ShanghAI Lectures 2010 – Robohub

ShanghAI Lectures: Simon Grand “Building Intelligent Companies: Enterpreneurial Management and Design Principles”

Nathan Labhart — Thu, 24 Apr 2014 16:41:21 +0000

Guest talk in the ShanghAI Lectures, 2010-11-18

In this guest lecture, Simon Grand from the University of St. Gallen in Switzerland, talks about building intelligent companies.

The ShanghAI Lectures are a videoconference-based lecture series on Embodied Intelligence, run and organized by Rolf Pfeifer (from 2009 till 2012), Fabio Bonsignorio (since 2013), and me with partners around the world.

https://www.youtube.com/watch?v=82nEo8usN-M

Slides

Dr. Simon Grand is an economist and entrepreneur. Since 2001, he is the founder and academic director of RISE management research, Institute of Systemic Management and Public Governance, University of St. Gallen HSG. His research focus is strategic entrepreneurship and management in the context of innovation and change. Areas of expertise include computer science, software engineering, life sciences, pharma, cognitive sciences, artificial intelligence, fashion design, and creative industries. In 2008 he became a founder and partner at TATIN Scoping Complexity in Zurich. Their focus is entrepreneurial strategy and strategy design in the context of innovation and change, and corporate governance. Since 2007, he is also senior researcher at the Institute for Art and Design Research at the Academy of Art and Design in Basel where his research focuses on design entrepreneurship, strategy design, design fiction, critical companies. Since 1998, he is research associate and senior lecturer at the University of St. Gallen HSG, with a focus on strategic management and entrepreneurship, management theory, technological innovation, and epistemology of management research. Dr. Grand studied economics, sociology and philosophy at the University of Zurich where he also completed his doctoral work at the Institute for Management Research. From 1990 to 1993 he was a research associate in the area of financial markets at the Swiss National Bank, and from 1996 to 1997 he was a research fellow in philosophy and epistemology at the Ecole des Hautes Etudes en Sciences Sociales in Paris.

The ShanghAI Lectures have brought us a treasure trove of guest lectures by experts in robotics. You can find the whole series from 2012 here. Now, we’re bringing you the guest lectures you haven’t yet seen from previous years, starting with the first lectures from 2009 and releasing a new guest lecture every Thursday until all the series are complete. Enjoy!

ShanghAI Lectures: Verena Hafner “Interactive Robotics”

Nathan Labhart — Thu, 17 Apr 2014 10:59:22 +0000

Guest talk in the ShanghAI Lectures, 2010-11-18

Sensorimotor interaction between an agent and its environment seems to be the key ingredient to develop intelligent behaviour. In this talk, the importance of interaction is shown with a number of examples from robotics research in interaction and imitation. The prerequisites for imitation learning are investigated and different methods for creating body maps and identifying behaviour are presented.

https://www.youtube.com/watch?v=Sz5HeTU3qTY

Slides

ShanghAI Lectures: Patrick van der Smagt “Biomimetic Robotics”

Nathan Labhart — Thu, 10 Apr 2014 14:46:46 +0000

Guest talk in the ShanghAI Lectures, 2010-10-21

In this guest presentation, Patrick van der Smagt talks about biomimetic approaches to robot control, kinematics, grasping, and ways to use the human body to control robots.

https://www.youtube.com/watch?v=A0ULXgISRsw

Van der Smagt is head of terrestrial robotics and bionics at the Institute of Robotics and Dynamics of the German Aerospace Center (DLR). He leads various EC projects, focusing on biomimetic robotics, with the goal of analyzing human motion behaviour and constructing the next generation of robots. This involves measuring and modelling limbs, but also understanding the underlying neural mechanisms.

To match the dexterity of the human upper extremities, van der Smagt analyses various aspects of the human biological components (using magnetic resonance tomography, sonography, electrode implantation, biophysics, and other tools).

