Search Results

Modeling uncertainties pose a significant challenge in the development and deployment of model-based vehicle control systems. Most model- based automotive control systems require the use of a well estimated vehicle dynamics prediction model. The ability of first principles-based models to represent vehicle behavior becomes limited under complex scenarios due to underlying rigid physical assumptions. Additionally, the increasing complexity of these models to meet ever-increasing fidelity requirements presents challenges for obtaining analytical solutions as well as control design. Alternatively, deterministic data driven techniques including but not limited to deep neural networks, polynomial regression, Sparse Identification of Nonlinear Dynamics (SINDy) have been deployed for vehicle dynamics system identification and prediction.

Data-driven driving safety assessment is crucial in understanding the insights of traffic accidents caused by dangerous driving behaviors. Meanwhile, quantifying driving safety through well-defined metrics in real-world naturalistic driving data is also an important step for the operational safety assessment of automated vehicles (AV). However, the lack of flexible data acquisition methods and fine-grained datasets has hindered progress in this critical area. In response to this challenge, we propose a novel dataset for driving safety metrics analysis specifically tailored to car-following situations. Leveraging state-of-the-art Artificial Intelligence (AI) technology, we employ drones to capture high-resolution video data at 12 traffic scenes in the Phoenix metropolitan area. After that, we developed advanced computer vision algorithms and semantically annotated maps to extract precise vehicle trajectories and leader-follower relations among vehicles.

In intelligent surveillance and reconnaissance (ISR) missions, multiple autonomous vehicles, such as unmanned ground vehicles (UGVs) or unmanned aerial vehicles (UAVs), coordinate with each other for efficient information gathering. These vehicles are usually battery-powered and require periodic charging when deployed for continuous monitoring that spans multiple hours or days. In this paper, we consider a mobile host charging vehicle that carries distributed sources, such as a generator, solar PV and battery, and is deployed in the area where the UAVs and UGVs operate. However, due to uncertainties, the state of charge of UAV and UGV batteries, their arrival time at the charging location and the charging duration cannot be predicted accurately.

Electric vehicles (EVs) are becoming increasingly recognized as an effective solution in the battle against climate change and reducing greenhouse gas emissions. Lithium-ion batteries have become the standard for energy storage in the automobile industry, widely used in EVs due to their superior characteristics compared to other batteries. The growing popularity of the Vehicle-to-grid (V2G) concept can be attributed to its surplus energy storage capacity, positive environmental impact, and the reliability and stability of the power grid. However, the increased utilization of the battery through these integrations can result in faster degradation and the need for replacement. As batteries are one of the most expensive components of EVs, the decision to deploy an EV in V2G operations may be uncertain due to the concerns of battery degradation from the owner’s perspective.

The design of transportation vehicles, whether passenger or commercial, typically involves a lengthy process from concept to prototype and eventual manufacture. To improve competitiveness, original equipment manufacturers are continually exploring ways to shorten the design process. The application of digital tools such as computer-aided-design and computer-aided-engineering, as well as model-based computer simulation enable team members to virtually design and evaluate ideas within realistic operating environments. Recent advances in machine learning (ML)/artificial intelligence (AI) can be integrated into this paradigm to shorten the initial design sequence through the creation of digital agents. A digital agent can intelligently explore the design space to identify promising component features which can be collectively assessed within a virtual vehicle simulation.

Design of internal combustion (IC) engine pistons is dependent on accurate prediction of the temperature field in the component. Experimental temperature measurements can be taken but are costly and typically limited to a few select locations. High-fidelity computer simulations can be used to predict the temperature at any number of locations within the model, but the models must be calibrated for the predictions to be accurate. The largest barrier to calibration of piston thermal models is estimating the backside boundary conditions, as there is not much literature available for these boundary conditions. Bayesian model calibration is a common choice for model calibration in literature, but little research is available applying this method to piston thermal models. Neural networks have been shown in literature to be effective for calibration of piston thermal models.

Opposed piston two-stroke (OP2S) diesel engines have demonstrated a reduction in engine-out emissions and increased efficiency compared to conventional four-stroke diesel engines. Due to the higher stroke-to-bore ratio and the absence of a cylinder head, the heat transfer loss to the coolant is lower near ‘Top Dead Center.’ The selection and design of the air path is critical to realizing the benefits of the OP2S engine architecture. Like any two-stroke diesel engine, the scavenging process and the composition of the internal residuals are predominantly governed by the pressure differential between the intake and the exhaust ports. Without dedicated pumping strokes, the two-stroke engine architecture requires external devices to breathe.

