Browse Topic: Electrical, Electronics, and Avionics

Items (60,223)
Bicycle computers and apps record, at minimum, positional data over time, and these data are commonly used in accident reconstruction to understand the behavior of the bicycle and rider prior to an incident in question. These positional data are obtained using the Global Positioning System (GPS), and while their absolute positional accuracy has been the subject of prior research, their accuracy at detecting and reporting particular movements is less studied. To improve the accident reconstruction industry’s understanding of these devices’ performance, this research aims to statistically quantify the temporal and positional accuracy of these devices reporting the onset of a lateral deviation or lane change. Controlled testing was performed and recorded with several commercially available bicycle GPS computers and apps, which were compared to a RaceLogic VBox 3i ADAS with Real-Time Kinematics (RTK) corrections from a RaceLogic Base Station. Three separate test bouts were performed, with each test bout consisting of 30 or 32 repeats of three different lateral deviation maneuvers. The bicycle GPS computers were individually synchronized to the RaceLogic data by offsetting their time to minimize the mean-square positional error across the entire test bout, which enabled calculation of the 50th percentile and 95th percentile absolute positional errors for each device. A custom script was then used to programmatically detect the start of each lateral deviation, and then, confidence intervals were calculated to estimate the probability of each GPS device reporting the start of the lateral deviation with zero lead or lag, with 1 s of lag, or with 0 or 1 s of lag based on the relative timestamps and positional data. All three of the tested bicycle GPS computers had a probability of at least 0.5 of reporting the onset of sharp lateral movements with zero lead or lag based on the time data, while only two of the devices maintained a similarly high probability for the position-based data. The iPhone 17 Pro had a probability greater than 0.6 of detecting the onset of both gradual and sharp lateral movements with 1 s of lag for both the time-based and position-based data. And across all lateral movement types, all devices had a probability of at least 0.6 of reporting the onset of lateral movement with either 0 or 1 s of lag.
Sweet, David Michael, Bretting, Gerald, Wilhelm, Chris, O’Brien, Nathan
The purpose of this document is to expressly describe the required diagnostics (DIAG) related to the on-road traction battery management systems (BMS). This document will attempt to clearly educate and explain four key areas of BMS DIAG: (1) fault identification, (2) fault classification, (3) system reaction, and (4) diagnostic data and reporting.
Battery Management Systems Committee
The purpose of this document is to expressly describe the method of calculating state of charge (SOC) related to the on-road traction battery management systems (BMS). This document will attempt to clearly educate and explain four key areas of BMS SOC: (1) basic SOC definition, (2) SOC calculation methods, (3) influence items for SOC, and (4) SOC warnings.
Battery Management Systems Committee
The purpose of this document is to expressly describe the method of calculating state of health (SOH) related to the on-road traction battery management systems (BMS). This document will attempt to clearly educate and explain four key areas of BMS SOH: (1) basic SOH definition, (2) SOH calculation methods, (3) influence items for SOH, and (4) SOH reporting.
Battery Management Systems Committee
This specification contains requirements for, and applies to, commercial and military aircraft external/ground electrical power cable assemblies, using either overmolded or attachable plug connectors used to connect external/ground electrical power to aircraft and to attachable plugs used as replacements for plugs damaged in service.
AE-8A Elec Wiring and Fiber Optic Interconnect Sys Install
This SAE Aerospace Standard (AS) establishes guidelines for enhancement to IEEE 1394-2008 Beta (formerly IEEE 1394b) PHYsical (PHY) layer. It encompasses enhancements to the IEEE 1394-2008 Beta PHY to reduce port connection times and increase port connection reliability. Therefore, this document contains extensions/restrictions to “off-the-shelf” IEEE 1394 standards and assumes that the reader already has a working knowledge of IEEE 1394. The enhancements covered in this document include: Detect loss of descrambler synchronization Fast-ReTrain (FRT) Fast Power-on Re-connect (FPR) Fast Connection Tone Debounce (FTD) Programmable invalidCount Bus Reset Cause This document does not identify specific environmental requirements (electromagnetic compatibility, temperature, vibration, etc.); such requirements will be vehicle-specific and even LRU-specific. One should refer to the appropriate sections of MIL-STD-461E for their particular LRU and utilize handbooks such as MIL-HDBK-454A and MIL-HDBK-5400 for guidance. This document is referred to as a “slash sheet” and accompanies the AS5643B base standard.
AS-1A Avionic Networks Committee
Contested logistics environments expose the limitations of both legacy fragmented systems and emerging Next Generation Command and Control architectures that assume persistent connectivity. In degraded or denied conditions, sustainment operations face latency, bandwidth constraints, and reduced decision velocity. Expanded decision support tools further increase reliance on timely, relevant data exchange. This paper argues that contested logistics requires distributed, mission-aware intelligence at the tactical edge. Low-power onboard compute enables real-time inference, adaptive data conditioning, and connectivity-aware transmission across Radio-Frequency and non-RF pathways. By selectively elevating critical information based on mission context and network state, edge-intelligent architectures improve survivability, bandwidth efficiency, and sustainment effectiveness in degraded networks.
