Safety Of Autonomous Vehicles Research Articles

Trust calibration through perceptual and predictive information of the external context in autonomous vehicle

Maintaining an appropriate level of trust is critical for driving safety in autonomous vehicles. While enhancing the driver’s situation awareness (SA) of system information in autonomous driving is known to significantly promote trust calibration, it remains unclear whether enhancing the driver’s SA of the external context during driving contributes to this calibration. This study addresses this gap by improving SA of the external context during Level 3 (L3) driving automation across various driving environments. Driving contexts were manipulated using distinct road conditions containing low, medium, or high contextual risks. To enhance driver’s SA of the driving context, we redesigned the in-vehicle central control panel to display real-time perceptual and predictive information about the external driving context. We hypothesized that SA of driving contexts would facilitate trust calibration rather than merely enhancing trust, allowing trust to adjust to appropriate levels under different driving conditions. Experiment 1 examined the impact of perceptual information about the road, traffic infrastructure, and surrounding vehicles on drivers’ trust. We found that driver’s trust decreased with increased contextual risk only when the reconfigured panel was used, while the number of accidents was not affected. Experiment 2 investigated the effect of predictive information about the external context on drivers’ trust by marking safe and dangerous zones around driver’s vehicle with green and red areas, respectively. We revealed that the predictive information calibrated the trust according to road conditions and increased overall trust levels, while the number of accidents was not affected. Together, these findings suggest that enhancing perception and prediction of external contexts helps drivers align their trust with contextual risk levels in L3 driving automation without compromising driving safety.

Improved lane detection for autonomous vehicles using deep learning, semantic segmentation, edge detection and multi-sensor data fusion

Automated driving has gained significant attention because it can eliminate severe driving risks in real time. While autonomous vehicles rely heavily on sensors for lane detection, obstacle identification, and environmental awareness, accurate lane recognition remains a persistent challenge due to factors such as noise from shadows, poor lane markings, and obstructed views. Despite advances in computer vision, this problem is yet to be fully resolved, presenting a gap in the current literature. The primary objective of this research is to address these challenges by developing an enhanced lane-detection system. To achieve this, the study integrates advanced techniques, including semantic segmentation, edge detection, and deep learning, coupled with multi-sensor data fusion from cameras, LIDAR, and radar. By employing this methodology, the research examines various lane-detection methods and benchmarks the proposed model against existing systems in terms of accuracy, specificity and processing speed. Initial findings demonstrate that the combination of semantic segmentation and multi-sensor fusion improves lane detection in real-time scenarios. The proposed model achieved a lane detection accuracy of 97.8%, a specificity of 99.28%, and an average processing time of 0.0047 seconds per epoch. This study not only addresses the limitations of existing lane detection systems but also offers insights into improving road safety for autonomous vehicles.

An Optimal Road Network Extraction Methodology for an Autonomous Driving-Based Demand-Responsive Transit Service Considering Operational Design Domains

In addition to addressing the labor shortage due to an aging population, the transition to autonomous vehicle (AV)-based mobility services offers enhanced efficiency and operational flexibility for public transportation. However, much of the existing focus has been on improving AV safety without fully considering road conditions and real-world service demand. This study contributes to the literature by proposing a comprehensive framework for efficiently integrating AV-based mobility services at the network level, addressing these gaps. The framework analyzes and optimizes service networks by incorporating actual demand patterns, quantifying road segment difficulty from an AV perspective, and developing an optimization model based on these factors. The framework begins by quantifying the operational difficulty of road segments through an evaluation of Operational Design Domains (ODDs), providing a precise measure of AV suitability under varying road conditions. It then introduces a quantitative metric to assess operational feasibility, considering factors such as the service margin, costs, and safety risks. Using these metrics alongside Genetic Algorithms (GAs), the framework identifies an optimal service network that balances safety, efficiency, and profitability. By analyzing real-world data from different mobility services, such as taxis, Demand-Responsive Transport (DRT), and Special Transportation Services (STSs), this study highlights the need for service-specific strategies to optimize AV deployment. The findings show that optimal networks vary with demand patterns and road difficulty, demonstrating the importance of tailored network designs. This research provides a scalable, data-driven approach for integrating AV services into public transportation systems and lays the foundation for further improvements by incorporating dynamic factors and broader urban contexts.

