Search

The development of self-driving or autonomous vehicles has led to significant advancements in 3D object detection technologies, which are critical for the safety and efficiency of autonomous driving. Despite recent advances, several challenges remain in sensor integration, handling sparse and noisy data, and ensuring reliable performance across diverse environmental conditions. This paper comprehensively surveys state-of-the-art 3D object detection techniques for autonomous vehicles, emphasizing the importance of multi-sensor fusion techniques and advanced deep learning models. Furthermore, we present key areas for future research, including enhancing sensor fusion algorithms, improving computational efficiency, and addressing ethical, security, and privacy concerns. The integration of these technologies into real-world applications for autonomous driving is presented by highlighting potential benefits and limitations. We also present a side-by-side comparison of different techniques in a tabular form. Through a comprehensive review, this paper aims to provide insights into the future directions of 3D object detection and its impact on the evolution of autonomous driving.

Autonomous driving is an active area of research in artificial intelligence and robotics. Recent advances in deep reinforcement learning (DRL) show promise for training autonomous vehicles to handle complex real-world driving tasks. This paper reviews recent advancement on the application of DRL to highway lane change, ramp merge, and platoon coordination. In particular, similarities, differences, limitations, and best practices regarding the DRL formulations, DRL training algorithms, simulations, and metrics are reviewed and discussed. The paper starts by reviewing different traffic scenarios that are discussed by the literature, followed by a thorough review on the DRL technology such as the state representation methods that capture interactive dynamics critical for safe and efficient merging and the reward formulations that manage key metrics like safety, efficiency, comfort, and adaptability. Insights from this review can guide future research toward realizing the potential of DRL for automated driving in complex traffic under uncertainty.

Autonomous vehicles (AVs) aim to improve safety and comfort of road users while contributing to the reduction of traffic congestion, air pollution, fuel consumption, and enabling mobility and accessibility of disabled and older people. As AV technology is rapidly advancing, there is an urgent need to explore how those new mobility services will impact urban transport systems, including the users, the infrastructure, and the design of future urban areas. This paper applies a systematic review to assess the role of AVs in urban areas. It reviews 41 articles published between 2003 and 2023, and uses inductive and deductive coding approaches to identify seven themes and thirty sub-themes within the literature. The seven include: benefits, attitudes, and behaviours and user perception, climate adaptation, climate mitigation, legislation and regulations, sustainability, and infrastructure. Studies related to benefits accounted for 25% of the sample, followed by behaviours and user perception (24%) and sustainability (22%). The least amount of research has been undertaken on the role of AVs to support climate adaptation. Geographically, almost half (#22) of the papers originate within Europe, followed by America (#10) and Asia (#7). There is only limited research originating from the Global South. This systematic review sets the scene for considering how AVs in public transport can be implemented in urban areas by establishing the current state of knowledge on user attitudes, perceptions, and behaviour, the benefits of AVs, the infrastructure and legislation and regulations required for AVs, and the role AVs have in climate mitigation, adaptation, and sustainability.

There are several standards for representing and compressing video information. These standards are adapted to the vision of the human eye. Autonomous cars see and perceive objects in a different way than humans and, therefore, the common standards are not suitable for them. In this paper, we will present a way of adjusting the common standards to be appropriate for the vision of autonomous cars. The focus of this paper will be on the H.264 format, but a similar order can be adapted to other standards as well.

Abstract The flourishing realm of advanced driver-assistance systems (ADAS) as well as autonomous vehicles (AVs) presents exceptional opportunities to enhance safe driving. An essential aspect of this transformation involves monitoring driver behavior through observable physiological indicators, including the driver’s facial expressions, hand placement on the wheels, and the driver’s body postures. An artificial intelligence (AI) system under consideration alerts drivers about potentially unsafe behaviors using real-time voice notifications. This paper offers an all-embracing survey of neural network-based methodologies for studying these driver bio-metrics, presenting an exhaustive examination of their advantages and drawbacks. The evaluation includes two relevant datasets, separately categorizing ten different in-cabinet behaviors, providing a systematic classification for driver behaviors detection. The ultimate aim is to inform the development of driver behavior monitoring systems. This survey is a valuable guide for those dedicated to enhancing vehicle safety and preventing accidents caused by careless driving. The paper’s structure encompasses sections on autonomous vehicles, neural networks, driver behavior analysis methods, dataset utilization, and final findings and future suggestions, ensuring accessibility for audiences with diverse levels of understanding regarding the subject matter.

Purpose: This paper aims to explore the potential impact of autonomous vehicles (AVs) on urban planning, sustainable urban development, and tourism. Methodology: The paper is a conceptual study that reviews and synthesizes existing literature on AVs, urban planning, and tourism. It also uses case studies to illustrate the potential effects of AVs. Results: The widespread adoption of AVs is likely to have significant implications for urban planning, including changes in land use, infrastructure design, and transportation patterns. AVs may also contribute to sustainable urban development by reducing traffic congestion and air pollution. In the tourism sector, AVs could lead to spatial changes, new social inequalities, and changes in the overnight visitor economy. Theoretical contribution: The paper contributes to the understanding of the complex interplay between AVs, urban planning, and tourism. It highlights the need for urban planners and tourism stakeholders to consider the potential impact of AVs in their decision-making processes. Practical implications: The paper provides practical insights for urban planners, tourism stakeholders, and policymakers on how to prepare for and adapt to the widespread use of AVs. It also emphasizes the importance of considering the potential benefits and challenges of AVs in the context of specific cities and tourism destinations.

Fog computing (FC) is considered one of the smart and effective solutions for service provisioning to the Internet of Everything (IoE) layer. IoE layer means the platforms including homes, vehicles, infrastructures, and alike others. FC supports the IoE layer in a smart and charismatic manner by providing services near the smart devices, from vehicles to other mobilities, and fitting the response and delay time requirements. In the proposed paper, the authors focused on discussing vehicular fog computing (VFC) and how FC supports smart vehicles operating on the IoT layer. In the previous decade, scheduling algorithms are proposed by different scholars such as RTFRS, FCFS, ILP, and others to improve the working and efficacy of VFC. In the proposed paper, an analysis is done on the VFC scheduling algorithms published in the last three years in accordance with areas such as traditional, meta-heuristic, deep reinforcement learning, fuzzy logic, heuristic, and integer linear programming. The analysis is done to examine the areas of scheduling such as task scheduling, resource allocation, and others on which the existing solutions are working. This helps in inspecting the gap across which in future further work can be done.

