The 12th International Conference on Ubiquitous Robots and Ambient Intelligence [URAI 2015]
October 28~30, 2015 / 3F, Convention Halls, Exhibition Center II, KINTEX, Goyang city, Korea
Dongheui Lee (Technical University of Munich (TUM), Germany)
Presentation Title : Incremental Robot Skill Learning by Human Motion Retargetting and Physical Human Guidance
Abstract : Research on skill acquisition and generalization to a different scenario has grown steadily in importance and became a main topic of robotics research. Imitation learning, one of the main streams for robot learning, provides an efficient way to learn new skills through human guidance, which can reduce time and cost to program the robot. Recent research on incremental skill learning through physical human robot interactions at the dynamic human robot interaction lab at TUM will be introduced. The proposed method allows to teach a robot how to learn synchronized and coordinated whole body motions. Our controller provides a human user comfortable assistance for physical guidance beyond the gravity compensation. External force torque estimation allows further possibilities. One is teaching motion primitives of a legged humanoid robot by taking human intervention into consideration for a balancing problem. Another extension is teaching multiple tasks like end-effector motions and null space motions. The proposed algorithms are verified on multiple robotic systems including full size humanoid robots.
Biography : Dongheui Lee is an assistant professor at the Institute of Automatic Control Engineering, Department of Electrical and Computer Engineering, Technische Universität München, Munich, Germany since October 2009. She is the head of Dynamic Human Robot Interaction for Automation System Lab and Carl-von-Linde Fellow at TUM Institute for Advanced Study. She received her B.S. and M.S degrees at the department of mechanical engineering, Kyunghee University, Korea, in 2001 and 2003, respectively. She worked as a research scientist at the Advanced Robotics Research Center, Korea Institute of Science and Technology (KIST) from 2001 to 2004. In 2007, she received her PhD degree at the department of Mechano‐Informatics, the University of Tokyo, Japan. After receiving PhD degree she joined the center of Information and Robot Technology at the University of Tokyo as a project assistant professor. Her research interests include human motion understanding, human robot interaction, machine learning in robotics, and mobile robot navigation. She is the Coordinator of euRobotics Topic Group on physical Human Robot Interaction and the co-coordinator of TUM Center of Competence Robotics, Autonomy and Interaction.
Woosoon Yim (University of Nevada, Las Vegas)
Presentation Title : Unmanned Aerial System for First Responders
Abstract : Enhancing the situational awareness capabilities of first responders for disaster remediation is a challenging task during emergency events in natural or man-made disasters or hazards. One of the major challenges is to act decisively based on available information and making high-quality real-time situational awareness to effectively safeguard civilians and in-field personnel. Employing unmanned autonomous or aerial systems (UAS) can be an effective means of achieving this goal. Depending on the area search scenarios, it can be very challenging to use a fixed-wing UAS especially in case where sensors need to be in close proximity to the sources. Advantages of using multicopter-based networked aerial platforms with sensors can be a solution for locating static and dynamic sources, and it requires a well-coordinated robotic control of multiple UAS platforms in predefined flight paths as well as in the adaptively calculated paths based on the data provided by the UAS-mounted detectors. A novel feature of aerial manipulation capability can also be added to the aerial platform to provide capability of interacting with environments when it is needed. Current research projects related with (1) UAS sensors for identifying locations of hot spots using a stereo FLIR camera system; (2) developing plug-and-play interchangeable components for emergency responders; (3) UAS-based method of remote sensing for wide area radiation and source localization will be presented.
Biography : Woosoon Yim is a professor of Mechanical Engineering Department at the University of Nevada, Las Vegas (UNLV). He received his B.S. degree in Mechanical Engineering from Hanyang University in Korea in 1981, and M.S. and Ph.D. degrees in Mechanical Engineering from the University of Wisconsin-Madison in 1984 and 1987, respectively. Since 1987, he has been with the Mechanical Engineering Department in the University of Nevada, Las Vegas, and was a department chairman from 2008 to 2014. His research has been focused in the area of robotics, smart material, and their dynamics and control system development, and has been sponsored by the National Science Foundation and other federal research organizations such as Army Research Lab., Army Research Office, NASA, DOE, and Sandia National Laboratory. Recently, he received awards from NSF PFI (Partnerships for Innovation) and DOE in Unmanned Aircraft System (UAS) development/applications in disaster remediation. Dr. Yim is an ASME Fellow and a recipient of 2011 Harry Reid Silver State Research Award.
Takashi Kubota (ISAS/JAXA, Japan)
Presentation Title : Robotics Technology for Deep Space Exploration
Abstract : Nowadays ISAS/JAXA has studied and developed a new roadmap for deep space exploration. Some working groups have earnestly studied new future lunar or planetary exploration missions including landers or rovers. A new lunar mission on vertical hole exploration on the moon is under study. Some explorers, such as surface exploration rovers, and wide area exploration by airplanes, are also under study. Subsurface exploration by mole-typed robots is also under development. Recently small body exploration missions have received a lot of attention in the world. In small body explorations, especially, detailed in-situ surface exploration by tiny probe is one of effective and fruitful means and is expected to make strong contributions towards scientific studies. JAXA is currently promoting Hayabusa-2 mission, which is the post Hayabusa including sample and return attempt to/from the near earth asteroid. This paper firstly presents future lunar or planetary exploration plans in detail, which consist of lunar, Mars and asteroid exploration. Then this paper presents a robotics technology roadmap based on deep space exploration. This paper introduces the detail of the developed robots and show some experimental results. This paper also presents the intelligent system for navigation, path planning, sampling,, etc.
