With the current technological transformation in the automotive industry, autonomous vehicles are getting closer to the Society of Automative Engineers (SAE) automation level 5. This level corresponds to the full vehicle automation, where the driving system autonomously monitors and navigates the environment. With SAE-level 5, the concept of a Shared Autonomous Vehicle (SAV) will soon become a reality and mainstream. The main purpose of an SAV is to allow unrelated passengers to share an autonomous vehicle without a driver/moderator inside the shared space. However, to ensure their safety and well-being until they reach their final destination, active monitoring of all passengers is required. In this context, this article presents a microphone-based sensor system that is able to localize sound events inside an SAV. The solution is composed of a Micro-Electro-Mechanical System (MEMS) microphone array with a circular geometry connected to an embedded processing platform that resorts to Field-Programmable Gate Array (FPGA) technology to successfully process in the hardware the sound localization algorithms.

The end of Moore’s Law aligned with data privacy concerns is forcing machine learning (ML) to shift from the cloud to the deep edge. In the next-generation ML systems, the inference and part of the training process will perform at the edge, while the cloud stays responsible for major updates. This new computing paradigm, called federated learning (FL), alleviates the cloud and network infrastructure while increasing data privacy. Recent advances empowered the inference pass of quantized artificial neural networks (ANNs) on Arm Cortex-M and RISC-V microcontroller units (MCUs). Nevertheless, the training remains confined to the cloud, imposing the transaction of high volumes of private data over a network and leading to unpredictable delays when ML applications attempt to adapt to adversarial environments. To fill this gap, we make the first attempt to evaluate the feasibility of ANN training in Arm Cortex-M MCUs. From the available optimization algorithms, stochastic gradient descent (SGD) has the best trade-off between accuracy, memory footprint, and latency. However, its original form and the variants available in the literature still do not fit the stringent requirements of Arm Cortex-M MCUs. We propose L-SGD, a lightweight implementation of SGD optimized for maximum speed and minimal memory footprint in this class of MCUs. We developed a floating-point version and another that operates over quantized weights. For a fully-connected ANN trained on the MNIST dataset, L-SGD (float-32) is 4.20× faster than the SGD while requiring only 2.80% of the memory with negligible accuracy loss. Results also show that quantized training is still unfeasible to train an ANN from the scratch but is a lightweight solution to perform minor model fixes and counteract the fairness problem in typical FL systems.

Capsule networks (CapsNets) are an emerging trend in image processing. In contrast to a convolutional neural network, CapsNets are not vulnerable to object deformation, as the relative spatial information of the objects is preserved across the network. However, their complexity is mainly related to the capsule structure and the dynamic routing mechanism, which makes it almost unreasonable to deploy a CapsNet, in its original form, in a resource-constrained device powered by a small microcontroller (MCU). In an era where intelligence is rapidly shifting from the cloud to the edge, this high complexity imposes serious challenges to the adoption of CapsNets at the very edge. To tackle this issue, we present an API for the execution of quantized CapsNets in Arm Cortex-M and RISC-V MCUs. Our software kernels extend the Arm CMSIS-NN and RISC-V PULP-NN to support capsule operations with 8-bit integers as operands. Along with it, we propose a framework to perform post-training quantization of a CapsNet. Results show a reduction in memory footprint of almost 75%, with accuracy loss ranging from 0.07% to 0.18%. In terms of throughput, our Arm Cortex-M API enables the execution of primary capsule and capsule layers with medium-sized kernels in just 119.94 and 90.60 ms, respectively (STM32H755ZIT6U, Cortex-M7 @ 480 MHz). For the GAP-8 SoC (RISC-V RV32IMCXpulp @ 170 MHz), the latency drops to 7.02 and 38.03 ms, respectively.

Capsule networks (CapsNets) are an emerging trend in image processing. In contrast to a convolutional neural network, CapsNets are not vulnerable to object deformation, as the relative spatial information of the objects is preserved across the network. However, their complexity is mainly related to the capsule structure and the dynamic routing mechanism, which makes it almost unreasonable to deploy a CapsNet, in its original form, in a resource-constrained device powered by a small microcontroller (MCU). In an era where intelligence is rapidly shifting from the cloud to the edge, this high complexity imposes serious challenges to the adoption of CapsNets at the very edge. To tackle this issue, we present an API for the execution of quantized CapsNets in Arm Cortex-M and RISC-V MCUs. Our software kernels extend the Arm CMSIS-NN and RISC-V PULP-NN to support capsule operations with 8-bit integers as operands. Along with it, we propose a framework to perform post-training quantization of a CapsNet. Results show a reduction in memory footprint of almost 75%, with accuracy loss ranging from 0.07% to 0.18%. In terms of throughput, our Arm Cortex-M API enables the execution of primary capsule and capsule layers with medium-sized kernels in just 119.94 and 90.60 milliseconds (ms), respectively (STM32H755ZIT6U, Cortex-M7 @ 480 MHz). For the GAP-8 SoC (RISC-V RV32IMCXpulp @ 170 MHz), the latency drops to 7.02 and 38.03 ms, respectively.