Safety Challenges for Autonomous Vehicles in the Absence of Connectivity

This article examines the critical safety challenges faced by autonomous vehicles (AVs) operating in environments without connectivity. As the global AV market expands rapidly, the disparity in Vehicle-to-Everything (V2X) infrastructure implementation across regions necessitates AVs to function safely in both connected and non-connected scenarios. The article explores five key areas of concern: limited real-time information access, absence of cooperative driving capabilities, lack of remote software updates, reduced traffic ecosystem support, and increased vulnerability to cybersecurity threats. By analyzing data from various transportation studies and industry reports, the article highlights the significant impact of these challenges on AV performance, efficiency, and safety. The research underscores the importance of developing robust, adaptable systems that can operate effectively in diverse connectivity environments, emphasizing the need for advanced onboard sensors, sophisticated AI algorithms, and enhanced traffic management strategies to mitigate the risks associated with non-connected autonomous driving.

Enhancing Planning for Autonomous Driving via an Iterative Optimization Framework Incorporating Safety-Critical Trajectory Generation

Ensuring the safety of autonomous vehicles (AVs) in complex and high-risk traffic scenarios remains a critical unresolved challenge. Current AV planning methods exhibit limitations in generating robust driving trajectories that effectively avoid collisions, highlighting the urgent need for improved planning strategies to address these issues. This paper introduces a novel iterative optimization framework that incorporates safety-critical trajectory generation to enhance AV planning. The use of the HighD dataset, which is collected using the wide-area remote sensing capabilities of unmanned aerial vehicles (UAVs), is fundamental to the framework. Remote sensing enables large-scale real-time observation of traffic conditions, providing precise data on vehicle dynamics, road structures, and surrounding environments. To generate safety-critical trajectories, the decoder within the conditional variational auto-encoder (CVAE) is innovatively designed through a data-mechanism integration method, ensuring that these trajectories strictly adhere to vehicle kinematic constraints. Furthermore, two parallel CVAEs (Dual-CVAE) are trained collaboratively by a shared objective function to implicitly model the multi-vehicle interactions. Inspired by the concept of “learning to collide”, adversarial optimization is integrated into the Dual-CVAE (Adv. Dual-CVAE), facilitating efficient generation from normal to safety-critical trajectories. Building upon this, these generated trajectories are then incorporated into an iterative optimization framework, significantly enhancing the AV’s planning ability to avoid collisions. This framework decomposes the optimization process into stages, initially addressing normal trajectories and progressively tackling more safety-critical and collision trajectories. Finally, comparative case studies of enhancing AV planning are conducted and the simulation results demonstrate that the proposed method can efficiently enhance AV planning by generating safety-critical trajectories.

Machine learning and vision neural networks in autonomous vehicles for the aging population: A scoping review protocol

This scoping review aims to systematically map the current body of literature on the role of Machine Learning (ML) and Vision Neural Networks (VNN) in enhancing the usability and accessibility of Autonomous Vehicles (AVs) for elderly and disabled users. While AV technology has advanced significantly in recent years, the solutions of how these technologies can address the unique challenges faced by these vulnerable populations still in an undeveloped or underdeveloped stage. For example, cognitive decline, physical limitations, and lower trust in automated systems. The review will investigate how ML and VNN contribute to improving safety, usability, accessibility, and trust in AVs, focusing on studies published between 2020 and 2024. A comprehensive search will be conducted across four major databases, which are PubMed, IEEE Xplore, Scopus, and Google Scholar. The language of targeting peer-reviewed empirical studies and reviews must be written in English. Data will be extracted using a standardized form and synthesized through a descriptive analytical framework to identify key themes, trends, and gaps in the literature. The findings will offer valuable insights into how AV technologies can be further optimized for elderly and disabled users. It will guide future research and informing the development of more inclusive, safe, and trustworthy AV systems. Therefore, they can promote greater mobility and independence for these populations.

Enhancement of photoresponse for InGaAs infrared photodetectors using plasmonic WO3-x/CsyWO3-xnanocrystals.

