Autonomous Vehicle Research Research Articles

Trajectory Planning and Tracking Control for Single Lane Changing with Different Driving Styles of Intelligent Vehicles Based on Seventh-Degree Polynomial

<div>Single lane changing is one of the typical scenarios in vehicle driving. Planning an appropriate lane change trajectory is crucial in autonomous and semi-autonomous vehicle research. Existing polynomial trajectory planning mostly uses cubic or quintic polynomials, neglecting the lateral jerk constraints during lane changes. This study uses seventh-degree polynomials for lane change trajectory planning by considering the vehicle lateral jerk constraints. Simulation results show that the utilization of the seventh-degree method results in a 41% reduction in jerk compared to the fifth-degree polynomial. Furthermore, this study also proposes lane change trajectory schemes that can cater to different driving styles (e.g., safety, efficiency, comfort, and balanced performance). Depending on the driving style, the planned lane change trajectory ensures that the vehicle achieves optimal performance in one or more aspects during the lane change process. For example, with the trajectory that provides the best comprehensive performance under given constraints (initial speed of 20 m/s, lane width of 3.5 m, and a longitudinal distance of 50 m to the obstacle in front), the four-wheel steering model predictive control can effectively track the planned trajectory, with the maximum jerk value being 6.4 m/s<sup>3</sup> and the longitudinal speed after lane change being approximately 12.6 m/s. Although this study assumes specific longitudinal displacement before and after the lane change, the methodology is applicable to other scenarios. For example, it can determine the shortest longitudinal displacement and the optimal lane change trajectory given predefined vehicle speeds and maximum lateral acceleration conditions. The lane change trajectories developed in this study can be directly applied to the system design of autonomous vehicles.</div>

Shared autonomous micro-mobility for walkable cities

The integration of autonomy into micro-mobility systems has given rise to a new solution known as shared autonomous micro-mobility (SAmM)11SAmM = Shared autonomous micro-mobility.. This paper delves into the opportunities that emerge from this concept, which is driven by the resurgence of walkable, human-centric cities and the advancements in autonomous vehicles. While most autonomous vehicle research has focused on cars and taxis, SAmM proposes more lightweight and environmentally friendly alternatives that align with the vision of more human-centered, walkable cities. At the same time, the integration of autonomy into micro-mobility systems holds the potential to enhance efficiency by reducing fleet sizes and increase convenience by transforming them into on-demand mobility services. This study presents a roadmap for the successful implementation of SAmM, covering essential aspects such as vehicle design, infrastructure requirements, and operational strategies. This research sheds light on the transformative potential of SAmM and provides insights for mobility operators, urban planners, policymakers, and researchers.

Optimizing Camera Exposure Time for Automotive Applications.

Camera-based object detection is integral to advanced driver assistance systems (ADAS) and autonomous vehicle research, and RGB cameras remain indispensable for their spatial resolution and color information. This study investigates exposure time optimization for such cameras, considering image quality in dynamic ADAS scenarios. Exposure time, the period during which the camera sensor is exposed to light, directly influences the amount of information captured. In dynamic scenarios, such as those encountered in typical driving scenarios, optimizing exposure time becomes challenging due to the inherent trade-off between Signal-to-Noise Ratio (SNR) and motion blur, i.e., extending exposure time to maximize information capture increases SNR, but also increases the risk of motion blur and overexposure, particularly in low-light conditions where objects may not be fully illuminated. The study introduces a comprehensive methodology for exposure time optimization under various lighting conditions, examining its impact on image quality and computer vision performance. Traditional image quality metrics show a poor correlation with computer vision performance, highlighting the need for newer metrics that demonstrate improved correlation. The research presented in this paper offers guidance into the enhancement of single-exposure camera-based systems for automotive applications. By addressing the balance between exposure time, image quality, and computer vision performance, the findings provide a road map for optimizing camera settings for ADAS and autonomous driving technologies, contributing to safety and performance advancements in the automotive landscape.

