Driver Assistance Research Articles

Machine-learning-based ensemble regression for vehicle-to-vehicle distance estimation using a toe-in style stereo camera

Adjusting the following distance from the front vehicle in highway traffic is important to reduce the risk of collision. Distance estimation is an important research area for advanced driver assistance systems. Therefore, this paper presents a methodology that combines the strengths of several machine learning algorithms using joint decision mechanisms and searches for optimal results for vehicle-to-vehicle distance estimation. The hyperparameter optimization of machine learning models is performed by an iterative algorithm that compares combinations of hyperparameter values. In addition, machine learning algorithms are combined and tested with ensemble learning methods to improve the results obtained. According to the experiments, the ensemble voting regression created by combining extreme gradient boosting, categorical boosting and two multi-layer perceptron models achieves the best result with a mean absolute percentage error value of 1.5444. Considering the comparisons made with other methods, the accuracy of the results obtained with the proposed method is quite high.Code is at: https://github.com/ozgurduran/V2V-VR.

Optimizing Camera Exposure Time for Automotive Applications.

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

A note on Tesla's revised safety report crash rates

Between June 2018 and December 2023, Tesla released quarterly safety reports citing average miles between crashes for Tesla vehicles. Prior to March 2021, crash rates were categorized as (1) with their SAE Level 2 automated driving system Autopilot engaged, (2) without Autopilot but with active safety features such as automatic emergency braking, and (3) without Autopilot and without active safety features. In January 2023, Tesla revised past reports to reflect their new categories of with and without Autopilot engaged, in addition to making small adjustments based on recently discovered double counting of reports and excluding previously recorded crashes that did not meet their thresholds of airbag or active safety restraint activation. The revisions are heavily biased towards no-active-safety-features—a surprising result given prior research showing that drivers predominantly keep most active safety features enabled. As Tesla's safety reports represent the only national source of Level 2 advanced driver assistance system crash rates, clarification of their methods is essential for researchers and regulators. This note describes the changes and considers possible explanations for the discrepancies.

Evaluating the User Experience of V2X Communication Alerts for Emergencies in Level 3 Autonomous Driving

Communicating effectively with autonomous vehicles requires contextualized visual and auditory cues to ensure clear message delivery. Evaluating the user experience involves assessing which types of information can be safely reacted to without additional monitoring and how it is presented. Validating the visual and auditory cues supports the driver’s course of action. This study investigates message types and preferred modalities of driver-to-driver communication via vehicle-to-everything (V2X) in advanced driver assistance systems technologies for autonomous and manual driving and proposes efficient ways to respond to event situations. Four modalities, including baseline and three message types with different information were proposed to investigate the information required by drivers. Results indicate that providing notifications during autonomous driving is more helpful and less workload-intensive than during manual driving. Most notifications were highly visible and easy to recognize. Although behavioral messages in both autonomous and manual driving enhance usability, providing advice and behavioral messages is safer for autonomous driving. Designing V2X notification information based on future events is vital because of its highly pragmatic nature.

Personalizing driver safety interfaces via driver cognitive factors inference

Recent advances in AI and intelligent vehicle technology hold the promise of revolutionizing mobility and transportation through advanced driver assistance systems (ADAS). Certain cognitive factors, such as impulsivity and inhibitory control have been shown to relate to risky driving behavior and on-road risk-taking. However, existing systems fail to leverage such factors in assistive driving technologies adequately. Varying the levels of these cognitive factors could influence the effectiveness and acceptance of ADAS interfaces. We demonstrate an approach for personalizing driver interaction via driver safety interfaces that are are triggered based on the inference of the driver’s latent cognitive states from their driving behavior. To accomplish this, we adopt a data-driven approach and train a recurrent neural network to infer impulsivity and inhibitory control from recent driving behavior. The network is trained on a population of human drivers to infer impulsivity and inhibitory control from recent driving behavior. Using data collected from a high-fidelity vehicle motion simulator experiment, we demonstrate the ability to deduce these factors from driver behavior. We then use these inferred factors to determine instantly whether or not to engage a driver safety interface. This approach was evaluated using leave-one-out cross validation using actual human data. Our evaluations reveal that our personalized driver safety interface that captures the cognitive profile of the driver is more effective in influencing driver behavior in yellow light zones by reducing their inclination to run through them.

