A Novel Lateral Control System for Autonomous Vehicles: A Look-Down Strategy

Nowadays, the development of modern technologies in the transportation area has increased rapidly. The latest technology is focused on autonomous vehicles. The most important aspect in autonomous vehicle control systems is safety, smooth operation and comfort. It can be provided by the natural element which is from human behavior as a reference to the autonomous control system. This paper is briefly describing the human behavior during braking for autonomous electric vehicle (AEV) control system development. To obtain the human behaviour during accelerating and braking, two units of angle sensors were installed to the accelerator and brake pedal of an electric car to measure the angle of both pedals. Real-time speed is recorded by using a GPS unit. The experiment is focused on braking characteristic of the electric vehicle. It was carried out based on four different distances with fixed initial speed before braking action was recorded. A software interface was designed to display and control real-time speed and pedal angle value during operation.

<div class="section abstract"><div class="htmlview paragraph">Lane detection plays a critical role in autonomous vehicles for safe and reliable navigation. Lane detection is traditionally accomplished using a camera sensor and computer vision processing. The downside of this traditional technique is that it can be computationally intensive when high quality images at a fast frame rate are used and has reliability issues from occlusion such as, glare, shadows, active road construction, and more. This study addresses these issues by exploring alternative methods for lane detection in specific scenarios caused from road construction-induced lane shift and sun glare. Specifically, a U-Net, a convolutional network used for image segmentation, camera-based lane detection method is compared with a radar-based approach using a new type of sensor previously unused in the autonomous vehicle space: radar retro-reflectors. This evaluation is performed using ground truth data, obtained by measuring the lane positions and transforming them into pixel coordinates. The performance of each method is assessed using the statistical <i>R</i><sup>2</sup> score, indicating the correlation between the detected lane lines and the ground truth. The results show that the U-Net camera-based method exhibits limitations in accurately detecting and aligning the lane lines, particularly in challenging scenarios. However, the radar-based lane detection method demonstrates a strong correlation with the ground truth which implies that the use of this sensor may improve current reliability issues from conventional camera lane detection approach. Furthermore, the study highlights the limitations of the U-Net model for camera lane detection, especially in scenarios with sun glare. This study shows that infrastructure-based radar retro-reflectors can improve autonomous vehicle lane detection reliability. The integration of different sensor modalities and the development of advanced computer vision algorithms are crucial for improving the accuracy, reliability, and energy efficiency of lane detection systems. Addressing these challenges contributes to the advancement of autonomous vehicles and the realization of safer and more efficient transportation systems.</div></div>

The recent development of autonomous vehicles has attracted much attention, but operating these vehicles may be too complex for average users. Therefore, we propose an intuitive, multimodal interface for the control of autonomous vehicles using speech and gesture recognition to interpret and execute the commands of users. For example, if the user says “turn there” while pointing at a landmark, the vehicle can utilize this behavior to correctly understand and comply with the user’s intent. To achieve this, we designed a two-part interface consisting of a multimodal understanding component and a dialog control component. Our multimodal understanding and dialog control components can be seen as a concatenation of two separate transducers. One transducer is used for multimodal understanding and the other for a conventional dialog system. We then construct a combined transducer from these two transducers. We developed various scenarios which might arise while operating an autonomous vehicle and displayed these scenes on a monitor. Subjects were then asked to operate a virtual car using speech commands and pointing gestures to control the vehicle while observing the monitor. The questionnaire results show that subjects felt they were able to easily and naturally operate the autonomous vehicle using utterances and gestures.

