Browse Topic: Pedestrian safety

Items (315)
Find
Understanding Adversarial Transferability in Vision-Language Models for Autonomous Driving: A Cross-Architecture Analysis2026-01-0170To be published on 04/07/2026
Vision-language models (VLMs) offer a promising end-to-end approach for autonomous driving, but their robustness to physical adversarial attacks remains an unaddressed gap for safety-critical deployment. This paper introduces a systematic framework for evaluating these attacks using the Dolphins VLM and CARLA simulator. We employ Natural Evolution Strategies (NES), a black-box optimization method, to generate adversarial patches without internal model access. Our approach uses semantic similarity loss and Expectation over Transformation (EoT) to ensure physical realizability under varying viewing conditions. Patches are strategically placed on realistic advertising infrastructure (bus shelter panels and highway billboards), reflecting a plausible threat model. We establish two complementary scenarios: crosswalk pedestrian detection suppression and highway steering manipulation. Our evaluation reveals critical vulnerabilities. Adversarial patches achieved a 76.0% overall attack success
Fernandez, David, MohajerAnsari, Pedram, Salarpour, Amir, Pese, Mert D.
High Order Control Lyapunov Function - Control Barrier Function - Quadratic Programming Based Autonomous Driving Controller for Bicyclist Safety2026-01-0034To be published on 04/07/2026
Ensuring the safety of vulnerable road users is a critical challenge in the development of advanced autonomous driving systems. Among vulnerable road users, bicyclists present unique characteristics that make their safety both critical and manageable. Compared to pedestrians, vehicles often travel at significantly higher relative speeds when interacting with bicyclists, yet bicyclist motion is generally more predictable and governed by clear traffic rules, offering opportunities for model-based control strategies. To address bicyclist safety in complex traffic environments, this study proposes a High-Order Control Lyapunov Function–High-Order Control Barrier Function–Quadratic Programming (HOCLF-HOCBF-QP) control framework. By using this approach, CLFs enforce system stability, ensuring the vehicle follows a desired trajectory, while CBFs define safety boundaries, preventing collisions between the ego-vehicle and other road users. The optimal control input is then obtained by solving a
Chen, Haochong, Cao, Xincheng, Guvenc, Levent, Aksun Guvenc, Bilin
Optimization of Active–Passive Integrated Evaluation Weighting for Pedestrian Protection2026-01-0577To be published on 04/07/2026
Pedestrians, as the most vulnerable road users, largely determine the severity of traffic accidents through the extent of their injuries. Traditional vehicle safety evaluations have primarily emphasized passive safety. However, with the widespread implementation of active safety technologies such as Automatic Emergency Braking (AEB), passive-only assessments no longer adequately reflect a vehicle’s true pedestrian protection performance.This study employed finite element models of a sedan and an SUV to analyze changes in pedestrian head and lower limb injury metrics before and after AEB intervention, thereby quantifying the associated injury-mitigation benefits. The results show that AEB reduced the maximum head injury value (HIC15) by about 50%, lowering the proportion of severe head injuries from 0.217 to 0.118. Conversely, braking-induced pitch effects increased the proportions of severe femur and tibia bending moment injuries to 0.235 and 0.294, respectively, making them higher
shi, Xinxin, YE, BIN, Liu, Yu, Zhan, Zhenfei, Sun, Bowen, Zhao, yuanyi, zhu, lei
Development of Automotive Hood Using Multi-Material Double Injection Molding2026-01-0476To be published on 04/07/2026
Introduction: The automotive hood is a critical closure component that must meet structural, safety, and styling requirements. Traditional metal hoods are increasingly being replaced or supplemented by polymer-based designs due to advancements in material technology and manufacturing methods. Among these, multi-material double injection molding presents a promising alternative to reduce production time and cost while achieving performance compliance. Aim: This study aims to develop an automotive hood using a hybrid plastic combination through a double-shot injection molding process. The focus is on evaluating the structural feasibility of such designs under regulatory and OEM-defined stiffness and crashworthiness performance targets. Purpose: The objective is to investigate the compatibility of different thermoplastic materials for outer and inner skin layers in achieving structural rigidity, impact resistance, and manufacturing efficiency. The approach targets the consolidation of
GANESAN, KARTHIKEYAN, Seok, Sang Ho, Jo, Hyoung Han
The Balance of Illumination and Glare Prevention of Upward Directed Lighting2026-01-0516To be published on 04/07/2026
This study investigates the ongoing challenge of balancing sufficient headlight illumination with the need to prevent glare for other drivers. It focuses on the upper portion of a headlight's beam pattern, which is particularly relevant for lighting overhead signs and the upper portions of vulnerable road users. This study investigates the influence of LED headlamp technology on upward directed lighting and compares illumination of systems with varying mounting heights. This is especially important when it comes to the performance of camera-based pedestrian detection and Automatic Emergency Braking (AEB) systems. Data was collected by testing multiple vehicles over time with pedestrians positioned at two distinct locations relative to the vehicle as well as some discrete points relative to the headlamp and independent of mounting height. The resulting analysis reveals trends, providing valuable insights for predicting optimal lighting strategies in future systems. These strategies may
Allen, Jodi Mary Jean
Safety-Centered Scenario Generation for Autonomous Vehicles2026-01-0529To be published on 04/07/2026
This paper focuses on a scenario generation framework that creates diverse, parametrized, and safety-critical driving situations to validate the safety features of autonomous vehicles in simulation. By modeling factors such as road geometry, traffic participants, environmental conditions, and perception uncertainties, the framework enables repeatable and scalable testing of safety mechanisms, including emergency braking, evasive maneuvers, and vulnerable road user protection. The framework supports both regulatory and edge-case scenarios, mapped to hazards and safety goals derived from Hazard Analysis and Risk Assessment (HARA), ensuring traceability to ISO 26262 functional safety requirements and performance limitations. The output from these simulations provide quantitative safety metrics such as time-to-collision, minimum distance, braking and steering performance, and residual collision severity. These metrics enable the systematic evaluation of evasive maneuvering as a safety
