Tactile Convolutional Networks for Online Slip and Rotation Detection

We present a deep convolutional neural network which is capable to distinguish between different contact states in robotic manipulation tasks. By integrating spatial and temporal tactile sensor data from a piezo-resistive sensor array through deep learning techniques, the network is not only able to classify the contact state into stable versus slipping, but also to distinguish between rotational and translation slippage. We evaluated different network layouts and reached a final classification rate of more than 97 %. Using consumer class GPUs, slippage and rotation events can be detected within 10 ms, which is still feasible for adaptive grasp control.

[1]  Gaurav S. Sukhatme,et al.  Force estimation and slip detection/classification for grip control using a biomimetic tactile sensor , 2015, 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids).

[2]  Danica Kragic,et al.  Predicting slippage and learning manipulation affordances through Gaussian Process regression , 2013, 2013 13th IEEE-RAS International Conference on Humanoid Robots (Humanoids).

[3]  Bhuvana Ramabhadran,et al.  Efficient GPU implementation of convolutional neural networks for speech recognition , 2015, INTERSPEECH.

[4]  Jan Peters,et al.  Stabilizing novel objects by learning to predict tactile slip , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[5]  Tara N. Sainath,et al.  Deep convolutional neural networks for LVCSR , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[6]  M. Picheny,et al.  Comparison of Parametric Representation for Monosyllabic Word Recognition in Continuously Spoken Sentences , 2017 .

[7]  Carsten Schürmann,et al.  Modular high speed tactile sensor system with video interface , 2009, Humanoids 2009.

[8]  R. Johansson,et al.  Signals in tactile afferents from the fingers eliciting adaptive motor responses during precision grip , 2004, Experimental Brain Research.

[9]  Chia-Hsien Lin,et al.  Signal processing and fabrication of a biomimetic tactile sensor array with thermal, force and microvibration modalities , 2009, 2009 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[10]  Aiguo Ming,et al.  Highly sensitive sensor for detection of initial slip and its application in a multi-fingered robot hand , 2011, 2011 IEEE International Conference on Robotics and Automation.

[11]  Maurizio Valle,et al.  Tactile Sensing Technologies , 2013 .

[12]  Edward H. Adelson,et al.  Measurement of shear and slip with a GelSight tactile sensor , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[13]  Gerald Penn,et al.  Convolutional Neural Networks for Speech Recognition , 2014, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[14]  Helge J. Ritter,et al.  Using a Piezo-Resistive Tactile Sensor for Detection of Incipient Slippage , 2010, ISR/ROBOTIK.

[15]  Sebastian Stober,et al.  Using Convolutional Neural Networks to Recognize Rhythm Stimuli from Electroencephalography Recordings , 2014, NIPS.

[16]  Stan Davis,et al.  Comparison of Parametric Representations for Monosyllabic Word Recognition in Continuously Spoken Se , 1980 .

[17]  Helge J. Ritter,et al.  A highly sensitive 3D-shaped tactile sensor , 2013, 2013 IEEE/ASME International Conference on Advanced Intelligent Mechatronics.