Road Scenarios Research Articles

A nonlinear model predictive control for air suspension of hub motor electric vehicle based on hybrid H2/H∞ state estimation

To alleviate the vibration from the road irregularities and the unbalanced electromagnetic forces (UEFs), deteriorating the dynamic performance of hub motor electric vehicles (HM-EVs), a novel nonlinear model predictive control (NMPC) is proposed based on a hybrid H2/H ∞ filtering algorithm for the HM-EVs with air suspension (HM-AS). The dynamic HM-AS model involves the electric vehicle’s longitudinal, lateral, and vertical motion. The air suspension system between the body and the hub motor enhances ride quality and insulates the oscillation delivered to the vehicle body. Then, the dynamic HM-AS model is validated by the actual vehicle test, and the proposed filter is developed to obtain the vehicle states. Besides, the NMPC controller guarantees the dynamic performance of HM-AS by intervening in vehicle attitude, road-holding stability, motor safety, and ride comfort. Finally, compared with the application of PID and MPC, the efficiency of the proposed method is demonstrated based on several random road scenarios. The results indicate the proposed algorithm can alleviate the dynamic performance of HM-AS and reduce motor vibration.

Traffic Congestion Detection Using YOLOv8 Algorithm With CCTV Data

Community development and growth according to data from the Central Java Statistics Agency regarding the number of vehicles in Central Java Province in 2021 is 20 320 743. The increasing growth of society has caused vehicle density which is a serious problem in urban areas. This study developed a congestion detection system using the YOLOv8 algorithm to analyze traffic density from CCTV footage. Automated detection of traffic congestion is a critical challenge in urban transport management. YOLOv8, a fast and accurate object detection algorithm, is used to identify vehicles and count their number in various areas of the highway. This information is then processed to assess road congestion conditions, with the aim of detecting congestion. The data obtained were tested on two road scenarios and traffic conditions to evaluate the performance of the system. The results showed that the proposed system was able to detect congestion with an accuracy level of 59.2% from several experiments. The use of YOLOv8 enables real-time detection with efficient computing resources, making it a potential solution for large-scale deployment. This research shows that the incorporation of advanced object detection algorithms such as YOLOv8 with CCTV data can provide an effective solution for traffic management in large cities. This system is expected to improve response to congestion, help control traffic, and reduce the negative impact of congestion in urban areas

Road surface semantic segmentation for autonomous driving

Although semantic segmentation is widely employed in autonomous driving, its performance in segmenting road surfaces falls short in complex traffic environments. This study proposes a frequency-based semantic segmentation with a transformer (FSSFormer) based on the sensitivity of semantic segmentation to frequency information. Specifically, we propose a weight-sharing factorized attention to select important frequency features that can improve the segmentation performance of overlapping targets. Moreover, to address boundary information loss, we used a cross-attention method combining spatial and frequency features to obtain further detailed pixel information. To improve the segmentation accuracy in complex road scenarios, we adopted a parallel-gated feedforward network segmentation method to encode the position information. Extensive experiments demonstrate that the mIoU of FSSFormer increased by 2% compared with existing segmentation methods on the Cityscapes dataset.

High-risk powered two-wheelers scenarios generation for autonomous vehicle testing using WGAN