Chandra Shekar, Kiruthiga, Arab, Aliasghar
Analysis of the biofidelity of aPLI under low-speed collision conditions2026-01-0551To be published on 04/07/2026
Abstract: With the increasing popularity of automotive active safety systems, the probability of collisions between vehicles and pedestrians has gradually decreased. Among them, the AEB system, as an important part of active safety systems, can actively intervene to avoid collisions in advance. However, in actual road traffic conditions, there are still situations where the AEB system cannot completely avoid collision accidents, and the impact speed between pedestrians and vehicles may drop to below 40 kph. However, the aPLI legform impactor, which is widely used in pedestrian protection evaluations in various regions, has a standard impact speed of 40 kph in the test procedure. The response of the aPLI to low-speed collisions and the resulting pedestrian leg injuries is still unclear. Based on finite element simulation, this study compared the kinematic responses and injury responses of the aPLI impactor with human body models (THUMS and GHBMC) under 5 different speeds (20kph, 25kph
Sun, Bowen, YE, BIN, LONG, YONGCHENG, Zhan, Zhenfei, shi, Xinxin, jun, yin
Human-Like Automatic Braking Algorithm Based on Kinematic Cue: Yield Behavior Analysis and Fuzzy Controller Design10-10-03-00192/25/2026
Pedestrians are among the most vulnerable participants in traffic, particularly when crossing the road. Extensive research has been conducted globally on the yielding behavior analysis of vehicle–pedestrian interaction and the design of automatic vehicle braking systems to mitigate pedestrian casualties. However, few studies have comprehensively addressed lateral risks using implicit kinematic cues in pedestrian–vehicle interactions. Moreover, the design of collision avoidance systems has rarely taken into account driving behavior, along with the pedestrian’s kinematics and crossing behavior. This article presents a human-like automatic braking fuzzy control strategy for pedestrian–vehicle collision avoidance, combining the advantages of professional driver emergency braking behavior and kinematic interaction cues. First, a high-fidelity driving simulator is used to investigate the yielding behavior of pedestrian–vehicle interaction when pedestrians cross the road. Second, the
Zhang, Wenyan, Huang, Xiaorong, Sun, Shulei, Fu, Kairong, Xiong, Qing, Huang, Haibo
Accidental Dooring Warning and Assist System2026-28-00532/12/2026
Dooring accidents occur when a vehicle door is opened into the path of an approaching cyclist, motorcyclist, or other road user, often causing serious collisions and injuries. These incidents are a major road safety concern, particularly in densely populated urban areas where heavy traffic, narrow roads, and inattentive behavior increase the likelihood of such events. To address this challenge, this project presents an intelligent computer vision based warning system designed to detect approaching vehicles and alert occupants before they open a door. The system can operate using either the existing rear parking camera in a vehicle or a USB webcam in vehicles without such a feature. The captured live video stream is processed by a Raspberry Pi 4 microprocessor, chosen for its compact size, low power consumption, and ability to support machine learning frameworks. The video feed is analyzed in real time using MobileNetSSD, a lightweight deep learning object detection model optimized
C, Jegadheesan, T, Karthi, Gurusamy, Varun Sankar, Balraj, Tharun, Murugaiya, Tamilselvan
Pre-Crash Characteristics of Motorized Two-Wheeler Crashes on Indian Roads2026-26-00341/16/2026
India has emerged as the world’s largest market for motorized two-wheelers (M2Ws) in 2024, reflecting their deep integration into the country’s transportation fabric. However, M2Ws are also a highly vulnerable road user category as according to the Ministry of Road Transport and Highways (MoRTH), the fatality share of M2W riders rose alarmingly from 27% in 2011 to 44% in 2022, underlining the urgency of understanding the circumstances that lead to such crashes. This study aims to investigate the pre-crash behavior and crash-phase characteristics of M2Ws using data from the Road Accident Sampling System – India (RASSI), the country’s only in-depth crash investigation database. The analysis covers 3,632 M2Ws involved in 3,307 crash samples from 2011 to 2022, representing approximately 5 million M2Ws nationally. Key variables examined include crash configuration, collision partner, road type, pre-event movement, travel speed, and human contributing factors. The study finds that straight
Govardhan, Rohan, Padmanaban, Jeya, Jethwa, Vaishnav
Jerk Evaluation Criteria for Pedestrian Head Impact on Windshield and Technological Requirement to Meet the Criteria2026-26-00231/16/2026
The safety of vulnerable road users, particularly pedestrians, cyclists, and motorcyclists, is a paramount concern in automotive design and regulation. In India, the situation is particularly alarming, with pedestrians being the second highest victims of road accidents, as evidenced by over 32,825 reported pedestrian accidents and 4,836 cyclist fatalities in 2022, excluding two-wheeler motorcyclists. On a global scale, the prevalence of such incidents has prompted European countries to introduce new regulatory requirements, such as ECE R127.03. This regulation encompasses the evaluation of pedestrian head form impacts on windshields, assessing the typical behavior of glass through jerk criteria following initial contact, in conjunction with the existing Head Injury Criterion (HIC) evaluation for pedestrian head forms. These criteria’s are meticulously designed to ensure that both acceleration and jerk remain within safe limits to reduce the severe risk of severe injury to head of
Kumar, Ritik, A, Rajesh
Analysis of Pedestrian Accidents in India2026-26-06931/16/2026
Pedestrian safety is a critical concern in India, where rapid urbanization, increased vehicular traffic, and inadequate infrastructure pose significant risks to pedestrians. This study aims to analyze pedestrian accidents across various regions in India, drawing insights from comprehensive accident data. By examining accident patterns, risk factors, and contributing variables, we seek to inform policy recommendations and enhance pedestrian safety measures.
