The integration of fuel cell technology with artificial intelligence and machine learning in electric vehicles (EVs) has the potential to enhance efficiency, performance, and reliability. Fuel cells, a clean alternative to traditional engines, produce electricity through electrochemical reactions between hydrogen and oxygen, with water vapor as the only byproduct. AI-driven algorithms analyze vast data from sensors and onboard systems, while ML algorithms enable early detection of potential system failures. AI-based driver assist systems can optimize driving behaviors using fuel cell data. However, integrating fuel cell technology with AI and ML faces challenges like data management, algorithm development, and interoperability with existing vehicle systems. Interdisciplinary collaboration between automotive engineers, data scientists, and AI specialists is needed to develop robust, scalable solutions.
Estimation of depth from a single image is an important scene understanding task in computer vision. With the advent of Deep Learning and Convolutional Neural Networks, staggeringly high accuracies have been achieved in this task. With advancements in model optimization, it has been possible to deploy these models on edge devices, allowing for efficient depth estimation in safety-critical applications in robots, rovers, drones and even self-driving vehicles. However, these models are susceptible to attacks from malicious adversaries, which aim to distort the output of the model for a seemingly clean image by adding minute perturbations. In the real-world scenario, the most plausible attack is the adversarial patch, which can be printed and used as a physical adversarial attack against Deep Learning models. In the case of Monocular Depth Estimation, we show that small adversarial patches, which range from 0.7% to 5% of the image size, greatly worsen model performance. It is thus essential that these models are made robust using defense mechanisms, to defend against malicious inputs while also not reducing performance on clean images. Moreover, it is essential that the defense mechanism be computationally efficient, for real-time inference on edge devices. In this work, we propose the first defense mechanism against adversarial patches for a regression network, in the context of Monocular Depth Estimation on an edge device. The defense mechanism adds very little overhead time of 38 milliseconds on a Raspberry Pi 3 Model B, maintaining performance on clean images while also achieving near clean image levels of performance on adversarial inputs.