award from the IEEE RA-L (Robotics and Automation - Letters) Journal, as a finalist for Best Student Paper at the Robotics Science and Systems Conference in 2017, among others. He is a frequent contributor to the Drake simulation and control library and is actively involved as an editor and reviewer for several of the leading journals and conferences in robotics and frequently gives guest lectures at multiple graduate-level classes at MIT on themes of tactile perception and control. Naveen is deeply passionate about using robots to assist people and improving the quality of life of those in need.

Toyota Research Institute

Jerry Pratt
Institute for Human & Machine Cognition (IHMC)

Jerry Pratt (Ph.D., M.Eng., and B.S. degrees from M.I.T. in Computer Science and B.S. degree from M.I.T. in Mechanical Engineering) leads a research group at IHMC that concentrates around the understanding and modeling of human gait and the applications of that understanding in the fields of robotics, human assistive devices, and man-machine interfaces. Current projects include Humanoid Avatar Robots for Co-Exploration of Hazardous Environments, FastRunner Robot, and Exoskeletons for Restoration of Gait in Paralyzed Individuals. Jerry was the team lead for Team IHMC in the DARPA Robotics Challenge (DRC) project. In 2015 IHMC won second place in the DRC finals. In 2013 Team IHMC achieved first place in the Virtual Robotics Challenge and second place in DARPA Robotics Challenge Trials. Before coming to IHMC, Jerry was the President of Yobotics, Inc., a small company that he cofounded in 2000. At Yobotics, Jerry helped develop the RoboKnee, a powered exoskeleton that allowed one to carry large loads while hiking over rough terrain with little effort. Prior to founding Yobotics, Jerry worked at the M.I.T. Leg Laboratory, where he designed, built, and controlled several bipedal robots. His approach of maximizing speed, agility, and biological similarity through the understanding of biological counterparts, is helping to remove the stereotype of robots as being clunky, jerky-moving machines. Jerry’s hobbies include sailing, playing board games, football, basketball, and paintball. Jerry recently founded Boardwalk Robotics, Inc. with the goal to further advance humanoid robots for commercial applications

IHMC Robotics

Nikos Tsagarakis
Italian Institute of Technology (IIT)

Nikos Tsagarakis is Tenured Senior Scientist and Principal Investigator of the Humanoid & Human Centred Mechatronics (HHCM) Research Line, a leading research laboratory at IIT with strong expertise in robot design, modelling and control, and in the development of new mechatronics components (actuation and sensing). HHCM is the home laboratory where the compliant humanoids COMAN and WALK-MAN and the CENTAURO hybrid wheeled-legged quadrupedal manipulation platform were developed. Nikos Tsagarakis was the coordinator of EU project WALKMAN and has served as principal investigator for several EU projects in the past including VIACTORS, SAPHARI, AMARSI, WEARHAP and most recently for CogiMON, CENTAURO and EUROBENCH.

He is an author or co-author of over 350 papers in research journals and at international conferences and holds 16 patents. He has received the Best Jubilee Video Award at IROS (2012), the 2009 PE Publishing Award from the Journal of Systems and Control Engineering and prizes for Best Paper at ICAR (2003) and the Best Student Paper Award at Robio (2013). He was also a finalist for Best Entertainment Robots and Systems - 20th Anniversary Award at IROS (2007) and finalist for the Best Manipulation paper at ICRA (2012), the Best Conference Paper at Humanoids (2012), the Best Student Papers at Robio (2013) and ICINCO (2014), Best Interactive Paper finalist at Humanoids (2016) and Best Interactive Paper at Humanoids (2017). He has been in the Program Committee of over 60 international conferences including IEEE ICRA, IROS, RSS, HUMANOIDS BIOROB and ICAR. Nikos Tsagarakis was Technical Editor of IEEE/ASME Transactions on Mechatronics (2012-2015) and from 2014 served on the Editorial Board of the IEEE Robotics and Automation Letters. He is currently a Senior Editor of IEEE/ASME Transactions on Mechatronics.

