Hostname: page-component-cd9895bd7-gxg78 Total loading time: 0 Render date: 2024-12-23T11:00:50.715Z Has data issue: false hasContentIssue false
  • English
  • Français

Estimating Fingertip Forces, Torques, and Local Curvatures from Fingernail Images

Published online by Cambridge University Press:  26 September 2019

Nutan Chen Open the ORCID record for Nutan Chen [Opens in a new window] ,
Göran Westling ,
Benoni B. Edin  and
Patrick van der Smagt
Nutan Chen*
Affiliation:
Machine Learning Research Lab, Volkswagen Group, Germany. E-mail: smagt@argmax.org
Göran Westling
Affiliation:
Department of Integrative Medical Biology, Physiology Section, Umeå University, Sweden. E-mails: goran.westling@gmail.com, benoni.edin@gmail.com
Benoni B. Edin
Affiliation:
Department of Integrative Medical Biology, Physiology Section, Umeå University, Sweden. E-mails: goran.westling@gmail.com, benoni.edin@gmail.com
Patrick van der Smagt
Affiliation:
Machine Learning Research Lab, Volkswagen Group, Germany. E-mail: smagt@argmax.org
*
*Corresponding author. E-mail: nutan.chen@gmail.com
Get access Rights & Permissions [Opens in a new window]

Summary

The study of dexterous manipulation has provided important insights into human sensorimotor control as well as inspiration for manipulation strategies in robotic hands. Previous work focused on experimental environment with restrictions. Here, we describe a method using the deformation and color distribution of the fingernail and its surrounding skin to estimate the fingertip forces, torques, and contact surface curvatures for various objects, including the shape and material of the contact surfaces and the weight of the objects. The proposed method circumvents limitations associated with sensorized objects, gloves, or fixed contact surface type. In addition, compared with previous single finger estimation in an experimental environment, we extend the approach to multiple finger force estimation, which can be used for applications such as human grasping analysis. Four algorithms are used, c.q., Gaussian process, convolutional neural networks, neural networks with fast dropout, and recurrent neural networks with fast dropout, to model a mapping from images to the corresponding labels. The results further show that the proposed method has high accuracy to predict force, torque, and contact surface.

Keywords

Fingertip forcesMachine learningImage processingFingernail images
Type
Articles
Information
Robotica , Volume 38 , Issue 7 , July 2020 , pp. 1242 - 1262
Copyright
© Cambridge University Press 2019

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Johansson, R. S. and Flanagan, J. R., Sensorimotor Control of Manipulation, Encyclopedia of Neuroscience. (Elsevier, Netherlands, 2009) pp. 593–604.Google Scholar
Panarese, A. and Edin, B. B., “Human ability to discriminate direction of three-dimensional force stimuli applied to the finger pad,” J. Neurophysiol. 105(2), 541–547 (2011).CrossRefGoogle ScholarPubMed
Sun, Y., Hollerbach, J. and Mascaro, S., “Estimation of fingertip force direction with computer vision,” IEEE Tr. Robot. 25(6), 1356–1369 (2009).CrossRefGoogle Scholar
Urban, S., Bayer, J., Osendorfer, C., Westling, G., Edin, B. B. and van der Smagt, P., “Computing Grip Force and Torque from Finger Nail Images Using Gaussian Processes,” In: IROS (IEEE, 2013).Google Scholar
Chen, N., Urban, S., Osendorfer, C., Bayer, J. and van der Smagt, P., “Estimating Finger Grip Force from an Image of the Hand Using Convolutional Neural Networks and Gaussian Processes,” In: Proc. ICRA (IEEE, 2014).CrossRefGoogle Scholar
Chen, N., Urban, S., Bayer, J. and van der Smagt, P., “Measuring Fingertip Forces from Camera Images for Random Finger Poses,” In: IROS (IEEE, 2015).Google Scholar
Sun, Y., Hollerbach, J. and Mascaro, S., “Predicting fingertip forces by imaging coloration changes in the fingernail and surrounding skin,” IEEE Tr. Biomed. Eng. 55(10), 2363–2371 (2008).CrossRefGoogle ScholarPubMed
Grieve, T., Lincoln, L., Sun, Y., Hollerbach, J. and Mascaro, S., “3d force prediction using fingernail imaging with automated calibration,” In: IEEE Haptics Symposium (IEEE, 2010) pp. 113–120.CrossRefGoogle Scholar
Grieve, T. R., Hollerbach, J. M. and Mascaro, S. A., “Optimizing fingernail imaging calibration for 3d force magnitude prediction,” IEEE Trans. Haptics 9(1), 69–79 (2016).CrossRefGoogle ScholarPubMed
Myronenko, A. and Song, X. B., “Intensity-based image registration by minimizing residual complexity.” IEEE Trans. Med. Imaging 29(11), 1882–1891 (2010).CrossRefGoogle ScholarPubMed
Grieve, T. R., Hollerbach, J. M. and Mascaro, S. A., “Force Prediction by Fingernail Imaging Using Active Appearance Models,” In: World Haptics Conference (WHC) (IEEE, 2013) pp. 181–186.CrossRefGoogle Scholar
Sun, Y., Hollerbach, J. and Mascaro, S., “EigenNail for Finger Force Direction Recognition,” In: ICRA (IEEE, 2007) pp. 3251–3256.Google Scholar
Yoshimoto, S., Kuroda, Y. and Oshiro, O., “Estimation of object elasticity by capturing fingernail images during haptic palpation,” IEEE Trans Haptics 11(2), 204–211 (2018).CrossRefGoogle ScholarPubMed
Comaniciu, D., Ramesh, V. and Meer, P., “Real-Time Tracking of Non-Rigid Objects Using Mean Shift,” In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition, vol. 2 (IEEE, 2000) pp. 142–149.Google Scholar
Rasmussen, C. and Williams, C., Gaussian Processes for Machine Learning (MIT Press, Cambridge, 2006).Google Scholar
Snelson, E. and Ghahramani, Z., “Sparse gaussian processes using pseudo-inputs,” In: Advances in Neural Information Processing Systems (MIT Press, Cambridge, 2006) pp. 1257–1264.Google Scholar
LeCun, Y., Bottou, L., Bengio, Y. and Haffner, P., “Gradient-based learning applied to document recognition,” In: Proc. IEEE 86(11), 2278–2324 (1998).CrossRefGoogle Scholar
Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I. and Salakhutdinov, R., “Improving neural networks by preventing co-adaptation of feature detectors,” CoRR, vol. abs/1207.0580 (2012).Google Scholar
Wang, S. and Manning, C., “Fast Dropout Training,” In: Proceedings of the 30th International Conference on Machine Learning (ICML-2013) (Dasgupta, S. and Mcallester, D., eds.), vol. 28(2). JMLR Workshop and Conference Proceedings (2013) pp. 118–126.Google Scholar
Bayer, J., Osendorfer, C., Korhammer, D., Chen, N., Urban, S. and van der Smagt, P., “On Fast Dropout and Its Applicability to Recurrent Networks,” In: Proc. ICLR (2014).Google Scholar
Luciw, M. D., Jarocka, E. and Edin, B. B., “Multi-channel EEG recordings during 3,936 grasp and lift trials with varying weight and friction,” Scientific Data 1, 1440047 (2014).CrossRefGoogle ScholarPubMed