GRTR: Gradient Rebalanced Traffic Sign Recognition for Autonomous Vehicles

Traffic sign recognition is a crucial aspect of autonomous vehicle research, and deep learning techniques have significantly contributed to its progress. Nevertheless, the distribution of traffic sign information in natural complex road conditions is long-tailed, and traffic sign identification in complex road conditions has become a significant barrier to autonomous vehicle applications. The imbalanced distribution of information on the dataset migrates to the feature space during training, resulting in imbalanced classifier prediction. In this paper, we propose the gradient rebalanced traffic sign recognition (GRTR) method to address this problem for the first time. GRTR first evaluates the prediction and classification bias of the classifier using the fitted deviation between the model’s output probability and the ground-truth distributions. Then, GRTR dynamically adjusts the correction and compensation factors following the classifier’s prediction and classification biases. GRTR rebalances the positive and negative sample gradients for each category based on the synergistic effect of the correction and compensation factors to prevent the transfer of distribution imbalance and to significantly enhance the performance of the traffic sign classifier under difficult road conditions. Experimental results demonstrate that our GRTR achieves state-of-the-art performance on long-tailed traffic sign and multilabel datasets. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —Most traffic sign recognition algorithms are still designed based on the assumption of a balanced distribution of traffic signs in the dataset. Real-world autonomous vehicles require traffic sign recognition on datasets with severely imbalanced distributions. This paper proposes a general approach to solving the long-tailed traffic sign recognition problem.

The Impact of Autonomous Vehicle Popularization on Safety, Comfort, and Overall Traffic Development

With the high-speed development of AI, machine learning, visual identification, and varieties of technology, autonomous vehicles are becoming more and more perfect in their design, safety performance, and function, and some autonomous vehicle companies have some chances to test the reliability of their products on roads with vehicle piloted by humans in some countries. The paper aims to understand the impact of autonomous vehicle popularization on safety, comfort, and overall traffic development and the feasibility of solving some existing problems that autonomous vehicles are facing. The paper offers some suggestions for future autonomous vehicle research and accomplishing autonomous vehicle popularization. The paper shows the futural traffic system and people’s travel experience.

Exploring the Landscape of Autonomous Vehicles Research: A Scientometric Analysis in the Context of Urban Transportation Planning

Exploring the Landscape of Autonomous Vehicles Research: A Scientometric Analysis in the Context of Urban Transportation Planning

Identifying Key Issues in Integration of Autonomous Ships in Container Ports: A Machine-Learning-Based Systematic Literature Review

Background: Autonomous ships have the potential to increase operational efficiency and reduce carbon footprints through technology and innovation. However, there is no comprehensive literature review of all the different types of papers related to autonomous ships, especially with regard to their integration with ports. This paper takes a systematic review approach to extract and summarize the main topics related to autonomous ships in the fields of container shipping and port management. Methods: A machine learning method is used to extract the main topics from more than 2000 journal publications indexed in WoS and Scopus. Results: The research findings highlight key issues related to technology, cybersecurity, data governance, regulations, and legal frameworks, providing a different perspective compared to human manual reviews of papers. Conclusions: Our search results confirm several recommendations. First, from a technological perspective, it is advised to increase support for the research and development of autonomous underwater vehicles and unmanned aerial vehicles, establish safety standards, mandate testing of wave model evaluation systems, and promote international standardization. Second, from a cyber–physical systems perspective, efforts should be made to strengthen logistics and supply chains for autonomous ships, establish data governance protocols, enforce strict control over IoT device data, and strengthen cybersecurity measures. Third, from an environmental perspective, measures should be implemented to address the environmental impact of autonomous ships. This can be achieved by promoting international agreements from a global societal standpoint and clarifying the legal framework regarding liability in the event of accidents.

High-Resolution Polarimetric Radar for Autonomous Vehicle Research at W-Band Frequencies

High-Resolution Polarimetric Radar for Autonomous Vehicle Research at <i>W</i>-Band Frequencies

Impact of ISP Tuning on Object Detection.

In advanced driver assistance systems (ADAS) or autonomous vehicle research, acquiring semantic information about the surrounding environment generally relies heavily on camera-based object detection. Image signal processors (ISPs) in cameras are generally tuned for human perception. In most cases, ISP parameters are selected subjectively and the resulting image differs depending on the individual who tuned it. While the installation of cameras on cars started as a means of providing a view of the vehicle's environment to the driver, cameras are increasingly becoming part of safety-critical object detection systems for ADAS. Deep learning-based object detection has become prominent, but the effect of varying the ISP parameters has an unknown performance impact. In this study, we analyze the performance of 14 popular object detection models in the context of changes in the ISP parameters. We consider eight ISP blocks: demosaicing, gamma, denoising, edge enhancement, local tone mapping, saturation, contrast, and hue angle. We investigate two raw datasets, PASCALRAW and a custom raw dataset collected from an advanced driver assistance system (ADAS) perspective. We found that varying from a default ISP degrades the object detection performance and that the models differ in sensitivity to varying ISP parameters. Finally, we propose a novel methodology that increases object detection model robustness via ISP variation data augmentation.

Autonomous vehicles: What are your intentions?

