Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content

Priors Inspired by Speed-Accuracy Trade-Offs for Incremental Learning of Probabilistic Movement Primitives

  • Conference paper
  • First Online:
Towards Autonomous Robotic Systems (TAROS 2021)

Abstract

Probabilistic Movement Primitives (ProMPs) model robot motor skills by capturing the mean and variance of a set of demonstrations provided by a human teacher. Such a probabilistic representation of motor skills is beneficial in physical human-robot cooperation (pHRC) where robots have to respond to the inherent variance in human motion. However, learning ProMPs incrementally and from scratch, as it is desirable in pHRC, is difficult due to the large number of parameters required to model the distribution of a motor skill compared to the few demonstrations available at the beginning of training. In this paper we propose to predict the variance structure of a motor skill based on the speed found in the individual demonstrations and to incorporate this prediction into the prior parameter distribution of the ProMP. Our basic approach is taking inspiration from the speed-accuracy trade-off found in human motion. Experimental evaluation suggests that with the proposed prior parameter distributions, the true distribution is approached faster in incremental learning of a motor skill than with the priors previously proposed for batch learning.

This work was funded by the Research Council of Norway through grant Nr. 280771.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 69.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 89.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Accot, J., Zhai, S.: Beyond Fitts’ law. In: Pemberton, S. (ed.) Human Factors in Computing Systems, pp. 295–302. ACM Press, Addison-Wesley (1997)

    Google Scholar 

  2. Fitts, P.M.: The information capacity of the human motor system in controlling the amplitude of movement. J. Exp. Psychol. 47(6), 381–391 (1954)

    Article  Google Scholar 

  3. Gomez-Gonzalez, S., Neumann, G., Scholkopf, B., Peters, J.: Adaptation and robust learning of probabilistic movement primitives. IEEE Trans. Rob. 36(2), 366–379 (2020)

    Article  Google Scholar 

  4. Murphy, K.P.: Machine Learning: A Probabilistic Perspective. Adaptive Computation and Machine Learning Series. MIT Press, Cambridge and London (2012)

    Google Scholar 

  5. Paraschos, A., Daniel, C., Peters, J.R., Neumann, G.: Probabilistic movement primitives. In: Burges, C.J.C., Bottou, L., Welling, M., Ghahramani, Z., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 26, pp. 2616–2624. Curran Ass., Inc. (2013)

    Google Scholar 

  6. Schäle, D., Stoelen, M.F., Kyrkjebø E.: Incremental learning of probabilistic movement primitives (ProMPs) for human-robot cooperation (2021, preprint available on arXiv). https://arxiv.org/abs/2105.13775

  7. Stoelen, M.F., Akin, D.L.: Assessment of Fitts’ law for quantifying combined rotational and translational movements. Hum. Factors 52(1), 63–77 (2010)

    Article  Google Scholar 

  8. Triantafyllidis, E., Li, Z.: The challenges in modeling human performance in 3D space with Fitts’ law (2021)

    Google Scholar 

  9. Yamanaka, S., Miyashita, H.: Modeling the steering time difference between narrowing and widening tunnels. In: Kaye, J., Druin, A., Lampe, C., Morris, D., Hourcade, J.P. (eds.) CHI 2016, pp. 1846–1856. The Association for Computing Machinery, New York (2016)

    Google Scholar 

  10. Yamanaka, S., Stuerzlinger, W., Miyashita, H., et al.: Steering through sequential linear path segments. In: Mark, G. (ed.) Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems, pp. 232–243. ACM, New York (2017)

    Chapter  Google Scholar 

  11. Zhou, X., Cao, X., Ren, X.: Speed-accuracy tradeoff in trajectory-based tasks with temporal constraint. In: Gross, T., et al. (eds.) INTERACT 2009. LNCS, vol. 5726, pp. 906–919. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-03655-2_99

    Chapter  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Daniel Schäle .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Schäle, D., Stoelen, M.F., Kyrkjebø, E. (2021). Priors Inspired by Speed-Accuracy Trade-Offs for Incremental Learning of Probabilistic Movement Primitives. In: Fox, C., Gao, J., Ghalamzan Esfahani, A., Saaj, M., Hanheide, M., Parsons, S. (eds) Towards Autonomous Robotic Systems. TAROS 2021. Lecture Notes in Computer Science(), vol 13054. Springer, Cham. https://doi.org/10.1007/978-3-030-89177-0_28

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-89177-0_28

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-89176-3

  • Online ISBN: 978-3-030-89177-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics