Search

Workload management is a critical concern in shared control of unmanned ground vehicles. In response to this challenge, prior studies have developed methods to estimate human operators' workload by analyzing their physiological data. However, these studies have primarily adopted a single-model-single-feature or a single-model-multiple-feature approach. The present study proposes a Bayesian inference model to estimate workload, which leverages different machine learning models for different features. We conducted a human subject experiment with 24 participants, in which a human operator teleoperated a simulated High Mobility Multipurpose Wheeled Vehicle (HMMWV) with the help from an autonomy while performing a surveillance task simultaneously. Participants' eye-related features, including gaze trajectory and pupil size change, were used as the physiological input to the proposed Bayesian inference model. Results show that the Bayesian inference model achieves a 0.823 F1 score, 0.824 precision, and 0.821 recall, outperforming the single models. [ABSTRACT FROM AUTHOR]

Objective: A human steering model for teleoperated driving is extended to capture the human steering behavior in haptic shared control of autonomy-enabled Unmanned Ground Vehicles (UGVs). Background: Prior studies presented human steering models for teleoperation of a passenger-sized Unmanned Ground Vehicle, where a human is fully in charge of driving. However, these models are not applicable when a human needs to interact with autonomy in haptic shared control of autonomy-enabled UGVs. How a human operator reacts to the presence of autonomy needs to be studied and mathematically encapsulated in a module to capture the collaboration between human and autonomy. Method: Human subject tests are conducted to collect data in haptic shared control for model development and validation. The ACT-R architecture and two-point steering model used in the previous literature are adopted to predict the operator's desired steering angle. A torque conversion module is developed to convert the steering command from the ACT-R model to human torque input, thus enabling haptic shared control with autonomy. A parameterization strategy is described to find the set of model parameters that optimize the haptic shared control performance in terms of minimum average lane keeping error (ALKE). Results: The model predicts the minimum ALKE human subjects achieve in shared control. Conclusions: The extended model can successfully predict the best haptic shared control performance as measured by ALKE. Application: This model can be used in place of human operators, enabling fully simulation-based engineering, in the development and evaluation of haptic shared control technologies for autonomy-enabled UGVs, including control negotiation strategies and autonomy capabilities. [ABSTRACT FROM AUTHOR]

Terrain traversability is critical for developing Go/No-Go maps for ground vehicles, which significantly impact a mission's success. To predict the mobility of terrain, one must understand the soil characteristics. In-situ measurements performed in the field are the current method of collecting this information, which is time-consuming, costly, and can be lethal for military operations. This paper investigates an alternative approach using thermal, multispectral, and hyperspectral remote sensing from an unmanned aerial vehicle (UAV) platform. Remotely sensed data combined with machine learning (linear, ridge, lasso, partial least squares (PLS), support vector machines (SVM), and k nearest neighbors (KNN)) and deep learning (multi-layer perceptron (MLP) and convolutional neural network (CNN)) are used to perform a comparative study to estimate the soil properties, such as the soil moisture and terrain strength, used to generate prediction maps of these terrain characteristics. This study found that deep learning outperformed machine learning. Specifically, a multi-layer perceptron performed the best for predicting the percent moisture content (R2/RMSE = 0.97/1.55) and the soil strength (in PSI), as measured by a cone penetrometer for the averaged 0–6" (CP06) (R2/RMSE = 0.95/67) and 0–12" depth (CP12) (R2/RMSE = 0.92/94). A Polaris MRZR vehicle was used to test the application of these prediction maps for mobility purposes, and correlations were observed between the CP06 and the rear wheel slip and the CP12 and the vehicle speed. Thus, this study demonstrates the potential of a more rapid, cost-efficient, and safer approach to predict terrain properties for mobility mapping using remote sensing data with machine and deep learning algorithms. [ABSTRACT FROM AUTHOR]

Studies on eco-driving have mostly taken an energy-centric view and considered driving performance, while less attention has been paid on emissions behavior. This work extends in an experimentally verified way our understanding of the trade-offs among fuel economy, driving aggressiveness, and, especially, emissions in connected automated diesel-powered vehicles. Experiments are performed with a 6.7-L Ford Powerstroke diesel engine, a urea-SCR based NOx aftertreatment system, and a full model for a Ford F250 medium-duty truck in the loop to provide realistic assessment of fuel consumption, tailpipe emissions, and driving style performances. An energy and emissions conscious speed planner is leveraged to follow the traffic. This planner offers flexibility in prioritizing energy or emissions while satisfying user-defined headway constraints, and thus allows exploration of different calibrations in a unified way. Results show how various calibrations of the flexible leader following policy yield 8%–14% decrease in total fuel consumption and 64%–70% decrease in tailpipe emissions compared with a strictly constrained following policy. [ABSTRACT FROM AUTHOR]

