Autonomous Vehicle Technology Research Articles

BIPOOLNET: An advanced UNet architecture for enhanced lane detection in autonomous vehicles

In the rapidly evolving landscape of autonomous vehicle technology, the imperative to bolster safety within smart urban ecosystems has never been more critical. This endeavor requires the deployment of advanced detection systems capable of navigating the intricacies of pedestrian, near-vehicle, and lane detection challenges, with a particular focus on the nuanced requirements of curved lane navigation – a domain where traditional AI models exhibit notable deficiencies. This paper introduces BIPOOLNET, an innovative encoder-decoder neural architecture, ingeniously augmented with a feature pyramid to facilitate the precise delineation of curved lane geometries. BIPOOLNET integrates max pooling and average pooling to extract critical features and mitigate the complexity of the feature map, redefining the benchmarks for lane detection technology. Rigorous evaluation using the TuSimple dataset underscores BIPOOLNET’s exemplary performance, evidenced by an unprecedented accuracy rate of 98.45%, an F1-score of 98.17%, and notably minimal false positive (1.84%) and false negative (1.09%) rates. These findings not only affirm BIPOOLNET’s supremacy over extant models but also signal a paradigm shift in enhancing the safety and navigational precision of autonomous vehicles, offering a scalable, robust solution to the multifaceted challenges posed by real-world driving dynamics.

An Improved YOLOv5s Model for Building Detection

With the continuous advancement of autonomous vehicle technology, the recognition of buildings becomes increasingly crucial. It enables autonomous vehicles to better comprehend their surrounding environment, facilitating safer navigation and decision-making processes. Therefore, it is significant to improve detection efficiency on edge devices. However, building recognition faces problems such as severe occlusion and large size of detection models that cannot be deployed on edge devices. To solve these problems, a lightweight building recognition model based on YOLOv5s is proposed in this study. We first collected a building dataset from real scenes and the internet, and applied an improved GridMask data augmentation method to expand the dataset and reduce the impact of occlusion. To make the model lightweight, we pruned the model by the channel pruning method, which decreases the computational costs of the model. Furthermore, we used Mish as the activation function to help the model converge better in sparse training. Finally, comparing it to YOLOv5s (baseline), the experiments show that the improved model reduces the model size by 9.595 MB, and the mAP@0.5 reaches 82.3%. This study will offer insights into lightweight building detection, demonstrating its significance in environmental perception, monitoring, and detection, particularly in the field of autonomous driving.

Autonomous vehicle tracking control for a curved trajectory

Recently, research about trajectory tracking of autonomous vehicles has significantly contributed to the development of autonomous vehicle technology, particularly with novel control methods. However, tracking a curved trajectory is still a challenge for autonomous vehicles. This research proposes a state feedback linearization with observer feedback to overcome some difficulties arising from such a path. This approach suits a complex nonlinear system such as an autonomous vehicle. This method also has been compared with the linear-quadratic regulator (LQR) method. So, the goal of this research is to improve the control system performance of autonomous vehicles that are stable enough to navigate a curved path. Moreover, the study shows that the developed control law can track the curved path and solve existing problems. However, improvements are still necessary for the vehicle's performance and robustness.

Traffic Sign Recognition using HIICNN Stack Ensemble Method

Abstract: This project introduces a novel deep convolutional neural network (CNN) model aimed at enhancing traffic sign recognition for autonomous vehicle technology and road safety. Employing a stacking ensemble approach, we combine multiple CNNs with diverse improvement techniques, including preprocessing for adverse weather conditions and shooting errors, and data augmentation to handle class imbalance. Through adjustments in learning rates during model training, we mitigate overfitting. Our ensemble model achieves an exceptional 99.4 percent test accuracy on the German Traffic Sign Recognition Benchmark (GTSRB) dataset, surpassing prior studies. We utilize gradient-weighted Class Activation Mapping (Grad-CAM) for model explain- ability and an evidential deep learning approach to quantify classification uncertainty. Our framework underscores the efficacy of combining preprocessing, ensemble learning, and transfer learning for superior perfor- mance and reliability in traffic sign recognition systems, contributing significantly to autonomous driving and road safety.

