An Energy Efficient System for Touch Modality Classification in Electronic Skin Applications

Electronic-skin aiming to mimic human skin is becoming a reality and systems able to process data close to the sensors are required to reduce latency and power consumption. This paper presents the design and implementation of an energy efficient smart system for tactile sensing based on a RISC-V parallel ultra-low power platform (PULP). The PULP processor, called Mr. Wolf, performs the on-board classification of different touch modalities. This demonstrates the promising use of on-board classification for emerging robot and prosthetic applications. Experimental results demonstrate the effectiveness of the platform on improving the energy efficiency of the online classification. In our experiments, Mr. Wolf runs 3.6 times faster than an ARM Cortex M4F (STM32F40), consuming only 28 mW. The proposed platform achieves 15× better energy efficiency, than the classification done on the STM32F40, consuming only 81mJ per classification.

[1]  Hussein Chible,et al.  Inexact Arithmetic Circuits for Energy Efficient IoT Sensors Data Processing , 2018, 2018 IEEE International Symposium on Circuits and Systems (ISCAS).

[2]  Paolo Gastaldo,et al.  A Tensor-Based Pattern-Recognition Framework for the Interpretation of Touch Modality in Artificial Skin Systems , 2014, IEEE Sensors Journal.

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

[4]  Maurizio Valle,et al.  A tensor-based approach to touch modality classification by using machine learning , 2015, Robotics Auton. Syst..

[5]  Viktor K. Prasanna,et al.  Accelerating Decision Tree Based Traffic Classification on FPGA and Multicore Platforms , 2017, IEEE Transactions on Parallel and Distributed Systems.

[6]  Michele Magno,et al.  DeepEmote: Towards multi-layer neural networks in a low power wearable multi-sensors bracelet , 2017, 2017 7th IEEE International Workshop on Advances in Sensors and Interfaces (IWASI).

[7]  Luca Benini,et al.  Mr. Wolf: A 1 GFLOP/s Energy-Proportional Parallel Ultra Low Power SoC for IOT Edge Processing , 2018, ESSCIRC 2018 - IEEE 44th European Solid State Circuits Conference (ESSCIRC).

[8]  Paul Young,et al.  Hardware/Software Implementation of Fuzzy-Neural-Network Self-Learning Control Methods for Brushless DC Motor Drives , 2016, IEEE Transactions on Industry Applications.

[9]  Michele Magno,et al.  Accelerated Visual Context Classification on a Low-Power Smartwatch , 2017, IEEE Transactions on Human-Machine Systems.

[10]  Maurizio Valle,et al.  Singular value decomposition FPGA implementation for tactile data processing , 2015, 2015 IEEE 13th International New Circuits and Systems Conference (NEWCAS).

[11]  Maurizio Valle,et al.  Real-Time Embedded Machine Learning for Tensorial Tactile Data Processing , 2018, IEEE Transactions on Circuits and Systems I: Regular Papers.

[12]  Maurizio Valle,et al.  Distributed Sensing and Stimulation Systems for Sense of Touch Restoration in Prosthetics , 2017, 2017 New Generation of CAS (NGCAS).

[13]  Michele Magno,et al.  Energy Efficient System for Tactile Data Decoding Using an Ultra-Low Power Parallel Platform , 2017, 2017 New Generation of CAS (NGCAS).

[14]  Maurizio Valle,et al.  Approximate Computing Methods for Embedded Machine Learning , 2018, 2018 25th IEEE International Conference on Electronics, Circuits and Systems (ICECS).

[15]  Luigi Pinna,et al.  Interface Electronics for Tactile Sensors Based on Piezoelectric Polymers , 2017, IEEE Sensors Journal.

[16]  Luca Benini,et al.  A Self-Aware Architecture for PVT Compensation and Power Nap in Near Threshold Processors , 2017, IEEE Design & Test.

[17]  Yang Li,et al.  An energy-efficient heterogeneous dual-core processor for Internet of Things , 2015, 2015 IEEE International Symposium on Circuits and Systems (ISCAS).

[18]  Maurizio Valle,et al.  Low Power Approximate Multipliers for Energy Efficient Data Processing , 2018, J. Low Power Electron..

[19]  Sanguthevar Rajasekaran,et al.  On Speeding-Up Parallel Jacobi Iterations for SVDs , 2016, 2016 IEEE 18th International Conference on High Performance Computing and Communications; IEEE 14th International Conference on Smart City; IEEE 2nd International Conference on Data Science and Systems (HPCC/SmartCity/DSS).