Advertisement

Train with Me: A Study Comparing a Socially Assistive Robot and a Virtual Agent for a Rehabilitation Task

  • Valentina VascoEmail author
  • Cesco WillemseEmail author
  • Pauline Chevalier
  • Davide De Tommaso
  • Valerio Gower
  • Furio Gramatica
  • Vadim Tikhanoff
  • Ugo Pattacini
  • Giorgio Metta
  • Agnieszka Wykowska
Conference paper
  • 276 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11876)

Abstract

Long-term motor deficits affect approximately two thirds of stroke survivors, reducing their quality of life. An effective rehabilitation therapy requires intense and repetitive training, which is resource demanding. Virtual Agents (VAs) and Socially Assistive Robots (SARs) offer high intensity, repetitive and reproducible therapy and are thus both promising as rehabilitation tools. In this paper, we compare a SAR and a VA during a rehabilitation task in terms of users’ engagement and movement performance, while leveraging neuroscientific methods to investigate potential differences at the neural level. Results show that our participants’ performance on the exercise was higher with a SAR than with a VA, which was especially clear under conditions of decreased perceptual information. Our participants reported higher levels of engagement with the SAR. Taken together, we provide evidence that SARs are a favorable alternative to VAs as rehabilitation tools.

Keywords

Socially assistive robot Virtual agent Embodiment 

Notes

Acknowledgments

This project is funded by the Joint Lab between IIT and Fondazione Don Carlo Gnocchi Onlus and by the Minded Program - Marie Skłodowska-Curie grant agreement No. 754490 (fellowship awarded to Pauline Chevalier). The authors thank Nina Hinz and Serena Marchesi for their assistance with data collection.

References

  1. 1.
    Lawrence, E.S., et al.: Estimates of the prevalence of acute stroke impairments and disability in a multiethnic population. Stroke 5, 1279–1284 (2001)CrossRefGoogle Scholar
  2. 2.
    Carlsson, H., et al.: SENSory re-learning of the UPPer limb after stroke (SENSUPP): study protocol for a pilot randomized controlled trial. Trials 19(1), 229 (2018)CrossRefGoogle Scholar
  3. 3.
    Feil-Seifer, D., Mataric, M.J.: Defining socially assistive robotics. In: Proceedings of the 2005 IEEE 9th International Conference on Rehabilitation Robotics, pp. 465–468 (2005)Google Scholar
  4. 4.
    Schneider, S., Kummert, F.: Comparing the effects of social robots and virtual agents on exercising motivation. In: Ge, S.S. (ed.) ICSR 2018. LNCS (LNAI), vol. 11357, pp. 451–461. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-05204-1_44CrossRefGoogle Scholar
  5. 5.
    Fasola, J., Mataric, M.: Comparing physical and virtual embodiment in a socially assistive robot exercise coach for the elderly. Technical report, CRES–11–003 (2011)Google Scholar
  6. 6.
    Brooks, D., Chen, Y., Howard, A.: Simulation versus embodied agents: does either induce better human adherence to physical therapy exercise? In: Proceedings of the IEEE International Conference on Biomedical Robotics and Biomechatronics, pp. 1715–1720 (2012)Google Scholar
  7. 7.
    Mataric, M., et al.: Socially assistive robotics for stroke and mild TBI rehabilitation. Stud. Health Technol. Inform. 145, 249–262 (2009)Google Scholar
  8. 8.
    Fiol-Roig, G., et al.: The intelligent butler: a virtual agent for disabled and elderly people assistance. In: Corchado, J.M., Rodríguez, S., Llinas, J., Molina, J.M. (eds.) International Symposium on Distributed Computing and Artificial Intelligence 2008. Advances in Soft Computing, vol. 50, pp. 375–384. Springer, Heidelberg (2008).  https://doi.org/10.1007/978-3-540-85863-8_44CrossRefGoogle Scholar
  9. 9.
    Arip, E.S.M., et al.: Virtual reality rehabilitation for stroke patients: recent review and research issues. AIP Conf. Proc. 1905, 050007 (2017).  https://doi.org/10.1063/1.5012226CrossRefGoogle Scholar
  10. 10.
    Li, J.: The benefit of being physically present: a survey of experimental works comparing copresent robots, telepresent robots and virtual agents. Int. J. Hum Comput Stud. 77, 23–37 (2015)CrossRefGoogle Scholar
  11. 11.
    Cao, Z., et al.: OpenPose: realtime multi-person 2D pose estimation using Part Affinity Fields, arXiv preprint arXiv:1812.08008 (2018)
  12. 12.
    Parmiggiani, A., et al.: The design and validation of the R1 personal humanoid. In: 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 674–680 (2017)Google Scholar
  13. 13.
    Chevalier, G.: LSTMs for human activity recognition (2016). https://github.com/guillaume-chevalier/LSTM-Human-Activity-Recognition
  14. 14.
    Sidner, C.L., et al.: Explorations in engagement for humans and robots. Artif. Intell. 166(1–2), 140–164 (2005)CrossRefGoogle Scholar
  15. 15.
    Hall, J., et al.: Perception of own and robot engagement in human–robot interactions and their dependence on robotics knowledge. Rob. Auton. Syst. 62(3), 392–399 (2014)CrossRefGoogle Scholar
  16. 16.
    Hobson, H.M., Bishop, V.M.: The interpretation of mu suppression as an index of mirror neuron activity: past, present and future. Roy. Soc. Open Sci. 4(3) (2017)CrossRefGoogle Scholar
  17. 17.
    Rossi, S., et al.: Socially assistive robot for providing recommendations: comparing a humanoid robot with a mobile application. Int. J. Soc. Rob. 10, 265–278 (2018)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Valentina Vasco
    • 1
    Email author
  • Cesco Willemse
    • 2
    Email author
  • Pauline Chevalier
    • 2
  • Davide De Tommaso
    • 2
  • Valerio Gower
    • 3
  • Furio Gramatica
    • 3
  • Vadim Tikhanoff
    • 1
  • Ugo Pattacini
    • 1
  • Giorgio Metta
    • 1
  • Agnieszka Wykowska
    • 2
  1. 1.iCubIstituto Italiano di Tecnologia (IIT)GenoaItaly
  2. 2.Social Cognition in Human-Robot InteractionIstituto Italiano di Tecnologia (IIT)GenoaItaly
  3. 3.IRCCS Fondazione Don Carlo GnocchiMilanItaly

Personalised recommendations