Objective Autonomous vehicles (AVs) have the potential to revolutionize the future of mobility by significantly improving traffic safety. This study presents a novel method for validating the safety performance of AVs in high-risk scenarios involving powered 2-wheelers (PTWs). By generating high-risk scenarios using in-depth crash data, this study is devoted to addressing the challenge of public road scenarios in testing, which often lack the necessary complexity and risk to effectively evaluate the capabilities of AVs in high-risk situations. Method Our approach employs a Wasserstein generative adversarial network (WGAN) to generate high-risk scenes, particularly focusing on PTW scenarios. By extracting 314 car-to-PTW crashes from the China In-depth Mobility Safety Study–Traffic Accident database, we simulate outcomes using PC-Crash software. The data are divided into scenes at 0.1-s intervals, with WGAN generating numerous high-risk scenes. By using a cumulative distribution function (CDF), we sampled and analyzed the vehicle’s dynamic information to generate complete scenarios applicable to the test. The validation process involves using the SVL Simulator and the Baidu Apollo joint simulation platform to evaluate the AV’s driving behavior and interactions with PTWs. Results This study evaluates model generation results by comparing distributions using Wasserstein distance as an indicator. The generator converges after approximately 200 epochs, with the iterator converging quickly. Subsequently, 10,000 new scenes are then generated. The distribution of several key parameters in the generated scenes can be found to approximate that of the original scenes. After sampling, the usability of generated scenarios is 64.76%. Virtual simulations confirm the effectiveness of the scenario generation method, with a generated scenario crash rate of 16.50% closely reflecting the original rate of 15.0%, showcasing the method’s capacity to produce realistic and hazardous scenarios. Conclusions The experimental results suggest that these scenarios exhibit a level of risk similar to the original crashes and are effective for testing AVs. Consequently, the generated scenarios enhance the diversity of the scenario library and accelerate the overall testing process of AVs.

Application of IMU/GPS Integrated Navigation System Based on Adaptive Unscented Kalman Filter Algorithm in 3D Positioning of Forest Rescue Personnel.

Utilizing reliable and accurate positioning and navigation systems is crucial for saving the lives of rescue personnel and accelerating rescue operations. However, Global Navigation Satellite Systems (GNSSs), such as GPS, may not provide stable signals in dense forests. Therefore, integrating multiple sensors like GPS and Inertial Measurement Units (IMUs) becomes essential to enhance the availability and accuracy of positioning systems. To accurately estimate rescuers' positions, this paper employs the Adaptive Unscented Kalman Filter (AUKF) algorithm with measurement noise variance matrix adaptation, integrating IMU and GPS data alongside barometric altitude measurements for precise three-dimensional positioning in complex environments. The AUKF enhances estimation robustness through the adaptive adjustment of the measurement noise variance matrix, particularly excelling when GPS signals are interrupted. This study conducted tests on two-dimensional and three-dimensional road scenarios in forest environments, confirming that the AUKF-algorithm-based integrated navigation system outperforms the traditional Extended Kalman Filter (EKF), Unscented Kalman Filter (UKF), and Adaptive Extended Kalman Filter (AEKF) in emergency rescue applications. The tests further evaluated the system's navigation performance on rugged roads and during GPS signal interruptions. The results demonstrate that the system achieves higher positioning accuracy on rugged forest roads, notably reducing errors by 18.32% in the north direction, 8.51% in the up direction, and 3.85% in the east direction compared to the EKF. Furthermore, the system exhibits good adaptability during GPS signal interruptions, ensuring continuous and accurate personnel positioning during rescue operations.

Experimental Validation of Truck Cab Suspension Model and Ride Comfort Improvement under Various Semi-Active Control Strategies

The semi-active cab suspension system for trucks is gaining increasing importance due to its economic advantages, low energy consumption, and significant enhancement of ride comfort. This paper investigates the effects of three control methods on improving ride comfort of semi-active cab suspension systems under random and bump road conditions: Proportional-Integral-Derivative (PID) control, fuzzy PID control, and Model Predictive Control (MPC). Initially, an accurate multi-degree-of-freedom truck cab suspension model was developed and validated through actual road tests. Based on this model, three control strategies were designed and implemented. Finally, the effectiveness of each control strategy was evaluated under various road conditions, including random and bump road scenarios. The results indicate that these control strategies can effectively reduce vibrations and impacts, significantly improving ride comfort. This improvement is crucial for alleviating driver fatigue and enhancing driving safety. Among them, the MPC control showed superior performance, reducing vibrations by at least 31% under both random and bump road conditions, outperforming PID and Fuzzy PID in terms of effectiveness and robustness.

Effect of Takeover Request Time and Warning Modality on Trust in L3 Automated Driving.

