Rediscovery of Anthropology from Robotics

Yoshihiko Nakamura

Professor, University of Tokyo

Abstract: The domain of humanoid robotics is not only to make a bipedal and bimanual robot any more. Technical challenges expand from following the human-like geometry for robot design to asking about the use of the human geometry for the design of robot intelligence. Scientific challenges may include investigating the role of human geometry for human cognition. This may be better explained by the word of "anthropomorphism." Anthropomorphism means how we interpret things as we see humans. To discover the principle of informatics behind anthropomorphism is the main scientific goal of humanoid robotics.

Anthropomorphism lies as the foundation to understand human psychology, human developments, human behaviors, and human society. Many applications will follow from the scope for medical care, social service, and industrial developments. We already find a lot of useful knowledge and technology in our fields of humanoid robotics. Although the talk will introduce some related works being studied by the speakers' team, it will focus more on sharing the scope of the grand challenge in humanoid robotics research and rediscovery of anthropology from robotics.

Bio: Prof. Yoshihiko Nakamura received the B.S., M.S., and Ph.D. degrees from Kyoto University. He was Assistant Professor at Automation Research Laboratory, Kyoto University. After serving as Assistant and Associate Professor at the Department of Mechanical and Environmental Engineering, University of California, Santa Barbara, he joined Department of Mechano-Informatics, University of Tokyo, Japan, and is currently Professor. Dr. Nakamura’s research grows from the foundation of kinematics, dynamics, and control. Humanoid robotics, cognitive robotics, neuro-musculoskeletal human modeling, biomedical systems, and their computational algorithms are the current fields of his research.

How to NOT build a Terminator

Ronald C. Arkin

Professor, Georgia Institute of Technology

Abstract: Given the present pace, direction, and funding of humanoid technological development, it seems that the science fiction vision of a Terminator robot is becoming more and more of a potential reality. Many researchers, perhaps unknowingly or unwittingly, are providing the capabilities to achieve such a platform, i.e., perhaps answering the question of "how to build a terminator". This talk focuses on the ethical questions surrounding the potential creation of robotic platforms with lethal autonomy, striving to answer the question of "how to NOT build a Terminator"), perhaps by either avoiding or restraining the use of lethal force when (not if) this capability is achieved.

Several options are presented that range from complete relinquishment of robotics research (Bill Joy and the Unabomber), to a moratorium (advocated by the United Nations Special Rapporteur to the U.N. Human Rights Council), to banning of such capability (advocated by Human Rights Watch and ICRAC), to directly governing the behavior of lethal robots in a manner consistent with International Humanitarian Law (research in the Georgia Tech Mobile Robot Laboratory).

Bio: Prof. Ronald C. Arkin received the B.S. Degree from the University of Michigan, the M.S. Degree from Stevens Institute of Technology, and a Ph.D. in Computer Science from the University of Massachusetts, Amherst in 1987. He then assumed the position of Assistant Professor in the College of Computing at the Georgia Institute of Technology where he now holds the rank of Regents' Professor and is the Director of the Mobile Robot Laboratory. He also serves as the Associate Dean for Research in the College of Computing at Georgia Tech since October 2008. Arkin's research interests include behavior-based reactive control and action-oriented perception formobile robots and unmanned aerial vehicles, hybrid deliberative/reactive software architectures, robot survivability, multiagent robotic systems, biorobotics, human-robot interaction, robot ethics, and learning in autonomous systems.

The Manipulation Action Language

Yiannis Aloimonos

Professor, University of Maryland

Abstract: Humanoid robots will need to learn the actions that humans perform. They will to recognize these actions when they see them and they will need to perform these actions themselves. In this presentation, which is given in the form of a Socratic dialogue, it is proposed that this learning task can be achieved using the manipulation grammar.

Context-free grammars have been in fashion in linguistics because they provide a simple and precise mechanism for describing the methods by which phrases in some natural language are built from smaller blocks. Also, the basic recursive structure of natural languages, the way in which clauses nest inside other clauses, and the way in which lists of adjectives and adverbs are followed by nouns and verbs, is described exactly. Similarly, for manipulation actions, every complex activity is built from smaller blocks involving hands and their movements, as well as objects, tools and the monitoring of their state. Thus, interpreting a “seen” action is like understanding language, and executing an action from knowledge in memory is like producing language. Several experiments will be shown interpreting human actions in the arts and crafts or assembly domain.

Bio: Prof. Yiannis Aloimonos is Professor of Computational Vision and Intelligence at the Department of Computer Science, University of Maryland, College Park, and the Director of the Computer Vision Laboratory at the Institute for Advanced Computer Studies (UMIACS). He is also affiliated with the Institute for Systems Research and the Neural and Cognitive Science Program. He was born in Sparta, Greece and studied Mathematics in Athens and Computer Science at the University of Rochester, NY (PhD 1990). He is interested in Active Perception and the modeling of vision as an active, dynamic process for real time robotic systems. For the past five years he has been working on bridging signals and symbols, specifically on the relationship of vision to reasoning and language.