Abstract The integration of IoT systems into automotive vehicles has raised concerns associated with intrusion detection within these systems. Vehicles equipped with a controller area network (CAN) control several systems within a vehicle where disruptions in function can lead to significant malfunctions, injuries, and even loss of life. Detecting disruption is a primary concern as vehicles move to higher degrees of autonomy and the possibility of self-driving is explored. Tackling cyber-security challenges within CAN is essential to improve vehicle and road safety. Standard differences between different manufacturers make the implementation of a discreet system difficult; therefore, data-driven techniques are needed to tackle the ever-evolving landscape of cyber security within the automotive field. This paper examines the possibility of using machine learning classifiers to identify cyber assaults in CAN systems. To achieve applicability, we cover two classifiers: extreme gradient boost and K-nearest neighbor algorithms. However, as their performance hinges on proper parameter selection, a modified metaheuristic optimizer is introduced as well to tackle parameter optimization. The proposed approach is tested on a publicly available dataset with the best-performing models exceeding 89% accuracy. Optimizer outcomes have undergone rigorous statistical analysis, and the best-performing models were subjected to analysis using explainable artificial intelligence techniques to determine feature impacts on the best-performing model.

The implementation of object detection for autonomous vehicles is essential as it is necessary to identify common object on the street so proper response could be designed. While single stage object may be smaller in computations, two-stage object detection is preferred due to the ability to localize the object. In this paper, we propose to use Faster R-CNN with VGG-16 backbone for detections of object on the street. We evaluate the method with open image subset by selecting objects that are common on street. We explore several hyper-parameters setup such as learning rate and the number of ROI regions to find the optimum set-up. We found that the use of learning rate 10-6 with Adam optimizer to be the optimum value for this task. We also found that increasing the number of ROI may benefit the performance. This shows that there is potential for getting a higher mAP with increase the amount of RoI.

Autonomous vehicles are at the forefront of future transportation solutions, but their success hinges on reliable perception. This review paper surveys image processing and sensor fusion techniques vital for ensuring vehicle safety and efficiency. The paper focuses on object detection, recognition, tracking, and scene comprehension via computer vision and machine learning methodologies. In addition, the paper explores challenges within the field, such as robustness in adverse weather conditions, the demand for real-time processing, and the integration of complex sensor data. Furthermore, we examine localization techniques specific to autonomous vehicles. The results show that while substantial progress has been made in each subfield, there are persistent limitations. These include a shortage of comprehensive large-scale testing, the absence of diverse and robust datasets, and occasional inaccuracies in certain studies. These issues impede the seamless deployment of this technology in real-world scenarios. This comprehensive literature review contributes to a deeper understanding of the current state and future directions of image processing and sensor fusion in autonomous vehicles, aiding researchers and practitioners in advancing the development of reliable autonomous driving systems.

Autonomous vehicles (AVs), defined as vehicles capable of navigation and decision-making independent of human intervention, represent a revolutionary advancement in transportation technology. These vehicles operate by synthesizing an array of sophisticated technologies, including sensors, cameras, GPS, radar, light imaging detection and ranging (LiDAR), and advanced computing systems. These components work in concert to accurately perceive the vehicle’s environment, ensuring the capacity to make optimal decisions in real-time. At the heart of AV functionality lies the ability to facilitate intercommunication between vehicles and with critical road infrastructure—a characteristic that, while central to their efficacy, also renders them susceptible to cyber threats. The potential infiltration of these communication channels poses a severe threat, enabling the possibility of personal information theft or the introduction of malicious software that could compromise vehicle safety. This paper offers a comprehensive exploration of the current state of AV technology, particularly examining the intersection of autonomous vehicles and emotional intelligence. We delve into an extensive analysis of recent research on safety lapses and security vulnerabilities in autonomous vehicles, placing specific emphasis on the different types of cyber attacks to which they are susceptible. We further explore the various security solutions that have been proposed and implemented to address these threats. The discussion not only provides an overview of the existing challenges but also presents a pathway toward future research directions. This includes potential advancements in the AV field, the continued refinement of safety measures, and the development of more robust, resilient security mechanisms. Ultimately, this paper seeks to contribute to a deeper understanding of the safety and security landscape of autonomous vehicles, fostering discourse on the intricate balance between technological advancement and security in this rapidly evolving field.

This paper presents the implementation of an innovative solution based on heterogeneous autonomous vehicles to tackle maritime pollution (in particular, oil spills). This solution is based on native microbial consortia with bioremediation capacity, and the adaptation of air and surface autonomous vehicles for in situ release of autochthonous microorganisms (bioaugmentation) and nutrients (biostimulation). By doing so, these systems can be applied as the first line of the response to pollution incidents from several origins that may occur inside ports, around industrial and extraction facilities, or in the open sea during transport activities in a fast, efficient, and low-cost way. The paper describes the work done in the development of a team of autonomous vehicles able to carry as payload, native organisms to naturally degrade oil spills (avoiding the introduction of additional chemical or biological additives), and the development of a multi-robot framework for efficient oil spill mitigation. Field tests have been performed in Portugal and Spain’s harbors, with a simulated oil spill, and the coordinate oil spill task between the autonomous surface vehicle (ASV) ROAZ and the unmanned aerial vehicle (UAV) STORK has been validated.

To realize accurate environment perception, which is the technological key to enabling autonomous vehicles to interact with their external environments, it is primarily necessary to solve the issues of object detection and tracking in the vehicle-movement process. Multi-sensor fusion has become an essential process in efforts to overcome the shortcomings of individual sensor types and improve the efficiency and reliability of autonomous vehicles. This paper puts forward moving object detection and tracking methods based on LiDAR—camera fusion. Operating based on the calibration of the camera and LiDAR technology, this paper uses YOLO and PointPillars network models to perform object detection based on image and point cloud data. Then, a target box intersection-over-union (IoU) matching strategy, based on center-point distance probability and the improved Dempster–Shafer (D–S) theory, is used to perform class confidence fusion to obtain the final fusion detection result. In the process of moving object tracking, the DeepSORT algorithm is improved to address the issue of identity switching resulting from dynamic objects re-emerging after occlusion. An unscented Kalman filter is utilized to accurately predict the motion state of nonlinear objects, and object motion information is added to the IoU matching module to improve the matching accuracy in the data association process. Through self-collected data verification, the performances of fusion detection and tracking are judged to be significantly better than those of a single sensor. The evaluation indexes of the improved DeepSORT algorithm are 66% for MOTA and 79% for MOTP, which are, respectively, 10% and 5% higher than those of the original DeepSORT algorithm. The improved DeepSORT algorithm effectively solves the problem of tracking instability caused by the occlusion of moving objects.