Howlader, Ashim, Mehta, Pooja
Enhancing Pedestrian Safety: LIDAR-Based Deployment of Front LID/Bonnet and Airbag Systems in Heavy Commercial Vehicles During Low-Speed Collisions2026-26-00061/16/2026
As urban population continues to grow, the safety of Vulnerable Road Users (VRUs) particularly in the presence of Heavy Good Vehicles (HGVs) has emerged as a critical concern. Research indicates that VRUs are at a 50% higher risk of fatal injury in collisions involving HGVs compared to passenger cars. To address this issue, this study proposes a novel pedestrian protection system that integrates LiDAR (Light Detection and Ranging) technology with a reusable airbag system to mitigate the severity of collisions. The proposed solution adopts a twofold approach for enhancing VRU protection in scenarios involving HGVs. In both approaches, LiDAR sensors are used to generate a real-time 3D model of the vehicle’s surroundings, enabling accurate VRU detection and predictive collision analysis. Scenario 1: When vehicle speed exceeds the first threshold and a collision is unavoidable, the onboard ECU activates front lid actuators, extending the vehicle's front lid which can be retracted back to
Patil, Uday, Sriharsha, Viswanath, Pillai, Rajiv
Leveraging Road Accident Database to Enhance ADAS Features and Testing Protocols in Context of Indian Driving Conditions2026-26-00141/16/2026
ADAS i.e. Advanced Driver Assistance Systems are pivotal towards amplifying road safety by reducing human error and assisting drivers in critical situations. Most major ADAS technologies are developed and validated using data and test scenarios that are predominantly based on the driving conditions and road environments of developed countries. However, in a country like India, where driving behavior, traffic dynamics, road infrastructure, and accident characteristics differ significantly, the ADAS technologies and test scenarios validated by different forums create a critical gap in deploying such systems on vehicles to work on Indian roads. The major aim of this study was to determine and generate India-specific ADAS test scenarios from the Road Accident Sampling System India (RASSI) database, available MoRTH reports, and data from previously executed ADAS test cases. Through this research, we propose a methodology to identify, extract, and analyze accident scenarios pertaining to the
Adhikari, Mayur, Bhagat, Ajinkya, Verma, Harshal, Kale, Jyoti Ganesh, Karle, Ujjwala, Sharma, Chinmaya
Intelligent Child-Safety Inhibition Framework for Preventing Accidental Vehicle Activation2026-26-00131/16/2026
Modern vehicle technologies such as keyless entry, push-button start, digital switches have made it easier and more convenient to operate cars. However, this ease of operation has also introduced new safety concerns, particularly the increased risk of accidental operations by children. This can lead to unintentional vehicle movement, injuries, and even fatalities. Existing safety features (e.g., unattended child presence alarms) mitigate entrapment risks but do not prevent children from unintentionally starting or shifting while inside. This paper proposes implementation of a solution for child-safety system which inhibits certain functionalities to prevent accidental operations by underage occupants. The proposed system combines multiple existing technologies like weight sensors, seat position detection, facial recognition, in vehicle camera tracking to determine the child presence. With this, certain operations can be temporarily inhibited, or the vehicle can ask for secondary
Mote, Vaishal, Garg, Mudit, Pasupuleti, Raju
Determining Absence of Unreasonable Risk: Proposed Criteria for the Evaluation of an Automated Driving System Deployment12-09-04-00261/12/2026
This article provides an overview of how the determination of absence of unreasonable risk can be operationalized. It complements previous theoretical work published by existing developers of automated driving systems (ADS) on the overall engineering practices and methodologies for readiness determination. Readiness determination is, at its core, a risk assessment process. It is aimed at evaluating the residual risk associated with a new ADS deployment. The article proposes methodological criteria to ground the readiness review process for an ADS release. Specifically, it lists 12 readiness criteria connected with system safety, cybersecurity, verification and validation, collision avoidance testing, predicted collision risks, impeded progress, rules of the road compliance, vulnerable road users interactions, high-severity assessment, conservative estimate of severity, risk management, and field safety. The criteria presented are agnostic of any specific ADS technological solution and
Favaro, Francesca Margherita, Schnelle, Scott, Fraade-Blanar, Laura, Victor, Trent, Peña, Mauricio, Webb, Nick, Broce, Holland, Paterson, Craig, Smith, Daniel
Arbe chipset improves automated driving decisions25AUTP12_0312/1/2025
Perception radar company Arbe was at IAA Mobility in Munich this year to press the case that customers can and should trust automated vehicles. One reason is the global trend of stricter regulations from the NHTSA, Euro NCAP, and in China, which now require automated vehicles to safely meet demanding use cases that are not covered by current sensors, according to Arbe co-founder and CTO Noam Arkind. Arkind told SAE Media that one such category is detecting vulnerable road users (VRU) in poor weather and lighting conditions. “We know from recent tests that a lot of Chinese cars, for example, failed VRU detections in the dark,” he said. “Camera alone doesn't really have reliable pedestrian detection in a dark situation. Radar is a great sensor. It's very sensitive. It's not dependent on weather conditions or lighting conditions, but it's noisy, it's low resolution, and it's hard to use.”
Blanco, Sebastian
Pedestrian Injury Case Reconstruction through Data Fusion and Machine Learning2025-22-000711/10/2025
The proportion of pedestrian injuries in motor-vehicle-crash-induced injuries in the U.S. has been increasing in recent years. Although extensive police-reported data on pedestrian injuries is available, the incomplete nature of the crash and injury information in these datasets presents a significant challenge for statistical injury analysis and pedestrian protection research. This study aims to address this issue by combining simulation data and field data to impute critical missing crash information in pedestrian crash cases through machine learning techniques. A total of 9,000 MADYMO simulations were generated using maximal projection design, incorporating variables such as pedestrian demographics, crash conditions, and vehicle impact parameters. Gaussian process (GP) surrogate models were trained to predict injury risks with simulation parameters calibrated using the complete crash information in the Pedestrian Crash Data Study (PCDS) dataset. Maximum likelihood estimations were
Song, Xiaoyang, Sun, Wenbo, Hu, Jingwen, Flannagan, Carol, Karlow, Jared, Bowman, Patrick, Farooq, Iskander, Kalra, Anil
Pedestrian Accident ReconstructionR-59010/30/2025
As technology advances, so too must the methods we use to investigate and understand pedestrian collisions. Pedestrian Accident Reconstruction provides a much-needed update to the field—one that reflects the dramatic rise in digital evidence and the growing role of simulation in modern reconstructions. While earlier texts laid the foundation for understanding pedestrian impacts, they were written before the widespread use of video footage, onboard vehicle sensors, and powerful simulation software. This book addresses that shift. It introduces updated methods that incorporate event data recorders, surveillance video, dash cams, and advanced simulation tools like the PC-Crash multibody pedestrian model. These technologies allow for more precise, repeatable, and illustrative reconstructions than ever before. The book highlights when and how simulation can enhance an investigation—especially in complex scenarios such as roof vaults, sideswipes, or collisions that defy conventional
