This paper was converted on www.awesomepapers.org from LaTeX by an anonymous user.
Want to know more? Visit the Converter page.

Implicit collaboration with a drawing machine
through dance movements

Itay Grinberg TechnionHaifaIsrael [email protected] Alexandra Bremers Cornell TechNew York, NYUSA [email protected] Louisa Pancoast louisanpancoast.comNew York, NYUSA  and  Wendy Ju 0000-0002-3119-611X Cornell TechNew York, NYUSA
(2023)
Abstract.

In this demonstration, we exhibit the initial results of an ongoing body of exploratory work, investigating the potential for creative machines to communicate and collaborate with people through movement as a form of implicit interaction (Ju, 2015). The paper describes a Wizard-of-Oz demo, where a hidden wizard controls an AxiDraw drawing robot while a participant collaborates with it to draw a custom postcard. This demonstration aims to gather perspectives from the computational fabrication community regarding how practitioners of fabrication with machines experience interacting with a mixed-initiative collaborative machine.

human-robot interaction, communication, collaboration
copyright: acmcopyrightconference: ACM Symposium on Computational Fabrication; October 08–10, 2023; New York, NY

1. Introduction and Background

Mixed-Initiative Interaction (MII), is a concept first coined by Horvitz (Horvitz, 1999) and is a paradigm that assumes that interactions are both initiated by technological artifacts as well as users—none of these two are consistently leading or following the interaction. Mixed-initiative interactions have been studied initially in the context of user interfaces (Horvitz, 1999), and later also robotics (Jiang and Arkin, 2015).

Our research investigates what happens when mixed-initiative interaction gets brought to creative machines. Since the presence of initiative brings agency to a machine, such as a pen plotter, we can consider that machine to be a non-anthropomorphic robot. This makes it worthwhile to consider interaction with mixed-initiative creative machines a topic in the field of human-robot interaction.

In creative activity, the activity itself can be understood as a conversation between the maker and material (Schon, 1983). Initiative from the machine itself, then, adds a third party to the interaction—it becomes a shared interaction between a person, a machine, and the material as an ongoing reflection. When an interaction is collaborative, there is a need for communication between the interacting parties. Past human-robot interaction research has looked into the similarities between animation and robotics and the benefits of applying animation principles to the design of robotic interactions (Takayama et al., 2011), as well as ways to design for this type of interaction. Due to the collaborative nature between creative machines and people in a mixed-initiative setting, the person is not just an observer—we propose that the interaction becomes like a dance between two parties, acting on and with the material.

In this demonstration, we present the initial results of an ongoing body of exploratory work, investigating the potential for creative machines to communicate and collaborate with people through movement as a form of implicit interaction (Ju, 2015). Through this demonstration, we aim to gather perspectives from the computational fabrication community regarding how practitioners of fabrication with machines experience interacting with a mixed-initiative collaborative machine.

2. The proposed demo

Refer to caption

Figure 1. The demo system is built around an AxiDraw plotter, modified by adding two additional motors.

We present a Wizard-of-Oz demo, where a hidden wizard controls a modified AxiDraw drawing robot while a participant collaborates with it to draw a custom postcard. An AxiDraw pen plotter (Scientist, 2022), which is augmented with two motors adding two additional degrees of freedom, is placed on the table with two cameras aimed at the work surface and at the user. Figure 1 shows four examples of the resulting postcards on the robot’s right side.

The Wizard will improvise using a set of pre-developed possible movements—however, the interaction consists of two clear stages that are described in Table 1, categorized as “Welcoming”, and Table 2, categorized as “Collaborative Drawing”. Afterwards, participants can take their postcard home.

3. Demo Requirements

The demo will be set up to run on a table. We require electricity and WiFi access, permission to use live cameras, and a chair for demo participants. The wizard will connect to the robot remotely by controlling the robot’s computer via SSH. The wizard’s “eyes” will be two cameras – one of them will show the participant, and the second one will show the workspace of the robot.

4. The Demo Design

This demonstration is intended to highlight the collaborative design method used in the design of the robot’s actions. One key element of our design approach is forming our interdisciplinary research team. The authors of this demo consist of two interaction design researchers, one mechanical engineer, and one dancer. The design process occurred during in-person meetings over the course of four months.

Refer to caption

Figure 2. A flow diagram of the communication scheme.
Images ©Evil Mad Scientist Laboratories and flaticon.com (Freepik, Muhammad_Usman, Nhor Phai)

Refer to caption

Figure 3. During one design session, the dancer instructed the interaction designer how to puppeteer the movements of the AxiDraw pen plotter.
Stage 1: Welcoming
Interaction (robot and you) Implementation (robot)
The robot calls you to come here. The robot wants you to notice it. Make noise, wave.
The robot makes eye contact. The robot points at you. Point pen at person and follow their gaze.
The robot invites you to sit down. Point pen at person, then at chair, and back at person.
If the wrong person sits down, the robot tries to communicate: ”No, not him – you!” Shake the pen and then point at the right person.
Table 1. This table describes the potential interactions between the robot and the participant before the collaborative drawing starts.
Stage 2: Collaborative Drawing
Interaction (robot and you) Implementation (robot)
The robot asks what kind of card you want to make. Point at cards and back at person.
The robot asks for paper. Point at paper, participant, and back to paper.
The robot might start drawing. Alternate between plotting and emotive movements.
The robot wants you to draw. Point at person, at the paper, then again at the person.
You draw. Wait in the home corner and make small observing movements.
The robot wants to see what you have drawn. Hover over the paper before proceeding to add plotted elements.
The robot thinks the design is done. Plot the ”Axi” signature and then make bowing movements and wait for the participant to take the paper.
The robot thinks you should take the drawing away. Point at paper, point at person, and bow again.
Table 2. This table describes the potential interactions during the collaborative drawing between the robot and the participant.

5. Acknowledgements

The authors would like to thank Cooper Murr, Tobias Weinberg, Avital Dell’Ariccia, Evil Mad Scientist, Antti Oulasvirta and François Guimbretière for their earlier suggestions, which fed into this work, and the Jacobs Technion-Cornell Institute for funding this work.

References

  • (1)
  • Horvitz (1999) Eric Horvitz. 1999. Principles of Mixed-Initiative User Interfaces. In CHI ’99: Proceedings of the SIGCHI conference on Human Factors in Computing Systems. 159 – 166.
  • Jiang and Arkin (2015) Shu Jiang and Ronald C Arkin. 2015. Mixed-initiative human-robot interaction: definition, taxonomy, and survey. In 2015 IEEE International conference on systems, man, and cybernetics. IEEE, 954–961.
  • Ju (2015) Wendy Ju. 2015. The design of implicit interactions. Issue: 2 Pages: 1–93 Publication Title: Synthesis Lectures on Human-Centered Informatics Volume: 8.
  • Schon (1983) Donald A Schon. 1983. The reflective practicioner: How professionals think in action. Basic Books New York.
  • Scientist (2022) Evil Mad Scientist. 2022. AxiDraw MiniKit 2. https://shop.evilmadscientist.com/
  • Takayama et al. (2011) Leila Takayama, Doug Dooley, and Wendy Ju. 2011. Expressing thought: improving robot readability with animation principles. In Proceedings of the 6th international conference on Human-robot interaction. ACM, Lausanne Switzerland, 69–76. https://doi.org/10.1145/1957656.1957674