The deployment of intelligent transportation is still in its early stages and there are many challenges that need to be addressed before it can be widely adopted. Autonomous vehicles are a class of intelligent transportation that is rapidly developing, and they are being deployed in selected cities. A combination of advanced sensors, machine learning algorithms, and artificial intelligence are being used in these vehicles to perceive their environment, navigate, and make the right decisions. These vehicles leverage extensive data sourced from various sensors and computers integrated into the vehicle. Hence, massive computational power is required to process the information from various built-in sensors in milliseconds to make the right decision. The power required by the sensors and the use of additional computational power increases the energy consumption, and, hence, could reduce the range of the autonomous electric vehicle relative to a standard electric car and lead to additional emissions. A number of review papers have highlighted the environmental benefits of autonomous vehicles, focusing on aspects like optimized driving, improved route selection, fewer stops, and platooning. However, these reviews often overlook the significant energy demands of the hardware systems—such as sensors, computers, and cameras—necessary for full autonomy, which can decrease the driving range of electric autonomous vehicles. Additionally, previous studies have not thoroughly examined the data processing requirements in these vehicles. This paper provides a more detailed review of the volume of data and energy usage by various sensors and computers integral to autonomous features in electric vehicles. It also discusses the effects of these factors on vehicle range and emissions. Furthermore, the paper explores advanced technologies currently being developed by various industries to enhance processing speeds and reduce energy consumption in autonomous vehicles.

Driver assistance systems have started becoming a key differentiator in automotive space and all major automotive manufacturers have such systems with various capabilities and stages of implementation. The main building blocks of such systems are similar in nature and one of the major building blocks is road lane detection. Even though lane detection technology has been around for decades, it is still an ongoing area of research and there are still several improvements and optimizations that are possible. This paper offers an Optimized Dynamic Origin Technique (Optimized DOT) for lane detection. The proposed optimization algorithm of optimized DOT gives better results in performance and accuracy compared to other methods of lane detection. Analysis of proposed optimized DOT with various edge detection techniques, various threshold levels, various sample dataset and various lane detection methods were done and the results are discussed in this paper. The proposed optimized DOT lane detection average processing time increases by 9.21 % when compared to previous Dynamic Origin Technique (DOT) and 59.09 % compared to traditional hough transform.

Connected and automated vehicles (CAVs) are expected to reshape traffic flow dynamics and present new challenges and opportunities for traffic flow modeling. While numerous studies have proposed optimal modeling and control strategies for CAVs with various objectives (e.g., traffic efficiency and safety), there are uncertainties about the flow dynamics of CAVs in real-world traffic. The uncertainties are especially amplified for mixed traffic flows, consisting of CAVs and human-driven vehicles, where the implications can be significant from the continuum-modeling perspective, which aims to capture macroscopic traffic flow dynamics based on hyperbolic systems of partial differential equations. This paper aims to highlight and discuss some essential problems in continuum modeling of real-world freeway traffic flows in the era of CAVs. We first provide a select review of some existing continuum models for conventional human-driven traffic as well as the recent attempts for incorporating CAVs into the continuum-modeling framework. Wherever applicable, we provide new insights about the properties of existing models and revisit their implications for traffic flows of CAVs using recent empirical observations with CAVs and the previous discussions and debates in the literature. The paper then discusses some major problems inherent to continuum modeling of real-world (mixed) CAV traffic flows modeling by distinguishing between two major research directions: (a) modeling for explaining purposes, where making reproducible inferences about the physical aspects of macroscopic properties is of the primary interest, and (b) modeling for practical purposes, in which the focus is on the reliable predictions for operation and control. The paper proposes some potential solutions in each research direction and recommends some future research topics.

The integration of Mixed Reality (MR) technology into Autonomous Vehicles (AVs) has ushered in a new era for the automotive industry, offering heightened safety, convenience, and passenger comfort. However, the substantial and varied data generated by MR-Connected AVs (MR-CAVs), encompassing both highly dynamic and static information, presents formidable challenges for efficient data management and retrieval. In this paper, we formulate our indexing problem as a constrained optimization problem, with the aim of maximizing the utility function that represents the overall performance of our indexing system. This optimization problem encompasses multiple decision variables and constraints, rendering it mathematically infeasible to solve directly. Therefore, we propose a heuristic algorithm to address the combinatorial complexity of the problem. Our heuristic indexing algorithm efficiently divides data into highly dynamic and static categories, distributing the index across Roadside Units (RSUs) and optimizing query processing. Our approach takes advantage of the computational capabilities of edge servers or RSUs to perform indexing operations, thereby shifting the burden away from the vehicles themselves. Our algorithm strategically places data in the cache, optimizing cache hit rate and space utilization while reducing latency. The quantitative evaluation demonstrates the superiority of our proposed scheme, with significant reductions in latency (averaging 27%−49.25%), a 30.75% improvement in throughput, a 22.50% enhancement in cache hit rate, and a 32%−50.75% improvement in space utilization compared to baseline schemes.

In the near future, fully autonomous vehicles may revolutionise mobility and contribute to the development of the smart city concept. In this work, we assume that vehicles are not only fully autonomous but also centrally controlled by a single operator, who can also define the traffic light control parameters at intersections. With the aim of optimising the system to achieve a global optimum, the operator can define both the routes of the fleet of vehicles and the traffic light control parameters. This paper proposes a model for the joint optimisation of traffic light control parameters and autonomous vehicle routes to achieve the system optimum. The model, which is solved using a gradient algorithm, is tested on networks of different sizes. The results obtained show the validity of the proposed approach and the advantages of centralised management of vehicles and intersection control parameters.

The integration of intelligent transportation systems (ITS) in urban infrastructure has increased significantly, and one of the most notable examples is the development of autonomous vehicles (AVs). AVs have become a solution to various driving problems, such as performing complete overtaking maneuvers (OM). These maneuvers are considered one of the most difficult to carry out. Although there are many papers on OM maneuvers with AVs, not all of these studies focus on the performance of complete OM. Therefore, a comprehensive and scientific exploration of the analysis of complete OM with AVs is lacking. This study aims to address this gap through a systematic review following the PRISMA protocol as methodology, examining 51 articles published between 2008 and 2024 in the Science Direct, Scopus, and Web of Science (WOS) databases. The results showed that methodologies such as Model Predictive Control (MPC), Fuzzy Control (FC), and sigmoidal functions are used most to perform complete OM with AVs. MPC is the most relevant methodology due to its capability to be combined with other control systems and its predictive ability. FC and sigmoidal functions are also appropriate for dealing with inaccuracies and non-linear features associated with overtaking maneuvers. However, there are still complications related to computational complexity and sensor limitations. Future studies should consider and integrate the development of comprehensive systems that combine multiple real-time control methodologies and offer a robust combination of sensors. This review contributes to teaching studies that reveal promising opportunities for complete OM with AVs research and provide access to methodologies that could be optimized based on technological advances and emerging needs of the ITS sector. Addressing these knowledge gaps is essential to achieving safer and more efficient overtaking maneuvers by AVs.