Enhancing advanced driver assistance systems through explainable artificial intelligence for driver anomaly detection

The recent advancements in Advanced Driver Assistance Systems (ADAS) have significantly contributed to road safety and driving comfort. An integral aspect of these systems is the detection of driver anomalies such as drowsiness, distraction, and impairment, which are crucial for preventing accidents. Building upon previous studies that utilized ensemble model learning (XGBoost) with deep learning models (ResNet50, DenseNet201, and InceptionV3) for anomaly detection, this study introduces a comprehensive feature importance analysis using the SHAP (SHapley Additive exPlanations) technique. The technique is implemented through explainable artificial intelligence (XAI). The primary objective is to unravel the complex decision-making process of the ensemble model, which has previously demonstrated near-perfect performance metrics in classifying driver behaviors using in-vehicle cameras. By applying SHAP, the study aims to identify and quantify the contribution of each feature – such as facial expressions, head position, yawning, and sleeping – in predicting driver states. This analysis offers insights into the model’s inner workings and guides the enhancement of feature engineering for more precise and reliable anomaly detection. The findings of this study are expected to impact the development of future ADAS technologies significantly. By pinpointing the most influential features and understanding their dynamics, a model can be optimized for various driving scenarios, ensuring that ADAS systems are robust, accurate, and tailored to real-world conditions. Ultimately, this study contributes to the overarching goal of enhancing road safety through technologically advanced, data-driven approaches.

Truck drivers’ views on the road safety benefits of advanced driver assistance systems and Intelligent Transport Systems in Tanzania

Truck drivers’ views on the road safety benefits of advanced driver assistance systems and Intelligent Transport Systems in Tanzania

CycleInSight: An enhanced YOLO approach for vulnerable cyclist detection in urban environments

As urbanization continues to reshape transportation, the safety of cyclists in complex traffic environments has become a pressing concern. In response to this challenge, our research introduces a CycleInSight framework, which harnesses advanced deep learning and computer vision techniques to enable precise and efficient cyclist detection in diverse urban settings. Utilizing you only look once version 8 (YOLOv8) object detection algorithm, the proposed model aims to detect and localize vulnerable cyclists near vehicles equipped with onboard cameras. Our research presents comprehensive experimental results demonstrating its effectiveness in identifying vulnerable cyclists amidst dynamic and challenging traffic conditions. With an impressive average precision of 90.91%, our approach outperforms existing models while maintaining efficient inference speeds. By effectively identifying and tracking cyclists, this framework holds significant potential to enhance urban traffic safety, inform data-driven infrastructure planning, and support the development of advanced driver assistance systems and autonomous vehicles.

Lived experience of driving in individuals with functional neurological disorder.

Functional neurological disorder (FND) is a common neurological diagnosis that encapsulates a range of incapacitating clinical presentations. These include functional seizures, movement disorders, and sensory disturbances. Safe driving requires both cognitive skills and physical abilities, which may be impacted by FND symptoms. The primary objective of this study was to gain deeper insights into the challenges faced by people with FND when driving. A qualitative study and interpretative phenomenological analysis were conducted. Individuals experiencing functional seizures and/or movement disorders completed both questionnaires and semi-structured interviews about FND symptoms, driving behavior, and crashes. A total of 26 patients with FND participated in this study. Based on the interviews, four key themes were identified: (1) driving difficulties experienced by individuals with FND; (2) strategies utilized by people with FND to overcome difficulties experienced while driving; (3) barriers preventing driving challenges being addressed in this population; and (4) crashes and perceived dangerous driving events experienced by individuals with FND. All participants reported that driving a car provoked FND symptoms and this affected their driving ability. FND sufferers reported using a number of strategies such as limiting how far they drive and relying on advanced driver assistance system features to help manage their associated symptoms, such as fatigue and/or pain. Several participants reported crashes and perceived dangerous driving events since developing FND. Individuals experiencing FND often employ self-regulation techniques, yet the extent to which these methods enhance driving safety remains uncertain. The variable nature of the disorder makes judging an individual's driving risk particularly difficult. The themes emerging from the interviews highlighted the need for further empirical research to inform guidelines and best practice when determining the impact of FND on an individual's driving safety .

