Skip to main content

Repairing Learned Controllers with Convex Optimization: A Case Study

Part of the Lecture Notes in Computer Science book series (LNTCS,volume 11494)

Abstract

Despite the increasing popularity of Machine Learning methods, their usage in safety-critical applications is sometimes limited by the impossibility of providing formal guarantees on their behaviour. In this work we focus on one such application, where Kernel Ridge Regression with Random Fourier Features is used to learn controllers for a prosthetic hand. Due to the non-linearity of the activation function used, these controllers sometimes fail in correctly identifying users’ intention. Under specific circumstances muscular activation levels may be misinterpreted by the method, resulting in the prosthetic hand not behaving as intended. To alleviate this problem, we propose a novel method to verify the presence of this kind of intent detection mismatch and to repair controllers leveraging off-the-shelf LP technology without using additional data. We demonstrate the feasibility of our approach using datasets gathered from human participants.

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   54.99
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

Learn about institutional subscriptions

Notes

  1. 1.

    In practice, the value of \(t_a\) is upper bounded by operating range of EMG sensors.

  2. 2.

    We implemented our procedure using Python version 2.7. and the libraries sklearn and cvxopt for learning and optimization respectively. The default solver of cvxopt, i.e., conelp, was used – see [27] for more details. All the experiments are capped at 10 min of CPU time and 4 GBs of memory; experiments ran on a Ubuntu 18.04 machine equipped with a quad-core i5 Intel CPU running at 2.60 GHz.

  3. 3.

    Notice that for power-grasping \(a_{max}\) is equal to one.

References

  1. Taigman, Y., Yang, M., Ranzato, M., Wolf, L.: DeepFace: closing the gap to human-level performance in face verification. In: CVPR, pp. 1701–1708 (2014)

    Google Scholar 

  2. Yu, D., Hinton, G.E., Morgan, N., Chien, J.-T., Sagayama, S.: Introduction to the special section on deep learning for speech and language processing. IEEE Trans. Audio Speech Lang. Process. 20(1), 4–6 (2012)

    CrossRef  Google Scholar 

  3. LeCun, Y., Bengio, Y., Hinton, G.E.: Deep learning. Nature 521(7553), 436–444 (2015)

    CrossRef  Google Scholar 

  4. Rahimi, A., Recht, B.: Random features for large-scale kernel machines. In: NIPS, pp. 1177–1184 (2008)

    Google Scholar 

  5. Gijsberts, A., Metta, G.: Incremental learning of robot dynamics using random features. In: ICRA, pp. 951–956 (2011)

    Google Scholar 

  6. Fougner, A., Stavdahl, Ø., Kyberd, P.J., Losier, Y.G., Parker, P.A.: Control of upper limb prostheses: terminology and proportional myoelectric control - a review. IEEE Trans. Neural Syst. Rehabil. Eng. 20(5), 663–677 (2012)

    CrossRef  Google Scholar 

  7. Merletti, R., Botter, A., Cescon, C., Minetto, M.A., Vieira, T.M.M.: Advances in surface EMG: recent progress in clinical research applications. Crit. Rev. Biomed. Eng. 38(4), 347–379 (2011)

    CrossRef  Google Scholar 

  8. Gijsberts, A., et al.: Stable myoelectric control of a hand prosthesis using non-linear incremental learning. Front. Neurorobot. 8 (2014)

    Google Scholar 

  9. Strazzulla, I., Nowak, M., Controzzi, M., Cipriani, C., Castellini, C.: Online bimanual manipulation using surface electromyography and incremental learning. IEEE Trans. Neural Syst. Rehabil. Eng. 25(3), 227–234 (2017)

    CrossRef  Google Scholar 

  10. Gestel, T.V., et al.: Benchmarking least squares support vector machine classifiers. Mach. Learn. 54(1), 5–32 (2004)

    CrossRef  Google Scholar 

  11. Patel, G., Nowak, M., Castellini, C.: Exploiting knowledge composition to improve real-life hand prosthetic control. IEEE Trans. Neural Syst. Rehabil. Eng. 25(7), 967–975 (2017)

    CrossRef  Google Scholar 

  12. Schrijver, A.: Theory of Linear and Integer Programming. Wiley-Interscience Series in Discrete Mathematics and Optimization. Wiley, Hoboken (1999)

    MATH  Google Scholar 

  13. Leofante, F., Narodytska, N., Pulina, L., Tacchella, A.: Automated verification of neural networks: advances, challenges and perspectives. arXiv preprint arXiv:1805.09938 (2018)