Fast and accurate detection of light in the near-infrared (NIR) spectral range plays a crucial role in modern society, from alleviating speed and capacity bottlenecks in optical communications to enhancing the control and safety of autonomous vehicles through NIR imaging systems. Several technological platforms are currently under investigation to improve NIR photodetection, aiming to surpass the performance of established III-V semiconductor p-i-n (PIN) junction technology. These platforms include in situ-grown inorganic nanocrystals and nanowire arrays, as well as hybrid organic-inorganic materials such as graphene-perovskite heterostructures. However, challenges remain in nanocrystal and nanowire growth, large-area fabrication of high-quality 2D materials, and the fabrication of devices for practical applications. Here, we explore the potential for tailored semiconductor nanocrystals to enhance the responsivity of planar metal-semiconductor-metal (MSM) photodetectors. MSM technology offers ease of fabrication and fast response times compared to PIN detectors. We observe enhancement of the optical-to-electric conversion efficiency by up to a factor of ~2.5 through the application of plasmonically-active semiconductor nanorods and nanocrystals. We present a protocol for synthesizing and rapidly testing the performance of non-stoichiometric tungsten oxide (WO3-x) nanorods and cesium-doped tungsten oxide (CsyWO3-x) hexagonal nanoprisms prepared in colloidal suspensions and drop-cast onto photodetector surfaces. The results demonstrate the potential for a cost-effective and scalable method exploiting tailored nanocrystals to improve the performance of NIR optoelectronic devices.

KPTr: Key point transformer for LiDAR-based 3D object detection

Accurate 3D environmental perception is crucial for ensuring the safety of autonomous vehicles. However, many existing point-based 3D object detection methods rely only on independent point features to extract spatial information and ignore the dependencies between points. Meanwhile, these methods usually use max-pooling operations to aggregate neighboring point features without considering the stability of local geometric information. To address these issues, this paper proposes a novel two-stage LiDAR-based key point transformer that consists of a region proposal network module and a region-based transformer module to enhance 3D detection performance. Firstly, unprocessed raw point clouds are taken as the input of the model to preserve detailed spatial structural information. Secondly, in the region proposal network an enhanced PointNet++ is used to segment foreground points and generate high-quality first-stage proposals. Then, the representation of proposals is improved by the region-based transformer module, which constructs long-range key point cloud relationship features within the regions of interest and diffuses spatial information into the feature channel layers. Additionally experiments on the KITTI dataset show that detection performance of the proposed method surpasses most mainstream 3D object detection methods and achieves a detection speed of 14.28 Hz, striking a good balance between detection accuracy and speed. Finally, the proposed method is deployed on real vehicle hardware platforms for online detection, thereby proving its industrial value.

Safe-Enhanced Autonomous Driving Technology Using Conformal Prediction Results

Abstract Autonomous driving technology significantly improves road safety, mitigates traffic congestion, and paves the way for a more efficient and connected transportation future. However, the uncertain driving scenarios poses a great challenge to the safe control of autonomous vehicles (AVs). Therefore, this paper proposes an enhanced safety control framework by integrating the quantified prediction results of human driving behaviors into the path-planning process. First, a Long Short-Term Memory (LSTM) network is employed for driver behavior prediction, based on which, the conformal prediction, a mathematical statistical method, is introduced to quantify the uncertainties of the prediction results with a probabilistic presentation. Then, a model predictive model controller (MPC) is designed to enable the path-planning ability. By using the Lipschitz constant, the inequality for obstacle avoidance is reformulated as a hard constraint in the MPC optimization framework while considering the conformal prediction results. Finally, some simulation test cases are conducted to validate the proposed method. The results demonstrate the effectiveness to guarantee the safety of AVs with uncertain prediction results.

An integration methodology of safety and security requirements for autonomous vehicles

Safety and security co-engineering is one of the latest challenge in autonomous vehicle (AV) development. Efficiently integrating safety and security requirements during co-engineering is a new issue. Most functional safety and security analysis methods do not directly derive safety requirements, and improper handling of their relationship can affect system design and timelines. This article aims to use large language models (LLMs) to assist in the collaborative work of functional safety and security analysis. The main contributions are as follows: First, we propose three types of formulations to summarize hazard scenarios and threat scenarios and use LLMs to extract functional safety requirements and security requirements from them. Second, we utilized the three LLMs to perform relationship checks on the extracted functional safety requirements and security requirements. The results showed that the majority of the checks were correct and consistent, with only a small portion requiring manual intervention, significantly reducing human labor. Through these methods, we demonstrate the potential and efficiency of LLMs in the collaborative analysis of functional safety and security.