This article presents an in‐depth review of path following control strategies that are applicable to a wide range class of marine, ground, and aerial autonomous robotic vehicles. From a control system standpoint, path following can be formulated as the problem of stabilizing a path following error system that describes the dynamics of position and possibly orientation errors of a vehicle with respect to a path, with the errors defined in an appropriate reference frame. In spite of the large variety of path following methods described in the literature we show that, in principle, most of them can be categorized in two groups: stabilization of the path following error system expressed either in the vehicle's body frame or in a frame attached to a “reference point” moving along the path, such as a Frenet‐Serret (F‐S) frame or a Parallel Transport (P‐T) frame. With this observation, we provide a unified formulation that is simple but general enough to cover many methods available in the literature. We then discuss the advantages and disadvantages of each method, comparing them from the design and implementation standpoint. We further show experimental results of the path following methods obtained from field trials testing with under‐actuated and over‐actuated autonomous marine vehicles. In addition, we introduce open‐source Matlab and Gazebo/ROS simulation toolboxes that are helpful in testing path following methods before their integration in the combined guidance, navigation, and control systems of autonomous vehicles.

The rapid advancement of deep learning has significantly transformed the development of next-generation autonomous vehicles, enhancing both safety and efficiency. This paper explores the integration of deep learning techniques, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and reinforcement learning, in perception, decision-making, and control systems of autonomous vehicles. By leveraging vast datasets and real-time processing, deep learning enables precise object detection, path planning, and adaptive driving strategies. Furthermore, the implementation of sensor fusion techniques combining LiDAR, radar, and cameras enhances situational awareness, reducing the risk of accidents. Despite these advancements, challenges such as computational complexity, adversarial robustness, and ethical considerations remain key research areas. This study provides an overview of the current state-of-the-art deep learning applications in autonomous vehicles and discusses future directions toward fully autonomous, safer, and more efficient transportation systems.

Transportation sustainability is adversely affected by recurring traffic congestions, especially at urban intersections. Frequent vehicle deceleration and acceleration caused by stop-and-go behaviours at intersections due to congestion adversely impacts energy consumption and ambient air quality. Availability of the maturing vehicle technologies such as autonomous vehicles and Vehicle-To-Vehicle (V2V) / Vehicle-To-Infrastructure (V2I) communications provides technical feasibility to develop solutions that can reduce vehicle stops at intersections, hence enhance the sustainability of intersections. This paper presents a next-generation intersection control system for autonomous vehicles, which is named ACUTA. ACUTA employs an enhanced reservation-based control algorithm that controls autonomous vehicles’ passing sequence at an intersection. Particularly, the intersection is divided into n-by-n tiles. An intersection controller reserves certain time-space for each vehicle, and assures no conflict exists between reservations. The algorithm was modelled in microscopic traffic simulation platform VISSIM. ACUTA algorithm modelling as well as enhancement strategies to minimize vehicle intersection stops and eventually emission and energy consumption were discussed in the paper. Sustainability benefits offered by this next-generation intersection were evaluated and compared with traditional intersection control strategies. The evaluation reveals that multi-tile ACUTA reduces carbon monoxide (CO) and Particulate Matter (PM) 2.5 emissions by about 5% under low to moderate volume conditions and by about 3% under high volume condition. Meanwhile, energy consumption is reduced by about 4% under low to moderate volume conditions and by about 12% under high volume condition. Compared with four-way stop control, single-tile ACUTA reduces CO and PM 2.5 emissions as well as energy consumption by about 15% under any prevailing volume conditions. These findings validated the sustainability benefits of employing next-generation vehicle technologies in intersection traffic control. In addition, extending the ACUTA to corridor level was explored in the paper.

Lane detection is a crucial task in the field of autonomous driving, as it enables vehicles to safely navigate on the road by interpreting the high-level semantics of traffic signs. Unfortunately, lane detection is a challenging problem due to factors such as low-light conditions, occlusions, and lane line blurring. These factors increase the perplexity and indeterminacy of the lane features, making them hard to distinguish and segment. To tackle these challenges, we propose a method called low-light enhancement fast lane detection (LLFLD) that integrates the automatic low-light scene enhancement network (ALLE) with the lane detection network to improve lane detection performance under low-light conditions. Specifically, we first utilize the ALLE network to enhance the input image’s brightness and contrast while reducing excessive noise and color distortion. Then, we introduce symmetric feature flipping module (SFFM) and channel fusion self-attention mechanism (CFSAT) to the model, which refine the low-level features and utilize more abundant global contextual information, respectively. Moreover, we devise a novel structural loss function that leverages the inherent prior geometric constraints of lanes to optimize the detection results. We evaluate our method on the CULane dataset, a public benchmark for lane detection in various lighting conditions. Our experiments show that our approach surpasses other state of the arts in both daytime and nighttime settings, especially in low-light scenarios.