Previous work by the authors developed algorithms for simplifying the structure of a lumped dynamic system model and reducing its order. This paper extends this previous work to enable simultaneous model structure and order reduction. Specifically, it introduces a new energy-based metric to evaluate the relative importance of energetic connections in a model. This metric (1) accounts for correlations between energy flow patterns in a model using the Karhunen-Loeve expansion; (2) examines all energetic connections in a model, thereby assessing the relative importance of both energetic components and their interactions, and enabling both order and structural reduction; and (3) is realization preserving, in the sense of not requiring a state transformation. A reduction scheme based on this metric is presented and illustrated using a simple example. The example shows that the proposed method can successfully concurrently reduce model order and structure without requiring a realization change, and that it can provide an improved assessment of the importance of various model components due to its correlation-based nature. [DOI: 10.1115/1.3072128] Keywords: model order/structure reduction, nonlinear systems, Karhunen-Loeve expansion, bond graphs

Objective: This paper extends a prior human operator model to capture human steering performance in the teleoperation of unmanned ground vehicles (UGVs) in path-following scenarios with varying speed. Background: A prior study presented a human operator model to predict human steering performance in the teleoperation of a passenger-sized UGV at constant speeds. To enable applications to varying speed scenarios, the model needs to be extended to incorporate speed control and be able to predict human performance under the effect of accelerations/decelerations and various time delays induced by the teleoperation setting. A strategy is also needed to parameterize the model without human subject data for a truly predictive capability. Method: This paper adopts the ACT-R cognitive architecture and two-point steering model used in the previous work, and extends the model by incorporating a far-point speed control model to allow for varying speed. A parameterization strategy is proposed to find a robust set of parameters for each time delay to maximize steering performance. Human subject experiments are conducted to validate the model. Results: Results show that the parameterized model can predict both the trend of average lane keeping error and its lowest value for human subjects under different time delays. Conclusions: The proposed model successfully extends the prior computational model to predict human steering behavior in a teleoperated UGV with varying speed. Application: This computational model can be used to substitute for human operators in the process of development and testing of teleoperated UGV technologies and allows fully simulation-based development and studies. [ABSTRACT FROM AUTHOR]

A dynamic system model is proper for a particular application if it achieves the accuracy required by the application with minimal complexity. Because model complexity often--but not always--correlates inversely with simulation speed, a proper model is often alternatively defined as one balancing accuracy and speed. Such balancing is crucial for applications requiring both model accuracy and speed, such as system optimization and hardware-in-the-loop simulation. Furthermore, the simplicity of proper models conduces to control system analysis and design, particularly given the ease with which lower-order controllers can be implemented compared to higher-order ones. The literature presents many algorithms for deducing proper models from simpler ones or reducing complex models until they become proper. This paper presents a broad survey of the proper modeling literature. To simplify the presentation, the algorithms are classified into frequency, projection, optimization, and energy based, based on the metrics they use for obtaining proper models. The basic mechanics, properties, advantages, and limitations of the methods are discussed, along with the relationships between different techniques, with the intention of helping the modeler to identify the most suitable proper modeling method for a given application. Keywords: proper modeling, model simplification, model reduction, model deduction, model partitioning

Motivated by military applications, this work considers connected platoons of ground vehicles of potentially different sizes and presents a model-free approach for optimizing the speed of the platoon to adjust the tradeoff between fuel economy and mobility as measured by travel speed. The motivation to seek a model-free solution is twofold: (1) vehicle models that are typically assumed to be available in model-based methods are not available on-board for military vehicles; (2) a model-free solution can offer robustness to modeling errors. Therefore, in this paper, the problem of optimizing the tradeoff between fuel economy and mobility of a mixed platoon is formulated as an optimization problem and solved using the model-free Nelder-Mead approach. To explore the performance characteristics of this approach, a case study is performed with two different size vehicles that are representative of military trucks, both in simulation and in a novel networked engine-in-the-loop setup. The results show that the proposed approach can achieve the desired balance between fuel economy and mobility in a model-free manner despite the nonlinearity caused by gear shift deadzones, albeit at the expense of relatively slow convergence time. In addition, a design guideline for the parameters in the Nelder-Mead approach is also discussed. [ABSTRACT FROM AUTHOR]