Browse Topic: Automated vehicles

Items (1,017)
In this paper, a safety-space-based hierarchical speed control strategy for high-speed vehicle-pedestrian conflict scenario is proposed. In this study, we call high-speed conflict scenario a transient interaction event in which the vehicle that is in the operation of relatively high speed and the crossing pedestrian may be in the same conflict point in the limited time-space margin. For such risk characterization, the spatiotemporal conflict model is established and the safety-space indicator with the incorporation of the braking demand and the time-to-arrival difference is defined. Then, based on the remaining safety space and the vehicle-pedestrian arrival-time gap at the conflict point, the conflict risk is classified into four levels, and the corresponding hierarchical speed control rules are designed. A VISSIM-based simulation scenario is constructed and the proposed method is compared with No Control and Fixed Deceleration benchmark strategy in terms of the safety, efficiency and smoothness. The results show that, in the simulated scenarios, the proposed strategy can improve the safety-efficiency balance by increasing minimum safety distance, suppressing high risk states, and reducing the unnecessary severe braking compared with the benchmark strategy. The proposed framework provides a preliminary methodological reference for active speed control for high speed vehicle-pedestrian interaction.
Guo, Jing, Wang, Jiaming, Qin, Wei, Shen, Mengyi
Forming connected and automated vehicle (CAV) platoons before a signalized intersection can substantially increase green-window throughput, yet existing platoon-formation methods target freeways and ignore signal-phase deadlines, while intersection-oriented studies optimise trajectories without addressing the cross-lane gathering process. This study develops a CPS-based, two-layer cooperative control framework to facilitate CAV platooning in the near-signal zones of mixed traffic. At the upper layer, the Signal-Aware Formation Planner (SAFP) evaluates the potential throughput gain of platooning during a given green-light window. It initiates formation only if the expected throughput improvement exceeds a specific threshold. Furthermore, a closed-loop feedback link with the trajectory layer allows the SAFP to adjust plans in real time if a lane change fails. The lower layer jointly optimises the longitudinal accelerations of all platoon-candidate CAVs through a single quadratic program (QP) that explicitly couples inter-vehicle spacing errors—structurally distinguishing it from per-vehicle MPC—while a signal-deadline-aware adaptive weighting strategy modulates the formation-urgency versus traffic-efficiency trade-off in real time. This study evaluated the proposed method using SUMO simulations across various CAV penetration rates (20%–80%) and traffic demands (600–1800 veh/h). Compared to a no-control baseline, our approach reduces average travel delays by 12%–23% and increases throughput by up to 12.9% under congested conditions. Additionally, it achieves platoon formation success rates of 14%–42%, while effectively maintaining safety and cutting fuel consumption by up to 6.1%.
Zhao, Guopeng
In expressway work zones, lane closures drastically lower the level of service (LOS) of road segments, resulting in transient bottlenecks that jeopardize traffic safety and network efficiency. A workable technique that can quickly and effectively forecast LOS in dynamic work-zone contexts is desperately needed to support scientific and effective traffic-diversion planning. This paper suggests an integrated prediction system that combines ensemble learning with microscopic traffic simulation. First, the VISSIM platform was used to create a high-fidelity simulation experiment matrix. The intended speed distribution was calibrated using field data to make sure the model accurately depicts the features of a genuine highway. The simulated speed distribution was similar with observed traffic, according to the findings of the Kolmogorov–Smirnov (K–S) test (D=0.038, p>0.05) and a Pearson correlation coefficient of 0.70.Five major influencing factors—heavy vehicle fraction (10%–40%), pre-construction traffic volume (25,000–100,000 pcu/d), number of lanes (2–5), speed restrictions (60–120 km/h), and work-zone lengths (1,000–4,000 m)—were combined to create 1,024 distinct work-zone scenarios. In order to capture intricate nonlinear coupling relationships, a Stacking ensemble prediction model was then created with XGBoost as the main learner with Support Vector Machine (SVM) and Random Forest (RF) as supplements. The suggested ensemble model performs noticeably better than single-algorithm approaches, according to experimental results. The model significantly outperformed the baseline XGBoost model’s accuracy of 72.75% on the test set, with an overall accuracy of 88.57%, a recall of 88.09%, and an F1-score of 87.85%.The model’s excellent generalization ability and dependability as a quantitative instrument for comparing traffic organization schemes and assessing the efficacy of pre-construction diversion methods are demonstrated via case validation.
Wang, Le, Jiang, Ruisen, Zhang, Guanghui, Li, Yangyang, Zhang, Mingbo, Wang, Yajie
Given the limited adaptability of conventional single-model model predictive control (MPC) to the complex driving conditions encountered by intelligent vehicles on varying road surfaces, as well as the trade-off between modeling accuracy and computational efficiency, this study proposes an adaptive multi-model-switching MPC strategy for trajectory tracking control. First, three prediction models with different levels of complexity are developed, including a kinematic model, a linear two-degree-of-freedom (2-DOF) dynamic model, and a nonlinear tire dynamic model. A model-switching mechanism based on vehicle speed, road curvature, and road-surface friction is then designed to select the appropriate prediction model according to the prevailing driving conditions. In addition, a lateral-deviation feedback correction strategy is introduced to further improve tracking accuracy and smooth the steering response. Finally, joint simulations using MATLAB/Simulink and CarSim are conducted under four representative driving scenarios. The results show that, compared with conventional single-model MPC, the proposed strategy effectively reduces lateral tracking errors and steering-angle fluctuations while maintaining favorable computational efficiency and vehicle stability. These results demonstrate the potential of the proposed method to achieve accurate and robust trajectory tracking for intelligent vehicles under complex and varying operating conditions.
Lai, Fei, Sun, Junhao, Huang, Chaoqun
This paper proposes a distributed cooperative control framework to address the stability control problem of connected and automated vehicle (CAV) platoons encountering external cut-in vehicles. To maintain platoon cohesion under cut-in scenarios, an active topology reconfiguration approach based on both the predecessor-following (PF) topology and the leader-following (LF) topology is first designed. By designating the first vehicle behind the cut-in vehicle as the new leader and combining with the LF topology, it is ensured that vehicles ahead of the cut-in can access the state information of those behind it, thereby maintaining platoon cohesion. Secondly, a model predictive control system is developed to adapt to the topology changes. Its prediction model, optimization objectives, and safety constraints can all be switched according to the topology, ensuring both platoon cohesion and operational safety. Simulation results demonstrate that the proposed strategy effectively suppresses oscillations in inter-vehicle spacing and speed fluctuations caused by the cut-in vehicle, enabling rapid recovery and smooth control of the platoon, and performs significantly better than static topology strategies. This provides a reliable solution for cooperative platoon control in dynamic traffic environments.