Driving towards inclusion: Using a service design framework to investigate technology-induced inequalities

Technological growth is realizing an ever more intelligent and convenient future. However, is this future equal, and what role does service design play in addressing, or exacerbating, these inequalities? The relationship between technology and inequality is fluid, moving from the elimination of existing inequalities to the creation of new ones, and service design has the potential to impact this bidirectional relationship. On the other hand, the current literature fails to clearly identify service design’s contribution to the technology-inequality-design nexus. This paper develops a framework to do so. Drawing on the four dimensions of the Information Technology Infrastructure Library (ITIL) 4 model, this paper uses double diamond design process and methods, including user journey, problem framing, and prototyping, etc. to propose a novel framework incorporating four dimensions of service design and their links to inequality. The framework is then demonstrated through an application to autonomous vehicle technology. More broadly, the framework can be used by service designers and practitioners to identify different dimensions of hidden inequality within service design.

Impact of Aggressive HGV Platoons and Human-Driven Heavy Goods Vehicles on Signalized Intersections Performance

This paper presents a study on the performance and environmental impacts of aggressive heavy goods vehicle (HGV) platoons in comparison to human-driven HGVs at a random signalized intersection under varying traffic volumes between 500 and 1500 HGVs. A total of 12 scenarios have been developed, 6 for each of the vehicular behaviors, to quantify the emissions (CO, NOX, VOC) and fuel consumption, travel time, and delays. The analysis is implemented using the PTV VISSIM microscopic traffic flow model. Realization that the majority of the differences in the performance of the two vehicular controls seems to be different as the traffic volume increases was the realization. In most cases, aggressive HGV platoons were found to have lower emissions, in comparison to fuel consumption, while the flow and delay of aggressive HGV platoons were comparatively better against the case with human-driven HGVs. The results have thus provided new avenues for the incorporation of aggressive HGV platoons into urban traffic systems, more so in scenarios that involve a high level of traffic at intersections, as a potentially effective tool for augmenting the efficiency of an intersection and cutting down its environmental impacts. The present study strongly recommends the advancement of traffic management strategies that can capture the dynamics between the two heterogenous traffic flows induced by autonomous and semi-autonomous vehicle technologies.

Lane detection using hough transformation and Yolov8

Autonomous vehicles necessitate the integration of advanced technologies such as computer vision and deep learning to comprehend and navigate their surroundings. A crucial yet challenging component of this integration is the accurate detection of lanes, which can be influenced by a multitude of varying lane characteristics and conditions. This research undertakes a comparative analysis of lane detection methodologies, explicitly focusing on traditional image processing techniques and Convolutional Neural Networks (CNNs). The evaluation utilized a sample of 500 images from the CULane dataset, which encompasses a diverse range of traffic scenarios. Initially, a method incorporating Gaussian blurring, Canny edge detection, and Hough line transformation was examined. Despite its efficiency, operating at 30 frames per second, this approach exhibited a high error rate (average Mean Squared Error (MSE) of 0.537), which is attributable to the loss of critical image details during the preprocessing stage. Subsequently, the performance of a fine-tuned YOLOv8 model, trained on a reformatted version of the CULane dataset was assessed. The combination of object detection and subsequent Hough transformation yielded high accuracy, demonstrating the model’s ability to learn and identify relevant lane features. The deep CNNs demonstrated superior performance over classical image processing techniques in terms of lane detection accuracy, thereby underscoring their potential applicability within the realm of autonomous vehicle technology

Transforming Driver Education: A Comparative Analysis of LLM-Augmented Training and Conventional Instruction for Autonomous Vehicle Technologies

Transforming Driver Education: A Comparative Analysis of LLM-Augmented Training and Conventional Instruction for Autonomous Vehicle Technologies

Development, Simulation and Visualization of Autonomous Farm Vehicles

Abstract: A Research in Autonomous Agricultural Vehicle Technology is presented. With the coming of the Smart Farming Revolution the development of more complicated machines has begun. Agricultural machines are made with the capability of driving themselves, using GPS maps and electronic sensors, an approach that will lead to the development of futuristic Precise Autonomous Farming Systems. The basic issues to be addressed are autonomous path planning, obstacle detection and avoidance for which various sensors will be employed such as GPS, laser-based sensors, ultrasonic sensors, IMU sensors and Camera sensors whose data has to be constantly monitored using Dead Reckoning algorithm and constant Pose Estimation. In these sensors, Camera, Ultrasonic, Laser-Based Sensors are used as Detection sensors while the IMU and GPS sensors are used as Localization sensors. Global Avoidance Subsystem which examines the whole environment of an autonomous vehicle mission-level path planner that pre-plans paths around all known obstacles. While Local Avoidance Subsystem/Reactive planner consists of an obstacle filter and an obstacle avoidance algorithm and re-plans a short way for the vehicle to navigate. With the ROS framework and all sensors data, a vehicle can guide itself through an unknown environment. This will help the farmer to undercut the labour shortage and improve the precision in farming which in turn improves the output to meet the growing demands

