Self-driving and semi-self-driving cars play an important role in our daily lives.The effectiveness of these cars is based heavily on the use of their surrounding areas to collect sensitive and vital information.Howev...Self-driving and semi-self-driving cars play an important role in our daily lives.The effectiveness of these cars is based heavily on the use of their surrounding areas to collect sensitive and vital information.However,external infrastructures also play significant roles in the transmission and reception of control data,cooperative awareness messages,and caution notifications.In this case,roadside units are considered one of themost important communication peripherals.Random distribution of these infrastructures will overburden the spread of self-driving vehicles in terms of cost,bandwidth,connectivity,and radio coverage area.In this paper,a new distributed roadside unit is proposed to enhance the performance and connectivity of these cars.Therefore,this approach is based primarily on k-means to find the optimal location of each roadside unit.In addition,this approach supports dynamicmobility with a long period of connectivity for each car.Further,this system can adapt to various locations(e.g.,highways,rural areas,urban environments).The simulation results of the proposed system are reflected in its efficiency and effectively.Thus,the system can achieve a high connectivity rate with a low error rate while reducing costs.展开更多
Security systems are a necessity for the deployment of smart vehicles in our society. Security in vehicular ad hoe networks is crucial to the reliable exchange of information and control data. In this paper, we propos...Security systems are a necessity for the deployment of smart vehicles in our society. Security in vehicular ad hoe networks is crucial to the reliable exchange of information and control data. In this paper, we propose an intelligent Intrusion Detection System （IDS） to protect the external communication of self-driving and semi self-driving vehicles. This technology has the ability to detect Denial of Service （DOS） and black hole attacks on vehicular ad hoe networks （VANETs）. The advantage of the proposed IDS over existing security systems is that it detects attacks before they causes significant damage. The intrusion prediction technique is based on Linear Discriminant Analysis （LDA） and Quadratic Diseriminant Analysis （QDA） which are used to predict attacks based on observed vehicle behavior. We perform simulations using Network Simulator 2 to demonstrate that the IDS achieves a low rate of false alarms and high accuracy in detection.展开更多
Late this March.China＇s Internet giant Baidu became the first self-driving car developer to obtain temporary license plates to carry out self driving tests on public roads in Beijing.
The advancement of artificial intelligence(AI)has truly stimulated the development and deployment of autonomous vehicles(AVs)in the transportation industry.Fueled by big data from various sensing devices and advanced ...The advancement of artificial intelligence(AI)has truly stimulated the development and deployment of autonomous vehicles(AVs)in the transportation industry.Fueled by big data from various sensing devices and advanced computing resources,AI has become an essential component of AVs for perceiving the surrounding environment and making appropriate decision in motion.To achieve goal of full automation(i.e.,self-driving),it is important to know how AI works in AV systems.Existing research have made great efforts in investigating different aspects of applying AI in AV development.However,few studies have offered the research community a thorough examination of current practices in implementing AI in AVs.Thus,this paper aims to shorten the gap by providing a comprehensive survey of key studies in this research avenue.Specifically,it intends to analyze their use of AIs in supporting the primary applications in AVs:1)perception;2)localization and mapping;and 3)decision making.It investigates the current practices to understand how AI can be used and what are the challenges and issues associated with their implementation.Based on the exploration of current practices and technology advances,this paper further provides insights into potential opportunities regarding the use of AI in conjunction with other emerging technologies:1)high definition maps,big data,and high performance computing;2)augmented reality(AR)/virtual reality(VR)enhanced simulation platform;and 3)5G communication for connected AVs.This paper is expected to offer a quick reference for researchers interested in understanding the use of AI in AV research.展开更多
Autonomous vehicles in industrial parks can provide intelligent,efficient,and environmentally friendly transportation services,making them crucial tools for solving internal transportation issues.Considering the chara...Autonomous vehicles in industrial parks can provide intelligent,efficient,and environmentally friendly transportation services,making them crucial tools for solving internal transportation issues.Considering the characteristics of industrial park scenarios and limited resources,designing and implementing autonomous driving solutions for autonomous vehicles in these areas has become a research hotspot.This paper proposes an efficient autonomous driving solution based on path planning,target recognition,and driving decision-making as its core components.Detailed designs for path planning,lane positioning,driving decision-making,and anti-collision algorithms are presented.Performance analysis and experimental validation of the proposed solution demonstrate its effectiveness in meeting the autonomous driving needs within resource-constrained environments in industrial parks.This solution provides important references for enhancing the performance of autonomous vehicles in these areas.展开更多
