Neuromorphic tactile sensor array based on fiber Bragg gratings to encode object qualities

Emulating the sense of touch is fundamental to endow robotic systems with perception abilities. This work presents an unprecedented mechanoreceptor-like neuromorphic tactile sensor implemented with fiber optic sensing technologies. A robotic gripper was sensorized using soft and flexible tactile sensors based on Fiber Bragg Grating (FBG) transducers and a neuro-bio-inspired model to extract tactile features. The FBGs connected to the neuron model emulated biological mechanoreceptors in encoding tactile information by means of spikes. This conversion of inflowing tactile information into event-based spikes has an advantage of reduced bandwidth requirements to allow communication between sensing and computational subsystems of robots. The outputs of the sensor were converted into spiking on-off events by means of an architecture implemented in a Field Programmable Gate Array (FPGA) and applied to robotic manipulation tasks to evaluate the effectiveness of such information encoding strategy. Different tasks were performed with the objective to grant fine manipulation abilities using the features extracted from the grasped objects (i.e., size and hardness). This is envisioned to be a futuristic sensor technology combining two promising technologies: optical and neuromorphic sensing.

[1]  Alberto Mazzoni,et al.  Intracellular Dynamics in Cuneate Nucleus Neurons Support Self-Stabilizing Learning of Generalizable Tactile Representations , 2018, Front. Cell. Neurosci..

[2]  Alberto Mazzoni,et al.  Neuromorphic Artificial Touch for Categorization of Naturalistic Textures , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[3]  Isao Shimoyama,et al.  Stretchable tri-axis force sensor using conductive liquid , 2014 .

[4]  Paul Ciprian Patic,et al.  THE BARRETTHAND GRASPER - PROGRAMMABLY FLEXIBLE PART HANDLING AND ASSEMBLY , 2006 .

[5]  Ingvars Birznieks,et al.  Effects of changing skin mechanics on the differential sensitivity to surface compliance by tactile afferents in the human finger pad. , 2015, Journal of neurophysiology.

[6]  Ian A. Gravagne,et al.  Goldfinger: a non-anthropomorphic, dextrous robot hand , 1999, Proceedings 1999 IEEE International Conference on Robotics and Automation (Cat. No.99CH36288C).

[7]  Alberto Mazzoni,et al.  Convergence of regular spiking and intrinsically bursting Izhikevich neuron models as a function of discretization time with Euler method , 2019, Neurocomputing.

[8]  J. Heo,et al.  Tactile sensor arrays using fiber Bragg grating sensors , 2006 .

[9]  Gert Cauwenberghs,et al.  Neuromorphic Silicon Neuron Circuits , 2011, Front. Neurosci.

[10]  O. Wolfbeis.  Fiber-optic chemical sensors and biosensors. , 2002, Analytical chemistry.

[11]  Bernard Brezzo,et al.  TrueNorth: Design and Tool Flow of a 65 mW 1 Million Neuron Programmable Neurosynaptic Chip , 2015, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[12]  D. Kleinfeld,et al.  'Where' and 'what' in the whisker sensorimotor system , 2008, Nature Reviews Neuroscience.

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

[14]  Alberto Mazzoni,et al.  Neuromorphic Artificial Sense of Touch: Bridging Robotics and Neuroscience , 2015, ISRR.

[15]  Eugene M. Izhikevich,et al.  Simple model of spiking neurons , 2003, IEEE Trans. Neural Networks.

[16]  Joel W. Burdick,et al.  Team RoboSimian: Semi‐autonomous Mobile Manipulation at the 2015 DARPA Robotics Challenge Finals , 2017, J. Field Robotics.

[17]  Craig T. Jin,et al.  An Active 2-D Silicon Cochlea , 2008, IEEE Transactions on Biomedical Circuits and Systems.

[18]  A. Loi,et al.  Piezoelectric polymer transducer arrays for flexible tactile sensors , 2012, 2012 IEEE Sensors.

[19]  Arianna Menciassi,et al.  Haptic Glove and Platform with Gestural Control For Neuromorphic Tactile Sensory Feedback In Medical Telepresence † , 2018, Sensors.

[20]  Hong Liu,et al.  DLR-Hand II: next generation of a dextrous robot hand , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[21]  Andrew S. Cassidy,et al.  A million spiking-neuron integrated circuit with a scalable communication network and interface , 2014, Science.

[22]  P. Rossini,et al.  Intraneural stimulation elicits discrimination of textural features by artificial fingertip in intact and amputee humans , 2016, eLife.

[23]  Kaspar Althoefer,et al.  Tactile sensing for dexterous in-hand manipulation in robotics-A review , 2011 .

[24]  C. Brodley,et al.  Decision tree classification of land cover from remotely sensed data , 1997 .

[25]  S. Schultz.  Principles of Neural Science, 4th ed. , 2001 .

[26]  Tobi Delbrück,et al.  A 128$\times$ 128 120 dB 15 $\mu$s Latency Asynchronous Temporal Contrast Vision Sensor , 2008, IEEE Journal of Solid-State Circuits.

[27]  Calogero M. Oddo,et al.  Tactile Sensing and Control of Robotic Manipulator Integrating Fiber Bragg Grating Strain-Sensor , 2019, Front. Neurorobot..

[28]  Paolo Dario,et al.  Tactile Decoding of Edge Orientation With Artificial Cuneate Neurons in Dynamic Conditions , 2019, Front. Neurorobot..

[29]  Stefan Begej,et al.  Planar and finger-shaped optical tactile sensors for robotic applications , 1988, IEEE J. Robotics Autom..

[30]  Nicola Vitiello,et al.  Feedforward Neural Network for Force Coding of an MRI-Compatible Tactile Sensor Array Based on Fiber Bragg Grating , 2015, J. Sensors.

[31]  Emiliano Schena,et al.  Medical Smart Textiles Based on Fiber Optic Technology: An Overview , 2015, Journal of functional biomaterials.

[32]  Xiaodong Chen,et al.  An Artificial Sensory Neuron with Tactile Perceptual Learning , 2018, Advanced materials.