Baumann, Edward, Pardee, Shawn
This paper describes ongoing research and development of an efficient optimization/search–based modeling and simulation framework for rapidly identifying low-performance scenarios in advanced autonomous systems. Ensuring predictable, safe behavior across complex, integrated systems remains a core operational test-and-evaluation challenge. Our goal is to balance rigorous validation with timely deployment. We are developing TEAAS (Test & Evaluation of Advanced Autonomous Systems), a scalable, faster-than-real-time framework designed to uncover critical failure scenarios efficiently. Key features include GPU-accelerated parallel simulation and learning, computational intelligence–based search of optimal parameters, uncertainty quantification for reproducibility, and real-time physics-accurate sensor models. We conducted simulation experiments to evaluate and demonstrate the framework performance for two black-box ground-vehicle autonomous systems. Key results were that adequate uncertainty quantification can be achieved with as few as 10 repeated runs per simulation scenario, sensor realism has a significant effect on failure rate, distinct differences between the two autonomies failure modes were identified, and our efficient optimization/search methods identify critical performance regions in a small fraction of the number of simulations required by a naïve Monte Carlo search.
Snarski, S., Menozzi, A., Persons, B., Lazar, D., Khan, N.
The modern battlefield is increasingly transparent, generating large volumes of open-source data on the use, damage, and loss of military vehicles. This paper presents a structured methodology to exploit such data for deriving operational requirements for future vehicles. It uses a mixed-method framework combining qualitative reporting with quantitatively verified loss data. Daily battlefield reports are analyzed with large language models to extract operational context, employment patterns, and tactical conditions. These insights are cross-referenced with loss data to assess how operational factors affect vehicle survivability, with the findings being used to prioritize requirements that improve vehicle performance. The approach is demonstrated through a case study of Leopard tanks in the Russia-Ukraine war, using Institute for the Study of War reports and Oryxspioenkop loss data. Results show how open-source intelligence can systematically inform survivability, mobility, and combat effectiveness in modern vehicle design.
Lynch, Benjamin, Mittal, Vikram
The U.S. Army’s Modular Open Systems Approach (MOSA) is driving data-centric vehicle architectures that demand higher bandwidth, faster decision loops, and greater cross-platform interoperability. Despite these needs, stakeholders hesitate to adopt fiber optics because of perceived fragility, field-retrofit FOD risk, and soldier-handling concerns. This paper characterizes common fiber failure modes in ground-vehicle environments and demonstrates how system-level ruggedization, connector design, and qualified components mitigate those risks. Drawing on demonstrated experience with hardened optics, connector-integrated transceivers, sealed media converters, and rugged cabling, we summarize practical architecture and field maintenance procedures that enable reliable fiber deployment in vehicles. Results show that, with appropriate component selection, installation practices, and built-in diagnostics, fiber optics can provide a robust, maintainable backbone for future ground vehicle networks.
Kouns, Heath, Simms, Marc, Weiss, Evan, Breedlove, Joe
Traditional Linear Circuit Analysis (LCA) relies on steady-state voltage assumptions that are fundamentally incompatible with battery-exclusive propulsion architecture. Whilst LCA remains valid for hybrid systems, where an auxiliary source actively regulates the State-of-Charge (SOC), it fails when analyzing non-passive, constant-power loads. In pure electric architecture, the time-dependent decay of the discharge voltage forces a continuous, non-linear increase in current to satisfy mechanical power demands. A time-dependent power flow methodology is introduced to resolve this theoretical divergence. Using the conservation of energy operating explicitly within the power domain, the time-dependent coupling of current and voltage can be modeled. This approach supersedes steady-state approximations for higher fidelity predictions for component efficiency, system heat generation, and battery capacity requirements for pure electric propulsion systems. Citation: N. Ingarra, K. J. Kobus, J. G. Kobus “TIME-DEPENDENT POWER FLOW MODELING FOR NONPASSIVE LOADS IN BATTERY ELECTRIC PROPULSION ARCHITECTURES” In Proceedings of the Ground Vehicle Systems Engineering and Technology Symposium (GVSETS), NDIA, Novi, MI, Aug. 11-13, 2026.
Ingarra, Nicholas A., Kobus, Krzysztof (Chris) J., Kobus, Jadon G.
This paper details the successful scaling demonstration of a comprehensive supply chain screening process for commercial off-the-shelf (COTS) motherboard subassemblies used in tactical servers for naval applications. Our approach leverages Power Fingerprinting (PFP) technology, which uses unintended analog emissions and machine learning to provide independent, non-destructive, and scalable integrity assessment of microelectronics. The primary goal of the effort was to demonstrate the effectiveness and scalability of the PFP screening process without disrupting or delaying the manufacturing workflow. The screening successfully detected hardware and firmware modifications and identified two cases of abnormal behavior: unusual BIOS power reset and elevated CPU sensor readings on two motherboard subassemblies. Following our quality control forensic analysis, we determined the root cause of these anomalies and their potential impact on the host platform.
Aguayo Gonzalez, Carlos R., Roberson, Ken
Early-stage Battery Thermal Management System (BTMS) design can be constrained by limited manufacturer data, resulting in the use of steady-state thermal assumptions. An analytical methodology is introduced to extract the real-time cell resistance, instantaneous efficiency, and transient heat generation directly from standard constant-current discharge curves, and Open Circuit Voltage (OCV) profiles. By evaluating the time-dependent voltage differential against current, equivalent cell resistance and transient heat generation are computed without explicit ohmic measurement or calorimetric testing. This enables direct, real-time coupling of electrical and thermal models. Application to an NMC chemistry cell demonstrates concentration losses dominate below a 20% State-of-Charge (SOC), increasing transient heat generation, and decreasing instantaneous efficiency. Extracting the time-dependent electro-thermal parameters provides the required quantitative inputs for benchmarking cells & accurately sizing BTMS cooling capacities. Citation: N. A. Ingarra, K. J. Kobus, J. G. Kobus, “Deriving Instantaneous Electro-Thermal Parameters and Heat Generation from Constant-Current Discharge Data,” In Proceedings of the Ground Vehicle Systems Engineering and Technology Symposium (GVSETS), NDIA, Novi, MI, Aug. 11-13, 2026.