The cooperative, connected, and automated mobility (CCAM) infrastructure plays a key role in understanding and enhancing the environmental perception of autonomous vehicles (AVs) driving in complex urban settings. However, the deployment of CCAM infrastructure necessitates the efficient selection of the computational processing layer and deployment of machine learning (ML) and deep learning (DL) models to achieve greater performance of AVs in complex urban environments. In this paper, we propose a computational framework and analyze the effectiveness of a custom-trained DL model (YOLOv8) when deployed in diverse devices and settings at the vehicle-edge-cloud-layered architecture. Our main focus is to understand the interplay and relationship between the DL model’s accuracy and execution time during deployment at the layered framework. Therefore, we investigate the trade-offs between accuracy and time by the deployment process of the YOLOv8 model over each layer of the computational framework. We consider the CCAM infrastructures, i.e., sensory devices, computation, and communication at each layer. The findings reveal that the performance metrics results (e.g., 0.842 mAP@0.5) of deployed DL models remain consistent regardless of the device type across any layer of the framework. However, we observe that inference times for object detection tasks tend to decrease when the DL model is subjected to different environmental conditions. For instance, the Jetson AGX (non-GPU) outperforms the Raspberry Pi (non-GPU) by reducing inference time by 72%, whereas the Jetson AGX Xavier (GPU) outperforms the Jetson AGX ARMv8 (non-GPU) by reducing inference time by 90%. A complete average time comparison analysis for the transfer time, preprocess time, and total time of devices Apple M2 Max, Intel Xeon, Tesla T4, NVIDIA A100, Tesla V100, etc., is provided in the paper. Our findings direct the researchers and practitioners to select the most appropriate device type and environment for the deployment of DL models required for production.

Enhancing the environmental perception of autonomous vehicles (AVs) in intelligent transportation systems requires computer vision technology to be effective in detecting objects and obstacles, particularly in adverse weather conditions. Adverse weather circumstances present serious difficulties for object-detecting systems, which are essential to contemporary safety procedures, infrastructure for monitoring, and intelligent transportation. AVs primarily depend on image processing algorithms that utilize a wide range of onboard visual sensors for guidance and decisionmaking. Ensuring the consistent identification of critical elements such as vehicles, pedestrians, and road lanes, even in adverse weather, is a paramount objective. This paper not only provides a comprehensive review of the literature on object detection (OD) under adverse weather conditions but also delves into the ever-evolving realm of the architecture of AVs, challenges for automated vehicles in adverse weather, the basic structure of OD, and explores the landscape of traditional and deep learning (DL) approaches for OD within the realm of AVs. These approaches are essential for advancing the capabilities of AVs in recognizing and responding to objects in their surroundings. This paper further investigates previous research that has employed both traditional and DL methodologies for the detection of vehicles, pedestrians, and road lanes, effectively linking these approaches with the evolving field of AVs. Moreover, this paper offers an in-depth analysis of the datasets commonly employed in AV research, with a specific focus on the detection of key elements in various environmental conditions, and then summarizes the evaluation matrix. We expect that this review paper will help scholars to gain a better understanding of this area of research.

This paper proposes a spatiotemporal architecture with a deep neural network (DNN) for road surface conditions and types classification using LiDAR for autonomous emergency braking (AEB) systems. It is known that LiDAR provides information on the reflectivity and number of point clouds depending on a road surface. Thus, this paper utilizes the characteristics of LiDAR and the vehicle’s speed obtained from in-vehicle sensors for classifying front road surface conditions for the AEB system application. First, we divided the front road area into four subregions to use spatial information from the vehicle’s speed. Second, we constructed feature vectors using each subregion’s reflectivity, number of point clouds, and in-vehicle information. Third, the DNN classifies road surface conditions and types for each subregion. Finally, the output of the DNN feeds into the spatiotemporal process to make the final classification reflecting vehicle speed and probability given by the outcomes of softmax functions of the DNN output layer. To validate the effectiveness of the proposed method, we performed a comparative study with five other algorithms. With the proposed DNN, we obtained the highest accuracy of 98.0% and 98.6% for two subregions near the vehicle. In addition, we implemented the proposed method on the NVIDIA Jetson TX2 board to confirm that it is applicable in real-time.

The advancement of Artificial Intelligence (AI) technology has accelerated the development of several systems that are elicited from it. This boom has made the systems vulnerable to security attacks and allows considerable bias in order to handle errors in the system. This puts humans at risk and leaves machines, robots, and data defenseless. Trustworthy AI (TAI) guarantees human value and the environment. In this paper, we present a comprehensive review of the state-of-the-art on how to build a Trustworthy and eXplainable AI, taking into account that AI is a black box with little insight into its underlying structure. The paper also discusses various TAI components, their corresponding bias, and inclinations that make the system unreliable. The study also discusses the necessity for TAI in many verticals, including banking, healthcare, autonomous system, and IoT. We unite the ways of building trust in all fragmented areas of data protection, pricing, expense, reliability, assurance, and decision-making processes utilizing TAI in several diverse industries and to differing degrees. It also emphasizes the importance of transparent and post hoc explanation models in the construction of an eXplainable AI and lists the potential drawbacks and pitfalls of building eXplainable AI. Finally, the policies for developing TAI in the autonomous vehicle construction sectors are thoroughly examined and eclectic ways of building a reliable, interpretable, eXplainable, and Trustworthy AI systems are explained to guarantee safe autonomous vehicle systems.

Validation and Verification (V&V) of Artificial Intelligence (AI) based cyber physical systems such as Autonomous Vehicles (AVs) is currently a vexing and unsolved problem. AVs integrate subsystems in areas such as detection, sensor fusion, localization, perception, and path planning. Each of these subsystems contains significant AI content integrated with traditional hardware and software components. The complexity for validating even a subsystem is daunting and the task of validating the whole system is nearly impossible. Fundamental research in advancing the state-of-the-art for AV V&V is required. However, for V&V researchers, it is exceedingly difficult to make progress because of the massive infrastructure requirements to demonstrate the viability of any solution. This paper presents PolyVerif, the world’s first open-source solution focused on V&V researchers with the objective of accelerating the state-of-the-art for AV V&V research. PolyVerif provides an AI design and verification framework consisting of a digital twin creation process, an open-source AV engine, access to several open-source physics based simulators, and open-source symbolic test generation engines. PolyVerif’s objective is to arm V&V researchers with a framework which extends the state-of-the-art on any one of the many major axes of interest and use the remainder of the infrastructure to quickly demonstrate the viability of their solution. Given its open-source nature, researchers can also contribute their innovations to the project. Using this critical property of open-source environments, the innovation rate of the whole research community to solve these vexing issues can be greatly accelerated. Finally, the paper also presents results from several projects which have used PolyVerif.