Yao, Yuan, Yang, Lei, Liu, Yafei, Liu, Fan, Sun, Zhanbo
The track irregularity has an important influence on the comfort, noise, and safety of the vehicle. At present, track unevenness is still measured using a track inspection trolley and other equipment, which is less efficient. In order to measure the track roughness on the existing operation lines, an evaluation method of track roughness based on inertial reference is proposed, and the method of calculating track roughness through the acceleration signal of the existing vehicle axle box is studied. The track roughness is obtained by integrating the acceleration signal twice in the time and frequency domains, respectively, and the simulation signal is established for theoretical verification, which is verified by experiments using the acceleration signal of an intelligent vehicle axle box. The analog signal is used for theoretical verification, and the axle box acceleration signal of the intelligent locomotive and rolling stock is used for experimental verification. The experimental results show that the axle-box acceleration signal of the rail vehicle can accurately reflect the characteristics of track unevenness, and at the same time, after removing the zero drift of the sensor and the trend term generated in the integration process, the calculation results of the two methods are highly consistent, which is of great significance for the state assessment of the rail line.
Li, Hailong, Hong, Zhi, Wang, Peng
As automotive architectures evolve toward Software Defined Vehicles (SDVs) and high levels of driving automation, traditional safety analysis techniques rooted in hardware reliability require significant adaptation. The Classical Event Tree Analysis (ETA), a cornerstone of ISO 26262 functional safety compliance, relies on static, binary branching logic where each function either fails or succeeds. While highly interpretable and effective for modelling random hardware failures, classical ETA struggles to capture the dynamic, non-linear interactions, temporal degradation, and complex human-machine interface (HMI) dependencies that are characteristic of modern Advanced Driver Assistance Systems (ADAS) and autonomous vehicles. This paper proposes State Dependent Event Tree Analysis (SD-ETA), a methodological extension designed to integrate discrete state vectors and temporal dependencies into the classical ETA framework. SD-ETA assigns probabilities to the branches for the dynamic nonlinear interactions, temporal degradation, and complex human-machine interface (HMI) dependencies instead of binary values, thereby allowing the system state (comprising vehicle physics, environmental conditions, and driver attention metrics) to dynamically update based on the outcomes of the preceding nodes. This approach retains the visual hierarchy and regulatory familiarity of standard event trees while significantly enhancing model fidelity for Safety of the Intended Functionality (SOTIF) scenarios governed by ISO 21448. To demonstrate the necessity and utility of this methodological evolution, this paper presents a comparative case study analysing a system operating under degraded environmental conditions. The quantitative application reveals that while classical ETA predicted a relatively low collision risk by treating sensor performance as a static binary state, the dynamic SD-ETA simulation exposed a critical hidden safety gap, calculating a higher collision probability due to compounded latency and degraded physical operating parameters. Ultimately, SD-ETA equips safety practitioners and automotive regulators with a modernized, time-aware framework to accurately evaluate the complex, interacting risks of autonomous systems without sacrificing the transparency required for rigorous safety certification.
Sharma, Dhiraj Mohan, Mutagi, Megha, Reddy, Kakarla Subba
Traffic oscillations degrade the operational efficiency and safety of vehicular platoons. This study proposes a predecessor-following platoon with periodically assigned feedback gains and investigates its frequency-selective disturbance attenuation mechanism. An auxiliary second-order undamped periodic model is first established, and the Bloch–Floquet formulation is used to derive the nominal dispersion relation and bandgap boundaries. Closed-loop disturbance attenuation is then evaluated separately using spacing-error transfer matrices that retain positive velocity feedback and actuator-response lag. Frequency-domain transmission analysis and time-domain simulations show that, under nominal homogeneous and fully controllable connected and automated vehicle (CAV) assumptions, the periodic gain configuration creates tunable attenuation bands and provides stronger downstream attenuation than a homogeneous-gain configuration. The results clarify the relationship among periodic gain assignment, bandgap formation, periodic-cell string stability, and finite-length traffic-wave suppression. The effects of vehicle heterogeneity, sensing delay, and mixed traffic remain topics for future investigation.
Yang, Xiujian, Fan, Yanwen, Zhuang, Qingyuan, Qiao, Feiyu
It is still difficult to reproduce the low-Earth-orbit (LEO) networking experiments since the experimental settings are scattered and the Large Language Model (LLM) assisted workflow is laborious and needs to be refined by manually crafting the prompt, transferring the code and debugging. Existing retrieval-assisted pipelines still demand substantial human effort for parameter inference and code repair, particularly given the precise alignment required for LEO topology, constellation, and simulator configurations. This paper presents LASERAgent, a highly automated agent system for LEO networking experiment reproduction. Unlike retrieval-assisted pipelines that mainly support evidence retrieval and code generation, LASERAgent organizes the downstream workflow into a bounded pipeline of retrieve - extract - generate - check - execute, integrating structured parameter extraction, template-guided generation, deterministic validation, controlled execution, and limited retry. Preliminary results show that LASERAgent reduces required human interventions by roughly half while improving result consistency over prior retrieval-assisted workflows, and that the validation stage plays an important role in reliable automation.
Tian, Siyu, Wei, Guangyu, He, Xiongwen, Liu, Donghua, Ma, Yue, Zhan, Yuheng, Xia, Lang
Proactive safety and vehicle automation typically requires high energy use from sensors and energy-intensive computing from sensor data processing. For high-quality, reliable perception and localization within a driving environment at the vehicle level, incoming data from multiple sensors need to be fused using advanced computational algorithms, which demand a high compute load. Alternatively, computational offloading of automated driving tasks shifts energy consumption from the vehicle to cloud infrastructure, where renewable energy sources, such as hydropower or solar power, can be utilized more efficiently. Herein, an optimal scheduling strategy for autonomous driving tasks via the cloud layer is formulated as a mixed-integer linear programming (MILP) problem and verified using measurement-informed task graphs. It is shown that cloud-based computational offloading enables energy-efficient operation while maintaining task deadlines to ensure the timely availability of perception and localization information, which is consistent with prior studies in the literature. Simulation results demonstrate that on average, 35.78% of the computational load was offloaded to the cloud, which can achieve significant energy savings for the onboard system. The compute operations achieved an average energy savings of 35.65%, while total system savings ranged from 26.16% to 30.67% under different cloud energy efficiency scenarios, highlighting the advantages of offloading compute-intensive tasks. The framework was further evaluated using multiple directed acyclic graph (DAG) configurations to assess its scalability and adaptability. Critical tasks, such as sensor fusion, were executed exclusively on the vehicle to ensure real-time responsiveness.
Sharma, Sachin, Meyer, Richard, Feinberg, Ben, Asher, Zachary
The form changes of vehicles directly affect their driving performance, terrain adaptability, and motion efficiency. Conventional path planning techniques are unable to address the unique needs of irregularly shaped vehicles. Consequently, a hierarchical path planning algorithm that takes configuration changes into account is introduced. By introducing a pattern decision-making mechanism, the path planning process is divided into multiple levels. According to the task requirements and environmental conditions, the vehicle configuration is dynamically selected, and the driving path is optimized for the driving characteristics under different configurations, thereby fully utilizing the adaptability and through capability of the vehicle.