Rose, Nathan, Carter, Neal
Customized Signalized Intersection Control for Pedestrian Safety Enhancement through Computer Vision Technologies09-13-02-00086/26/2025
The escalating complexity at intersections challenges the safety of the interaction between vehicles and pedestrians, especially for those with mobility impairments. Traditional traffic control systems detect pedestrians through costly technologies such as LiDAR and radar, limiting their adoption due to high costs and static programming. Therefore, the article proposes a customized signalized intersection control (CSIC) algorithm for pedestrian safety enhancement. This algorithm integrates advanced computer vision (CV) algorithms to detect, track, and predict pedestrian movements in real time, enhancing safety at a signalized intersection while remaining economically viable and easily integrated into existing infrastructure. Implemented at a key intersection in Bellevue, the CSIC system achieves a 100% pedestrian passing rate while simultaneously minimizing the average remaining walk time after crossings. The algorithm used in this study demonstrates the potential of combining CV with
Xia, Rongjing, Fang, Hongchao, Zhang, Chenyang
V2P-Based Speed Guidance Method for Avoiding Vehicle–Pedestrian Collisions at Intersections12-09-01-00065/14/2025
Conflicts between vehicles and pedestrians at unsignalized intersections occur frequently and often result in serious consequences. In order to alleviate traffic flow congestion at unsignalized intersections caused by accidents, reduce vehicle congestion time and waiting time, and improve intersection safety as well as intersection access efficiency, a speed guidance algorithm based on pedestrian-to-vehicle (P2V) and vehicle-to-pedestrian (V2P) communication technologies is proposed. The method considers the heading angle (direction of motion) of vehicles and pedestrians and combines the post encroachment time (PET) and time to collision (TTC) to determine whether there is a risk of collision, so as to guide the speed of vehicles. Network simulator NS3 and traffic flow simulation software SUMO are used to verify the effectiveness of the speed guidance strategy proposed in this article. The experimental findings demonstrate that the speed guidance strategy introduced in this article
Sun, Yuanyuan, Wang, Kan, Liu, Weizhen, Li, Wenli
Global Vehicle Vibration Enhancement Using Circular Force Technology2025-01-00155/5/2025
In addition to providing safety advantages, sound and vibration are being utilized to enhance the driver experience in Battery Electric Vehicles (BEVs). There's growing interest and investment in using both interior and exterior sounds for pedestrian safety, driver awareness, and unique brand recognition. Several automakers are also using audio to simulate virtual gear shifting of automatic and manual transmissions in BEVs. According to several automotive industry articles and market research, the audio enhancements alone, without the vibration that drivers are accustomed to when operating combustion engine vehicles, are not sufficient to meet the engagement, excitement, and emotion that driving enthusiasts expect. In this paper, we introduce the use of new automotive, high-force, compact, light-weight circular force generators for providing the vibration element that is lacking in BEVs. The technology was developed originally for vibration reduction/control in aerospace applications
Norris, Mark A., Orzechowski, Jeffrey, Sanderson, Brad, Swanson, Douglas, Vantimmeren, Andrew
Compensation Algorithm Development in Platform for Pedestrian ADAS Testing2025-01-80664/1/2025
Test procedures such as EuroNCAP, NHTSA’s FMVSS 127, and UNECE 152 all require specific pedestrian to vehicle overlaps. These overlap variations allow the vehicle differing amounts of time to respond to the pedestrian’s presence. In this work, a compensation algorithm was developed to be used with the STRIDE robot for Pedestrian Automatic Emergency Braking tests. The compensation algorithm uses information about the robot and vehicle speeds and positions determine whether the robot needs to move faster or slower in order to properly overlap the vehicle. In addition to presenting the algorithm, tests were performed which demonstrate the function of the compensation algorithm. These tests include repeatability, overlap testing, vehicle speed variation, and abort logic tests. For these tests of the robot involving vehicle data, a method of replaying vehicle data via UDP was used to provide the same vehicle stimulus to the robot during every trial without a robotic driver in the vehicle.
Bartholomew, Meredith, Nguyen, An, Helber, Nicholas, Heydinger, Gary
Study on the Improvement of Pedestrian and Vehicle Visibility by Geometric Patterns Projection Lighting2025-01-86634/1/2025
The proportion of pedestrian fatalities due to traffic accidents is higher at night than during the day. Drivers can more easily recognize pedestrians by setting their headlights to high beam, but use of high beam poses the issue of increasing glare for pedestrians. This study proposes a lighting technology that increases the noticeability of pedestrians for drivers and the noticeability of approaching vehicles for pedestrians while at the same time helping to reduce glare for pedestrians. The newly designed lighting enables geometric patterns projection lighting that makes use of projection technology. This geometric pattern projection lighting was compared with conventional low beam and high beam headlights to verify the effectiveness. Tests were conducted on a closed course with the participation of 20 drivers to evaluate the functionality of each headlight type. In these tests, subjects performed specific tasks such as evaluation of pedestrian visibility from the driver’s point of
Kawamura, Kazuyuki, Oshida, Kei
Empirical Analysis on Machine Vision Recognition of Green Bike Lanes for Vulnerable Road Users Safety2025-01-80174/1/2025
Deliberate modifications to infrastructure can significantly enhance machine vision recognition of road sections designed for Vulnerable Road Users, such as green bike lanes. This study evaluates how green bike lanes, compared to unpainted lanes, enhance machine vision recognition and vulnerable road users safety by keeping vehicles at a safe distance and preventing encroachment into designated bike lanes. Conducted at the American Center for Mobility, this study utilizes a vehicle equipped with a front-facing camera to assess green bike lane recognition capabilities across various environmental conditions including dry daytime, dry nighttime, rain, fog, and snow. Data collection involved gathering a comprehensive dataset under diverse conditions and generating masks for lane markings to perform comparative analysis for training Advanced Driver Assistance Systems. Quality measurement and statistical analysis are used to evaluate the effectiveness of machine vision recognition using
Ponnuru, Venkata Naga Rithika, Das, Sushanta, Grant, Joseph, Naber, Jeffrey, Bahramgiri, Mojtaba
Efficient Sidewalk Route Planning on Aerial Images with Cost-Based A* and Mini-Max Objective Function2025-01-80324/1/2025
