Development Of Autonomous Cars Research Articles

End-to-End Steering Angle Prediction for Autonomous Car Using Vision Transformer

The development of autonomous cars is currently increasing along with the need for safe and comfortable autonomous cars. The development of autonomous cars cannot be separated from the use of deep learning to determine the steering angle of an autonomous car according to the road conditions it faces. In the research, a Vision Transformer (ViT) model is proposed to determine the steering angle based on images taken using a front-facing camera on an autonomous car. The dataset used to train ViT is a public dataset. The dataset is taken from streets around Rancho Palos Verdes and San Pedro, California. The number of images is 45,560, which are labeled with the steering angle value for each image. The proposed model can predict steering angle well. Then, the steering angle prediction results are compared using the same dataset with existing models. The experimental results show that the proposed model has better accuracy regarding the resulting MSE value of 2,991 compared to the CNN-based model of 5,358 and the CNN-LSTM combination model of 4,065. From the results of this experiment, the ViT model can replace the existing model, namely the CNN model and the combination model between CNN and LSTM, in predicting the steering angle of an autonomous car.

From senses to sensors: autonomous cars and probing what machine learning does to mobilities studies

ABSTRACT Cars are nowadays being programmed to learn how to drive themselves. While autonomous cars are often portrayed as the next step in the auto-motive industry, they have already begun roaming the streets in some US cities. Building on a growing body of critical scholarship on the development of autonomous cars, we explore what machine learning is in open environments like cities by juxtaposing this to the field of mobilities studies. We do so by revisiting core concepts in mobilities studies: movement, representation and embodied experience. Our analysis of machine learning is centred around the transition from human senses to sensors mounted on cars, and what this implies in terms of autonomy. While much of the discussions related to this transition are already foregrounded in mobilities studies, due to this field's emphasis on complexities and the understanding of automobility as a socio-technological system, questions about autonomy still emerge in a slightly new light with the advent of machine learning. We conclude by suggesting that in mobilities studies, autonomy has always been seen as intertwined with technology, yet we argue that machine learning unfolds autonomy as intrinsic to technology, as the space between the car, the driver and the context is collapsing with autonomous cars.

Autonomous cars, development of modern transport technology

The article presents selected issues from the conducted research and analyzes in the field of the development of autonomous vehicles, carried out under the project: Polish road to Automation of Road Transport. The development of autonomous cars is a global challenge for the automotive industry. The creation of a fully autonomous vehicle capable of transporting passengers and goods without the participation of a driver has become a priority goal of automotive concerns. The huge costs incurred by automotive concerns for the development of autonomous vehicles prove the progressing automotive revolution, which will have a significant impact on the shape of future transport systems, transport based on autonomous transport. Very often in the literature there are overly optimistic forecasts for the development of autonomous vehicles, as well as overestimating the benefits they are to bring, without pointing to the costs and problems of their implementation and functioning in the real transport system. The publication presents forecasts for the development of autonomous vehicles as well as the related risks and advantages of their implementation. The factors that have a significant impact on the development of these vehicles are also outlined.

Decision making framework for autonomous vehicles driving behavior in complex scenarios via hierarchical state machine

With the development of autonomous car, a vehicle is capable to sense its environment more precisely. That allows improved drving behavior decision strategy to be used for more safety and effectiveness in complex scenarios. In this paper, a decision making framework based on hierarchical state machine is proposed with a top-down structure of three-layer finite state machine decision system. The upper layer classifies the driving scenario based on relative position of the vehicle and its surrounding vehicles. The middle layer judges the optimal driving behavior according to the improved energy efficiency function targeted at multiple criteria including driving efficiency, safety and the grid-based lane vacancy rate. The lower layer constructs the state transition matrix combined with the calculation results of the previous layer to predict the optimal pass way in the region. The simulation results show that the proposed driving strategy can integrate multiple criteria to evaluate the energy efficiency value of vehicle behavior in real time, and realize the selection of optimal vehicle driving strategy. With popularity of automatic vehicles in future, the driving strategy can be used as a reference to provide assistance for human drive or even the real-time decision-making of autonomous driving.