Ingarra, Nicholas A., Kobus, Krzysztof (Chris) J., Kobus, Jadon G.
Modern defense manufacturing and sustainment require timely engineering decisions (e.g., inspection triage, rework/accept decisions, and process adjustment) based on the as-built geometric quality. Advanced machining systems generate rich multichannel controller and sensor streams, yet accurate geometric deviation labels remain costly and delayed because they depend on downstream metrology. This paper introduces ChronosGD, a retrieval-based virtual metrology framework. ChronosGD predicts pointwise geometric deviation from multichannel time series data by: (1) retrieving the most similar historical process windows in a frozen Chronos-2 embedding space, and (2) transferring deviation information through similarity-weighted aggregation. ChronosGD avoids plant-specific gradient retraining during deployment; adaptation is achieved by refreshing a labeled historical memory as new inspected parts become available, while preserving traceability through explicit neighbor provenance.
Hoang, Danny, Matthiessen, Ryan, Miller, Christopher, Mannan, Nasir, ElKharboutly, Ruby, Gorsich, David, Castanier, Matthew P., Imani, Farhad
Synthesizing novel camera views is important for autonomous ground vehicles, with applications in surround-view monitoring, occlusion recovery, and training data augmentation. We present View Translation, a geometry-guided latent diffusion framework that generates a target camera view from a source image, relative camera pose, and an available target-view depth prior. The method combines three components: a Vector Quantized Variational Autoencoder for compact latent encoding, a depth-based warping module that projects the source image into the target view to provide geometric guidance, and a ControlNet-augmented denoising UNet conditioned on source appearance, relative pose, and an auxiliary Image-Depth fusion network. Evaluated on KITTI and a simulated off-road dataset, our method achieves competitive FID while improving LPIPS and PSNR over baseline approaches, supporting cross-view synthesis for ground vehicle perception.
Mayekar, Omkar, Aiyetigbo, Mary, Salvi, Ameya, Samak, Tanmay, Samak, Chinmay, Desjardins, Brendan, Smereka, Jonathon, Brudnak, Mark, Krovi, Venkat, Luo, Feng, Li, Nianyi
Semantic Segmentation (SS) is critical for autonomous vehicles to navigate off-road environments by identifying drivable terrain. Although models like ResNet34+UNet and EfficientViT have been proposed for these tasks, their susceptibility to localized adversarial patches in unstructured environments remains under-researched. This paper presents a comprehensive robustness evaluation of six real-time SS architectures, including the state-of-the-art YOLOv11 and YOLOv12 segmentation variants against five diverse adversarial patch schemes. Our experiments, conducted on a modified YCOR dataset, demonstrate that EfficientViT is the most resilient architecture, maintaining high accuracy with minimal performance degradation. In contrast, single-stage models like YOLOv11n-seg exhibit significant vulnerability, with pixel accuracy drops reaching 26.55%. We also show how decreases in overall segmentation accuracy impact the segmentation models’ ability to discern traversable terrain from non-traversable terrain.
Salas, Christopher, Pesé, Mert D., Li, Bing, Smereka, Jonathon, Cheng, Long
The US Army and several NATO allies have committed funds for directed energy weapons including high energy lasers (HEL), which require substantial electrical power. Silent Mobility and Silent Watch requirements mandate hybridization, which also provides the electrical capacity needed for a HEL. This paper introduces a HEL framework of classes A-E based on target types and fluence physics. It estimates installed HEL mass and power demand by class, and applies rapid powertrain screening to hypothetical hybrid variants of the UK vehicles Foxhound and Boxer. Results show that HELs up to Class B (60 kW) and D (300 kW) laser output can be supported with minimal powertrain modifications by Foxhound and Boxer respectively, and upgrades to support Class C (150 kW) and E (500 kW) are containable within the payload of each vehicle. A rapid methodology is presented to determine what powertrain architecture is needed to support a given HEL.
Salis, Rupert Tull
There is a need for advanced collaboration tools to meet the needs of increasingly complex engineering design challenges and of global design teams. Specifically, virtual design reviews are a means by which teams can obtain a better understanding of a product’s design. Many CAD systems have integrated cloud features, which can be utilized to perform design reviews within these systems. The focus of this paper is to evaluate CAD systems in three CAD architectures: traditional, cloud-enabled, and cloud-native, to assess their capabilities and highlight areas of improvement for CAD developers. Using a list of previously generated requirements, CAD systems were evaluated on how well they met each requirement to determine how they can foster collaborative work. While cloud-native CAD systems performed the best against the requirements, no CAD system was able to fully meet all requirements, showcasing multiple areas for future development.
Hughes, Katelynn, Petty, Emily, Mocko, Gregory M.
