Browse Topic: Automated vehicles

Items (711)
Find
Optimizing Virtual Scenario Testing for Autonomous Vehicles with Large-Scale Scenario Generation.2026-01-0050To be published on 04/07/2026
The validation of Advanced Driver Assistance Systems (ADAS) and Automated Driving (AD) Systems, especially at higher automation levels such as SAE Level 3 or 4, demands the testing of a vast array of scenario variants far exceeding the scope of standard safety specifications like Euro NCAP (The European New Car Assessment Programme). Autonomous vehicles require thorough real-world testing to ensure automotive safety. However, public road tests are costly and risky. Instead, virtual scenarios - digital twins of real environments - offer a safe, cost-effective testing alternative. Exhaustive simulation across this high-dimensional scenario space, which includes variations in actor behavior, environmental conditions, and event characteristics, is computationally infeasible. We propose a constraint-solving approach to address this challenge that leverages mathematical and geometric techniques to analytically assess the existence and validity of scenario variants prior to simulation. Two
Karve, Omkar, Saurav, Saket, Purwar, Prabhanshu
Benchmarking Driver Responses in Head-On Conflicts: Toward an Objective Protocol for Human and AV Evaluation2026-01-0534To be published on 04/07/2026
Head-on emergency conflicts present a unique challenge for evaluating driver and automated vehicle (AV) performance. Unlike most emergency scenarios that follow a direct stimulus–response sequence, head-on encounters are characterized by a stimulus–wait–response pattern in which time to contact (TTC) strongly shapes driver behavior. Drawing on naturalistic and simulator data, this study quantified human responses to head-on conflicts. When the opposing vehicle crossed the centerline with more than 2 seconds of TTC, drivers delayed braking until an average of 1.3 seconds (SD = 0.8) before impact, regardless of the timing of the intrusion. By contrast, when TTC was less than 2 seconds, braking was initiated only 0 to 1.0 second before impact. As a result, many drivers applied the brakes less than half a second before collision. These findings provide a meta-analytically grounded benchmark for comparing human behavior to AV decision-making processes and demonstrate the need for conflict
Muttart, Jeffrey, Dinakar, Swaroop, Maloney, Tim, Adikhari, Bikram, Gernhard-Macha, Suntasty
Developing Safety Case for Automated Driving following UL4600 & ISO50832026-01-0527To be published on 04/07/2026
With the increasing in probabilistic outcomes by using complex algorithms/trainings for autonomous features, the safety of the product becomes more comprehensive where the safety case is one of claims to the overall safety assurance. Nonetheless, the safety case still needs to follow rigorous processes and provide all critical safety deliverables. Newer and updated standard such as UL4600 and ISO5083 have more considerations and claims can include in the safety case. From the definition of the autonomous feature to the risk acceptance criteria to the verification and validation of these features can all have elements from those new standards. ISO 5083 provides a framework for an autonomous system which can align with both ISO26262 and 21448. The scope and the fallback maneuvers can complement the hazards identified through safety analysis. The risk acceptance covers both Functional Safety and SOTIF through validation of potential metrics. Similarly, the evidence sufficiency and risk
Mudunuri, Venkateswara Raju, Almasri, Hossam, Fan, Hsing-Hua
Mathematical Modeling of Trust Calibration for Human–Automation Safety2026-01-0530To be published on 04/07/2026
Trust between humans and automated vehicles is increasingly recognized as a pivotal factor in achieving safety in advanced vehicles and mobility environments. Poorly calibrated trust—either over-trust leading to complacency or under-trust leading to disengagement—has been identified in numerous incidents involving advanced driver assistance systems and autonomous functions. Yet, most current approaches to managing trust rely on surveys, heuristics, or qualitative assessments, providing little predictive capability for safety engineers and system designers. This paper presents a formal mathematical framework for trust calibration, modeling trust as a dynamic, evolving construct grounded in probabilistic reasoning. We represent trust as a Beta-distributed belief that updates over time through Bayesian inference, with parameters adjusted by observed successes and failures, contextual cues, and system feedback signals. The model also incorporates forgetting and drift functions, allowing
Wen, He, Mounir, Adil
Securing the AI-Driven Vehicle: A Hardware-Based Security Framework for Scalable, Trustworthy Autonomy2026-01-0085To be published on 04/07/2026
Autonomous driving technology in modern vehicles marks a pivotal evolution in transportation, but it may also introduce system-level vulnerabilities that span from tampering with sensors and interfaces to compromising compute units and communication links. This paper proposes a unified, layered hardware security architecture for AI-equipped automated vehicles. Based on current automotive Ethernet and zonal architectures, it provides end-to-end trust using hardware interface security, accelerated-cryptography, and SRAM PUF-based key provisioning. All security primitives are anchored to a hardware root of trust, delivering cryptographic identity, secure boot enforcement, and trusted key storage across the entire vehicle lifecycle. Our architectural assumptions follow the direction ISO 26262, ISO/SAE 21434 and AI development mandates for next-generation SAE Level 3+ vehicles using zonal Ethernet backbones, Time-Sensitive Networking (TSN), and heterogeneous compute islands (e.g., vision
C Suriyanarayanan, Pav, Iacob, Radu
A Simple Analytical Model for Predicting Cooperative Ratio in Agreement-Seeking Cooperative Driving Automation with C-V2X Communication2026-01-0078To be published on 04/07/2026
Cooperative Driving Automation (CDA) has emerged as an active research area in recent years, categorized into four classes of operations with varying levels of cooperation as defined in the SAE J3216 standard. Among these, Class C CDA, referred to as Agreement-Seeking Cooperation (ASC), has received limited attention in literature. Unlike Cooperative Adaptive Cruise Control (CACC), which typically engages when lead vehicles are identified as cooperative and disagree under manual override or safety-critical conditions, ASC requires agents to exchange messages interactively to reach consensus on a proposed plan and its implementation. This necessitates more sophisticated communication and control designs, which in turn influences customized ASC efficiency. Previous work has examined, through simulation, the impact of three key parameters on ASC system performance: CDA message transmission frequency, Packet Drop Ratio (PDR), and Cooperation Duration Length (CDL). In this paper, we extend