Enhancing Safety in Autonomous Vehicles: The Impact of Auditory and Visual Warning Signals on Driver Behavior and Situational Awareness

Semi-autonomous vehicles (AVs) enable drivers to engage in non-driving tasks but require them to be ready to take control during critical situations. This “out-of-the-loop” problem demands a quick transition to active information processing, raising safety concerns and anxiety. Multimodal signals in AVs aim to deliver take-over requests and facilitate driver–vehicle cooperation. However, the effectiveness of auditory, visual, or combined signals in improving situational awareness and reaction time for safe maneuvering remains unclear. This study investigates how signal modalities affect drivers’ behavior using virtual reality (VR). We measured drivers’ reaction times from signal onset to take-over response and gaze dwell time for situational awareness across twelve critical events. Furthermore, we assessed self-reported anxiety and trust levels using the Autonomous Vehicle Acceptance Model questionnaire. The results showed that visual signals significantly reduced reaction times, whereas auditory signals did not. Additionally, any warning signal, together with seeing driving hazards, increased successful maneuvering. The analysis of gaze dwell time on driving hazards revealed that audio and visual signals improved situational awareness. Lastly, warning signals reduced anxiety and increased trust. These results highlight the distinct effectiveness of signal modalities in improving driver reaction times, situational awareness, and perceived safety, mitigating the “out-of-the-loop” problem and fostering human–vehicle cooperation.

Development of a system that changes the speed of the motor for a given radius of curvature of an autonomous car while taking turn

This work endeavors to create a system capable of autonomously regulating a car’s speed while navigating turns, based on the curvature of the road. The primary objective is to bolster the safety and stability of autonomous vehicles by curbing excessive speeds during turns, thereby mitigating the risk of accidents such as loss of control or rollovers. The approach blends theoretical analysis with practical application, involving computations to ascertain the ideal speed for a given curve radius. Factors such as vehicle mass, wheel specifications, and centrifugal and gyroscopic forces are considered in these calculations. Subsequently, an algorithm is devised and implemented using Arduino Uno and programmed within the Arduino IDE software environment. The system employs sensors to monitor the motor’s speed and adjust the motor’s speed accordingly. Both simulated scenarios and real-world experiments validate the system’s efficacy in maintaining safe speeds during turns. The study concludes by underlining the potential of this system to heighten the safety and dependability of autonomous vehicles, while also proposing future avenues for research, such as integration with broader autonomous driving frameworks and field testing across diverse environmental conditions.

Securing the Future of Transportation: An In-Depth Analysis of Cybersecurity Challenges and Solutions for Autonomous Vehicles

Abstract: As autonomous vehicles (AVs) become increasingly integrated into transportation systems, ensuring their cybersecurity has emerged as a critical challenge. This comprehensive article examines the complex landscape of AV cybersecurity, focusing on the unique vulnerabilities arising from integrating advanced sensors, artificial intelligence, and vehicle-to-everything (V2X) communication systems. We analyze potential attack vectors, including sensor spoofing, communication system breaches, and software vulnerabilities. We also evaluate state-of-the-art defense mechanisms such as encryption protocols, intrusion detection systems, and AI-based security solutions. The article also addresses the regulatory frameworks and industry standards shaping AV cybersecurity practices. By synthesizing current research, industry reports, and case studies, we provide insights into emerging threats and defense strategies, highlighting the need for a holistic approach to security in AV design and development. This article contributes to the ongoing dialogue on AV safety and reliability, offering valuable perspectives for researchers, policymakers, and industry stakeholders in navigating the evolving cybersecurity challenges in autonomous transportation.

Risk Assessment of Roundabout Scenarios in Virtual Testing Based on an Improved Driving Safety Field.