In pursuit of future high-power capabilities for U.S. military ground vehicles, the transition towards vehicle electrification has been heavily adopted. High power-density and high temperature inverters play a key role in progressing vehicle electrification adoption across the U.S. military. This paper presents experimental results to evaluate the power quality performance of the developed high power-density and high temperature inverter, Enercycle™ DC-1000 Inverter based on silicon carbide (SiC). The DC-1000 inverter is a bi-directional inverter with a power density of 11.4 kW/L, which is capable of operating at 600 Vdc and delivering 500kW continuous output power and transient output power up to 640 kW, enable ground vehicle electrification. The experimental results to evaluate the power quality aspects such as distortion factor, ac voltage ripple, and voltage transient due to step load are presented in this paper. Moreover, challenges and next steps for further improvement of design have been discussed. Citation: A. Sadigh, Iris Shiroma “Electrical and Power Quality Performance Evaluation of a SiC Based 500kW High Temperature and High Power-Density Inverter,” In Proceedings of the Ground Vehicle Systems Engineering and Technology Symposium (GVSETS), NDIA, Novi, MI, Aug. 11-13, 2026.
Sadigh, Arash, Shiroma, Iris
Biomanufacturing uses microorganisms to produce chemicals or materials of interest, much like a brewery uses fermentation by yeast to produce the alcohol in beer. Biomanufacturing relies upon synthetic biology to reprogram yeast or other microorganisms to produce something of greater value, such as fuel, food, or pharmaceuticals. Industrial biomanufacturing has made significant advances and the products it can deliver include reactive coatings and textiles, sensors, optical materials that can bend light, and new therapeutics such as antimicrobials and vaccines. The convergence of synthetic biology, robotics, and artificial intelligence is opening the way to produce materials never before possible in the commercial market. These same technologies create the opportunity for the miniaturization of this technology to fit into ever more compact spaces, bringing forward deployment of these mini-factories closer and closer to the point of need.
Ahern, Brooke, Crumbley, Annie, Walker, Anne, Grodecki, Joseph
This paper presents a cooperative object tracking framework that enables robots to share object observations, improving world model accuracy and consistency in environments with occlusions. An open-source, MHT-based object tracking package was applied in conjunction with an inter-robot communication system developed to fuse object observations across multiple robots. Experimental results demonstrate greater than 1.4-fold improvements in tracking performance in cluttered, occluded environments compared to individual tracking.
Kennedy, William, Alton, Nicholas
The architecture of Controller Area Network (CAN)-based protocols offers straightforward, centralized, and cost-efficient methods for various Electronic Control Units (ECUs) to communicate via the CAN bus. However, the CAN protocol was not designed with security as a priority. The CAN bus used in vehicles lacks built-in security features, (i.e., messages are broadcast without authentication or encryption). This makes CAN vulnerable to eavesdropping, spoofing, and replay attacks. Any compromised node can inject false messages (e.g., impersonating the brakes or engine controller) with no cryptographic checks to stop it. The protocol’s primary integrity safeguard, a Cyclic Redundancy Check (CRC), was designed solely for detecting transmission errors and is easily manipulated, offering no real protection against malicious adversaries. Implementing cryptography on CAN is challenging due to CAN’s most popular limited 8-byte data payload, real-time latency requirements, and the need for compatibility with millions of existing CAN devices. To address this issue, this study focuses on developing a Cryptographic Message Authentication Code (CMAC) Intrusion Detection System (IDS) implementation for CAN bus communication using existing ECUs.
Beer, Spencer, Jepson, Jake, Nogin, Aleksey, Daily, Jeremy
Unmanned ground vehicles (UGVs) operating in unstructured environments must account not only for terrain traversability but also for terrain-induced loads that affect component durability. Existing path planning approaches primarily consider obstacle avoidance and mobility, while neglecting cumulative structural degradation due to repeated loading. High-fidelity physics-based simulations can capture these effects but are computationally prohibitive for real-time applications. This study investigates machine learning-based surrogate models for predicting vehicle component reaction forces from terrain height sequences generated using a controlled parametric terrain formulation. Both feed-forward and recurrent neural network architectures are evaluated, and ensemble-based probabilistic techniques are incorporated to quantify predictive uncertainty. Results show that the ensemble long short-term memory (Ens-LSTM) model achieves the lowest prediction error (mean absolute error of 0.621 kN) while maintaining narrow 95% prediction intervals (3.22–4.28 kN). A simpler ensemble feed-forward network (Ens-NN) achieves comparable accuracy (0.626 kN) with reduced model complexity. These results demonstrate that data-driven surrogate models can provide accurate and uncertainty-aware force predictions, enabling the integration of structural reliability considerations into fatigue-aware path planning for UGVs.
Chua, Yang Kang, Mundiwala, Mohammad, Wang, Xudong, Castanier, Matthew, Hu, Zhen, Hu, Chao
Advancements in autonomous ground vehicle technology have led to widespread developments in the field. Autonomous ground vehicles require robust emergency stop systems capable of safely managing system failures without human intervention. This paper presents an intelligent emergency stop system that combines minimum-jerk trajectory optimization, linear quadratic regulator path tracking control, and friction-aware velocity planning to perform collision avoidance maneuvers while bringing the vehicle to a controlled stop. The system is designed for implementation on a low-cost single board computer operating as an inline gateway between the main autonomy system and the vehicle CAN bus, providing redundancy against primary system failures. Simulation results, including a 1000-run Monte Carlo analysis, demonstrate robustness to vehicle parameter uncertainty while maintaining tire forces within friction limits. Live testing on a Lincoln MKZ sedan at 30 mph confirmed real-time operation on a $15 Raspberry Pi Zero 2 with lateral tracking errors of less than 15 cm.
Thompson, Kyle, Bevly, David M.
