Abstract
Robot-assisted training can be enhanced by using augmented feedback to support trainees during learning. Efficacy of augmented feedback is assumed to be dependent on the trainee's skill level and task characteristics. Thus, selecting the most efficient augmented feedback for individual subjects over the course of training is challenging.
We present a general concept to automate feedback selection based on predicted performance improvement. As proof of concept, we applied our concept to trunkarm rowing. Using existing data, the assumption that improvement is skill level dependent was verified and a predictive linear mixed model was obtained. We used this model to automatically select feedback for new trainees. The observed improvements were used to adapt the prediction model to the individual subject. The prediction model did not over-fit and generalized to new subjects with this adaptation.
Mainly, feedback was selected that showed the highest baseline to retention learning in previous studies. By this replication of our former best results we demonstrate that a simple decision rule based on improvement prediction has the potential to reasonably select feedback, or to provide a comprehensible suggestion to a human supervisor. To our knowledge, this is the first time an automated feedback selection has been realized in motor learning.
References
Bates, D., Maechler, M., Bolker, B., & Walker, S. (2014). lme4: Linear mixed-effects models using Eigen and S4. Retrieved from http://CRAN.R-project.org/package=lme4
Bertsekas, D. P. (2012). Dynamic Programming and Optimal Control. Athena Scientific optimization and computation series. Athena Scientific. Retrieved from https://books.google.ie/books?id=H-PSMwEACAAJ
Bishop, C. M. (2006). Pattern Recognition and Machine Learning (Information Science and Statistics). Secaucus, NJ, USA: Springer-Verlag New York, Inc.
Gelman, A., & Hill, J. (2007). Data Analysis Using Regression and Multilevel/Hierarchical Models. Analytical Methods for Social Research. Cambridge University Press. Retrieved from https://books.google.ch/books?id=lV3DIdV0F9AC
Giese, M. A., & Poggio, T. (2000). Morphable models for the analysis and synthesis of complex motion patterns. International Journal of Computer Vision, 38(1), 59–73.
Guadagnoli, M. A., & Lee, T. D. (2004). Challenge point: a framework for conceptualizing the effects of various practice conditions in motor learning. Journal of Motor Behavior, 36(2), 212–224. doi:10.3200/JMBR.36.2.212-224
Huang, Y., Guerra-Hollstein, J. D., & Brusilovsky, P. (2016). Modeling Skill Combination Patterns for Deeper Knowledge Tracing. UMAP (Extended Proceedings).
Joiner, W. M., & Smith, M. A. (2008). Long-term retention explained by a model of short-sterm learning in the adaptive control of reaching. Journal of neurophysiology, 100(5), 2948–2955.
Marchal-Crespo, L., Wolf, P., Gerig, N., Rauter, G., Jaeger, L., Vallery, H., & Riener, R. (2015). The role of skill level and motor task characteristics on the effectiveness of robotic training: first results. Rehabilitation Robotics (ICORR), 2015 IEEE International Conference on (pp. 151–156). IEEE.
R Development Core Team. (2008). R: A Language and Environment for Statistical Computing. Vienna, Austria: R Foundation for Statistical Computing. Retrieved from http://www.R-project.org
Rauter, G., Sigrist, R., Koch, C., Crivelli, F., Raai, M. van, Riener, R., & Wolf, P. (2013). Transfer of Complex Skill Learning from Virtual to Real Rowing. PLoS ONE, 8(12), 1–18. doi:10.1371/journal.pone.0082145
Rauter, G., Sigrist, R., Marchal-Crespo, L., Vallery, H., Riener, R., & Wolf, P. (2011). Assistance or challenge? Filling a gap in user-cooperative control. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (pp. 3068–3073). San Francisco, California. doi:10.1109/IROS.2011.6094832
Rauter, G., Sigrist, R., Riener, R., & Wolf, P. (2015). Learning of temporal and spatial movement aspects: A comparison of four types of haptic control and concurrent visual feedback. IEEE Transactions on Haptics, 8(4), 421-433.
Rauter, G., Zitzewitz, J. von, Duschau-Wicke, A., Vallery, H., & Riener, R. (2010). A tendon based parallel robot applied to motor learning in sports. 3rd IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob), 2010 (pp. 82–87). Tokyo, Japan. doi:10.1109/BIOROB.2010.5627788
Reinkensmeyer, D. J., Akoner, O., Ferris, D. P., & Gordon, K. E. (2009). Slacking by the human motor system: computational models and implications for robotic orthoses. Engineering in Medicine and Biology Society, 2009. EMBC 2009. Annual International Conference of the IEEE (pp. 2129–2132). IEEE.
Russell, S., Norvig, P., & Davis, E. (2010). Artificial intelligence: a modern approach. Upper Saddle River, NJ: Prentice Hall.
Scheipl, F., Greven, S., & Kuechenhoff, H. (2008). Size and power of tests for a zero random effect variance or polynomial regression in additive and linear mixed models. Computational Statistics & Data Analysis, 52(7), 3283–3299.
Sigrist, R., Rauter, G., Marchal-Crespo, L., Riener, R., & Wolf, P. (2015). Sonification and haptic feedback in addition to visual feedback enhances complex motor task learning. Experimental brain research, 233, 909–925.
Sigrist, R., Rauter, G., Riener, R., & Wolf, P. (2013). Augmented visual, auditory, haptic, and multimodal feedback in motor learning: A review. Psychonomic Bulletin & Review, 20(1), 21–53. doi:http://dx.doi.org/10.3758/s13423-012-0333-8
Vlachos, M., Hadjieleftheriou, M., Gunopulos, D., & Keogh, E. (2003). Indexing multi-dimensional time-series with support for multiple distance measures. Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining, KDD ’03 (pp. 216–225). Washington, D.C.: ACM. doi:10.1145/956750.956777
West, B. T., Welch, K. B., & Galecki, A. T. (2006). Linear Mixed Models: A Practical Guide Using Statistical Software. CRC Press. Retrieved from http://books.google.com.au/books?id=LSJ__7lDSdgC
Wu, H. G., Miyamoto, Y. R., Castro, L. N. G., Ölveczky, B. P., & Smith, M. A. (2014). Temporal structure of motor variability is dynamically regulated and predicts motor learning ability. Nature neuroscience, 17(2), 312-321.
