Program

Time	Talk
08:30 9:05	Introductory talk by the organizers
09:05 09:40	Katsushi Ikeuchi, Microsoft Research Asia, University of Tokyo, Japan
09:40 10:15	Teaser presentations for papers 1-6
10:15 10:45	Coffee break with demos and posters
10:45 11:20	Kathrin Dörfler, Gramazio Kohler Research, Chair of Architecture and Digital Fabrication, ETHZ, Switzerland
11:20 11:55	Seiichiro Katsura, Keio University, Japan
11:55 12:30	Louis-Philippe Demers, NTU’s School of Art, Design and Media, Singapore
12:30 13:30	Lunch Break
13:30 14:05	Damith Herath, Human Centred Technology Research Centre, ESTeM, University of Canberra, Australia
14:05 14:40	Heather Knight, Carnegie Mellon University, USA
14:40 15:15	Teaser presentations for papers 7-12
15:15 15:45	Coffee break with demos and posters
15:45 16:20	Kendra Byrne, X, Google, USA
16:20 16:55	Michel Taix, LAAS-CNRS, France
16:55 17:30	Katsuyoshi Tsujita, Osaka Institute of Technology, Japan
17:30 18:00	Conclusion/discussion

Invited presentations

Katsushi Ikeuchi (Microsoft Research Asia)
e-Intangible Heritage

Abstract

Tangible heritage, such as temples and statues, is disappearing day-by-day due to human and natural disaster. In-tangible heritage, such as folk dances, local songs, and dialects, has the same story due to lack of inheritors and mixing cultures. We have been developing methods to preserve such tangible and in-tangible heritage in the digital form. This project, which we refer to as e-Heritage, aims not only record heritage, but also analyze those recorded data for better understanding as well as display those data in new forms for promotion and education.
This talk mainly covers how to preserve in-tangible heritage, in particular, preservation of Japanese and Taiwanese folk dances. The first half of my talk covers how to display such a Japanese folk dance on a humanoid robot. Here, we follow the paradigm, learning-from-observation, in which a robot learns how to dance from observing human dance. Due to the physical difference between a human and a robot, the robot cannot mimic the entire human actions. Instead, the robot first extracts important actions of a dance, referred to key poses, only exactly mimics those key poses and then interpolates interval trajectories as much as possible but within the limit of the robot capabilities. The second half of my talk covers our effort to apply similar technics to Taiwanese folk dances. Here, I concentrate on the analysis of the key poses and how such key poses relate to their social institutions.

Bio

Dr. Katsushi Ikeuchi is a Principal Researcher of Microsoft Research. He received a Ph.D. degree in Information Engineering from the University of Tokyo in 1978. After working at AI Lab of MIT as a pos-doc fellows for three years, Electrotechnical Lab, Japan as a researcher for five years, Robotics Institute of Carnegie Mellon University as a faculty member for ten years, the University of Tokyo as a faculty member for nineteen years, he joined Microsoft Research Asia in 2015. His research interest spans computer vision, robotics, and computer graphics. He has received several awards, including IEEE-PAMI Distinguished Researcher Award, the Okawa Prize from the Okawa foundation, and 紫綬褒章 (the Medal of Honor with Purple ribbon) from the Emperor of Japan. He is a fellow of IEEE, IEICE, IPSJ, and RSJ.

www.cvl.iis.u-tokyo.ac.jp/~ki

Kathrin Doerfler (ETH Zurich)
Robotic Fabrication beyond Factory Settings

Abstract

The group of Gramazio Kohler Research focuses on developing and examining additive digital fabrication techniques to build customized architectural components. In essence, the group’s special interest lies in combining data, material processes and assembly logics and the resulting implications this has on architectural design: The possibility of fabricating digitally designed building components with robots expands not only the spectrum of possibilities for construction, but, by the direct implementation of material and production logic into the design process, it establishes a unique architectural expression and new aesthetics. As such, the group tries to introduce and expand robotic fabrication in prefabrication, but to also fully implement it directly on construction sites.
This talk will focus on concepts of how to bring robots directly to the construction site and autonomously fabricate structures beyond factory conditions. A short introduction and overview to this branch of research will be followed by the presentation of the mobile construction robot, the “In Situ Fabricator”. This augmented system will reduce the need for manual input and should enable to accurately build complex structures to construction tolerances, while simultaneously being able to deal with the uncertainties of a construction site.