  14. Narodytska, N., Kasiviswanathan, S.P., Ryzhyk, L., Sagiv, M., Walsh, T.: Verifying properties of binarized deep neural networks. In: AAAI, pp. 6615–6624 (2018)

    Google Scholar 

  15. Pulina, L., Tacchella, A.: An abstraction-refinement approach to verification of artificial neural networks. In: Touili, T., Cook, B., Jackson, P. (eds.) CAV 2010. LNCS, vol. 6174, pp. 243–257. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-14295-6_24

    CrossRef  Google Scholar 

  16. Katz, G., Barrett, C., Dill, D.L., Julian, K., Kochenderfer, M.J.: Reluplex: an efficient SMT solver for verifying deep neural networks. In: Majumdar, R., Kunčak, V. (eds.) CAV 2017. LNCS, vol. 10426, pp. 97–117. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-63387-9_5

    CrossRef  Google Scholar 

  17. Leofante, F., Tacchella, A.: Learning in physical domains: mating safety requirements and costly sampling. In: Adorni, G., Cagnoni, S., Gori, M., Maratea, M. (eds.) AI*IA 2016. LNCS (LNAI), vol. 10037, pp. 539–552. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-49130-1_39

    CrossRef  Google Scholar 

  18. Cheng, C.-H., Nührenberg, G., Ruess, H.: Maximum resilience of artificial neural networks. In: D’Souza, D., Narayan Kumar, K. (eds.) ATVA 2017. LNCS, vol. 10482, pp. 251–268. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-68167-2_18

    CrossRef  Google Scholar 

  19. Fischetti, M., Jo, J.: Deep neural networks and mixed integer linear optimization. Constraints 23(3), 296–309 (2018)

    CrossRef  MathSciNet  Google Scholar 

  20. Ehlers, R.: Formal verification of piece-wise linear feed-forward neural networks. In: D’Souza, D., Narayan Kumar, K. (eds.) ATVA 2017. LNCS, vol. 10482, pp. 269–286. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-68167-2_19

    CrossRef  Google Scholar 

  21. Gehr, T., Mirman, M., Drachsler-Cohen, D., Tsankov, P., Chaudhuri, S., Vechev, M.: AI2: safety and robustness certification of neural networks with abstract interpretation. In: 2018 IEEE Symposium on Security and Privacy (SP) (2018)

    Google Scholar 

  22. Valero-Cuevas, F.J.: Predictive modulation of muscle coordination pattern magnitude scales fingertip force magnitude over the voluntary range. J. Neurophysiol. 83(3), 1469–1479 (2000)

    CrossRef  Google Scholar 

  23. Poston, B., Danna-Dos Santos, A., Jesunathadas, M., Hamm, T.M., Santello, M.: Force-independent distribution of correlated neural inputs to hand muscles during three-digit grasping. J. Neurophysiol. 104(2), 1141–1154 (2010)

    CrossRef  Google Scholar 

  24. de Rugy, A., Loeb, G.E., Carroll, T.J.: Muscle coordination is habitual rather than optimal. J. Neurosci. 32(21), 7384–7391 (2012)

    CrossRef  Google Scholar 

  25. He, J., Zhang, D., Sheng, X., Li, S., Zhu, X.: Invariant surface emg feature against varying contraction level for myoelectric control based on muscle coordination. IEEE J. Biomed. Heal. Inform. 19(3), 874–882 (2015)

    Google Scholar 

  26. Al-Timemy, A.H., Khushaba, R.N., Bugmann, G., Escudero, J.: Improving the performance against force variation of emg controlled multifunctional upper-limb prostheses for transradial amputees. IEEE Trans. Neural Syst. Rehabil. Eng. 24(6), 650–661 (2016)

    CrossRef  Google Scholar 

  27. Vandenberghe, L.: The CVXOPT linear and quadratic cone program solvers (2010)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Dario Guidotti .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2019 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Guidotti, D., Leofante, F., Castellini, C., Tacchella, A. (2019). Repairing Learned Controllers with Convex Optimization: A Case Study. In: Rousseau, LM., Stergiou, K. (eds) Integration of Constraint Programming, Artificial Intelligence, and Operations Research. CPAIOR 2019. Lecture Notes in Computer Science(), vol 11494. Springer, Cham. https://doi.org/10.1007/978-3-030-19212-9_24

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-19212-9_24

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-19211-2

  • Online ISBN: 978-3-030-19212-9

  • eBook Packages: Computer ScienceComputer Science (R0)