With the newly founded Munich School of Robotics and Machine Intelligence (MSRM) as an integrative research center, the Technical University of Munich (TUM) has set the goal of developing innovative and sustainable technologies and solutions for central challenges of our time with cutting edge robotics and artificial intelligence research.
With the MSRM, a leading institution shall be established which researches the science and technologies of robotics, artificial intelligence and machine learning – in short machine intelligence – with great visibility and an innovative and sustainable agenda.
As founding director of MSRM, the winner of the German Future Prize, Prof. Sami Haddadin, joined TUM as a joint appointment by the Departments of Electrical and Computer Engineering and Informatics.
The President of the Technical University of Munich, Prof. Wolfgang A. Herrmann cordially invites you to the opening gala on October 26th, 2018 at the Pinakothek der Moderne in Munich as part of the 150-year celebrations of the TUM. Under the theme ”Machine Intelligence: The Science of Robotics and Artificial Intelligence“ the day will include the following highlights:
”Behind the Scenes“ with lectures by leaders in the field of robotics
and artificial intelligence
9 am - 5 pm
”The Machine Apprentice“ brings the invited guests from research,
politics, art and society closer to machine intelligence in a completely
from 6 pm
No 27 to Pinakotheken
U2 to Königsplatz or Theresienstrasse
U3 | U6 to Odeonsplatz or Universität
U4 | U5 to Odeonsplatz
No 154 to Schellingstraße
No 100 (Museumslinie/ museum line): to Pinakotheken
No 100 (Museumslinie/ museum line): to Maxvorstadt / Sammlung Brandhorst
We recommend the use of public transportation. Parking is not available.
Two coach parking spaces are available in front of the Neue Pinakothek. Parking is limited to two hours (with parking disc) between 10 am and 6 pm.
Robotics AI – Cognitive Abilities for Bodies with Motion Intelligence
Nowadays, we are experiencing AI systems with superhuman performance in games, image and speech processing and medical diagnosis. However, the underlying techniques of these systems do not allow the transferability of solutions to different context in the same domain let alone across different domains. In robotics, motion is fundamental! The development of motion abilities requires the co-joint consideration of perception and action while taking into account the physical body - the bodyware – and the interaction with the real world. This is where current AI technologies fail. Robotics AI emphasizes the interaction between cognitive abilities and bodyware to create robots with human-like abilities and even superhuman performance. The talk will discuss current progress (and limitations) of current AI and robotics and describe our efforts towards building humanoid robots with motion intelligence.
Tamim Asfour is full Professor of Humanoid Robotics at the Karlsruhe Institute of Technology (KIT), where he is head of the High Performance Humanoid Technologies lab at the Institute for Anthropomatics and Robotics. His research focuses on the engineering of high performance 24/7 humanoid robotics as well as on the mechano-informatics of humanoids as the synergetic integration of mechatronics, informatics and artificial intelligence methods into humanoid robot systems, which are able to predict, act and interact in the real world. Tamim is the developer of the ARMAR humanoid robot family. In his research, he is reaching out and connecting to neighboring areas in large-scale national and European interdisciplinary projects in the area of robotics in combination with machine learning and computer vision.
Robotics: Body, Intelligence, and Control
Modern approaches to the design of robots are changing the way robots are built, often inspired by a philosophy of embodied intelligence, by which many natural behaviours are deeply rooted in the way our bodies are built. Accordingly, the physical structure of robots is evolving from traditional rigid, heavy industrial machines into soft bodies exhibiting new levels of versatility, adaptability, safety, elasticity, dynamism and energy efficiency. New challenges and opportunities arise for the control of soft robots: for instance, carefully planning for collision avoidance may no longer be a dominating concern, being on the contrary physical interaction with the environment not only allowed, but even desirable to solve complex tasks. Similarly, the traditional use of high-authority feedback loops to control robot motion is challenged by the desire to maintain adaptability to the environment. In this talk I will discuss how these challenges can be addressed, at least partially, by looking at how humans use their own bodies in similar tasks.
Antonio Bicchi is a scientist interested in Robotics and Machine Intelligence. After graduating from the University of Bologna, he has been with the MIT AI Lab in Cambridge, USA, and is now Professor of Robotics at the University of Pisa, Dept. of Information Engineering. Since 2009 he leads the Soft Robotics Lab at the Italian Institute of Technology in Genoa, and from 2013 he is Adjunct Professor at Arizona State University in Tempe, Arizona.
He has published more than 500 peer reviewed papers on international journals, books, and refereed conferences. In 2016 he was the founding Editor in Chief of the IEEE Robotics and Automation Letters, which in only two years became the Journal attracting mostsubmissions in the field. His 2012-2017 ERC Advanced Grant "SoftHands'' established the basis for the theory of soft synergies in human manipulation, led to the design of a new generation of robotic and prosthetic hands, and contributed to establishing the new field of "soft manipulation''. He has organized and co-chaired the First WorldHaptics Conference (2005), launching the major series of gatherings of haptic researchers worldwide.