Autonomous vehicles provide a variety of societal and environmental benefits, however significant technological, legislative, and infrastructural advancements are still required for successful integration of autonomous vehicles into society. The present study applied the Theory of Planned Behaviour to examine the factors driving and impeding autonomous vehicle adoption. Participants were 254 adults (Mage = 37.89, SD = 14.33) who took part in an online survey assessing attitudes, subjective norms, perceived behavioural control, perceived barriers and intentions to adopt autonomous vehicles. Results indicated that attitudes and both personal and work-related subjective norms were positively associated with adoption intention. An association was not found between perceived behavioural control and adoption intention, and the relationships between psychosocial factors and adoption intention were not found to be moderated by perceived barriers. Concerns regarding the risk of operating errors and fear of equipment or system failure were found to be negatively associated with adoption intention and concerns regarding cost was found to be positively associated with adoption intention. Encouragingly from a safety perspective, it appears that concerns regarding safety are more influential to adoption intention than costs associated with the purchase of the vehicle. The results of this research have important implications for future research and integration of autonomous vehicles into society.

Knowledge mapping of an artificial intelligence application scenario: A bibliometric analysis of the basic research of data-driven autonomous vehicles

With the rapid development and maturation of basic research in related fields such as deep learning and convolutional neural networks, artificial intelligence (AI) has become a policy hotspot of high interest in all major economies. Furthermore, the governance of application scenarios has become one of the important topics of AI governance policy research. The practice of AI governance policy depends on a change in the paradigm of relevant governance policy research theories, and there is an urgent need to empirically analyze the structural characteristics of the knowledge evolution of AI application scenarios. This study conducts a bibliometric analysis of the basic research trends in autonomous vehicles, which is one of the most important application scenarios of AI. The study empirically analyzes the relevant literature data from the Science Citation Index Expanded (SCI-Expanded) and Social Sciences Citation Index (SSCI) databases of Web of Science, based on both technical and social dimensions through the knowledge mapping analysis tools in Bibliometrix (in R environment). Based on the empirical analysis, the results show that the basic research on autonomous vehicles is characterized by strong data-driven innovation under the influence of AI. The fusion of AI and basic research on autonomous vehicles has become a major driver of knowledge innovation in this domain while there is a lack of the integration of social science research.

Research on Path Planning and Path Tracking Control of Autonomous Vehicles Based on Improved APF and SMC.

Path planning and tracking control is an essential part of autonomous vehicle research. In terms of path planning, the artificial potential field (APF) algorithm has attracted much attention due to its completeness. However, it has many limitations, such as local minima, unreachable targets, and inadequate safety. This study proposes an improved APF algorithm that addresses these issues. Firstly, a repulsion field action area is designed to consider the velocity of the nearest obstacle. Secondly, a road repulsion field is introduced to ensure the safety of the vehicle while driving. Thirdly, the distance factor between the target point and the virtual sub-target point is established to facilitate smooth driving and parking. Fourthly, a velocity repulsion field is created to avoid collisions. Finally, these repulsive fields are merged to derive a new formula, which facilitates the planning of a route that aligns with the structured road. After path planning, a cubic B-spline path optimization method is proposed to optimize the path obtained using the improved APF algorithm. In terms of path tracking, an improved sliding mode controller is designed. This controller integrates lateral and heading errors, improves the sliding mode function, and enhances the accuracy of path tracking. The MATLAB platform is used to verify the effectiveness of the improved APF algorithm. The results demonstrate that it effectively plans a path that considers car kinematics, resulting in smaller and more continuous heading angles and curvatures compared with general APF planning. In a tracking control experiment conducted on the Carsim-Simulink platform, the lateral error of the vehicle is controlled within 0.06 m at both high and low speeds, and the yaw angle error is controlled within 0.3 rad. These results validate the traceability of the improved APF method proposed in this study and the high tracking accuracy of the controller.

Rethinking engagement in urban design: reimagining the value of co-design and participation at every stage of planning for autonomous vehicles

PurposeThe practical demonstrations and research which led to the preparation of this paper involved a combination of stakeholder engagement, policy debate and the practical demonstration and testing of autonomous vehicles. By adhering to a design approach which in centred on participation and human-centred engagement, the advent of autonomous vehicles might avoid many of the problems encountered in relation to conventional transport.Design/methodology/approachThe research explored how a new and potentially disruptive technology might be incorporated in urban settings, through the lens of participation and problem-based design. The research critically reviews key strands in the literature (autonomous vehicles, social research and participatory design), with allusion to current case study experiments.FindingsAlthough there are numerous examples of autonomous vehicles (AV) research concentrating on technical aspects alone, this paper finds that such an approach appears to be an unusual starting point for the design of innovative technology. That is, AVs would appear to hold the potential to be genuinely disruptive in terms of innovation, yet the way that disruption takes place should surely be guided by design principles and by issues and problems encountered by potential users.Practical implicationsThe research carries significant implications for practice in that it advocates locating those socio-contextual issues at the heart of the problem definition and design process and ahead of technical solutions.Originality/valueWhat sets this research apart from other studies concerning AVs was that the starting point for investigation was the framing of AVs within contexts and scenarios leading to the emergence of wicked problems. This begins with a research position where the potential uses for AVs are considered in a social context, within which the problems and issues to be solved become the starting point for design at a fundamental level.