Bio

Kathrin Dörfler studied architecture at TU Vienna and Digital Art at the University for Applied Arts Vienna, Austria. During her studies she has been working for architecture firms in Vienna, among others for Soma Architects and gaupenraub. In 2012, Romana Rust and she founded the collective “dorfundrust”, a studio for digital processes in architecture. Between 2012 and 2013 she was university assistant at the Institute of Art and Design at the TU Vienna, teaching in the field of computer-aided design and fabrication. Since 2013, she is a PhD researcher at the Chair of Architecture and Digital Fabrication at ETH Zurich and joined the NCCR Digital Fabrication in September 2014.

gramaziokohler.arch.ethz.ch/
www.dfab.ch/
insitufabricator.com
dorfundrust.com

Seiichiro Katsura (Keio University)
Applied Abstraction and Integrated Design for Reproduction of Human Motion

Abstract

A novel method for preserving and reproducing human motion based on motion control is presented. A motion control makes it possible to preserve and reproduce human motion. Because motion information is preserved based on position trajectory and force input, future human support technologies that will facilitate skill acquisition, physical rehabilitation, tele-communication, etc. will be developed. Once human motions are preserved, it will be possible to process them for various applications. For example, being able to reproduce the speed and trajectory of motion will allow for adjustments that fit the desired function. As a result, the temporal and spatial coupling of perception and action can be attained. This type of applied abstraction technology for integrated design will be important for the future of human support in our society.

Bio

Seiichiro Katsura received the B.E. degree in system design engineering and the M.E. and Ph.D. degrees in integrated design engineering from Keio University, Yokohama, Japan, in 2001, 2002 and 2004, respectively. From 2003 to 2005, he was a Research Fellow of the Japan Society for the Promotion of Science (JSPS). From 2005 to 2008, he worked at Nagaoka University of Technology, Nagaoka, Niigata, Japan. Since 2008, he has been with Keio University, Yokohama, Japan. His research interests include abstraction science and engineering, human support, wave system, systems energy conversion, and industrial electronics. Prof. Katsura received the IEEE Industrial Electronics Society Best Conference Paper Award in 2012 and JSPS Prize in 2016. He serves as an Associate Editor of the IEEE Transactions on Industrial Electronics and Advanced Robotics.

www.katsura.sd.keio.ac.jp/

Louis-Philippe Demers (Nanyang Technological University)
Can Machine Perform?

Abstract

While I was searching about machines on stage from the perspective of performance theory, I encounter theatre theorist Phillip Auslander’s essay on the performative values of robots (Auslander 2006). Performers in the traditional performing arts such as music, dance and theatre are generally thought to have both technical skills and interpretive skills, where the latter skills are regarded as specific human skills. Auslander’s main argument is that “Although I insist that robots can possess technical performance skills, I will not claim that robots possess interpretive skills” (p.91). This presentation will then look at several levels of embodiment, from the ecological to the social, and their impact on the perceived interpretive capacities of a robot. The presentation will also refer to theatrical theories of “presence”. Presence tries to nuance the grey area between having a body and being a body, an intrinsic element for a machine to radiate liveliness, to feel animate rather than animated. I will bring several examples of live robotic performances and discuss about their liveliness on the stage.

Bio

Louis-Philippe Demers makes large-scale installations and performances. His projects can be found in theatre, opera, subway stations, art museums, science museums, music events and trade shows. Over the past two decades, he participated in more than seventy artistic and stage productions and has built more than 375 machines. Demers’ works have been featured at major venues such as Theatre de la Ville, Lille 2004, Expo 1992 and 2000, Sonambiente, ISEA, Siggraph and Sonar. He received six mentions and one distinction at Ars Electronica, the first prize of Vida 2.0, mentions at Vida 12.0 and 15.0, two jury recommendations at the Japan Media Arts Festival, the Interactive prize for Lightforms 98 and six prizes for Devolution including two Helpmann Awards. Demers was Professor of Digital Media and Exhibit Design/Scenography at the Hochschule fuer Gestaltung Karlsruhe, 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.