He served as Vice President for Publications in IEEE Robotics and Automation Society (RAS), as President of the Italian Society of Researchers in Automatic Control, as Editor in Chief of the Conference Editorial Board for the IEEE RAS, as Vice President for Membership and as Distinguished Lecturer of IEEE RAS. He was Editor-in-Chief for the series "Springer Briefs on Control, Automation and Robotics,'' and has served in the editorial board of all top-ranked journals in Robotics (Int.l J. Robotics Research, the IEEE Trans. on Robotics and Automation, IEEE Trans. Automation Science and Engineering, and IEEE RAS Magazine). He has chaired ICRA (the Int. Conf. on Robotics and Automation) in 2016, ISRR (the Int. Symp. on Robotics Research) in 2015, and HSCC (Hybrid Systems: Computation and Control) in 2007. He will chair RSS (Robotics: Science and Systems) in 2019.
Antonio Bicchi is the recipient of several awards and honors. He is a Fellow of IEEE since 2005, and has received the prestigious IEEE Saridis Leadership Award in 2018.
Flexible joint robots: Model-based control revisited
In the early days, joint flexibility in industrial robots equipped with compliant transmissions (harmonic drives, cycloidal gears, belts) was seen only as a negative effect to be milden as much as possible. Suitable stiffening control laws were used to remove position offsets due to static deflections and suppress vibrations during execution of dynamic trajectories. This control design approach led first to approximate solutions (singular perturbation laws for trajectory tracking in robots with relatively stiff joints, as well as compensation at steady state or partial cancellation of gravity during robot motion), and then to the complete cancellation of the fourth-order dynamics based on feedback linearization, followed by stabilization of the resulting closed-loop linear error dynamics. The next step in this evolution was the development of torque-controlled robots, as the DLR LWR-III manipulator and its later industrial derivatives. The presence of joint elasticity, together with the possible use of reliable joint torque sensors, allowed then to transfer in a rather seamless way for the end-user many control results from the rigid case, in particular impedance control to handle interaction with the environment. The inner low-level loops enabled in fact an approximate recovery of the rigid robot dynamics. Indeed, when joint compliance is included on purpose, like in SEA-based robots, or modified online over a large range of soft/hard values, like in VSA-based robots, it would be just naïve to remove this mechanical property by feedback. The actual control challenge is to take advantage of this richer natural dynamics so as to obtain better performance with a reduced actuation effort. Whereas passivity is one of the usual recipes for getting safer and/or energy-efficient motions, I will present a different, general framework inspired by the principle of feedback equivalence, which has been recently applied with success to a number of control tasks in compliant robots. The idea is to introduce the least possible modification of the original fourth-order dynamics, while matching accurately a desired target behavior via nonlinear state feedback. This concept will be illustrated through a few simple examples: exact cancellation of gravity on the robot links, injection of viscous damping in the link dynamics, and imposition of a generalized impedance model for interaction control.
Alessandro De Luca was born in Roma, Italy, on October 11, 1957. He received the Laurea degree in Electronic Engineering and the PhD in Systems Engineering from the University of Rome “La Sapienza” in 1982 and 1987, respectively. Since 2000, he is a Full Professor of Robotics, Automation, and Automatic Control at the Sapienza University of Rome. From September 2005 to April 2006, he spent a sabbatical at the Institute for Robotics and Mechatronics at DLR in Oberpfaffenhofen, Germany. Since 2013, he is the Director of the Master of Science in Control Engineering, a new Sapienza program fully taught in English. In 2017, he became a Senior Research Fellow of the Sapienza School of Advanced Studies (SSAS). His research interests include modeling, motion planning, and control of flexible manipulators, kinematically redundant manipulators, underactuated robots, wheeled mobile robots and mobile manipulators; physical human-robot interaction; hybrid force-velocity control; visual servoing; iterative learning; nonlinear control of nonholonomic mechanical systems; fault detection and isolation; control of locomotion platforms. He has published over 200 journal and conference papers and book chapters, receiving two best conference paper awards (ICRA 1998, BioRob 2012) and one best application paper award (IROS 2008). He is one of the authors of the PROSE-awarded Springer Handbook of Robotics (2008, 2016), and Editor of the book Advances in Control of Articulated and Mobile Robots (Springer, 2004). For the IEEE Transactions on Robotics and Automation, he served as an Associate Editor (1994–98), an Editor (1998–2003), and the Editor-in-Chief (2003–04). He has been the Editor-in-Chief of the renamed IEEE Transactions on Robotics from its birth in 2004 until September 2008. He has been a member of the IEEE Robotics and Automation Society (RAS) AdCom (2008–10) and has served as RAS Vice-President for Publication Activities in 2012–13. He was General Chair of the 2007 IEEE International Conference on Robotics and Automation held in Rome and Program Chair of the 2016 IEEE International Conference on Robotics and Automation in Stockholm. He is an IEEE Fellow (class of 2007). He received the German Helmholtz Humboldt Research Award for foreign scientists in 2005, and the IEEE-RAS Distinguished Service Award in 2009. Between 2006 and 2012, he has been a member of the Search Committee for Physical Sciences (former Technical Sciences) of the Körber European Science Award, granted by the Körber Foundation. He was Chair of Panel PE7 (Systems and Communication Engineering) of the European Research Council for Advanced Grants evaluation in 2009, 2011, and 2013, and a member of the Scientific Advisory Board of the Max Planck Institute for Biological Cybernetics (from 2015 to 2017). With the DIAG Robotics group, he has been principal investigator in five European research projects (PROMotion, PHRIDOM, FP6 CyberWalk, FP6 PHRIENDS, H2020 SYMPLEXITY) and in many national projects, and participates to H2020 COMANOID). He was national co-ordinator of the MIUR PRIN project SICURA (2008-10) and european coordinator of the FP7 project SAPHARI (2011-15).