ShanghAI Lectures: Rafael Núñez “Where mathematics comes from’”

Nathan Labhart — Thu, 03 Apr 2014 13:51:32 +0000

Guest talk in the ShanghAI Lectures, 2010-12-16

In this guest lecture, Rafael Núñez from the University of California, San Diego, USA, talks about Mathematics as a paradox for embodiment and cognitive mechanisms in conceptual systems and human imagination.

https://www.youtube.com/watch?v=muPMMgRwf3g

ShanghAI Lectures: Nikolaos Mavridis “Robots, language, and social networks”

Nathan Labhart — Thu, 27 Mar 2014 18:08:18 +0000

Guest talk in the ShanghAI Lectures, 2010-12-16

The lecture starts with a short introduction to the Interactive Robots and Media Lab and the United Arab Emirates. Then, it continues by exploring some basic requirements towards creating Situated Conversational Assistants, i.e. devices with sensing, actuation, and spoken natural language which can assist humans in various tasks.

A concrete example of such a device is presented: Ripley the Robot, a manipulator robot with vision and speech that can serve motor commands, answer questions about the current or past situations, and get information about the current state of the world through language. In the context of such devices, a number of considerations are introduced, which then lead to the Symbol Grounding Problem, a philosophical problem which is shown to be at the heart of attempts towards building such embodied agents that can talk about their surroundings – which cannot just “plug-and-play” with traditional NLP approaches.

The symbol grounding problem is discussed, as well as its relation to semantics and semiotics, and then three practical pathways towards real-world solutions to the problem that promise to enable wider application of Situated Conversational Assistants are introduced. Then, Grounded Situation Models are briefly discussed, followed by a very quick glimpse of other requirements towards conversational robots.

The lecture finishes with a brief look at the FaceBots social robots, which utilize and publish social information on the internet in order to create sustainable human-robot relationships, as well as the Ibn Sina arabic speaking conversational robot and the modalities available for tele-participation in the interactive theatre that is built around him.

https://www.youtube.com/watch?v=phL1-FiRwUQ

Dr. Nikolaos Mavridis, PhD from the Massachusetts Institute of Technology, has taught, written about, researched, and built Intelligent Systems and Robots, having been active in the area since his early youth. Currently he is serving as Ass. Professor at New York University in Abu Dhabi. He is the founder of IRML (the Interactive Robots and Media Lab), which achieved wide publicity for “Ibn Sina”, the world’s first Arabic-Language Android Robot, as well as “FaceBots”, Microsoft-award-recipient Social Robots which access info and publish on FaceBook. His past work includes “Ripley”, a language-learning robot with abilities comparable to those assessed by the token test, a test administered to 3-year-old children. He is a member of the IEEE, has served in numerous leadership positions in the past, is now a TEDx curator and has been a TEDx speaker twice.

Watch Dr. Mavridis at:

ShanghAI Lectures: Louis-Philippe Demers “Embodiment and robotic arts”

Nathan Labhart — Fri, 21 Mar 2014 14:18:40 +0000

The Blind Robot by Louis-Philippe Demers is a reference to the works of Merleau-Ponty and his example of the body extension of the blind man’s cane, where the cane not only senses the world but also reveals the blind man as blind. Photo credit: Louis-Philippe Demers

Guest talk in the ShanghAI Lectures, 2010-12-16

Embodied agents have a material existence whilst audiences share this very same world and space. This lecture explores the far-reaching and often surprising implications of embodiment, both from the perspective of the audience and of the robotic agents in Robotic Arts, which empower intangible contributions from the cultural context, the suspension of disbelief and the attribution of intention towards any outside physical objects acting upon the world.

https://www.youtube.com/watch?v=s_JSIqb_TAA

Louis-Philippe Demers makes large-scale installations and performances. His main areas of work are entertainment robotics and interaction design. Over the past two decades, he participated in more than seventy artistic and stage productions and has built more than 300 machines. His projects can be found in theatre, opera, subway stations, art museums, science museums, music events and trade shows.

Demers’ works have been featured at major venues such as Lille 2004, Expo 1992 and 2000, Sonambiente, ISEA, Siggraph and Sonar. He received three mentions at Ars Electronica, the Distinction of Prix Ars 96, the first prize of Vida 2.0, a mention for the Tiller Girls at Vida 12.0, the Interactive prize for Lightforms 98 and six prizes for Devolution including two Helpmann Awards, the Australian equivalent of the Broadway’s Tony.