This paper presents a deep learning-based approach for online rotor temperature estimation in electrically excited synchronous motors (EESMs). Accurate rotor temperature estimation is critical for ensuring safe operation, improving performance, and enabling reliable thermal management of electric traction motors. Recurrent neural network (RNN) architectures, including gated recurrent unit (GRU) and long short-term memory (LSTM) networks, are investigated to develop a data-driven thermal virtual sensor capable of capturing the temporal dynamics of motor operation. Experimental data collected from a 190 kW EESM prototype are used to train and evaluate the proposed models. A systematic training, testing, and 10-fold cross-validation framework is employed to assess prediction accuracy and generalization capability. The results demonstrate that the GRU-based model achieves higher prediction accuracy than the LSTM model while maintaining comparable inference latency. The proposed approach provides an efficient and lightweight solution for real-time rotor temperature estimation suitable for embedded motor control applications.
Tatari, Farzaneh, Aligoudarzi, Mohsen Mirza
Artificial Intelligence (AI) and Machine Learning (ML) are increasingly transforming Computer-Aided Engineering (CAE) workflows by enabling faster design iterations and reducing computational costs. This paper presents the application of Ansys SimAI and Ansys GeomAI in modelling an automotive side impact scenario using high-fidelity data from LS-DYNA simulations. Two AI models are trained on datasets with systematically varied parameters: one encompassing pole impact position and door beam configurations, and another focusing on rocker panel reinforcements. Both models exhibit strong predictive performance, reliably capturing deformation patterns and force-time histories for previously unseen configurations. The datasets are subsequently merged to train a comprehensive surrogate model capable of simultaneously representing variations in pole position, door beam geometry, and rocker reinforcement design, demonstrating robust generalization across a multidimensional design space. To address the emerging bottleneck of geometry creation, GeomAI’s geometry exploration functionality is employed to generate new rocker reinforcement geometries from existing ones, which are then rapidly validated using the pre-trained surrogate model. The results confirm that LS-DYNA simulations can be leveraged effectively to build AI models that dramatically reduce design exploration time. With SimAI and GeomAI in the loop, CAE workflows can evolve from simulation-driven design toward AI-augmented autonomous engineering, where geometry generation, simulation, validation, and optimization converge into an intelligent closed loop.
Adya, Srikanth, Karadogan, Celalettin, Vasu, Shyam S., Lazarov, Nikolay, Husek, Martin, Haufe, André
Intelligence, surveillance and reconnaissance (ISR) often require review of significant quantities of video. While machine vision is used to flag objects for human review, too many flags are generated. Integrating newer methods like Open-Vocabulary Object Detection (OVOD) that support zero shot detection, but with significantly lower accuracy only make the problem worse. This work addresses the utility of OVOD in ISR missions by focusing only what has changed between successive runs through an environment. A Vision Language Model (VLM) compares current observations against a registered “cleared” baseline to focus only on what has changed. Testing across three distinct environments, and using either monocular camera phones or RGB-D equipped vehicles, demonstrates that integrating change detection can automatically remove as much as 80% of unchanged objects without impacting recall.
Martinson, Eric, Fishta, Igri
Unmanned Aerial Systems (UAS) pose a growing threat on the modern battlefield, demanding rapid detection and characterization capabilities for the warfighter. Existing single-model solutions are inadequate for Counter-UAS (C-UAS), as they struggle across varying ranges and cannot provide detailed contextual information beyond bounding boxes. We present ZEUS (Zero-shot Explainable Universal Segmentation), a multi-model detection and recognition system that integrates several machine learning approaches. ZEUS employs a high-performance UAS detector trained on synthetic, internally collected, and open-source datasets, with real-time capability demonstrated on edge hardware across both electro-optical and infrared modalities. For classification, ZEUS uses a zero-shot approach: detected UAS are segmented and compared against a library of 3D reference models rendered at various poses, enabling identification of new UAS types without retraining. This methodology additionally provides UAS pose and range estimates critical for threat assessment and engagement decisions.
Matousek, Gregory, Varberg, Nathan, Torrione, Pete, Brandon, Namdi, Inkawhich, Matt, Camilo, Joe
Ground vehicle commanders operate in scenarios which bare high cognitive load. They must be reactive to time-critical events where attention is divided between a variety of sensors, crew members, the physical world, and digital displays, which can result in missed situational cues. This paper presents a Human Digital Twin (HDT) architecture which provides real-time, embodied AI assistance to commanders in a military ground vehicle simulation scenario. The system integrates a data pipeline for combining a MetaHuman avatar in Unreal Engine with multi-modal data ingestion and a large language model (LLM). In addition, a retrieval-augmented generation approach grounds the LLM with mission-specific context, and a Big Five personality framework for prompt design constructs a consistent agent persona throughout the scenario. The architecture is demonstrated with a prisoner of war camp scouting mission, in which the HDT selectively intervenes when needed to alert the commander to critical events when missed. A system latency evaluation is provided to demonstrate viability for real-time integration. Results show the potential of integrated HDT systems to improve situational awareness and decision support in high stakes ground vehicle operations.
McCarthy, Martin, Mohammed, Abdul Mannan, Gallagher, Reese, Neumann, Carsten, Bruder, Gerd, Reiners, Dirk, Cruz-Neira, Carolina, Paul, Victor
This paper details the development of an intelligence and inspection platform consisting of an attritable sub-250g UAV, a ground control station, and a visualization interface for users. The UAV architecture combines onboard obstacle detection and avoidance along with simultaneous localization and mapping to have full autonomous navigation inside of complicated GPS-denied environments. The ROS 2-to-Unreal Engine data pipeline allows for sensor fusion, data cleansing, and initial analysis as well as creation of a high-fidelity real-time 3D digital twin. The visualization interface allows users to easily identify critical features and turn data into intelligence to support decision making by soldiers and first responders.
