Autonomous vehicles (AVs) have promised to drastically improve the convenience of driving by releasing the burden of drivers and reducing traffic accidents with more precise control. With the fast development of artificial intelligence and significant advancements of the Internet of Things technologies, we have witnessed the steady progress of autonomous driving over the recent years. As promising as it is, the march of autonomous driving technologies also faces new challenges, among which security is the top concern. In this article, we give a systematic study on the security threats surrounding autonomous driving, from the angles of perception, navigation, and control. In addition to the in-depth overview of these threats, we also summarize the corresponding defense strategies. Furthermore, we discuss future research directions about the new security threats, especially those related to deep-learning-based self-driving vehicles. By providing the security guidelines at this early stage, we aim to promote new techniques and designs related to AVs from both academia and industry and boost the development of secure autonomous driving.

The Security of Autonomous Driving: Threats, Defenses, and Future Directions

Vehicle classification (VC) is an underlying approach in an intelligent transportation system and is widely used in various applications like the monitoring of traffic flow, automated parking systems, and security enforcement. The existing VC methods generally have a local nature and can classify the vehicles if the target vehicle passes through fixed sensors, passes through the short-range coverage monitoring area, or a hybrid of these methods. Using global positioning system (GPS) can provide reliable global information regarding kinematic characteristics; however, the methods lack information about the physical parameter of vehicles. Furthermore, in the available studies, smartphone or portable GPS apparatuses are used as the source of the extraction vehicle’s kinematic characteristics, which are not dependable for the tracking and classification of vehicles in real time. To deal with the limitation of the available VC methods, potential global methods to identify physical and kinematic characteristics in real time states are investigated. Vehicular Ad Hoc Networks (VANETs) are networks of intelligent interconnected vehicles that can provide traffic parameters such as type, velocity, direction, and position of each vehicle in a real time manner. In this study, VANETs are introduced for VC and their capabilities, which can be used for the above purpose, are presented from the available literature. To the best of the authors’ knowledge, this is the first study that introduces VANETs for VC purposes. Finally, a comparison is conducted that shows that VANETs outperform the conventional techniques.

https://www.mdpi.com/1424-8220/20/11/3274/pdf

A Review on Vehicle Classification and Potential Use of Smart Vehicle-Assisted Techniques

Learning control policies that are safe, robust and interpretable are prominent challenges in developing robotic systems. Learning-from-demonstrations with formal logic is an arising paradigm in reinforcement learning to estimate rewards and extract robot control policies that seek to overcome these challenges. In this approach, we assume that mission-level specifications for the robotic system are expressed in a suitable temporal logic such as Signal Temporal Logic (STL). The main idea is to automatically infer rewards from user demonstrations (that could be suboptimal or incomplete) by evaluating and ranking them w.r.t. the given STL specifications. In contrast to existing work that focuses on deterministic environments and discrete state spaces, in this letter, we propose significant extensions that tackle stochastic environments and continuous state spaces.

Learning From Demonstrations Using Signal Temporal Logic in Stochastic and Continuous Domains

China is in a development period of urbanization construction, while its environment is threatened by an increasing amount of construction and demolition (CD results show that the total number of illegal cases has decreased from 510 to 89 per year since the system was put into operation.

https://www.mdpi.com/2071-1050/12/4/1672/pdf

An Informatization Scheme for Construction and Demolition Waste Supervision and Management in China

Auto Recognition of License Plate is a kind of image processing technology for recognizing the number plate information from images or videos. The observed plate images are normally in low resolution and suffer severe loss of edge data, which cast, incredible test to existing vehicle number plate detection and recognition patterns. The process of Auto recognition of License plate requires a high level of precision, when there are various vehicles going in a brief span and number plate abstraction is a number is a difficult task, basically because of number arrangement, and impact of environmental work. This step influences the accuracy of character separation and acknowledgment framework. This paper introduces a algorithm for Auto recognition of license plate system utilizing various approaches. Auto recognition of license plate method comprises of three segments: Character segmentation, Optical character recognition and template matching. The proposed framework presents the automatic vehicle number plate identification system utilizing a vehicle number plate extraction. Another strategy utilizing Gabor filtering for character recognition in gray scale image is proposed in this paper. Components are separated directly from gray-scale character images by Gabor filters which are exceptionally intended for measurable data of character structures. Template matching is a system which is exploited to find a sub image of an target image which coordinates a template image. Experiment result outcomes to show the superiority of our proposed approach as far as effectiveness.

