RSS 2016 Workshop.

[Updated 6/24/2016 with references and images from the event]

Embodied Experience and Movement Observation for Roboticists
Saturday June 18, 2016 / Ann Arbor, MI Amy LaViers alaviers@illinois.edu

Abstract:  As we work to bring robots out of the factory and into humans’ everyday life, it is important to begin designing the expression of their movement with greater care.  An area of work that is promising for helping in this task is the performing arts where professionals are trained in techniques for design and description of movement.  However, in order to effectively collaborate with this community, some transfer of concepts and approach must occur.  In this ½ day tutorial and ½ day workshop, participants will explore movement from an embodied perspective.  Participants will learn about Laban/Bartenieff Movement Studies, a set of concepts, terms, and principles utilized by many dancers and actors, in three short sessions led by a roboticist trained in this work.  The goal of this session will be to attune participants to the philosophy of many movement professionals and provide key takeaways that may be of use in their research.  Then, invited speakers will present their work, often in collaboration with artists without technical training, using participatory techniques to present their technical work in a similarly embodied format.  Finally, the day will conclude with breakout sessions for targeted discussions about the benefits and challenges of working in this way and for brainstorming sessions that will hopefully spawn new collaborations.

Attendees: We had great attendees from CMU, JPL, U Mich, Duke, WPI, Google, Sphero, UIUC, Princeton, and Aalborg University!

Speakers:  

Elizabeth Jochum – Assistant Professor – Aalborg University; Co-founder Robot Culture and Aesthetics – University of Copenhagen; theater techniques for embodied robotics

Visual and performance artists have long sought to understand what makes movement appear expressive and organic.  Artists abstract choreographic and movement principles from human performers for non-human objects and systems, such as dynamic sculptures, automated puppets, and autonomous robot performers. In many cases, this process does not involve a direct mapping of human gestures onto robots but rather observing and adapting the underlying principles that influence expressive motion and create believable characters.  Following the success of an experiment with choreographing two industrial KUKA robots in a live theatre production, this paper presents recent experiments in designing original robots with expressive motions and behaviours for a original, full-length stage play.  The presentation will also include an active, participatory demonstration of the Alexander technique – a movement training system used by actors, dancers, athletes and musicians for generating greater awareness and understanding of human movement.

 

IMG_6280

“You have to tune in to your own movement patterns to see them in others.”

Alexander Links:

Conable,Barbara. How to Learn the Alexander Technique

https://www.amazon.com/How-Learn-Alexander-Technique-Students/dp/0962259543

Entertainment Robots and Embodied Interaction:

E. Jochum et al., Using theatre to study interaction with care robots, International Journal of Social Robotics (in press).

E. Jochum et al., Sequence and Chance: Design and Control Methods for Entertainment Robots, Robotics and Autonomous Systems (in press).

ACM CHI Workshop: “Move to Be Moved” (2016)

C. Erkut and A. Rajala-Erkut, Beyond Command & Control: Sketching Embodied Interaction, Proceedings CHI EA, 18 (2015), 1681–1686.

C. Erkut et al., Sketches in Embodied Interaction: Balancing Movement and Technological Perspectives, Proceedings HCI International (2014), 30–35.

L. Wonjun et al., Practicing somaesthetics, Proceedings of Designing Interactive Systems (2014), 1055–1064.

R. Fensham Choreographic Archives: Towards an Ontology of Movement Images. Performing Archives/Archives of Performance. Museum Tusculanum Press. 2013

Of Interest:

Fremtiden (the Future): https://vimeo.com/89607669

Truckballet – Veera Suvalo Grimberg – Finland https://www.youtube.com/watch?v=eOqRYYfGoNE

Eurovision Grand Prix – https://www.youtube.com/watch?v=hTWstBgmThE

Digital Dance Archives: http://www.dance-archives.ac.uk

Heather Knight – PhD Candidate – Carnegie Mellon University; interactions with non-anthropomorphic platforms

By adapting strategies from theater, my research improves the ability of non-anthropomorphic robots to effectively layer nonverbal behaviors on their task actions, and interact with us successfully & charismatically. Designing motion-based interfaces enables us to efficiently quantify data from non-technical expressive motion experts that can then be applied to autonomous robotic systems. Workshop participants will have a chance to enact hallway navigation trajectories, which will we discuss in terms of Laban Effort System component features.

IMG_6308

“Motion is one way we anthropomorphize robots.”

References:

Knight, H. and and Simmons, R. “Designing motions that express a robot’s thoughts, intentions, or feelings using the Laban Effort System.” Journal of Social Robotics, Springer, 2017 (In progress)

H. Knight and R. Simmons. “Laban Head-Motions Convey Robot State: A Call for Robot Body Language.”International Conference on Robotics and Automation, 2016.

Knight, H, Veloso, M. and Simmons, R. “Taking Candy from a Robot: Speed Features and Candy Accessibility Predict Human Response.” In Proceedings of International Conference on Robot and Human Interactive Communication (Ro-Man ‘15), September 2015 in Kobe, Japan.