Demers was Professor of Digital Media and Exhibit Design/Scenography at the Hochschule fuer Gestaltung, the academic institution affiliated to the world renowned Zentrum fuer Kunst und Medientechnologie (ZKM, Germany). Since he joined the Interaction and Entertainment Research Centre and the newly founded School of Art, Design and Media at the Nanyang Technological University (NTU, Singapore).

ShanghAI Lectures: Tamim Asfour “Robots think with their hands”

Nathan Labhart — Fri, 14 Mar 2014 03:13:51 +0000

Guest talk in the ShanghAI Lectures, 2010-12-16

The design of cognitive situated robots able to learn to operate in the real world and to interact and communicate with humans, must model and reflectively reason about their perceptions and actions in order to learn, act, predict and react appropriately. Such capabilities can only be attained by embodied agents through physical interaction with and exploration of the real world and requires the simultaneous consideration of perception and action. Representations built from such interactions are much better adapted to guiding behaviour than human crafted rules and allow embodied agents to gradually extend their cognitive horizon.

In the first part of the talk, I present the concept of Object-Action Complexes (OAC, pronounced “oak”) which has been introduced by the European project PACO-PLUS (www.paco-plus.org) to emphasize the notion that objects and actions are inseparably intertwined and that categories are therefore determined (and also limited) by the action an agent can perform and by the attributes of the world it can perceive. Entities (things) in the world of a robot (or human) will only become semantically useful objects through the action that the agent can/will perform on them. The second part of the talk presents current results toward the implementation of integrated 24/7 humanoid robots able to 1) perform complex grasping and manipulation tasks in a kitchen environment 2) autonomously acquire object knowledge through visual and haptic exploration and 3) learn actions from human observation. The developed capabilities are demonstrated on the humanoid robots ARMAR-IIIa and ARMAR-IIIb.

https://www.youtube.com/watch?v=tJLzV418pF4

Slides

Tamim Asfour is senior research scientist and leader of the Humanoid Research Group at Humanoids and Intelligence Systems Lab, Institute for Anthropomatics, Karlsruhe Institute of Technology (KIT).

His major research interest is humanoid robotics. In particular, his research topics include action learning from human observation, goal-directed imitation learning, dexterous grasping and manipulation, active vision and active touch, whole-body motion planning, cognitive control architectures, system integration, robot software and hardware control architecture, motor control and mechatronics.

He is leading the system integration tasks and the development team of the humanoid robot series ARMAR in the German Humanoid Robotics Project (SFB 588) funded by the German Research Foundation (DFG). He is currently involved in the following projects funded by the European Commission: PACO-PLUS, GRASP and Xperience.

Tamim Asfour is member of the Editorial Board of IEEE Transactions on Robotics and European Chair of the IEEE-RAS Technical Committee on Humanoid Robots. He is member the Executive Board of the German Association of Robotics (DGR: Deutsche Gesellschaft für Robotik). He serves as member on several program committees and review panels.

He received his diploma degree in Electrical Engineering (Dipl.-Ing.) in 1994 and his PhD in Computer Science (Dr.-Ing.) in 2003 from the University of Karlsruhe. In 2003 he was awarded with the Research Center for Information Technology (FZI) price for his outstanding Ph.D. thesis on sensorimotor control in humanoid robotics and the development of the humanoid robot ARMAR. Since September 2010 he holds an Adjunct Professor position at the Georgia Institute of Technology (Georgia Tech), College of Computing, Interactive Computing.

ShanghAI Lectures: Shuhei Miyashita “Tribolon: Scalable Self-Assembling Robots”

Nathan Labhart — Thu, 06 Mar 2014 15:20:34 +0000

Guest talk in the ShanghAI Lectures, 2010-12-02

Self-assembly is of crucial importance in the biological realm at all scales. This talk introduces a series of self-assembling robots developed in our project, and discusses key features that such robots are expected to possess. The robots give rise to unique insight into the interdependencies between the components’ morphology, systems’ stochasticity, and the emerged behaviors, and cast light on the design principle of self-assembling components. We believe that the research introduced deepens the practical understanding of the formation of spontaneous structure and function, firmly provides knowledge for the realization of scalable self-assembly systems, and will, ultimately brings us closer to answering the nature of “living” systems.

https://www.youtube.com/watch?v=d8mKmXQzDWg

Shuhei Miyashita received his masters degree in computational intelligence and systems science from the Tokyo Institute of Technology, his bachelor degree in electrical and electronics engineering from Jouchi University, and his PhD degree at the AI Lab, University of Zurich in Switzerland. He is a postdoctoral research associate at the Massachusetts Institute of Technology, USA. His publications can be found at http://shuhei.net/.