Chen, Zixuan, Pi, Dawei, Li, Guangda, Zhou, Yulin
Traffic flow environment testing is indispensable in the research and evaluation process of intelligent vehicles. However, the current vehicle evaluation systems mostly focus on simple dynamic scenarios and lack a comprehensive assessment of vehicle performance in complex traffic flow environments. In view of this, this paper constructs a multi-dimensional comprehensive performance evaluation system for vehicles in traffic flow environments. Firstly, based on the randomness and dynamics of traffic flow, four core evaluation dimensions covering safety, comfort, efficiency, and economy are constructed. In terms of security, the collision time and Predicted Safety Metrics are adopted. This enables the dual quantification of immediate collision risks and dynamic obstacle avoidance capabilities. The comfort evaluation focuses on the impact of vibration frequency on the human body and constructs a graded quantitative index. Efficiency and economy evaluation models are built through time cost and energy consumption cost. The verification is carried out under different traffic flow scenarios, and the final results demonstrate the consistency between the evaluation method of this paper and the expert evaluation method, thereby verifying the rationality of the evaluation system presented in this paper.
Wang, Guangyu, Song, Shiping, Zhang, Cheng, Qu, Ge, Yu, Xiaojun
Despite a distinct lack of superheroes, the automated driving community scored big victories in San Diego at the end of July. The annual Automated Transportation Symposium opened just as the massive pop culture event that is ComicCon was leaving town. Iron Man and Aang stared out from nearby billboards as the conference tackled announcements regarding Zoox, changing automated vehicle regulations, and repeated discussions on how AVs need to improve interactions with first responders.
Blanco, Sebastian
Engineer them to identical and tough specs all you want; autonomous vehicles are unlikely to drive the same way everywhere. They may all have the same technical capabilities, but this world is too messy for an AV engineer in San Francisco to be working on the same problems as one in Amsterdam. These global differences were front and center at the recebt 2026 SAE Automated Transportation Symposium (see more on page 11). I came away with renewed excitement about automated driving technology, given the real-world impact AVs are already making. Reports from Waymo, Kodiak and Uber and others all the way down prove the technology is working. But uccessful deployment depends on more than vehicle technology.
Blanco, Sebastian
The safety and reliability of autonomous vehicles are critically linked to network communication quality. Consequently, threats such as Denial-of-Service attacks pose significant risks by disrupting communication between essential components and jeopardizing driving safety. This article presents a robust trajectory tracking control method resilient to such attacks. Utilizing a Linear Parameter–Varying control framework, the method effectively addresses time-varying vehicle speeds and incorporates a norm-bounded strategy to manage tire behavior uncertainties. By employing a Static Output-Feedback scheme, it avoids the need of costly sensors while maintaining a straightforward control structure suitable for real-time implementation. Using Lyapunov’s method, we analyze the system stability under attack conditions, ensuring the controller remains robust against disturbances. The design of the resilient controller is formulated as a convex optimization problem with Linear Matrix Inequalities constraints. The effectiveness of the proposed controller is validated through co-simulation in MATLAB/CarSim®, where it outperforms several state-of-the-art controllers across different driving scenarios, maintaining consistent tracking performance despite varying attack severity levels.
Meléndez-Useros, Miguel, Viadero-Monasterio, Fernando, Nguyen, Anh-Tu, López-Boada, María Jesús
A dispatch from the automaker's “let's just try it” city finds hydrogen fuel cells, automated parking robots, and a robust spirit of innovation. For a planned high-tech community created by an automaker, Woven City is not laser-focused on automobiles and transportation. In fact, to get a glimpse of Toyota's priorities here, look to the pedestrian stoplights at intersections. They remain a constant green, until the connected city senses an approaching vehicle and turns them red. This focus on pedestrians over vehicles is one small part of Toyota's rebranding as a mobility company. Toyota announced Woven City at CES 2020, converting its recently closed Higashi-Fuji factory, which built over 7.5 million Toyota vehicles during a 53-year run, into a blank slate for new technologies, automotive and otherwise.
Blanco, Sebastian
Connected and Automated Vehicles (CAVs) represent a transformative innovation poised to revolutionize roadway transportation by leveraging automated driving systems equipped with advanced sensors, high-performance computing, and communication technologies. While urban areas are the primary focus of current CAV developments, rural transportation systems risk being left behind despite the significant benefits that CAVs can bring to these regions. This article, therefore, explores the physical and digital infrastructure requirements for the safe deployment of CAVs in rural areas, drawing insights from standards, recommendations, and guidelines developed by leading standard organizations. The study highlights the specific design of physical infrastructure, including traffic signs, traffic signals, and pavement markings, and digital infrastructure, including communication, sensing, and mapping, to ensure rural communities are effectively prepared to benefit from the potential of CAVs. As its primary contribution, this article provides a comprehensive review of existing standards and guidelines relevant to rural CAV deployment. By synthesizing guidance across multiple standard-setting organizations, this review delivers a structured analytical assessment of existing standards, revealing their limitations and misalignment with rural transportation contexts while highlighting emerging good practices. The article clarifies the applicability of current guidance to rural infrastructure, identifies systemic infrastructure-related failure modes, and informs context-aware planning considerations for efficient and scalable CAV deployment in rural areas.
Zakaria, Mohammed, Getahun, Tesfamichael, Tavasoli, Mahsa, Pandey, Venktesh, Sarrafzadeh, Abdolhossein, Karimoddini, Ali
North American CAV Performance Data StandardWP-00157/22/2026
As the deployment of connected and automated vehicles (CAVs) expands, the need for a consistent, cross-industry approach to performance relevant CAV data exchange is becoming more pressing. Vehicle developers, infrastructure owners and operators (IOOs), and technology providers generate and consume data that support safety, mobility, and operational efficiency, yet much of the data remains fragmented, inconsistently formatted, and difficult to reuse across systems. To address these gaps, the Society of Automotive Engineers (SAE) and the Canadian Standards Association (CSA) convened a multi-stakeholder workshop on November 3, 2025, with participants representing original equipment manufacturers (OEMs), automated driving system (ADS) developers, state and local agencies, standards bodies, and technology partners. The workshop focused on identifying challenges, clarifying needs, and outlining a path toward a North American CAV Performance Data Standard. Key themes from the workshop included: -The need for a shared data language to support safe and interoperable CAV operations. -The lack of consistent formatting, labeling and visibility regarding who produces and consumes data. -A “start small, iterate and scale” approach beginning with well-defined use cases. -The need for technical harmonization and governance structures that build trust and support sustained coordination. This white paper summarizes the key findings and outlines a practical approach to developing a Version 0.1 base-layer data standard that can support measurable progress in 2026 and beyond.
Nesheli, Mahmood
The development and validation of advanced driver-assistance systems (ADAS) and automated driving systems (ADS) are shifting from traditional linear V-model processes toward more iterative engineering cycles. Despite faster iteration, these safety-critical systems remain subject to stringent regulations. Standards and guidance, including UNECE UN Regulation No. 157 and ISO/TS 5083, emphasize traceability, transparency, and explainability throughout development and validation. Nevertheless, as ADAS/ADS are developed and validated in faster, more iterative release cycles, additional stakeholders become involved and new explainability requirements emerge. These requirements vary between stakeholders and across development, validation, and post-market deployment phases, yet they are not systematically captured in the current state of research and practice. Therefore, to ensure that explainability supports rapid iteration, it is essential to identify relevant stakeholders and specify their explainability needs. Standards such as IEEE Standard 7001-2021 provide a broad foundation for transparency in autonomous systems. However, their generic nature does not address the domain-specific complexities of ADAS/ADS. Furthermore, a conceptual gap remains between general transparency principles and explainability requirements in automotive development and validation. Building on IEEE Standard 7001-2021, this paper first offers a stakeholder taxonomy in the context of ADAS/ADS, then proposes a stakeholder-oriented analysis of explainability requirements within an automated driving use case and contexts. This analysis specifically focuses on the motivations for requiring explainability and the necessary explanation modalities. Finally, the paper discusses the limitations of the analysis and outlines directions for future research. The results of the paper provide a structured guideline for stakeholder-oriented explainability requirements in ADAS/ADS.