Countries have invested considerable sums of human capital and material resources in the practical application of self-driving cars demonstrating the impressive market opportunity.In light of this trend,Taiwan does no...Countries have invested considerable sums of human capital and material resources in the practical application of self-driving cars demonstrating the impressive market opportunity.In light of this trend,Taiwan does not want to fall behind either.As on-road testing and technological development for self-driving cars continue to develop in different countries,the controversial issues of safety,ethics,liability,and the invasion of privacy continue to emerge.In order to resolve these issues,the government of Taiwan seeks to provide a good environment for AI(artificial intelligence)innovation and applications.This article summarizes and highlights relevant content and key points of Unmanned Vehicles Technology Innovative Experimentation Act,which was legislated in Taiwan in 2018.In addition,it points out the fundamental ethics regulation of AI,which has influenced Taiwan legal policy.展开更多
The autonomous vehicle(AV)technology has the potential to significantly improve safety and efficiency of the transportation and logistics industry.Full-scale AV testing is limited by time,space,and cost,while simulati...The autonomous vehicle(AV)technology has the potential to significantly improve safety and efficiency of the transportation and logistics industry.Full-scale AV testing is limited by time,space,and cost,while simulation-based testing often lacks the necessary accuracy of AV and environmental modeling.In recent years,several initiatives have emerged to test autonomous software and hardware on scaled vehicles.This systematic literature review provides an overview of the literature surrounding small-scale self-driving cars,summarizing the current autonomous platforms deployed and focusing on the software and hardware developments in this field.The studies published in English-language journals or conference papers that present small-scale testing of self-driving cars were included.Web of Science,Scopus,Springer Link,Wiley,ACM Digital Library,and TRID databases were used for the literature search.The systematic literature search found 38 eligible studies.Research gaps in the reviewed papers were identified to provide guidance for future research.Some key takeaway emerging from this manuscript are:(i)there is a need to improve the models and neural network architectures used in autonomous driving systems,as most papers present only preliminary results;(ii)increasing datasets and sharing databases can help in developing more reliable control policies and reducing bias and variance in the training process;(iii)small-scaled vehicles to ensure safety is a major benefit,and incorporating data about unsafe driving behaviors and infrastructure problems can improve the accuracy of predictive models.展开更多
One of the most basic and difficult areas of computer vision and image understanding applications is still object detection. Deep neural network models and enhanced object representation have led to significant progre...One of the most basic and difficult areas of computer vision and image understanding applications is still object detection. Deep neural network models and enhanced object representation have led to significant progress in object detection. This research investigates in greater detail how object detection has changed in the recent years in the deep learning age. We provide an overview of the literature on a range of cutting-edge object identification algorithms and the theoretical underpinnings of these techniques. Deep learning technologies are contributing to substantial innovations in the field of object detection. While Convolutional Neural Networks (CNN) have laid a solid foundation, new models such as You Only Look Once (YOLO) and Vision Transformers (ViTs) have expanded the possibilities even further by providing high accuracy and fast detection in a variety of settings. Even with these developments, integrating CNN, YOLO and ViTs, into a coherent framework still poses challenges with juggling computing demand, speed, and accuracy especially in dynamic contexts. Real-time processing in applications like surveillance and autonomous driving necessitates improvements that take use of each model type’s advantages. The goal of this work is to provide an object detection system that maximizes detection speed and accuracy while decreasing processing requirements by integrating YOLO, CNN, and ViTs. Improving real-time detection performance in changing weather and light exposure circumstances, as well as detecting small or partially obscured objects in crowded cities, are among the goals. We provide a hybrid architecture which leverages CNN for robust feature extraction, YOLO for rapid detection, and ViTs for remarkable global context capture via self-attention techniques. Using an innovative training regimen that prioritizes flexible learning rates and data augmentation procedures, the model is trained on an extensive dataset of urban settings. Compared to solo YOLO, CNN, or ViTs models, the suggested model exhibits an increase in detection accuracy. This improvement is especially noticeable in difficult situations such settings with high occlusion and low light. In addition, it attains a decrease in inference time in comparison to baseline models, allowing real-time object detection without performance loss. This work introduces a novel method of object identification that integrates CNN, YOLO and ViTs, in a synergistic way. The resultant framework extends the use of integrated deep learning models in practical applications while also setting a new standard for detection performance under a variety of conditions. Our research advances computer vision by providing a scalable and effective approach to object identification problems. Its possible uses include autonomous navigation, security, and other areas.展开更多