Molecular robotics is the art of constructing ultra-miniaturized machines capable of carrying out actions automatically. Molecular robots could have important impact in technology and health, but the field is still in its infancy. Basic physical, chemical principles and technological capabilities still need to be established. I will outline some of the perspectives, discuss current approaches pursued in this field, and report on progress made here in Munich laboratories.
Since 2009: Professor for Biophysics, Physik Department, Technische Universität München.
2007-2009: Postdoctoral research fellow, Department of Biological Chemistry and Molecular Pharmacology, Harvard Medical School
2004-2007: Doctorate studies in (bio-)physics, Physik Department, Technische Universität München, Germany
Oct 2001 to Mar 2004: Diploma studies in physics, Fakultät für Physik, Ludwig-Maximilians-Universität München, Germany
Dietz obtained numerous awards, among them ERC Starting and Consolidator grants, and the Gottfried-Wilhelm-Leibniz-Preis, Germany highest scientific distinction.
Biologically Inspired Drones: from the lab to the real world
The use of drones in in confined spaces and near humans presents great scientific and technical challenges in perception and mechanical design. In this talk I will show that biologically-inspired design principles and soft robotics technologies can improve usability, resilience, and human safety of drones. In particular, I will describe three examples of biologically inspired drones that are having an impact in real world applications.
Prof. Dario Floreano is director of the Laboratory of Intelligent Systems at the Swiss Federal Institute of Technology Lausanne (EPFL). He is also founding director of the Swiss National Center of Competence in Robotics, which sponsors almost 60 researchers in 20 labs across Switzerland. Prof. Floreano holds an M.A. in Vision, an M.S. in Neural Computation, and a PhD in Robotics. He has held research positions at Sony Computer Science Laboratory, at Caltech/JPL, and at Harvard University. His main research interests are robotics and A.I. at the convergence of biology and engineering. Prof. Floreano has made pioneering contributions to the fields of evolutionary robotics, aerial robotics, and soft robotics that have been published in almost 400 peer-reviewed articles, and 4 books on Artificial Neural Networks, Evolutionary Robotics, Bio-inspired Artificial Intelligence and Bio-inspired Flying Robots with MIT Press and Springer Verlag. He served in several advisory boards and committees, including the Future and Emerging Technologies division of the European Commission, the World Economic Forum Agenda Council, the International Society of Artificial Life, the International Neural Network Society, and in the editorial committee of ten scientific journal. In addition, he helped spinning off two drone companies (senseFly and Flyability) and a non-for-profit communication platform on robotics and A.I. (RoboHub).
Toward robot manipulators that understand people and their environments
Over the last years, advances in deep learning and GPU-based computing have enabled significant progress in several areas of robotics, including object manipulation, visual recognition, real-time tracking, and learning-based reasoning and control. This progress turns applications such as autonomous driving and robust navigation in warehouses, hospitals, and hotels into realistic application scenarios. However, we still need to make a lot of progress to enable the next generation of robots that can robustly manipulate the physical world and interact with people in a natural way. In this talk, I will highlight some of the recent advances in robotic perception and discuss the main challenges that still lie ahead. I will also comment on the roles physics-based modeling, simulation, and deep learning can play in the development of such robust, interactive manipulators.