Humanoids and Human Centered Mechatronics (HHCM)

Organizers

Chris Atkeson, Carnegie Mellon University
Joohyung Kim, University of Illinois Urbana-Champaign
Jinoh Lee, German Aerospace Center (DLR)
Katsu Yamane, Bosch Research & Technology Center
Alex Alspach, Toyota Research Institute

Christopher G. Atkeson

I am a Professor in the Robotics Institute and Human-Computer Interaction Institute at Carnegie Mellon University. My life goal is to fulfill the science fiction vision of machines that achieve human levels of competence in perceiving, thinking, and acting. A more narrow technical goal is to understand how to get machines to generate and perceive human behavior. I use two complementary approaches, exploring humanoid robotics and human aware environments. Building humanoid robots tests our understanding of how to generate human-like behavior, and exposes the gaps and failures in current approaches.

build-baymax.org

Joohyung Kim

Joohyung Kim is currently an Associate Professor of Electrical and Computer Engineering at the University of Illinois Urbana-Champaign. His research focuses on design and control for humanoid robots, systems for motion learning in robot hardware, and safe human-robot interaction. He received BSE and Ph.D. degrees in Electrical Engineering and Computer Science (EECS) from Seoul National University, Korea, in 2001 and 2012. He was a Research Scientist in Disney Research from 2013 to 2019. Prior to joining Disney, he was a postdoctoral fellow in the Robotics Institute at Carnegie Mellon University for the DARPA Robotics Challenge in 2013. From 2009 to 2012, he was a Research Staff Member in Samsung Advanced Institute of Technology, Korea, developing biped walking controllers for humanoid robots.

KIMLAB (Kinetic Intelligent Machine LAB)

Jinoh Lee

Jinoh Lee is a Research Scientist with the Institute of Robotics and Mechatronics, German Aerospace Center (DLR), Germany. He received the B.S. degree in mechanical engineering from Hanyang University, Seoul, South Korea, in 2003 (awarded Summa Cum Laude), and the M.Sc. and Ph.D. degrees in mechanical engineering from Korea Advanced Institute of Science and Technology, Daejeon, South Korea, in 2012. Prior to joining DLR in 2020, he held the Research Scientist position at the Department of Advanced Robotics, Istituto Italiano di Tecnologia (IIT), Italy. His professional focus is on robotics and control engineering, which include manipulation of highly redundant robots such as dual-arm and humanoids, robust control of nonlinear systems and compliant robotic system control for safe human-robot interaction.

Institute of Robotics and Mechatronics

Katsu Yamane

Dr. Katsu Yamane is a Principal Research Scientist at Bosch Research. He received his B.S., M.S., and Ph.D. degrees in Mechanical Engineering in 1997, 1999, and 2002 respectively from the University of Tokyo, Japan. Prior to joining Bosch Research in 2021, he was a Senior Scientist at Honda Research Institute USA, Senior Research Scientist at Disney Research, an Associate Professor at the University of Tokyo, and a postdoctoral fellow at Carnegie Mellon University. Dr. Yamane is a recipient of King-Sun Fu Best Transactions Paper Award and Early Academic Career Award from IEEE Robotics and Automation Society, and Young Scientist Award from Ministry of Education, Japan. His research interests include humanoid robot control and motion synthesis, physical human-robot interaction, character animation, and human motion simulation.

katsuyamane.com

Alex Alspach

Alex designs and builds soft systems for sensing and manipulation at Toyota Research Institute (TRI), where he currently leads the Tactile Team. He earned his bachelor's and master's degrees at Drexel University with time spent in the Drexel Autonomous Systems Lab (DASL) and KAIST's HuboLab. After graduating, Alex spent two years at SimLab in Korea developing and marketing tools for manipulation research. While there, he also worked with a production company to develop artists' tools for animating complex, constrained, synchronized industrial robot motions. Prior to joining TRI, Alex developed soft huggable humanoid robots and various other creative robotic systems at Disney Research with Joohyung and Katsu!

alexalspach.com/cv
punyo.tech
Toyota Research Institute (TRI) Careers - We're hiring!