Next Generation Automotive Architecture Modeling and Exploration for Autonomous Driving

Zheng, Bowen; Liang, Hengyi; Zhu, Qi; Yu, Huafeng; Lin, Chung-Wei

doi:10.1109/isvlsi.2016.126

Cited by 25 publications

(8 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The inherent challenge in developing such a safety automotive system is that intelligent vehicles are equipped with a growing number of complex components which need to run simultaneously while also being time-critical because of the safety requirements (Zheng et al, 2016). These components include the sensors used such as radar, camera and GPS to estimate the SSMs and to collect real-time traffic variables.…”

Section: Cif = V () : Ttcmentioning

confidence: 99%

Predicting real-time traffic conflicts using deep learning

Formosa

Quddus

Ison

et al. 2020

Accident Analysis & Prevention

122

View full text Add to dashboard Cite

Recently, technologies for predicting traffic conflicts in real-time have been gaining momentum due to their proactive nature of application and the growing implementation of ADAS technology in intelligent vehicles. In ADAS, machine learning classifiers are utilised to predict potential traffic conflicts by analysing data from in-vehicle sensors. In most cases, a condition is classified as a traffic conflict when a safety surrogate (e.g. time-to-collision, TTC) crosses a predefined threshold. This approach, however, largely ignores other factors that influence traffic conflicts such as speed variance, traffic density, speed and weather conditions. Considering all these factors in detecting traffic conflicts is rather complex as it requires an integration and mining of heterodox data, the unavailability of traffic conflicts and conflict prediction models capable of extracting meaningful and accurate information in a timely manner. In addition, the model has to effectively handle large imbalanced data. To overcome these limitations, this paper presents a centralised digital architecture and employs a Deep Learning methodology to predict traffic conflicts. Highly disaggregated traffic data and in-vehicle sensors data from an instrumented vehicle are collected from a section of the UK M1 motorway to build the model. Traffic conflicts are identified by a Regional-Convolution Neural Network (R-CNN) model which detects lane markings and tracks vehicles from images captured by a single frontfacing camera. This data is then integrated with traffic variables and calculated safety surrogate measures (SSMs) via a centralised digital architecture to develop a series of Deep Neural Network (DNN) models to predict these traffic conflicts. The results indicate that TTC, as expected, varies by speed, weather and traffic density and the best DNN model provides an accuracy of 94% making it reliable to employ in ADAS technology as proactive safety management strategies. Furthermore, by exchanging this traffic conflict awareness data, connected vehicles (CVs) can mitigate the risk of traffic collisions.

show abstract

Section: Cif = V () : Ttcmentioning

confidence: 99%

Predicting real-time traffic conflicts using deep learning

Formosa

Quddus

Ison

et al. 2020

Accident Analysis & Prevention

122

View full text Add to dashboard Cite

show abstract

“…Moreover, well known vulnerabilities of machine learning algorithms have to be considered early in the design phase [61,62]. Next generation automotive architectures take into consideration moving to more centralised models, with high band Ethernet communication and networks closer to computer networks [63].…”

Section: Related Workmentioning

confidence: 99%

A Standard Driven Software Architecture for Fully Autonomous Vehicles

Serban¹,

Poll²,

Visser³

2020

JASEN

View full text Add to dashboard Cite

The development of self-driving vehicles is often regarded as adding a layer of intelligence on top of classic vehicle platforms. However, the amount of software needed to reach autonomy will exceed the software deployed for operation of normal vehicles. As complexity increases, the demand for proper structure also increases. Moreover, the shift from open, deterministic components to more opaque, probabilistic software components raises new challenges for system designers. In this paper we introduce a functional software architecture for fully autonomous vehicles aimed to standardise and ease the development process. Existing literature presents past experiments with autonomous driving or implementations specific to limited domains (e.g. winning a competition). The architectural solutions are often an after-math of building or evolving an autonomous vehicle and not the result of a clear software development life-cycle. A major issue of this approach is that requirements cannot be traced with respect to functional components and several components group most functionality. Therefore, it is often difficult to adopt the proposals. In this paper we take a prescriptive approach starting with requirements from a widely adopted automotive standard. We follow a clear software engineering process, specific to the automotive industry. During the design process, we make extensive use of robotic architectures -which seem to be often ignored by automotive software engineers -to support standard driven requirements.

show abstract

“…The outputs of the sensors are processed by on-board processing units, such as CPUs, GPUs, and FPGAs [22]. To communicate with the processing units, the sensors are connected to them via multiple buses, which are in turn connected through gateways [43]. The self-driving unit is the software that, using the information given by the sensors, controls the mechanical components to drive the vehicle.…”

Section: Components Of Self-driving Vehiclesmentioning

confidence: 99%

Validation Frameworks for Self-Driving Vehicles: A Survey

Concas,

Nurminen,

Mikkonen

et al. 2020

Preprint

View full text Add to dashboard Cite

As a part of the digital transformation, we interact with more and more intelligent gadgets. Today, these gadgets are often mobile devices, but in the advent of smart cities, more and more infrastructuresuch as traffic and buildings-in our surroundings becomes intelligent. The intelligence, however, does not emerge by itself. Instead, we need both design techniques to create intelligent systems, as well as approaches to validate their correct behavior. An example of intelligent systems that could benefit smart cities are self-driving vehicles. Self-driving vehicles are continuously becoming both commercially available and common on roads. Accidents involving self-driving vehicles, however, have raised concerns about their reliability. Due to these concerns, the safety of self-driving vehicles should be thoroughly tested before they can be released into traffic. To ensure that self-driving vehicles encounter all possible scenarios, several millions of hours of testing must be carried out; therefore, testing self-driving vehicles in the real world is impractical. There is also the issue that testing self-driving vehicles directly in the traffic poses a potential safety hazard to human drivers. To tackle this challenge, validation frameworks for testing self-driving vehicles in simulated scenarios are being developed by academia and industry. In this chapter, we briefly introduce self-driving vehicles and give an overview of validation frameworks for testing them in a simulated environment. We conclude by discussing what an ideal validation framework at the state of the art should be and what could benefit validation frameworks for self-driving vehicles in the future.

show abstract

Next Generation Automotive Architecture Modeling and Exploration for Autonomous Driving

Cited by 25 publications

References 42 publications

Predicting real-time traffic conflicts using deep learning

Predicting real-time traffic conflicts using deep learning

A Standard Driven Software Architecture for Fully Autonomous Vehicles

Validation Frameworks for Self-Driving Vehicles: A Survey

Contact Info

Product

Resources

About