Adaptive Scale and Correlative Attention PointPillars: An Efficient Real-Time 3D Point Cloud Object Detection Algorithm

Recognizing 3D objects from point clouds is a crucial technology for autonomous vehicles. Nevertheless, LiDAR (Light Detection and Ranging) point clouds are generally sparse, and they provide limited contextual information, resulting in unsatisfactory recognition performance for distant or small objects. Consequently, this article proposes an object recognition algorithm named Adaptive Scale and Correlative Attention PointPillars (ASCA-PointPillars) to address this problem. Firstly, an innovative adaptive scale pillars (ASP) encoding method is proposed, which encodes point clouds using pillars of varying sizes. Secondly, ASCA-PointPillars introduces a feature enhancement mechanism called correlative point attention (CPA) to enhance the feature associations within each pillar. Additionally, a data augmentation algorithm called random sampling data augmentation (RS-Aug) is proposed to solve the class imbalance problem. The experimental results on the KITTI 3D object dataset demonstrate that the proposed ASCA-PointPillars algorithm significantly boosts the recognition performance and RS-Aug effectively enhances the training effects on an imbalanced dataset.

Enhanced Road Safety through Integrated Speed Breaker, Pothole, and Lane Detection System

Abstract: Amidst the rapid evolution of autonomous vehicle technologies, ensuring road safety remains a paramount challenge. Effective detection of lanes and potential hazards, including speed breakers and potholes, is critical for safe autonomous driving. In this study, we introduce an innovative Lane, Speed Breaker, and Pothole Detection System (LSPDS) utilizing YOLOv4 Tiny, a state-of-the-art object detection algorithm and computer vision techniques. Our system integrates computer vision and machine learning techniques for analysis of road conditions. By employing camera sensors, we capture the road scene and apply image processing algorithms to identify lanes, speed breakers, and potholes. Moreover, the system incorporates Firebase for user authentication and SMS services for real-time alerts. YOLOv4 Tiny is employed for accurate detection and classification of these features within the captured images, thereby enhancing the perception capabilities of autonomous vehicles.

A Comprehensive Overview of the Current State of Development in Autonomous Vehicle Driving

The 21st century has witnessed a rapid evolution in information technology, leading to significant transformations in the automotive industry. The focus has shifted from purely mechanical enhancements to the advent of a new generation of vehicles equipped with intelligent driving technology. These smart vehicles are capable of perceiving their surroundings and adapting to real-time conditions and traffic, enabling assisted or even fully autonomous driving. This advancement promises substantial improvements in safety, environmental sustainability, and comfort, enhancing the overall driving experience. This paper provides a comprehensive overview of the current state of autonomous vehicle technology, focusing on the fundamental principles of intelligent driving. It delves into three key areas: environmental perception, path planning, and the application of artificial intelligence in autonomous driving systems.

Investigating levels of remote operation in high-level on-road autonomous vehicles using operator sequence diagrams

The continuing development of autonomous vehicle technology is making the presence of fully autonomous vehicles (SAE Level 5 of Driving Automation) on the road an ever more likely possibility. Similarly, regulation changes show countries are preparing for autonomous vehicles to increase their presence on public roads for both testing and use after sale. With this in mind, solutions to the problem of disengagement from the autonomous driving system by Level 5 vehicles, due to damage, operation outside of expected parameters or software failure among other reasons are being investigated including remote operation. This research aims to give evidence for the inclusion of remote operation into the autonomous driving and define the types of remote operation that may occur from existing literature. The four types of remote operation are Remote Monitoring, Remote Assistance, Remote Management and Remote Driving. Operator sequence diagrams are used to evaluate these types of remote operation in likely scenarios they may occur and draw conclusions about the role and the tasks the operator will be required to complete.

