Search Results (140)

Legal requirements for minimum distances between vehicles are often not met for short periods of time, especially when changing lanes on multi-lane roads. These situations are typically non-hazardous, as human drivers anticipate surrounding traffic, allowing for shorter headways and improved traffic flow. Automated vehicles (AVs), however, are typically designed to maintain strict headway limits, potentially reducing traffic efficiency. Therefore, legal questions arise as to whether mandatory gap and headway limits for AVs may be violated during periods of non-compliance. While traffic flow simulation is a common method for analyzing AV impacts, previous studies have typically modeled AV behavior using driver models originally designed to replicate human driving. These models are not well suited for representing clearly defined, structured non-compliant maneuvers, as they cannot simulate intentional, rule-deviating strategies. This paper addresses this gap by introducing a concept for AV non-compliant behavior and implementing it as a module within a pre-existing AV driver model. Simulations were conducted on a three-lane highway with an on-ramp under varying traffic volumes and AV penetration rates. The results showed that, with an AV-penetration rate of more than 25%, road capacity at highway entrances could be increased and travel times reduced by over 20%, provided that AVs were allowed to merge with a legal gap of 0.9 s and a minimum non-compliant gap of 0.6 s lasting up to 3 s. This suggests that performance gains are achievable under adjusted legal requirements. In addition, the proposed framework can serve as a foundation for further development of AV driver models aiming at improving traffic efficiency while maintaining regulatory compliance. Full article

Path planning and collision avoidance are essential components of an autonomous driving system (ADS), ensuring safe navigation in complex environments shared with other road users. High-quality planning and reliable obstacle avoidance strategies are essential for advancing the SAE autonomy level of autonomous vehicles, which can largely reduce the risk of traffic accidents. In daily driving scenarios, lane changing is a common maneuver used to avoid unexpected obstacles such as parked vehicles or suddenly appearing pedestrians. Notably, lane-changing behavior is also widely regarded as a key evaluation criterion in driver license examinations, highlighting its practical importance in real-world driving. Motivated by this observation, this paper aims to develop an autonomous lane-changing system capable of dynamically avoiding obstacles in multi-lane traffic environments. To achieve this objective, we propose a hierarchical decision-making and control framework in which a Double Deep Q-Network (DDQN) agent operates as the high-level planner to select lane-level maneuvers, while a High-Order Control Lyapunov Function–High-Order Control Barrier Function–based Quadratic Program (HOCLF-HOCBF-QP) serves as the low-level controller to ensure safe and stable trajectory tracking under dynamic constraints. Simulation studies are used to evaluate the planning efficiency and overall collision avoidance performance of the proposed hierarchical control framework. The results demonstrate that the system is capable of autonomously executing appropriate lane-changing maneuvers to avoid multiple obstacles in complex multi-lane traffic environments. In computational cost tests, the low-level controller operates at 100 Hz with an average solve time of 0.66 ms per step, and the high-level policy operates at 5 Hz with an average solve time of 0.60 ms per step. The results demonstrate real-time capability in autonomous driving systems. Full article

Validating the safety and reliability of automated driving systems is a critical challenge in the development of autonomous driving technology. Such systems must reliably replicate human driving behavior across scenarios of varying complexity and criticality. Ensuring this level of accuracy necessitates robust testing methodologies that can systematically assess performance under various driving conditions. Scenario-based testing addresses this challenge by recreating safety-critical situations at varying levels of abstraction, from simulations to real-world field tests. However, conventional parameterized models for scenario generation are often resource intensive, prone to bias from simplifications, and limited in capturing realistic vehicle trajectories. To overcome these limitations, the paper explores AI-based methods for scenario generation, with a focus on the cut-in maneuver. Four different approaches are trained and compared: Variational Autoencoder enhanced with a convolutional neural network (VAE), a basic Generative Adversarial Network (GAN), Wasserstein GAN (WGAN), and Time-Series GAN (TimeGAN). Their performance is assessed with respect to their ability to generate realistic and diverse trajectories for the cut-in scenario using qualitative analysis, quantitative metrics, and statistical analysis. Among the investigated approaches, VAE demonstrates superior performance, effectively generating realistic and diverse scenarios while maintaining computational efficiency. Full article