www.processing-plant.com

Damith Herath (University of Canberra)
Creative Failures

Abstract

“Let’s make more mistakes” was the call from the artist to the engineer. Thus began, what is now an almost a decade of collaborations with the performance artist Stelarc.
Multidisciplinary research, from a distance appears attractive and suggests great promise. In fact, Robotic Art by definition announces an inherent mixing of the engineering and the art. However, at close scrutiny, we observe that many Robotic Art projects have been realised by artists who are also skilled in engineering or at least have had the aptitude (or tenacity?) to articulate well the necessary engineering to an engineer. From this vantage point, arguing for ‘true’ research collaborations between the disciplines becomes problematic as it is an unidirectional collaboration driven by the artist. In fact, when I first encountered Stelarc, I was merely an instrument in the creative process. A process which involved making mistakes in my part. Obviously an antagonistic position to take given the profession I represent.
True collaborations emerged only later as a result of continuous dialogue and patient observations coupled with mutual respect for one another’s disciplines. As the euphemism goes, this is not about ‘Engineers creating bad art or artists creating bad engineering’, but mutually benefiting from each other's practice. In this talk I will explore some of the nuances of multidisciplinary research through my experience working with a host of collaborators from a gamut of disciplines with robotic art as the setting. During this process, there were some spectacular failures with humorous consequences, and at times, the consequences were dire. I will also draw support from a book we recently edited on Robotic Art, that for the first time brought together several leading art practitioners and engineers who work in this niche field.

Bio

Damith Herath holds a PhD in Robotics from the University of Technology, Sydney for his research at the ARC Centre of Excellence for Autonomous Systems (CAS) on robotic mapping and navigation. He has worked as a Research Fellow at CAS, as a visiting Fellow at Toyohashi University of Technology and as the lead Research Engineer on the ARC funded Thinking Head project at the MARCS institute, the Western Sydney University. Damith has over a decade of experience leading multidisciplinary robotic research projects and is the co- and founding chair of the International Workshops on Robotics & Art held in 2011 and 2014 alongside two key robotics conferences.
He is currently an Assistant Professor in Software Engineering attached to the Human-Centred Computing Laboratory at the Faculty of Education, Science, Technology and Mathematics. He is also an honorary visiting Fellow at the Sustainable Materials Research & Technology centre at the University of New South Wales. He is also the CEO and co-founder of Robological, a multi-award winning Robotics Startup based in Sydney, named one of the 23 most innovative young technology companies in Australia in 2014.

damith.org
roboticart.org/

Heather Knight (Stanford University)
What actors can teach robots

Abstract

In an age where machines are increasingly entering our daily lives, social robotics focuses on how robots can successfully share spaces, interface, and collaborate with people. Machines that fail to interact appropriately run the risk of becoming irritating and unwelcome, however, when personality and charm are added, functional machines could not only add value to their environment, but also engage, elicit trust and foster bonds with their human partners.
It turns out that acting training can inform the development of such charismatic robots, however, the challenge is to operationalize their knowledge into computational systems. This talk briefly presents Dr. Knight's past work in developing a robotic comedian, followed by a description of her work adapting acting movement training into the Computational Laban Effort system (CLE), which can be used to layer motion expression into pre-existing robot tasks. People parse non-verbal communications intuitively, even from machines that do not look like people, thus, expressive motion is a natural and efficient way to communicate with people.
Typically, researchers build instances of expressive motion into individual robot behaviors (which is not scalable), or use an independent channel such as lights or facial expressions that do not interfere with the robot's task. What is unique about this work is that it uses the same modality to do both task and expression: the robot's joint and whole-body motions. While this is not the only way for a robot to communicate expression, Expressive Motion is a channel available to all moving machines, which can work in tandem with additional communication modalities. By training robot motion features with humans in the loop, robotics researchers can gain insight on how to create interfaces that adapt the knowledge of human charisma experts -- such as actors and performers -- into robotics.