Biography : Takashi Kubota is a professor at Institute of Space and Astronautical Science (ISAS), Japan Aerospace Exploration Agency (JAXA), Japan. He received Dr. degree in electrical engineering in 1991 from the University of Tokyo. He is also a professor of the graduate school of the University of Tokyo. He is currently a space science program director of ISAS/JAXA. He was a visiting scientist in Jet Propulsion Laboratory in 1997 and 1998. He was in charge of guidance, navigation, and control in asteroid exploration mission HAYABUSA. His research interests include exploration robots, AI in space, Robotics, Image based navigation etc.
Jonghyuk Kim (The Australian National University, Australia)
Presentation Title : Aerial Inertial-SLAM: Progresses and Future Challenges
Abstract : This paper will summarize the recent progresses made in the area of aerial SLAM, particularly focusing on high-dynamics and high-maneuvering flying vehicles. Although there have been significant progresses in SLAM for low-dynamic platforms, such as multi-rotors which has virtually 3∥DOF motion, the high-dynamic vehicles still have many theoretical and practical challenges, such as high-dimensionality and non-linearity in the vehicle state and high-speed sensing and perception. This paper will briefly introduce 1) the partitioned Rao-Blackwellised SLAM approach and 2) GPS raw measurement integration into SLAM to maximize the sensor calibration. Future challenges and outlooks will be discussed.
Biography : Jonghyuk Kim is a senior lecturer at the Research School of Engineering, the Australian National University. He is the recipient of the prestigious Charles Sharpe Beecher Prize and Award from IMechE, UK, 2005 for his contributions to aerial robotics. He co-chaired ACRA (Australasian Conference in Robotics and Automation) in 2008 and program chaired ACRA 2015. He also served the secretarial role to ARAA (Australian Robotics and Automation Association). Dr Kim is currently an associate investigator of ARC Centre of Excellence on Robotics Vision (ACRV) and was part of ARC Centre of Excellence on Autonomous System (CAS) at the University of Sydney. He has contributed to several industrial automation projects with BAE Systems, Ministry of Defense UK and GINTIC Singapore. He has published 80+ papers with collective citation of 1500+.
Jean Ponce (PSL Research University, France)
Presentation Title : Unsupervised Object Discovery and Localization in Images and Videos
Abstract : This paper addresses unsupervised discovery and localization of dominant objects from a noisy collection of images or videos. The setting of this problem is fully unsupervised, without even class labels or any assumption of a single dominant class, and thus far more general than those of typical co localization or weakly supervised localization tasks. Interestingly, our approach also discovers the topology of images/frames associated with instances of the same object class, a role normally left to supervisory information in the form of class labels in conventional image and video understanding methods. We tackle the discovery and localization problem using a part-based region matching approach: Off-the-shelf region proposals are extracted to form a set of candidate bounding boxes for objects and object parts, and these regions are effectively matched across images/frames. For each image/frame, a dominant object is localized by comparing the scores of candidate regions and selecting those that stand out over other regions containing them. Given a video collection, we also associate similar object regions along consecutive frames within the same video, thus achieving unsupervised tracking. Extensive experimental evaluations on standard benchmarks demonstrate that the proposed approach substantially outperforms the current state of the art in co localization, and achieves robust object discovery in challenging mixed-class datasets.
Biography : Jean Ponce received the Doctorat de Troisieme Cycle and Doctoratd’Etat degrees in Computer Science from the University of Paris Orsay
in 1983 and 1988. He held Research Scientist positions at the Institut National de la Recherche en Informatique et Automatique, the MIT Artificial Intelligence Laboratory, and the Stanford University Robotics Laboratory, and served on the faculty of the Dept. of Computer Science at the University of Illinois at Urbana-Champaign from 1990 to 2005. Since 2005, he has been a Professor at Ecole Normale Superieure in Paris, France, where he has been heading the Department of Computer Science since 2011. Dr. Ponce is an IEEE Fellow and the recipient of two US patents, as well as an Advanced ERC grant. He has served on the editorial boards of Computer Vision and Image Understanding, Foundations and Trends in Computer Graphics and Vision, the IEEE Transactions on Robotics and Automation, the International Journal of Computer Vision (for which he served as Editor-in-Chief from 2003 to 2008), and the SIAM Journal on Imaging Sciences. He was Program Chair of the 1997 IEEE Conference on Computer Vision and Pattern Recognition and served as General Chair of the year 2000 edition of this conference. He also served as General Chair of the 2008 European Conference on Computer Vision. Dr. Ponce is the co-author of Computer Vision: A Modern Approach, a textbook that has been translated in Chinese, Japanese, and Russian.