Zhan, Lu, Hyeon, Eunjeong, JEONG, Jongryeol, Misra, Priyash, Di Russo, Miriam, Das, DEBASHIS, Stutenberg, Kevin
Integrated Design and Validation of a Robust Lane Centering Controller for Automated Driving.2026-01-0037To be published on 04/07/2026
Lane centering is a critical active safety feature whose effectiveness depends on robust design and validation across diverse driving conditions. This paper presents the development of a Lane Centering Controller (LCC) using a structured model-based design workflow in MATLAB and Simulink. A kinematic bicycle model was employed to simulate vehicle dynamics and evaluate an angle based steering controller integrating both feedforward and feedback control paths. The controller was tested across multiple road geometries and speeds up to 65 mph to ensure tracking consistency and stability under nominal and perturbed conditions. Perception noise models for lane curvature and curvature rate were extracted from onboard camera data under controlled conditions, revealing Gaussian characteristics. No filtering was applied, allowing direct evaluation of the controller’s inherent robustness to raw signal variability. The LCC maintained a peak lateral offset within ±0.35 m and lateral jerk within ±9
Bijinepalli, Ravi Teja, Tambolkar, Pooja, Midlam-Mohler, Shawn
Innovative Smart Switch Architecture Catering to 12 Volts to 48 Volts Battery Bus Requirements2026-01-0064To be published on 04/07/2026
Electronics is rapidly entering all automotive subsystems, performing control and monitoring tasks apart from making the entire vehicle intelligent.. Interface with the external automotive ecosystem needs careful attention during the system design. It defines how seamlessly the electronic unit interacts with the rest of the vehicle. It needs to do so in an effective manner without compromising on cost and other automotive application constraints. This paper focuses on the “ smart switch building block” that forms the heart of an automotive output interface echo system. Its importance stems from the fact that a smart switch is an indispensable building block for any electronic control system driving external loads. As various novel electrical and electronics architectures are entering various vehicle segments need for a single reusable solution that will cater to 12 Volts to 48 Volts battery buses is increasingly being felt. However, no prevalent solution meets this requirement. Even
Vaidya, Vishwas Manohar
Agile Safety Case Assessments for Autonomous Vehicle Fleets2026-01-0521To be published on 04/07/2026
The large-scale deployment of autonomous vehicles (AVs) demands not only robust safety cases but also systematic approaches for their assessment. A safety case is a structured argument, supported by evidence, that a system is acceptably safe within its intended domain. While many AV developers are now adopting safety cases as a prerequisite for launch readiness, effective assessment methods have not kept pace with the field’s rapid progress. This paper presents a three-stage methodology for safety case assessment—framework, solution, and implementation assessment—developed through nearly fifty evaluations across commercial and defense AV programs. Framework assessment benefits from leveraging safety case frameworks, which accelerate development and prevent argument defects. Solution assessment focuses on defining clear evidence criteria, while implementation assessment evaluates the sufficiency of complete evidence packages. Together, these stages support iterative improvement and
Wagner, Michael
The Necessity of a Holistic Safety Evaluation Framework for AI-Based Automation Features2026-01-0522To be published on 04/07/2026
The intersection of Safety of Intended Functionality (SOTIF) and Functional Safety (FuSa) analysis for driving automation features has traditionally excluded Quality Management (QM) components from rigorous safety impact evaluations. Historically, QM components have not been classified as safety-relevant, and therefore their potential influence on overall system safety has often been overlooked. However, recent advancements in artificial intelligence (AI) integration within automated driving systems have revealed that these components can, under certain conditions, contribute to SOTIF-related hazardous risks. This emerging reality challenges long-standing assumptions and underscores the need for a more inclusive approach to safety analysis. Furthermore, compliance with evolving AI safety standards, such as ISO/PAS 8800, necessitates a re-evaluation of safety considerations for components previously deemed outside the scope of FuSa and SOTIF frameworks. This paper examines the necessity
Abbaspour, Ali Reza, Mahadevan, Shabin, Zwirglmaier, Kilian, Stafford, Jeff
Driving with Influence: Exploring Crash Factors of Automated Systems in Different Roadway Contexts2026-01-0526To be published on 04/07/2026
Although SAE Level 2 Advanced Driver Assistance Systems (ADAS) and Automated Driving Systems (ADS) have been shown to provide some safety benefits, they have largely been constrained to specific driving contexts namely motorways for ADAS and lower speed roadways for ADS. As more advanced systems are entering the roadways and their operating conditions are expanding, it remains an ongoing challenge to assess the safe operation of vehicles with automation in different roadway contexts and leverage lessons learned from real-world incidents to create safer and more robust systems. As of August 2025, the NHTSA’s Standing General Order on Crash Reporting offers systematic data on such incidents, providing at least a cursory overview of where and how they occur. From this source, a total of 2,263 crash records were extracted—472 for ADAS systems and 1,791 for ADS systems. Through the application of association rule mining and a novel metric termed influence, patterns in ADAS- and ADS-related
Astle, W. Abram, Haus, Samantha
High Biofidelity Modification of Thoracolumbar Structure in THOR model for Reclined Occupant2026-01-0196To be published on 04/07/2026
With the rapid development of automated driving and the increasing adoption of zero-gravity seats, the crash safety of highly reclined occupants has become a critical issue. The current THOR model, designed for frontal impacts in the standard upright posture, shows limitations when applied directly for reclined occupants, including excessive thoracolumbar flexion stiffness and large backward pelvis rotation. In this study, we analyzed the thoracolumbar spine kinematics of the THUMS human body model, which had been reconstructed against post-mortem human subject (PMHS) tests. A two-segment fitting was used to “dummy-ize” the spinal flexion response, yielding a virtual rotation hinge located close to the thoracic hinge of the original THOR model. The hinge rotation angle exhibited a strong linear correlation with the flexion moment of the L1–T12 segment. Based on this relationship, angular stiffness derived from the fitting was applied to the thoracolumbar hinge of the dummy. Additional
Guo, Wencheng, Kuang, Gaoyuan, Shen, Wenxuan, Tan, Puyuan, Zhou, Qing
A Real-Time Vehicle Detection and Counting System Using a GUI Interface.2026-01-0156To be published on 04/07/2026
The growing need for intelligent traffic monitoring and environmental control has fuelled the importance of automated vehicle detection and counting systems. Fuel consumption estimation, vehicular emissions calculations, and traffic pattern comprehension- all play a vital role in shaping sustainable environmental policies. Therefore, accurate identification and counting of vehicles is essential. In this paper, we have shown the development of a real-time vehicle detection and counting application that uses computer vision and deep learning techniques to effectively detect, categorise, and count several types of vehicles on Indian roads. The computer vision vehicle counting application uses the YOLO (You Only Look Once) deep learning model for real-time identification and categorisation of diverse vehicle types, including cars, buses, trucks, and motorbikes [1]. A tracking module based on the SORT (Simple Online and Real-time Tracking) algorithm ensures unique identification of vehicles
Gusain, Ashna, Maurya, Akshay, PATHAK, SUNIL, Khan, Tuhin
Effects of Child Anthropometry, Seatback Angle, Seat Rotation Angle, Seatbelt Force Limiting, and Collision Type on Injury Risk of Child Occupants in Highly Automated Vehicles2026-01-0570To be published on 04/07/2026
This study aimed to evaluate the influence of child anthropometry, seat posture (recline and rotation), seatbelt force limiting, and frontal collision scenarios on the kinematic response and injury risk to children in highly automated vehicles. The TUST IBMs 6YO-O model was conducted the frontal collisions in sled tests. This simulation matrix includes five percentiles six-year-old occupants (P3, P25, P50, P75, and P97), three seatback angles (20°, 30°, and 45°), four seat rotation angles (0°, 90°, 180°, and 270°), three seatbelt force limiting (2.6 kN, 3.6 kN, and 4.6 kN), and three collision types. Injury risks were assessed including the child occupant's head, neck, chest/abdomen, and lumbar region in each simulation (n=540). The results indicate that the child anthropometry, the seatback angle, and the seat rotation angle have a significant influence on the motion responses. Statistically significant differences between all the groups within each independent variable category were
Wang, Yanxin, Zhao, Hongqian, Li, Haiyan, He, Lijuan, Cui, Shihai, Lv, Wenle
Development of a model-based data-driven control algorithm for a Drive-By-Wire System for a Level 4 Automated Vehicle2026-01-0043To be published on 04/07/2026
Precision control in Level 4 Automated Vehicles is essential for enhancing operational efficiency, accuracy, and safety, including improvements in time and fuel consumption. This research, conducted as part of ARPA-E’s NEXTCAR program, focuses on developing a robust control algorithm for a 2021 Honda Clarity Plug-In Hybrid Electric Vehicle (PHEV) to enable drive-by-wire functionality. A model-based control algorithm was created for a 2021 Honda Clarity Plug-In Hybrid Electric Vehicle (PHEV) to enable drive-by-wire functionality for longitudinal and lateral motion controls. This vehicle was equipped with a set of sensors and an onboard processing unit to enable Level 4 automation. An algorithm was designed to command steering torque to the electronic power steering module, ensuring the vehicle could attain the desired steering angle position at varying speeds. The system leveraged feedforward and feedback mechanisms to command steering torque to the electronic power steering module
Adsule, Kartik, Bhagdikar, Piyush, Drallmeier, Joseph, Alden, Joshua, Gankov, Stanislav
A Comparison of Road Grade Preview Signals from Lidar and Maps2026-01-0026To be published on 04/07/2026
Road grade can impact the energy efficiency, safety, and comfort associated with automated vehicle control systems. Currently, control systems that attempt to compensate for road grade are designed with one of two assumptions. Either the grade is only known once the vehicle is driving over the road segment through proprioception, or complete knowledge of the oncoming road grade is known from a pre-made map. Both assumptions limit the performance of a control system, as not having a preview signal prevents proactive grade compensation, whereas relying only on map data potentially subjects the control system to missing or outdated information. These limits can be avoided by measuring the oncoming grade in real-time using on-board lidar sensors. In this work, we use point returns accumulated during travel to estimate the grade at each waypoint along a path. The estimated grade is defined as the difference in height between the front and rear wheelbase at a given waypoint. Kalman filtering
Schexnaydre, Logan, Poovalappil, Aman, Robinette, Darrell, Bos, Jeremy
An Enhanced Canny-Based Vision System for Vanishing Point Detection in Camera Calibration and Sun Glare Mitigation for ADAS2026-01-0016To be published on 04/07/2026
Abstract— 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
Uppala, Rohit Raj, Kaye, Murali, Zadeh, Mehrdad, TAN, Teik-Khoon
A Frequency-Aware Reinforcement Learning Framework for Suspension Control with Integrated Temporal Features and Expert Guidance2026-01-0209To be published on 04/07/2026
Active suspension systems play a crucial role in improving vehicle ride comfort and handling stability. However, most existing studies focus on the low-frequency range below 20 Hz, leaving the suppression of high-frequency vibrations within 50–500 Hz largely unexplored, even though these vibrations strongly affect in-cabin noise and ride quality. To address this gap, this study introduces a quarter-car suspension model incorporating both bushing dynamics and a rigid-ring tire within a reinforcement learning (RL) framework. A major challenge for RL-based suspension control is its degradation in high-frequency performance. To overcome this issue, we design an innovative training framework that integrates multiple synergistic strategies. First, frequency-domain rewards are incorporated as auxiliary signals to explicitly guide policy optimization in the high-frequency band. Second, long short-term memory (LSTM) networks are embedded in both the Actor and Critic to capture the sequential