Lee, Yeen K., Bainard, Sean, Shaughnessy, Michael, Bolger, Matt, Koepp, R. Tucker, Salehzadeh, Roya, Mallory, Stephen, Mynderse, James A., Guillen, Pedro, Hernandez, Margarita
Employment of Robotic and Autonomous Systems requires a different paradigm of mission planning. The GTRI Missioneer for Organic Collaborative Kill-Chains (MOCKS) effort was developed to mature the concepts of mission planning in light of autonomy, where the decision making is distributed across the battlespace and each individual entity has limited awareness of global state. The paper presents some initial characterizations of the impact of constraints on periods out of communication, or no-comms windows, on the number of resources required for missions of a certain operational area. This metric, along with the foundational metric of remaining effective range margin are foundational to robust a priori planning.
Spratley, Michael
Maintaining consistent object identities across multiple camera viewpoints is a critical challenge in synthetic perception environments used for autonomous ground vehicle evaluation. This paper presents a scene-level multi-view instance consistency framework that integrates OpenUSD scene composition, Omniverse Replicator synthetic-data generation, and a multi-feature vision fusion pipeline. The proposed approach combines semantic embeddings from CLIP, patch-level descriptors from DINOv2, geometric correspondences from LoFTR, mask-derived shape invariants using Hu moments, and relative-position priors to associate object instances across views, including visually identical objects. A compact composite scoring function fuses these complementary cues to achieve robust cross-view identity assignment while preserving OpenUSD asset modularity through grouped-prim support. Synthetic experiments across 120 multi-camera scenes demonstrate improved Top-1 Match Accuracy and Identity Consistency Rate, with reduced ID-switch occurrences compared to single-cue baselines. The framework supports scalable, repeatable, and traceable digital engineering workflows for defense-oriented perception evaluation.
Bhattacharya, Sambit, Nakamoto, Kyle
Ground vehicle autonomy increasingly depends on human-on-the-loop (HOTL) supervision, yet supervisors are often overloaded by visual interfaces that can obscure emerging risks. This paper presents an AI-driven predictive sonification architecture that converts short-horizon forecasts of platoon behavior into structured auditory cues for supervisory monitoring. A forecasting engine predicts future vehicle interaction states and evaluates predicted and active violations to generate a composite risk indicator. When risk exceeds defined thresholds, a sonification module conveys risk magnitude and trajectory through changes in pitch, loudness, modulation, and spatial panning. The paper describes the system architecture, sonification design, operational use cases, and a planned human-subject evaluation. The proposed framework is intended to improve early awareness of emerging instability and support more timely supervisory intervention.
Plotzke, Zachary R., Mohammadi, Alireza, Cheung, Calvin M.
Digital engineering (DE) and model-based systems engineering (MBSE) improve traceability for requirements, architecture, and verification, but concept decisions—the governance events that turn evolving evidence into binding commitments—are poorly captured. Rationale, assumptions, alternatives, model baselines, and approval conditions are scattered across slides and minutes, limiting auditability, reproducibility, and automation. We propose a Decision Digital Thread (DDT): a typed graph schema that makes decisions governable by linking framing and scope, structured (including set-based) alternatives, uncertainty and risk, immutable evaluation-run provenance with reviewed evidence, and commitment events with machine-actionable conditions, authorized actions, and outcome feedback. DDT serves as the decision system of record and a contract between platform modules and enterprise policy while referencing MBSE/PLM/simulation artifacts via stable identifiers and configuration context. Policy-driven readiness gates block lifecycle transitions when evaluator coverage, evidence review, or bias checks are incomplete. An electric pickup range-extension case demonstrates auditable gates, evidence lineage, and safe AI-agent authority boundaries.
Chinnam, Ratna Babu, Murat, Alper, Rana, Satyendra, Rapp, Stephen H., O’Bruba, Joseph G., McGregor, Michael, Bechtel, James E., Costa, Laura W.
Modern electrified ground vehicles introduce complex, multi-domain safety requirements, such as post-crash thermal runaway prevention, that expose the traceability limitations of Document-Based Systems Engineering (DBSE). This paper proposes a four-layer, bidirectional digital thread architecture that integrates Model-Based Systems Engineering (MBSE) with high-fidelity, non-linear Computer-Aided Engineering (CAE) crash simulations. Leveraging SysML, System-Theoretic Process Analysis (STPA), and Python-based orchestration middleware, the framework automates the translation of descriptive safety requirements into explicit finite element boundary conditions. The architecture programmatically extracts key performance indicators from massive binary solver outputs and injects them back into the SysML environment for automated compliance verification. Demonstrated through a simplified electric vehicle side-pole impact case study utilizing LS-DYNA and a 1D thermal model, the framework successfully eliminates manual data handoffs, accelerates multidisciplinary design optimization, and ensures robust, risk-driven requirement traceability across the engineering lifecycle.
Rye, Patrick J.