The overall goal of the paper is to derive a kinematic model for vehicle path-following systems, where the pitch and yaw angles $(\theta, \psi)$ together with the surge velocity $u$ can be treated as control inputs. Then the outer control loop can be designed as a nonlinear path-following guidance law. At the same time, the inner control loops can be stabilized using commercial autopilot systems to control the pitch and yaw angles. The main result of the paper is a novel kinematic amplitude-phase representation of the North-East-Down (NED) positional rates, which can replace the classical Euler angle rotation matrix representation. The proposed kinematic model gives equivalent NED positional rates as the rotation matrix representation for all combinations of the Euler angles and the linear velocities. The main advantage of the kinematic amplitude-phase representation is the design of vehicle guidance laws using nonlinear control theory and Lyapunov stability analysis. Furthermore, it is shown that nonlinear guidance laws can be designed for path following and that the proposed methods guarantee that the origins are uniformly semiglobally exponentially stable (USGES). A case study of an unmanned surface vehicle (USV) demonstrates how a path-following control system can be designed using the amplitude-phase representation.

Abstract In the near future, autonomous vehicles (AVs) may cohabit with human drivers in mixed traffic. This cohabitation raises serious challenges, both in terms of traffic flow and individual mobility, as well as from the road safety point of view. Mixed traffic may fail to fulfill expected security requirements due to the heterogeneity and unpredictability of human drivers, and autonomous cars could then monopolize the traffic. Using multi-agent reinforcement learning (MARL) algorithms, researchers have attempted to design autonomous vehicles for both scenarios, and this paper investigates their recent advances. We focus on articles tackling decision-making problems and identify four paradigms. While some authors address mixed traffic problems with or without social-desirable AVs, others tackle the case of fully-autonomous traffic. While the latter case is essentially a communication problem, most authors addressing the mixed traffic admit some limitations. The current human driver models found in the literature are too simplistic since they do not cover the heterogeneity of the drivers’ behaviors. As a result, they fail to generalize over the wide range of possible behaviors. For each paper investigated, we analyze how the authors formulated the MARL problem in terms of observation, action, and rewards to match the paradigm they apply.

As the complexity of autonomous vehicles (AVs) continues to increase and artificial intelligence algorithms are becoming increasingly ubiquitous, a novel safety concern known as the safety of the intended functionality (SOTIF) has emerged, presenting significant challenges to the widespread deployment of AVs. SOTIF focuses on issues arising from the functional insufficiencies of the AVs’ intended functionality or its implementation, apart from conventional safety considerations. From the systems engineering standpoint, this study offers a comprehensive exploration of the SOTIF landscape by reviewing academic research, practical activities, challenges, and perspectives across the development, verification, validation, and operation phases. Academic research encompasses system-level SOTIF studies and algorithm-related SOTIF issues and solutions. Moreover, it encapsulates practical SOTIF activities undertaken by corporations, government entities, and academic institutions spanning international and Chinese contexts, focusing on the overarching methodologies and practices in different phases. Finally, the paper presents future challenges and outlook pertaining to the development, verification, validation, and operation phases, motivating stakeholders to address the remaining obstacles and challenges.

ABSTRACTThis paper investigates elements of trust in autonomous vehicles (AVs). We contextualise autonomous vehicles as part of people's everyday settings to extend previous understandings of trust and explore trust in autonomous vehicles in concrete social contexts. We conducted online co-creation workshops with 22 participants, using design probes to explore trust and AVs in relation to people's everyday lives. Using a socio-technical perspective, we show how trust and acceptance depend not only on the underlying AV technology but also – if not more so – on human-to-human relationships and real-life social circumstances. We argue that when investigating issues of trust and automation, the scope of analysis needs to be broadened to include a more complex socio-technical set of (human and non-human) agents, to extend from momentary human-computer interactions to a wider timescale, and be situated in concrete spaces, social networks, and situations.

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.

Ride-hailing has expanded substantially around the globe over the last decade and is likely to be an integral part of future transportation systems. We perform a systematic review of the literature on energy and environmental impacts of ride-hailing. In general, empirical papers find that ride-hailing has increased congestion, vehicle miles traveled, and emissions. However, theoretical papers overwhelmingly point to the potential for energy and emissions reductions in a future with increased electrification and pooling. Future research addressing the gap between observed and predicted impacts is warranted.

AVs are increasingly becoming present on public roads, the ethics of which have captured the publics attention. This study represents the first ever investigation into the opinion of AV development experts on the ethics of programming AVs in collision scenarios. The study makes use of a qualitative research model. A sample of 24 Swiss experts were interviewed using semi-structured interviews. The majority of experts were directly involved in the development of AVs and represented both research, private, and public sectors as well as national regulatory bodies. Three core themes emerged from the data. 1) Experts were keenly aware of the ethical challenges involved in AVs on public roads, including in collision situations. 2) Experts felt a moral responsibility for how AVs are programmed and developed. However, experts’ moral framework was not well developed with many experts stating that their own personal moral framework should not be used to program motion planning. 3) Experts saw a need for an ethical framework to guide the development of AVs. The paper concludes that it is clear experts are keenly aware of the ethics involved in AVs on public roads, and in particular collision scenarios. They feel a sense of responsibility for how AVs are programmed but do not feel ethically well-equipped themselves. Experts would, therefore, appreciate an ethical framework that would assist the development of these algorithms. This framework may be driven by either industry or government but should be clear and simple. We recommend countries like Switzerland develop such a framework.

This paper presents an analysis and implementation of a robust autonomous driving system for an electric passenger shuttle in shared spaces. We present results of a risk assessment for our vehicle scenario and develop a flexible architecture that integrates safety features and optimises open-source software, facilitating research and operational functionality. Identifying limitations of the Robot Operating System (ROS) framework, we incorporate our own control measures for autonomous, unsupervised operation with enhanced intelligence. The study emphasizes algorithm selection based on application requirements to ensure optimal performance. We discuss system improvements, including monitoring node implementation and localization algorithm selection. Future work should explore transitioning to a real-time operating system (RTOS) and establishing standardized software engineering practices for consistent reliability. Our findings contribute to effective autonomous shuttle systems in shared spaces, promoting safer and more reliable transportation solutions.

This paper presents an X-in-Loop test platform designed for the Proof-of-Concept testing of intelligent braking ECPBS in commercial vehicle. Firstly, the concept of intelligent braking is introduced, outlining its research scope and defining the necessary test requirements for the proof of concept. Based on these experimental criteria, the composition and operational principles of the Proof-of-Concept experimental platform are developed in accordance with X-in-Loop testing methodologies. The various subsystems and functionalities of the X-in-Loop Proof-of-Concept test platform are subsequently detailed. The working principle of the X-in-Loop Proof-of-Concept test platform is thoroughly explained using a loop example, and its workflow is presented. Finally, the platform’s fundamental functionalities are validated through a vehicle braking test conducted under specific working conditions, followed by an analysis of its potential applications.