With the growing diversification of modern urban transportation options, such as delivery robots, patrol robots, service robots, E-bikes, and E-scooters, sidewalks have gained newfound importance as critical features of High-Definition (HD) Maps. Since these emerging modes of transportation are designed to operate on sidewalks to ensure public safety, there is an urgent need for efficient and optimal sidewalk routing plans for autonomous driving systems. This paper proposed a sidewalk route planning method using a cost-based A* algorithm and a mini-max-based objective function for optimal routes. The proposed cost-based A* route planning algorithm can generate different routes based on the costs of different terrains (sidewalks and crosswalks), and the objective function can produce an efficient route for different routing scenarios or preferences while considering both travelling distance and safety levels. This paper’s work is meant to fill the gap in efficient route planning for
Bao, Zhibin, Lang, Haoxiang, Lin, Xianke
Developing a Vehicle-in-Virtual-Environment (VVE) Based Autonomous Driving Function Development and Evaluation Pipeline for Vulnerable Road User Safety2025-01-80614/1/2025
Traditional methods for developing and evaluating autonomous driving functions, such as model-in-the-loop (MIL) and hardware-in-the-loop (HIL) simulations, heavily depend on the accuracy of simulated vehicle models and human factors, especially for vulnerable road user safety systems. Continuation of development during public road deployment forces other road users including vulnerable ones to involuntarily participate in the development process, leading to safety risks, inefficiencies, and a decline in public trust. To address these deficiencies, the Vehicle-in-Virtual-Environment (VVE) method was proposed as a safer, more efficient, and cost-effective solution for developing and testing connected and autonomous driving technologies by operating the real vehicle and multiple other actors like vulnerable road users in different test areas while being immersed within the same highly realistic virtual environment. This VVE approach synchronizes real-world vehicle and vulnerable road user
Chen, Haochong, Cao, Xincheng, Guvenc, Levent, Aksun Guvenc, Bilin
Research on the Boundary of Pedestrian Leg Impactor Test in Low-Speed Passive and Active Conditions2025-01-87354/1/2025
With the widespread application of the Automatic Emergency Braking System (AEB) in vehicles, its impact on pedestrian safety has received increasing attention. However, after the intervention of AEB, the kinematic characteristics of pedestrian leg collisions and their corresponding biological injury responses also change. At the same time, in order to accurately evaluate the pedestrian protection performance of vehicles, the current assessment regulations generally use advanced pedestrian protection leg impactors (aPLI) and rigid leg impactors (TRL) to simulate the movement and injury conditions of pedestrian legs. Based on this, in order to explore the collision boundary conditions and changes in injury between vehicles and APLI and TRL leg impactors under the action of AEB, this paper first analyzes the current passive and active assessment conditions. Secondly, the simulation software LS-DYNA is used to build a finite element model of APLI and TRL impactor-vehicle collisions to
Ye, Bin, Hong, Cheng, Wan, Xinming, Liu, Yu, Cheng, James, Long, Yongchen, Hao, Haizhou
Lattice Based Localized Energy Absorber for Improved Vulnerable Road User Performance for a Vehicle2025-01-87234/1/2025
A passenger vehicle hood is designed to meet Vulnerable Road User (VRU) regulatory requirements and consumer metric targets. Generally, hood inner design and its reinforcements, along with deformable space available under the hood are the main enablers to meet the Head Impact performance targets. However, cross functional balancing requirements, such as hood stiffness and packaging space constraints, can lead to higher Head Injury Criteria (HIC15) scores, particularly when secondary impacts are present. In such cases, a localized energy absorber is utilized to absorb the impact energy to reduce HIC within the target value. The current localized energy absorber solutions include the usage of flexible metal brackets, plastic absorbers etc. which have limited energy absorbing capacity and tuning capability. This paper focuses on usage of a novel 3D printed energy absorbers, based on various kinds of lattice structures. These absorbers are either sandwiched between the inner and the outer
Kinila, Vivekananda, Agarwal, Varun, V S, Rajamanickam, Tripathy, Biswajit, Gupta, Vishal
Study on the Impact of Vehicle Pitch During Braking on Pedestrian Leg Injuries2025-01-87414/1/2025
With the increasing prevalence of Automatic Emergency Braking Systems (AEB) in vehicles, their performance in actual collision accidents has garnered increasing attention. In the context of AEB systems, the pitch angle of a vehicle can significantly alter the nature of collisions with pedestrians. Typically, during such collisions, the pedestrian's legs are the first to come into contact with the vehicle's front structure, leading to a noticeable change in the point of impact. Thus, to investigate the differences in leg injuries to pedestrians under various pitch angles of vehicles when AEB is activated, this study employs the Total Human Model for Safety (THUMS) pedestrian finite element model, sensors were established at the leg location based on the Advanced Pedestrian Legform Impactor (APLI), and a corresponding vehicle finite element model was used for simulation, analyzing the dynamic responses of the pedestrian finite element model at different pitch angles for sedan and Sport
Hong, Cheng, Ye, Bin, Zhan, Zhenfei, Liu, Yu, Wan, Xinming, Hao, Haizhou
Biofidelity Evaluation of AC-HUMs Pedestrian Model Based on Generic Sedan Buck Model2025-01-87434/1/2025
Objective: This study aims to evaluate the biofidelity of the Advanced Chinese Human Body Model (AC-HUMs) by utilizing a generic sedan buck model and post-mortem human surrogates (PMHS) test data. Methods: The boundary conditions of the simulation were derived from the PMHS test with the buck vehicle. The methodology involved the pose adjustment of the upper and lower extremities of AC-HUMs, executed through a pre-simulation approach. Subsequently, a 200 milliseconds whole body pedestrian crash simulation was conducted using the buck vehicle and the AC-HUMs pedestrian model. The trajectories of AC-HUMs during the period from initial position to head impact were recorded, including the Head CG, T1, T8 and pelvis. Based on the knee joint, the corridors of trajectories from the PMHS test were scaled to match the Chinese 50th percentile male to evaluate the biofidelity of AC-HUMs's kinematic response. Furthermore, the biomechanical responses were compared with the PMHS tests, including
Qian, Jiaqi, Wang, Qiang, Liu, Yu, Wu, Xiaofan, Huida, Zhang, Bai, Zhonghao
Analysis of OEM Collision Avoidance Data Outputs during VRU Testing2025-01-80534/1/2025
Using OEM tools to analyze data available from on-vehicle collision avoidance systems can shed light on the data scope that is available to analyze failures in these systems. In this work, an Advanced Driver Assistance System (ADAS)-equipped vehicle was tested to determine the performance in several collision imminent scenarios. Vehicle Event Data Recorder (EDR) data was pulled and compared to data collected from independent instrumentation to determine the vehicle system accuracy in detecting targets, investigate timings, and understand the scope of data available to an agency investigating a failure. Images and data files are presented as an example of scope of output. Tests included several variable overlap tests, along with several tests specifically chosen due to compare performance across the operating design domain.