Purpose–Recent studies on commuter parking in an age of fully autonomous vehicles(FAVs)suggest,that the number of parking spaces close to the workplace demanded by commuters will decline because of the capability of ...Purpose–Recent studies on commuter parking in an age of fully autonomous vehicles(FAVs)suggest,that the number of parking spaces close to the workplace demanded by commuters will decline because of the capability of FAVs to return home,to seek out(free)parking elsewhere or just cruise.This would be good news because,as of today,parking is one of the largest consumers of urban land and is associated with substantial costs to society.None of the studies,however,is concerned with the special case of employer-provided parking,although workplace parking is a widespread phenomenon and,in many instances,the dominant form of commuter parking.The purpose of this paper is to analyze whether commuter parking will decline with the advent of self-driving cars when parking is provided by the employer.Design/methodology/approach–This study looks at commuter parking from the perspective of both the employer and the employee because in the case of employer-provided parking,the firm’s decision to offer a parking space and the incentive of employees to accept that offer are closely interrelated because of the fringe benefit character of workplace parking.This study develops an economic equilibrium model that explicitly maps the employer–employee relationship,considering the treatment of parking provision and parking policy in the income tax code and accounting for adverse effects from commuting,parking and public transit.This study determines the market level of employer-provided parking in the absence and presence of FAVs and identifies the factors that drive the difference.This study then approximates the magnitude of each factor,relying on recent(first)empirical evidence on the impacts of FAVs.Findings–This paper’s analysis suggests that as long as distortive(tax)policy favors employer-provided parking,FAVs are no guarantee to end up with less commuter parking.Originality/value–This study’s findings imply that in a world of self-driving cars,policy intervention related to work commuting(e.g.fringe benefit taxation or transport pricing)might be even more warranted than today.展开更多
Autonomous vehicles are currently developed, and are expected to be introduced gradually. Society needs a basis for decisions regarding market interventions. This study identifies, quantifies and values the benefits a...Autonomous vehicles are currently developed, and are expected to be introduced gradually. Society needs a basis for decisions regarding market interventions. This study identifies, quantifies and values the benefits and costs of autonomous trucks and cars considering generalized costs, external effects and social marginal cost pricing to consumers with Swedish data. The results show that the greatest benefits are saved driver costs for trucks and decreased travel time costs for car drivers. In the example calculations, capital costs may increase by 22 percent for cars and 36 percent for trucks for benefits to exceed costs in 2025. Subsidies are not needed since the producers and consumers get the major benefits and pay the costs.展开更多
Rule-based autonomous driving systems may suffer from increased complexity with large-scale intercoupled rules,so many researchers are exploring learning-based approaches.Reinforcement learning(RL)has been applied in ...Rule-based autonomous driving systems may suffer from increased complexity with large-scale intercoupled rules,so many researchers are exploring learning-based approaches.Reinforcement learning(RL)has been applied in designing autonomous driving systems because of its outstanding performance on a wide variety of sequential control problems.However,poor initial performance is a major challenge to the practical implementation of an RL-based autonomous driving system.RL training requires extensive training data before the model achieves reasonable performance,making an RL-based model inapplicable in a real-world setting,particularly when data are expensive.We propose an asynchronous supervised learning(ASL)method for the RL-based end-to-end autonomous driving model to address the problem of poor initial performance before training this RL-based model in real-world settings.Specifically,prior knowledge is introduced in the ASL pre-training stage by asynchronously executing multiple supervised learning processes in parallel,on multiple driving demonstration data sets.After pre-training,the model is deployed on a real vehicle to be further trained by RL to adapt to the real environment and continuously break the performance limit.The presented pre-training method is evaluated on the race car simulator,TORCS(The Open Racing Car Simulator),to verify that it can be sufficiently reliable in improving the initial performance and convergence speed of an end-to-end autonomous driving model in the RL training stage.In addition,a real-vehicle verification system is built to verify the feasibility of the proposed pre-training method in a real-vehicle deployment.Simulations results show that using some demonstrations during a supervised pre-training stage allows significant improvements in initial performance and convergence speed in the RL training stage.展开更多