Liu, Xuanheng, Bairy, Akhila, Paudel, Bijay, Adolph, Laurenz, Heck, Melanie, Hettich, Lennard, Nägele, Ann-Therese, Rudolf, Korbinian, Bause, Katharina, Düser, Tobias, Schwammberger, Maike
The UMV Peoplemover 2+2 is part of a modular vehicle family (Urban Modular Vehicle) that includes derivatives for passenger and cargo transport in urban environments. The platform supports automated movers as well as conventionally controlled vehicles with a human driver, ensuring high flexibility across applications. The modular platform enables the extensive use of common parts, allowing the efficient and cost-effective realization of multiple vehicle variants. The increased share of common parts also improves sustainability by reducing derivative-specific parts, material usage, and production complexity. A drivable demonstrator of the UMV Peoplemover 2+2 has already been realized. The vehicle is designed for the automated transport of up to four occupants in a 2+2 vis-à-vis seating arrangement and is targeted at demand-oriented shuttle services. While the drivable demonstrator validated the proof of concept, it lacked the core Level 4 hardware and software stack for automated driving functions. To address this limitation, we deployed a software-defined vehicle architecture to the concept. This paper introduces the novel e/e-architecture and software stack enabling the Peoplemover 2+2 to initiate its first shuttle service at the German Aerospace Center (DLR e.V.) in Stuttgart. We further detail the deployed multi-modal sensor suite, comprising modern solid-state LiDARs and a 4D imaging radar, which were carefully selected to meet the operational design domain requirements while also serving as a versatile research platform for future advanced perception studies. Finally, we analyze the SDV-based modular software stack, which facilitates rapid application development through straightforward switching between commercial, open-source, and in-house software domains, and supports parallel execution of domain-specific functions across all three software sources.
Pohl, Eric, Schmid, Fabian, Münster, Marco, Siefkes, Tjark, Stuebler, Tillmann, Mohammed, Shawan
Automated Vehicle Marshalling (AVM) is the first functionally safe Level 4 automated driving system. It consists of the wireless control of unoccupied vehicles at low speed in well-defined environments, such as parking facilities or manufacturing plants. The driverless operation in an AVM system is achieved by transmitting control messages between connected vehicles and intelligent infrastructure. Similar to other wireless applications, network reliability poses a major challenge to ensuring safe automated driving. An AVM system must provide uninterrupted communication between the vehicle and the infrastructure at a stable frequency. However, wireless systems usually suffer from varying latencies and network disturbances. In this context, international organizations and automotive industry contributors have defined requirements specifying network performance, communication interfaces, and message formats for different AVM use cases. These requirements cover communication aspects without involving core automated driving functions, such as vehicle motion control, which are also decisive in ensuring the safety of the overall system. Therefore, studying communication factors in combination with vehicle motion control offers better interpretability of system capabilities. In this work, we investigate the trade-off between communication specifications and vehicle lateral control within an AVM framework implemented on a real vehicle. We aim to address the limitations that may arise under real-world AVM driving conditions. First, we revisit the current technical specifications to highlight the specific AVM messages relevant to vehicle lateral control. Then, we propose a testing framework by establishing communication with the test vehicle over a Wi-Fi network using multiple access points deployed across an indoor parking facility and an outdoor test track. Thus, we obtain a quantitative analysis of network factors, such as latency, in different driving environments. In the next step, we present a Model Predictive Control (MPC) approach that uses the AVM control messages to achieve robust vehicle lateral control. By evaluating the control performance under communication conditions, we assess the impact of network latency on vehicle lateral control. This work provides a baseline for exploring the limitations of AVM and deriving potential optimizations.
Mejri, Mohamed Amine, Münchhausen, Henrik, Flormann, Maximilian, Sturm, Axel, Henze, Roman
As automation advances and occupants transition from active drivers to passive passengers, understanding how automated driving behavior is evaluated becomes increasingly important. While longitudinal and lateral vehicle dynamics are known to influence perceived comfort and safety, it remains unclear to what extent motion–perception relationships remain stable across urban traffic contexts. This study compares two real-world investigations of automated driving: a left-turn maneuver at a signalized intersection on a test track and a roundabout maneuver with a shuttle in public traffic. Both datasets include high-resolution vehicle dynamics and structured subjective ratings. A consistent objectification approach was applied to examine the transferability of motion–perception relationships across contexts. However, differences in vehicle platform, automation level, trajectory characteristics, and study design limit direct comparability and require cautious interpretation. Despite partially overlapping ranges in selected peak-based dynamic parameters, such as longitudinal acceleration, subjective comfort and safety ratings were consistently higher in the roundabout scenario. Furthermore, strong associations were observed between motion parameters and subjective evaluations in the intersection context (adj. R2 up to 0.891), whereas objective parameters showed only limited explanatory power in the roundabout scenario (adj. R2 ≤ 0.06). The results indicate that motion–perception relationships derived within a specific context may not be directly transferable across different traffic scenarios. The findings highlight limitations of globally derived motion-based evaluation models and underline the importance of validating objectification approaches across diverse operational environments.
Panzer, Anna, Strenge, Emma, Iatropoulos, Jannes, Henze, Roman
Trajectory tracking control and vehicle state estimation are core functionalities of highly automated vehicles and must operate reliably under strict real-time constraints as well as in the presence of model uncertainties and limited sensor availability. This paper presents an integrated, real-time capable framework for trajectory tracking control and vehicle state estimation, developed within the UShift II research project and implemented on the highly automated vehicle platform. The framework combines nonlinear model predictive control (NMPC) for trajectory tracking with an extended Kalman filter (EKF) for multi-sensor state estimation within a modular system architecture. The NMPC is based on a vehicle model designed for low-speed automated driving maneuvers and explicitly accounts for actuator constraints. Trajectories are tracked based on local planned reference trajectories while ensuring smooth and physically feasible control inputs for underlying control. The EKF fuses measurements from global navigation satellite system (GNSS), inertial sensors, and wheel-speed-based odometry, providing consistent estimates of the vehicle states under varying sensor availability. Particular emphasis is placed on robustness and computational efficiency in order to meet the real-time execution requirements on the target hardware. The complete framework is implemented on automotive-grade real-time hardware and validated on the U-Shift II vehicle platform. Experimental results demonstrate reliable localization performance, smooth and accurate trajectory tracking, and deterministic real-time execution, confirming the suitability of the proposed approach for practical low-speed automated driving applications.