Bartholomew, Meredith, Heydinger, Gary
Dynamic Driving Task Assessment Scores for Scenarios Navigated by an OEM ADS-Equipped Vehicle2025-01-86724/1/2025
One of the major issues facing the automated driving system (ADS)-equipped vehicle (AV) industry is how to evaluate the performance of an AV as it navigates a given scenario. The development and validation of a sound, consistent, and transparent dynamic driving task (DDT) assessment (DA) methodology is a key component of the safety case framework (SCF) of the Automated Vehicle – Test and Evaluation Process (AV-TEP) Mission, a collaboration between Science Foundation Arizona and Arizona State University. The DA methodology was presented in earlier work and includes the DA metrics from the recently published SAE J3237 Recommended Practice. This work extends and implements the methodology with an AV developed by OEM May Mobility in four diverse, real-world scenarios: (1) an oncoming vehicle entering the AV’s lane, (2) vulnerable road user (VRU) crossing in front of the AV’s path, (3) a vehicle executing a three-point turn encroaches into the AV’s path, and (4) the AV exhibiting aggressive
Wishart, Jeffrey, Rahimi, Shujauddin, Swaminathan, Sunder, Zhao, Junfeng, Frantz, Matt, Singh, Satvir, Como, Steven Gerard
Deriving Architectural Requirements for SAE J3016 TM Level 3 System from Functional Safety Perspective2025-01-80094/1/2025
Vehicles with SAE J3016TM Level 3 systems are exposed to road infrastructure, Vulnerable Road Users (VRUs), traffic and other actors on roadways. Hence safe deployment of Level 3 systems is of paramount importance. One aspect of safe deployment of SAE Level 3 systems is the application of functional safety (ISO 26262) to their design, development, integration, and testing. This ensures freedom from unreasonable risk, in the event of a system failure and sufficient provisions to maintain Dynamic Driving Task (DDT) and to initiate Minimum Risk Maneuver (MRM), in the presence of random hardware and systematic failures. This paper explores leveraging ISO 26262 standard to develop architectural requirements for enabling SAE Level 3 systems to maintain DDT and MRM during fault conditions and outlines the importance of fail-operability for Level 3 systems, from a functional safety perspective. At a high-level, UN Regulation No. 157 – Automated Lane Keeping Systems (ALKS) is used as a baseline
Mudunuri, Venkateswara Raju, Jayakumar, Namitha
Validation of Pedestrian Collision Reconstruction Using the PC-Crash Multibody Pedestrian Model2025-01-86814/1/2025
This study validates the use of the pedestrian multibody model in the simulation software PC-Crash. If reasonable inputs are used, the pedestrian model will yield accurate simulations of pedestrian collisions, particularly in terms of accurately simulating the contact points between the pedestrian and the vehicle and in predicting the throw distance of the pedestrian. This study extends prior studies of the PC-Crash pedestrian multibody model by simulating additional staged collisions, by comparing the results of the model to widely utilized throw distance equations, by providing guidance on inputs for the pedestrian multibody, and by providing documentation of the characteristics of the multibody pedestrian. In addition, two new staged pedestrian collisions are discussed and simulated. This study demonstrates the following: (1) The center of gravity height of the PC-Crash pedestrian model is comparable to the center of gravity height reported for pedestrians in anthropometric data. (2
Rose, Nathan, Smith, Connor, Carter, Neal, Metanias, Andrew
Longitudinal Analysis of Forward Blind Zone Changes in Popular Vehicle Models (1997–2023)09-13-01-00053/26/2025
Background. In 2022, vulnerable road user (VRU) deaths in the United States increased to their highest level in more than 40 years. At the same time, increasing vehicle size and taller front ends may contribute to larger forward blind zones, but little is known about the role that visual occlusion may play in this trend. Goal. Researchers measured the blind zones of six top-selling light-duty vehicle models (one pickup truck, three SUVs, and two passenger cars) across multiple redesign cycles (1997–2023) to determine whether the blind zones were getting larger. Method. To quantify the blind zones, the markerless method developed by the Insurance Institute for Highway Safety was used to calculate the occluded and visible areas at ground level in the forward 180° arc around the driver at ranges of 10 m and 20 m. Results. In the 10-m forward radius nearest the vehicle, outward visibility declined in all six vehicle models measured across time. The SUV models showed up to a 58% reduction
Epstein, Alexander K., Brodeur, Alyssa, Drake, Juwon, Englin, Eric, Fisher, Donald L., Zoepf, Stephen, Mueller, Becky C., Bragg, Haden
Research on Automatic Emergency Braking Pedestrian System Considering Road Adhesion Coefficient10-09-03-00223/8/2025
To further optimize the automatic emergency braking for pedestrian (AEB-P) control algorithm, this study proposes an AEB-P hierarchical control strategy considering road adhesion coefficient. First, the extended Kalman filter is used to estimate the road adhesion coefficient, and the recursive least square method is used to predict the pedestrian trajectory. Then, a safety distance model considering the influence factor of road adhesion coefficient is proposed to adapt to different road conditions. Finally, the desired deceleration is converted into the desired pressure and desired current to the requirements of the electric power-assisted braking system. The strategy is verified through the hardware-in-the-loop (HIL) platform; the simulation results show that the control algorithm proposed in this article can effectively avoid collision in typical scenarios, the safe distance of parking is between 0.61 m and 2.34 m, and the stop speed is in the range of 1.85 km/h–27.64 km/h.
