Browse Topic: Active safety systems

Items (2,151)
Modern automotive platforms must serve multiple market segments amid rapid technological change and stringent regulation, making early concept selection a multi-criteria, product-line problem. This paper presents a repeatable workflow that integrates Model-Based Product Line Engineering (MBPLE), Multi-Criteria Decision Analysis (MCDA), and enterprise visualization. A Systems Modeling Language (SysML) 150% vehicle architecture in Cameo captures powertrain, chassis, and Advanced Driver Assistance Systems (ADAS) variability plus baseline and segment-specific requirements. Parametric models compute vehicle-level attributes (e.g., cost, mass, braking capacity, detection performance, Technology Readiness Level (TRL)) and enforce segment limits. A multi-attribute value theory (MAVT) framework model is implemented as constraint blocks to normalize attributes and aggregate stakeholder-elicited weights into an overall score per configuration. Cameo Trade Study sweeps the design space, exports a configuration–criteria dataset, and Power Business Intelligence (BI) dashboards enable interactive cost–value views, requirement compliance, and shortlist comparisons. Selected concepts are fed back into Cameo as feature configurations, improving traceability, scalability across product lines, and alignment between engineering models and management decisions.
Kliczinski, Gary, Pykor, Ryan
Advanced Driver Assistance Systems (ADAS) are evolving beyond onboard perception. The ability to dynamically map and share temporary road hazards is important for connected and autonomous driving, but authenticating the data is critical. An in-vehicle hazard recognition layer performs real-time video analysis and geotagging on embedded platforms. Real-time video is analyzed for road hazards—such as potholes, construction zones, waterlogging, fallen trees, roadside accidents, and debris—using onboard cameras and lightweight computer vision models. This metadata is sent to a cloud-based aggregation layer to validate hazard reports. It is of paramount importance to validate hazard reports originating from diverse sources, regardless of their accuracy. This paper presents a mathematical approach to determine an overall Hazard Confidence Score (HCS) based on data received from diverse sources. A unique hazard authentication model is introduced to quantify the credibility of each hazard report using six validation metrics.
Bose, Souvik
This document describes [motor] vehicle driving automation systems that perform part or all of the dynamic driving task (DDT) on a sustained basis. It provides a taxonomy with detailed definitions for levels of driving automation, ranging from no driving automation (Level 0) to automated driving under all conditions in which humans can drive, with human driving not needed (Level 5), in the context of [motor] vehicles (hereafter also referred to as “vehicle” or “vehicles”) and their operation on roadways: Level 0: No driving automation Level 1: Driver support for steering OR speed, with continual driver supervision necessary and driver intervention when needed Level 2: Driver support for steering AND speed, with continual driver supervision necessary and driver intervention when needed Level 3: Automated driving under defined conditions, with human driving needed following an alert or evident vehicle malfunction Level 4: Automated driving under defined conditions, with human driving not needed to mitigate risk Level 5: Automated driving under all conditions in which humans can drive, with human driving not needed. The simple level descriptors have been changed to improve understanding of the differences among levels, but these are NOT the definitions of the levels of driving automation. See the definitions of each automation level in Sections 4 and 5 for explanation of these changes. These level definitions, along with additional supporting terms and definitions provided herein, can be used to describe the full range of driving automation features equipped on [motor] vehicles in a functionally consistent and coherent manner. “On-road” refers to publicly accessible roadways (including parking areas and private campuses that permit public access) that collectively serve all road users, including cyclists, pedestrians, and users of vehicles with and without driving automation features. The levels apply to the driving automation feature(s) that are engaged in any given instance of on-road operation of an equipped vehicle. As such, although a given vehicle may be equipped with a driving automation system that is capable of delivering multiple driving automation features that perform at different levels, the level of driving automation exhibited in any given instance is determined by the feature(s) that are engaged. This document also refers to three primary actors in driving: the (human) user, the driving automation system, and other vehicle systems and components. These other vehicle systems and components (or the vehicle in general terms) do not include the driving automation system in this model, even though as a practical matter a driving automation system may actually share hardware and software components with other vehicle systems, such as a processing module(s) or operating code. The levels of driving automation are defined by reference to the specific role played by each of the three primary actors in performance of the DDT and/or DDT fallback. “Role” in this context refers to the expected role of a given primary actor, based on the design of the driving automation system in question and not necessarily to the actual performance of a given primary actor. For example, a driver who fails to monitor the roadway during engagement of a Level 1 adaptive cruise control (ACC) system still has the role of driver, even while they are neglecting it. Active safety systems, such as electronic stability control (ESC) and automatic emergency braking (AEB), and certain types of driver assistance systems, such as lane keeping assistance (LKA), are excluded from the scope of this driving automation taxonomy because they do not perform part or all of the DDT on a sustained basis, but rather provide momentary intervention during potentially hazardous situations. Due to the momentary nature of the actions of active safety systems, their intervention does not change or eliminate the role of the driver in performing part or all of the DDT, and thus are not considered to be driving automation, even though they perform automated functions. In addition, systems that inform, alert, or warn the driver about hazards in the driving environment are also outside the scope of this driving automation taxonomy, as they neither automate part or all of the DDT, nor change the driver’s role in performance of the DDT (see 8.13). It should be noted, however, that crash avoidance features, including intervention-type active safety systems, may be included in vehicles equipped with driving automation systems at any level. For automated driving system (ADS) features (i.e., Levels 3 to 5) that perform the entire DDT, crash mitigation and avoidance capability is part of ADS functionality (see also 8.13). Note that this document provides a taxonomy and definitions and is not a safety standard. The document is not intended to provide guidance for safe vehicle operation by the driving automation system.
On-Road Automated Driving (ORAD) Committee
An adaptive performance-enhanced path planning algorithm is proposed for unmanned surface vehicle (USV) to improve their responsiveness in dynamic maritime environments. The improved ant colony (ACO) algorithm incorporates a pheromone penalty mechanism and path smoothing to enhance search efficiency and path smoothness by removing redundant nodes and reducing excessive turning. Additionally, the dynamic window approach (DWA) is enhanced through three key modifications: optimizing overshoot, enhancing selection efficiency in candidate path, and adaptively adjusting evaluation function weights. These improvements improve the accuracy of planning and avoidance ability. Comparative analysis based on simulation data indicates that the proposed method yields a measurable improvement in path quality—characterized by reduced travel length and enhanced collision avoidance—leading to more robust navigation performance in complex marine transportation scenarios.
Sun, Jiamian, Li, Weifeng
With the continuous development of autonomous driving technology, vehicle collision warning systems are playing an increasingly important role in this field, promoting the progress and improvement of the whole autonomous driving field. But existing methods have low detection rates and unstable multi-target tracking performance. In particular, the estimation of relative motion parameters is still inaccurate due to the loss of direction information when relative speed is described as a scalar quantity. These limits produce easy collisions in the judgment of the car in a dangerous traffic environment. To solve these problems, a vehicle collision warning algorithm based on YOLOv8 and DeepSORT is proposed in this paper. YOLOv8 is introduced to detect the vehicle precisely, and DeepSORT is used to enhance multi-target vehicle tracking. The geometric principles of monocular vision are applied to extract key motion parameters such as distance and direction-signed relative speed. A classification logic is designed to distinguish between positive and negative relative velocities, enabling more accurate judgment of collision risk levels. In order to further enhance the reliability of the system, a four-stage cascaded false-alarm suppression mechanism is proposed. By adding velocity direction validation, distance validity checks, adaptive confidence thresholds, and a temporal consistency verification mechanism, the false alarm rate is reduced, and the proposed approach can realize direction- aware velocity estimation without requiring additional sensors and can be easily integrated into the existing YOLOv8 perception system.