Fuchs, Sören, Neubeck, Jens, Wagner, Andreas
Electrical/Electronic Architectures (EEAs) are continuously evolving to meet newly emerging demands. In recent years, major drivers of this evolution have been the increasing software-defined nature of vehicles and the push toward automated driving. Key technologies such as edge-enhanced functions, vehicle-to-vehicle communication, and service-oriented architectures are therefore the focus of current research efforts. This paper presents a vision of how these technologies can be used to enable cooperation between vehicles, illustrated by using parked vehicles as edge nodes. These are typically seen as obstructions, as they significantly increase the risk of missing or misinterpreting vulnerable road users such as pedestrians or cyclists. Our proposed approach to counteract this problem is the use of the parked vehicles themselves as edge nodes that support object detection or even trajectory planning. Current research primarily considers smart traffic infrastructure, roadside units, and other vehicles as potential edge nodes. Including parked vehicles as edge nodes means that, instead of acting solely as obstacles, we leverage their built-in sensors to contribute to cooperative awareness. While such cooperation will enhance the safety of automated vehicles in urban areas, several challenges arise. In this paper, we discuss how data traceability, decision-making in the presence of conflicting information, and incentive mechanisms for owners of parked vehicles can be addressed. Based on these challenges, the paper outlines requirements for future cooperative architecture and highlights the role of edge-enhanced functions, Vehicle-to-Vehicle (V2V) communication, and service-oriented architectures in enabling fully automated driving.
Lüntzel, Vitus, Lukezic, Nikola, Kraus, David, Seidel, Luca, Beck, Maximilian, Schindewolf, Marc, Sax, Eric
This article presents a cross-layer framework that integrates realistic vehicle-to-network-to-vehicle (V2N2V) delay characterization with a rigorous stability analysis of automated vehicle steering control. Both constant and network-induced time-varying delays modeled via deterministic bounds are addressed. For constant delays, delay-independent stability regions within the controller gain space are analytically derived. For time-varying delays with stochastic network origins, modeled using deterministic bounds, a refined Lyapunov–Krasovskii functional (LKF) incorporating augmented single- and double-integral terms is constructed. To establish delay-dependent linear matrix inequality (LMI) conditions, a reciprocally convex combination approach is employed to handle the delay interval partitioning, and the second-order Bessel–Legendre inequality is applied to tighten the integral quadratic bounds. The resulting LMI conditions explicitly capture the coupled effects of delay magnitude, delay variation rate, and control gains on closed-loop stability. Simulations of a lane-keeping scenario confirm that the predicted stability boundaries accurately match the closed-loop system behavior. Notably, incorporating a realistic time-varying V2N2V delay profile into the controller design reduces the lateral-state root-mean-square error (RMSE) by over 54% and decreases the settling time by a factor of 10 compared to designs relying on an average-delay assumption. However, high packet loss rates are shown to still induce residual oscillations due to information scarcity. Ultimately, these results elucidate delay-induced instability mechanisms and provide practical guidelines for designing delay-robust steering controllers for connected and automated vehicles.
Li, Jialin, Lu, Jianwei, Wei, Heng, Ao, Di
Sound source localization is a fundamental capability for environmental awareness in a wide range of applications, including automotive or automated vehicles. Microphone-array-based signal processing techniques are widely used for this task. However, achieving sufficient localization accuracy often requires a large number of microphones and wide array apertures, which can be incompatible with limited installation space and cost constraints. Moreover, standard array-processing methods often rely on free-field transfer functions. In environments with reflections, diffraction, and scattering, particularly under non-line-of-sight conditions, this mismatch can degrade both accuracy and interpretability. This paper presents a methodology for sound source localization in partially known environments that addresses these challenges by combining two ideas. First, the method reduces sensor requirements by exploiting sequential pressure measurements acquired at different spatial locations along a moving receiver trajectory. Second, environmental effects are incorporated through an approximate acoustic model derived from rough geometric cues assumed to be retrievable from visual sensing modalities. Geometric and acoustic parameters are treated as unknowns and estimated jointly with the source location, reducing the need for precise prior environmental knowledge. Numerical simulations validate the approach in two representative scenarios: (i) a single source in the presence of a wall with unknown absorbing properties and unknown distance, and (ii) a T-junction configuration where the source is not in direct line of sight. The case studies establish proof-of-concept feasibility and highlight the potential of jointly leveraging single or dual sequential measurements and approximate environmental information while maintaining low modeling and computational complexity.
Pirro, Giovanni Battista, Nijman, Eugene, Deckers, Elke, Denayer, Hervé
The vibro-acoustic performance of a vehicle is a critical factor in customer perception of quality and comfort, yet optimizing for Noise, Vibration, and Harshness (NVH)—specifically road noise—presents a persistent challenge in the modern automotive development cycle. While advanced Finite Element Method (FEM) analysis is essential, the increasing complexity and volume of CAE simulation data often overwhelm manual interpretation, potentially leading to prolonged development times or compromises in final comfort quality. To address these challenges, this paper introduces the application of CDH/ACE (Autonomous Computational Experiments), a framework that integrates conventional CAE simulation workflows with advanced machine learning in an iterative, cyclic process. This creates an exceptionally user-friendly and self-correcting system that autonomously defines, performs, and learns from computational experiments. By leveraging machine learning algorithms to build robust predictive models from simulation data, the framework intelligently guides design exploration to achieve complex engineering objectives such as design of experiments, multi-objective optimization, and robustness analysis. We demonstrate this methodology through a comprehensive full-vehicle road noise optimization study, detailing the process of defining experiment parameters and configuring acoustic targets within the autonomous learning cycle. The results highlight the effectiveness of this highly automated and intuitive workflow, showing significant reductions in road noise and vehicle mass alongside a substantial decrease in manual engineering effort. Finally, the paper presents the tangible benefits of this approach, assessing current advantages and limitations while providing an outlook on the future application of autonomous, machine-learning-driven methodologies in accelerating modern vehicle development.
Visser, Rene
Framing Rules of the Road Compliance for Driving Automation Systems from an Engineering StandpointDRRC-WP-01-20266/18/2026
Rules of the road were created to enable safe, predictable, and efficient road use by governing both individual vehicle operation and interactions among road users. Driving automation systems must be capable of complying with rules of the road to operate lawfully on public roads. Human drivers often rely on simplified guidance, such as state driver’s handbooks, together with tacit knowledge developed through experience and social norms to generalize behavior across jurisdictions. By contrast, driving automation systems must reasonably and explicitly account for the substantial volume of applicable legal requirements within its operational design domain (ODD). Accordingly, relevant legal requirements must be converted into explicit objective logic that can be utilized by driving automation systems. This paper proposes a method to address how driving behavior-related rules of the road can be consistently applied in engineering practice in a harmonized fashion across industry. Specifically, while rules of the road are expressed in natural language—often with subjective and context-dependent terms—driving automation systems require those rules to be interpreted and translated into unambiguous, testable engineering requirements. To address this, this white paper articulates key challenges and outlines systems-engineering approaches for engineering interpretation of rules of the road and their translation into objective requirements suitable for verification. Validation is also discussed as the process for ensuring that the requirements themselves remain appropriate over time.
