Abstract:The advent of machine learning (ML) methods for the industry has opened new possibilities in the automotive domain, especially for Advanced Driver Assistance Systems (ADAS). These methods mainly focus on specific problems ranging from traffic sign and light recognition to pedestrian detection. In most cases, the computational resources and power budget found in ADAS systems are constrained while most machine learning methods are computationally intensive. The usual solution consists in adapting the ML models t… Show more
“…All steps bring computational complexities along and require appropriate hardware capabilities. The systems may not meet high-level computational needs and constraint the solutions [57]- [60]. Therefore, the detection of system bottlenecks is critical for the selection of the proper machine learning algorithm.…”
Section: Be Aware Of the System Bottlenecksmentioning
Communications are realized as a result of successive decisions at the physical layer, from modulation selection to multi-antenna strategy, and each decision affects the performance of the communication systems. Future communication systems must include extensive capabilities as they will encompass a wide variety of devices and applications. Conventional physical layer decision mechanisms may not meet these requirements, as they are often based on impractical and oversimplifying assumptions that result in a trade-off between complexity and efficiency. By leveraging past experiences, learning-driven designs are promising solutions to present a resilient decision mechanism and enable rapid response even under exceptional circumstances. The corresponding design solutions should evolve following the lines of learning-driven paradigms that offer more autonomy and robustness. This evolution must take place by considering the facts of real-world systems and without restraining assumptions. In this paper, the common assumptions in the physical layer are presented to highlight their discrepancies with practical systems. As a solution, learning algorithms are examined by considering the implementation steps and challenges. Furthermore, these issues are discussed through a real-time case study using software-defined radio nodes to demonstrate the potential performance improvement. A cyber-physical framework is presented to incorporate future remedies.
“…All steps bring computational complexities along and require appropriate hardware capabilities. The systems may not meet high-level computational needs and constraint the solutions [57]- [60]. Therefore, the detection of system bottlenecks is critical for the selection of the proper machine learning algorithm.…”
Section: Be Aware Of the System Bottlenecksmentioning
Communications are realized as a result of successive decisions at the physical layer, from modulation selection to multi-antenna strategy, and each decision affects the performance of the communication systems. Future communication systems must include extensive capabilities as they will encompass a wide variety of devices and applications. Conventional physical layer decision mechanisms may not meet these requirements, as they are often based on impractical and oversimplifying assumptions that result in a trade-off between complexity and efficiency. By leveraging past experiences, learning-driven designs are promising solutions to present a resilient decision mechanism and enable rapid response even under exceptional circumstances. The corresponding design solutions should evolve following the lines of learning-driven paradigms that offer more autonomy and robustness. This evolution must take place by considering the facts of real-world systems and without restraining assumptions. In this paper, the common assumptions in the physical layer are presented to highlight their discrepancies with practical systems. As a solution, learning algorithms are examined by considering the implementation steps and challenges. Furthermore, these issues are discussed through a real-time case study using software-defined radio nodes to demonstrate the potential performance improvement. A cyber-physical framework is presented to incorporate future remedies.
“…Gargoum et al divide possible features for pattern recognition in LiDAR data into on-road information, roadside information, and in conducting assessment of highway [64]. The property inference involved in ADAS can be categorized into 1) vehicle and pedestrian detection, 2) driver's state, behavior and identification, 3) traffic sign recognition, and 4) road detection and scene understanding [65]. A machine vision based traffic sign detection methods are reviewed in [66].…”
With the rise of advanced driver assistance systems (ADAS), range sensors and their data processing methods are becoming more and more important. Light detection and ranging (LiDAR) sensors are attracting attention due to their unique advantages in terms of radial distance resolution and detection range. However, the study of LiDAR data processing is usually divorced from the LiDAR sensor measurement process itself. This leads to critical measurement information being overlooked. This paper seeks a breakthrough to improve the performance of singlephoton-avalanche-diode-based direct time-of-flight LiDAR systems by reviewing the data processing stages and corresponding processing approaches for LiDAR measurements, starting from photon incidence and ending with high-level feature recognition. Firstly, we propose a LiDAR system model based on data generation and transfer. The data forms in such a LiDAR system are mainly classified into timestamps, time-correlated histograms, point cloud data, and high-level properties. Subsequently, data processing methods applied to each of these data forms are analyzed. A number of hardware solutions closely related to data transmission and control are also included in the discussion. The principles, limitations, and challenges of these methods are discussed in detail and the criteria for evaluation of time-correlated histograms in ADAS are proposed. Finally, the research gaps in data processing are summarized, and future directions for research development are presented.
“…In autonomous driving, Advanced Driver Assistance Systems (ADAS) rely on embedded systems with limited resources. ADAS is responsible of executing various machine learning tasks, including object detection, meaning that efficient implementations that take into account those limitations are critical [15]. To this end, singlestage detectors have been particularly studied for autonomous driving by either proposing specialized, compact deep models (e.g., [16], SqueezeDet [11], SA-YOLOv3 [17], Mini-YOLOv3 [18]) or applying MCA techniques [19] to existing, pre-trained models (e.g., [20] [21], [22], Efficient YOLO [23], ICME 2020 Competition [24]).…”
Section: Relevant Bibliography and Contributionmentioning
Automotive Cyber-Physical Systems (ACPS) have attracted a significant amount of interest in the past few decades, while one of the most critical operations in these systems is the perception of the environment. Deep learning and, especially, the use of Deep Neural Networks (DNNs) provides impressive results in analyzing and understanding complex and dynamic scenes from visual data. The prediction horizons for those perception systems are very short and inference must often be performed in real time, stressing the need of transforming the original large pre-trained networks into new smaller models, by utilizing Model Compression and Acceleration (MCA) techniques. Our goal in this work is to investigate best practices for appropriately applying novel weight sharing techniques, optimizing the available variables and the training procedures towards the significant acceleration of widely adopted DNNs. Extensive evaluation studies carried out using various state-of-the-art DNN models in object detection and tracking experiments, provide details about the type of errors that manifest after the application of weight sharing techniques, resulting in significant acceleration gains with negligible accuracy losses.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.