文摘Self-driving and semi-self-driving cars play an important role in our daily lives.The effectiveness of these cars is based heavily on the use of their surrounding areas to collect sensitive and vital information.However,external infrastructures also play significant roles in the transmission and reception of control data,cooperative awareness messages,and caution notifications.In this case,roadside units are considered one of themost important communication peripherals.Random distribution of these infrastructures will overburden the spread of self-driving vehicles in terms of cost,bandwidth,connectivity,and radio coverage area.In this paper,a new distributed roadside unit is proposed to enhance the performance and connectivity of these cars.Therefore,this approach is based primarily on k-means to find the optimal location of each roadside unit.In addition,this approach supports dynamicmobility with a long period of connectivity for each car.Further,this system can adapt to various locations(e.g.,highways,rural areas,urban environments).The simulation results of the proposed system are reflected in its efficiency and effectively.Thus,the system can achieve a high connectivity rate with a low error rate while reducing costs.
文摘Security systems are a necessity for the deployment of smart vehicles in our society. Security in vehicular ad hoe networks is crucial to the reliable exchange of information and control data. In this paper, we propose an intelligent Intrusion Detection System （IDS） to protect the external communication of self-driving and semi self-driving vehicles. This technology has the ability to detect Denial of Service （DOS） and black hole attacks on vehicular ad hoe networks （VANETs）. The advantage of the proposed IDS over existing security systems is that it detects attacks before they causes significant damage. The intrusion prediction technique is based on Linear Discriminant Analysis （LDA） and Quadratic Diseriminant Analysis （QDA） which are used to predict attacks based on observed vehicle behavior. We perform simulations using Network Simulator 2 to demonstrate that the IDS achieves a low rate of false alarms and high accuracy in detection.
文摘Late this March.China＇s Internet giant Baidu became the first self-driving car developer to obtain temporary license plates to carry out self driving tests on public roads in Beijing.
基金supported by the FundamentalResearch Funds for the Central Universities(2662019QD002)
文摘The advancement of artificial intelligence(AI)has truly stimulated the development and deployment of autonomous vehicles(AVs)in the transportation industry.Fueled by big data from various sensing devices and advanced computing resources,AI has become an essential component of AVs for perceiving the surrounding environment and making appropriate decision in motion.To achieve goal of full automation(i.e.,self-driving),it is important to know how AI works in AV systems.Existing research have made great efforts in investigating different aspects of applying AI in AV development.However,few studies have offered the research community a thorough examination of current practices in implementing AI in AVs.Thus,this paper aims to shorten the gap by providing a comprehensive survey of key studies in this research avenue.Specifically,it intends to analyze their use of AIs in supporting the primary applications in AVs:1)perception;2)localization and mapping;and 3)decision making.It investigates the current practices to understand how AI can be used and what are the challenges and issues associated with their implementation.Based on the exploration of current practices and technology advances,this paper further provides insights into potential opportunities regarding the use of AI in conjunction with other emerging technologies:1)high definition maps,big data,and high performance computing;2)augmented reality(AR)/virtual reality(VR)enhanced simulation platform;and 3)5G communication for connected AVs.This paper is expected to offer a quick reference for researchers interested in understanding the use of AI in AV research.
基金supported by the Natural Science Foundation of Jiangsu Province(BK20211357)the Qing Lan Project of Jiangsu Province(2022)+1 种基金the Natural Science Foundation of the Jiangsu Higher Education Institutions of China(22KJB520036 and 23KJB510033)the Innovation Project of Engineering Research Center of Integration and Application of Digital Learning Technology of MOE(1221046)。
文摘Autonomous vehicles in industrial parks can provide intelligent,efficient,and environmentally friendly transportation services,making them crucial tools for solving internal transportation issues.Considering the characteristics of industrial park scenarios and limited resources,designing and implementing autonomous driving solutions for autonomous vehicles in these areas has become a research hotspot.This paper proposes an efficient autonomous driving solution based on path planning,target recognition,and driving decision-making as its core components.Detailed designs for path planning,lane positioning,driving decision-making,and anti-collision algorithms are presented.Performance analysis and experimental validation of the proposed solution demonstrate its effectiveness in meeting the autonomous driving needs within resource-constrained environments in industrial parks.This solution provides important references for enhancing the performance of autonomous vehicles in these areas.
