Convolutional Neural Networks on Embedded Automotive Platforms: A Qualitative Comparison

Brilli, Gianluca; Burgio, Paolo; Bertogna, Marko

doi:10.1109/hpcs.2018.00084

Cited by 4 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, depending on the task and the inference engine, this advantage (and others like throughput) is not fulfilled. In [60], authors compare a NVIDIA Tegra X2 board with a Xilinx Ultrascale regarding throughput and energy consumption. In the case of a complex task such as detection, both platforms show similar results in both parameters.…”

Section: ) Embedding Methods and Performancementioning

confidence: 99%

See 1 more Smart Citation

Resource-Constrained Machine Learning for ADAS: A Systematic Review

Borrego-Carazo

Castells-Rufas

Biempica³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

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 to comply with the memory and real-time (RT) requirements for inference. Some models are easily adapted to resource-constrained hardware, such as Support Vector Machines, while others, like Neural Networks, need more complex processes to fit into the desired hardware. The ADAS hardware (HW platforms) are diverse, from complex MPSoC CPUs down to classical MCUs, DPSs and application-specific FPGAs and ASICs or specific GPU platforms (such as the NVIDIA families Tegra or Jetson). Therefore, there is a tradeoff between the complexity of the ML model implemented and the selected platform that impacts the performance metrics: function results, energy consumption and speed (latency and throughput). In this paper, a survey in the form of systematic review is conducted to analyze the scope of the published research works that embed ML models into resource-constrained implementations for ADAS applications and what are the achievements regarding the ML performance, energy and speed trade-off. INDEX TERMS Machine learning, embedded software, automotive engineering, GPU, FPGA, ADAS. I. INTRODUCTION Safety is increasingly important for drivers and other users of the driving environment such as pedestrians, cyclists, bikers, scooters, etc. Only in 2016, road accidents in the European Union summed up to 25.600 fatalities and 1.4 million people injured [1]. Many measures are being taken by public institutions (improving road quality, enhancing driver consciousness and driving regulations, etc.) to improve these numbers. However, the cause of most of these accidents resides in human errors or distractions. For this reason, automotive firms are pushing up research on improving safety. The cornerstone of these advances are Advanced Driver Assistance Systems (ADAS). ADAS systems consist in several sensors, processing and actuators components that help drivers to avoid accidents and The associate editor coordinating the review of this manuscript and approving it for publication was Ye Duan.

show abstract

Section: ) Embedding Methods and Performancementioning

confidence: 99%

“…For Adaboost, they arrange the learning steps in memory blocks. As noted in the case of a GP-GPU platform [60], memory access can become burden for throughput and energy efficiency.…”

Section: ) Embedding Methods and Performancementioning

confidence: 99%

Resource-Constrained Machine Learning for ADAS: A Systematic Review

Borrego-Carazo

Castells-Rufas

Biempica³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Such platforms are widely adopted in several application domains, e.g., automotive, autonomous drones, computer vision, etc (AMD Xilinx, 2022b). Nonetheless, FPGA-based architectures are less widely adopted than General-Purpose computing on Graphics Processing Units (GPGPUs), due to their complexity, but have shown to provide a comparable or higher Performance/Watt trade-off and an increased predictability (Brilli et al, 2018;Liu et al, 2019). The FPGA of the ZCU102 is occupied by a further described TSN connectivity module, while the ZCU106's FPGA embeds an acceleration unit for the detection.…”

Section: Ecusmentioning

confidence: 99%

Time-sensitive autonomous architectures

Ferraro,

Palazzi,

Gavioli

et al. 2023

Real-Time Syst

Self Cite

View full text Add to dashboard Cite

show abstract

“…Deploying AI Inference Engines inside autonomous vehicles requires overcoming limitations of platform dependencies and limited computation resources. Therefore, new transportation vehicles are equipped with embedded ECU devices specialized for AI and exploited to ensure adequate performance and energy efficiency [ 36 ].…”

Section: Background and Related Workmentioning

confidence: 99%

Cloud2Edge Elastic AI Framework for Prototyping and Deployment of AI Inference Engines in Autonomous Vehicles

Grigorescu

Cocias

Trasnea

et al. 2020

Sensors

View full text Add to dashboard Cite

Self-driving cars and autonomous vehicles are revolutionizing the automotive sector, shaping the future of mobility altogether. Although the integration of novel technologies such as Artificial Intelligence (AI) and Cloud/Edge computing provides golden opportunities to improve autonomous driving applications, there is the need to modernize accordingly the whole prototyping and deployment cycle of AI components. This paper proposes a novel framework for developing so-called AI Inference Engines for autonomous driving applications based on deep learning modules, where training tasks are deployed elastically over both Cloud and Edge resources, with the purpose of reducing the required network bandwidth, as well as mitigating privacy issues. Based on our proposed data driven V-Model, we introduce a simple yet elegant solution for the AI components development cycle, where prototyping takes place in the cloud according to the Software-in-the-Loop (SiL) paradigm, while deployment and evaluation on the target ECUs (Electronic Control Units) is performed as Hardware-in-the-Loop (HiL) testing. The effectiveness of the proposed framework is demonstrated using two real-world use-cases of AI inference engines for autonomous vehicles, that is environment perception and most probable path prediction.

show abstract

Convolutional Neural Networks on Embedded Automotive Platforms: A Qualitative Comparison

Cited by 4 publications

References 7 publications

Resource-Constrained Machine Learning for ADAS: A Systematic Review

Resource-Constrained Machine Learning for ADAS: A Systematic Review

Time-sensitive autonomous architectures

Cloud2Edge Elastic AI Framework for Prototyping and Deployment of AI Inference Engines in Autonomous Vehicles

Contact Info

Product

Resources

About