ShanghAI Lectures: Serge Kernbach “Collective and Modular Robotics: Fundamentials and Frontiers”

Nathan Labhart — Thu, 27 Feb 2014 15:59:51 +0000

Guest talk in the ShanghAI Lectures, 2010-12-02

Collective systems play very important role on Earth, and we encounter them in all sizes, scales and forms; in biological and technological areas; in ocean, air and on the ground. Examples include viruses, different colloidal systems, nano- and micro-scale particles, huge world of social insects and animals; collective systems in robotics vary from nano- up to large space exploration robots. To some extent, collective systems are ubiquitous. Such a prevalence and diversity and can be explained by several unique properties: scalability, reliability, flexibility, self-developmental capabilities. This guest lecture introduces the area of collective robotics and answers the questions “what and why”. Special attention is given to reconfigurable robotics, we discuses a big vision of “universal modularity” and several ways of its achieving.

https://www.youtube.com/watch?v=R_V_3yN1ZrA

Serge Kernbach is the head of the collective robotics group at the University of Stuttgart, Germany. He graduated in electronic engineering and computer science in 1994. During 1996-1998 he received several research grants, in 2007 his doctoral thesis won the faculty-award as the best dissertation of the year. Since 2004 he has been a coordinator of several European research projects on the field of collective robotics. Serge’s main research interest is focused on artificial collective systems, he is the author and co-author of over 100 articles in international journals and conferences, edited a few books related to robotics. Since 2000 he acquired for IPVS more than 3.5 M€ in different research projects.

ShanghAI Lectures: Weidong Chen “Modeling and control of mobile robotic networks”

Nathan Labhart — Wed, 14 Aug 2013 20:01:43 +0000

Guest talk in the ShanghAI Lectures, 2010-12-16

Swarm intelligence of mobile robots is defined as a mobile robot network with only local interactions and finite sensing capabilities which however could achieve global objectives and collective behaviors. The most well-known examples of swarm intelligence in nature are discovered in the collective behaviors of ant and bee colonies. Self-healing is one of the most important components in swarm intelligence.

In this talk, we will provide a theoretical modelling as well as a control method for self-healing of mobile robot networks based on motion synchronization. Using the graph and complex network theories, we establish the model of a mobile robot network that combines switched network topologies with an interaction dynamic model for describing the motion of the robots. We propose a performance metric of the network topology to evaluate the stability and the robustness of motion synchronization, analyze the effect of failed robots upon the network topology, and show the necessity and principle of the self-healing method based on only local interactions. A fully distributed and recursive topology control for self-healing with switched topologies is then proposed. We show that the self-healing algorithm can prevent the network topology from being separated into two or more disconnected parts, and maintain the performance of the network. Based on the Lyapunov exponent, we further provide a criterion of the stability of the network with the proposed distributed control. Finally, we demonstrate the advantages of our self-healing method by performing simulations of two typical tasks, formation generation and coverage.

https://www.youtube.com/watch?v=4D3GLq997JQ

Weidong Chen received the B.S. and M.S. degrees in Control Engineering in 1990 and 1993, and Ph.D. degree in Mechatronics in 1996, respectively, all from the Harbin Institute of Technology, Harbin, China. Since 2005 he has been a professor of the Department of Automation at the Shanghai Jiao Tong University, Shanghai, China, and director of the Institute of Robotics and Intelligent Processing. From 2003 to 2004, he was a visiting associate professor in the Department of Electrical and Computer Engineering at The Ohio State University. Dr. Chen’s research interests include autonomous mobile robot, multi-robot cooperation, and micro manipulation.