zhu, Zhehui, Zhang, Lijun, Meng, Dejian, Hu, Xingyu
MBSE-Driven XIL Workflow for Energy Evaluation of Automated Vehicles: From Simulation to VIL Testing2026-01-0289To be published on 04/07/2026
This paper presents a Model-Based Systems Engineering (MBSE)-driven X-in-the-Loop (XiL) methodology for quantifying the energy impacts of automated vehicles in realistic road scenarios while preserving high-fidelity powertrain behavior. We developed Argonne’s multi-vehicle simulation tool, RoadRunner, which automatically builds closed-loop road scenarios (road geometry, vehicle sensors, other vehicles, and traffic controls) and connects them to Argonne’s validated, high-fidelity vehicle and powertrain models in Autonomie. The MBSE backbone in AMBER organizes requirements, interfaces, plant and controller models, and test scenarios into a single set of models that carries through pure simulation, Software-in-the-Loop (SiL), Processor-in-the-Loop (PiL), and Vehicle-in-the-Loop (ViL) stages. Each stage has a clear role: simulation enables rapid development and validation of advanced models or controls across a large number of scenarios; SiL supports standalone algorithm verification and
JEONG, Jongryeol, Sharer, Phillip, Di Russo, Miriam, Das, DEBASHIS, Zhang, Yaozhong, Karbowski, Dominik
Optimization of Road Reference Profiles based on Highway Design for Connected and Automated Vehicles2026-01-0096To be published on 04/07/2026
Advances in Connected and Automated Vehicles (CAVs) have developed a level in which high-definition maps can be used to improve road safety. Data compactness and robustness on road characterization is essential for the proper handling of vehicles under curves. In this paper, an optimization scheme that relates highway-design road curvature and optimal speed of travel is defined to safely navigate through a given road. The scheme is divided in two main steps. First a nonlinear optimization problem, in which curvature profiles are fitted from a model that based on street design standards as per the American Association of State Highway and Transportation Officials (AASHTO). Secondly, the optimized curvature profile is subject to a secondary optimization problem that uses vehicle dynamics for both constraints and objective function derivation. Guidance reference parameters such as curvature and velocity, at different levels of friction are analyzed. Results show that, even in sparse
Jacome, Ricardo Osmar, Stolle, Cody, Grispos, George
Real-time Parameter Optimization for Eco-driving Control in Connected and Automated Vehicles Using Reinforcement Learning2026-01-0041To be published on 04/07/2026
This paper introduces a novel methodology to enhance the energy efficiency of eco-driving controllers in Connected and Automated Vehicles (CAVs) by leveraging Reinforcement Learning (RL) techniques for real-time parameter optimization. Traditional eco-driving strategies rely on fixed control parameters, which limit adaptability across diverse traffic and road conditions. To address this, we apply continuous action space RL algorithms, specifically Deep Deterministic Policy Gradient (DDPG) and Proximal Policy Optimization (PPO), to dynamically tune four key parameters within a model predictive control framework that is grounded in Pontryagin’s Maximum Principle (PMP). These parameters influence acceleration, braking, cruising, and intersection-approach behaviors, making them critical for achieving optimal eco-driving performance. Our study employs Argonne National Laboratory’s RoadRunner simulator, a Simulink-based environment designed for high-fidelity CAV analysis, incorporating
Zhang, Yaozhong, Ammourah, Rami, Han, Jihun, Moawad, Ayman, Shen, Daliang, Karbowski, Dominik
Characterizing the Impact of C-V2X PC5 Radio on Cooperative Driving Automation in Hardware-in-the-Loop Experiments2026-01-0077To be published on 04/07/2026
The SAE J3216 standard defines Cooperative Driving Automation (CDA), which has gained increasing attention in recent years as an umbrella framework encompassing a wide range of automated vehicle applications enabled by Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) technologies. However, limited research has investigated how Cellular Vehicle-to-Everything (C-V2X) technology affects CDA applications, especially the agreement seeking operations. This work presents a hardware-in-the-loop (HIL) experimental study designed to evaluate the Argonne CDA controller under varying C-V2X radio transmission frequencies and message configurations. A three-vehicle car-following scenario was implemented in the Argonne-developed Roadrunner Simulator, incorporating CDA agreement-seeking operations, vehicle powertrain models, and V2V communication modules. The CDA messages were then exchanged through two actual C-V2X radios with realistic communication impairment caused by the hardware
Zhan, Lu, Hyeon, Eunjeong, Misra, Priyash, JEONG, Jongryeol, Di Russo, Miriam, Das, DEBASHIS, Stutenberg, Kevin
Sensitivity Analysis toward Differential Braking as Backup Steering Functionality2026-01-50132/20/2026
This paper presents a novel sensitivity analysis framework for differential braking as a backup steering solution in fail-operational Steer-by-Wire systems. The fault-tolerant design approach of Steer-by-Wire and steering systems for highly automated driving relies on the availability of road wheel actuators (RWA). Redundancies are therefore commonly used to ensure fail-operationality. Since its widespread implementation in production vehicles through electronic stability control, the use of differential braking as a cost-effective measure is desirable to increase functional diversity. However, feasible lateral accelerations through this backup solution are limited compared to conventional steering systems and lie close to ordinary driving scenarios. To address this limitation, this work investigates the influence of chassis parameters on differential braking performance. After defining characteristic values and a simulation test plan, a preliminary analysis using a linear single-track
Salzwedel, Leon, Iatropoulos, Jannes, Heise, Cedric, Frohn, Christian, Henze, Roman
Recommendations for ADS-DVs to Accommodate the Needs of People with DisabilitiesJ3261_202602 (Current)2/17/2026
ADS-DVs promise to expand transportation options for individuals who have been historically underserved in personal transportation. However, for this to be truly realized, the unique needs of persons with disabilities (PWDs; including those who are deaf and hard of hearing, blind, have low vision, have upper body limitations, have lower body limitations, are wheelchair users, and have cognitive disabilities) should be understood at the design stage of vehicle development. This document presents a list of recommendations for use in the design and development of ADS-DVs based on the identified needs of PWDs. It considers the accessibility of services used to interact with the ADS-DV before the trip and the complete trip (including planning the trip and requesting the vehicle, determining a pickup location, finding the vehicle, authenticating the user, entering the vehicle, interacting with the vehicle while inside, determining a drop-off location, exiting the vehicle, and finding the