Pedestrian Perception Tracking in Complex Environment of Unmanned Vehicles Based on Deep Neural Networks

INTRODUCTION: In recent years, machine learning and deep learning have emerged as pivotal technologies with transformative potential across various industries. Among these, the automobile industry stands out as a significant arena for the application of these technologies, particularly in the development of smart cars with unmanned driving systems. This article delves into the extensive research conducted on the detection technology employed by autonomous vehicles to navigate road conditions, a critical aspect of driverless car technology.
 OBJECTIVES: The primary aim of this research is to explore and highlight the intricacies of road condition detection for autonomous vehicles. Emphasizing the importance of this key component in the development of driverless cars, we aim to provide insights into cutting-edge algorithms that enhance the capabilities of these vehicles, ultimately contributing to their widespread adoption.
 METHODS: In addressing the challenge of road condition detection, we introduce the TidyYOLOv4 algorithm. This algorithm, deemed more advantageous than YOLOv4, particularly excels in pedestrian recognition within urban traffic environments. Its real-time capabilities make it a suitable choice for detecting pedestrians on the road under dynamic conditions.
 RESULTS: The application of the TidyYOLOv4 algorithm in autonomous vehicles has yielded promising results, especially in enhancing pedestrian recognition in urban traffic settings. The algorithm's real-time functionality proves crucial in ensuring the timely detection of pedestrians on the road, thereby improving the overall safety and efficiency of autonomous vehicles.
 CONCLUSION: In conclusion, the detection of road conditions is a critical aspect of autonomous vehicle technology, with implications for safety and efficiency. The TidyYOLOv4 algorithm emerges as a noteworthy advancement, outperforming its predecessor YOLOv4 in pedestrian recognition within urban traffic environments. As companies continue to invest in driverless technology, leveraging such advanced algorithms becomes imperative for the successful deployment of autonomous vehicles in real-world scenarios.

Real-Time Vehicle Detection for Traffic Monitoring: A Deep Learning Approach

Vehicle detection is an essential technology for intelligent transportation systems and autonomous vehicles. Reliable real-time detection allows for traffic monitoring, safety enhancements and navigation aids. However, vehicle detection is a challenging computer vision task, especially in complex urban settings. Traditional methods using hand-crafted features like HAAR cascades have limitations. Recent deep learning advances have enabled convolutional neural networks (CNNs) like Faster R-CNN, SSD and YOLO to be applied to vehicle detection with significantly improved accuracy. But each technique has tradeoffs between precision and processing speed. Two-stage detectors like Faster R-CNN are highly accurate but slow at 7 FPS. Single-shot detectors like SSD are faster at 22 FPS but less precise. YOLO is extremely fast at 45 FPS but has lower accuracy. This paper reviews prominent deep learning vehicle detectors. It proposes a new integrated method combining YOLOv3 detection, optical flow tracking and trajectory analysis to enhance both accuracy and speed. Results on highway and urban datasets show improved precision, recall and F1 scores compared to YOLOv3 alone. Optical flow helps filter noise and recover missed detections. Trajectory analysis enables consistent object IDs across frames. Compared to other CNN models, the proposed technique achieves a better balance of real-time performance and accuracy. Occlusion handling and small object detection remain open challenges. In summary, deep learning has enabled major progress but enhancements in model architecture, training data and occlusion handling are needed to realize the full potential for traffic management applications. The integrated method proposed offers improved performance over baseline detectors. We have achieved 99 % accuracy in our project

Vehicle Detection in Adverse Weather: A Multi-Head Attention Approach with Multimodal Fusion

In the realm of autonomous vehicle technology, the multimodal vehicle detection network (MVDNet) represents a significant leap forward, particularly in the challenging context of weather conditions. This paper focuses on the enhancement of MVDNet through the integration of a multi-head attention layer, aimed at refining its performance. The integrated multi-head attention layer in the MVDNet model is a pivotal modification, advancing the network’s ability to process and fuse multimodal sensor information more efficiently. The paper validates the improved performance of MVDNet with multi-head attention through comprehensive testing, which includes a training dataset derived from the Oxford Radar RobotCar. The results clearly demonstrate that the multi-head MVDNet outperforms the other related conventional models, particularly in the average precision (AP) of estimation, under challenging environmental conditions. The proposed multi-head MVDNet not only contributes significantly to the field of autonomous vehicle detection but also underscores the potential of sophisticated sensor fusion techniques in overcoming environmental limitations.