This study introduces a novel magnetorheological (MR) damper for semi-active vehicle suspension systems that enhance ride comfort and handling stability. The proposed damper integrates reverse and normal damping modes, enabling independent control of rebound and compression strokes through an external MR valve. This configuration supports four damping modes—Soft/Soft, Hard/Soft, Soft/Hard, and Hard/Hard—allowing adaptability to varying driving conditions. Magnetic circuit optimization ensures rapid damping force adjustments (≈10 ms), while a semi-active control algorithm incorporating skyhook logic, roll, dive, and squat control strategies was implemented. Experimental validation on a mid-sized sedan demonstrated significant improvements, including a 30–40% reduction in vertical acceleration and pitch/roll rates. These enhancements improve vehicle safety by reducing body motion during critical maneuvers, potentially lowering accident risk and driver fatigue. In addition to performance gains, the simplified MR damper architecture and modular control facilitate easier integration into diverse vehicle platforms, potentially streamlining vehicle design and manufacturing processes and enabling cost-effective adoption in mass-market applications. These findings highlight the potential of MR dampers to support next-generation vehicle architectures with enhanced adaptability and manufacturability. Full article

In recent years, system intelligence has revolutionized various domains, including the automotive industry, which has fully incorporated intelligence through the emergence of Advanced Driver Assistance Systems (ADAS). Within this transformative context, Autonomous Parking Systems (APS) have emerged as a foundational component, revolutionizing the way vehicles navigate and park with precision and efficiency. This paper presents a comprehensive approach to autonomous parallel parking, leveraging advancements in Artificial Intelligence (AI). Three state-of-the-practice approaches—Imitation Learning (IL), deep Reinforcement Learning (deep RL), and a hybrid deep RL-IL method—are employed and evaluated through extensive experiments in the CARLA Simulator using randomly generated parallel parking scenarios. Results demonstrate that the hybrid deep RL-IL approach achieves a remarkable success rate of 98% in parking attempts, surpassing the individual IL and deep RL methods. Furthermore, the proposed hybrid model exhibits superior maneuvering efficiency and higher overall reward accumulation. These findings underscore the advantages of combining deep RL and IL, representing a significant advancement in APS technology. Full article

With the rapid advancement of autonomous driving (AD) technology, its application in road traffic has garnered increasing attention. This study analyzes 534 AD and 82,030 human driver traffic accidents and employs SMOTE to balance the sample sizes between the two groups. Using association rule mining, this study identifies key risk factors and behavioral patterns. The results indicate that while both AD and human driver accidents exhibit seasonal trends, their risk characteristics and distributions differ markedly. AD accidents are more frequent in summer (July–August) on clear days and tend to occur at intersections and on streets, with a higher proportion of non-injury collisions observed at night. Collisions involving non-motorized road users are more prevalent in human driver accidents. AD systems show certain advantages in detecting non-motorized vehicles and performing low-speed evasive maneuvers, particularly at night; however, limitations remain in perception and decision-making under complex conditions. Human driver accidents are more susceptible to driver-related factors such as fatigue, distraction, and risk-prone behaviors. Although AD accidents generally result in lower injury severity, further technological refinement and scenario adaptability are required. This study provides insights and recommendations to enhance the safety performance of both AD and human-driven systems, offering valuable guidance for policymakers and developers. Full article

This paper presents a calibration technique for the Intelligent Driver Model (IDM), a car-following model that considers the physical interpretation of each parameter. Using an instrumented vehicle, trajectory data were gathered for a group of Portuguese drivers. The data included various basic scenarios, such as unrestricted acceleration and deceleration maneuvers, as well as following other cars in steady-state conditions. The calibration process involved two steps. In the first step, specific parameters that have clear physical interpretations were manually adjusted to accurately reproduce the speed patterns of basic driving scenarios. In the second step, the obtained results were used to establish the limits of values for a simultaneous calibration procedure. The results demonstrate that the calibration procedure enables precise replication of the actual trajectories. Nevertheless, the model validation results indicate that calibrating without limitations on the parameter search space produces estimates with greater explanatory capability, contradicting previous research and supporting the need for additional analyses. Full article