Digital Road Rules Consortium
1Systems level and integration testing are an integral part of the design and development of Automated Vehicles (AVs). Measurement science plays a pivotal role in testing to ensure the safe and efficient operation of AVs. This science establishes a common understanding of the units of measurement, crucial in linking human activities. This article describes the significance of measurement in studying interactions between key system technologies in AVs, including AI for perception, sensing, communications, and cybersecurity. To address the complexities of these interactions, a novel, adaptable, and interactive framework called the System Technology Interaction Model (STIM) is introduced. STIM considers both designed and emergent interactions between these system technologies, allowing AV developers to explore tailored experiments with the flexibility of filtering for focused testing. The framework currently models system interactions statically, not in real-time, to define potential relationships and influences during the design phase. The novelty of this framework comes from providing a holistic evaluation that captures testing of interactions between modules in addition to component-level testing, while other frameworks focus on testing individual component behaviors. It also assesses the equality of two interactions, meaning it ensures that two interactions behave the same way for consistent results. Moreover, the framework serves as a valuable tool for AV designers and safety regulators to aid in establishing robust design and assessment approaches. This work highlights the need for a common framework to thoroughly test AVs and gain a holistic understanding of system interactions. Finally, the framework aims to understand how to mitigate potential influences leading to AV malfunctions to advance the development and deployment of safe and reliable Automated Vehicles. The work focuses on level 1 and level 4 automated driving features to simplify the work, although it can be from level 1 to level 5. Although framework performance is inherently difficult to quantify, this framework’s performance can be reflected through its ability to accurately capture system interactions for improved AV design and support a broader usability among AV stakeholders. In the future, the framework can be expanded to include additional elements, such as infrastructure or other vehicles, to analyze information provided to AVs, allowing experts from various domains to collaborate, create similar models, integrate them when feasible, and model the interactions in real-time.
Griffor, Edward R., Arora, Mahima, Kootbally, Zeid, Nguyen, Vinh
This study presents a data-driven approach for strengthening aviation safety by integrating human factors assessment with modern predictive modeling techniques. The work focuses on understanding how human performance, operational conditions, and system-level interactions collectively influence safety risk, and how these interactions can be quantified to support improved design and decision-making. Unlike previous studies that address human factors or predictive modeling in isolation, this research offers a unified framework that links causal human factors indicators with statistical modeling, feature extraction, and machine learning based risk estimation. The novelty of this work lies in the structured pipeline that transforms raw categorical and narrative human factors information into measurable predictors that can be analyzed using structural modeling and machine learning. The methodology includes data preparation, dimensionality reduction, latent pattern discovery, dependence modeling, model training, and interpretability analysis. The study demonstrates how this pipeline uncovers hidden relationships among operational errors, environmental influences, maintenance actions, design considerations, and crew behavior. The findings show that the integrated approach improves the accuracy and stability of risk prediction and highlights specific human factors patterns that consistently contribute to elevated risk levels. These insights support targeted mitigation strategies, inform design improvements, and help prioritize safety interventions. The work concludes that a combined human factors and predictive modeling framework enhances the ability of organizations to identify vulnerabilities earlier, allocate resources more effectively, and strengthen system resilience. This approach is adaptable to diverse aviation contexts and offers a practical path for transforming human factors data into actionable safety intelligence.
Valiyaparambil, Praveen
As automated vehicle technologies enable increased seat recline angles during travel, understanding the biomechanics of injury under these novel occupant postures becomes imperative. This study evaluated the pelvis injury response and associated kinematics of reclined small female post-mortem human surrogates (PMHS) subjected to frontal sled tests across three restraint configurations. Each configuration varied in seat stiffness and the presence of a knee bolster to assess their influence on pelvic dynamics and submarining risk. Nine PMHS tests were conducted using a consistent reclined posture (38° thorax, 75–80° pelvis angle) and production restraint systems. Submarining probability was estimated using a validated logistic regression referenced from previous study. Distinct pelvic kinematics, fracture patterns, and associated injury mechanisms emerged across the test configurations in the current dataset. Configuration 1, featuring a stiffer seat without a knee bolster, exhibited complex pelvic fractures—most notably iliac wing fractures resulting from inward bending of the ilium—and a higher probability of submarining primarily due to rearward pelvic rotation. In contrast, Configuration 2, with a compliant seat and no knee bolster, produced comminuted iliac wing fractures, dominated by shear component and a moderate probability of submarining driven primarily by downward pelvic displacement. Configuration 3, which included a knee bolster, showed injury propagation to the posterior pelvis, and none of the subjects submarined. Each configuration included three specimens; therefore, results should be interpreted with caution. Despite the small sample size, the findings highlight the critical influence of seat stiffness and restraint design on pelvic kinematics and injury mechanisms under reclined conditions. The data provided could serve in validating computational models and anthropomorphic test devices (ATDs) in reclined seating configurations.
Somasundaram, Karthik, Driesslein, Klaus, Pintar, Frank A.
Trajectory tracking control is a core technology in intelligent vehicle autonomous driving systems, directly influencing both driving safety and control accuracy. To overcome the limitations of traditional model predictive control (MPC) in real-time performance under complex operating conditions, as well as the limited robustness of linear quadratic regulators (LQR) against system uncertainties, this article proposes a hybrid iterative LQR–MPC (ILQR-MPC) control strategy. First, a dynamic model of the intelligent vehicle is developed to capture its behavior during high-speed driving and cornering. Next, an ILQR-MPC hybrid framework is designed. By exploiting the rapid iterative optimization capabilities of the ILQR algorithm, an initial control sequence is generated for the MPC, thereby reducing the computational load during MPC’s online rolling-horizon optimization. This approach preserves MPC’s advantages in handling constraints and maintaining robustness against parameter variations and external disturbances. Finally, joint simulations using MATLAB/Simulink and CarSim are conducted to evaluate the proposed approach against conventional MPC under standard road conditions, curved sections, and sudden changes in road friction. The results show that the ILQR-MPC strategy reduces trajectory tracking errors, shortens computational time, and maintains excellent stability and robustness under complex operating conditions.
Lai, Fei, Sun, Junhao, Huang, Chaoqun
Automated Vehicles (AV) pose new challenges in road safety, multimodal interaction, and urban planning, requiring a holistic approach that prioritizes sustainability and protects all road users. The KASSA.AST project addresses this by deploying and evaluating an automated shuttle in southern Austria on three routes. The study area is a Park & Ride zone near a train station, enabling seamless transfers and higher transit use. To assess the safety impacts of the automated shuttle, four Mobility Observation Boxes (MOBs) were deployed. These AI-based systems detect and classify road users, track their trajectories and geospatial coordinates, and identify safety-critical events via Surrogate Safety Measures (SSMs). Over 10 days, a trajectory dataset captured interactions among vehicles and the shuttle. The resulting real-world dataset is a core contribution. This dataset underpins microscopic behavior modeling. Trajectory pairs yield car-following and interaction metrics (relative distance, relative speed, acceleration) to calibrate custom models for realistic mixed traffic. Simulations generate a structured interaction database with time spans, trajectories, conflict points, and SSMs (such as Time-to Collision—TTC, Post-Encroachment Time—PET, and Deceleration-rate-to-avoid-crash—DRAC). These outputs support detailed analysis of shuttle interactions, including near misses. To reveal patterns, clustering identified three interpretable safety-relevant regimes: (i) a low-demand background regime (n = 96) with low speeds and near-zero deceleration demand, (ii) a fast-and-tight regime (n = 33) with reduced TTC, elevated critical-event speeds, and high DRAC/Modified (M)DRAC demand, and (iii) an AV-regulated regime (n = 10) dominated by the shuttle as adversary, showing short TTC but stable moderate speeds (~4 m/s) and conservative headway policies. Ensemble-tree supervised learning reproduced these regimes with high accuracy and revealed that critical-event speeds and counterpart headway are the strongest discriminators, while AV role metadata contributes marginally. This integrated approach—linking field data, behavior modeling, simulation, and machine learning—provides a robust framework for assessing AV safety in urban contexts.