Wang, Zijun, Wang, Liang, Ma, Liang, Sun, Yong, Li, Chenghao, Yang, Xinglong
Tunnel Traffic Anomaly Detection via Multi-Modal LLMs2025-01-71292/21/2025
Tunnels play a crucial role in urban transportation, yet they frequently encounter various incidents during operation. Manual video inspections and sensor-based systems are inefficient and limited in accurately detecting and addressing these issues. The emergence of artificial intelligence has led to the development of object detection models such as YOLO, which have shown promise in real-time anomaly detection. However, these single-modality models achieve suboptimal results when dealing with complex events. Multi-modal large language models (LLMs) offer a potential solution, with their ability to process and understand information from different modalities. This paper develops a novel tunnel traffic anomaly detection method that combines single-modal models and multi-modal LLMs. The proposed system first employs YOLO for an initial detection round and then utilizes a specially designed LLM with an effective prompt and a data filtering strategy tailored for traffic tunnel scenarios
Liu, Hongyu, Zhou, Ruohan, Bai, Jiayang, Li, Yuanqi
Verification of Vulnerable Road User Pre-Crash Scenarios in Vision-Based Safety Applications12-08-01-00041/10/2025
Verifying training datasets in vision-based vehicle safety applications is crucial to understanding the potential limitations of detection capabilities that may result in a higher safety risk. Vision-based pedestrian safety applications with crash avoidance technologies rely on prompt detection to avoid a crash. This research aims to develop a verification process for vulnerable road user safety applications with vision-based detection functionalities. It consists of reviewing the application’s safety requirements, identifying the target objects of detection in the operational design domain and pre-crash scenarios, and evaluating the safety risks qualitatively by examining the training dataset based on the results of pre-crash scenarios classification. As a demonstration, the process is implemented using open-source pedestrian tracking software, and the pre-crash scenarios are classified based on the trajectories of pedestrians in an example training dataset used in a pedestrian
Hsu, Chung-Jen
Lightweight Neural Network Model and Algorithm for Pedestrian Detection12-08-03-002712/18/2024
Traditional pedestrian detection methods have poor robustness. Deep learning-based methods have shown high performance in recent years but rely on substantial computational resources. Developing a lightweight, deep learning-based pedestrian detection algorithm is essential for applying deep learning-based algorithms in resource-limited scenarios, such as driverless and advanced driver assistance systems. In this article, an improved model based on YOLOv3 called “YOLOPD” (You Only Look Once—Pedestrian Detection), is proposed. It is obtained by constructing a self-attentive module, introducing a CIOU (Complete Intersection over Union) loss function and a depth separated convolutional layer. Experimental results show that on the INRIA (National Institute for Research in Computer Science and Automation), Caltech, and CityPerson pedestrian dataset, the MR (miss rate) of the model YOLOPD is better than that of the original YOLOv3 model, and the number of parameters is reduced by about 1/3
Li, Shanglin, Wang, Qi Feng, Li, Ren Fa, Xiao, Juan
Skeletal Surrogate Metastructural Anisotropy Mimicry and the Influence of Fabrication Material09-12-02-000911/12/2024
Human body models have been used for decades to inform efforts in promoting automobile occupant and pedestrian safety. However, many of these models fail to capture the intricacies of individual variability. Cadaveric subjects typically exceed representative age ranges and hence mechanics. Animal subjects typically require specific setups that stray from that which is representative of human crash scenarios. Computational models can only consider so many practical real-world variables. Artificial surrogates, dummies being popular among them, are very popular for reusability and robust data collection. However, even the biomechanically accurate skeletal surrogates available commercially are limited in that they do not consider human variability and skeletal microstructure local variability. The objective of the work herein is to assess computational methods of metastructural variability mimicry by fabrication material. We implement mimicry approaches focusing on bulk isotropic
Hezrony, Benjamin S., C. F. Lopes, Pedro, Brown, Philip J.
Enhancing Availability of Autonomous Shuttle Services: A Conceptual Approach toward Challenges and Opportunities12-08-03-002310/9/2024
Autonomous vehicle technologies have become increasingly popular over the last few years. One of their most important application is autonomous shuttle buses that could radically change public transport systems. In order to enhance the availability of shuttle service, this article outlines a series of interconnected challenges and innovative solutions to optimize the operation of autonomous shuttles based on the experience within the Shuttle Modellregion Oberfranken (SMO) project. The shuttle shall be able to work in every weather condition, including the robustness of the perception algorithm. Besides, the shuttle shall react to environmental changes, interact with other traffic participants, and ensure comfortable travel for passengers and awareness of VRUs. These challenging situations shall be solved alone or with a teleoperator’s help. Our analysis considers the basic sense–plan–act architecture for autonomous driving. Critical components like object detection, pedestrian tracking
Dehghani, Ali, Salaar, Hamza, Srinivasan, Shanmuga Priya, Zhou, Lixian, Arbeiter, Georg, Lindner, Alisa, Patino-Studencki, Lucila
Micromobility and the Next Infrastructure WaveEPR202402210/4/2024
US transportation infrastructure is dominated by the automobile form factor. Alternative modalities of movement, such as bikes, golf carts, and other micromobility options, have existed but are decidedly at a lower tier of importance. Even pedestrian access ways are not overly emphasized in the US transportation system. This lack of prioritization matches the reality that the vast majority of people and commerce moves through the motor vehicle infrastructure, with micromobility sitting in the periphery. Additionally, given the current lack of commercial applications, there are limited direct fee-based funding mechanisms connected to micromobility form factors. Micromobility and the Next Infrastructure Wave discusses how recent technological innovations in electrification, e-commerce, and autonomy are enabling a new class of micromobility devices which offer palpable value to consumers and enable significant commercial applications. Unlike the past, these micromobility devices now have
Razdan, Rahul
Comprehensive Study on Challenges to Introduce Autonomous Emergency Braking (AEBS) Feature in Indian Perspective2024-01-30509/8/2024
India is a diverse country in terms of road conditions, road maintenance, traffic conditions, traffic density, quality of traffic which implies presence of agricultural tractors, bullock carts, autos, motor bikes, oncoming traffic in same lane, vulnerable road users (VRU) walking in the same lanes as vehicles, VRU’s crossing roads without using zebra crossings etc. as additional traffic quality deterrents in comparison to developed countries. The braking capacity of such vivid road users may not be at par with global standards due to their maintenance, loading beyond specifications, driver behavior which includes the tendency to maintain a close gap between the preceding vehicle etc. which may lead to incidents specifically of rear collisions due to the front vehicle going through an emergency braking event. The following paper provides a comprehensive study of the special considerations or intricacies in implementation of Autonomous Emergency Braking (AEBS) feature into Indian traffic
