Experiments with Vizzy as a Coach for Elderly Exercise Martina ai - - PowerPoint PPT Presentation

Experiments with Vizzy as a Coach for Elderly Exercise

João Avelino, Hugo Simão, Ricardo Ribeiro, Plinio Moreno, Rui Figueiredo, Nuno Duarte, Ricardo Nunes, Alexandre Bernardino Institute for Systems and Robotics, Instituto Superior Técnico, University of Lisbon Lisbon, Portugal Martina Čaić, Dominik Mahr, Gaby Odekerken-Schröder Marketing & Supply Chain Management Maastricht University Maastricht, The Netherlands

• Motivation
• Related Work
• Approach
• End-user trials
• Conclusions and future work

Outline

2

• Sedentarism increases health risks
• It affects elderly populations
• Elderly population growing at a fast pace

Motivation

3

• A robot instructor that performs gestures for the

user to imitate or vice-versa [1]

• NAO with Kinect to promote imitation games [2]
• The robot that demonstrates fitness exercises [3]
• A robot that exercises along with the young

users [4]

Related Work

4

[1] Juan Fasola and Maja J Matarić. 2013. A Socially Assistive Robot Exercise Coach for the Elderly. J. Hum.-Robot Interact. 2, 2 (June 2013), 3–32. https://doi.org/10.5898/JHRI.2.2.Fasola [2] Werner, F., Krainer, D., Oberzaucher, J., & Werner, K. (2013). Evaluation of the acceptance of a social assistive robot for physical training support together with older users and domain experts. Assistive Technology: From Research to Practice: AAATE 2013, 33, 137. [3] Görer, B., Salah, A. A., & Akın, H. L. (2017). An autonomous robotic exercise tutor for elderly people. Autonomous Robots, 41(3), 657-678. [4] Schneider, S., & Kümmert, F. (2016, November). Exercising with a humanoid companion is more effective than exercising

• alone. In Humanoid Robots (Humanoids), 2016 IEEE-RAS 16th International Conference on (pp. 495-501). IEEE.

• Users play exergames [2] on the PEPE platform [1]
• A robot (Vizzy) [3] acts as a coach for the elderly

Approach

5 [1] Hugo Simão and Alexandre Bernardino. 2017. User Centered Design of an Augmented Reality Gaming Platform for Active

Aging in Elderly Institutions. In Proceedings of the 5th International Congress on Sport Sciences Research and Technology Support (icSPORTS 2017). [2] Afonso Gonçalves, J. Muñoz, E. Gouveia, M. S. Cameir‹o, and S. Bermudez i Badia.2017. Portuguese Tradition Inspired Exergames for Older People - Strategic Tools to Promote Functional Fitness. In Proceedings of the 5th International Congress on Sport Sciences Research and Technology Support (icSPORTS 2017). [3] R. Nunes, R. Beira, P. Moreno, L. Vargas, J. Santos-Victor, A. Bernardino, M. Aragão, D. Aragão, and R. Figueiredo. 2015. Vizzy: A humanoid on wheels for assistive robotics. In Proceedings of the Second Iberian Robotics Conference (ROBOT 2015).

PEPE – Portable Exergame Platform for the Elderly

6

Vizzy: the exercise coach

7

Laser scanner Cameras RGBD camera 30 degrees of freedom https://www.facebook.com/vizzyvisla b

Dialogue control GUI

8

Motor control interface

9

End user trials: Experimental protocol

10

Inviting user Guiding user to game area Coaching and motivating

Selfie time

• Participants and test conditions
• 36 elderly participants:

65 to 94 years old (μ = 80.83, σ = 5.84)

• Can play the game sitting or

walking

• 3 Institutions:
• LATI – Liga dos Amigos da

Terceira Idade

• Centro Social Comunitário

da Nossa Sra. Dos Milagres

• Residência Sénior de

Belverde

End user trials (2)

11

• Items adapted from the following scales:
• Godspeed Questionnaire
• ALMERE model
• Adapted from Jiun-Yin Jian et al for Trust [5]
• Dimensions:
• Perceived Competence
• Perceived Enjoyment
• Perceived Trust
• Aesthetics

Questionnaire

12 [5] Jian, J. Y., Bisantz, A. M., & Drury, C. G. (2000). Foundations for an empirically determined scale of trust in automated systems. International Journal of Cognitive Ergonomics, 4(1), 53-71.

Questionnaire Results

13

• Novelty effect: some people felt anxious at

first, but then interacted without problems

• Gaze direction is important:
• If accurate people will immediately

understand that the robot is talking to them

• Head control seemed to effect persuasion

Observation results

14

• Group effects:
• Persuasion
• Support
• More spontaneous interaction
• Voice commands:
• Need to be assertive
• Have a good repertoire of utterances

Observation results (2)

15

• Humor:
• People enjoy when the robot displays humor
• People feel challenged by the robot
• Users that were not interacting started to interact

Observation results (3)

16

“I bet you haven’t exercised this much since you were 20 years old.” “What? I exercise a lot. Every day I go up and down my stairs!” Robot Human

• Good robot acceptance
• Future developments:
• More diverse, emotional and quicker utterances
• Add arm gestures for instructions and feedback

Conclusions and future work

17

End – Thank You