Dieter Fox is a Professor in the Paul G. Allen School of Computer Science & Engineering at the University of Washington, where he heads the UW Robotics and State Estimation Lab. Since October 2017, he is on partial leave from UW and serves as Senior Director of Robotics Research at NVIDIA. Dieter obtained his Ph.D. from the University of Bonn, Germany. His research is in robotics and artificial intelligence, with a focus on state estimation and perception applied to problems such as mapping, object detection and tracking, manipulation, and activity recognition. He has published more than 200 technical papers and is the co-author of the textbook “Probabilistic Robotics.” He is a Fellow of the IEEE and the AAAI, and he received several best paper awards at major robotics, AI, and computer vision conferences. He was an editor of the IEEE Transactions on Robotics, program co-chair of the 2008 AAAI Conference on Artificial Intelligence, and program chair of the 2013 Robotics: Science and Systems conference.
Robotics Studies from Humanoid Series
This talk will introduce ongoing robotics studies done from humanoid series at JSK Lab, The University of Tokyo. JSK lab is a research group of about 60 members of professors and students enrolled in Department of Creative Inforamtics, Department of Mechano-Informatics and Emerging Design and Infomation Course of Department of Interdisciplinary Information Studies. A humanoid is a typical platform for intelligent robotics research. It needs essential key elemental technologies and their continuous integration. The research result from humanoids can provide seeds for future robotics and machine intelligence. The activities evolved from the JSK research environment for humanoid series will be presented.
Masayuki Inaba is a professor of Department of Creative Informatics, in the Graduate School of Information Science and Technology, The University of Tokyo and directing JSK Lab of Department of Mechano-Informatics in the same graduate school. He received B.S of Mechanical Engineering in 1981, M.S and Dr. Degrees of Information Engineering from The University of Tokyo in 1983 and 1986 respectively. He was appointed as a lecturer in 1986, an associate professor in 1989, and a professor in 2000 at The University of Tokyo.
Robots for Physical Interaction
While robots dominates repetitive labors in factories, the mechanical design and controller of these robots are not suitable for relatively complex tasks that humans do easily. These tasks typically require intricate interaction force control on impacts and rich physical interactions such as walking, grinding, and manipulating non-rigid objects. Conventional robots are not built to control force or being flexible to perform like human arms. The talk will discuss how the new design paradigm allows such dynamic interactive force control with environments. Demonstrating the effect of using employing robot design paradigm, the latest version of cheetah robot and force feedback teleoperation arms will be presented. This new class of robots will play a crucial role in future robot applications such as elderly care, home service, delivery, and services in unfavorable environments.
Prof. Sangbae Kim, is the director of the Biomimetic Robotics Laboratory and an Associate Professor of Mechanical Engineering at MIT. His research focuses on the bio-inspired robot design by extracting principles from animals. Kim's achievements on bio-inspired robot development include the world's first directional adhesive inspired from gecko lizards, and a climbing robot, Stickybot, that utilizes the directional adhesives to climb smooth surfaces featured in TIME's best inventions in 2006. Recent achievement includes the development of the MIT Cheetah capable of stable outdoor running up to 13mph and autonomous jumping over an obstacles at an efficiency of animals. This achievement was covered by more than 300 media articles. He is a recipient of King-Sun Fu Memorial Best Transactions on Robotics Paper Award (2008), DARPA YFA(2013), NSF CAREER (2014) award, and Ruth and Joel Spira Award for Distinguished Teaching.
The Age of Human-Robot Collaboration
Robotics is undergoing a major transformation in scope and dimension with accelerating impact on the economy, production, and culture of our global society. The generations of robots now being developed will increasingly touch people and their lives. They will explore, work, and interact with humans in their homes, workplaces, in new production systems, and in challenging field domains. The emerging robots will provide increased support in mining, underwater, hostile environments, as well as in domestic, health, industry, and service applications. Combining the experience and cognitive abilities of the human with the strength, dependability, reach, and endurance of robots will fuel a wide range of new robotic applications. The discussion focuses on design concepts, control architectures, task primitives and strategies that bring human modeling and skill understanding to the development of this new generation of collaborative robots.
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. He is a Fellow of IEEE, Co-Editor of the Springer Tracts in Advanced Robotics (STAR) series, and the Springer Handbook of Robotics. Professor Khatib is the President of the International Foundation of Robotics Research (IFRR). He is recipient of the IEEE RAS Pioneer Award, the George Saridis Leadership Award, the Distinguished Service Award, the Japan Robot Association (JARA) Award, the Rudolf Kalman Award, and the IEEE Technical Field Award. In 2018, Professor Khatib was elected to the National Academy of Engineering.
Are humanoids the ultimate quest of human augmentation and “intelligence”?