Losada Arias, Ángel, Rosenkranz, Paul, Hula, Andreas, Aleksa, Michael, Saleh, Peter, Erdelean, Isabela
The objective of this research was to understand the impact of transition window duration on success and performance during nominal transitions from conditional driving automation (SAE level 3). Because the driver can be disengaged from driving when conditional driving automation is engaged, the central challenge is how to safely transition from automated control to human control. Past research from the literature on Level 3 Automated Driving Systems (L3 ADS) has focused on safety-critical event responses (e.g., responding to a hazard) and on automation that operates at high speeds, which is not representative of the systems currently deployed that operate in lower-speed traffic jam situations [4, 5]. This article presents an analysis of data from several transition-of-control studies with conditional driving automation in a high-fidelity driving simulator. A range of transition window durations were compared, and different transition-of-control behaviors were coded from video data. Transition windows for 4, 6, 8, and 10 s conditions resulted in failures by the drivers to resume control. Success rates by condition were lowest with 4 s transition windows, but also lower with 10 s windows, compared to 6 s, 8 s, or 15 s windows (potential explanations appear in the discussion). Time to first glance back at the forward road and time to first-hand on the steering wheel were predictors of transition of control success across all transition windows. Survival analyses showed that drivers needed to begin the transition process within a few seconds to make successful transitions, even with longer transition windows. The results demonstrate the impact of different transition window durations on transition of control and provide unique insights into the factors influencing transition success in situations representative of those happening on the road now. These results help shape understanding of the requisite time needed for safe transition from automated to manual control and speak to the design recommendations for human–automation interactions.
Gaspar, John, Ahmad, Omar, Schwarz, Chris, Fincannon, Thomas, Jerome, Christian
SAE TOMORROW TODAY - Building Trust in AV Safety135644/17/2026
As AVs continue to grow in popularity, one question remains top of mind: How do we know autonomous driving systems are genuinely safe? The Automated Vehicle Safety Consortium (AVSC) is an industry collaboration group focused on improving the safe development and deployment of automated driving systems (ADS). By bringing together automakers, technology companies, suppliers, mobility providers, and government stakeholders, the AVSC develops voluntary best practices and technical guidance that fosters public trust and delivers consistent AV safety standards. Listen in as we sit down with Darcyne Foldenauer, Executive Director, AVSC, and Erin McCurry, Principal Engineer, AVSC, to explore two new publications: Best Practice for ADS-DV Assessment of Safety Claims, and the Information Report on ADS-DV Stopped Conditions. From the difference between minimal risk maneuvers and minimal risk conditions, to when it's actually safer for a vehicle to stay stopped in lane, this conversation sheds light on the complex decisions behind automated driving safety. We'd love to hear from you. Share your comments, questions and ideas for future topics and guests to podcast@sae.org. Don't forget to take a moment to follow SAE Tomorrow Today--a podcast where we discuss emerging technology and trends in mobility with the leaders, innovators and strategists making it all happen--and give us a review on your preferred podcasting platform. Follow SAE on LinkedIn, Instagram, Facebook, X, and YouTube. Follow host Grayson Brulte on LinkedIn, X, and Instagram.
Patterson, Lori
This study aimed to evaluate the influence of child anthropometry, seating postures (recline and rotation), seatbelt force limiting, and frontal collision scenarios on the kinematic response and injury risk 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 frontal 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 observed based on the analysis of variance. As the child dimension increases, the risk of head injury decreases showing by HIC15, while the risk of neck and lumbar injuries increases. As the seatback angle increases, biomechanical parameters of the head show an increasing trend. The risk of upper neck injury decreases, while the risk of lumbar injury decreases and then increases. As the seat rotation angle increases, the risks of head, neck, and chest injuries initially rise and subsequently decrease, while the risk of lumbar injury demonstrates a downward trend. Seatbelt force limiting exhibited a positive correlation with head, neck, and lumbar injury risks. Consequently, small percentile child experiences higher head loads in smart cockpits, with seatback angle and seat rotation angle being key factors contributing to child injuries. These findings highlight the critical need to address the vulnerability of smaller children in smart cockpits by adapting integrated active and passive safety systems to mitigate their injury risk.
Wang, Yanxin, Zhao, Hongqian, Li, Haiyan, He, Lijuan, Cui, Shihai, Lv, Wenle
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 techniques are used to mitigate the effects of odometry and motion uncertainty on the grade estimates. This estimator’s performance is compared to the measurements of a map created with a GNSS/INS system via a field experiment. When compared to the map-based system, the lidar-based estimator produces an unbiased error with a standard deviation of 0.6 degrees at an average range of 52.7 meters. By having similar precision to map-based systems, automotive lidar-based grade estimation systems are shown to be a valid approach for measuring road grade when a map is unavailable or inaccurate. In using lidar as an input signal for grade-based control system tasks, autonomous vehicles achieve higher redundancy and independence in contrast to existing methods.
Schexnaydre, Logan, Poovalappil, Aman, Robinette, Darrell, Bos, Jeremy
Edge detection is fundamental for intelligent vehicle applications, directly supporting ADAS functions such as lane detection, obstacle recognition, and scene understanding. The conventional Canny edge detection method exhibits notable shortcomings, especially in color-image processing, adaptive threshold selection, and preserving edge integrity under noisy conditions. In this study, we present an enhanced Canny edge detection framework tailored for ADAS-oriented intelligent vehicle systems, incorporating a quaternion-based weighted averaging scheme for color preservation, adaptive thresholds derived from gradient-amplitude histograms, multiscale edge localization via scale multiplication, and a novel gravitational-field-intensity operator for improved gradient robustness. Moreover, we extend the method to vanishing-point estimation an essential ADAS capability by performing precise intersection calculations combined with clustering techniques such as DBSCAN and RANSAC. Experimental evaluations demonstrate that the proposed algorithm markedly outperforms traditional approaches in edge clarity, localization accuracy, and noise resilience, underscoring its promise for strengthening ADAS perception modules in intelligent vehicles.
Uppala, Rohit Raj, Kaye, Murali, Zadeh, Mehrdad, Tan, Teik-Khoon
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 realistic traffic signals, road gradients, and vehicle interactions. RL agents are trained to interpret vehicle states, road attributes, and traffic light information to adjust control parameters in real time. This integration enables the controller to anticipate and respond to dynamic driving scenarios, thereby improving both energy efficiency and operational robustness. Simulation experiments across multiple driving scenarios demonstrate that the RL-enhanced eco-driving controller achieves substantial energy savings without compromising travel time. On average, our approach surpasses a baseline eco-driving controller without RL by 12% and outperforms a high-fidelity human driver model by 24.2% in terms of energy consumption reduction. These results highlight the potential of continuous action space RL to advance real-time eco-driving control in CAVs. Overall, this work provides a pathway toward more intelligent, adaptive, and sustainable vehicle control systems that can accelerate the deployment of energy-efficient mobility solutions.