Formal analysis of an AUTOSAR-based basic software module

The widespread use of advanced driver assistance systems in modern vehicles, together with their integration with the Internet and other road nodes, has made vehicle more vulnerable to cyber-attacks. To address these risks, the automotive industry is increasingly focusing on the development of security solutions: formal methods and software verification techniques, which have been successfully applied to a number of safety-critical systems, could be a promising approach in the automotive area. In this work, we concentrate on in-vehicle communications, provided by many Electronic Control Units (ECUs) that work together thanks to serial protocols such as Controller Area Network (CAN). However, increasing connectivity exposes the internal network to a variety of cyber-risks. Our aim is to formally verify the AUTOSAR-based Basic Software module called CINNAMON, designed to ensure confidentiality, integrity, and authentication at the same time for traffic exchanged over CAN protocol. More precisely, it adds confidentiality guarantees to the Secure Onboard Communication (SecOC) module. We formally analyze CINNAMON with the verification tool Tamarin. Our analysis shows that CINNAMON could be an effective security solution, as it can ensure the desired properties, in particular, confidentiality in a send-receive scenario between two ECUs. Finally, we describe a potential application scenario.

ADAS and automation-arelevant contribution to maintaining mobility of older drivers?

Driving is the most important and safest form of mobility for the majority of senior citizens. However, physical and mental performance gradually decline with age, which can lead to more problems, critical situations or even accidents. Vehicle technology innovations such as advanced driver assistance systems (ADAS) have the potential to increase the road safety of older people and maintain their individual mobility for as long as possible.This overview article aims to identify ADAS that have the greatest potential to reduce the number of accidents involving older drivers. For this purpose, the accident and damage occurrence as well as the driving behaviour and compensation strategies of older people are examined in more detail. Suitable ADAS should compensate for typical driver errors, reduce information deficiencies and have ahigh level of acceptance. For older drivers, emergency braking, parking assistance, navigation, intersection assistance and distance speed control systems as well as systems for detecting blind spots and obstacles appear to be particularly suitable.Some of the disadvantages of ADAS are the lack of market penetration, acceptance problems and interface designs that have not yet been optimally adapted to the needs of older users. For older drivers in particular, it appears to be apriority to develop coherent and integrated solutions in the sense of cooperative assistance instead of pushing ahead with high and full automation with many system limits and exceptions, which can place high demands on attention, for example if the vehicle has to be taken over in acritical situation.

Real Time Traffic Sign Recognition Using Integrated Camera Sensors and YOLOV8 Algorithm

Traffic signs are an important element in maintaining smoothness and safety on the road. However, there are still many drivers who violate them, causing various negative impacts. Traffic Sign Recognition (TSR) is a technology that has the ability to detect and identify various types of traffic signs by utilizing artificial intelligence in the computer vision domain. TSR has been applied in various vehicle applications, such as Advance Driver Assistance System (ADAS) and Autonomous Driving System (ADS). This system is made by integrating camera sensors with the YOLOv8 algorithm which has high accuracy and fast data processing. The data used were 2093 images and annotated through Roboflow. Then the data is trained through Google Collaboratory with a mAP evaluation result of 95.5% which shows that the system can detect objects accurately. The level of precision and success of the model in detecting objects is 93.5% and the success is 93.3%. The results of system testing can use images, videos, and through cameras in real time.