Robert O. Ambrose: Humanoids in Space

Deputy Chief, NASA Johnson Space Center

Abstract: NASA and General Motors have recently produced robots strong enough to do work, yet safe enough to be trusted to work near humans. This follows more than a decade of work that produced advances in dexterity, telepresence, remote supervision across time delay, combining mobility with manipulation, human-robot interaction, force control and autonomous grasping. Design challenges included hardware performance and packaging improvements as well as the overall implementation of a system software approach for human safety. The Robonaut 2 (R2) system resulting from this work was launched to the International Space Station (ISS) aboard Space Shuttle Mission STS-133 on February 24, 2011, fulfilling a 15-year dream to put a humanoid robot into space. As the first humanoid robot in space, R2 is arguably the most sophisticated robot in the world, bringing NASA into the 21st century as the world's leader in this field. On the ISS, R2 will be tested performing tasks with human interfaces and with the crew involved in helping to select tasks that are dull, dirty or dangerous. This talk will address related activities and challenges.

Bio: Robert O. Ambrose received his Ph.D. from the University of Texas at Austin in Mechanical Engineering. He received his M.S. and B.S. degrees from Washington University in St. Louis. Dr. Ambrose currently serves as the Division Chief of the Software, Robotics and Simulation (SR&S) Division at tha NASA Johnson Space Center in Houston Texas, USA. The SR&S Division is responsible for flight spacecraft software, space robotics and human system simulations for human spaceflight missions. Dr. Ambrose leads NASA's agency wide Human-Robotics Systems technology project, and is the lead for robotics elements in support of the human exploration architecture study teams.

Rodney Brooks: Humanoids Working Indoors

Professor, Chairman and CTO of Rethink Robotics

Abstract: Humanoid robots, from multiple companies, are starting to be deployed in numbers in manufacturing and packaging applications. High volume low cost research humanoid robots mean that hundreds of new researchers will be experimenting with more applications for indoor humanoids. Demographics suggest that there will be a need for safe humanoids operating in health and elder care domains. The number of humanoids deployed and doing real work for society will grow rapidly over the next decades.

Bio: Rodney Brooks is the founder, chairman, and CTO of Rethink Robotics, a company that is deploying low cost, safe, and easy to train interactive humanoid robots in manufacturing and packaging applications. He was also cofounder, CTO, and board member of iRobot Corporation (nasdaq: IRBT) and is the emeritus Panasonic Professor of Robotics at MIT, where he was director of the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) until 2007. Earlier he was on the faculty at Stanford University and a member of research staff at both Carnegie Mellon and MIT. He received his PhD in Computer Science from Stanford in 1981, after earning degrees in mathematics at the Flinders University of South Australia. He is a member of both the US National Academy of Engineering and of the American Academy of Arts and Sciences, and also a Fellow of the IEEE, ACM, AAAI, and AAAS.

Oussama Khatib: Sindibād: Underwater Humanoid

Professor, Stanford University

Abstract: Exploring and monitoring oceanic marine ecosystems is expensive and challenging. Human divers can only explore these environments during short periods of time and within limited depths. In this presentation we discuss the concept of an underwater robot in the form of a human diver, Sindibād, being developed at Stanford, in collaboration with KAUST and MEKA Robotics. Sinbad is designed to safely explore fragile coral reef environments, like the Red Sea, with the goal of exploring regions that have not been accessible before. Sindibād's compliant lightweight arms, agile body, stereo vision, and tactile fingers will allow the robot to inspect, collect samples, build structures, and perform manipulation tasks under the guidance of a marine biologist. The robot effectively extends the human’s hands to reach and touch remote fragile environments. This is achieved through an intuitive user interface with a haptic device, and an advanced whole body robot controller.

Bio: Oussama Khatib received his Doctorate degree from Sup’Aero, Toulouse, France, in 1980. He is Professor of Computer Science at Stanford University. His research interests include human-centered robotics, humanoid systems, human motion understanding, haptic interaction, and human-friendly robot design. He is the President of the International Foundation of Robotics Research, IFRR. Professor Khatib is Editor of Springer Handbook of Robotics and the Springer Tracts in Advanced Robotics series. He is a Fellow of IEEE and has served as the Program Chair of ICRA 2000, and the General Chair of IROS 2011. He is a recipient of the Japan Robot Association (JARA) Award in Research and Development, the IEEE RAS Pioneer Award in Robotics and Automation for his fundamental pioneering contributions in robotics research, visionary leadership, and life-long commitment to the field.