On-Road Automated Driving (ORAD) Committee
Intelligent Steering System to Improve Fuel Efficiency in Heavy Duty Vehicles2026-28-01032/12/2026
In commercial vehicles, conventional engine-driven hydraulic steering systems result in continuous energy consumption, contributing to parasitic losses and reduced overall powertrain efficiency. This study introduces an Electric Powered Hydraulic Steering (EPHS) system that decouples steering actuation from the engine and operates only on demand, thereby optimizing energy usage. Field trials conducted under loaded conditions demonstrated a 3–6% improvement in fuel economy, confirming the system’s effectiveness in real-world applications. A MATLAB-based simulation model was developed to replicate dynamic steering loads and vehicle operating conditions, with results closely aligning with field data, thereby validating the model’s predictive accuracy. The reduction in fuel consumption directly translates to lower CO₂ emissions, supporting regulatory compliance and sustainability goals, particularly in the context of tightening emission norms for commercial fleets. These findings position
T, Aravind Muthu Suthan, Mani, Kishore, Ayyappan, Rakshna, D, Senthil Kumar, S, Mathankumar
Bosch is ready to bring AI to your vehicle, likely to still be ICE-powered in 203526AUTP02_022/1/2026
CES provided Bosch with another high-profile chance - as it did with its Super Bowl ads in 2025 and in 2026 - to expand its reach with non-industry customers through a livestreamed press conference that touched on power tools and home appliances. Tanja Rueckert, a member of Bosch's board of management, said that Bosch's expertise “bridges a gap that many others struggle to cross: the divide between the physical and the digital.” This advantage, she said, turned the company into an AI leader, with over 2,000 AI patents and a plan to have invested over 2.5 billion euros in AI by the end of 2027. On the automotive front, Bosch's efforts to connect the digital and physical worlds can be seen in a meaningful update to its Vehicle Motion Management system. The system now has capabilities that will let it control a vehicle's movement in six degrees of movement, which should minimize motion sickness, especially in automated driving vehicles. Bosch's hardware-agnostic software solution manages
Blanco, Sebastian
Type Approval for ADS: Considerations for the ODD2026-26-02451/16/2026
The rapid introduction of new Automated Driving Systems (ADS) in the last years has led to an urge for robust methodologies for the type approval of vehicles equipped with such technologies. As a result, different Regulations addressing this field have been adopted. These Regulations are mainly based in the New Assessment and Testing Methodology (NATM) developed within the World Forum for the Harmonisation of Vehicle Regulations (WP29). However, the complexity of the regulatory ecosystem extends beyond type approval. This complexity requires a thorough analysis in order to avoid any possible gap which may jeopardise the feasibility of Automated Driving Vehicles deployment. This paper analyses the possible mismatches among the different regulations currently in place or under development and proposes a holistic approach, where the concept of the Operational Design Domain (ODD) takes a relevant role.
Lujan Tutusaus, Carlos, Hidalgo, Justin, Flix, Oriol
Introducing a Novel System Engineering Framework for the Safe Deployment of Software Defined-Vehicles2026-26-06901/16/2026
The past decade has seen a systemic shift in the automotive landscape and the constituent parts of a vehicle. The automotive industry has shifted from a primarily hardware components industry to a software heavy industry, with software controlling majority of the vehicle functions. Coupled with the ability to fully update or evolve a vehicle’s capabilities or functionalities, post point of sale through software updates, the technical, commercial and service landscape of the automotive industry is rapidly changing. This has brought increasing focus to the concept of Software Defined Vehicle, where the vehicle is not only constantly evolving, but is also becoming more personalised by leveraging data collected through the life of the vehicle. This requires a rethink of the current development and deployment approaches for vehicles, which are software-intensive. In this paper, we introduce a novel four-step system engineering framework for the safe development and deployment of Software
El Badaoui, Halima, Jame-Elizebeth, Mariat, Khastgir, Siddartha, Jennings, Paul
Unlocking the Potential of In-Vehicle Edge AI2026-26-06861/16/2026
Edge Artificial Intelligence (AI) is poised to usher in a new era of innovations in automotive and mobility. In concert with the transition towards software-defined vehicle (SDV) architectures, the application of in-vehicle edge AI has the potential to extend well beyond ADAS and AV. Applications such as adaptive energy management, real-time powertrain calibration, predictive diagnostics, and tailored user experiences. By moving AI model execution right into edge, i.e. the vehicle, automakers can significantly reduce data transmission and processing costs, ensure privacy of user data, and ensure timely decision-making, even when connectivity is limited. However, achieving such use of edge AI will require essential cloud and in-vehicle infrastructure, such as automotive-specific MLOps toolchains, along with the proper SDV infrastructure. Elements such as flexible compute environments, deterministic and high-speed networks, seamless access to vehicle-wide data and control functions. This
Khatri, Sanjay, Sah, Mohamadali
Vehicle-to-Vehicle Negotiation Via Manoeuvre Coordination Messages for Cooperative Cut-in Scenarios2026-26-02741/16/2026
The automotive industry is rapidly extending the capabilities of automated systems by incorporating connectivity and cooperation features that enable real-time information exchange between vehicles and road infrastructure. Within the Connected, Cooperative, and Automated Mobility (CCAM) framework, Vehicle-to-Vehicle (V2V) communication is expected to play a key role in improving road safety, traffic efficiency, and driving comfort. This work addresses a practical implementation of the standardized Manoeuvre Coordination Messages (MCMs), as defined in the ongoing ETSI standard (ETSI TS 103 561). The proposed approach is demonstrated through a cooperative cut-in use case in which two vehicles negotiate a lane change manoeuvre. In the considered scenario, the ego vehicle, driven by a Highway Pilot (HWP) system, receives the intention to cut-in from a neighbouring cooperative vehicle through an MCM. In response, the ego vehicle adapts its behaviour by decelerating to generate a safe