Kartheek, Nedunuri, Khare, Rashmita, Sathyamurthy, Sainathan, Manickam, Praveenkumar, Kuchipudi, Venkata Sai Pavan
Effect of A-Pillar Blind Spots on a Driver’s Pedestrian Visibility during Vehicle Turns at an Intersection2024-22-00029/5/2024
This study aims to elucidate the impact of A-pillar blind spots on drivers’ visibility of pedestrians during left and right turns at an intersection. An experiment was conducted using a sedan and a truck, with a professional test driver participating. The driver was instructed to maintain sole focus on a designated pedestrian model from the moment it was first sighted during each drive. The experimental results revealed how the blind spots caused by A-pillars occur and clarified the relationship between the pedestrian visible trajectory distance and specific vehicle windows. The results indicated that the shortest trajectory distance over which a pedestrian remained visible in the sedan was 17.6 m for a far-side pedestrian model during a right turn, where visibility was exclusively through the windshield. For the truck, this distance was 20.9 m for a near-side pedestrian model during a left turn, with visibility through the windshield of 9.5 m (45.5% of 20.9 m) and through the
Matsui, Yasuhiro, Oikawa, Shoko
Toward Trustworthy Automated Driving through Qualitative Scene Understanding and Explanations12-08-01-00037/12/2024
Understanding driving scenes and communicating automated vehicle decisions are key requirements for trustworthy automated driving. In this article, we introduce the qualitative explainable graph (QXG), which is a unified symbolic and qualitative representation for scene understanding in urban mobility. The QXG enables interpreting an automated vehicle’s environment using sensor data and machine learning models. It utilizes spatiotemporal graphs and qualitative constraints to extract scene semantics from raw sensor inputs, such as LiDAR and camera data, offering an interpretable scene model. A QXG can be incrementally constructed in real-time, making it a versatile tool for in-vehicle explanations across various sensor types. Our research showcases the potential of QXG, particularly in the context of automated driving, where it can rationalize decisions by linking the graph with observed actions. These explanations can serve diverse purposes, from informing passengers and alerting
Belmecheri, Nassim, Gotlieb, Arnaud, Lazaar, Nadjib, Spieker, Helge
Harmonizing Safety Regulations and Perception: A Simulation Methodology for AVAS System Design2024-01-29156/12/2024
The development of an effective Acoustic Vehicle Alerting System (AVAS) is not solely about adhering to safety regulations; it also involves crafting an auditory experience that aligns with the expectations of vulnerable road users. To achieve this, a deep understanding of the acoustic transfer function is essential, as it defines the relationship between the sound emitter (the speaker inside the vehicle) and the receiver (the vulnerable road user). Maintaining the constancy of this acoustic transfer function is paramount, as it ensures that the sound emitted by the vehicle aligns with the intended safety cues and brand identity that is defined by the car manufacturer. In this research paper, three distinct methodologies for calculating the acoustic transfer function are presented: the classical Boundary Element method, the H-Matrix BEM accelerated method, and the Ray Tracing method. Furthermore, the paper encompasses an assessment of the correlation between these methods and their
Calloni, Massimiliano, Hadjit, Rabah, Salvekar, Pinak, Musser, Chad
Lighting and Visual Information for Vulnerable Road User (VRU) Safety: An Introductory ReviewVRUSC-002-20245/3/2024
Injuries and fatalities among pedestrians, cyclists, scooterists, highway road workers, and safety and emergency personnel—often referred to as vulnerable road users (VRUs)—continue to rise at alarming rates worldwide. Emphasizing the urgent need for enhanced safety measures, this study, commissioned by the Vulnerable Road User Safety Consortium™ (VRUSC) and conducted by the Light and Health Research Center at the Icahn School of Medicine at Mount Sinai, evaluates the potential effectiveness of lighting and visual information systems in improving VRU safety. The white paper presents a synthesis of published research on lighting and markings from the perspective of both human drivers and machine vision systems. It identifies potential preliminary guidelines for the intensity, color, temporal, and spatial characteristics of lighting and visual information that can help prevent crashes involving VRUs. The study also highlights knowledge gaps that require further research, including the
Vulnerable Road Users Safety Consortium
Active Collision Avoidance System for E-Scooters in Pedestrian Environment2024-01-25554/9/2024
In the dense fabric of urban areas, electric scooters have rapidly become a preferred mode of transportation. As they cater to modern mobility demands, they present significant safety challenges, especially when interacting with pedestrians. In general, e-scooters are suggested to be ridden in bike lanes/sidewalks or share the road with cars at the maximum speed of about 15-20 mph, which is more flexible and much faster than pedestrians and bicyclists. Accurate prediction of pedestrian movement, coupled with assistant motion control of scooters, is essential in minimizing collision risks and seamlessly integrating scooters in areas dense with pedestrians. Addressing these safety concerns, our research introduces a novel e-Scooter collision avoidance system (eCAS) with a method for predicting pedestrian trajectories, employing an advanced Long short-term memory (LSTM) network integrated with a state refinement module. This method predicts future trajectories by considering not just past
Yan, Xuke, Shen, Dan
Evaluating Vehicle Response Through Non-Traditional Pedestrian Automatic Emergency Braking Scenarios2024-01-19754/9/2024
Pedestrian Automatic Emergency Braking (P-AEB) is a technology designed to avoid or reduce the severity of vehicle to pedestrian collisions. This technology is currently assessed and evaluated via EuroNCAP and similar procedures in which a pedestrian test target is crossing the road, walking alongside the road, or stationary in the forward vehicle travel path. While these assessment methods serve the purpose of providing cross-comparison of technology performance in a standardized set of scenarios, there are many scenarios which could occur which are not considered or studied. By identifying and performing non-EuroNCAP, non-standardized scenarios using similar methodology, the robustness of P-AEB systems can be analyzed. These scenarios help identify areas of further development and consideration for future testing programs. Three scenarios were considered as a part of this work: straight line approach, curved path approach, and parking lot testing. Exemplar tests were performed for
Bartholomew, Meredith, Helber, Nicholas, Heydinger, Gary, Zagorski, Scott
Items per page:
1 – 50 of 315