In this paper a novel method is presented for hierarchical control of autonomous vehicles consisting of high-level (HLC) and low-level (LLC) control systems. The LLC system can be commanded to assure a prescribed velocity and steering profile using PID-type active suspension, velocity and steering control. The outputs of the LLC system are the generalized forces and moments required by the vehicle. Because of its nature, the LLC system cannot eliminate position and orientation errors caused by the unknown centre of gravity point, drifting and time-varying friction. These errors are compensated by the HLC which uses the kinematic model of the vehicle to generate the reference trajectory from the prescribed profiles and employs a linear quadratic optimal controller to compensate the tracking errors. The control algorithm minimizes the perturbations and the optimal solution is realized as a time-varying state-feedback control law. The efficiency of the hierarchical vehicle control system is validated for realistic motion maneuvers by simulation on the nonlinear vehicle model using multibody robotic formalism.

Intelligent ground vehicles require automated steering control systems. The complexity of the automated steering systems has increased as the concurrent data receiving, processing, decision-making and monitoring all happen simultaneously in super-fast sampling rates. The research reported in this paper focuses on the neural network training and machine learning approach for an automated steering system. The essential information of the steering controller was trained using artificial neural network (ANN) and pattern recognition algorithm approaches. The objective is to investigate the design of ANN training and deep machine learning on collected data from sensors of steering wheel angular position, speed, steering column torque, and ego vehicle speed and generating acceptable steering commands for the vehicle. The results of the research showed that the proposed network control system had trained and validated more than 96.5% steering system behavior patterns and adapted large random disturbances of the steering controller commands. It is, therefore, necessary to develop artificial intelligence methodologies in automated steering systems of autonomous vehicles with neural network representing the main topology blocks of the control system architecture and utilize ANN abstraction in the control system of autonomous vehicle steering control system.

With the advancements in utilizing Artificial Intelligence (AI) in embedded safety-critical systems based on Field-Programmable Gate Arrays (FPGAs), assuring that these systems meet their safety requirements is of paramount importance for their revenue service. Based on this context, this paper has two main objectives. The first of them is to present the Safety ArtISt method, developed by the authors to guide the lifecycle of AI-based safety-critical systems, and emphasize its FPGA-oriented tasks and recommended practice towards safety assurance. The second one is to illustrate the application of Safety ArtISt with an FPGA-based braking control system for autonomous vehicles relying on explainable AI generated with High-Level Synthesis. The results indicate that Safety ArtISt played four main roles in the safety lifecycle of AI-based systems for FPGAs. Firstly, it provided guidance in identifying the safety-critical role of activities such as sensitivity analyses for numeric representation and FPGA dimensioning to achieve safety. Furthermore, it allowed building qualitative and quantitative safety arguments from analyses and physical experimentation with actual FPGAs. It also allowed the early detection of safety issues—thus reducing project costs—and, ultimately, it uncovered relevant challenges not discussed in detail when designing safety-critical, explainable AI for FPGAs.

Modern cars are incorporating an increasing number of driver assist features, among which automatic lane keeping. The latter allows the car to properly position itself within the road lanes, which is also crucial for any subsequent lane departure or trajectory planning decision in fully autonomous cars. Traditional lane detection methods rely on a combination of highly-specialized, hand-crafted features and heuristics, usually followed by post-processing techniques, that are computationally expensive and prone to scalability due to road scene variations. More recent approaches leverage deep learning models, trained for pixel-wise lane segmentation, even when no markings are present in the image due to their big receptive field. Despite their advantages, these methods are limited to detecting a pre-defined, fixed number of lanes, e.g. ego-lanes, and can not cope with lane changes. In this paper, we go beyond the aforementioned limitations and propose to cast the lane detection problem as an instance segmentation problem - in which each lane forms its own instance - that can be trained end-to-end. To parametrize the segmented lane instances before fitting the lane, we further propose to apply a learned perspective transformation, conditioned on the image, in contrast to a fixed ”bird’s-eye view” transformation. By doing so, we ensure a lane fitting which is robust against road plane changes, unlike existing approaches that rely on a fixed, predefined transformation. In summary, we propose a fast lane detection algorithm, running at 50 fps, which can handle a variable number of lanes and cope with lane changes. We verify our method on the tuSimple dataset and achieve competitive results.