With the advancement of autonomous driving technology, scenario-based testing has become the mainstream testing method for intelligent vehicles. However, traditional risk indicators often fail in roundabout scenarios and cannot accurately define dangerous situations. To accurately quantify driving risks in roundabout scenarios, an improved driving safety field model is proposed in this paper. First, considering the unique traffic flow characteristics of roundabouts, the dynamic characteristics of vehicles during diverging or merging were taken into account, and the driving safety field model was improved to accurately quantify the driving risks in roundabout scenarios. Second, based on data from the rounD dataset, the model parameters were calibrated using the social force model. Finally, a DENCLUE-like method was used to extract collision systems, calculate vehicle risk degree, and analyze these risks for both the temporal and the spatial dimensions, providing guidance for virtual testing. The proposed method significantly improves detection efficiency, increasing the number of identified dangerous scenarios by 175% compared to the Time to Collision (TTC) method. Moreover, this method can more accurately quantify driving risks in roundabout scenarios and enhance the efficiency of generating dangerous scenarios, contributing to promoting the safety of autonomous vehicles.

Exploration of Traffic Accident-Based Pilot Zones for Autonomous Vehicle Safety Validation

Recently, the commercialization of autonomous vehicles has increased the importance of verifying vehicle safety through autonomous trials. Autonomous driving trials are conducted in limited areas within artificially constructed test roads and pilot districts and directly explore road sections and areas with similar environments to ensure the safety of AVs driving on real roads. Many previous studies have evaluated the complex response potential of AVs by deriving edge scenarios to ensure their safety. However, difficulties arise in exploring real roads with traffic accident factors and configurations similar to those in edge scenarios, making validation on real roads uncertain. This paper proposes a novel method for exploring pilot zones using traffic accident data to verify the safety of autonomous vehicles (AVs). The method employs a CNN + BiGRU model trained on DMV dataset data to classify traffic accidents as AV- or human-caused. The model’s classification accuracy was evaluated using recall, precision, F1 score, and accuracy, achieving 100.0%, 97.8%, 98.9, and 99.5%, respectively. The trained model was applied to the KNPA dataset, identifying 562 out of 798 cases as AV-like, indicating potential areas of high accident density due to AV operation. Outlier detection and DBSCAN clustering were utilized to identify compact pilot zones, effectively reducing the area size compared to raw data clusters. This approach significantly lowers the cost and time associated with selecting test roads and provides a viable alternative for countries lacking real AV accident data. The proposed method’s effectiveness in identifying pilot zones demonstrates its potential for advancing AV safety validation.

Enhanced Vision-Based Taillight Signal Recognition for Analyzing Forward Vehicle Behavior.

This study develops a vision-based technique for enhancing taillight recognition in autonomous vehicles, aimed at improving real-time decision making by analyzing the driving behaviors of vehicles ahead. The approach utilizes a convolutional 3D neural network (C3D) with feature simplification to classify taillight images into eight distinct states, adapting to various environmental conditions. The problem addressed is the variability in environmental conditions that affect the performance of vision-based systems. Our objective is to improve the accuracy and generalizability of taillight signal recognition under different conditions. The methodology involves using a C3D model to analyze video sequences, capturing both spatial and temporal features. Experimental results demonstrate a significant improvement in the model's accuracy (85.19%) and generalizability, enabling precise interpretation of preceding vehicle maneuvers. The proposed technique effectively enhances autonomous vehicle navigation and safety by ensuring reliable taillight state recognition, with potential for further improvements under nighttime and adverse weather conditions. Additionally, the system reduces latency in signal processing, ensuring faster and more reliable decision making directly on the edge devices installed within the vehicles.

LDIPRS: A novel longitudinal driving intention prior recognition technique empowered by TENG and deep learning

For autonomous vehicles, real-time and accurate longitudinal driving intention recognition is crucial as it effectively enhances driving safety and improves the driving experience. This study proposes a novel data and model hybrid-driven fine-grained longitudinal driving intention prior recognition system (LDIPRS). Firstly, the system integrates a human-pedal interaction sensor (HPIS) based on triboelectric nanogenerators for fine-grained longitudinal driving maneuver monitoring and the channel attention (CA)-enhanced convolutional neural network (CBRCNet). The HPIS, integrated into the vehicle's acceleration and brake pedals, is capable of monitoring driver foot movement information in the form of electrical signals before the vehicle responds, achieving data level advance. The collected electrical signals are fed into the CBRCNet network, which models and learns the mapping relationship between these signals and fine-grained longitudinal driving intentions, leading to model level advances. The HPIS completes the capture of longitudinal maneuver information 541 ms before the driving simulator starts to respond at the data level. At the model level, CBRCNet can achieve a recognition accuracy of 96.1 % based on partial response data (50 ms after starting response) rather than complete response data of the HPIS. Finally, our proposed LDIPRS realizes the recognition of emergency braking, rapid acceleration, normal braking, and normal acceleration in advance by 732 ms, 1035 ms, 1757 ms, and 2227 ms, respectively. This study introduces self-powered, low-cost, highly sensitive triboelectric sensors into the field of intention recognition, and combines the triboelectric sensors with deep learning algorithms to offer a promising solution to improve the safety of autonomous vehicles and the efficiency of intelligent transportation systems.