An efficient approach for automatic license plate recognition system

growing affluence of urban India has made the ownership of vehicles a necessity. This has resulted in an unexpected civic problem - that of traffic control and vehicle identification. Parking areas have become overstressed due to the growing numbers of vehicles on the roads today. The Automatic Number Plate Recognition System (ANPR) plays an important role in addressing these issues as its application ranges from parking admission to monitoring urban traffic and to tracking automobile thefts. There are numerous ANPR systems available today which are based on different methodologies. In this paper, we attempt to review the various techniques and their usage. The ANPR system has been implemented using template Matching and its accuracy was found to be 80.8% for Indian number plates.

/pdf/vehicle-number-plate-recognition-system-a-literature-review-2xb91dzyvr.pdf

Vehicle Number Plate Recognition System: A Literature Review and Implementation using Template Matching

Robust perception algorithms are a vital ingredient for autonomous systems such as self-driving vehicles. Checking the correctness of perception algorithms such as those based on deep convolutional neural networks (CNN) is a formidable challenge problem. In this paper, we suggest the use of Timed Quality Temporal Logic (TQTL) as a formal language to express desirable spatio-temporal properties of a perception algorithm processing a video. While perception algorithms are traditionally tested by comparing their performance to ground truth labels, we show how TQTL can be a useful tool to determine quality of perception, and offers an alternative metric that can give useful information, even in the absence of ground truth labels. We demonstrate TQTL monitoring on two popular CNNs: YOLO and SqueezeDet, and give a comparative study of the results obtained for each architecture.

Specifying and Evaluating Quality Metrics for Vision-based Perception Systems

Cyber-physical system applications such as autonomous vehicles, wearable devices, and avionic systems generate a large volume of time-series data. Designers often look for tools to help classify and categorize the data. Traditional machine learning techniques for time-series data offer several solutions to solve these problems; however, the artifacts trained by these algorithms often lack interpretability. On the other hand, temporal logics, such as Signal Temporal Logic (STL) have been successfully used in the formal methods community as specifications of time-series behaviors. In this work, we propose a new technique to automatically learn temporal logic formulae that are able to cluster and classify real-valued time-series data. Previous work on learning STL formulas from data either assumes a formula-template to be given by the user, or assumes some special fragment of STL that enables exploring the formula structure in a systematic fashion. In our technique, we relax these assumptions, and provide a way to systematically explore the space of all STL formulas. As the space of all STL formulas is very large, and contains many semantically equivalent formulas, we suggest a technique to heuristically prune the space of formulas considered. Finally, we illustrate our technique on various case studies from the automotive, transportation and healthcare domain.

Interpretable Classification of Time-Series Data using Efficient Enumerative Techniques

Cyber-physical system applications such as autonomous vehicles, wearable devices, and avionic systems generate a large volume of time-series data. Designers often look for tools to help classify and categorize the data. Traditional machine learning techniques for time-series data offer several solutions to solve these problems; however, the artifacts trained by these algorithms often lack interpretability. On the other hand, temporal logic, such as Signal Temporal Logic (STL) have been successfully used in the formal methods community as specifications of time-series behaviors. In this work, we propose a new technique to automatically learn temporal logic formulas that are able to classify real-valued time-series data. Previous work on learning STL formulas from data either assumes a formula-template to be given by the user, or assumes some special fragment of STL that enables exploring the formula structure in a systematic fashion. In our technique, we relax these assumptions, and provide a way to systematically explore the space of all STL formulas. As the space of all STL formulas is very large, and contains many semantically equivalent formulas, we suggest a technique to heuristically prune the space of formulas considered. Finally, we illustrate our technique on various case studies from the automotive and transportation domains.

Aniruddh G. Puranic

Papers

Vehicle Number Plate Recognition System: A Literature Review and Implementation using Template Matching

Specifying and Evaluating Quality Metrics for Vision-based Perception Systems

Learning From Demonstrations Using Signal Temporal Logic in Stochastic and Continuous Domains

Interpretable Classification of Time-Series Data using Efficient Enumerative Techniques

Interpretable classification of time-series data using efficient enumerative techniques