One way to understand how we reason and act on our environment is to try replicating our abilities. Humans have physical capabilities to transform the world by acting, interacting and communicating using “body-motion intelligence”. To replicate our ability, we may think of modeling and designing some sort of functional copy of ourselves: a cybernetic avatar using robotic technology and machine “intelligence”. Humanoid robots have great potential to be exploited as sophisticated robotic systems in many manufacturing applications and also as tools to investigate fundamental questions in the human quest for augmentation. Their shape imparts them interesting properties in terms of integration, interaction with humans, empathy, and embodiment. The underlying background of my talk is means of autonomy and interaction in standalone applications; and mind-controlled humanoids and embodiment to understand the basics of what self and consciousness mean. Embodiment is a feature that goes beyond the robotic telepresence technologies: its mechanisms and effective characterization is far from being well understood and is relatively new. Such understanding however, is very important in technologies of human robotic clones, exoskeletons and wearable robots at large. By the time when mind-control systems meet the capability of autonomous learning and understanding –i.e. intelligence, can we transfer our experiences, preferences and intelligence to a robotic body?
Professor Abderrahmane Kheddar received the BS in Computer Science degree from the Institut National d’Informatique (ESI), Algiers, the MSc and Ph.D. degree in robotics, both from the University of Pierre et Marie Curie, Paris. He is presently first class Directeur de Recherche at CNRS and the Codirector of the CNRS-AIST Joint Robotic Laboratory (JRL), UMI3218/RL, Tsukuba, Japan. He is also leading the Interactive Digital Humans (IDH) team at CNRS-University of Montpellier LIRMM, France. His research interests include haptics, humanoids and recently thought-based control using brain machine interfaces. He is a founding member of the IEEE/RAS chapter on haptics, the co-chair and founding member of the IEEE/RAS Technical committee on model-based optimization, he is a member of the steering committee of the IEEE Brain Initiative, Editor of the IEEE Transactions on Robotics and within the editorial board of some other robotics journals; he is a founding member of the IEEE Transactions on Haptics and served in its editorial board during three years (2007-2010). He is an IEEE senior member and titular full member of the National Academy of Technology of France and recently knight of the national order of merits of France.
Dance Partner Robot and its Real-world Applications
A dance partner robot, PBDR (Partner Ballroom Dance Robot), developed in our laboratory, was unveiled and gave dance demonstrations in EXPO 2005, Aichi, Japan. PBDR dances waltz as a female dancer together with a human male dancer. One of the key research issues for the development of the dance partner robot was how to read the male dancer’s lead, or how to estimate the male dancer’s intention. RoboDANTE (Robot DANce TEacher) is a dance instructor robot and teaches its partner how to dance based on the concept of Progressive Teaching. These robots, as research platforms for Physical Human-Robot Interaction (pHRI), have given us opportunities to reconsider issues relating to pHRI. We will introduce the dance partner robots, PBDR and RoboDANTE, to discuss pHRI first. Then, a co-worker robot, PaDY, will be introduced as an example of industrial applications of pHRI. How it could be enhanced by machine learning will be also discussed.
Dr. Kazuhiro Kosuge is a Professor in the Department of Robotics at Tohoku University, Japan. He received the B.S., M.S., and Ph.D. in Control Engineering from the Tokyo Institute of Technology, in 1978, 1980, and 1988 respectively. From 1980 through 1982, he was a Research Staff in the Production Engineering Department, DENSO Co., Ltd. From 1982 through 1990, he was a Research Associate in the Department of Control Engineering at Tokyo Institute of Technology. From 1990 to 1995, he was an Associate Professor at Nagoya University. From 1995, he has been at Tohoku University. He is an IEEE Fellow, a JSME Fellow, a SICE Fellow, a RSJ Fellow, a JSAE Fellow, a member of IEEE HKN. He served as President of IEEE Robotics and Automation Society for 2010-2011, and Division X Director of the Board of Directors of IEEE for 2015-2016.
Does the progress of robotics pass through soft materials?
Though a young discipline, robotics progressed rapidly and pervaded our lives more than we perceive, becoming a tool we cannot do without in manufacturing. Futuristic scenarios have been proposing robots in daily life of citizens and professionals for decades, creating expectations that have not yet been matched. What is the real status of development of robotics today and what are the realistic scenarios that robotics technologies enable today? What are the abilities that robots still miss to match expectations for extensive application and healthier and safer human life?
Largely inspired by the observation of the role of soft tissues in living organisms, the use of soft materials for building robots is recognized as one of the current challenges for pushing the boundaries of robotics technologies and building robotic systems for service tasks in natural environments. The study of living organisms sheds light on principles that can be fruitfully adopted to develop additional robot abilities or to facilitate more efficient accomplishment of tasks, because living organisms exploit soft tissues and compliant structures to move effectively in complex natural environments.
