A Survey of FPGA-Based Vision Systems for Autonomous Cars

Castells-Rufas, David; Ngo, Vinh; Borrego-Carazo, Juan; Codina, Marc; Sánchez, C.; Gil, Débora; Carrabina, Jordi

doi:10.1109/access.2022.3230282

Cited by 8 publications

(5 citation statements)

References 289 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ASICs offer higher performance and energy efficiency but the high development costs can be sustainable only for production series units. FPGA shows slightly less performance, but its flexibility makes it feasible for hardware development and testing, and applications with an expected low number of products [130]. High-generalpurpose units such as CPU and GPU can be useful in development, but recently these have also been employed on prototype CAVs.…”

Section: Data Processingmentioning

confidence: 99%

Architecture and Potential of Connected and Autonomous Vehicles

Pipicelli,

Gimelli,

Sessa

et al. 2024

Vehicles

View full text Add to dashboard Cite

The transport sector is under an intensive renovation process. Innovative concepts such as shared and intermodal mobility, mobility as a service, and connected and autonomous vehicles (CAVs) will contribute to the transition toward carbon neutrality and are foreseen as crucial parts of future mobility systems, as demonstrated by worldwide efforts in research and industry communities. The main driver of CAVs development is road safety, but other benefits, such as comfort and energy saving, are not to be neglected. CAVs analysis and development usually focus on Information and Communication Technology (ICT) research themes and less on the entire vehicle system. Many studies on specific aspects of CAVs are available in the literature, including advanced powertrain control strategies and their effects on vehicle efficiency. However, most studies neglect the additional power consumption due to the autonomous driving system. This work aims to assess uncertain CAVs’ efficiency improvements and offers an overview of their architecture. In particular, a combination of the literature survey and proper statistical methods are proposed to provide a comprehensive overview of CAVs. The CAV layout, data processing, and management to be used in energy management strategies are discussed. The data gathered are used to define statistical distribution relative to the efficiency improvement, number of sensors, computing units and their power requirements. Those distributions have been employed within a Monte Carlo method simulation to evaluate the effect on vehicle energy consumption and energy saving, using optimal driving behaviour, and considering the power consumption from additional CAV hardware. The results show that the assumption that CAV technologies will reduce energy consumption compared to the reference vehicle, should not be taken for granted. In 75% of scenarios, simulated light-duty CAVs worsen energy efficiency, while the results are more promising for heavy-duty vehicles.

show abstract

Section: Data Processingmentioning

confidence: 99%

Architecture and Potential of Connected and Autonomous Vehicles

Pipicelli,

Gimelli,

Sessa

et al. 2024

Vehicles

View full text Add to dashboard Cite

show abstract

“…Work [14] is devoted to the analysis of machine vision systems based on FPGA accelerators for unmanned vehicles. Various aspects of autonomous driving and existing FPGAbased solutions for the efficient implementation of neural network computing are considered and discussed.…”

Section: Overview Of Review Papersmentioning

confidence: 99%

Modern Trends in Improving the Technical Characteristics of Devices and Systems for Digital Image Processing

Nagornov,

Lyakhov,

Bergerman

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The technology development greatly increases the amount of digital visual information. Existing devices cannot efficiently process such huge amounts of data. The technical characteristics of digital image processing (DIP) devices and systems are being actively improved to resolve this contradiction in science and technology. The state-of-the-art methodology includes a huge number of very diverse approaches at the mathematical, software, and hardware implementation levels. We have analyzed all modern trends to improve the technical characteristics of DIP devices and systems. The main distinguishing feature of this review is that we are not limited to considering various aspects of neural network image processing, to which the vast majority of both review and research papers on the designated topic are devoted. Review papers on the subject under consideration are analyzed. Various mathematical and arithmetic-logical methods for improving the characteristics of image processing devices are described in detail. Original and significant architectural and structural solutions are analyzed. Promising neural network models of visual data processing are characterized. Hardware platforms for the design and operation of DIP systems that are efficient in terms of resource costs are considered. The most significant improvements achieved through the hardware implementation of models and methods on field-programmable gate arrays and application-specific integrated circuits are noted.INDEX TERMS High-performance computing, low-area design, low-power device, energy-efficient architecture, neural network, hardware accelerator, FPGA, ASIC.

show abstract

“…The energetics of autonomous vehicles may differ from conventional vehicles in many ways, as their design and operation present new challenges in terms of energy efficiency and energy management. The integration of various electronic systems, such as edge computing, artificial intelligence (AI), and advanced driver assistance systems (ADAS), significantly affects the power consumption and overall energy efficiency of autonomous vehicles [14,15]. In addition, deploying numerous sensors and computing resources on board autonomous vehicles significantly increases the continuous vehicle load, resulting in higher power consumption [16].…”

Section: Introductionmentioning

confidence: 99%

“…In addition, deploying numerous sensors and computing resources on board autonomous vehicles significantly increases the continuous vehicle load, resulting in higher power consumption [16]. Furthermore, using deep learning approaches in autonomous vehicles introduces high computational complexity and power consumption, which may affect the driving range of these vehicles [15,17]. In addition, integrating electronic components in autonomous vehicles has implications for fuel consumption and environmental sustainability.…”

Section: Introductionmentioning

confidence: 99%

Self-Diagnostic Opportunities for Battery Systems in Electric and Hybrid Vehicles

Szürke,

Sütheö,

Őri

et al. 2024

Machines

View full text Add to dashboard Cite

The number of battery systems is also growing significantly along with the rise in electric and hybrid car sales. Different vehicles use different types and numbers of batteries. Furthermore, the layout and operation of the control and protection electronics units may also differ. The research aims to develop an approach that can autonomously detect and localize the weakest cells. The method was validated by testing the battery systems of three different VW e-Golf electric vehicles. A wide-range discharge test was performed to examine the condition assessment and select the appropriate state of charge (SoC) for all three vehicles. On the one hand, the analysis investigated the cell voltage deviations from the average; the tests cover deviations of 0 mV, 12 mV, 60 mV, 120 mV, and 240 mV. On the other hand, the mean value calculation was used to filter out possible erroneous values. Another important aspect was examining the relationship between the state of charges (SoC) and the deviations. Therefore, the 10% step changes were tested to see which SoC level exhibited more significant voltage deviations. Based on the results, it was observed that there are differences between the cases, and the critical range is not necessarily at the lowest SoC level. Furthermore, the load rate (current) and time of its occurrence play an important role in the search for a faulty cell. An additional advantage of this approach is that the process currently being tested on the VW e-Golf can be relatively simply transferred to other types of vehicles. It can also be a very useful addition for autonomous vehicles, as it can self-test the cells in the system at low power consumption.

show abstract

A Survey of FPGA-Based Vision Systems for Autonomous Cars

Cited by 8 publications

References 289 publications

Architecture and Potential of Connected and Autonomous Vehicles

Architecture and Potential of Connected and Autonomous Vehicles

Modern Trends in Improving the Technical Characteristics of Devices and Systems for Digital Image Processing

Self-Diagnostic Opportunities for Battery Systems in Electric and Hybrid Vehicles

Contact Info

Product

Resources

About