Leiva Ricart, Gisela, Domingo Mateu, Bernat
A Dynamic Cybersecurity Benchmarking Framework for Automotive Cyber-Physical Systems2026-26-06121/16/2026
The modern vehicle is no longer a mechanical appliance—it has transformed into a software-defined cyber-physical system, integrating OTA updates, cloud-connected diagnostics, V2X services, and telematics-driven personalization. While this evolution promises unprecedented value in consumer experience and fleet operations, it also surfaces a dramatically expanded and evolving attack perimeter, especially across safety-critical ECUs and communication buses. Cyber vulnerabilities have shifted from isolated IT threats to real-time, embedded exploits. Controller area network (CAN), the backbone of vehicle bus systems, remains intrinsically insecure due to its lack of authentication and encryption, making it highly susceptible to message injection and denial-of-service by low-cost tools. Similarly, OEM implementations of BLE-based passive entry systems have proven vulnerable to replay and spoofing attacks with minimal hardware. In the Indian context, the transition to connected mobility is
Shah, Ravindra, Awasthi, Vibhu Vaibhav, Karle, Ujjwala
Artificial Intelligence in Passenger Cars: Unlocking Intelligent Mobility and Human-Centric Vehicle Innovation2026-26-06721/16/2026
Artificial Intelligence (AI) is radically transforming the automotive industry, particularly in the domain of passenger vehicles where personalization, safety, diagnostics, and efficiency. This paper presents an exploration of AI/ML applications through quadrant of the key pillars: Customer Experience (CX), Vehicle Diagnostics, Lifecycle Management, and Connected Technologies. Through detailed use cases, including AI-powered active suspension systems, intelligent fault code prioritization, and eco-routing strategies, we demonstrate how AI models such as machine learning, deep learning, and computer vision are reshaping both the user experience and engineering workflow of modern electric vehicles (EVs). This paper combines simulations, pseudo-algorithms and data-centric examples of the combined depth of functionality and deployment readiness of these technologies. In addition to technical effectiveness, the paper also discusses the challenges at field level in adopting AI at scale i.e
Hazra, Sandip, Tangadpalliwar, Sonali, Khan, Arkadip
High-Fidelity Modeling of Vehicle Dynamics for Control-Oriented Stability Enhancement2026-26-00931/16/2026
This study presents an integrated vehicle dynamics framework combining a 12-degree-of-freedom full vehicle model with advanced control strategies to enhance both ride comfort and handling stability. Unlike simplified models, it incorporates linear and nonlinear tire characteristics to simulate real-world dynamic behavior with higher accuracy. An active roll control system using rear suspension actuators is developed to mitigate excessive body roll and yaw instability during cornering and maneuvers. A co-simulation environment is established by coupling MATLAB/Simulink-based control algorithms with high-fidelity multibody dynamics modeled in ADAMS Car, enabling precise, real-time interaction between control logic and vehicle response. The model is calibrated and validated against data from an instrumented test vehicle, ensuring practical relevance. Simulation results show significant reductions in roll angle, yaw rate deviation, and lateral acceleration, highlighting the effectiveness
Duraikannu, Dinesh, Dumpala, Gangi Reddi
Adaptability Survey and Analysis of Camera Monitoring Systems (CMS) on Various Driving Population for Passenger Vehicles in Indian Driving Scenario2026-26-06011/16/2026
This paper presents a comprehensive survey and data collection study on the adaptability of Camera Monitoring Systems (CMS) for passenger vehicles. With the growing demand for enhanced safety, automation, and driver assistance technologies, Camera Monitoring Systems (CMS) has emerged as a key component in modern automotive design. This study aims to explore the current state of camera-based monitoring in passenger vehicles, focusing on their adaptability through survey data collection of various driving population and analysis. This paper evaluates the acceptance of CMS configurations in replacement to conventional rear-view mirrors through Position of Monitor, Clarity, CMS Adaptiveness to eyes, Comfort while turning, Merging into moving traffic, Monitoring Rear Traffic, while Getting Out of Car, while Overtaking, Coverage Area and Overall Acceptance. The findings offer valuable insights for manufacturers, engineers, and researchers working toward the evolution of intelligent vehicle
Sinha, Ankit, Tambolkar, Sonali Ameya, Belavadi Venkataramaiah, Shamsundara, Kauffmann, Maximilian
Risk-Aware Navigation Framework for Autonomous and Human-Driven Vehicles: Integrating Crash Probability Data for Safer Mobility12-09-03-00191/9/2026
This article presents a system to incorporate crash risk into navigation routing algorithms, enabling safety-aware path optimization for autonomous and human-driven vehicles alike. Current navigation systems optimize travel time or distance, while our approach adds crash probability as a routing criterion, allowing users to balance efficiency with safety. We transform disparate data sources, including traffic counts, crash reports, and road network data, into standardized risk metrics. Because traffic volume data only exist for a small subset of road segments, we develop a solution to project average daily traffic estimates to an entire road inventory using machine learning, achieving sufficient coverage for practical implementation. The framework computes exposure-normalized crash rates weighted by severity and integrates these metrics into routing cost functions compatible with existing navigation algorithms. The key strength of our solution is its scalability. In addition to the
Skaug, Lars, Nojoumian, Mehrdad
Corner Scenario Generation Method Based on Feature-Optimized Combinations for Automated Driving Systems2025-01-731712/31/2025