Improving passenger safety inside vehicle cabins requires continuously monitoring vehicle seat occupancy statuses. Monitoring a vehicle seat’s occupancy status includes detecting if the seat is occupied and classifying the seat’s occupancy type. This paper introduces an innovative non-intrusive technique that employs capacitive sensing and an occupancy classifier to monitor a vehicle seat’s occupancy status. Capacitive sensing is facilitated by a meticulously constructed capacitance-sensing mat that easily integrates with any vehicle seat. When a passenger or an inanimate object occupies a vehicle seat equipped with the mat, they will induce variations in the mat’s internal capacitances. The variations are, in turn, represented pictorially as grayscale capacitance-sensing images (CSI), which yield the feature vectors the classifier requires to classify the seat’s occupancy type.

A major concern for a high-power density, heavy-duty engine is the durability of its components, which are subjected to high thermal loads from combustion. The thermal loads from combustion are unsteady and exhibit strong spatial gradients. Experimental techniques to characterize these thermal loads at high load conditions on a moving component such as the piston are challenging and expensive due to mechanical limitations. High performance computing has improved the capability of numerical techniques to predict these thermal loads with considerable accuracy. High-fidelity simulation techniques such as three-dimensional computational fluid dynamics and finite element thermal analysis were coupled offline and iterated by exchanging boundary conditions to predict the crank angle-resolved convective heat flux and surface temperature distribution on the piston of a heavy-duty diesel engine.

Off-road vehicles are increasingly adopting hybrid and electric powertrains for improved mobility, range, and energy efficiency. However, their cooling systems consume a significant amount of energy, affecting the vehicle’s operating range. This study develops a predictive controller for the battery thermal management system in an autonomous electric tracked off-road vehicle. By analyzing the system dynamics, the controller determines the optimal preview horizon and controller timestep. Sensitivity analysis is conducted to evaluate temperature tracking and energy consumption. Compared to an optimal controller without preview, the predictive controller reduces energy consumption by 55%. Additionally, a relationship between cooling system energy consumption and battery size is established. The impact of the preview horizon on energy consumption is examined, and a tradeoff between computational cost and optimality is identified.

With the development of vehicles equipped with automated driving systems, the need for systematic evaluation of AV performance has grown increasingly imperative. According to ISO 34502, one of the safety test objectives is to learn the minimum performance levels required for diverse scenarios. To address this need, this paper combines two essential methodologies - scenario-based testing procedures and scoring systems - to systematically evaluate the behavioral competence of AVs. In this study, we conduct comprehensive testing across diverse scenarios within a simulator environment following Mcity AV Driver Licensing Test procedure. These scenarios span several common real-world driving situations, including BV Cut-in, BV Lane Departure into VUT Path from Opposite Direction, BV Left Turn Across VUT Path, and BV Right Turn into VUT Path scenarios.

Ensuring the safety of vulnerable road users (VRUs) such as pedestrians, users of micro-mobility vehicles, and cyclists is imperative for the commercialization of automated vehicles (AVs) in urban traffic scenarios. City traffic intersections are of particular concern due to the precarious situations VRUs often encounter when navigating these locations, primarily because of the unpredictable nature of urban traffic. Earlier work from the Institute of Automated Vehicles (IAM) has developed and evaluated Driving Assessment (DA) metrics for analyzing car following scenarios. In this work, we extend those evaluations to an urban traffic intersection testbed located in downtown Tempe, Arizona. A multimodal infrastructure sensor setup, comprising a high-density, 128-channel LiDAR and a 720p RGB camera, was employed to collect data during the dusk period, with the objective of capturing data during the transition from daylight to night.

Effectively determining automated driving system (ADS)-equipped vehicle (AV) safety without relying on testing an infeasibly large number of driving scenarios is a challenge with wide recognition in industry and academia. The following paper builds on previous work by the Institute of Automated Mobility (IAM) and Science Foundation Arizona (SFAz), and proposes a test selection and scoring methodology (TSSM) as part of a safety case-based framework being developed by the SFAz to ensure the safety of AVs while addressing the scenario testing challenge. The TSSM is an AV verification and validation (V&V) process that relies, in part, on iterative, partially random generation of AV driving scenarios. These scenarios are generated using an operational design domain (ODD) and behavioral competency portfolio, which expresses the vehicle ODD and behavioral competencies in terms of quantifiable amounts or intensities of discrete components.