Optimum Control for Path Tracking Problem of Vehicle Handling Inverse Dynamics.

Accurate tracking of a given path is one of the primary factors in the maneuverability of a vehicle and is also an important topic in autonomous vehicle research. To solve the problem of vehicle path tracking, the problem must first be transformed into an optimal control problem. Then, a symplectic pseudospectral method (SPM) based on the third-generation function of symplectic theory and pseudospectral discretization is proposed to efficiently solve the nonlinear optimal control problems. Finally, the results obtained by the proposed algorithm are compared with those obtained by the Gauss pseudospectral method (GPM). The simulation results show that the proposed method can effectively solve the vehicle path tracking problem. Furthermore, the vehicle can track the given path controlled by the proposed algorithm with higher accuracy and greater applicability than other methods.

Research on Path Planning and Tracking Control of Autonomous Vehicles Based on Improved RRT* and PSO-LQR

Path planning and tracking control are essential parts of autonomous vehicle research. Regarding path planning, the Rapid Exploration Random Tree Star (RRT*) algorithm has attracted much attention due to its completeness. However, the algorithm still suffers from slow convergence and high randomness. Regarding path tracking, the Linear Quadratic Regulator (LQR) algorithm is widely used in various control applications due to its efficient stability and ease of implementation. However, the relatively empirical selection of its weight matrix can affect the control effect. This study suggests a path planning and tracking control framework for autonomous vehicles based on an upgraded RRT* and Particle Swarm Optimization Linear Quadratic Regulator (PSO-LQR) to address the abovementioned issues. Firstly, according to the driving characteristics of autonomous vehicles, a variable sampling area is used to limit the generation of random sampling points, significantly reducing the number of iterations. At the same time, an improved Artificial Potential Field (APF) method was introduced into the RRT* algorithm, which improved the convergence speed of the algorithm. Utilizing path pruning based on the maximum steering angle constraint of the vehicle and the cubic B-spline algorithm to achieve path optimization, a continuous curvature path that conforms to the precise tracking of the vehicle was obtained. In addition, optimizing the weight matrix of LQR using POS improved path-tracking accuracy. Finally, this article’s improved RRT* algorithm was simulated and compared with the RRT*, target bias RRT*, and P-RRT*. At the same time, on the Simulink–Carsim joint simulation platform, the PSO-LQR is used to track the planned path at different vehicle speeds. The results show that the improved RRT* algorithm optimizes the path search speed by 34.40% and the iteration number by 33.97%, respectively, and the generated paths are curvature continuous. The tracking accuracy of the PSO-LQR was improved by about 59% compared to LQR, and its stability was higher. The position error and heading error were controlled within 0.06 m and 0.05 rad, respectively, verifying the effectiveness and feasibility of the proposed path planning and tracking control framework.

3D Road Lane Classification with Improved Texture Patterns and Optimized Deep Classifier.

The understanding of roads and lanes incorporates identifying the level of the road, the position and count of lanes, and ending, splitting, and merging roads and lanes in highway, rural, and urban scenarios. Even though a large amount of progress has been made recently, this kind of understanding is ahead of the accomplishments of the present perceptual methods. Nowadays, 3D lane detection has become the trending research in autonomous vehicles, which shows an exact estimation of the 3D position of the drivable lanes. This work mainly aims at proposing a new technique with Phase I (road or non-road classification) and Phase II (lane or non-lane classification) with 3D images. Phase I: Initially, the features, such as the proposed local texton XOR pattern (LTXOR), local Gabor binary pattern histogram sequence (LGBPHS), and median ternary pattern (MTP), are derived. These features are subjected to the bidirectional gated recurrent unit (BI-GRU) that detects whether the object is road or non-road. Phase II: Similar features in Phase I are further classified using the optimized BI-GRU, where the weights are chosen optimally via self-improved honey badger optimization (SI-HBO). As a result, the system can be identified, and whether it is lane-related or not. Particularly, the proposed BI-GRU + SI-HBO obtained a higher precision of 0.946 for db 1. Furthermore, the best-case accuracy for the BI-GRU + SI-HBO was 0.928, which was better compared with honey badger optimization. Finally, the development of SI-HBO was proven to be better than the others.

