Timing of Autonomous Driving Software: Problem Analysis and Prospects for Future Solutions

Alcon, Miguel; Tabani, Hamid; Kosmidis, Leonidas; Mezzetti, Enrico; Abella, Jaume; Cazorla, Francisco J.

doi:10.1109/rtas48715.2020.000-1

Cited by 40 publications

(20 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…12 presents the measurement results of the detector subsystem delay along with our predictions obtained using Eq. (15). The figures show that our predictions well estimate the detector subsystem delays with varying neural network resolutions.…”

Section: B Evaluation Of Our Analysis Methodsmentioning

confidence: 73%

“…YOLO is one of the most famous single-stage object detectors based on the convolutional neural network (CNN) architecture. Because of its high speed and accuracy, it is widely used for implementing real-time object detection systems for autonomous driving [5], [14], [15]. YOLO has evolved from its original version [16] to more recent versions (v2, v3, and v4) [7]- [9] in which its object detection accuracy has been continually increased.…”

Section: Background and Problem Descriptionmentioning

confidence: 99%

See 1 more Smart Citation

R-TOD: Real-Time Object Detector with Minimized End-to-End Delay for Autonomous Driving

Jang

Jeong

Kang

et al. 2020

Preprint

View full text Add to dashboard Cite

For realizing safe autonomous driving, the endto-end delays of real-time object detection systems should be thoroughly analyzed and minimized. However, despite recent development of neural networks with minimized inference delays, surprisingly little attention has been paid to their end-to-end delays from an object's appearance until its detection is reported. With this motivation, this paper aims to provide more comprehensive understanding of the end-to-end delay, through which precise best-and worst-case delay predictions are formulated, and three optimization methods are implemented: (i) on-demand capture, (ii) zero-slack pipeline, and (iii) contention-free pipeline. Our experimental results show a 76% reduction in the end-toend delay of Darknet YOLO (You Only Look Once) v3 (from 1070 ms to 261 ms), thereby demonstrating the great potential of exploiting the end-to-end delay analysis for autonomous driving. Furthermore, as we only modify the system architecture and do not change the neural network architecture itself, our approach incurs no penalty on the detection accuracy.

show abstract

Section: B Evaluation Of Our Analysis Methodsmentioning

confidence: 73%

Section: Background and Problem Descriptionmentioning

confidence: 99%

R-TOD: Real-Time Object Detector with Minimized End-to-End Delay for Autonomous Driving

Jang

Jeong

Kang

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…In this study, we use the Darknet framework along with the YOLO object detector for both the training and the inference. Our choice is based on the fact that they are commonly used in recent autonomous driving systems [23][24][25].…”

Section: Related Workmentioning

confidence: 99%

CarFree: Hassle-Free Object Detection Dataset Generation Using Carla Autonomous Driving Simulator

2021

View full text Add to dashboard Cite

For safe autonomous driving, deep neural network (DNN)-based perception systems play essential roles, where a vast amount of driving images should be manually collected and labeled with ground truth (GT) for training and validation purposes. After observing the manual GT generation’s high cost and unavoidable human errors, this study presents an open-source automatic GT generation tool, CarFree, based on the Carla autonomous driving simulator. By that, we aim to democratize the daunting task of (in particular) object detection dataset generation, which was only possible by big companies or institutes due to its high cost. CarFree comprises (i) a data extraction client that automatically collects relevant information from the Carla simulator’s server and (ii) a post-processing software that produces precise 2D bounding boxes of vehicles and pedestrians on the gathered driving images. Our evaluation results show that CarFree can generate a considerable amount of realistic driving images along with their GTs in a reasonable time. Moreover, using the synthesized training images with artificially made unusual weather and lighting conditions, which are difficult to obtain in real-world driving scenarios, CarFree significantly improves the object detection accuracy in the real world, particularly in the case of harsh environments. With CarFree, we expect its users to generate a variety of object detection datasets in hassle-free ways.

show abstract

“…Timing analysis of AD systems proved to be challenging and complex. Authors in [25] show the main challenges and limitations in finding a satisfactory software timing analysis solution for Apollo. All the analysis in this work is based on the entire Apollo system with all modules running concurrently.…”

Section: Related Workmentioning

confidence: 99%

Enabling Unit Testing of Already-Integrated AI Software Systems: The Case of Apollo for Autonomous Driving

Alcon

Tabani

Abella

et al. 2021

2021 24th Euromicro Conference on Digital System Design (DSD)

Self Cite

View full text Add to dashboard Cite

The advanced AI-based software used for autonomous driving comprises multiple highly-coupled modules that are data and control dependent. Deploying those alreadyintegrated software frameworks makes unit testing, a fundamental step in the validation process of critical software, very challenging in safety-critical systems. To tackle this issue, in this paper, we show the steps we followed to develop standalone versions of the modules in an industry-level autonomous driving framework (Apollo) by applying several modifications to its architectural design. We show how the standalone modules have the same functional behavior as their integrated counterpart modules. We exemplify the benefits of standalone modules by performing incremental analysis of the software timing requirements of each module running on a heterogeneous System on Chip (SoC). This is a mandatory step to consolidate and integrate software modules guaranteeing timing constraints (e.g. related to freedom from interference) while maximizing SoC utilization.Index Terms-Unit testing, autonomous driving, Apollo1 The residual risk is the amount of risk remaining after specific risk mitigation measures are put in place.

show abstract

Timing of Autonomous Driving Software: Problem Analysis and Prospects for Future Solutions

Cited by 40 publications

References 41 publications

R-TOD: Real-Time Object Detector with Minimized End-to-End Delay for Autonomous Driving

R-TOD: Real-Time Object Detector with Minimized End-to-End Delay for Autonomous Driving

CarFree: Hassle-Free Object Detection Dataset Generation Using Carla Autonomous Driving Simulator

Enabling Unit Testing of Already-Integrated AI Software Systems: The Case of Apollo for Autonomous Driving

Contact Info

Product

Resources

About