This paper presents a formulation for deterministically calculating optimized paths for a multi-agent system consisting of heterogeneous vehicles. The key idea is the calculation of the shortest time for each agent to reach every grid point from its known initial position. Such arrival time map is efficiently computed using the Fast Marching Method (FMM), a computational algorithm originally designed for solving boundary value problems of the Eikonal equation. By leveraging the FMM, we demonstrate that the minimal time rendezvous point and paths for all member vehicles can be uniquely determined with minimal computational overhead. The scalability and adaptability of the present method during online execution are investigated, followed by a comparison with a baseline method that highlights the effectiveness of the proposed approach. Then, the potential of the present method is showcased through a virtual rendezvous scenario involving the coordination of a ship, an underwater vehicle, an aerial vehicle, and a ground vehicle, all converging at the optimal location within the Tampa Bay area in minimal time. The results show that the developed framework can efficiently construct continuous paths of heterogeneous vehicles by accommodating operational constraints via an FMM algorithm.

Fifth Generation (5G) enabled Vehicle to Everything (V2X) communication emerges as a promising solution for seamless communication in Vehicular Ad hoc Networks (VANET) comprising both driver-based and autonomous vehicles to overcome security threats. The existing approaches focused on either vehicle or message authentication using blockchain technology; however, doesn’t achieve overall security and face scalability issues due to the linearity of blockchain. In this paper, the network is initially partitioned into M $\times $ M grid structures, and the Edge Assisted Roadside Units (ERSU) form a network graph using an Arithmetic Optimization Algorithm (AOA) with entities in the grid. The Bayesian DAG blockchain-based decentralized authentication of entities is carried out to mitigate the scalability issues and reduce the computational complexity of the Trusted Authorities (TA). The anonymity of the entities is preserved by generating the Virtual ID by means of the Enhanced Blowfish Algorithm (EBA). The proposed approach is simulated using OMNET++ and SUMO simulation tools and evaluated with several performance metrics. The results show that our work outperforms the existing approaches in all the metrics, making it a valuable candidate for ensuring the security of 5G-V2X communication.

This paper presents a novel framework for socially aware path-planning in autonomous vehicles, integrating Social Value Orientation (SVO) within Artificial Potential Fields (APF) and employing Type-2 Fuzzy Logic for robust SVO approximation. By incorporating an adaptive gradient descent algorithm and leveraging a Type-2 fuzzy system for dynamic modeling of social psychology in vehicular navigation, we enhance autonomous vehicles’ ability to interpret and react to social cues in real-time traffic scenarios. Our approach significantly improves interaction with human road users, ensuring safer and more efficient navigation. The proposed model addresses the limitations of traditional APFs, such as local minima issues, by incorporating dynamic enhanced firework algorithms and resistance networks. It also considers vehicle dynamics, including nonholonomic constraints and tire forces, using a bicycle model for realistic trajectory planning. We introduce a comprehensive set of social cues for pedestrians and vehicles, operationalized through interval type-2 fuzzy system (IT2FS) approximation, to accurately estimate SVO and adjust AV behavior accordingly. Validation is conducted through extensive simulations in a realistic environment using the CARLA simulator, demonstrating the effectiveness of our socially intelligent path-planning mechanism in diverse driving situations. The results show a significant improvement in AV performance, with a 2.93% more altruistic estimation for the vehicle in the right lane and a 1.85% more altruistic estimation for the immobile vehicle. Additionally, the system demonstrated smoother acceleration and steering profiles, reducing peak longitudinal acceleration from $4.181~m/s^{2}$ to $0.196~m/s^{2}$ and improving overall driving stability. This framework enhances autonomous vehicles’ safety, efficiency, and social acceptability, contributing to their successful integration into urban traffic systems.

In this paper, an automated and real-time anomaly detection approach for sensors of autonomous vehicles called ARAD is presented. Automated vehicles gather environmental information through their diverse built-in sensors thus the correctness of this data affects the system’s reliability, directly. Accordingly, anomaly detection schemes are employed to guarantee the correctness of the sensors’ data. Moreover, due to the necessity of real-time operation in automated vehicles, the response time of the anomaly detection unit is important along with its precision. To this aim, in our proposed ARAD a lightweight and hierarchical architecture to detect and classify the anomalies based on their types is employed. Moreover, to enhance the detection capability, ARAD utilizes the data diversity property based on the sequence prediction scheme. After anomaly detection, ARAD mitigates and removes them from the system’s input by its rule-based engine. To meet the precision and real-time requirements of the anomaly detection unit in autonomous vehicles, ARAD has a lightweight sequence prediction structure based on statistical and data-driven methods. To evaluate the effectiveness of our proposed ARAD, several experiments are performed and a performance measurement metric called FoC is proposed to study the contradicted effects of precision and real-time operation in terms of computation overhead, simultaneously. Based on these experiments, ARAD is capable of detecting anomalies efficiently with precision and recall of $84.6~\%$ and 87%, respectively in real-time while applying low overhead to the system. It also shows 75.6% improvement in terms of computation cost over related methods.

In the domain of pedestrian trajectory prediction(PTP) from a roadbed perspective, the visibility of pedestrian feature points is inevitably compromised by external noise interference, impacting both pedestrian pose estimation(PPE) and PTP. This paper presents an innovative model for PTP. The model not only tackles noise interference but also takes into account the inherent correlation between pedestrian pose features and trajectory coordinates. To tackle the challenge of noise interference during pedestrian crossing, we reframe it as an anomalous feature detection problem using the Graph Deviation Network (GDN). Subsequently, we enhance the Long Short-Term Memory (LSTM) module by incorporating a time-domain anomaly suppression module, resulting in the development of an Anomaly Inhibition-LSTM (AI-LSTM) with robust noise suppression capabilities. Finally, by integrating the predicted values of behavioral pose and trajectory position, considering the behavioral characteristic relationship resolved by the GDN algorithm, we achieve accurate prediction and pose estimation of pedestrian crossing trajectories amidst noise interference. Experimental results demonstrate superior performance of our algorithm in the PPE task when compared to GDN and LSTM algorithms. In the PTP task, our algorithm exhibits performance comparable to the Transformer-based method, with the added advantage of improved interpretability.