Knight, H and Simmons, R. “Expressive Motion with X, Y and Theta: Laban Effort Features for Mobile Robots.” In Proceedings of International Symposium Robot and Human Interactive Communication (RO-MAN ‘14), August 2014 in Edinburgh, Scotland.

Knight, H. “Eight Lessons learned about Non-verbal Interactions through Robot Theater.” Social Robotics.Springer Berlin Heidelberg, 2011. 42-51.

Amy LaViers – Assistant Professor – University of Illinois at Urbana-Champaign; embodied, platform-invariant motion primitives

This talk will discuss a project creating a supervisory control system that has knobs aligned with the experience of human movement. This work is translating concepts from Laban/Bartenieff Movement Studies (LBMS) to give high-level, cross-platform abstractions an embodied starting point.  The goal of the project is to develop a control interface that will allow operators greater control – particularly for complex movement tasks – over existing hardware and that can be utilized on any robotic platforms through a formulated translation process.

IMG_6327

“Your body creates complex accommodations to respond to a spatial pull.”

 

LBMS General References:

K. Studd and L. Cox. “Everybody is a Body.” Dog Ear Publishing. 2013.

P. Hackney. “Making Connections: Total Body Integration Through Bartenieff Fundamentals.” Routledge. 2000.

I. Bartenieff. “Body Movement: Coping with the Environment.” Routledge. 1980.

R. Laban and L. Ullman. “Mastery of Movement.” 4th Ed. Pre Texos Ed. 2011.

R. Laban. “Choreutics.” Dance Books Ltd. 2011.

My References:

Umer Huzaifa, Anum Jang Sher, and Amy LaViers. “Platform-invariant Labeling and Data-Driven Platform Configuration Determination for Spatial Commands.” (In progress)

U. Huzaifa and A. LaViers. “Control Design for Planar Model of a Core-located Actuation Walker.” IEEE BioRob. Singapore. 2016.

U. Huzaifa, C. Bernier, Z. Calhoun, C. Kohout, J. Heddy, B. Libowitz, A. Moenning, J. Ye, C. Maguire, and A. LaViers. “Embodied Movement Strategies for Development of a Core-located Actuation Walker.” IEEE BioRob. Singapore. 2016.

A. LaViers, Y. Sheng, J. Heddy, A. Bashiri, and L. Bai. Abstractions for Design-by-Humans of Heterogeneous Autonomous Behaviors. Dance Notations and Robot Motion Springer Tracts in Advanced Robotics (STAR). 2015.

A. LaViers, L. Teague, M. Egerstedt. Style-based Robotic Motion in Contemporary Dance Performance. Controls and Art: Inquires that Intersect the Subjective and the Objective. A. LaViers and M. Egerstedt (Eds.) Springer. 2014.

A. LaViers and M. Egerstedt. Style-based Robotic Motion. American Control Conference. Montreal, CAN. 2012.

A. LaViers, Y. Chen, C. Belta, and M. Egerstedt. Automatic Sequencing of Ballet Poses: A Formal Approach to Phrase Generation IEEE Robotics and Automation Magazine, pp. 87-95 Sept. 2011.

Kayhan Ozcimder – Postdoctoral Research Associate – Princeton University; communication through motion in dance

In this talk, I will discuss principles of motion-based communication in human group behavior by investigating the leader-follower interactions in a performance art, salsa. I will show that the dance performance can be abstracted to a topological space and the constraints on the motion transitions can be mapped to the invariances defined in topological knot theory. I will demonstrate how to dance elementary level salsa with a mathematical perception of communication through actions.

IMG_6338

“Salsa dancers teach with mathematical precision.”

References:

 Baillieul, John, and Kayhan Özcimder. “The control theory of motion-based communication: Problems in teaching robots to dance.” 2012 American Control Conference (ACC). IEEE, 2012.

Baillieul, John, and Kayhan Özcimder. “Dancing Robots: The Control Theory of Communication Through Movement.” Controls and Art. Springer International Publishing, 2014. 51-72.

Özcimder, Kayhan. “Communication through motion in dance with topological constraints.” 2014 American Control Conference. IEEE, 2014.

Özcimder, Kayhan, Zhaodan Kong, and John Baillieul. “Algorithmic approaches to artistic movement.” 53rd IEEE Conference on Decision and Control. IEEE, 2014.

The “Human Robot Dance” youtube video : https://www.youtube.com/watch?v=3S5jXhZG-u0

Event Schedule:

8:30-9:20am – Body, Effort, Space, and Shape in Motif

– 10 minute break –

9:30-11:30am – Invited speakers give 30 minute “embodied talks” that continue to get participants up on their feet and moving

– 10 minute break –

11:40am-12pm – Theme of Function/Expression in Movement

**During the workshop, participants will be invited to identify lessons learned, ideas generated, and questions moving forward to report back to the large group via a large working whiteboard.

***Participants are also invited to bring a poster describing their work, which will be posted around the room during the event and can generate discussion during the breaks!