At the same time, to reach abilities that make them effective in realistic applications, robots need to develop a form of intelligence that allows them to use their body abilities at the best, to negotiate real-world scenarios. Again, living beings can be an excellent source of inspiration, with their brains. Taking inspiration from brains stands as a quite straightforward strategy in robotics, for endowing robots with cognitive functions. Recent advances in AI provide powerful tools for developing cognitive functions in robots, while the advances in brain-inspired robotics provide opportunities for embodied approaches in AI research.
Robots have a great potential for becoming part of our lives, for responding to current societal challenges, for contributing to the economic growth of Europe. New materials and AI techniques are key directions for the future robotics progress.
Cecilia Laschi is Full Professor of Biorobotics at the BioRobotics Institute of the Scuola Superiore Sant'Anna in Pisa, Italy, where she serves as Rector’s delegate to Research. She graduated in Computer Science at the University of Pisa in 1993 and received the Ph.D. in Robotics from the University of Genoa in 1998. In 2001-2002 she was JSPS visiting researcher at Waseda University in Tokyo.
Her research interests are in the field of soft robotics, a young research area that she pioneered and contributed to develop at international level, including its applications in marine robotics and in the biomedical field. She has been working in humanoid robotics and neurorobotics, at the merge of neuroscience and robotics.
She is in the Editorial Boards of several international journals. She serves as reviewer for many journals, including Nature and Science, for the European Commission, including the ERC programme, and for many national research agencies.
She is member of the IEEE, of the Engineering in Medicine and Biology Society (EMBS), and of the Robotics & Automation Society (RAS), where she served as elected AdCom member and currently is Co-Chair of the TC on Soft Robotics. She founded and served as General Chair for the IEEE-RAS First International Conference on Soft Robotics in Livorno, in April 24-28, 2018.
She is founding member of RoboTech srl, spin-off company of the Scuola Superiore Sant’Anna, in the sector of edutainment robotics.
Nonholonomic motion: from the rolling car to the rolling man
The talk reports more than 30 years of research conducted at LAAS-CNRS on nonholonomic systems applied to mobile robotics and biomechanics. After introducing the wheel as a parangon of nonholonomic systems, the first part of the talk will show how mobile robotics has renewed since the 1990’s the research in robot motion planning and control by introducing the need to combine computational geometry and geometric control theory (optimal control and differential flatness). Doing so, Hilare was able in 1997 to park itself while maneuvering a trailer. In a second part of the presentation, we will focus on a multidisciplinary research action exploring the motor synergies of anthropomorphic walking. By combining biomechanical, neurophysiology, and robotics perspectives, it is shown that the wheel offers a relevant model to better understand human locomotion and to design new bipedal robot architectures.
Jean-Paul Laumond, IEEE Fellow, is a roboticist. He is Directeur de Recherche at LAAS-CNRS (team Gepetto) in Toulouse, France. His research is about robot motion planning and control. In 2001 and 2002 he created and managed Kineo CAM, a spin-off company from LAAS-CNRS devoted to develop and market motion planning technology. Siemens acquired Kineo CAM in 2012. In 2006, he launched the research team Gepetto dedicated to anthropomorphic motion studies along three perspectives: artificial motion for humanoid robots, virtual motion for digital actors, and natural motions of human beings. He has published more than 150 papers in international journals and conferences in Robotics, Computer Science, Automatic Control and in Neurosciences. His current project Actanthrope (ERC-ADG 340050) is devoted to the computational foundations of anthropomorphic action. He teaches Robotics at Ecole Normale Supérieure in Paris. He has been the 2011-2012 recipient of the Chaire Innovation technologique Liliane Bettencourt at Collège de France in Paris. He is the 2016 recipient of the IEEE Inaba Technical Award for Innovation Leading to Production. He is a member of the French Academy of Technologies and of the French Academy of Sciences.
Mocap as a Service: a humanoid robotics spin-off
Robotics, especially humanoid robotics, has thrown light over the human attribution. The control of stable bipedal walk revealed the property of human motion. The interaction with human required the interpretation of human body movements. The computational foundation in humanoid robotics includes the simulation of complex mechanical systems, the optimization of many-variables systems, and the statistical classification and reasoning of motion data. Combined with recent advance of artificial intelligence in image recognition and natural language processing, the computational foundation of humanoid robotics finds its spin-off in human services. We have developed the technology of 3D reconstruction of human movements from multiple-camera video data and connected with the humanoid technology. This talk will introduce the scope of "Mocap as a Service."
Yoshihiko Nakamura is Professor at Department of Mechano-Informatics, University of Tokyo. He received Doctor of Engineering Degree from Kyoto University. He worked at Kyoto University as Assistant Professor (1982-1987) and at University of California, Santa Barbara, as Assistant and Associate Professor (1987-1991) before joining University of Tokyo. Humanoid robotics, cognitive robotics, neuro musculoskeletal human modeling, biomedical systems, and their computational algorithms are his current fields of research. He is Fellow of JSME, Fellow of RSJ, Fellow of IEEE, and Fellow of WAAS. Dr. Nakamura served as President of IFToMM (2012-2015). Dr. Nakamura is Foreign Member of Academy of Engineering Science of Serbia, and TUM Distinguished Affiliated Professor of Technische Universität München.