A robust and real-time lane detection method in low-light scenarios to advanced driver assistance systems

Lane detection, which relies on front-view RGB cameras, is a crucial aspect of Advanced Driver Assistance Systems (ADAS), but its effectiveness is notably reduced in low-light conditions. This issue is exacerbated by the lack of specialized datasets and generalizable methods for such scenarios. To address this gap, we introduce NightLane, a comprehensive dataset tailored for low-light, multi-traffic lane detection. We adhere to stringent data annotation guidelines, ensuring reliable detection accuracy. Additionally, we propose the Fused Low-Light Enhancement Framework (FLLENet), which leverages modern detection networks and incorporates a low-light enhancement module and attention mechanisms. The enhancement module, based on zero-reference learning, improves image quality and channel richness, while the attention mechanisms effectively extract and utilize these features. Our extensive testing on NightLane and CULane datasets demonstrates superior performance in low-light lane detection, showcasing FLLENet’s robust generalizability and efficacy. Specifically, our approach achieves an F1 measure of 76.90 on CULane and 78.91 on NightLane, demonstrating its effectiveness against state-of-the-art methods. We also evaluate the real-time applicability of our framework on a low-power embedded lane detection system using NVIDIA Jetson AGX/Orin, achieving high accuracy and real-time performance. Our work offers a new approach and reference in the field of low-light lane detection, potentially aiding in the ongoing enhancement of ADAS (ADAS). Dateset are available at https://github.com/pengjingt/FLLENet.

Deep learning approach for unified recognition of driver speed and lateral intentions using naturalistic driving data

Driver intention recognition is a critical component of advanced driver assistance systems, with significant implications for improving vehicle safety, intelligence, and fuel economy. However, previous research on driver intention recognition has not fully considered the influence of the driving environment on speed intentions and has not exploited the temporal dependency inherent in the lateral intentions to prevent erroneous changes in recognition. Furthermore, the coupling of speed and lateral intentions was overlooked; they were generally considered separately. To address these limitations, a unified recognition approach for speed and lateral intentions based on deep learning is presented in this study. First, extensive naturalistic driving data are collected, and information related to road slope and driving trajectories is extracted. A comprehensive classification of driver intentions is then performed. Toeplitz inverse covariance-based clustering and trajectory clustering methods are applied separately to label speed and lateral intentions, so that the influence of driving environments and the coupling of speed and lateral intentions are integrated into intention recognition. Finally, a deep-learning-based unified recognition model for driver intention is developed. This model uses a hierarchical recognition approach for speed intentions and includes a double-layer networks architecture with long short-term memory for the recognition of lateral intention. The validation results show that the created driver intention recognition model can accurately and stably recognize both speed and lateral intentions in complex driving environments.

Combining Optimization and Simulation for Next-Generation Off-Road Vehicle E/E Architectural Design.

The automotive industry, with particular reference to the off-road sector, is facing several challenges, including the integration of Advanced Driver Assistance Systems (ADASs), the introduction of autonomous driving capabilities, and system-specific requirements that are different from the traditional car market. Current vehicular electrical-electronic (E/E) architectures are unable to support the amount of data for new vehicle functionalities, requiring the transition to zonal architectures, new communication standards, and the adoption of Drive-by-Wire technologies. In this work, we propose an automated methodology for next-generation off-road vehicle E/E architectural design. Starting from the regulatory requirements, we use a MILP-based optimizer to find candidate solutions, a discrete event simulator to validate their feasibility, and an ascent-based gradient method to reformulate the constraints for the optimizer in order to converge to the final architectural solution. We evaluate the results in terms of latency, jitter, and network load, as well as provide a Pareto analysis that includes power consumption, cost, and system weight.

A Comparative Study of Recent Practices and Technologies in Advanced Driver Assistance System

A Comparative Study of Recent Practices and Technologies in Advanced Driver Assistance System

Lane Detection, Segmentation, Pothole Detection and Traffic Sign Recognition for ADAS

Lane detection, a critical aspect of advanced driver assistance systems (ADAS) and autonomous vehicles, is addressed in this work, combining classical computer vision methods with deep learning techniques. The proposed solution, utilizing a UNet-based model trained with TensorFlow and Keras, enhances vehicle perception for intelligent transportation systems. Integrated functionalities for pothole detection and traffic sign detection further contribute to safety and efficiency, enabling vehicles to identify road hazards and comply with regulations. The system encompasses data preprocessing, model training, and real-time video analysis, while a classical lane detection pipeline using OpenCV showcases various stages such as grayscale conversion, Gaussian blur, Canny edge detection, masking, Hough transform, and lane overlay. This comprehensive approach supports road safety, traffic management, and transportation efficiency initiatives, making significant strides in intelligent transportation systems and urban planning.