In the ever-evolving landscape of automotive technology, the need for robust security measures and dependable vehicle performance has become paramount with connected vehicles and autonomous driving. The Unified Diagnostic Services (UDS) protocol is the diagnostic communication layer between various vehicle components which serves as a critical interface for vehicle servicing and for software updates. Fuzz testing is a dynamic software testing technique that involves the barrage of unexpected and invalid inputs to uncover vulnerabilities and erratic behavior. This paper presents the implementation of fuzz testing methodologies on the UDS layer, revealing the potential vulnerabilities that could be exploited by malicious entities. By employing both open-source and commercial fuzzing tools and techniques, this paper simulates real-world scenarios to assess the UDS layer’s resilience against anomalous data inputs.

Robust communications are crucial for autonomous military fleets. Ground vehicles function as mobile local area networks utilizing Controller Area Network (CAN) backbones. Fleet coordination between autonomous platforms relies on the Robot Operating System (ROS) publish/subscribe robotic middleware for effective operation. To bridge communications between the CAN and ROS network segments, the CAN2ROS bridge software supports bidirectional data flow with message mapping and node translation. Fuzzing, a software testing technique, involves injecting randomized data inputs into the target system. This method plays a pivotal role in identifying vulnerabilities. It has proven effective in discovering vulnerabilities in online systems, such as the integrated CAN/ROS system. In our study, we consider ROS implementing zero-trust access control policies, running on a Gazebo test-bed connected to a CAN bus.

Semiconductor devices in electric vehicle (EV) motor drive systems are considered the most fragile components with a high occurrence rate for open circuit fault (OCF). Various signal-based and model-based methods with explicit mathematical models have been previously published for OCF diagnosis. However, this proposed work presents a model-free machine learning (ML) approach for a single-switch OCF detection and localization (DaL) for a two-level, three-phase inverter. Compared to already available ML models with complex feature extraction methods in the literature, a new and simple way to extract OCF feature data with sufficient classification accuracy is proposed. In this regard, the inherent property of active thermal management (ATM) based model predictive control (MPC) to quantify the conduction losses for each semiconductor device in a power converter is integrated with an ML network.

Tradespace exploration (TSE) describes the activity occurring early in the design process through which stakeholders explore a broad solution space in search of more-optimal alternatives. In doing so, these stakeholders attempt to maximize the utility inherent in the chosen solution while understanding the tradeoffs and compromises that may be required to find an acceptable solution. In the field of vehicle design, tradespaces are often comprised of vast amounts of alternatives which increases the complexity of the decision-making process. Additionally, the number of stakeholders has grown, as decision-makers seek to include more variety in both perspectives and expertise. As such, decision-making stakeholders can often find themselves working at odds and attempting to maximize vastly different objectives in the process. One way to rectify these contrasting viewpoints can be to intentionally introduce a group framing prior to the start of decision making.

The driving safety performance of automated driving system (ADS)-equipped vehicles (AVs) must be quantified using metrics in order to be able to assess the driving safety performance and compare it to that of human-driven vehicles. In this research, driving safety performance metrics and methods for the measurement and analysis of said metrics are defined and/or developed. A comprehensive literature review of metrics that have been proposed for measuring the driving safety performance of both human-driven vehicles and AVs was conducted. A list of proposed metrics, including novel contributions to the literature, that collectively, quantitatively describe the driving safety performance of an AV was then compiled, including proximal surrogate indicators, driving behaviors, and rules-of-the-road violations.

Formal verification plays an important role in proving the safety of autonomous vehicles (AV). It is crucial to find errors in the AV system model to ensure safety critical features are not compromised. Model checking is a formal verification method which checks if the finite state machine (FSM) model meets system requirements. These requirements can be expressed as linear Temporal logic (LTL) formulae to describe a sequence of states with linear Temporal properties to be satisfied. NuSMV is a dedicated software for performing model checking based on Temporal logic formulae on FSM models. However, NuSMV does not provide model-based design. On the other hand, Stateflow in MATLAB/SIMULINK is a powerful tool for designing the model and offers an interactive Graphical User Interface (GUI) for the user/verifier but is not as efficient as NuSMV in model checking.

In military applications, diesel engines are required to achieve high power outputs and therefore must operate at high loads. This high load operation leads to high piston component temperatures and heat rejection rates limiting the packaged power density of the powertrain. To help predict and understand these constraints, as well as their effects on performance, a thermodynamic engine model coupled to a finite element heat conduction solver is proposed and validated in this work. The finite element solver is used to calculate crank angle resolved, spatially averaged piston temperatures from in-cylinder heat transfer calculations. The calculated piston temperatures refine the heat transfer predictions as well requiring iteration between the thermodynamic model and finite element solver.