Hardware-in-the-Loop (HiL) testing has emerged as a pivotal technique for validating and enhancing the performance of control systems across various industries, notably in automotive and embedded manufacturing sectors...
详细信息
ISBN:
(纸本)9798331300579
Hardware-in-the-Loop (HiL) testing has emerged as a pivotal technique for validating and enhancing the performance of control systems across various industries, notably in automotive and embedded manufacturing sectors. this paper provides an extensive exploration of HiL testing methodologies and their application in the Internet of things (IoT) domain. HiL testing involves simulating real-world conditions by integrating specialized simulation software and hardware components, facilitating realistic evaluation of controllers' functionality and behaviour. Different variants of HiL, such as Model-in-the-Loop (MiL), Software-in-the-Loop (SiL), Processor-in-the-Loop (PiL), and Hardware-in-the-Loop (HiL), are discussed within the broader context of XiL (Anything-in-the-Loop) models. the paper underscores the significance of HiL testing in optimizing the development process, reducing costs, and minimizing hazards. It elaborates on the utilization of HiL testing to validate intricate control algorithms, simulate fault scenarios, and assess system behaviour under diverse conditions. the integration of HiL testing with IoT applications is examined, highlighting the potential benefits in areas like smart cities, industrial IoT, healthcare, agriculture, and energy management. the study presents a novel fault injection framework within HiL testing, allowing real-time analysis of complex systems' responses to simulated faults. this framework aids in identifying vulnerabilities and evaluating system reliability, thereby enhancing safety and performance. the authors introduce the concept of sensor schema, Observations & Measurements (O&M), and Sensor Web Enablement (SWE) as key components for efficient sensor data integration, sharing, and interoperability. the paper concludes by emphasizing the indispensable role of Hardware-in-the-Loop testing in fostering innovation, safety, and efficiency in the IoT landscape. By offering a comprehensive overview, analysis, and practical insigh
the rapid expansion of the Internet of things (IoT) has necessitated real-time signal processing capabilities in embeddedsystems, but traditional cloud-based models often fall short in meeting the low-latency demands...
详细信息
Computer Vision has changed how a lot of smart systems function. Cyber Physical systems, such as Advanced Driver Assistance systems (ADAS), make use of this technology to see their surroundings and act accordingly, bu...
详细信息
Optical flow estimation is used in many embedded computer vision applications, and it is known to be computationally intensive. In the literature, many methods exist to estimate optical flow. thus, the challenge is to...
详细信息
ISBN:
(纸本)9798350346855
Optical flow estimation is used in many embedded computer vision applications, and it is known to be computationally intensive. In the literature, many methods exist to estimate optical flow. thus, the challenge is to find a method that matches the applicative constraints. In an embedded system, a trade-off between power consumption and execution time has to be made to meet both energy and framerate constraints. this work proposes methods to implement an approximate HORN & SCHUNCK optical flow estimation that meets embedded CPUs constraints. this is achieved thanks to architectural optimizations, software optimizations and algorithm tuning. For instance, on the NVIDIA Jetson Nano, and for HD video sequences, the achieved frame latency is 12 ms for 5 Watts. To the best of our knowledge, this is the fastest optical flow implementation on embedded CPUs.
Machine learning has attracted a lot of interest in the last few years as a solution to a variety of difficult challenges in many disciplines. An emerging area is that of embedded devices, where machine learning is de...
详细信息
ISBN:
(纸本)9798350332865
Machine learning has attracted a lot of interest in the last few years as a solution to a variety of difficult challenges in many disciplines. An emerging area is that of embedded devices, where machine learning is deployed to efficiently carry out tasks like data analysis, prediction, and decision-making in real-timeapplications. Challenges such as the necessity for fast and effective algorithms and the restricted resources available in embeddedsystems to cover the computational and storage demands need to be confronted to successfully integrate machine learning models into embeddedsystems. this work aims to provide an overview of the use of machine learning in embeddedsystems, including past and current solutions, and to present the challenges that need to be addressed. Future directions for the use of machine learning in embeddedsystems are also discussed.
the rapid advancement of IoT technologies has generated much interest in the development of learning-based sensing applications on embedded edge devices. However, these efforts are being challenged by the need to adap...