With the advancement of automated driving system levels, corner scenarios characterized by low probability and high risk have become critical for the safety validation of automated vehicles. However, due to the typical long-tail distribution of such scenarios, data-driven mining approaches face significant challenges in achieving efficient generation. To address this issue, this study proposes a feature-optimized combination-based method for generating corner scenarios in automated driving systems. Key scenario features related to functional failures are first identified using a combined approach of system theoretic process analysis (STPA) and hazard and operability analysis (HAZOP). Based on these features, an adaptive genetic algorithm is employed to optimize feature combinations and generate large numbers of corner scenario types that meet specified constraints. The proposed method is validated using cut-in and pedestrian-crossing scenarios as baseline cases. The results show that
Zhou, Shiying, Zhang, Dongbo, Zhao, Deyin, Zhu, Bing, Zhang, Peixing
On Optima Selection Strategies of Adversarial Swarm Learning for Energy Management of PHEVs2025-01-732012/31/2025
Developing robust optimization and learning methods is necessary for intelligent vehicles since an increasing number of critical control functions will be handled by artificial intelligence. This paper proposes an adversary swarm learning (ASL) system and an optima selection strategy for robust energy management of plug-in hybrid electric vehicles (PHEVs). The proposed ASL system comprises an attacking swarm and a defending swarm, which compete against each other iteratively to derive the most robust equivalent consumption minimization strategy (ECMS) for PHEV energy management. During the attacking rounds, the ECMS settings are fixed by the defender. Meanwhile, the attacker generates worst-case driving conditions by training a model in order to Maximize the equivalent energy consumption. During the defending rounds, the ECMS settings are optimized by the defender based on the driving scenarios generated by the attacker. The settings of robust ECMS are derived by introducing the
Zhong, Danyang, Yu, Zhuoping, Xiong, Lu, Zhou, Quan
Real-Time Multidimensional Vehicle Dynamic Stability Domain Calculation and Its Application in Intelligent Vehicles2025-01-732412/31/2025
Vehicle stability is fundamental to the safe operation of intelligent vehicles, and real-time, high-accuracy calculation of the stability domain is crucial for maintaining control across the full range of driving conditions. Because the real stability domain is difficult to parameterize accurately and is shaped by multiple driving factors including vehicle-dynamics parameters and environmental conditions, existing approaches fail to capture the multidimensional couplings between time-varying driving inputs and the resulting stability boundaries. Moreover, these methods remain overly conservative owing to algorithmic limitations and cautious design assumptions, thereby restricting dynamic performance in complex scenarios. To address these limitations, this paper introduces a multidimensional vehicle dynamic stability region calculation framework under time-varying driving conditions and apply it into path tracking controller of intelligent vehicle. Sum-of-squares programming (SOSP) is
Wang, Chengye, Zhang, Yu, Hu, Xuepeng, Qin, Haipeng, Wang, Guoli, Qin, Yechen
Deconstructing Driver State in Smart Cockpits: Physiological Validation of Perceived Risk, Trust, and Fatigue during Automated Driving2025-01-734512/31/2025
For driver-automation collaborative driving, accurately monitoring driver state in smart cockpits is crucial for enhancing safety, comfort, and human-computer interactions. However, existing research lacks clarity regarding the relationships among driver states, and there is no consensus on the optimal physiological channels to reliably capture these states. This study examined three critical psychological constructs (i.e., perceived risk, trust in the automated driving system, and driver fatigue) using a 37-participant driving simulation experiment. We manipulated multiple factors to induce distinct driver states among participants and recorded subjective scale ratings, heart rate variability, galvanic skin response, and eye movement data. Subjective scale ratings were adopted as the ground truth to examine the corresponding measurement relationships between different physiological signals and the three targeted dimensions of driver states. Our results proved that perceived risk
Wang, Zhenyuan, Li, Qingkun, Wang, Wenjun, Liu, Weimin, Sun, Zhaocong, Cheng, Bo
Driver Personalized Lane Change Behavior Analysis Based on Attention Deep Embedding Clustering2025-01-734712/31/2025
The characteristic representation and in-depth understanding of driver personalized driving behavior are fundamental to achieving human-like autonomous driving, enhancing the rationality of autonomous driving decisions, and meeting passengers’ personalized needs. [ADDED]Personalized driving behavior refers to individual-specific patterns in vehicle operation that emerge from drivers’ unique combinations of skills, risk tolerance, and habitual responses.However, current research lacks consideration of cluster analysis in the feature representation stage and ignores the time-varying contribution degree of time series values to low-dimensional features, which inhibits further utilization and development. This study adopts deep embedding clustering method and introduces attention mechanism to investigate driver personalized high-speed lane change behavior.[ADDED] Using a comprehensive driving simulator platform, we collected 15-channel time series data from 12 drivers performing 216 lane
Dong, Haomin, Wang, Wei, Wang, Yue, Li, Lun, Yue, Yi, Tian, Jiaxiao, Han, Jiayi
GP-LGFusion: Deep Fusion of Infrared-Visible Driving Images Based on Gradient Preservation and Local Guidance2025-01-730512/31/2025
Infrared and visible driving image fusion represents a pivotal technology in multi-source perception for automated driving. The objective of this technology is to generate fused images that exhibit significant targets and comprehensive road information in complex traffic scenes. However, the existing image fusion algorithms demonstrate inconsistent capacity to complement information in diverse environments. Additionally, there are limitations in their ability to extract features, such as the detailed texture of traffic targets under complex lighting conditions, including low-light scenes and multi-exposure scenes. To overcome these limitations, we propose a novel gradient-preserving and locally guided fusion method (GP-LGFusion). Our primary contribution is a Multi-scale Gradient Residual Block (MGRRB), an encoder module specifically designed to capture and retain both strong and weak texture features across different scales, a capability lacking in conventional approaches. Second, we
Meng, Zhangjie, Shi, Yicui, Chen, Yuhan, Zhou, Xiaoji, Li, Jie, Li, Guofa
Research on the Influencing Factors of Driver’s Trust in Autonomous Driving System2025-01-734412/31/2025