This study investigated the effects of four takeover request (TOR) times and seven warning modalities on performance and trust in automated driving on a mildly congested urban road scenario, as well as the relationship between takeover performance and trust. Takeover is crucial in L3 automated driving, where human-machine codriving is employed. Establishing trust in takeover scenarios among drivers can enhance the acceptance of autonomous vehicles, thereby promoting their widespread adoption. Using a driving simulator, data from 28 participants, including collision counts, takeover time (ToT), electrodermal activity (EDA) data, and self-reported trust scores, were collected and analyzed primarily using Generalized Linear Mixed Models (GLMM). Collisions during the takeover undermined participants' trust in the autonomous driving system. As TOR time increased, participants' trust improved, and the longer TOR time did not lead to participant confusion. There was no significant relationship between warning modality and trust. Furthermore, the combination of three warning modalities did not exhibit a notable advantage over the combination of two modalities. The study examined the effects of TOR time and warning modality on trust, as well as preliminarily explored the potential association between takeover performance, including collisions and ToT, and trust in autonomous driving takeovers. Researchers and designers of automotive interactions were given referenceable TOR time and warning modality by this study, which extended the autonomous driving takeover scenarios. These findings contributed to boosting drivers' confidence in transferring control to the automated system.

Thermoelectric energy harvesting associated with heat pipes for monitoring highways weather conditions

This work aims to develop a prototype for autonomously monitoring highway weather conditions using thermoelectric energy. The prototype utilizes solar thermal energy, heat absorbed by the asphalt and soil heat to generate, convert, manage, and store energy. The study investigates the optimal functioning of the thermoelectric generator, including utilizing the soil as a heat sink and incorporating passive thermal control devices like heat pipes. A commercial ultra-low power converter model LTC3108 was experimentally tested for efficient energy conversion. The monitoring system is designed to acquire readings from sensors measuring relevant climate parameters such as temperature, atmospheric pressure, and humidity, focusing on ultra-low power characteristics. The acquired data is transmitted via LoRa technology to a server for processing and analysis. The prototype generated 286.24 J of energy with a maximum temperature gradient of 4.25 ºC in the thermoelectric generator. The energy cost of transmitting a 40-byte message through the LoRaWAN module was 0.625 J. The proposed climate data acquisition circuit had a theoretical consumption of 17.69 J. Experimental tests with the LTC3108 converter, and a 0.22 F supercapacitor demonstrated successful data transmission. This work provides a solid foundation for future studies utilizing thermoelectric energy in highway applications, resulting in a prototype suitable for real-world road scenarios.

Design and optimization of two-stage controller for three-phase multi-converter/multi-machine electric vehicle

Abstract Electric vehicles (EVs) cut greenhouse gas emissions and our use of non-renewable resources, making them more attractive. EVs have lower fuel and maintenance expenses than internal combustion engine automobiles. This study proposes a multi-converter/Multi‒Machine system with two induction motors (IM) that drive a pure EV’s rear wheels. EV two-stage controllers using a simple Adaline neural network (NN) regulate Field-Oriented regulate of a three-phase IM. To control IM speed, the first controller level is a hybrid proportional–integral (PI) with a robust integral sign of error (RISE) controller. Injection torque is controlled by PI‒adaline NN in the second controller step. The simple Adaline NN improves two-stage controller performance. The Multi-Verse Optimization algorithm found the ideal RISE parameter to improve EV drive system performance. A plug-in EV’s linear speed is controlled by the Electronic Differential Controller (EDC). It uses the driver’s reference speed and steering angle to set each driving wheel’s reference speed. EDC adjusts wheel speeds to enhance traction and stability during cornering, accelerating, and decelerating. Utilizing this information, the EDC can effectively distribute power and torque to the wheels, thereby enhancing vehicle handling and overall performance. Three distinct road scenarios and the designated driving route topology have been used to act and demonstrate the resistive forces that affected the EV while it was traveling down the road. By using Matlab (Simulink), EV’s roadworthiness and efficiency will be evaluated.