What if autonomous vehicles had been introduced into cities? A counterfactual analysis

The impact of autonomous vehicles on the spatial size of cities remains ambiguous, as the future is highly uncertain. This paper uses counterfactual analysis techniques to examine the effects of autonomous vehicles on urban expansion for metropolitan areas in the United States if autonomous vehicles had been introduced before. We argue that distance cost and congestion cost, which are the two components of transportation cost with different effects on urban expansion, should be addressed in autonomous vehicle research. By coupling historical data with hypothetical scenarios of introducing autonomous vehicles to cities, we find that urban expansion, rather than urban densification, would have been the dominant effect if autonomous vehicles had been introduced into cities. The finding indicates that if autonomous vehicles are widely adopted in the future, they are likely to have similar, or even larger, effects on future urban expansion than in the counterfactual past.

Radar Based Pedestrian Classification using Deep Learning Approach

Developments in sensor fusion systems led to extensive research in autonomous vehicles, and object detection is a crucial aspect of vehicle operation. Detecting obstacles can be difficult due to the wide range of potential obstructions, the characteristics of each sensor, and the influence of the surrounding environment. In this paper, the authors use automotive radar data and various neural networks to classify various objects (vehicles, single and multiple people, and bicycles). Combined with the vehicle radar, this research proposed a rapid radar algorithmic implementation for locating, monitoring and extracting micro-Doppler. The authors evaluate three distinct neural network architectures for the five recorded classes of targets: the basic CNN, the residual network, and the combined neural architecture of convolution and recurrent layers. Considerable accuracy is 95.6% immediately before identification of the radar spectrogram from (~0.55 s to produce 0.5 s long spectrogram).

How to train a self-driving vehicle: On the added value (or lack thereof) of curriculum learning and replay buffers.

Learning from only real-world collected data can be unrealistic and time consuming in many scenario. One alternative is to use synthetic data as learning environments to learn rare situations and replay buffers to speed up the learning. In this work, we examine the hypothesis of how the creation of the environment affects the training of reinforcement learning agent through auto-generated environment mechanisms. We take the autonomous vehicle as an application. We compare the effect of two approaches to generate training data for artificial cognitive agents. We consider the added value of curriculum learning-just as in human learning-as a way to structure novel training data that the agent has not seen before as well as that of using a replay buffer to train further on data the agent has seen before. In other words, the focus of this paper is on characteristics of the training data rather than on learning algorithms. We therefore use two tasks that are commonly trained early on in autonomous vehicle research: lane keeping and pedestrian avoidance. Our main results show that curriculum learning indeed offers an additional benefit over a vanilla reinforcement learning approach (using Deep-Q Learning), but the replay buffer actually has a detrimental effect in most (but not all) combinations of data generation approaches we considered here. The benefit of curriculum learning does depend on the existence of a well-defined difficulty metric with which various training scenarios can be ordered. In the lane-keeping task, we can define it as a function of the curvature of the road, in which the steeper and more occurring curves on the road, the more difficult it gets. Defining such a difficulty metric in other scenarios is not always trivial. In general, the results of this paper emphasize both the importance of considering data characterization, such as curriculum learning, and the importance of defining an appropriate metric for the task.

Developing a Deep Q-Learning and Neural Network Framework for Trajectory Planning

With the recent expansion in Self-Driving and Autonomy field, every vehicle is occupied with some kind or alter driver assist features in order to compensate driver comfort. Expansion further to fully Autonomy is extremely complicated since it requires planning safe paths in unstable and dynamic environments. Impression learning and other path learning techniques lack generalization and safety assurances. Selecting the model and avoiding obstacles are two difficult issues in the research of autonomous vehicles. Q-learning has evolved into a potent learning framework that can now acquire complicated strategies in high-dimensional contexts to the advent of deep feature representation. A deep Q-learning approach is proposed in this study by using experienced replay and contextual expertise to address these issues. A path planning strategy utilizing deep Q-learning on the network edge node is proposed to enhance the driving performance of autonomous vehicles in terms of energy consumption. When linked vehicles maintain the recommended speed, the suggested approach simulates the trajectory using a proportional-integral-derivative (PID) concept controller. Smooth trajectory and reduced jerk are ensured when employing the PID controller to monitor the terminals. The computational findings demonstrate that, in contrast to traditional techniques, the approach could investigate a path in an unknown situation with small iterations and a higher average payoff. It can also more quickly converge to an ideal strategic plan.