A scalable and distributed architecture for secure and privacy-preserving authentication and message dissemination in VANETs

With significant advances in the development of autonomous cars and Internet of Things (IoT) in recent years, Vehicular Ad-hoc NETworks (VANETs) have become a promising technology for Intelligent Transportation Systems (ITS) as well. However, the wireless nature of VANET communication makes it vulnerable to a plethora of attack vectors to otherwise secure vehicles. Authenticated message dissemination plays a key role to avert such security vulnerabilities. Many of the existing Public Key Infrastructure (PKI) based schemes use Certificates for authentication. In such schemes, for authenticating an entity which presents its certificate, Certificate Revocation List (CRL) is used to check if the entity’s certificate has been revoked. But, as the size of the CRL grows, using CRL for authentication can incur computation and storage overhead in VANETs. To overcome this limitation of CRL-based approach for authentication, in this paper, we propose a distributed, scalable, low-overhead, privacy-preserving authentication scheme for VANETs. The proposed scheme uses a Merkle Hash Tree (MHT) for authenticating Road Side Units (RSUs) and Modified Merkle Patricia Trie (MMPT) for authenticating vehicles. We also present an informal analysis as well as formal correctness proof of the proposed scheme.

Multiple Sensing Method Using Moving Average Filter for Automotive Ultrasonic Sensor

Distance sensing on vehicles is a trend in the development of autonomous cars. So that the use of proximity sensors such as ultrasonic and infrared, is very important. This research paper focuses on developing a reading of 4 ultrasonic sensors simultaneously. Where the reading method is done using 4 pin echo and 4 pins trigger and 1 pin echo with 4 pin triggers. In order for better reading, the programming algorithm for each method is integrated with the moving average filter. The use of this filter is able to correct the noise that occurs when reading the distance. The test was carried out at the computer simulation stage using a microcontroller. The final results of the study obtained a very small reading error.

Theoretical limit evaluation of ranging accuracy and power for LiDAR systems in autonomous cars

With the development of autonomous cars, the demand for accurate light detection and ranging (LiDAR) systems is increasing. Previous evaluations of LiDAR were mainly based on experiments and lacked theoretical significance. We theoretically evaluate the accuracy and optical output power of LiDAR systems in autonomous cars. We focus on two ranging schemes: the time-of-flight (TOF) method and the quadrature phase detection (QPD) method. Considering the special requirements of autonomous driving, the theoretical limits of ranging accuracy are calculated by deriving the Cramer–Rao bound (CRB). The influence of reflectivity as well as distance on accuracy are discussed. We also determine the relationship between optical output power and essential parameters, and make comparisons between TOF and QPD. It can be concluded that TOF is more efficient under most circumstances. When designing autonomous cars, such theoretical evaluation provides guidance for choosing laser emitters and receivers, justifying the significance of our work to LiDAR development.

A Review of the Technical Content of Autonomous Vehicle

In order to analyze the system composition of the development status of autonomous technology and the problems and prospects of autonomous vehicles, this paper analyzes the development of unmanned driving technology at home and abroad in recent years through field research and literature review, and finds Internet technology. Rapid development has brought new changes to the automotive industry, and the increasingly serious traffic safety problem has accelerated the development of autonomous technology. Through investigation, it is found that autonomous cars are developing rapidly. The development of autonomous cars has greatly improved the efficiency and safety of transportation systems. For the entire automobile development industry, autonomous cars will undoubtedly become the first direction of automobile development. In this paper, the composition of unmanned vehicles is described by explaining the development status of unmanned vehicles at home and abroad. This paper also briefly analyzes the key technologies of autonomous vehicles: environment-aware technology, navigation and positioning technology, path planning technology, decision-making control technology, and further compares the current problems and development prospects of autonomous technology, and through the investigation of materials The study further prospects the development direction of unmanned vehicles. In the end, it was found that despite the series of problems, unmanned driving is in line with the trend of intelligent and Internet-oriented vehicles, which is a major opportunity for the automotive industry to change under the Internet wave.

Autonomous Cars: In Favor of a Mandatory Ethics Setting.

The recent progress in the development of autonomous cars has seen ethical questions come to the forefront. In particular, life and death decisions regarding the behavior of self-driving cars in trolley dilemma situations are attracting widespread interest in the recent debate. In this essay we want to ask whether we should implement a mandatory ethics setting (MES) for the whole of society or, whether every driver should have the choice to select his own personal ethics setting (PES). While the consensus view seems to be that people would not be willing to use an automated car that might sacrifice themselves in a dilemma situation, we will defend the somewhat contra-intuitive claim that this would be nevertheless in their best interest. The reason is, simply put, that a PES regime would most likely result in a prisoner's dilemma.