Wireless channel characterizations in UMi scenarios via ray-tracing at 28 GHz: A perspective of asymmetric beams

As a novel communication pattern, the asymmetric beams adopt a strategy of different beamwidths for a specific link to reduce the beam alignment overheads and energy consumption. A good and thorough knowledge of the radio propagation characteristics is pivotal for further network deployment and optimization of wireless mobile communication systems. In this paper, a multiple-bounce beam channel model is proposed based on the ray-tracing considering the beamforming effects. Besides, a space–time–frequency (STF) power density profile reconstruction method is proposed. Relevant simulations are conducted to emulate an urban micro-cellular (UMi) street scenario at 28 GHz under the case of perfect beam alignment. On this basis, the beam-dependent small-scale fading properties (including STF power density profiles, delay spread, Doppler frequency shift spread, and angular spread) together with the large-scale fading characteristics (involving path loss and shadow fading) are fully investigated. Results reveal that the downlink of asymmetric beams presents more dispersions in contrast to the uplink in the STF domains. Furthermore, the shadow fading variances are asymmetric over different transceivers array element numbers.

Traffic flow model considering the dynamics prediction of the leading vehicle

Traffic flow modeling has become increasingly important in today’s society due to the growing number of vehicles on the roads, leading to congestion and traffic incidents. Mathematical modeling can aid in the planning and optimization of transportation systems, enhancing overall efficiency and safety. The main result of this study is a mathematical model that describes the dynamics of multiple vehicles, taking into account the prediction of the leading vehicle’s behavior. The model is formulated as a system of delay differential equations. A computer program has been developed based on this model, which simulates traffic flow in various road scenarios. The simulation results are consistent with observed data from real traffic flows.

Z-YOLOv8s-based approach for road object recognition in complex traffic scenarios

Object detection in road scenarios is crucial for intelligent transport systems and autonomous driving, but complex traffic conditions pose significant challenges. This paper introduces Z-You Only Look Once version 8 small (Z-YOLOv8s), designed to improve both accuracy and real-time efficiency under real-world uncertainties. By incorporating Revisiting Perspective Vision Transformer (RepViT) and C2f into the YOLOv8s framework, and integrating the Large Selective Kernel Network (LSKNet), the model enhances spatial feature extraction. Additionally, the YOLOv8s backbone is optimized with Space-to-Depth Convolution (SPD-Conv) for better small object detection. The Softpool-Spatial Pyramid Pooling Fast (SoftPool-SPPF) module ensures precise characteristic information preservation. Z-YOLOv8s improves mean average precision (mAP)@0.5 on the Berkeley Deep Drive 100 K (BDD100K) and Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI) datasets by 7.3 % and 3.8 %, respectively. It also achieves accuracy increases of 5.7 % and 6.5 % in Average Precision (AP)-Small, and a real-time detection speed of 78.41 frames per second (FPS) on the BDD100K. Z-YOLOv8s balances detection precision and processing speed more effectively than other detectors, as demonstrated by experimental results and comparisons.

A Faster and Lightweight Lane Detection Method in Complex Scenarios

Lane detection is a crucial visual perception task in the field of autonomous driving, serving as one of the core modules in advanced driver assistance systems (ADASs).To address the insufficient real-time performance of current segmentation-based models and the conflict between the demand for high inference speed and the excessive parameters in resource-constrained edge devices (such as onboard hardware, mobile terminals, etc.) in complex real-world scenarios, this paper proposes an efficient and lightweight auxiliary branch network (CBGA-Auxiliary) to tackle these issues. Firstly, to enhance the model’s capability to extract feature information in complex scenarios, a row anchor-based feature extraction method based on global features was adopted. Secondly, employing ResNet as the backbone network and CBGA (Conv-Bn-GELU-SE Attention) as the fundamental module, we formed the auxiliary segmentation network, significantly enhancing the segmentation training speed of the model. Additionally, we replaced the standard convolutions in the branch network with lightweight GhostConv convolutions. This reduced the parameters and computational complexity while maintaining accuracy. Finally, an additional enhanced structural loss function was introduced to compensate for the structural defect loss issue inherent in the row anchor-based method, further improving the detection accuracy. The model underwent extensive experimentation on the Tusimple dataset and the CULane dataset, which encompass various road scenarios. The experimental results indicate that the model achieved the highest F1 scores of 96.1% and 71.0% on the Tusimple and CULane datasets, respectively. At a resolution of 288 × 800, the ResNet18 and ResNet34 models achieved maximum inference speeds of 410FPS and 280FPS, respectively. Compared to existing SOTA models, it demonstrates a significant advantage in terms of inference speed. The model achieved a good balance between accuracy and inference speed, making it suitable for deployment on edge devices and validates the effectiveness of the model.