Bio

Heather Knight is a post-doc at Stanford University and adjunct Computer Science professor at Oregon State University. She also runs Marilyn Monrobot, a robot theater company featuring comedy performances by Data the Robot, and an annual Robot Film Festival. Her research interests include human-robot interaction, non-verbal machine communications and non-anthropomorphic social robots. She completed her PhD in Robotics at Carnegie Mellon University, was named to the 2011 Forbes List for 30 under 30 in Scienc, and is featured on TED.com for her Robot Comedy performances. Additional past work includes: robotics and instrumentation at NASA's Jet Propulsion Laboratory, interactive installations with Syyn Labs (including the award winning "This too shall pass" Rube Goldberg Machine music video with OK GO), field applications and sensor design at Aldebaran Robotics, and she is an alumnus from the Personal Robots Group at the MIT Media Lab.

marilynmonrobot.com

Kendra Byrne (Google [x])
Robots as creative partner

Abstract

Robots are typically thought of as the workhorses of rigid factory automation, but if you can treat them like creative partners they have the potential to take on eclectic and vibrant roles. This talk will tell the story of Bot & Dolly, a design and engineering studio that co-opted industrial automation for film, entertainment, and interactive installations. With each project, we created a new bridge between humans and machines – we built tools that enable new ways to interface with robotics. Bot & Dolly’s work includes projects for Microsoft, Chevy, and Under Armor, the award-winning film Gravity, and groundbreaking work with 3D projection mapping.

Bio

Kendra Byrne is a creative technologist who has worked with a variety of technology firms including Bot & Dolly and Google [x]. While at Bot & Dolly, she leveraged her diverse background in robotics and design to develop accessible interfaces for using technology in creative and innovative applications. This meant creating tools and systems that re-invent how engineers, creatives, and humans understand and interact with robots - for industries such as Hollywood, live entertainment, and theater. She is currently incubating innovative products and concept applications at Google [x].

www.solveforx.com/

Michel Taix (LAAS-CNRS, Toulouse, France)
When Mobile Robots meets Art

Abstract

Through two artistic experiences in mobile robotics, Off Road and transHumUs, we show how to translate these poetic ambitions into technological terms. This paper reports on the setup and the implementation of the projects. It shows how state of the art mobile robotics technology can contribute to contemporary art development. The challenge has been to design original mobile platforms carrying charges according to artist criteria in operational spaces populated by visitors.

Bio

Michel Taix received the PhD degree in Robotics from the University Paul Sabatier, Toulouse, in 1991. He is currently an Assistant Professor of the Automation Department at the University Paul Sabatier. He is completing his research at the LAAS-CNRS, Toulouse. His research interests are motion planning, anthropomorphic robots and human–computer interaction.

Michel Taix @ LAAS

Katsuyoshi Tsujita (Osaka Institute of Technology, Japan)
Robots as Mediums

Abstract

In order to verify the way of emotional communication in the visual arts, we have developed "medium perception robots" to display the relative movement between subject and medium during a drawing activity. We introduce the experimental study using three types of automated systems. The first system is an automatic drawing computer using a simulation algorithm based on the coiling patterns of heteromorphic ammonoids. The second system is a parallel-link robot that plays the role of medium combining two types of consciousness arising in the process of creating pictures: (i) consciousness of the attempts to draw, and (ii) consciousness of material resistance in the action of drawing. The third system is a Cartesian robot system which captures drawing motions. A number of experiments were conducted with human observers of such automated systems, who could then attempt to identify their drawing actions in these systems, and eventually regain or recall subjectivity in the drawing act, with the robots as mediums.

Bio

Katsuyoshi Tsujita is a Professor (Associate) at the Osaka Institute of Technology, in the Department of Robotics he joined in 2005. He received his PhD in 2004 from Kyoto University, His research has focused on multi-body dynamics, bio-inspired robotics, space engineering, motion control of legged robots and other autonomous robots, as well as the intersection between art and robots.

oit-jp.academia.edu/KatsuyoshiTsujita

Roland Fischer
Artificial Creativity - do we need machines to open up new horizons for the arts?

science.tc/
www.madscientist-festival.ch/en/
twitter.com/roland_fischer

Contributions