This paper presents a novel approach for lane detection using a Convolutional Neural Network with Line Detection (CNN-LD) methodology, aimed at enhancing the accuracy and efficiency of road lane recognition. The proposed model leverages advanced pre-processing techniques, including distortion correction, color space transformation, and noise reduction, to prepare input images for effective feature extraction. The methodology incorporates edge detection using Sobel filters and the Hough transform for precise lane identification. A comprehensive dataset of 4,000 annotated images captured under diverse lighting conditions—daytime, low light, and night-time—was utilized to train and evaluate the model. The CNN-LD framework demonstrated superior performance, achieving an accuracy of 98.92% and an F1-Score of 97.90%, significantly outperforming traditional methods. The integration of the Kanade–Lucas–Tomasi (KLT) tracker ensures robust lane tracking, even in challenging environments. Experimental results indicate that the proposed approach effectively addresses common issues in lane detection, such as variations in visibility and road conditions. This research contributes to the development of intelligent transportation systems, providing a reliable solution for autonomous driving applications. Future work will focus on improving model robustness against adverse weather conditions and integrating multimodal data for enhanced lane detection capabilities.

There have been many studies that developed approaches for real-time lane and vehicle detection. However, the majority of implementations that have been made with these approaches are focused on cars. On this paper, the existing approach of object detection is implemented for motorcycle detection. Lane detection is also incorporated for the validation of object's position. We employ Haar cascade classifier approach for motorcycle detection and edge detection approach for lane detection. In order to refine the detection result, angle-based elimination is applied to lines in lane detection. For the refinement of motorcycle detection, object candidates are eliminated by object's position on lane, frequency of occurrence, and variation of horizontal edges. Experimental results show that these approaches followed by the refinement method results provide better precision of motorcycle detection. This implementation is also able to operate in real-time.

An advanced driver-assistance system (ADAS), based on lane detection technology, detects dangerous situations through various sensors and either warns the driver or takes over direct control of the vehicle. At present, cameras are commonly used for lane detection; however, their performance varies widely depending on the lighting conditions. Consequently, many studies have focused on using radar for lane detection. However, when using radar, it is difficult to distinguish between the plain road surface and painted lane markers, necessitating the use of radar reflectors for guidance. Previous studies have used long-range radars which may receive interference signals from various objects, including other vehicles, pedestrians, and buildings, thereby hampering lane detection. Therefore, we propose a lane detection method that uses an impulse radio ultra-wideband radar with high-range resolution and metal lane markers installed at regular intervals on the road. Lane detection and departure is realized upon using the periodically reflected signals as well as vehicle speed data as inputs. For verification, a field test was conducted by attaching radar to a vehicle and installing metal lane markers on the road. Experimental scenarios were established by varying the position and movement of the vehicle, and it was demonstrated that the proposed method enables lane detection based on the data measured.

Dealing with complex and variable road scenes is a challenge for autonomous driving, so lane detection with good performance is crucial. Currently, mainstream lane detection methods are divided into semantic segmentation-based and instance segmentation-based methods. The former is limited to detect a pre-defined, fixed number of lanes and unable to cope with lane changes, while the latter requires post-clustering processing despite a variable number of lanes detected. In this paper, we propose a novel instance segmentation-based method using lane locations to get an arbitrary number of lane instances directly. In addition, in order to improve the speed of lane detection, we employee key points to represent lanes instead of pixels to reduce the granularity of segmentation. In conclusion, we propose a real-time lane detection method which can predict an arbitrary number of lanes directly. We validate our method on two public datasets and the competitive results are obtained by comparing with existing methods.