Investigation of the impacts of the deployment of autonomous vehicles on first responders

Purpose The purpose of this study is to address the significant impact AVs will have on public services and the ability of first responders to conduct their jobs safely and effectively. Autonomous vehicles (AVs) are expected to drastically change the transportation industry, and it is vital that first responders be equipped to integrate them into their occupational responsibilities. Design/methodology/approach A systematic literature review was conducted, and following a multistep exclusion process, 161 articles were selected for detailed review. The impacts of AVs on first responders were identified, classified and categorized into lists of challenges and opportunities. Based on the findings of the literature review, a SWOT (strengths, weaknesses, opportunities and threats) analysis was conducted, and stakeholder management strategies were designed. Findings Through the examination of the impacts of AVs on first responders, 17 identified challenges and opportunities were classified into the following categories: AV-related emergency response and training, perceptions and acceptance of AVs, technology development and laws and regulations. The study revealed that the optimal benefits of AVs would require stakeholders to focus more on how they interact with first responders; thus, 14 stakeholder management strategies were identified. First responders, AV manufacturers, legislators and future research paths will all benefit from this study, as it can facilitate smooth interactions between AVs and first responders. Originality/value A range of studies have been published on the safety of AVs and the public’s perceptions of this new technology; however, the integration of AVs and their interactions with first responders has been neglected. The goal of this study was to fill that research gap by providing a thorough synthesis of autonomous driving systems in the context of their interactions with first responders.

Enhancing autonomous vehicle navigation using SVM-based multi-target detection with photonic radar in complex traffic scenarios

Efficient transportation systems are essential for the development of smart cities. Autonomous vehicles and Intelligent Transportation Systems (ITS) are crucial components of such systems, contributing to safe, reliable, and sustainable transportation. They can reduce traffic congestion, improve traffic flow, and enhance road safety, thereby making urban transportation more efficient and environmentally friendly. We present an innovative combination of photonic radar technology and Support Vector Machine classification, aimed at improving multi-target detection in complex traffic scenarios. Central to our approach is the Frequency-Modulated Continuous-Wave photonic radar, augmented with spatial multiplexing, enabling the identification of multiple targets in various environmental conditions, including challenging weather. Notably, our system achieves an impressive range resolution of 7 cm, even under adverse weather conditions, utilizing an operating bandwidth of 4 GHz. This feature is particularly crucial for precise detection and classification in dynamic traffic environments. The radar system's low power requirement and compact design enhance its suitability for deployment in autonomous vehicles. Through comprehensive numerical simulations, our system demonstrated its capability to accurately detect targets at varying distances and movement states, achieving classification accuracies of 75% for stationary and 33% for moving targets. This research substantially contributes to ITS by offering a sophisticated solution for obstacle detection and classification, thereby improving the safety and efficiency of autonomous vehicles navigating through urban environments.

A method based on Vision Transformer and multiple image information for vehicle lane-changing recognition in mixed traffic and connected environment

ABSTRACT To enhance the safety of autonomous vehicles in mixed traffic and connected environment, it is crucial to recognize the lane-changing intentions (LCIs) of human-driven vehicles for autonomous vehicles. This paper presents a novel method for LCI recognition, which extracts features from the driving state and relative motion of the target vehicle and its neighbors. The method applies short-time Fourier transform, Gramian angular summation field, and Gramian angular difference field to the time-series data, and generates three grayscale images, which are merged into one information fusion image (IFI) by image processing techniques. The IFIs are then classified into three categories: lane keeping, lane-changing left, and lane-changing right, using the Vision Transformer model with transfer learning to speed up convergence and reduce training cost. The experimental results demonstrate that the proposed method outperforms the traditional methods, achieving an accuracy of 95.65% for recognizing LCI 3s before the lane change point.