详细信息
ISBN:
(数字)9781665453448
ISBN:
(纸本)9781665453448
the rapid advancement of IoT technologies has generated much interest in the development of learning-based sensing applications on embedded edge devices. However, these efforts are being challenged by the need to adapt to unforeseen conditions in an open-world environment. Updating a learning model suffers from the lack of training data as well as the high computational demand beyond that available on edge devices. In this paper, we propose an open-world time-series sensing framework for making inferences from time-series sensor data and achieving incremental learning on an embedded edge device with limited resources. the proposed framework is able to achieve two essential tasks, inference and learning, without requiring access to a powerful cloud server. We discuss the design choices made to ensure satisfactory learning performance and efficient resource usage. Experimental results demonstrate the ability of the system to incrementally adapt to unforeseen conditions and to effectively run on a resource-constrained device.
the rapid advancements in machine learning, environmental sensing hardware, modern aviation, robotics, and embeddedsystems highlight the need for a forward-thinking approach to interdisciplinary education. these adva...
详细信息
ISBN:
(纸本)9798350394023;9798350394030
the rapid advancements in machine learning, environmental sensing hardware, modern aviation, robotics, and embeddedsystems highlight the need for a forward-thinking approach to interdisciplinary education. these advancements are closely linked, leading to challenges that need a comprehensive and joined-up approach. In response, this paper presents an educational platform that seamlessly blends theory with hands-on application, providing students an immersive learning experience. By interacting with a tangible representation of cyber-physical systems, students can better grasp abstract concepts, grounding their theoretical knowledge in observable outcomes. Its design emphasizes real-time interactions between embedded sensors, actuators, and onboard processors. With its modular nature, the platform supports customization to suit diverse educational objectives and spur creativity. As an open-source tool, the platform encourages a global community of learners and educators to contribute, refine, and adapt, ensuring that the tool remains relevant and up-to-date withthe ever-evolving technological landscape. It features AI-on-the-edge capable hardware, a variety of environmental scanning sensors, and an embedded microcontroller hosting an open-source flight controller. this platform's adaptability fosters collaboration among students from different academic backgrounds, leading to a synergy of expertise and innovation. Beyond individual learning, the platform cultivates a community where peer-to-peer learning flourishes. AI postgraduates can exploit its robust features to craft aerial algorithms, while electronic engineering students refine motor controls, power systems, and signal processing. Such an approach promotes cross-disciplinary teamwork, bridging classroom teachings withrealworld applications. the platform thus emerges as a hub for collaboration, idea exchange, and solution-seeking, underscoring the essence of modern interdisciplinary education.
this research examines 5G-enabled IoT devices' real-time data processing capability and constraints. A thorough literary study helps understand current technologies, application situations, and industrial difficul...
详细信息
When machine learning (ML) models are supplied with data outside their training distribution, they are more likely to make inaccurate predictions;in a cyber-physical system (CPS), this could lead to catastrophic syste...
详细信息
ISBN:
(数字)9781665453448
ISBN:
(纸本)9781665453448
When machine learning (ML) models are supplied with data outside their training distribution, they are more likely to make inaccurate predictions;in a cyber-physical system (CPS), this could lead to catastrophic system failure. To mitigate this risk, an out-of-distribution (OOD) detector can run in parallel with an ML model and flag inputs that could lead to undesirable outcomes. Although OOD detectors have been well studied in terms of accuracy, there has been less focus on deployment to resource constrained CPSs. In this study, a design methodology is proposed to tune deep OOD detectors to meet the accuracy and response time requirements of embeddedapplications. the methodology uses genetic algorithms to optimize the detector's preprocessing pipeline and selects a quantization method that balances robustness and response time. It also identifies several candidate task graphs under the Robot Operating System (ROS) for deployment of the selected design. the methodology is demonstrated on two variational autoencoder based OOD detectors from the literature on two embedded platforms. Insights into the trade-offs that occur during the design process are provided, and it is shown that this design methodology can lead to a drastic reduction in response time in relation to an unoptimized OOD detector while maintaining comparable accuracy.
Telexistence refers to various technologies that enable a high sense of embodiment and interaction capabilities with remote environments. Although numerous telexistence systems have been explored in previous works of ...
详细信息
暂无评论