Artificial Intelligence Based on Self Driving Cars with Safety Algorithm

The auto industry is going through a radical transformation with the introduction of self-driving cars, which offer safer and more effective transportation systems. An extensive analysis of the most recent developments in autonomous vehicle technology is given in this research report. It examines the different parts and mechanisms such as perception, decision-making, and control that are essential for autonomous functioning. The study also explores the benefits and problems that come with self-driving automobiles, including ethical issues, legal barriers, and public acceptance. This study contributes to the continuing discussion on the future of transportation by providing insightful information about the existing and potential states of autonomous cars through a synthesis of recent academic findings and industry advances. Keywords-- Self-driving Cars, Road Safety, Autonomous Vehicles, Decision Making, Safety Algorithm.

Relax on the way to work or work on the way to relax? Influences of vehicle interior on travel time perceptions in autonomous vehicles

The impending arrival of autonomous vehicle (AV) technology has the potential to transform how individuals perceive time spent travelling. By removing the need to drive and pay attention to the road, AV users could perform other activities, including those for work or leisure. As a result, AVs are expected to lower the burden of travel and, therefore, the value of travel time (VOTT). Despite the significant impacts that AVs may have on individuals’ choices and the transportation system, few have studied their impacts on travel time perceptions, and even fewer have examined the extent to which these impacts will vary depending on the types of tasks that can be performed within an AV. This study uses stated preference data collected in Fall 2022 to develop mode choice models and subsequently quantify how the availability of three types of AV: privately-owned, exclusive, and pooled AV may shift perceived travel times in the Greater Toronto and Hamilton Area. The error-component mixed logit models highlight the cross-nesting between privately-owned AVs and driving. In addition, this study is the first in Canada to distinguish the VOTT reductions by AV type, trip purpose, and interior description (which caters to different tasks). VOTT reductions as large as 42% less than driving a conventional vehicle were estimated. The results of this study provide additional empirical evidence for AV VOTT reductions (particularly in the Canadian context) and can be used to help craft policies in preparation for the arrival of AVs.

Gauging Public Acceptance of Conditionally Automated Vehicles in the United States

Public acceptance of conditionally automated vehicles is a crucial step in the realization of smart cities. Prior research in Europe has shown that the factors of hedonic motivation, social influence, and performance expectancy, in decreasing order of importance, influence acceptance. Moreover, a generally positive acceptance of the technology was reported. However, there is a lack of information regarding the public acceptance of conditionally automated vehicles in the United States. In this study, we carried out a web-based experiment where participants were provided information regarding the technology and then completed a questionnaire on their perceptions. The collected data was analyzed using PLS-SEM to examine the factors that may lead to public acceptance of the technology in the United States. Our findings showed that social influence, performance expectancy, effort expectancy, hedonic motivation, and facilitating conditions determine conditionally automated vehicle acceptance. Additionally, certain factors were found to influence the perception of how useful the technology is, the effort required to use it, and the facilitating conditions for its use. By integrating the insights gained from this study, stakeholders can better facilitate the adoption of autonomous vehicle technology, contributing to safer, more efficient, and user-friendly transportation systems in the future that help realize the vision of the smart city.

LIDAR-based SLAM system for autonomous vehicles in degraded point cloud scenarios: dynamic obstacle removal

PurposeThis study aims to achieve superior localization and mapping performance in point cloud degradation scenarios through the effective removal of dynamic obstacles. With the continuous development of various technologies for autonomous vehicles, the LIDAR-based Simultaneous localization and mapping (SLAM) system is becoming increasingly important. However, in SLAM systems, effectively addressing the challenges of point cloud degradation scenarios is essential for accurate localization and mapping, with dynamic obstacle removal being a key component.Design/methodology/approachThis paper proposes a method that combines adaptive feature extraction and loop closure detection algorithms to address this challenge. In the SLAM system, the ground point cloud and non-ground point cloud are separated to reduce the impact of noise. And based on the cylindrical projection image of the point cloud, the intensity features are adaptively extracted, the degradation direction is determined by the degradation factor and the intensity features are matched with the map to correct the degraded pose. Moreover, through the difference in raster distribution of the point clouds before and after two frames in the loop process, the dynamic point clouds are identified and removed, and the map is updated.FindingsExperimental results show that the method has good performance. The absolute displacement accuracy of the laser odometer is improved by 27.1%, the relative displacement accuracy is improved by 33.5% and the relative angle accuracy is improved by 23.8% after using the adaptive intensity feature extraction method. The position error is reduced by 30% after removing the dynamic target.Originality/valueCompared with LiDAR odometry and mapping algorithm, the method has greater robustness and accuracy in mapping and localization.