Model-Based Systems Engineering (MBSE) has become a mandated practice for Department of Defense acquisition programs, yet measured benefits remain elusive. The 2024 Defense Science Board found that less than one percent of published literature actually quantified MBSE outcomes, and flagship ground vehicle programs such as the XM30 Infantry Fighting Vehicle have experienced schedule delays attributed directly to insufficient proficiency with model-based approaches. This paper presents the Digital Safety Twin concept: an AI-powered safety intelligence architecture that addresses three of the most labor-intensive and error-prone MBSE workflows. First, the architecture uses hybrid natural language processing and large language model (NLP/LLM) pipelines to auto-formalize unstructured natural language documents into formally structured, traceable requirements. Second, it auto-generates and continuously maintains traceability relationships across requirements, design elements, hazard analyses, and verification artifacts. Third, it provides continuous safety case completeness and confidence assessment through automated Goal Structuring Notation (GSN) synthesis connected to live evidence sources. The approach is grounded in Systems-Theoretic Process Analysis (STPA), the OMG Risk Analysis and Assessment Modeling Language (RAAML), MIL-STD-882E system safety practice, and the UL 4600 safety case framework. We present the methodology, its alignment to the DoD Digital Engineering Strategy, and its applicability to ground vehicle autonomy programs including next-generation infantry fighting vehicles and robotic combat vehicles. We also discuss the limitations, risks, and cultural barriers that must be addressed for AI-augmented safety engineering to achieve acceptance in mission-critical defense applications.
Wagner, Michael, Santini, Nelson, Balakrishnan, Anoop
Autonomous reconnaissance in unknown or contested environments demands robust perception systems capable of identifying diverse objects without prior training data. This paper presents HybridNAV, a hybrid framework that combines multiple foundation models with an adaptive navigation system for zero-shot object detection and autonomous exploration. Unlike monolithic detection models, HybridNAV’s multi-model fusion achieves balanced precision (0.60) and recall (0.58) with a macro F-score of 0.59, representing a 24% improvement over single-model baselines. The adaptive navigation system reduces scan time by 25% and path length by 30% compared to static waypoint approaches, while operating in real-time at 3.2 Hz with sub-100 msec latency on resource-constrained hardware. All processing is performed locally on the robotic platform, eliminating reliance on external communication infrastructure—a critical requirement for operations in communication-denied environments. We evaluate HybridNAV in both simulated indoor scenes and physical robot trials, demonstrating its effectiveness for intelligence gathering in unknown environments.
Indurthi, Hemanth, Martinson, Eric
The proliferation of small unmanned aircraft systems (sUAS) presents an asymmetric threat to ground maneuver forces operating in contested and gray-zone environments. The Bullfrog Autonomous Weapon Station (AWS) addresses this operational gap through a passive, AI-powered counter-UAS system employing computer vision and machine learning for autonomous detection, tracking, classification, and engagement. Field testing at Technology Readiness Experimentation (T-REX) 26-1 demonstrated 100% probability of defeat against Group 1 UAS targets with a mean engagement time of 6 seconds and 10 rounds per kill at ranges exceeding 160 meters. Operating in both autonomous and human-in-the-loop modes, Bullfrog achieved 99.45% operational availability while leveraging service-common M240B weapons and Modular Open Systems Architecture for rapid integration with Joint All-Domain Command and Control (JADC2) networks. At $300,000 per unit with $10 cost-per-engagement, Bullfrog demonstrates operational relevance, speed-to-field, and alignment with Army and Marine Corps autonomy priorities.
Cunningham, Jason, Clark, Alex
Verification of functional requirements in Model-Based Systems Engineering environments remains fragmented across heterogeneous tools and manual processes. This paper presents a digital twin–enabled workflow that supports automated requirement verification through integration of SysML models, executable simulation environments, and verification evaluation functions. Within this scope, the objective is to formalize a verification workflow that preserves architectural abstraction while enabling automated, traceable, and simulation-driven evaluation of functional requirements. The approach establishes a continuous digital thread that maintains traceability between requirements, system architecture, and verification outcomes. The workflow is demonstrated using a differential-drive robotic platform, where sensor data availability and update rate verification are used as representative examples of digital twin-based functional requirement evaluation. Results illustrate the feasibility of incorporating digital twin-driven verification into model-centric engineering processes while maintaining consistent verification feedback within the system model. The demonstration produced both passing and failing verification outcomes, illustrating the workflow’s ability to surface requirement-design mismatches.
Zeki, Omar, Sahebsara, Farid, Torkjazi, Mohammadreza, Hieb, Michael R., Raz, Ali K.
This research is meant to enhance the analytic capabilities of OneSAF for usage as a Monte Carlo-style data generator for use in large problem space trade studies. Using novel ground vehicle data such as: RHA armor values, weapon penetration prediction models, and sensor values, new models can be developed in OneSAF for use in data generation and analysis. This process and companion software developed for this purpose enables the rapid construction and evaluation of differing vehicle variants in a fraction of the time of the baseline process, improving the efficiency of using OneSAF as a data analysis tool. This approach facilitates a more comprehensive virtual experimentation approach that can use manufactured data as a part of the process.
Sapunkov, Oleg, Roberts, Bradshaw, Jorgensen, Maxwell
We present atomistic molecular dynamics simulations of linear and branched fluorinated polymer chains, with and without imidazole functionalization, designed as a model for solvent-free proton-conducting membranes for high-temperature fuel cell applications. Simulations conducted over a temperature range of 300 to 550 K, and diffusion-based relaxation times reveal that glass transition temperatures depend on polymer architecture: the branched and functionalized systems exhibit transitions near 400 K compared to 500 K for the linear chain. Fluorine-fluorine radial distribution functions demonstrate that branching disrupts local packing order, while imidazole substitution creates specific intra-chain interactions. Radius-of-gyration distributions reveal that branching significantly increases chain extension and creates multiple conformational families, whereas imidazole groups stabilize compact conformations at low temperatures that transition to more diverse states upon heating. These findings provide molecular-scale insight into how polymer architecture controls thermal transitions and structural organization in model high-temperature polymer electrolyte membranes.