Skill Learning in Robotics
Autonomous robots that can assist humans in situations of daily life have been a long standing vision of robotics, artificial intelligence, and cognitive sciences. A first step towards this goal is to create robots that can learn tasks triggered by environmental context or higher level instruction. However, learning techniques have yet to live up to this promise as only few methods manage to scale to high-dimensional manipulator or humanoid robots. In this talk, we investigate a general framework suitable for learning motor skills in robotics which is based on the principles behind many analytical robotics approaches. It involves generating a representation of motor skills by parameterized motor primitive policies acting as building blocks of movement generation, and a learned task execution module that transforms these movements into motor commands. We discuss learning on three different levels of abstraction, i.e., learning for accurate control is needed to execute, learning of motor primitives is needed to acquire simple movements, and learning of the task-dependent „hyperparameters“ of these motor primitives allows learning complex tasks. We discuss task-appropriate learning approaches for imitation learning, model learning and reinforcement learning for robots with many degrees of freedom. Empirical evaluations on a several robot systems illustrate the effectiveness and applicability to learning control on an anthropomorphic robot arm. These robot motor skills range from toy examples (e.g., paddling a ball, ball-in-a-cup) to playing robot table tennis against a human being and manipulation of various objects.
Jan Peters is a full professor (W3) for Intelligent Autonomous Systems at the Computer Science Department of the Technische Universitaet Darmstadt and at the same time a senior research scientist and group leader at the Max-Planck Institute for Intelligent Systems, where he heads the interdepartmental Robot Learning Group. Jan Peters has received the Dick Volz Best 2007 US PhD Thesis Runner-Up Award, the Robotics: Science & Systems - Early Career Spotlight, the INNS Young Investigator Award, and the IEEE Robotics & Automation Society's Early Career Award. Recently, he received an ERC Starting Grant.
Jan Peters has studied Computer Science, Electrical, Mechanical and Control Engineering at TU Munich and FernUni Hagen in Germany, at the National University of Singapore (NUS) and the University of Southern California (USC). He has received four Master's degrees in these disciplines as well as a Computer Science PhD from USC. Jan Peters has performed research in Germany at DLR, TU Munich and the Max Planck Institute for Biological Cybernetics (in addition to the institutions above), in Japan at the Advanced Telecommunication Research Center (ATR), at USC and at both NUS and Siemens Advanced Engineering in Singapore.
From Humanoid Robots to Anthropomorphic Minds
The performance of humanoid robots has been steadily increasing and nowadays we can claim that sensing and motion abilities of robots are approaching those of humans. This has created the impression that a society where humans and robots co-exist and collaborate is not very far away. Is this true?
During the talk I will argue that robots interacting with humans in everyday situations, even if motorically and sensorially very skilled and extremely clever in action execution are still very much primitive in their ability to understand actions executed by others and that this is the major obstacle for the advancement of social robotics. I will argue that the reason why this is happening is rooted in our limited knowledge about ourselves and the way we interact socially. I will also argue that robotics can serve a very crucial role by joining forces with the communities studying the cognitive aspects of social interaction and by co-designing robots able to establish a mutual communication channel with the human partner (the distinctive mark of human social interaction) [Sandini & Sciutti, 2018].
Sandini, G. and A. Sciutti, Humane Robots—from Robots with a Humanoid Body to Robots with an Anthropomorphic Mind. ACM Transactions on Human-Robot Interaction, 2018. 7(1): p. Article 7.
Giulio Sandini is Director of Research at the Italian Institute of Technology and full professor of bioengineering at the University of Genoa. He was research fellow and assistant professor at the Scuola Normale Superiore in Pisa and Visiting Research Associate at the Department of Neurology of the Harvard Medical School. In 1990 he founded the LIRA-Lab (Laboratory for Integrated Advanced Robotics, www.liralab.it) and in 1996 he was Visiting Scientist at the Artificial Intelligence Lab of MIT.
Giulio Sandini is a founding Director of the Italian Institute of Technology where in 2006 he established the department of Robotics, Brain and Cognitive Sciences.
Energy Aware Robotics and Port-Based thinking
Physically interactive robots act and interact in a physical environment which is often unknown and not easy to model. Considering that interaction is an a-causal bidirectional “exchange” it is important to use languages and methods which are able to fully describe such interactions and make possible to design effective and safe controllers in all situations. The presentation will give an introduction on these methods which are called by the presented: “Energy Aware Robotics”.