Crash data analysis is key to improving road safety, but imbalanced data challenges accurate predictions for severe crashes, often leading to biased outcomes. This study investigates crash severity among young drivers (aged 17–24) in England, using crash data collected between April 2019 and February 2022. To address the imbalance issue, the performance of a standard classification and regression tree (CART) model is compared with a modified approach—random undersampling of the majority class CART (RUMC-CART). Although RUMC-CART yields slightly lower accuracy, it demonstrates superior performance in identifying severe crashes. Key contributing factors—categorized as type of vehicle and vulnerabilities, number of vehicles and casualties, area type (urban vs. rural), vehicle maneuvers and dynamic factors, and minor influences and timeline—are shown to significantly impact injury severity outcomes among young drivers. The findings of the study provide valuable insights for developing targeted interventions to enhance road safety. Full article

Timely prediction of collisions enables advanced driver assistance systems to issue warnings and initiate emergency maneuvers as needed to avoid collisions. With recent developments in computer vision and deep learning, collision warning systems that use vision as the only sensory input have emerged. They are less expensive than those that use multiple sensors, but their effectiveness must be thoroughly assessed. We systematically searched academic literature for studies proposing ego-centric, vision-based collision warning systems that use deep learning techniques. Thirty-one studies among the search results satisfied our inclusion criteria. Risk of bias was assessed with PROBAST. We reviewed the selected studies and answer three primary questions: What are the (1) deep learning techniques used and how are they used? (2) datasets and experiments used to evaluate? (3) results achieved? We identified two main categories of methods: Those that use deep learning models to directly predict the probability of a future collision from input video, and those that use deep learning models at one or more stages of a pipeline to compute a threat metric before predicting collisions. More importantly, we show that the experimental evaluation of most systems is inadequate due to either not performing quantitative experiments or various biases present in the datasets used. Lack of suitable datasets is a major challenge to the evaluation of these systems and we suggest future work to address this issue. Full article

This paper focuses on a method of rearview camera-based blind-spot detection and a lane change assistance system for autonomous vehicles, utilizing a convolutional neural network and lane detection. In this study, we propose a method for providing real-time warnings to autonomous vehicles and drivers regarding collision risks during lane-changing maneuvers. We propose a method for lane detection to delineate the area for blind-spot detection and for measuring time to collision—both utilized to ascertain the vehicle’s location and compensate for vertical vibrations caused by vehicle movement. The lane detection method uses edge detection on an input image to extract lane markings by employing edge pairs consisting of positive and negative edges. Lanes were extracted through third-polynomial fitting of the extracted lane markings, with each lane marking being tracked using the results from the previous frame detections. Using the vanishing point where the two lanes converge, the camera calibration information is updated to compensate for the vertical vibrations caused by vehicle movement. Additionally, the proposed method utilized YOLOv9 for object detection, leveraging lane information to define the region of interest (ROI) and detect small-sized objects. The object detection achieved a precision of 90.2% and a recall of 82.8%. The detected object information was subsequently used to calculate the collision risk. A collision risk assessment was performed for various objects using a three-level collision warning system that adapts to the relative speed of obstacles. The proposed method demonstrated a performance of 11.64 fps with an execution time of 85.87 ms. It provides real-time warnings to both drivers and autonomous vehicles regarding potential collisions with detected objects. Full article

Background and Objectives: Rib fractures are common in patients with trauma, and patients with multiple rib fractures often require surgical stabilization. Because rib fractures may occur at different sites along the ribs, the technical approach to surgical stabilization varies. Here, we present a case of posterior rib fractures with multiple paraspinal fragmented rib segments that were successfully treated with costovertebral plate fixation. Case Presentation: A truck driver was injured after falling from the top of a truck. Computed tomography scans of the chest showed multiple flail segments along the paraspinal and posterolateral regions with a clinically evident flail chest. Owing to the proximity of the flail segments to the thoracic spine, rib plating was performed across the ribs and the transverse processes of the thoracic spine with the assistance of a neurosurgeon. The patient was extubated on postoperative day 1 and discharged successfully after the other traumatic injuries were treated. Discussion: Far posterior rib fractures close to the spine may be challenging, particularly if plates for rib fractures cannot be placed on the ribs alone. For such challenges, costotransverse plating is a feasible surgical option. However, the anatomical orientation of the rib and the transverse process of the thoracic spine are different, which complicates surgical planning and maneuvers. Therefore, a thorough understanding of the costotransverse anatomy is critical for successful surgical stabilization of fractured ribs. Conclusions: This is a good example of a challenging case of rib fractures requiring paraspinal plate stabilization. Full article