DRAWING FOR TRAFFIC MARKING USING BIDIRECTIONAL GRADIENT-BASED DETECTION WITH MMS LIDAR INTENSITY

Abstract. Recently, the development of autonomous cars is accelerating on the integration of highly advanced artificial intelligence, which increases demand for a digital map with high accuracy. In particular, traffic markings are required to be precisely digitized since automatic driving utilizes them for position detection. To draw traffic markings, we benefit from Mobile Mapping Systems (MMS) equipped with high-density Laser imaging Detection and Ranging (LiDAR) scanners, which produces large amount of data efficiently with XYZ coordination along with reflectance intensity. Digitizing this data, on the other hand, conventionally has been dependent on human operation, which thus suffers from human errors, subjectivity errors, and low reproductivity. We have tackled this problem by means of automatic extraction of traffic marking, which partially accomplished to draw several traffic markings (G. Takahashi et al., 2014). The key idea of the method was extracting lines using the Hough transform strategically focused on changes in local reflection intensity along scan lines. However, it failed to extract traffic markings properly in a densely marked area, especially when local changing points are close each other. In this paper, we propose a bidirectional gradient-based detection method where local changing points are labelled with plus or minus group. Given that each label corresponds to the boundary between traffic markings and background, we can identify traffic markings explicitly, meaning traffic lines are differentiated correctly by the proposed method. As such, our automated method, a highly accurate and non-human-operator-dependent method using bidirectional gradient-based algorithm, can successfully extract traffic lines composed of complex shapes such as a cross walk, resulting in minimizing cost and obtaining highly accurate results.

DRAWING FOR TRAFFIC MARKING USING BIDIRECTIONAL GRADIENT-BASED DETECTION WITH MMS LIDAR INTENSITY

Recently, the development of autonomous cars is accelerating on the integration of highly advanced artificial intelligence, which increases demand for a digital map with high accuracy. In particular, traffic markings are required to be precisely digitized since automatic driving utilizes them for position detection. To draw traffic markings, we benefit from Mobile Mapping Systems (MMS) equipped with high-density Laser imaging Detection and Ranging (LiDAR) scanners, which produces large amount of data efficiently with XYZ coordination along with reflectance intensity. Digitizing this data, on the other hand, conventionally has been dependent on human operation, which thus suffers from human errors, subjectivity errors, and low reproductivity. We have tackled this problem by means of automatic extraction of traffic marking, which partially accomplished to draw several traffic markings (G. Takahashi et al., 2014). The key idea of the method was extracting lines using the Hough transform strategically focused on changes in local reflection intensity along scan lines. However, it failed to extract traffic markings properly in a densely marked area, especially when local changing points are close each other. <br><br> In this paper, we propose a bidirectional gradient-based detection method where local changing points are labelled with plus or minus group. Given that each label corresponds to the boundary between traffic markings and background, we can identify traffic markings explicitly, meaning traffic lines are differentiated correctly by the proposed method. As such, our automated method, a highly accurate and non-human-operator-dependent method using bidirectional gradient-based algorithm, can successfully extract traffic lines composed of complex shapes such as a cross walk, resulting in minimizing cost and obtaining highly accurate results.

Navigating a Driverless World

In the recent years there has been a tremendous advancement in the autonomous sector resulting in development of autonomous car or driverless cars. The research paper focuses on features of this car and on its practical implementation in developing countries. The points taken into account include issues for its implementation in developing countries as they differ from that of developed countries. The paper includes security features of the car, the problems faced due to the geographical conditions among various areas as well as cultural background (social issues), high speed internet connectivity, fully mapped global terrain, ability to fetch real time traffic data through internet, non-availability of standardized road network and weather interference are the key issues that will be reviewed and their solutions suggested in this paper.

Responsibility for crashes of autonomous vehicles: an ethical analysis.

A number of companies including Google and BMW are currently working on the development of autonomous cars. But if fully autonomous cars are going to drive on our roads, it must be decided who is to be held responsible in case of accidents. This involves not only legal questions, but also moral ones. The first question discussed is whether we should try to design the tort liability for car manufacturers in a way that will help along the development and improvement of autonomous vehicles. In particular, Patrick Lin’s concern that any security gain derived from the introduction of autonomous cars would constitute a trade-off in human lives will be addressed. The second question is whether it would be morally permissible to impose liability on the user based on a duty to pay attention to the road and traffic and to intervene when necessary to avoid accidents. Doubts about the moral legitimacy of such a scheme are based on the notion that it is a form of defamation if a person is held to blame for causing the death of another by his inattention if he never had a real chance to intervene. Therefore, the legitimacy of such an approach would depend on the user having an actual chance to do so. The last option discussed in this paper is a system in which a person using an autonomous vehicle has no duty (and possibly no way) of interfering, but is still held (financially, not criminally) responsible for possible accidents. Two ways of doing so are discussed, but only one is judged morally feasible.