Autonomous Vehicle Safety through the SIFT Method: A Conceptual Analysis

This study aims to provide a conceptual analysis of the dynamic transformations occurring in an autonomous vehicle (AV), placing a specific emphasis on the safety implications for pedestrians and passengers. AV, also known as self-driving automobiles, are positioned as potential disruptors in the contemporary transportation landscape, offering heightened safety and improved traffic efficiency. Despite these promises, the intricate nature of road scenarios and the looming specter of misinformation pose challenges that can compromise the efficacy of AV decision-making. A crucial aspect of the proposed verification process is the incorporation of the stop, investigate the source, find better coverage, trace claims, quotes, and media to the original context (SIFT) method. The SIFT method, originally designed to combat misinformation, emerges as a valuable mechanism for enhancing AV safety by ensuring the accuracy and reliability of information influencing autonomous decision-making processes.

An integrated navigation algorithm assisted by CNN-Informer during short-time GNSS outages

Abstract Inertial Navigation System (INS) and Global Navigation Satellite System (GNSSs) are commonly used in integrated navigation systems. The GNSS navigation system, however, is not autonomous, and its signals are susceptible to environmental influences leading to poor navigation results. In order to improve the positioning accuracy of the INS/GNSS integrated navigation system during GNSS outages, a hybrid algorithm of Convolutional Neural Network (CNN)-Informer model-assisted INS is proposed. The CNN-Informer model combines the advantages of each of the convolutional neural network and the Informer network. It utilizes CNN to rapidly extract spatial features from input data, employs the Informer network to establish relationships between inputs and outputs, and acquires pseudo-GNSS signals to compensate for position errors in the INS. Lastly, we evaluate the proposed algorithm through six sets of experiments conducted on public datasets and real road scenarios. The comparative results demonstrate that the proposed method offers a more accurate and reliable solution during GNSS outages. Specifically, CNN-Informer can improve navigation accuracy by 81.46% over MLP and by 58.91% over LSTM during 20-second GNSS outages.

Devising a High-Level Command Language for the Teleoperation of Autonomous Vehicles

Autonomous vehicles (AVs) are rapidly evolving as a novel way of transportation. Nevertheless, there is a consensus that AVs cannot address all traffic scenarios independently. Consequently, there arises a need for remote human intervention. To pave the way for large-scale deployment of AVs onto public roadways, innovative models of remote operation must evolve. Such a paradigm is Tele-assistance, which posits that the low-level control of AVs should be delegated through high-level commands. Our work explores how such a command language should be constructed as a first step in designing a Tele-assistance user interface. Through interviews with 17 experienced teleoperators, we elicit a set of discrete commands that a remote operator can use to resolve various road scenarios. Subsequently, we create a scenario-command mapping and a thematic classification of the defined commands. Finally, we present an initial Tele-assistance interface design based on these commands.

Safe platooning and merging control using constructive barrier feedback

This paper proposes a novel formation control design for safe platooning and merging of a group of vehicles in multi-lane road scenarios. Provided a leader vehicle is independently controlled, the objective is controlling the follower vehicles to drive in the desired lane with a constant desired distance behind the neighboring (preceding) vehicle while preventing collisions with both the neighboring vehicle and the road’s edges. Inspired by the recent concept of constructive barrier feedback, the proposed controller for each follower vehicle is composed of two parts: one is the nominal controller that ensures its tracking of the neighboring vehicle; another is for collision avoidance by using divergent flow as a dissipative term, which slows down the relative velocity in the direction of the neighboring vehicle and road edges without compromising the nominal controller’s performance. The key contribution of this work is that the proposed control method ensures collision-free platooning and merging control in multi-lane road scenarios with computational efficiency and systematic stability analysis. Simulation results are provided to demonstrate the effectiveness of the proposed algorithms.