Research on Driver Style Recognition Based on GA-K-Means and PSO-SVM

<div>This article aims to address the challenge of recognizing driving styles, a task that has become increasingly complex due to the high dimensionality of driving data. To tackle this problem, a novel method for driver style clustering, which leverages the principal component analysis (PCA) for dimensionality reduction and an improved GA-K-means algorithm for clustering, is proposed. In order to distill low-dimensional features from the original dataset, PCA algorithm is employed for feature extraction and dimensionality reduction. Subsequently, an enhanced GA-K-means algorithm is utilized to cluster the extracted driving features. The incorporation of the genetic algorithm circumvents the issue of the model falling into local optima, thereby facilitating effective driver style recognition. The clustering results are evaluated using the silhouette coefficient, Calinski–Harabasz (CH) index, and GAP value, demonstrating that this method yields more stable classification results compared to traditional clustering methods. In the final stage, a particle swarm optimization-SVM (PSO-SVM) algorithm is applied to classify the clustering results, which are then compared with results from other machine learning algorithms such as decision tree, naive Bayes network, and K-nearest-neighbor (KNN). This comprehensive approach to driver style recognition holds promise for enhancing traffic safety and efficiency. The accurate recognition of driving style can lay the foundation for further optimization of advanced driver assistance systems (ADAS).</div>

Sensor-Fused Nighttime System for Enhanced Pedestrian Detection in ADAS and Autonomous Vehicles.

Ensuring a safe nighttime environmental perception system relies on the early detection of vulnerable road users with minimal delay and high precision. This paper presents a sensor-fused nighttime environmental perception system by integrating data from thermal and RGB cameras. A new alignment algorithm is proposed to fuse the data from the two camera sensors. The proposed alignment procedure is crucial for effective sensor fusion. To develop a robust Deep Neural Network (DNN) system, nighttime thermal and RGB images were collected under various scenarios, creating a labeled dataset of 32,000 image pairs. Three fusion techniques were explored using transfer learning, alongside two single-sensor models using only RGB or thermal data. Five DNN models were developed and evaluated, with experimental results showing superior performance of fused models over non-fusion counterparts. The late-fusion system was selected for its optimal balance of accuracy and response time. For real-time inferencing, the best model was further optimized, achieving 33 fps on the embedded edge computing device, an 83.33% improvement in inference speed over the system without optimization. These findings are valuable for advancing Advanced Driver Assistance Systems (ADASs) and autonomous vehicle technologies, enhancing pedestrian detection during nighttime to improve road safety and reduce accidents.

Unveiling gap acceptance behaviour during lane change with EDIV data: A deep dive into driving behaviour on expressway using a three level mixed effect linear regression approach

Lane change has a potential significance in road safety. Gap acceptance phenomena serves as a primary and critical phase in lane change maneuver. This study aims to investigate the gap acceptance behaviour of drivers during lane changes on expressways, with a focus on understanding how various factors influence drivers' decisions to change lanes. An extensive dataset collected through various sensors tailored for expressway driving, known as the ‘Expressway Drive: Instrumented Vehicle (EDIV) Dataset’ is utilized. Driving data from 59 drivers covering a distance of around 4000 km was used in the current study. Total 2578 lane changing events are identified through computing lateral deviations measured through 3D LiDAR sensor. Substantial differences are observed within the groups in primary analysis which suggest that lane-change direction significantly affect gap acceptance. To effectively manage both intra- and inter-cluster variances, this study employs two separate three levels mixed-effects linear models. These models account for the interdependence of gap acceptance characteristics within individual drivers and for different directions of lane changes by incorporating random effects. Furthermore, these models examine relationships between lead/ lag gap acceptance and the various influencing factors as fixed effects. It was found that factors such as speed of the subject vehicle, gap position, relative speeds, and surrounding vehicle types had influence on gap acceptance during lane changes on expressways. The insights gained from this study could inform the development of advanced driver assistance systems (ADAS) as well as development of autonomous vehicles, contributing to improved road safety and traffic flow management in high-speed environments.