Qin, Xiaoyu, Li, Wei
Typical maritime monitoring scenarios are usually constrained by factors such as multi-scale ship density, frequent motion overlap, and limited viewing angle of shore-based cameras. These challenges often lead to trajectory interruptions and identity mismatches in target detection and multi-target tracking tasks. In order to solve these problems, this study proposes a ship occlusion detection and tracking method based on the improved YOLOv8 model and further integrates an automatic identification system (AIS) trajectory reasoning. The method builds a unified perception framework with enhanced detection architecture, multi-source data fusion, and behavioral reasoning capabilities. First, in the target detection module, the improved SEConv structure is introduced into the YOLOv8 trunk network to address challenges caused by small-scale variations and severe occlusion in maritime scenes. The ReLU activation function in SEConv is replaced by the Swish activation function to enhance the nonlinear feature representation. In addition, the optimized SEConv is embedded in the C2f structure, and the convolutional block attention module (CBAM) attention mechanism is introduced to enhance the sensitivity of the model to the occlusion area. Next, for multi-target tracking, ByteTrack is used as the basic tracking framework. AIS trajectory data is introduced as auxiliary input to compensate for trajectory losses caused by occlusion. Finally, experimental results on the SeaShips public dataset and the self-built occlusion reference dataset show that the improved YOLOv8 detector achieves stable mAP gains in mild, moderate, and severe occlusion scenarios. The AIS enhanced tracking system improves the multi-target tracking accuracy (MOTA) and identification F1 score (IDF1) by about 6.3% and 8.1%, respectively, and the average occlusion reconstruction error is controlled within 1.4 seconds. The proposed method effectively enhances the perception ability of ships in complex occlusion environments and verifies the feasibility and superiority of the strategy of combining visual detection with AIS data assistance.
Guan, Keping, Chen, Miao, Zhou, Yue
Research on automatic emergency braking (AEB) control algorithms for heavy vehicles is relatively limited. Compared with passenger cars, heavy vehicle AEB algorithms must accommodate both unloaded and fully loaded conditions, with the latter posing higher demands. This study compares two distinct AEB control strategies: the time-to-collision (TTC) algorithm and the professional driver fitted (PDF) algorithm. Using simulation analyses under three regulatory-recommended scenarios—stationary lead vehicle, slow-moving lead vehicle, and decelerating lead vehicle—the results indicate that the PDF-based control system better adapts to both unloaded and fully loaded conditions. It demonstrates significant improvements in braking performance and robustness compared to the TTC-based system. For an unloaded vehicle equipped with the PDF–AEB control system (5500 kg), the final gap to the lead vehicle is the longest (11.5 m) under the scenario of a stationary lead vehicle with an initial ego vehicle speed of 80 km/h and the shortest (3.1 m) under the scenario of a lead vehicle with an initial speed of 50 km/h braking at 0.4 g. For a fully loaded vehicle (12,500 kg), the corresponding final gaps to the lead vehicle are 11.2 m and 2.5 m, respectively.
Lai, Fei, Huang, Chaoqun
Driver’s distraction and fatigue are among the major contributing factors of traffic accidents. This study presents a methodology to identify driver’s distraction using a refined You Only Look Once (YOLO) model, denoted as YOLOv11.To address the inconsistent performance of earlier versions of YOLO, especially with regard to lack of systematic evaluations, this study proposes an improved YOLOv11 model. A mixed local channel attention (MLCA) module is further introduced to enhance small object feature extractions considering the use of Wise-Intersection over Union (IoU) v3 loss function to improve localization accuracy and training stability. Experiments demonstrated that this model outperforms competing models across all metrics, achieving 99.13% mAP at 0.5 and 82.54% mAP at 0.5:0.95, while also achieving minimal bounding box loss. The proposed model demonstrated higher accuracy and robustness, making it suitable for real-world driver monitoring system (DMS) deployments.
Ma, Bao, Taghavifar, Hamid, Fu, Zhijun, Karangwa, Jules, Rakheja, Subhash
As tractor-trailers are essential to global logistics, their roll stability during emergency maneuvers is a critical safety concern. This paper presents a novel delay-compensated active roll control strategy for tractor-trailers using a two-dimensional piston pump electro-hydrostatic actuator (EHA). Unlike existing advanced strategies that assume ideal actuator behavior, this approach specifically targets the inherent response delay in high-tonnage applications. A detailed EHA model, including pump flow characteristics and hydraulic mechanics, was developed and validated through step response experiments. A seven-degree-of-freedom vehicle dynamics model and a model predictive controller were also constructed to compute the required anti-roll moment under emergency driving conditions. In order to address the EHA actuator’s response delay, a delay feedforward controller (DFC) was designed, integrating acceleration feedforward, feedback regulation, and delay disturbance estimation. TruckSim–Simulink co-simulations under double lane-change (DLC) maneuvers at 40 km/h, 60 km/h, and 80 km/h show that DFC improves displacement tracking and reduces peak trailer roll angle by up to 15% compared to a velocity-feedforward proportional-integral-derivative (VFPID) controller. It also enhances control efficiency, as evidenced by lower average motor speeds and pressure response of EHA. The system demonstrates high power-to-weight ratio and efficient tracking capabilities under dynamic conditions. Although active control provides limited benefit at low speeds, the proposed strategy effectively improves roll stability and driving safety under dynamic conditions.
Chen, Lijie, Yin, Yuming, Zeng, Yuhang, Ruan, Jian, Li, Hangqi, Sun, Peng
This specification covers a corrosion- and heat-resistant steel in the form of wire.
AMS F Corrosion and Heat Resistant Alloys Committee
Sonatus and Omdia surveyed over 500 auto executives for their thoughts on SDVs, and the responses revealed that - once again - the future is unwritten. Data monetization as a top priority dropped from 51% to 44% (YoY) as automakers focus more on using data internally, with ADAS and product improvements rising six points to 41%. We spoke with Sonatus CMO John Heinlein about the survey for a recent episode of the SAE Automotive Engineering Podcast. You can listen via the links at the bottom of this Q&A, which is an edited version of our full discussion.
Blanco, Sebastian
Advanced Driver Assistance Systems (ADAS) are increasingly integrated into heavy-duty commercial vehicles to improve road safety, mitigate accident severity, and enhance operational efficiency. In the context of braking systems, however, a significant gap remains between system calibration practices and real-world operating conditions, where most evaluations and validations of ADAS and braking performance are conducted under nominal or standardized load assumptions, which fail to represent the wide variability of payload magnitude and distribution typically observed in trucks, semi- trailers, and buses. Variations in vehicle mass and load distribution directly affect braking efficiency, axle load transfer, center of gravity (CG) position, and stability limits, posing critical challenges to both conventional brake systems and brake-related assistance functions. This paper presents an exploratory qualitative study based on a systematic literature review addressing the influence of variable loading on braking performance and the operation of ADAS in commercial vehicles. Scientific publications, experimental investigations, and technical reports from both academia and industry were thoroughly analyzed, with emphasis on service brake efficiency, load-dependent braking behavior, rollover propensity, and the performance of the ADAS systems. The reviewed studies demonstrate that longitudinal, lateral, and vertical CG displacements significantly modify braking force distribution, actuator effectiveness, and stopping distances, particularly under emergency braking and downhill driving conditions. Improper load distribution was consistently associated with reduced braking margins and increased instability risk. The findings further indicate that integrating load-aware strategies into braking control and ADAS calibration can improve braking consistency, reduce component stress, and enhance overall vehicle safety. As a contribution, this work emphasizes the need to incorporate variable load conditions into braking system evaluation, ADAS development, and certification procedures for heavy commercial vehicles, ensuring robust and reliable performance under real operating conditions.
Rubbo, Bruno Tiago, Dacol, Franco De Bastiani, Do Nascimento, Vagner
This paper proposes a nonlinear and robust State-Dependent Riccati Equation (SDRE) combined with H∞ control architecture for brake- by-wire systems, specifically designed to handle severe tire-road friction variations and μ-split scenarios. The primary objective is to maximize deceleration capabilities while rigorously maintaining yaw stability, trajectory tracking, and passenger comfort through jerk limitation. Situated within the domain of active safety, this research addresses robustness against real-world uncertainties by utilizing a high-fidelity 14-degree-of-freedom vehicle model that accounts for longitudinal, lateral, and yaw dynamics, suspension-induced pitch and roll effects, and nonlinear tire behavior with explicit load transfer. To ensure near-optimal slip tracking under variable surface conditions, the system employs online friction estimation via Extended and Unscented Kalman Filters (EKF/UKF) fusing wheel and IMU data to adaptively adjust slip targets. The control strategy is bifurcated: the SDRE component manages dominant nonlinearities through state-dependent gains to prevent wheel lock-up, while the H∞ component provides robust disturbance rejection against parametric uncertainties such as mass variations and sensor noise. Control efforts are distributed via a Quadratic Programming (QP) torque allocator featuring anti-windup mechanisms and explicit saturation handling to compensate for lateral drift during μ-split braking. Validation is conducted through a Model- in-the-Loop (MIL) to Software-in-the-Loop (SIL) pipeline using scenarios including wet surfaces and panic braking. Simulation results demonstrate enhanced yaw stability and controlled deceleration profiles compared to conventional baselines, ensuring computational feasibility for automotive Electronic Control Units (ECUs).
Cubillos, Ximena Celia Méndez
The implementation of ADAS in buses represents both a significant opportunity and a complex challenge for the future of urban mobility. While ADAS technologies such as lane departure warning, adaptive cruise control, blind spot detection, and autonomous emergency braking have been widely adopted in passenger cars and trucks, their integration into buses has been slower due to unique operational and safety concerns. This paper provides a broad overview of the advantages and obstacles associated with ADAS deployment in public transport vehicles, with particular emphasis on passenger safety, regulatory frameworks, and operational efficiency. Key barriers include the vulnerability of standing passengers during sudden braking events, the unpredictability of pedestrians and cyclists in dense urban environments, and the economic constraints faced by bus operators. At the same time, regulatory initiatives such as Transport for London’s Bus Safety Standard, the European Union’s General Safety Regulation, and Brazil’s MOVER program are driving the gradual adoption of these systems. The benefits of ADAS in buses extend beyond accident reduction, encompassing improved driver ergonomics, reduced fatigue, lower maintenance costs, and enhanced passenger comfort. Case studies from Europe, Brazil, and Asia highlight both the safety potential and the reluctance of drivers to fully embrace these technologies, often due to knowledge gaps and perceived inconvenience. The analysis underscores that successful implementation requires not only technological adaptation but also comprehensive driver training, infrastructure readiness, and public policy support. Ultimately, ADAS in buses should be understood as a transitional step toward autonomous mobility, offering immediate safety gains while reshaping the paradigm of urban transport.
Marcon, Ederson, Michelon, Gabriel, do Nascimento, Vagner
Ammonia is receiving heightened attention as a carbon-neutral and hydrogen energy carrier alternative fuel for compression ignition engines. However, replacing diesel with ammonia poses significant challenges due to its low reactivity and slow-burning nature, particularly at low-load conditions. This study investigated the effect of ammonia energy share (AES) on the combustion characteristics and performance of an ammonia–diesel dual-fuel (ADDF) compression ignition engine operating under low loads and at a constant speed of 1800 RPM. The experiments were conducted at three different loads: 6 Nm, 13.5 Nm, and 18 Nm, corresponding to 11%, 25%, and 33% of full load, respectively. At each load, the AES was incrementally increased, ranging from zero to its maximum limit, while maintaining the COV of IMEP below 3% to ensure stable combustion. Furthermore, CFD simulations were performed using a CONVERGE CFD model of the engine to analyze the in-cylinder thermal and chemical behavior, and the model was validated against the experimental data. The experimental results showed that the AES reached 40%, 58%, and 61% for engine loads of 6 Nm, 13.5 Nm, and 18 Nm, respectively. Increasing AES reduced the mean in-cylinder temperature and peak cylinder pressure, and shifted the peak pressure location toward the expansion stroke. Combustion phasing was delayed, and combustion duration increased with higher ammonia substitution. CFD analysis revealed weaker high-temperature and OH reaction zones, along with reduced OH and H radical activity, and increased persistence of NH2 and HO2 evolution at higher AES, indicating slower oxidation of the ammonia-containing mixture. The results highlight the challenges associated with high-ammonia operation at low loads and provide deeper insight into the combustion processes governing ADDF engine performance.
Sardar, Gobinda, Kishore, Kislay, Pradeep, P., Mittal, Mayank
Advanced Driver Assistance Systems (ADAS) are increasingly prevalent in light vehicles, both in the United States and worldwide. Moreover, ADAS are steadily being incorporated into regulatory requirements globally. Like ADAS, the automotive aftermarket is also increasing in size and significance. As both ADAS and the aftermarket industry are growing, the effect of aftermarket modifications on ADAS functionality should be examined. However, there is very little information available in the public domain about the effect of aftermarket modifications on original equipment ADAS. This work is centered on a considerable research project that was conducted to address the knowledge gap at the intersection of ADAS and the aftermarket. The project investigates five light vehicles that are important to the aftermarket, including four pickup trucks and one sport-utility vehicle. It focuses solely on the effect of popular aftermarket suspension modifications, and it does not evaluate aftermarket ADAS equipment. Typical suspension modifications were applied to the test vehicles in five modification categories, including stock, lower kits, level kits, 3–4 in. lift kits, and 6 in. lift kits. Six ADAS test procedures were performed for the test vehicles, comprised of blind spot detection, crash imminent braking, lane departure warning, pedestrian automatic emergency braking, rear cross traffic alert, and traffic jam assist. The physical tests were developed based on National Highway Traffic Safety Administration (NHTSA) New Car Assessment Program (NCAP) written experimental procedures. Statistical hypothesis testing was performed for the purpose of determining if average measured dynamic responses varied in the modified vehicles compared to stock. The results show that vehicles modified with typical aftermarket modifications will likely retain their ADAS functionality, given the limitations of the small sample size of five vehicles. Vehicles with 6 in. lift kits are expected to exhibit greater variability in their dynamic responses compared to stock. Plans for future work and unanswered research questions are outlined, with the goal of advancing aftermarket ADAS integration and ensuring the safety and performance of modified vehicles.
Bastiaan, Jennifer M., Morales, Luis, Muller, Mike
This SAE Information Report provides a broad summary of existing Reverse Automatic Emergency Braking test protocols to help assess whether additional test protocols are needed. Eventually, the task force may develop additional protocols to support testing of Reverse Automatic Emergency Braking systems.
Active Safety and Driver Support Systems Standards Committee
Internal recirculating ball screws are widely used as linear motion components in automotive active safety systems, owing to their simple structure and compact size. The recirculation (or deflection) channel is a key feature that distinguishes this type from other ball screw designs. The objective of this article is to investigate this key feature that has been rarely addressed in existing research on internal ball screw. The conventional design method for the recirculation channel involves sweeping the cross-section along the center curve. The center curve is typically defined by various classical equations. These equations are applied in different application scenarios. In automotive braking systems, high loads and strict size constraints place critical demands on both the recirculation channel and its center curve. As a representative best-practice example, the machined channel in the screw is typically employed in this application. This article compares several classical center curve equations and proposes a new general approach based on a family of transition curves. The mechanical analysis identifies the inherent structural characteristics of recirculation channel and develops corresponding design guideline. Furthermore, parameter optimization is performed using MSC ADAMS Multibody Dynamics (MBD) software.
Xia, Xinan, Xia, Yanzhe, Zhao, Tina
Ultrasonic sensors are widely deployed in automotive driver assistance systems for near-range environment perception and provide safety-relevant inputs for functions such as parking assistance and automated parking. With increasing vehicle automation, the integrity and availability of ultrasonic sensor data become more critical, as compromised measurements may lead to incorrect vehicle decisions and hazardous behavior. While prior research has extensively studied physical attacks on ultrasonic sensors, a structured cybersecurity risk analysis in accordance with automotive cybersecurity standards, combined with experimental validation, is largely missing. In particular, the communication interface between ultrasonic sensors and control units has received limited attention despite its relevance as a potential attack surface. This paper presents a systematic security analysis of an automotive ultrasonic sensing system based on a demonstrator setup. The work applies a Threat Analysis and Risk Assessment methodology aligned with ISO/SAE 21434 and HEAVENS 2.0 to identify security-relevant assets, threat scenarios, and attack paths. Risk levels are derived by evaluating potential impact and attack feasibility. To validate the risk assessment, a structured test strategy is developed using the ISTQB test process and translated into laboratory experiments. Both digital attacks targeting the sensor communication interface, with DSI3 selected as the representative protocol, and physical manipulations of the sensor environment are examined. Experimental results show that selected communication-level attacks can be realized with moderate effort and can cause controlled falsification or loss of measurement data. Physical environmental manipulations significantly degrade signal quality but do not fully suppress object detection in the evaluated configuration. The findings largely confirm the initial risk assessment while enabling refinement of attack feasibility parameters. The results provide a validated linkage between automotive cyber-security risk assessment methods and practical testing of ultrasonic sensing systems and underline the importance of jointly addressing communication interfaces and physical effects in future security concept development.
Gahm, Sebastian, Haller, Jonathan, Kriesten, Reiner
This paper investigates the integration of Artificial Intelligence (AI) within radar-based perception for Advanced Driver Assistance Systems (ADAS) under safety considerations aligned with ISO 26262 [1] for functional safety and ISO 21448 (SOTIF) [2] for performance-related safety of the intended functionality. The study evaluates a hybrid architecture in which AI-based perception modules are combined with deterministic supervisory mechanisms to maintain safety compliance. A simulation-based case study using CARLA with radar sensor modeling is presented to compare a deterministic radar perception pipeline with an AI-enhanced approach under nominal and degraded environmental conditions. Performance is evaluated using precision, recall, and F1 score metrics. Results indicate improved recall and F1 score under adverse scenarios for the AI-based perception module, accompanied by a moderate increase in false positives. The paper discusses architectural constraints required to limit non-deterministic behavior, including confidence gating, deterministic supervision, and scenario-based validation. The findings are limited to simulation and are intended to provide preliminary insights into the technical and safety implications of incorporating AI-based radar perception within ISO 26262-compliant ADAS architectures.
Jain, Yesha
The development and validation of advanced driver-assistance systems (ADAS) and automated driving systems (ADS) are shifting from traditional linear V-model processes toward more iterative engineering cycles. Despite faster iteration, these safety-critical systems remain subject to stringent regulations. Standards and guidance, including UNECE UN Regulation No. 157 and ISO/TS 5083, emphasize traceability, transparency, and explainability throughout development and validation. Nevertheless, as ADAS/ADS are developed and validated in faster, more iterative release cycles, additional stakeholders become involved and new explainability requirements emerge. These requirements vary between stakeholders and across development, validation, and post-market deployment phases, yet they are not systematically captured in the current state of research and practice. Therefore, to ensure that explainability supports rapid iteration, it is essential to identify relevant stakeholders and specify their explainability needs. Standards such as IEEE Standard 7001-2021 provide a broad foundation for transparency in autonomous systems. However, their generic nature does not address the domain-specific complexities of ADAS/ADS. Furthermore, a conceptual gap remains between general transparency principles and explainability requirements in automotive development and validation. Building on IEEE Standard 7001-2021, this paper first offers a stakeholder taxonomy in the context of ADAS/ADS, then proposes a stakeholder-oriented analysis of explainability requirements within an automated driving use case and contexts. This analysis specifically focuses on the motivations for requiring explainability and the necessary explanation modalities. Finally, the paper discusses the limitations of the analysis and outlines directions for future research. The results of the paper provide a structured guideline for stakeholder-oriented explainability requirements in ADAS/ADS.
Liu, Xuanheng, Bairy, Akhila, Paudel, Bijay, Adolph, Laurenz, Heck, Melanie, Hettich, Lennard, Nägele, Ann-Therese, Rudolf, Korbinian, Bause, Katharina, Düser, Tobias, Schwammberger, Maike
Driver monitoring systems are an important component of active safety systems, continuously evaluating the driver’s state and issuing real-time warnings. As defined by the SAE Levels of Automation, driving tasks are increasingly transferred from the driver to the vehicle from Level 0 to Level 2, however, the driver remains fully responsible for monitoring the driving environment. Current implementations, such as driver drowsiness and attention warning, assess driver alertness, while advanced driver distraction warning ensures that the driver maintains visual focus. Nevertheless, these systems do not identify the specific objects or regions the driver is observing. This limitation motivates the presented research question: can an in-car monitoring system be integrated with external environment perception sensors to infer the driver’s field of view (FoV)? This paper presents a system consisting of a driver-facing camera and a front-view camera. Facial features, including gaze direction, head pose, and iris offset are extracted using computer vision techniques. These features, together with cropped eye images, are used as inputs to a multi-modal network. Training labels were generated using a driving simulator study with 16 participants who sequentially fixated on visual targets displayed on a front screen. Experimental results show that the proposed system can predict driver visual attention and approximate FoV with a mean pixel error of 35.40 px, enabling identification of the regions of the road scene observed by the driver in real time. This work provides a foundation for explicitly modeling driver perception and its correspondence with vehicle perception systems.
Ji, Dejie, Lausch, Hendryk, Flormann, Maximilian, Henze, Roman
The current document is a part of an effort of the Active Safety Systems Committee, Active Safety Systems Sensors Task Force whose objectives are to: a Identify the functionality and performance you could expect from active safety sensors b Establish a basic understanding of how sensors work c Establish a basic understanding of how sensors can be tested d Describe an exemplar set of acceptable requirements and tests associated with each technology e Describe the key requirements/functionality for the test targets f Describe the unique characteristics of the targets or tests This document will cover items (a) and (b).
Active Safety and Driver Support Systems Standards Committee
Automotive Engineering: June 202626AUTP066/4/2026
New York 2026: diversity on full display New powertrain choices keep popping up on new vehicles from OEMs that debuted at NYIAS this year. Sealing integrity in a Formula 1 limited-slip differential High-temperature hydraulic control in a Formula 1 drivetrain requires dimensional stability, controlled sealing force, and resistance to wear under sustained pressure cycling. Inside the limited-slip differential, the sealing architecture plays a defined mechanical role in maintaining consistent torque management under race conditions. From ADAS to autonomy How engineering thermoplastics can advance sensor-based technologies. Synthetic data and the future of ADAS validation Why ADAS validation can't be solved with more miles alone. Intelligent power distribution will change the way vehicles are designed Electronic fuse (eFuse) technology can create electronic power distribution modules (ePDMs) for architectural flexibility, higher reliability, greater safety, and proactive maintenance. Editorial Maybe more than ever, let's talk transportation diversity The Navigator Can legacy automakers finally succeed with SDVs? AI scares and excites cybersecurity professionals at WCX Expert claims war hurting China's already-struggling economy NHTSA open to negotiated rulemaking on some safety issues Resilient propulsion strategies require options Driven: Honda Fastport eQuad Prototype Product Briefs Spotlight: Connectors & harnesses, EV thermal management Q&A Neural Concept's Thomas von Tschammer: Working with AI at speed
In the two months since Microvision bought Luminar and acquired key tech and talent, the sensor company has been busy. In that time, they've merged key lidar units from each company and created a perception software stack to run it in a convincing demo of its ADAS and autonomous capabilities. The company is also pushing innovative lidar tech into the defense drone and antidrone markets, already working with a German defense supplier that works with NATO member countries.
Clonts, Chris
Why ADAS validation can't be solved with more miles alone. Modern advanced driver assistance systems (ADAS) are expected to operate reliably across an almost limitless range of real-world conditions, including changing weather, low lighting, unpredictable traffic behavior, and sensor noise. Validating performance across that level of variability has become one of the most demanding parts of ADAS development. Physical road testing, or even large-scale simulation, alone cannot provide sufficient coverage to meet these demands. This challenge is driven by increasing system complexity. Modern ADAS platforms rely on machine-learning-based perception, multi-sensor fusion, and tightly integrated software architectures that must interpret complex sensor data in real time. Each additional sensing modality, software update, or feature expansion drives a significant validation effort and, in many cases, increases the number of scenarios that must be evaluated.
Kuehnke, Lutz
Bird accidental collision with overhead transmission lines poses a threat to the ecology of rare bird populations. This article analyzes the warning measures to prevent birds from accidental collisions at home and abroad. In response to the low efficiency of manual installation and the poor static warning effect in preventing birds from accidental collisions with overhead transmission lines, the visual characteristics of birds are analyzed. A drone-based automatic installation flash-type bird accidental collision warning device is proposed, which includes a fixture, a disc, and a luminous circuit. The fixture can be carried and installed on the overhead line by a drone and can be easily disassembled. The disc adopts eye-catching colors and has a hollow structure to reduce wind resistance load. The luminous circuit includes solar panels, charge and discharge control circuits, flicker control circuits, batteries, and luminous components. The drone suspension warning device test was conducted, and the results showed that the device can be easily suspended from the overhead line by the drone.
Wang, Jian, Wang, Xiulong, Liu, Bin, Li, Danyu, Xu, Xunjian
Active collision avoidance methods are crucial components of vehicle active safety systems, which can effectively prevent collisions or mitigate collision-induced losses. To address the limitations of existing methods, particularly their insufficient foresight in dynamic traffic environments, this paper proposes an active collision avoidance control method based on driving intention recognition and an improved Driving Safety Field (DSF) model to enable more proactive and stable collision avoidance. First, a Hidden Markov Model (HMM) is trained using vehicle trajectory data from a public dataset to accurately identify the driving intentions of the obstacle vehicles, including Lane Change Left (LCL), Lane Keeping (LK), and Lane Change Right (LCR). Then, an improved potential field model is established, which incorporates vehicle acceleration to more comprehensively quantify the driving risk faced by the host vehicle within the DSF model framework. Subsequently, an active collision avoidance controller combining a longitudinal dual-PID braking controller and a lateral MPC steering controller is designed. This controller initiates corresponding avoidance actions based on the results of driving intention recognition and driving risk evaluation. Finally, co-simulation and hardware-in-the-loop (HIL) tests are conducted. The results demonstrate that, compared to conventional methods lacking driving intention recognition, the proposed method can initiate avoidance maneuvers approximately 1 s earlier, thereby more effectively avoiding potential collisions. Furthermore, key vehicle stability indicators, such as lateral acceleration and yaw rate, are significantly reduced during the avoidance process, indicating enhanced stability and satisfactory real-time performance. This method provides a solution for enhancing the active safety of vehicles in complex real traffic scenarios.
Pan, Yuxiang, Chen, Jin, Wang, Haitao, Bai, Xianxu
Letter from the Guest Editor
Tylko, Suzanne
NHTSA is conducting research to evaluate the current state-of-the-art technology for lane departure warning (LDW) and lane-keeping assistance (LKA) technology. NHTSA is undertaking research to understand the nature of real-world lane departures and recovery behaviors. While some information about lane departures can be learned from crash datasets, the purpose of this work was to mine simulator datasets for lane departures, analyze them in greater detail than is possible from crash reports or naturalistic studies, and link their characteristics to driver drowsiness. The objective of the study was to determine whether there are differences in lane departure characteristics as a function of driver drowsiness. This research used a novel approach by combining data from six different driving simulator studies on driver drowsiness. The dataset included a sample of 380 drivers. Study drives occurred during overnight hours after periods of sleep deprivation, with participants being awake for at least 16 h prior to driving. Study drives ranged in duration from relatively short 45-min to nearly 4 h. The datasets were reduced to characterize 5805 individual lane departures. Lane departures were delineated into three phases (pre-departure, departure, and recovery) and two transition points (onset and reentry) to capture driver behaviors under drowsiness. We hypothesized that lane departures would look different under different levels of drowsiness. Drives took place across a range of roadway environments that included interstate highways, rural highways, rural roads, and low-speed urban areas. Drowsiness was sampled at points before, during, and after the drive using self-ratings [Karolinska Sleepiness Scale (KSS) or Stanford Sleepiness Scale (SSS)] as well as the expert Observational Rating of Drowsiness (ORD). High levels of drowsiness were associated with a narrow speed range at highway speeds and the least amount of throttle input, while low levels of drowsiness had more steering activity, more throttle input, and a broader range of speeds. The results of this study will improve understanding of vehicle kinematics and driver behavior in drowsy lane departures using a safe methodology to help address crash dataset limitations.
Schwarz, Chris, Gaspar, John, Shull, Emily, Venegas, Michael
Roadway departures remain a major cause of crashes, injuries, and fatalities on U.S. roads. Technologies such as lane keeping assist (LKA) and lane centering assist (LCA) can help mitigate these crashes, but their development involves extensive characterization of the parameter space in which they operate. Lane and road departures (LDs/RDs) and lane changes (LCs) must be systematically described and quantified to distinguish kinematic features, identify contributing factors, and benchmark system influence on lateral control. This study developed a unified pipeline to mine over 36 million miles of naturalistic driving study (NDS) data collected from more than 3800 participants. The pipeline integrates various types of signals to detect roadway boundary crossings, classify LKA-relevant scenarios, and extract roadway, driver, environmental, and assistance-related parameters. Lane keeping epochs with and without LKA were also extracted to quantify system influence on lateral control. In the NDS analysis, crashes include both object contact events and RDs, defined as non-premeditated departures from the intended travel surface involving at least one tire. Analysis of pre-identified crashes in the NDS showed that unintentional RDs accounted for 5.67%, unintentional LDs for 1.76%, and intentional LCs for 1.55%, corresponding to lower-bound rates of 2.7, 0.8, and 0.7 crashes per million vehicle miles traveled. RD crashes were predominantly right-sided, LD crashes left-sided, and both were overrepresented on curves and under adverse conditions. Loss of control preceded 22% of RD crashes and 69% of LD crashes. Beyond crashes and near-crashes (CNCs), the algorithm identified approximately 3 million LCs and 0.3 million LDs/RDs. LCs typically involved larger crossing angles that decreased with speed, while departures clustered within 0°–2°. Compared with CNCs, these occurred at higher speeds and smaller angles. LKA consistently reduced lateral variability without biasing the mean offset.
Ali, Gibran, Terranova, Paolo, Williams, Vicki, Holley, Dustin, Saffy, Joshua, Antona-Makoshi, Jacobo, Kefauver, Kevin, Shull, Emily, Li, Eric, Venegas, Michael
This research examined the performance of SAE Level 2 (L2) advanced driver assistance systems (ADAS) in crash-imminent scenarios (CIS), with particular attention to how vehicle configuration like body style and powertrain (internal combustion engine, plug-in hybrid, electric vehicle) influences vehicle system performance. The objectives were to (1) identify CIS relevant to L2-equipped vehicles using crash databases and naturalistic driving studies (NDSs), (2) develop scenario-based test procedures and test matrices, and (3) evaluate system and vehicle responses across configurations and conditions. Multiple crash data sources were analyzed, including NHTSA’s Standing General Order dataset of L2-related crashes, the Fatality Analysis Reporting System, the Crash Report Sampling System, and NDS data from the Second Strategic Highway Research Program and the Virginia Tech Transportation Institute L2 NDS. Coded variable analyses from the datasets identified three common CIS: lane and road departures, rear-end striking events, and intersection conflicts. Supporting variables such as speed, roadway condition, and driver actions were also extracted to characterize scenarios and inform test development. Tests were executed at a closed-track testing facility using four vehicles selected for diversity of L2 systems, body types, and powertrains. Phase 0 exploratory testing assessed vehicle kinematics and L2 responses to refine the test matrix. Phases 1 and 2 conducted controlled evaluations of selected CIS, with expansion factors reflecting real-world crash variability. The testing highlighted interactions between L2 features and active safety systems. For example, results showed that all four vehicles employed distinct hand-off strategies between L2 longitudinal control and active safety systems during rear-end striking crash scenarios, and AEB engagement was strongly correlated with TTC at the moment the vehicle identified the crash partner. This work contributes novel insights into vehicle L2 and ADAS behavior in CIS events across multiple factors and provides a structured framework to evaluate system behavior for those crash-imminent scenarios.
Beale, Gregory, Kefauver, Kevin, Venegas, Michael, Li, Eric, Chen, Jay, Huggins, Steven, Guduri, Balachandar, Llaneras, Eddy
The objective of this study was to characterize and compare pedestrian automatic emergency braking (PAEB) pulses in modern light vehicles to understand the loading environment that vehicle occupants are being exposed to during PAEB maneuvers. PAEB tests (n = 8008) conducted using 2018–2023 vehicle model years were analyzed. Pulse, vehicle, and impact characteristics (e.g., jerk, peak acceleration, pedestrian scenario, etc.) were derived from each PAEB test. Two k-means clustering analyses were used to group PAEB pulses with and without target collisions based on their similarity between characteristics. One-way ANOVA and Kruskal–Wallis tests were performed on the PAEB pulse characteristics to examine differences between clusters (p < 0.05). Two non-collision clusters (NC1 and NC2) were identified for PAEB pulses without collisions: NC1 had a statistically significant lower jerk (0.8 ± 0.4 g/s) and peak acceleration (1.0 ± 0.1 g) compared to NC2 (1.6 ± 0.8 g/s and 0.9 ± 0.1 g, respectively, p < 0.001). NC1 was mostly represented by stationary adult (88.6%), 60 km/h (99.5%), and 40 km/h (62.2%) tests. NC2 was mostly represented by crossing scenarios (child: 92.3%; adult: 70.5%) and 20 km/h (96.2%) tests. Three collision clusters (C1, C2, and C3) were identified for PAEB pulses with collisions. C3 showed a greater jerk (1.5 ± 0.8 g/s) compared to C1 (0.9 ± 0.6 g/s) and C2 (1.1 ± 0.9 g/s, p < 0.001). These results suggest that with successful avoidance, deceleration begins earlier with higher speeds and a stationary pedestrian, resulting in potentially milder loading conditions for vehicle occupants (i.e., lower jerk in NC1 vs NC2). With unsuccessful avoidance, in daytime pedestrian crossing scenarios, lower impact speeds were observed, resulting in potentially non-optimal loading conditions (i.e., higher jerk and peak acceleration in C3) for vehicle occupants. At night with low beams, C2 may result in advantageous loading conditions for vehicle occupants (i.e., lower jerk and peak acceleration), but it may lead to the worst outcome for pedestrians (i.e., greatest impact speed).
Witmer, Maitland, Kidd, David, Graci, Valentina
While an enlarged lead time from risk notifications to collisions is widely acknowledged to facilitate safe driving, it remains challenging to effectively notify drivers of invisible risks and non-apparent risks coming from uncertain behaviors on the part of road users. The current study examined whether verbal notifications are able to assist early awareness of predictive risks. We also attempted to identify human and environmental factors that could possibly improve the effectiveness of predictive risk information. Twenty-eight licensed drivers participated in a public road test conducted in two different urban areas on 3 days. They drove predefined courses on which potential risk locations were identified prior to the test, using a sport utility vehicle equipped with an automatic verbal notification system triggered based on the distance to the potential risk locations. After passing through the locations each time, the participants were instructed to verbally evaluate the shift in awareness provided by the notification and the usefulness of the assistance. After the driving test was completed, we acquired a subjective evaluation on annoyance acceptability and a self-report of participants’ road usage frequency at notified locations in daily life, as well as questionnaires on their driving style and workload sensitivity. We found that the effectiveness of verbal notifications increased by conveying uncertainty risks at visible locations and by using interrogative sentences or expressions of risk target perspective, although it decreased as a function of age. Our model showed strong performance in predicting positive ratings for the notifications, but this was not the case for negative ratings. We identified individual characteristics and the risk factor of uncertainty as important features in our model. In conclusion, the findings provide an important reference for understanding the early notification of predictive risk and constructing a numerical model for the implementation of assistance systems in vehicles and nomadic devices.
Maruyama, Masaki, Koyama, Keiichiro, Ezaki, Toru, Sakamoto, Junichi, Sawada, Yuta, Matsuoka, Takahiro
Drivers frequently encounter Type II dilemma zones at signalized intersections, where the decision to stop or proceed during the onset of a yellow indication can be ambiguous. Decision-making relies on drivers’ expectations of the yellow change interval duration and behavioral factors. While boundaries of these zones are well studied, less is known about how familiar drivers are with their local yellow indication laws, which vary from state to state, and whether their typical reactions to yellow indications align with the laws. Existing interventions like signal timing adjustments, improved vehicle detection, and advance warning signs reduce the number of drivers caught in dilemma zones but may not reach distracted drivers. In-vehicle alerts tailored to dilemma zone scenarios are a potential solution not yet implemented widely in North America. This study addresses how drivers may interpret these alerts. A web-based survey of 640 licensed drivers in Michigan and Washington (ages 18–85) assessed respondents’ knowledge of their state’s law, typical responses to yellow indications, interpretations of proposed in-vehicle alerts, and preferences for alert modality, frequency, and placement. These states were selected for their differing yellow indication laws—restrictive in Michigan, permissive in Washington. Nine alert visuals were tested, including pairs of implicit and explicit messages, and were inspired by or designed to address gaps in prior research. Respondents evaluated these alerts in response to hypothetical intersection scenarios that varied by the presence of other vehicles. Results revealed a prevalent misunderstanding of local yellow indication laws across both states. Statistical analyses showed significant differences in rankings among the nine alert visuals, and explicit messages showed higher rates of correct interpretation. Findings show overall driver support for dilemma zone alerts, but higher receptivity in drivers who more frequently use other ADAS features and lower receptivity in drivers within older, but not the oldest, age groups. Future research could explore whether these alerts promote safe behaviors aimed at crash avoidance.
Anderson, Erika, Jashami, Hisham, Ahmed, Ananna, Hurwitz, David
Programs that teach older drivers how to confidently and competently use advanced vehicle technologies (AVTs) are limited. The MOVETech study evaluated a training program specifically designed to teach older drivers how to use these technologies. Participants (n = 119) were randomized to the intervention (training program) or control group (brochure). The intervention involved an in-person classroom education session on the use and benefits of AVTs, and an on-road driving session where participants drove along a pre-defined route in a dual-controlled vehicle with instruction on AVT use by a driving instructor. All participants completed in-person and telephone assessments at baseline and 3 months. Driving performance and on-road AVT competence assessments were the primary outcomes. Self-reported driving confidence, competence, and confidence in use of AVT, crashes, citations, and count of vehicle damage were the secondary outcomes. Program fidelity was also evaluated using a checklist. At 3 months, overall driving performance was high (96/100) and similar between groups. The intervention group, however, had slightly higher competence in AVT use (77 vs 73), but the between-group difference was not statistically significant (4.14, 95% CI −4.85 to 13.13). There were no differences in secondary outcomes. Program fidelity was high for all classroom sessions but varied for on-road sessions due to external and environmental factors, which impacted how AVT was demonstrated. The findings indicate AVT competence and confidence may be improved by combining classroom and on-road sessions, and importantly, that this type of program is feasible and very well-accepted among older drivers. Future work could target drivers with new vehicles who are unfamiliar with AVT to determine potential real-world benefits. This study provides evidence for vehicle manufacturers and policymakers to explore efficient ways of providing support to older drivers with AVT.
Nguyen, Helen, Ren, Kerrie, Coxon, Kristy, Neville, Nick, O’Donnell, Joan, Cheal, Beth, Brown, Julie, Keay, Lisa
Vehicle maneuver data are essential for perception and planning in advanced driver-assistance systems (ADAS) and automated driving systems (ADS). While high-quality annotations improve machine-learning performance, existing maneuver datasets remain fragmented, labor-intensive to annotate, and inconsistent in semantic richness. Challenges persist in scalability, interpretability, and contextual labeling. This article establishes a structured framework for maneuver data analysis by combining a systematic review of existing resources with the development of a new multimodal dataset. First, we conduct a systematic review of publicly available datasets such as HDD, KITTI, BDD-X, D2CAV, Brain4Cars, DrivingDojo, and the Driving Behavior Database. We further evaluate the data modality and sensor configurations including event data recorders, onboard logging systems, and smartphone sensing. We then propose the Matt3r Data Collection System with modern metadata management, which integrates video, GPS, and IMU signals into temporally coherent clips. Next, we outline the limitations of traditional annotation approaches, which rely on manual labeling and rule-based methods. To address the limitations of traditional manual and semi-automated labeling, we propose a Vision–Language Model (VLM)–driven annotation pipeline. VLMs generate maneuver categories and causal explanations through prompt-based reasoning, with selected outputs refined through human-in-the-loop verification. Finally, we propose an annotation quality evaluation based on accuracy, inter-annotator agreement, credibility, consistency, and efficiency gain. In summary, this article bridges the gap between the environment perception requirements of existing ADAS and ADS systems and the developing capabilities of generative artificial intelligence. By providing a novel and scalable research approach for AI-driven maneuver data annotation and analysis, this article supports data engineering efforts for both research and practical applications aimed at enhancing vehicle safety.
Bai, Ling, Yuan, Chongyu, Osman, Islam, Lin, Zirui, Mirab, Ghazal, Saheb, Amir, Parnian, Neda, Shapiro, Evgeny, Shehata, Mohamed S., Liu, Zheng
To reduce traffic fatalities through vehicle safety measures, particular attention must be given to cyclist-related fatalities. Clarifying the characteristics of hazardous events leading to cyclist fatalities, not only by vehicle speed range but also by vehicle type, is essential and should be based on analyses of real-world accident data. Accordingly, this study aimed to characterize fatal cyclist accidents involving vehicles traveling at low and high speeds in Japan. We used macro accident data from the Japanese Institute for Traffic Accident Research and Data Analysis covering the period from 2013 to 2022. Based on nine vehicle types, we investigated the effects of road type, vehicle behavior, and accident type on cyclist fatalities. Additionally, we identified the five most frequent accident scenarios separately for each low- and high-speed category. At signalized intersections, the proportions of cyclist fatalities involving vehicles traveling at low speeds were higher than those involving vehicles traveling at high speeds across all vehicle types. In contrast, on straight roads, the proportions at low speeds were lower than those at high speeds for all vehicle types. In the low-speed range, cyclist fatalities within the top five scenarios accounted for 65% of all fatalities, with the most frequent scenario occurring at signalized intersections during left-turn maneuvers, where heavy-duty trucks accounted for 86% of the fatalities. In the high-speed range, cyclist fatalities within the top five scenarios accounted for 71% of all fatalities. The most frequent high-speed scenario involved crossing collisions at unsignalized intersections when vehicles traveled straight, with light passenger cars and sedans accounting for 29% and 24% of the fatalities, respectively. These findings provide valuable insights for the development of targeted traffic safety regulations and vehicle technologies aimed at reducing vehicle–cyclist collisions across different speed ranges.
Matsui, Yasuhiro, Oikawa, Shoko
Building a trusted digital twin and decision-centric simulation ecosystem The automotive industry has been experiencing significant change and transformation. Electrification, software-defined vehicles, advanced driver assistance systems, and increasing electrical system integration are fundamentally reshaping how vehicles are designed and validated. As integration complexity continues to increase, the expectations for design cycle times are being compressed. Programs that once relied on extended validation timelines are now expected to deliver the same level of confidence in a fraction of the time. Traditional engineering workflows were built around sequential design phases, iterative simulations, and heavy reliance on physical validation. Design concepts were documented, prototypes were constructed, tests were performed, and results were compiled in reports and specifications that informed the next iteration. That approach worked well when systems were less complex and product life cycles were longer. In recent years, the volume of data, the speed of development, and the interconnected nature of modern vehicle architectures demand a different approach.
Patterson, Jeremy
This study presents the development and validation of a muddy water spray apparatus designed to simulate dust contamination on vehicle sensors for sensor cleaning system testing. It is important to have a constant and quantifiable test environment for the vehicle development process. For verifying the apparatus, muddy water, prepared by mixing standardized dust powder, salt, and water to maintain constant contamination test conditions, was sprayed onto glass specimens to evaluate equipment consistency. Deposited dust weight and thickness were measured across multiple spray cycles, with statistical analyses confirming consistent and reliable deposition. Paired t-tests indicated no significant difference between sample positions, demonstrating uniform spray distribution. The apparatus was further applied to individual infrared (IR) cameras to observe performance degradation under dry and wet contamination conditions showing statistically consistent increases in contamination levels. Application of the system in low-temperature performance testing of sensor cleaning systems on a development vehicle's rearview mirror yielded significant reductions in test time and variability compared to manual methods. These results affirm the apparatus as an effective, quantitative, and reproducible method for contamination simulation, contributing to streamlined and standardized sensor cleaning system development in the automotive industry.
Jinhyeok, Gong
Energy efficiency and range optimization remain critical challenges to the widespread adoption of battery electric vehicles (BEVs). As a result, there is a growing demand for intelligent driver assistance systems that can extend the operating range and reduce range anxiety. This paper presents an adaptive eco-feedback and driver rating system based on proximal policy optimization (PPO) reinforcement learning, designed to support drivers with the target to reduce energy consumption and maximize driving range. The system processes real-time driving data, such as velocity, acceleration and powertrain status. Map data of high quality is used to anticipate traffic events, including but not limited to speed limits, curves, gradients, preceding vehicles and traffic lights. This contextual awareness allows the system to continuously assess driving behavior and provide personalized, context-aware visual feedback alongside a dynamic driving behavior rating. A PPO agent learns optimal feedback strategies through continuous interaction and evaluates the impact of specific guidance actions, such as but not limited to “release accelerator pedal”, “brake” and “recuperate”, on immediate energy efficiency and long-term driver adaptation patterns. Feedback intensity and modality are dynamically tailored to individual driver profiles based on observed reaction patterns and feedback adherence. This approach encourages drivers to prioritize energy efficiency while aiming to minimize cognitive distraction and discomfort. The algorithm is implemented and validated within a driving simulation environment that replicates diverse and realistic conditions. Virtual driving tests conducted in various scenarios, such as congested urban areas, suburban routes, mountain roads and highways demonstrate that the proposed PPO-based eco-driving assistance system can reduce energy losses by about 28% compared to conventional driving behavior.
Stocker, Christoph, Hirz, Mario, Martin, Michael, Kreis, Alexander, Stadler, Severin
With the steady increase in autonomous driving (AD) and advanced driver-assistance systems (ADAS) aimed at improving road safety and navigation efficiency, simulation tools have become a critical part of the development process, allowing systems to be tested while mitigating the risk of physical injury or property damage upon failure. Physics-based simulators are central to virtual vehicle development, yet their control responses often differ from real vehicles, potentially limiting the transfer of controllers and algorithms developed in simulation. As these simulations play an important role in the vehicle design and validation process, a critical question is how well their predicted behavior translates to real-world physical systems. This paper presents a calibration framework for an autonomous vehicle platform that learns the motion characteristics of an experimental vehicle and uses that knowledge to correct the actuator response of a simulation model. The model is trained by collecting training data consisting of angular velocity data recorded during motion sequences from the wheel encoders mounted on the vehicle. After the data is post-processed, a long-short-term memory (LSTM) model is trained that predicts the angular velocity that the physical vehicle would achieve given a sequence of the past 30 command velocities.
Soloiu, Valentin, Sutton, Timothy, Mehrzed, Shaen, Lange, Robin, Zimmerman, Charles, Peralta Lopez, Guillermo
This study develops a personalized driver model for expressway merging, embedding individual driving characteristics into automated longitudinal and lateral control via Long Short-Term Memory (LSTM) networks. Uniform assistance (Advanced Driver Assist System, ADAS) can feel uncomfortable when it does not match a driver’s style; we therefore target the merge maneuver—a safety-critical task requiring anticipation and timing—and test whether merging-related context improves model fidelity. Driving data were collected in a high-fidelity motion-base simulator across two merging scenarios (13 licensed drivers in total). Inputs comprised ego speed, Headway distance and relative speed to the lead vehicle, and geometric context variables (distance to the end of the acceleration lane and to the hard/soft nose); outputs were longitudinal and, in the cross-scenario study, lateral accelerations. Models were trained per driver and evaluated by root mean square error (RMSE). Including merging context reduced longitudinal error in Experiment 1 (Gotemba IC) by about 30% on average relative to models without context, while errors remained below 0.5 m/s2. In Experiment 2 (Tokyo–Nagoya Expressway vs. Tokyo Metropolitan Expressway), longitudinal and lateral errors were low across both geometries; group-mean trends favored context but were non-significant, reflecting small sample size and inter-individual variability. Questionnaire-based evaluations in the simulator showed ratings close to real driving for discomfort, merge timing, and perceived safety; similarity and willingness to use were slightly higher in the urban expressway scenario, suggesting good user acceptance in constrained conditions. These findings indicate that incorporating merging context enables personalized control that better reflects individual driving behavior, while pointing to future work on generalization across geometries, speed ranges, and richer interaction semantics.
Shen, Shuncong, Hirose, Toshiya
Edge detection is fundamental for intelligent vehicle applications, directly supporting ADAS functions such as lane detection, obstacle recognition, and scene understanding. The conventional Canny edge detection method exhibits notable shortcomings, especially in color-image processing, adaptive threshold selection, and preserving edge integrity under noisy conditions. In this study, we present an enhanced Canny edge detection framework tailored for ADAS-oriented intelligent vehicle systems, incorporating a quaternion-based weighted averaging scheme for color preservation, adaptive thresholds derived from gradient-amplitude histograms, multiscale edge localization via scale multiplication, and a novel gravitational-field-intensity operator for improved gradient robustness. Moreover, we extend the method to vanishing-point estimation an essential ADAS capability by performing precise intersection calculations combined with clustering techniques such as DBSCAN and RANSAC. Experimental evaluations demonstrate that the proposed algorithm markedly outperforms traditional approaches in edge clarity, localization accuracy, and noise resilience, underscoring its promise for strengthening ADAS perception modules in intelligent vehicles.
Uppala, Rohit Raj, Kaye, Murali, Zadeh, Mehrdad, Tan, Teik-Khoon
Autonomous platforms such as self-driving vehicles, advanced driver-assistance systems (ADAS), and intelligent aerial drones demand real-time video perception systems capable of delivering actionable visual information at ultra-low latency. High-resolution vision pipelines are often hindered by delays introduced at multiple stages—sensor acquisition, video encoding, data transmission, decoding, and display—undermining the responsiveness required for safety-critical decision making. This study introduces a holistic system-level optimization framework that systematically reduces end-to-end video latency while maintaining image fidelity and perception accuracy. The proposed approach integrates hardware-accelerated encoding, zero-copy direct memory access (DMA), lightweight UDP-based RTP transport, and GPU-accelerated decoding into a unified pipeline. By minimizing redundant memory copies and software bottlenecks, the system achieves seamless data flow across hardware and software boundaries. Evaluations demonstrate a latency reduction from a baseline of 45.3 milliseconds to an optimized 23.5 milliseconds, representing a 48.1% improvement without sacrificing spatial resolution or detection robustness. Under optimized configurations, the framework sustains frame rates above 60 FPS at both Full HD and 4K resolutions, with frame drop rates held to approximately 3%. Perceptual evaluation further confirms that object detection accuracy consistently exceeds 91% within the <35 ms latency range, while collision-prediction delays are reduced to below 12.4 ms, ensuring timely responses in dynamic scenarios. These improvements collectively validate the critical importance of hardware-software co-design for embedded vision systems. The results highlight that ultra-low-latency perception is achievable on edge platforms when pipelines are designed with cross-layer optimization, bridging sensor interfaces, video codecs, network transport, and GPU computation. The proposed architecture provides a scalable foundation for future embedded vision deployments in autonomous driving, robotics, and unmanned aerial systems, where low latency is a non-negotiable requirement for safety, reliability, and operational efficiency.
Indrakanti, Rama Kiran Kumar
Recent years have seen a rapid rise in edge-oriented object detection models, including new YOLO variants and transformer-based RT-DETR. Choosing an appropriate model for vehicle detection, however, remains challenged because common metrics such as precision, recall, and mAP capture only part of the trade-off between accuracy and computational cost. To better support model selection, we introduce the Multi-dimensional Equilibrium Detection Assessment Score (MEDAS), which evaluates detectors across four practical dimensions: performance, balance, efficiency, and adaptability. The framework includes a normalization strategy and adjustable weighting so that evaluations can reflect specific deployment needs, especially in resource-limited settings. Experiments on the MS-COCO vehicle dataset show that while RT-DETR models offer competitive accuracy, they require substantially more computation. In contrast, lightweight YOLO variants provide a stronger balance between accuracy and efficiency. Among all evaluated models, YOLOv11s achieves the highest MEDAS score, suggesting it is well suited for applications such as ADAS and embedded autonomous systems. MEDAS offers a practical way to compare modern detectors and helps connect offline accuracy metrics with real deployment constraints in intelligent transportation systems.
Guo, Bin
Ensuring ISO 26262 functional safety in advanced driver assistance systems (ADAS) is increasingly complex as these platforms integrate artificial intelligence (AI) for perception, decision-making, and vehicle control. Traditional safety mechanisms are largely deterministic, but AI introduces non-determinism, creating challenges for verification, validation, and certification. Real-time vehicle telemetry, sensor outputs, and environmental inputs are processed through machine learning algorithms that forecast hardware and software faults before they escalate into hazardous conditions. These predictions are systematically integrated with ISO 26262 safety measures, enabling adaptive diagnostics, fault isolation, and rapid recovery strategies. The AI model introduces hazards such as data bias, model drift, opaque decision-making, and unsafe automation. A dedicated AI Hazard Analysis and Risk Assessment addresses data quality, validation, monitoring, explainability, and fail-safe mechanisms alongside system-level safety controls. The proposed approach demonstrates measurable improvements, including up to 25 % higher diagnostic coverage and fault-recovery times under 30 ms, while maintaining ASIL-D compliance and adhering to FTTI, SPFM, and DC requirements. Hardware-in-the-loop (HIL) simulations validate system performance and robustness under diverse operational scenarios. Future work focuses on uncertainty quantification and explainable AI integration, enhancing traceability and safety certification readiness for intelligent ADAS controllers. By demonstrating how AI can complement functional safety principles instead of conflicting with them, this study provides OEMs and Tier-1 suppliers with a roadmap for deploying certifiable, intelligent, and resilient ADAS platforms. This framework ensures safer, more reliable AI-enhanced vehicle systems while bridging the gap between emerging AI technologies and rigorous functional safety standards. This paper presents a predictive fault management framework that enhances functional safety in ADAS controllers by combining AI-driven predictive models with ISO 26262 safety mechanisms. This work uniquely bridges deterministic ISO 26262 workflows with predictive AI fault forecasting. In this framework, the AI model is used solely as a diagnostic enhancement and is not credited as an ISO 26262 safety mechanism; all safety decisions and fault reactions remain under deterministic safety-shell control.
Abdul Karim, Abdul Salam
Items per page:
1 – 50 of 2151