Assessing the Adherence of an Industrial Autonomous Driving Framework to ISO 26262 Software Guidelines

Tabani, Hamid; Kosmidis, Leonidas; Abella, Jaume; Cazorla, Francisco J.; Bernat, Guillem

doi:10.1145/3316781.3317779

Cited by 20 publications

(23 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The input size of the first layer has been extended to hold the 64 × 64 × 3 color images of the GTSRB datasets. We have also started an activity to assess the performance of Posits using the Yolo (You Only Look Once) approach [60,61] and on Apollo [62] (http://apollo.auto/) heterogeneous framework and the results achieved confirm [33,34]) on famous datasets like CityScapes, see Figure 7. The results we are obtaining are in line with those obtained on, MNIST and fashion-MNIST and GTRS benchmark datasets.…”

Section: A Mnist Fashion-mnist and Cifar-10mentioning

confidence: 99%

Novel Arithmetics in Deep Neural Networks Signal Processing for Autonomous Driving: Challenges and Opportunities

Cococcioni

Rossi

Ruffaldi

et al. 2021

IEEE Signal Process. Mag.

View full text Add to dashboard Cite

This paper focuses on trends, opportunities and challenges of novel arithmetics for DNN signal processing, with particular reference to assisted and autonomous driving applications. Due to strict constrains in terms of latency, dependability and security of autonomous driving, machine perception (i.e. detection or decisions tasks) based on DNN can not be implemented relying on a remote cloud access. These tasks must be performed in real-time on embedded systems on-board the vehicle, particularly for the inference phase (considering the use of DNNs pre-trained during an off-line step). When developing a DNN computing platform, the choice of the computing arithmetics matters. Moreover, functional safe applications like autonomous driving pose severe constraints on the effect that signal processing accuracy has on final rate of wrong detection/decisions. Hence, after reviewing the different choices and trade-off concerning arithmetics, both in academia and industry, we highlight the issues in implementing DNN accelerators to achieve accurate and low-complex processing of automotive sensor signals (the latter coming from diverse sources like cameras, radars, lidars, ultrasonics). The focus is on both on general-purpose operations massively used in DNN like multiply, accumulation, compare, or on specific functions like for example sigmoid or hyperbolic tangent, used for neuron activation.

show abstract

Section: A Mnist Fashion-mnist and Cifar-10mentioning

confidence: 99%

Novel Arithmetics in Deep Neural Networks Signal Processing for Autonomous Driving: Challenges and Opportunities

Cococcioni

Rossi

Ruffaldi

et al. 2021

IEEE Signal Process. Mag.

View full text Add to dashboard Cite

show abstract

“…In order to analyze the impact of input data on timing variability, we focus on a controlled scenario in which we can reason on the variability caused by input data (both random and deterministic) and the platform related variability. Note that Apollo's modules have more than 130,000 lines of code, and 6,200 functions with intricate dependences and high cyclomatic complexity [55]. Furthermore, these functions are event-triggered by events arriving from the sensors at different frequencies.…”

Section: A Reasoning On Apollo's Variabilitymentioning

confidence: 99%

“…The effectiveness and scalability of traditional Verification and Validation (V&V) approaches are threatened by the complexity and unboundedness of the input and result spaces of functionalities such as perception and tracking [55,6]. The untenable number of potential inputs from the operational environment, and the non-deterministic nature of decision-making algorithms, complicate the definition of worst-case scenarios in both functional and non-functional dimensions [55]. As a result, it is hard to define budgets for software timing, relevant criteria for software timing V&V, and adequate testing methodologies.…”

Section: Introductionmentioning

confidence: 99%

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

Alcon

Tabani

Kosmidis

et al. 2020

2020 IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS)

Self Cite

View full text Add to dashboard Cite

The software used to implement advanced functionalities in critical domains (e.g. autonomous operation) impairs software timing. This is not only due to the complexity of the underlying high-performance hardware deployed to provide the required levels of computing performance, but also due to the complexity, non-deterministic nature, and huge input space of the artificial intelligence (AI) algorithms used. In this paper, we focus on Apollo, an industrial-quality Autonomous Driving (AD) software framework: we statistically characterize its observed execution time variability and reason on the sources behind it. We discuss the main challenges and limitations in finding a satisfactory software timing analysis solution for Apollo and also show the main traits for the acceptability of statistical timing analysis techniques as a feasible path. While providing a consolidated solution for the software timing analysis of Apollo is a huge effort far beyond the scope of a single research paper, our work aims to set the basis for future and more elaborated techniques for the timing analysis of AD software.

show abstract

“…The latter are covered, under the stringent time constraints of the automotive domain, by executing AD software on powerful hardware [6,7,11,18], e.g. high-end GPUs despite the existing challenges [8,16,24]. Naturally, these hardware devices consume significant amounts of energy, which recent studies show can reduce the driving range (i.e.…”

Section: Introductionmentioning

confidence: 99%

IntPred

Tabani

Fusi

Kosmidis

et al. 2020

Proceedings of the 35th Annual ACM Symposium on Applied Computing

Self Cite

View full text Add to dashboard Cite

Deep Neural-Network (DNN) based Object Detection is one of the most important and time-consuming stages of Autonomous Driving software in cars. In non-critical domains, the performance and energy requirements of object detection can be reduced at the cost of accuracy in the detected objects. This is not the case in a critical domain like automotive, for which a delicate balance between performance/energy overheads and accuracy of object detection must be found. We propose IntPred to achieve such a balance by leveraging on the fact that, with high frame rates, objects do not move significantly across frames. IntPred tailors object interpolation for the case of object detection in autonomous driving frameworks, in line with approaches devised for other domains, thus heavily reducing the performance requirements of full-fledged DNN-based object prediction. IntPred results in comparable accuracy to the original object detection, while saving more than 70% of the computations. The latter allows using lower-performance and cheaper platforms resulting in saving energy and reducing heat dissipation: for instance, in an NVIDIA Jetson TX2 platform, specific for autonomous driving systems, our technique increases the frame processing rate by 4.6x. IntPred also allows consolidating additional applications onto the same platform.

show abstract

Assessing the Adherence of an Industrial Autonomous Driving Framework to ISO 26262 Software Guidelines

Cited by 20 publications

References 5 publications

Novel Arithmetics in Deep Neural Networks Signal Processing for Autonomous Driving: Challenges and Opportunities

Novel Arithmetics in Deep Neural Networks Signal Processing for Autonomous Driving: Challenges and Opportunities

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

IntPred

Contact Info

Product

Resources

About