文摘Countries have invested considerable sums of human capital and material resources in the practical application of self-driving cars demonstrating the impressive market opportunity.In light of this trend,Taiwan does not want to fall behind either.As on-road testing and technological development for self-driving cars continue to develop in different countries,the controversial issues of safety,ethics,liability,and the invasion of privacy continue to emerge.In order to resolve these issues,the government of Taiwan seeks to provide a good environment for AI(artificial intelligence)innovation and applications.This article summarizes and highlights relevant content and key points of Unmanned Vehicles Technology Innovative Experimentation Act,which was legislated in Taiwan in 2018.In addition,it points out the fundamental ethics regulation of AI,which has influenced Taiwan legal policy.
基金funded by the Brazilian National Council for Scientific and Technological Development(CNPq),under research grant number 408186/2021-6.
文摘The autonomous vehicle(AV)technology has the potential to significantly improve safety and efficiency of the transportation and logistics industry.Full-scale AV testing is limited by time,space,and cost,while simulation-based testing often lacks the necessary accuracy of AV and environmental modeling.In recent years,several initiatives have emerged to test autonomous software and hardware on scaled vehicles.This systematic literature review provides an overview of the literature surrounding small-scale self-driving cars,summarizing the current autonomous platforms deployed and focusing on the software and hardware developments in this field.The studies published in English-language journals or conference papers that present small-scale testing of self-driving cars were included.Web of Science,Scopus,Springer Link,Wiley,ACM Digital Library,and TRID databases were used for the literature search.The systematic literature search found 38 eligible studies.Research gaps in the reviewed papers were identified to provide guidance for future research.Some key takeaway emerging from this manuscript are:(i)there is a need to improve the models and neural network architectures used in autonomous driving systems,as most papers present only preliminary results;(ii)increasing datasets and sharing databases can help in developing more reliable control policies and reducing bias and variance in the training process;(iii)small-scaled vehicles to ensure safety is a major benefit,and incorporating data about unsafe driving behaviors and infrastructure problems can improve the accuracy of predictive models.
文摘One of the most basic and difficult areas of computer vision and image understanding applications is still object detection. Deep neural network models and enhanced object representation have led to significant progress in object detection. This research investigates in greater detail how object detection has changed in the recent years in the deep learning age. We provide an overview of the literature on a range of cutting-edge object identification algorithms and the theoretical underpinnings of these techniques. Deep learning technologies are contributing to substantial innovations in the field of object detection. While Convolutional Neural Networks (CNN) have laid a solid foundation, new models such as You Only Look Once (YOLO) and Vision Transformers (ViTs) have expanded the possibilities even further by providing high accuracy and fast detection in a variety of settings. Even with these developments, integrating CNN, YOLO and ViTs, into a coherent framework still poses challenges with juggling computing demand, speed, and accuracy especially in dynamic contexts. Real-time processing in applications like surveillance and autonomous driving necessitates improvements that take use of each model type’s advantages. The goal of this work is to provide an object detection system that maximizes detection speed and accuracy while decreasing processing requirements by integrating YOLO, CNN, and ViTs. Improving real-time detection performance in changing weather and light exposure circumstances, as well as detecting small or partially obscured objects in crowded cities, are among the goals. We provide a hybrid architecture which leverages CNN for robust feature extraction, YOLO for rapid detection, and ViTs for remarkable global context capture via self-attention techniques. Using an innovative training regimen that prioritizes flexible learning rates and data augmentation procedures, the model is trained on an extensive dataset of urban settings. Compared to solo YOLO, CNN, or ViTs models, the suggested model exhibits an increase in detection accuracy. This improvement is especially noticeable in difficult situations such settings with high occlusion and low light. In addition, it attains a decrease in inference time in comparison to baseline models, allowing real-time object detection without performance loss. This work introduces a novel method of object identification that integrates CNN, YOLO and ViTs, in a synergistic way. The resultant framework extends the use of integrated deep learning models in practical applications while also setting a new standard for detection performance under a variety of conditions. Our research advances computer vision by providing a scalable and effective approach to object identification problems. Its possible uses include autonomous navigation, security, and other areas.