When car following is controlled by human drivers (i.e., by their behavior), the traffic system does not meet stability conditions. In order to ensure the safety and reliability of self-driving vehicles, an additional hazard warning system should be incorporated into the adaptive control system in order to prevent any possible unavoidable collisions. The time to contact is a reasonable indicator of potential collisions. This research examines systems and solutions developed in this field to determine collision times and uses various alarms in self-driving cars that prevent collisions with obstacles. In the proposed analysis, we have tried to classify the various techniques and methods, including image processing, machine learning, deep learning, sensors, and so on, based on the solutions we have investigated. Challenges, future research directions, and open problems in this important field are also highlighted in the paper.

Intelligent Transportation Systems (ITS) operate within a highly intricate and dynamic environment characterized by complex spatial and temporal dynamics at various scales, further compounded by fluctuating conditions influenced by external factors such as social events, holidays, and weather. Navigating the intricacies of modeling the intricate interaction among these elements, creating universal representations, and employing them to address transportation issues. Yet, these intricacies comprise just one facet of the multifaceted trials confronting contemporary ITS. This paper offers an all-encompassing survey exploring Deep learning (DL) utilization in ITS, primarily focusing on practitioners' methodologies to address these multifaceted challenges. The emphasis lies on the architectural and problem-specific factors that guide the formulation of innovative solutions. In addition to shedding light on the state-of-the-art DL algorithms, we also explore potential applications of DL and large language models (LLMs) in ITS, including traffic flow prediction, vehicle detection and classification, road condition monitoring, traffic sign recognition, and autonomous vehicles. Besides, we identify several future challenges and research directions that can push the boundaries of ITS, including the critical aspects, including transfer learning, hybrid models, privacy and security, and ultra-reliable low-latency communication. Our aim for this survey is to bridge the gap between the burgeoning DL and transportation communities. By doing so, we aim to facilitate a deeper comprehension of the challenges and possibilities within this field. We hope that this effort will inspire further exploration of fresh perspectives and issues, which, in turn, will play a pivotal role in shaping the future of transportation systems.

Optimizing traffic dynamics in an evolving transportation landscape is crucial, particularly in scenarios where autonomous vehicles (AVs) with varying levels of autonomy coexist with human-driven cars. While optimizing Reinforcement Learning (RL) policies for such scenarios is becoming more and more common, little has been said about realistic evaluations of such trained policies. This paper presents an evaluation of the effects of AVs penetration among human drivers in a roundabout scenario, considering both quantitative and qualitative aspects. In particular, we learn a policy to minimize traffic jams (i.e., minimize the time to cross the scenario) and to minimize pollution in a roundabout in Milan, Italy. Through empirical analysis, we demonstrate that the presence of AVs can reduce time and pollution levels. Furthermore, we qualitatively evaluate the learned policy using a cutting-edge cockpit to assess its performance in near-real-world conditions. To gauge the practicality and acceptability of the policy, we conduct evaluations with human participants using the simulator, focusing on a range of metrics like traffic smoothness and safety perception. In general, our findings show that human-driven vehicles benefit from optimizing AVs dynamics. Also, participants in the study highlight that the scenario with 80% AVs is perceived as safer than the scenario with 20%. The same result is obtained for traffic smoothness perception.

Steering angle controller is a core module of autonomous vehicles, where a slight miscalculation can cause severe accidents. Following safety precautions, development of robust and precise steering angle predictor is an active area of research. However, existing simulator based steering angle predictors lack in predictive performance and have not been evaluated on same benchmark datasets. Furthermore, most of them are evaluated on simulated datasets and their potential on real-world data as well as in cross-domain evaluation of both types data (real-world, simulated) remain unexplored. To accelerate and expedite research related to steering angle prediction contributions of this paper are manifold: 1) It presents two benchmark datasets that are developed using Udacity and CARLA simulators. 2) Following the need for comparative study, over both simulated datasets, it benchmarks the performance of existing predictors under 2 different evaluation settings namely: same-track and cross-track evaluation. 3) In cross-domain evaluation, it explores generalization potential of predictors by training predictors on simulated data and evaluating them on 2 real-world datasets and vice versa. 4) It presents a robust and precise steering angle predictor that utilizes skip connections for proper gradient flow among different convolutional layers. In same-track evaluation where predictors are trained and evaluated on same-track data, proposed predictor outperforms existing predictors by achieving least Mean Absolute Error (MAE) of 0.13, 0.19 and 0.065 over lake track, jungle track and CARLA based datasets, respectively. Similarly, in cross-track evaluation where predictors are trained on one track and are evaluated on other track data, once again proposed predictor outperforms existing predictors by producing average least MAE errors of 0.33 and 0.06 over Udacity and CARLA datasets, respectively. Over two real-world datasets, Sully Chen and Comma.ai, the proposed predictor demonstrates superior performance compared to existing simulator-based predictors, achieving the lowest MAE of 2.41 and 0.50, respectively.

The exchange of perceptual information between autonomous vehicles could significantly improve driving safety. In general, obtaining more information means driving more safely. However, Frequent information sharing consumes a significant amount of channel bandwidth resources, which will reduce transmission efficiency and increase delay, especially in crowded cities. This paper presents a novel method of motion prediction compensation to solve this problem. Firstly, we propose a distributed fountain coding scheme to improve transmission efficiency and reduce vehicles’ delay in acquiring peripheral information. Secondly, we design a mobile prediction model and information transmission control algorithm to reduce traffic while ensuring information reliability. The simulation results show that the prediction accuracy of this method is above 94 %, the information transmission is reduced by more than 50 %, and the vehicle perception rate is increased by 34 %.

In the ever-changing world of decision-making, when game theory and reinforcement learning(RL) come together, they create a fascinating combination that shows a new way to solve complex problems in many fields. The combination of game theory and RL is a powerful convergence that opens up a hopeful new frontier for dealing with complex decision-making problems in many different fields. Research on the convergence of game theory and RL has shown to be beneficial, providing essential insights into challenging decision-making issues in various disciplines. This study investigates the recent developments of game theory and RL approaches through a systematic review and highlights the significance of game theory in boosting reinforcement algorithms and increasing the interaction of autonomous vehicles, safeguarding edge caching, and more. It offers a thorough account of the developments at the confluence of game theory and RL. The reviewed papers mainly focus on broad themes and address three important research questions: the impact of game theory on multi-agent reinforcement learning (MARL), the significant contributions of game theory to RL, and the significant impact areas. Following the methodology, search outcomes, and study areas is a discussion on game theory-related terminology, followed by study findings. The review’s conclusions offer ideas for further study and open research questions. The importance of game theory in advancing MARL, the potential of game theory in promoting RL strategies, and the opportunities for combining game theory and RL in cutting-edge fields like mobile edge caching and cyber-physical systems(CPS) are all emphasized in the conclusion. This review article advances our knowledge of the theoretical underpinnings and real-world applications of game theory and RL, laying the groundwork for future improvements in decision-making techniques and algorithms.

