Recently we introduced a new model-based fault injection method implemented as a highly-customizable Simulink block called FIBlock. It supports the injection of typical faults of essential heterogeneous components of Cyber-Physical Systems, such as sensors, computing hardware, and network. The FIBlock allows to tune a fault type and configure multiple parameters to tune error magnitude, fault activation time, and fault exposure duration.We demonstrated its performance to generate highly adjustable and various CPS fault types on a Simulink case study representing a lower-limb EXO-LEGS exoskeleton, an assistive device for the elderly in everyday life. In our previous paper we discovered the spatial and temporal thresholds for different fault types. Upon exceeding said thresholds, the Dynamic Movement Primitives-based control system could no longer adequately compensate these errors.In this paper we proposed a Deep Learning-based approach for the system failure prevention. We employed the Long Short-Term Memory (LSTM) network for error detection and mitigation. Error detection was performed using data prediction. The LSTM models were mitigating the detected errors with computed predictions only when they were subject to the imminent failure (i.e., exceeded the aforementioned thresholds). To compare our approach with previous findings, we trained two LSTM models on angular position and on angular velocity signals. For evaluation, we performed fault injection experiments with varying fault effect parameters. The ’Stuck-at current value’ fault was injected into angular position sensor, and the ’Stuck-at 0’ fault was injected into angular velocity sensor. Presented Deep Learning-based approach prevented system failure even when the injected faults were substantially exceeding thresholds.In addition, a reasoning for data access point choice has been evaluated. We compared two options: (i) the input data for LSTM is provided from the controller output and (ii) from the sensor output. In the paper the pros and cons for both options are presented.We deployed the trained LSTM models on an Edge Tensor Processing Unit. For that, the models have been quantized, i.e. all the 32-bit floating-point numbers (such as weights and activation outputs) were converted to the nearest 8-bit fixed-point numbers and converted to the TensorFlow Lite models. The Coral USB Accelerator was coupled with a Raspberry Pi 4B for signal processing. The result proves the feasibility of the proposed method. Because the LSTM models were converted to the 8-bit integer TensorFlow Lite models, it allowed real-time error mitigation. Furthermore, the light weight of the system and a minimal power consumption allows its integration into wearable robotic systems.

Deep Learning-Based Error Mitigation for Assistive Exoskeleton With Computational-Resource-Limited Platform and Edge Tensor Processing Unit

Paper Proceedings: https://asmedigitalcollection.asme.org/IMECE/IMECE2021/volume/85543

ASME 2021 International Mechanical Engineering Congress and Exposition (IMECE2021)

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.