文摘Purpose–Recent studies on commuter parking in an age of fully autonomous vehicles(FAVs)suggest,that the number of parking spaces close to the workplace demanded by commuters will decline because of the capability of FAVs to return home,to seek out(free)parking elsewhere or just cruise.This would be good news because,as of today,parking is one of the largest consumers of urban land and is associated with substantial costs to society.None of the studies,however,is concerned with the special case of employer-provided parking,although workplace parking is a widespread phenomenon and,in many instances,the dominant form of commuter parking.The purpose of this paper is to analyze whether commuter parking will decline with the advent of self-driving cars when parking is provided by the employer.Design/methodology/approach–This study looks at commuter parking from the perspective of both the employer and the employee because in the case of employer-provided parking,the firm’s decision to offer a parking space and the incentive of employees to accept that offer are closely interrelated because of the fringe benefit character of workplace parking.This study develops an economic equilibrium model that explicitly maps the employer–employee relationship,considering the treatment of parking provision and parking policy in the income tax code and accounting for adverse effects from commuting,parking and public transit.This study determines the market level of employer-provided parking in the absence and presence of FAVs and identifies the factors that drive the difference.This study then approximates the magnitude of each factor,relying on recent(first)empirical evidence on the impacts of FAVs.Findings–This paper’s analysis suggests that as long as distortive(tax)policy favors employer-provided parking,FAVs are no guarantee to end up with less commuter parking.Originality/value–This study’s findings imply that in a world of self-driving cars,policy intervention related to work commuting(e.g.fringe benefit taxation or transport pricing)might be even more warranted than today.
文摘Autonomous vehicles are currently developed, and are expected to be introduced gradually. Society needs a basis for decisions regarding market interventions. This study identifies, quantifies and values the benefits and costs of autonomous trucks and cars considering generalized costs, external effects and social marginal cost pricing to consumers with Swedish data. The results show that the greatest benefits are saved driver costs for trucks and decreased travel time costs for car drivers. In the example calculations, capital costs may increase by 22 percent for cars and 36 percent for trucks for benefits to exceed costs in 2025. Subsidies are not needed since the producers and consumers get the major benefits and pay the costs.
基金Project supported by the National Natural Science Foundation of China(Nos.61672082 and 61822101)the Beijing Municipal Natural Science Foundation,China(No.4181002)the Beihang University Innovation and Practice Fund for Graduate,China(No.YCSJ-02-2018-05)。
文摘Rule-based autonomous driving systems may suffer from increased complexity with large-scale intercoupled rules,so many researchers are exploring learning-based approaches.Reinforcement learning(RL)has been applied in designing autonomous driving systems because of its outstanding performance on a wide variety of sequential control problems.However,poor initial performance is a major challenge to the practical implementation of an RL-based autonomous driving system.RL training requires extensive training data before the model achieves reasonable performance,making an RL-based model inapplicable in a real-world setting,particularly when data are expensive.We propose an asynchronous supervised learning(ASL)method for the RL-based end-to-end autonomous driving model to address the problem of poor initial performance before training this RL-based model in real-world settings.Specifically,prior knowledge is introduced in the ASL pre-training stage by asynchronously executing multiple supervised learning processes in parallel,on multiple driving demonstration data sets.After pre-training,the model is deployed on a real vehicle to be further trained by RL to adapt to the real environment and continuously break the performance limit.The presented pre-training method is evaluated on the race car simulator,TORCS(The Open Racing Car Simulator),to verify that it can be sufficiently reliable in improving the initial performance and convergence speed of an end-to-end autonomous driving model in the RL training stage.In addition,a real-vehicle verification system is built to verify the feasibility of the proposed pre-training method in a real-vehicle deployment.Simulations results show that using some demonstrations during a supervised pre-training stage allows significant improvements in initial performance and convergence speed in the RL training stage.