Investment Feasibility and Strategic Development Scenarios of Yogyakarta-Bawen Toll Road

This study examines the feasibility of the investment in the Yogyakarta-Bawen toll road project by analyzing traffic conditions, expenditure costs, toll revenues, and investment value. Simulation using PTV Visum shows a significant increase in the volume-to-capacity ratio (VCR) on the national road sections around the toll road until 2061. The modeling result also indicates that the operation of the toll road reduces traffic loads on several surrounding national road sections with a decrease in VCR. The analysis results reveal a negative net present value (NPV) amounting to -Rp.506,560,648,100, and an internal rate of return (IRR) of 11.49% is under the discount rate (12.03%). In the tariff adjustment scenario, the project shows an IRR of 12.48% with an NPV of Rp 575,501 million, and the payback period (PBP) is achieved after 16 years. In the concession adjustment scenario, the IRR is 12.12% with an NPV of Rp 123,461 million, and the PBP is achieved after 17 years. Meanwhile, the tariff and concession adjustment scenario show an IRR of 12.48% with an NPV of Rp 652,033 million, and the PBP is achieved after 16 years. Based on the investment feasibility evaluation, the recommended best strategy is tariff adjustment. This strategy allows for an optimal increase in toll revenue and investment returns. It is expected that the Yogyakarta-Bawen toll road project can achieve better investment feasibility and provide long-term benefits to investors, road users, and the overall community.

Traffic Sign Recognition Using Deep Learning

Abstract: Traffic sign recognition is a crucial component in advanced driver assistance systems and autonomous vehicles, enhancing road safety and overall transportation efficiency. Deep learning, specifically convolutional neural networks (CNNs), has emerged as a powerful tool for image based recognition tasks. The proposed deep learning-based traffic sign recognition system exhibits promising results, providing a foundation for the development of intelligent transportation systems. The trained model demonstrates remarkable accuracy in recognizing a wide range of traffic signs under different scenarios, including challenging lighting conditions and occlusions. The system's real-time performance is evaluated on both simulated and actual road scenarios, showcasing its feasibility for deployment in practical driving environments. The integration of such technology into vehicles holds great potential for enhancing road safety, reducing accidents, and contributing to the evolution of autonomous driving technology.

3D Object Detection under Urban Road Traffic Scenarios Based on Dual-Layer Voxel Features Fusion Augmentation.

To enhance the accuracy of detecting objects in front of intelligent vehicles in urban road scenarios, this paper proposes a dual-layer voxel feature fusion augmentation network (DL-VFFA). It aims to address the issue of objects misrecognition caused by local occlusion or limited field of view for targets. The network employs a point cloud voxelization architecture, utilizing the Mahalanobis distance to associate similar point clouds within neighborhood voxel units. It integrates local and global information through weight sharing to extract boundary point information within each voxel unit. The relative position encoding of voxel features is computed using an improved attention Gaussian deviation matrix in point cloud space to focus on the relative positions of different voxel sequences within channels. During the fusion of point cloud and image features, learnable weight parameters are designed to decouple fine-grained regions, enabling two-layer feature fusion from voxel to voxel and from point cloud to image. Extensive experiments on the KITTI dataset demonstrate the significant performance of DL-VFFA. Compared to the baseline network Second, DL-VFFA performs better in medium- and high-difficulty scenarios. Furthermore, compared to the voxel fusion module in MVX-Net, the voxel feature fusion results in this paper are more accurate, effectively capturing fine-grained object features post-voxelization. Through ablative experiments, we conducted in-depth analyses of the three voxel fusion modules in DL-VFFA to enhance the performance of the baseline detector and achieved superior results.