Zhang, Yaozhong, Ammourah, Rami, Han, Jihun, Moawad, Ayman, Shen, Daliang, Karbowski, Dominik
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, 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 1,375 crash records were extracted, 657 for ADAS systems and 715 for ADS systems. Through the application of association rule mining and a novel metric termed influence, patterns in ADAS- and ADS-related crashes were examined within different roadway contexts. In general, it was found that subject vehicle and crash partner pre-crash movements as well as collision types were some of the most distinguishing factors between the two systems used. Differences in context specific rule summations also indicate distinct crash factor combinations between the two systems. The results offer an initial, exploratory perspective on the impact of vehicle automation on public roadways, providing insights that can inform system-specific safety assessments, risk mitigation strategies, and future research into the evolving dynamics of automated driving technologies.
Astle, W. Abram, Haus, Samantha
Rapidly upcoming deployment of autonomous vehicles (AVs), including robotaxis and trucks, has intensified the need for rigorous safety assessment of complex AI-driven systems. While considerable effort has been invested in constructing safety cases for AVs, systematic approaches for evaluating these safety cases remain underdeveloped. This paper presents a three-stage methodology for assessing AV safety cases. A process for assessing argumentation is presented that involves traceability to pre-reviewed and peer-reviewed safety cases such as the Open Autonomy Safety Case (OASC). Next, we present a structured process for evaluating the quality of evidence supporting these arguments. We applied this methodology to evaluate safety cases from multiple AV developers, enabling iterative refinement throughout the development lifecycle. Our agile approach supports efficient assessments by establishing clear traceability to industry standards and enabling early identification of potential gaps. This work provides regulators, operators, and developers with a practical framework for systematically evaluating AV safety cases and identifies lessons learned and areas for continued improvement.
Wagner, Michael
Automated Driving Systems (ADS) rely on AI algorithms, machine learning, and sensor fusion to perform autonomous driving tasks. Safety challenges arise due to the probabilistic behavior of AI/ML algorithms and the need to ensure safety within defined Operational Design Domains (ODDs). Traditional standards such as ISO 26262[3] (Functional Safety) and ISO 21448[4] (SOTIF) address hardware and software failures or functional deficiencies but are insufficient for higher-level autonomous systems (SAE Levels 3–5). To close this gap, additional standards such as UL 4600[1] and ISO 5083[2] provide complementary frameworks for ADS safety assurance. UL 4600[1] establishes a claim-based safety case encompassing the vehicle, infrastructure, and processes, emphasizing structured arguments supported by evidence and reasoning. It offers guidance on autonomy functions, V & V, tool qualification, dependability, and safety culture. ISO 5083[2] focuses on design, verification, and validation of ADS, extending safety lifecycles with system-level principles, risk criteria, and validation metrics. It defines the ADS safety case as proof of acceptable safety for specific features and environments, stressing safety-by-design, layered verification, and post-deployment monitoring, including cybersecurity. Together, UL 4600[1] and ISO 5083[2] enable a unified approach to safety assurance, aligning with Functional Safety and SOTIF principles. Their integration helps manufacturers evaluate ADS systematically, demonstrate risk acceptance, and maintain safety throughout the lifecycle.
Mudunuri, Venkateswara Raju, Almasri, Hossam, Fan, Hsing-Hua
With the increasing market penetration of automated vehicles, there is a critical need for credible and repeatable methods to quantify their energy impacts. This paper presents a Model-Based Systems Engineering (MBSE)-driven Anything-in-the-Loop (XIL) methodology for quantifying the powertrain energy consumption and potential savings from various controls for automated vehicles in realistic road scenarios while preserving high-fidelity powertrain behavior. The novelty of this approach lies in its use of a unified MBSE backbone (AMBER: Argonne National Laboratory’s [Argonne’s] MBSE-centric platform for transportation energy analysis) to automate the seamless and traceable progression from pure simulation to Vehicle-in-the-Loop (VIL) testing. This work utilizes Argonne's multi-vehicle simulation tool, RoadRunner, which automatically constructs 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 is maintained across pure simulation, Software-in-the-Loop (SIL), Processor-in-the-Loop (PIL), and 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 scenario down-selection; PIL validates real-time execution, inputs/outputs, and timing on the target processor; and VIL provides closed-loop evaluation with a real vehicle under controlled laboratory conditions. AMBER’s automated build and configuration enable rapid retargeting across platforms and repeatable scenario reproduction, making validation fast and cost-effective. To demonstrate its practical application, the workflow is used to validate the functionality and quantify the energy savings of an eco-driving control against a calibrated human driver model. Experiments show strong repeatability and consistent energy gains for the eco-driving strategy while preserving trip time, yielding average energy savings of 7.8% across the evaluated scenarios. Overall, the MBSE-guided XIL workflow shortens development time and reduces test cost by limiting on-road testing and lowering integration risk before track evaluation, while producing credible, closed-loop energy assessments traceable from requirements to test evidence.
Jeong, Jongryeol, Sharer, Phillip, Di Russo, Miriam, Das, Debashis, Zhang, Yaozhong, Karbowski, Dominik
As electric intelligent vehicles advance, drive-by-wire systems are increasingly adopted, and the thermal reliability of electromechanical brake (EMB) motors—the key actuators—remains safety-critical. Under stalled-rotor operation, unequal DC currents are typically applied to the three phases, producing nonuniform winding heating. Conventional thermal models can miss the associated tangential heat-transfer effects, increasing the risk of phase-wise end-winding hot spot. This paper analyzes EMB motor thermal behavior under stalled-rotor conditions using a modular 3-D lumped-parameter thermal network (LPTN). First, a standardized tooth module with external interfaces is developed. Its internal parameters are informed by experiments and computational fluid dynamics (CFD) and identified via particle swarm optimization (PSO), allowing the module to be encapsulated for reuse. Next, based on the machine topology, a minimal motor is derived and multiple tooth modules are interconnected through common nodes to form a modular 3-D LPTN that resolves radial, axial, and tangential heat-flow paths. Finally, a stepwise, weighted PSO is applied—module level followed by system level—to calibrate the full network. The tooth-module abstraction also enables rapid network assembly, and the boundary-cooling and loss-allocation modules can be updated to accommodate different cooling architectures and heating patterns while retaining the same internal formulation. Bench tests with inhomogeneous three-phase heating, validated against three-phase end-winding thermocouple measurements, show that the proposed model predicts temperatures more accurately than existing LPTNs. These results indicate that explicitly accounting for tangential heat exchange can improve temperature prediction for EMB motors under stalled-rotor duty and provides a reusable template for other concentrated-winding machines subject to nonuniform thermal loading.
Duan, Yanlong, Xiong, Lu, Wang, Xinjian, Zhuo, Guirong, Zeng, Jie
Items per page:
1 – 50 of 1017