Although autonomous driving system is being used more frequently, its widespread adoption is still in its infancy. As a result, drivers may perceive the autonomous driving system as unreliable, which hinders the spread of automated driving. The goal of this study is to investigate the major variables influencing drivers’ trust in autonomous driving system. Significant positive correlations between the variables were found using the questionnaire survey, reliability validity test, and factor analysis of the questionnaire data. In order to measure the impact of system performance, user comprehension, system feedback mechanism, individual characteristics, and environmental factors on trust perception, a structural equation modeling (SEM) as an analytical tool. A total of 274 valid data were retained. By modeling and analyzing the recovered data, it showed that the fit are all in the acceptable range, the model construction is reasonable, and therefore the subsequent path analysis can be
Wang, Caiyong, He, Xingmiao, Tang, Yu, Chen, Rong, Li, Chuzhao
Infrastructure Enablers for Automation: Vol. 4EPRCOMPV02202512/29/2025
Coyner, Kelley, Bittner, Jason, Ercisli, Safak, Razdan, Rahul
Automated Vehicles: Development, Testing, and Validation: Vol. 4EPRCOMPV03202512/29/2025
Goswami, Partha, Genter, David Paul, Abdul Hamid, Umar Zakir, Razdan, Rahul, Khan, Samir
Commercial Vehicles: Vol. 2EPRCOMPV05202512/29/2025
Hsu, Tsung-Ming, Muelaner, Jody Emlyn
Chinese Standard Typical Traffic Participant Characteristic Parameters Model Library Construction Technology2025-99-021012/23/2025
In the context of the automotive industry’s rapid evolution, traffic safety has become a top priority. Automobile active safety technology has shown great potential in reducing traffic accidents. Soft targets in intelligent vehicle testing play a pivotal role in assessing active safety performance. However, these targets are designed according to standards set by European and American countries, which may not fully reflect China’s needs. The study’s objective is to design a library of pedestrian parameter models that meet Chinese standards. It began with the design of a representative pedestrian target, created using Chinese body size parameters and data. An experimental investigation was then conducted to determine the radar characteristics of pedestrian targets. A comparative analysis was performed with reference products. The study led to the creation of a model library for pedestrian targets, following the Chinese standard. It was formulated using experimental data and standards.
Tian, Xinpeng, Guo, Juwei, Chen, Xingyu, Zhang, Jie, Zhang, Xin, Wang, Ke
Trajectory Reconstruction at Signalized Intersections in a Vehicle-to-Infrastructure Environment2025-99-021712/23/2025
Vehicle trajectories encapsulate critical spatial-temporal information essential for traffic state estimation, congestion analysis, and operational parameter optimization. In a Vehicle-to-Infrastructure (V2I) environment, connected automated vehicles (CAVs) not only continuously transmit their own real-time trajectory data but also utilize onboard sensors to perceive and estimate the motion states of surrounding regular vehicles (RVs) within a defined communication range. These multi-source data streams, when integrated with fixed infrastructure-based detectors such as speed cameras at intersections, create a robust foundation for reconstructing full-sample vehicle trajectories, thereby addressing data sparsity issues caused by incomplete CAV penetration. Building upon classical car-following (CF) theory, this study introduces a novel trajectory reconstruction framework that fuses CAV-generated trajectories and infrastructure-based speed detection data. The proposed method specifically
Bai, Wei, Fu, Chengxin, Yao, Zhihong
Intelligent Vehicle Longitudinal and Lateral Cooperative Tracking Control Based on Feed-Forward Compensation and Error Model2025-99-031912/17/2025
The cooperation between the longitudinal and lateral control enables the vehicle to accurately and stably follow the target trajectory, allowing the vehicle to perform basic operations such as speed adjustment, headway maintenance, lane-changing, and overtaking during the driving process. Based on the dynamics model, the lateral and longitudinal control models of the vehicle are presented in this paper. In the lateral LQR control model, the feed-forward compensation is added to reduce the steady-state error of the system. In the longitudinal PID control model, a PID control strategy based on position and speed is set. Using the CarSim and Simulink software, a co-simulation platform is established. Through the comparison of co-simulation analysis under various working conditions, it is demonstrated that the designed controller achieves satisfactory tracking control performance under different vehicle speed conditions. The results also show that the designed control model has a good
Liu, Jinwei, Wang, Yiping, Qi, Fei, Mao, Jiang, Wang, Xudong
AVSC Information Report on Automated Driving System-Dedicated Vehicle (ADS-DV) Stopped ConditionsAVSC-I-06-202512/11/2025
AVSC Information Report on Automated Driving System-Dedicated Vehicle (ADS-DV) Stopped Conditions provides a taxonomy of stopped conditions and definitions of key terms and concepts that can support stakeholder discussions around these topics. By offering guidance on appropriate use of terminology related to ADS-DV stops, this report clarifies complex technical concepts and contributes to a more unified understanding across the industry.
Automated Vehicle Safety Consortium
A Cooperative Conflict-Free Algorithm for Autonomous Vehicles at Unsignalized Intersections Based on Incremental Learning Monte Carlo Tree Search2025-99-043412/10/2025
The paper examines how connected automated vehicles (CAVs) can navigate unsignalized intersections—especially those where major roads differ significantly from minor roads. The proposed method uses an improved incremental learning Monte Carlo Tree Search to quickly determine an optimal passing order for vehicles, adjusting in real time based on road conditions and vehicle states. Numerical experiments demonstrate that this approach achieves conflict-free, real-time cooperative, reducing average delays significantly compared to traditional traffic signal control. Compared to fully-actuated signal control, the proposed method achieves average delay reductions of 19.92s, 16.46s, and 15.47s for CAVs across varying demand patterns. The practical application of this research lies in its potential to enhance traffic efficiency in urban areas by replacing traditional signal-based control with intelligent, autonomous intersection management. This could lead to reduced congestion, lower fuel
Xue, Yongjie, Gao, Feng, Feng, Qiang, Cui, Shaohua
Items per page:
1 – 50 of 711