Force Estimation and Slip Detection for Grip Control using a Biomimetic Tactile Sensor

We introduce and evaluate contact-based techniques to estimate tactile properties and detect manipulation events using a biomimetic tactile sensor. In particular, we estimate finger forces, and detect and classify slip events. In addition, we present a grip force controller that uses the estimation results to gently pick up objects of various weights and texture. The estimation techniques and the grip controller are experimentally evaluated on a robotic system consisting of Barrett arms and hands. Our results indicate that we are able to accurately estimate forces acting in all directions, detect the incipient slip, and classify slip with over 80% success rate.

[1]  Veronica J. Santos,et al.  Biomimetic Tactile Sensor Array , 2008, Adv. Robotics.

[2]  Mark R. Cutkosky,et al.  Slip interface classification through tactile signal coherence , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[3]  M. Srinivasan,et al.  Tactile detection of slip: surface microgeometry and peripheral neural codes. , 1990, Journal of neurophysiology.

[4]  Dumitru Erhan,et al.  Scalable Object Detection Using Deep Neural Networks , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Stefan Schaal,et al.  Incremental Online Learning in High Dimensions , 2005, Neural Computation.

[6]  J. Randall Flanagan,et al.  Coding and use of tactile signals from the fingertips in object manipulation tasks , 2009, Nature Reviews Neuroscience.

[7]  Claudio Melchiorri,et al.  Slip detection and control using tactile and force sensors , 2000 .

[8]  Tomonori Yamamoto,et al.  Use of tactile feedback to control exploratory movements to characterize object compliance , 2012, Front. Neurorobot..

[9]  Sachin Chitta,et al.  Human-Inspired Robotic Grasp Control With Tactile Sensing , 2011, IEEE Transactions on Robotics.

[10]  G.E. Loeb,et al.  Grip Control Using Biomimetic Tactile Sensing Systems , 2009, IEEE/ASME Transactions on Mechatronics.

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

[12]  Gerald E. Loeb,et al.  Multimodal Tactile Sensor , 2014, The Human Hand as an Inspiration for Robot Hand Development.

[13]  R. Johansson,et al.  Mechanisms for force adjustments to unpredictable frictional changes at individual digits during two-fingered manipulation. , 1998, Journal of neurophysiology.

[14]  R. Johansson,et al.  Tangential torque effects on the control of grip forces when holding objects with a precision grip. , 1997, Journal of neurophysiology.

[15]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[16]  Y. Yao,et al.  On Early Stopping in Gradient Descent Learning , 2007 .

[17]  C. Natale,et al.  Tactile sensor for human-like manipulation , 2012, 2012 4th IEEE RAS & EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob).

[18]  Pietro Falco,et al.  Integrated force/tactile sensing: The enabling technology for slipping detection and avoidance , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[19]  Martin Fodslette Meiller.  A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning , 1993 .

[20]  Monica Gori,et al.  Better manipulation with human inspired tactile sensing , 2009 .