The perception system is a safety-critical component that directly impacts the overall safety of autonomous driving systems (ADSs). It is imperative to ensure the robustness of the deep-learning model used in the perception system. However, studies have shown that these models are highly vulnerable to the adversarial perturbation of input data. The existing works mainly focused on studying the impact of these adversarial attacks on classification rather than regression models. Therefore, this paper first introduces two generalized methods for perturbation-based attacks: (1) We used naturally occurring noises to create perturbations in the input data. (2) We introduce a modified square, HopSkipJump, and decision-based/boundary attack to attack the regression models used in ADSs. Then, we propose a deep-autoencoder-based adversarial attack detector. In addition to offline evaluation metrics (e.g., F1 score and precision, etc.), we introduce an online evaluation framework to evaluate the robustness of the model under attack. The framework considers the reconstruction loss of the deep autoencoder that validates the robustness of the models under attack in an end-to-end fashion at runtime. Our experimental results showed that the proposed adversarial attack detector could detect square, HopSkipJump, and decision-based/boundary attacks with a true positive rate (TPR) of 93%.

Self-driving cars are one of the main areas of research today, but it has to be acknowledged that the information from the sensors (the perceptron) is a huge amount of data, which is now unmanageable even when projected onto a single traffic junction. In the case of self-driving, the nodes have to be sequenced and organized according to the planned route. A self-driving car in Hungary would have to be able to interpret more than 70,000 traffic junctions to be able to drive all over the country. Besides the huge amount of data, another problem is the issue of validation and verification. For self-driving cars, this implies a level of complexity using traditional methods that calls into question the economics of the already existing system. Fuzzy Petri nets provide an alternative solution to both problems. They allow us to obtain a model that accurately describes the reliability of a node through its dynamics, which is essential in perception since the more reliable a node is, the smaller the deep learning mesh required. In this paper, we outline the analysis of a traffic node’s safety using Petri nets and fuzzy analysis to gain information on the reliability of the node, which is essential for the modeling of self-driving cars, due to the deep learning model of perception. The reliability of the dynamics of the node is determined by using the modified fuzzy Petri net procedure. The need for a fuzzy extension of the Petri net was developed by knowledge of real traffic databases.

This paper proposes an evaluating and mapping methodology of terrain traversability for off-road navigation of autonomous vehicles in unstructured environments. Terrain features are extracted from RGB images and 3D point clouds to create a traversal cost map. The cost map is then employed to plan safe trajectories. Bayesian generalized kernel inference is employed to assess unknown grid attributes due to the sparse raw point cloud data. A Kalman filter also creates density local elevation maps in real time by fusing multiframe information. Consequently, the terrain semantic mapping procedure considers the uncertainty of semantic segmentation and the impact of sensor noise. A Bayesian filter is used to update the surface semantic information in a probabilistic manner. Ultimately, the elevation map is utilized to extract geometric characteristics, which are then integrated with the probabilistic semantic map. This combined map is then used in conjunction with the extended motion primitive planner to plan the most effective trajectory. The experimental results demonstrate that the autonomous vehicles obtain a success rate enhancement ranging from 4.4% to 13.6% and a decrease in trajectory roughness ranging from 5.1% to 35.8% when compared with the most developed outdoor navigation algorithms. Additionally, the autonomous vehicles maintain a terrain surface selection accuracy of over 85% during the navigation process.

Road conditions, often degraded by insufficient maintenance or adverse weather, significantly contribute to accidents, exacerbated by the limited human reaction time to sudden hazards like potholes. Early detection of distant potholes is crucial for timely corrective actions, such as reducing speed or avoiding obstacles, to mitigate vehicle damage and accidents. This paper introduces a novel approach that utilizes perspective transformation to enhance pothole detection at different distances, focusing particularly on distant potholes. Perspective transformation improves the visibility and clarity of potholes by virtually bringing them closer and enlarging their features, which is particularly beneficial given the fixed-size input requirement of object detection networks, typically significantly smaller than the raw image resolutions captured by cameras. Our method automatically identifies the region of interest (ROI)—the road area—and calculates the corner points to generate a perspective transformation matrix. This matrix is applied to all images and corresponding bounding box labels, enhancing the representation of potholes in the dataset. This approach significantly boosts detection performance when used with YOLOv5-small, achieving a 43% improvement in the average precision (AP) metric at intersection-over-union thresholds of 0.5 to 0.95 for single class evaluation, and notable improvements of 34%, 63%, and 194% for near, medium, and far potholes, respectively, after categorizing them based on their distance. To the best of our knowledge, this work is the first to employ perspective transformation specifically for enhancing the detection of distant potholes.

The introduction of autonomous vehicles (AVs) has the potential to drastically change society, planning, design, and development strategies. This study uses the PRISMA protocol to carry out a systematic literature review, focusing on the backcasting method as an analytic tool. By examining. 21 studies published between 2003 and 2024, this paper highlights the phases of backcasting: visioning, policy packaging, and appraisal, and identifies critical factors necessary for the successful integration of AVs. Visioning for future driverless cities includes high-quality urban areas, active mobility, and innovative developments. Policies and Packaging suggested a focus on restricting vehicular access, transit-oriented development, and encouraging public transportation. Appraisal reveals skepticism about the positive impacts of AVs, urging policies that limit access to urban areas and promote sustainable modes of transportation. The main contribution of this study lies in its comprehensive application of backcasting to AV implementation, offering a structured approach to envisioning future urban scenarios, formulating supportive policies, and evaluating their impact. This analysis provides a solid foundation for future research, urging us to explore the intersection between AVs, citizen participation, and environmental sustainability to achieve more efficient and sustainable cities.

With the advancement of autonomous driving technology, scenario-based testing has become the mainstream testing method for intelligent vehicles. However, traditional risk indicators often fail in roundabout scenarios and cannot accurately define dangerous situations. To accurately quantify driving risks in roundabout scenarios, an improved driving safety field model is proposed in this paper. First, considering the unique traffic flow characteristics of roundabouts, the dynamic characteristics of vehicles during diverging or merging were taken into account, and the driving safety field model was improved to accurately quantify the driving risks in roundabout scenarios. Second, based on data from the rounD dataset, the model parameters were calibrated using the social force model. Finally, a DENCLUE-like method was used to extract collision systems, calculate vehicle risk degree, and analyze these risks for both the temporal and the spatial dimensions, providing guidance for virtual testing. The proposed method significantly improves detection efficiency, increasing the number of identified dangerous scenarios by 175% compared to the Time to Collision (TTC) method. Moreover, this method can more accurately quantify driving risks in roundabout scenarios and enhance the efficiency of generating dangerous scenarios, contributing to promoting the safety of autonomous vehicles.