Ganta, Sujith, Alim, Twaha, Rakesh, Leela, Mueller, Anja, Mellinger, Axel, Burye, Theodore, Sebastian, Talia
ISO 26262ISO/SAE 21434ISTQB/ASPICEMOSAGCIAVICTORY
Priemer, Douglas, Sime, Karl
Early electrical/electronic (E/E) architecture decisions in ground combat vehicles (GCVs) strongly influence lifecycle cost, upgradeability, survivability, cyber resilience, and integration risk across decades-long service lives. As Army programs transition from distributed E/E architectures toward zonal and software-defined vehicle concepts, the number of viable architectural options expands while the cost of late architectural change increases. This paper presents a detailed, model-based architecture evaluation methodology structured around Requirements–Functional–Logical–Physical (RFLP) principles, using Modular Open Systems Approach (MOSA) constraints as architectural requirements and VICTORY-aligned concepts as validation targets. The methodology emphasizes multi-variant architecture definition with large-scale reuse, early synthesis of wiring and network impacts, end-to-end traceability, change impact awareness, and continuity from architecture evaluation into detailed, multi-team design. The approach enables early, evidence-based comparison of architectural alternatives and preserves a traceable rationale to support modernization, sustainment, and future system evolution.
Anderson, Tony
This position paper presents
Dattathreya, Macam
The radio-based wide area network (WAN) that forms the command-and-control backbone for deployments of multiple ground vehicles is a classic DIL (disconnected, intermittent, limited) communications infrastructure for bandwidth-intensive services like video streams, situational awareness feeds, and command-and-control messages. This paper describes an inter-vehicle network architecture that leverages the radio-aware routing features of an existing vehicle Ethernet switch/router to provide mission-optimized, fault-tolerant data delivery while minimizing both network overhead and vehicle SWaP requirements.
Al-Gharaibeh, Jafar, Bonney, Jordan
This document recommends criteria for the layout and for the design, installation, and operation of flight deck facilities for transport aircraft.
S-7 Flight Deck Handling Qualities Stds for Trans Aircraft
While autonomous perception has matured within the structured confines of urban roadways, it remains brittle when confronting the chaotic, non-rigid terrain of the natural world. This paper introduces the Clemson Off-Road Dataset, a high-fidelity, multimodal dataset engineered to bridge this gap by challenging standard “flat-world” assumptions. Featuring 2.90 TB of sensor data, the dataset captures a diverse spectrum of unstructured environments, ranging from the transitional trails of CU-ICAR and the day/night lighting dynamics of TN3 to the unstructured wilderness of Camp Daniels and the novel coastal scenery of Edisto Island. Distinguishing itself from existing forest-centric benchmarks, the Clemson Dataset provides a first-of-its-kind focus on coastal data, featuring unique adversarial conditions such as extreme solar glare, loose sand, and shifting tide lines. The data is collected aboard a Polaris RZR Pro R 4, a high-performance platform integrated with a sensor suite designed to perceive physics beyond geometry. Alongside 360° HD camera coverage, 3D LiDAR, and Radar, we integrate Cubert Ultris Hyperspectral imaging and Prophesee EVK4 Event-based vision to enable material classification and high-dynamic-range motion tracking. To overcome the bottleneck in ground truth generation, we used our “AI LabelMate,” a context-aware semi-automated annotation agent that fuses Vision-Language Models (Florence-2) with SAM2 to generate 6331 pixel-perfect annotated frames using a specialized off-road ontology and a human-in-the-loop pipeline. We establish performance baselines using Oneformer for semantic segmentation and used SalsaNext for lidar point clouds labelling. Available in both raw ROS2 bag and extracted standard formats, this Dataset serves as a pivotal testing ground for the next generation of robust autonomous systems.The dataset of this paper is available upon request to the Virtual Prototyping of Autonomy-Enabled Ground Systems (VIPR-GS) Center.
Patil, Ashish, Gupta, Prakhar, Bhosale, Mayuresh, Mukwaya, Arthur, Jegede, Akinbobola, Mikulski, Dariusz, Mwakalonge, Judith, Jia, Yunyi
Research in autonomous driving has largely focused on structured, on-road environments in densely populated urban areas, leaving off-road autonomy comparatively underexplored despite its importance for applications such as search and rescue, agriculture, and defense. Progress in developing solutions for off-road autonomy is heavily constrained by the high cost, safety risks, and limited coverage of real-world off-road data collection, particularly for rare terrain-induced failure cases. To address these challenges, we introduce a large-scale simulation platform for off-road autonomous driving generated in the Unity3D engine. Our simulator provides indefinite data from multiple RGB cameras, LiDAR, GPS, and IMU sensors to support research in long-duration applications. Our platform also facilitates research in risk-aware planning through dynamic weather, lighting, and annotations for sequence-level failures like collisions and weather-induced sensor blockages. By combining long-duration temporal coverage, multimodal sensing, and procedurally generated terrain diversity, our simulator facilitates progress for systematic evaluation of learning-based autonomous driving models in unstructured, safety-critical environments.
Ross, Timothy, Boone, Julia, Afghah, Fatemeh
Items per page:
1 – 50 of 60223