Stefano Stramigioli received the M.Sc. with honors (cum laude) in 1992 and the Ph.D with honors (cum laude) in 1998. Between the two degrees he has been working as a researcher at the University of Twente, has started his enterprise and received the Dutch Institute of System and Control certificate. Since 1998 he has been faculty member first as assistant, associate and currently full professor in Advanced Robotics. He is an IEEE Fellow and has been an IEEE RAS officer for many years.
He is currently leading a growing group of about 50 people (http:// www.ce.utwente.nl). He has been Editor in chief of the IEEE Robotics and Automation Magazine, which he brought from the seventh to the first place in the ranking of the Impact Factor among all journals on Robotics. He has furthermore been Editor in Chief of the IEEE ITSC Newsletter and guest editor for others. He is member of the Editorial Board of the Springer Journal of Intelligent Service Robotics.
He has been an AdCom member of the IEEE Robotics and Automation Society, he has been the founder and chair of the Electronic Products and Services of the IEEE Robotics and Automation Society and he has been serving as Vice President for Membership of the same society for two consecutive terms. He is involved in different projects related to Control and Robotics for medical, inspection and home and care applications.
Nationally, he has been a member of the Management team of the graduate school DISC, has been the founder and chair of RoboNED, the national platform coordinating all academic, industrial and governmental institutions on Robotics and responsible for producing a Strategic Research Agenda for Robotics for the Netherlands and he is one of the initiator of the LEO (www.leo-robotics.eu) robotics center. He has been the UT representative for the formation of the 3TU CoE on Intelligent Mechatronic Systems and the 3TU Master on System and Control. He has served as the UT representative of the Management Team of the Mechatronica Valley Twente. He is member of the program board of the STW national research program on Autonomous Sensors Systems.
He has been the 2009 recipient of the IEEE-RAS distinguish service award and he is a member of the 3TU Center of Excellence on Intelligent Mechatronics Systems.
He has been invited many times as speaker at international schools, workshops and conferences for lecturing or plenary speeches, and he has numerous national and international cooperations. He has been teaching Modeling, Control and Robotics for under and post-graduates. He is currently serving as the Vice President for Research of euRobotics, the private part of the PPP cooperation with the European Commission known as SPARC, the biggest robotic civil program worldwide. He has around 300 publications including 4 books.
Shared Autonomy: The Future of Interactive Robotics
The next generation of robots are going to work much more closely with humans, other robots and interact significantly with the environment around it. As a result, the key paradigms are shifting from isolated decision making systems to one that involves shared control -- with significant autonomy devolved to the robot platform; and end-users in the loop making only high level decisions. This talk will briefly introduce powerful machine learning technologies ranging from robust multi-modal sensing, shared representations, scalable real-time learning and adaptation and optimal scheduling of compliant actuation that are enabling us to reap the benefits of increased autonomy while still feeling securely in control. This also raises some fundamental questions: while the robots are ready to share control, what is the optimal trade-off between autonomy and control that we are comfortable with? Domains where this debate is relevant include self-driving cars, offshore asset inspection and maintenance, deep sea and autonomous mining, shared manufacturing, exoskeletons/prosthetics for rehabilitation as well as smart cities to list a few.
Sethu Vijayakumar is the Professor of Robotics in the School of Informatics at the University of Edinburgh and the Director of the Edinburgh Centre for Robotics. He holds the prestigious Senior Research Fellowship of the Royal Academy of Engineering, co-funded by Microsoft Research and is also an Adjunct Faculty of the University of Southern California (USC), Los Angeles. Professor Vijayakumar, who has a PhD (1998) from the Tokyo Institute of Technology, has pioneered the use of large scale machine learning techniques in the real time control of several iconic large degree of freedom anthropomorphic robotic systems. His latest project (2016) involves a collaboration with NASA Johnson Space Centre on the Valkyrie humanoid robot being prepared for unmanned robotic pre-deployment missions to Mars. He is the author of over 180 highly cited publications in robotics and machine learning and the winner of the IEEE Vincent Bendix award, the Japanese Monbusho fellowship, 2013 IEEE Transaction on Robotics Best Paper Award and several other paper awards from leading conferences and journals. He has led several UK, EU and international projects in the field of Robotics, attracted funding of over £38M in research grants over the last 8 years and has been appointed to grant review panels for the DFG-Germany, NSF-USA and the EU. He is a Fellow of the Royal Society of Edinburgh and a keen science communicator with a significant annual outreach agenda. He is the recipient of the 2015 Tam Dalyell Award for excellence in engaging the public with science and serves as a judge on BBC Robot Wars and was involved with the UK wide launch of the BBC micro:bit initiative for STEM education. He has recently taken on the role of the Co-Program Director of The Alan Turing Institute, driving their Robotics and Autonomous Systems agenda.