The article describes the application of a vehicle simulation model to assess the driving hazards that arise due to changes in the tyre–road adhesion during a lane change. An experimentally verified vehicle dynamics model was used. The typical single lane change maneuver, performed on dry concrete, wet concrete, and ice-covered roads, was simulated for three vehicle speeds. The disturbance was introduced as a changed tyre–road adhesion on the target lane. Typical sinusoidal (one-period) input was applied to the steering wheel. Adhesion change may lead to an accident when considering the driver’s reaction time. An original control algorithm has been built. It is the driver assistance system with a double PID controller of the steering wheel angle. The system parameters were determined based on the principles recommended in the automatic control engineering monographs. The controller fulfils its tasks for motion at very high speeds on a homogeneous road surface and for the case where the tyre–road adhesion is changed during a maneuver. Thanks to this, the threat can be avoided. Full article

This paper presents the results of a study on the effects of low car speeds and the elastic-damping properties of tires on steering effort. “Steering effort” is a measure of the demand/energy consumption of the power steering system that limits the force applied by the driver to the steering wheel. Low driving speeds, on the other hand, are characteristic of urban traffic, where we would like to see as many electric cars moving as possible. An increase in “driver effort” means a higher electricity consumption and shorter car range. In this study, energy intensity was evaluated for a typical maneuver such as a double lane change. For this purpose, measurements were made of the torque on the steering wheel, the speed of the car, and the lateral accelerations acting on the car. A torque wheel, an optoelectronic sensor for measuring the components of the car’s motion, and an acceleration sensor were used for the study. The test subjects were two passenger cars with hydraulic power steering systems. The tests were carried out for four values of air pressure in the tires. This made it possible to determine four work charts for each wheel. The work charts made it possible to identify the stiffness and damping coefficients of the tires for the tested cars. The values of the coefficients were used to determine the correlation between the directional coefficient of the regression lines of the skeletal axes of the elastic and damping characteristics and the index determining steering effort. Full article

Accurately predicting the long-term trajectories of agents in complex traffic environments is crucial for the safety and effectiveness of autonomous driving systems. This paper introduces DBN-MACTraj, a probabilistic model that takes historical trajectories and surrounding lane information as inputs to generate a distribution of predicted trajectory combinations for all agents. DBN-MACTraj consists of two main components: a single-agent probabilistic model and a multi-agent risk-averse sampling algorithm. The single-agent model utilizes a dynamic Bayesian network, which incorporates the driver’s maneuvering decisions along with information about surrounding lanes. The multi-agent sampling algorithm simultaneously generates predictions for all agents, using a risk potential field model to filter out samples that may lead to traffic accidents. Ultimately, this results in a probability distribution of the combinations of long-term trajectories. Experimental evaluations on the nuScenes dataset demonstrate that DBN-MACTraj delivers competitive performance in trajectory prediction compared to other state-of-the-art approaches. Full article

Yaoundé, the capital of Cameroon, is one of the cities in the country most affected by road traffic crashes. Despite the measures taken by authorities, the human factor remains a major cause of these crashes. This study aimed to evaluate the measures taken to reduce the risk-taking behaviors of collective taxi drivers in Yaoundé. A survey of 144 collective taxi drivers was conducted to gather information on their driving habits, adherence to, and perceived effects of safety regulations. The study revealed the following prevalence of risky driving behaviors among collective taxi drivers: 41.33% for impaired driving; 67% for speeding, 62% for disobeying traffic lights, 68.86% for distraction; and 67% for risky maneuvering on the road. Significant associations were found between risk perceptions and involvement in risky driving behaviors. Associations were also established between the frequency of police inspections and involvement in risky behaviors, between the participation in training programs on safety issues and using poorly maintained vehicles, and between the frequency of awareness campaigns and poor maneuvering on the road. To address these issues, it is essential to strengthen preventive measures on risk factors, raise awareness on a large scale and on a regular basis, and strictly enforce the existing regulations. Full article