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.

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.

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.

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.

Range anxiety and lack of adequate access to fast charging are proving to be important impediments to electric vehicle (EV) adoption. While many techniques to fast charging EV batteries (model-based & model-free) have been developed, they have focused on a single Lithium-ion cell. Extensions to battery packs are scarce, often considering simplified architectures (e.g., series-connected) for ease of modeling. Computational considerations have also restricted fast-charging simulations to small battery packs, e.g., four cells (for both series and parallel connected cells). Hence, in this paper, we pursue a model-free approach based on reinforcement learning (RL) to fast charge a large battery pack (comprising 444 cells). Each cell is characterized by an equivalent circuit model coupled with a second-order lumped thermal model to simulate the battery behavior. After training the underlying RL, the developed model will be straightforward to implement with low computational complexity.

This paper proposes a novel reconfigurable battery balancing topology and reinforcement learning-based intelligent balancing management system. The different degradations cause a significant loss of battery pack available capacity, as the pack power output relies on the weakest cell due to the relevant physical requirements. To handle this capacity drop issue, a reconfigurable battery topology is adopted to improve the usability of the heterogeneous battery. There are some existing battery reconfigurable topologies in the literature. However, these studies rely on the limited options of topology designs, and there is a lack of study on the reconfigurability of these designs and other possible new designs. Also, it is rare to find an optimal management system for the reconfigurable battery topology. To fill these research gaps, this paper explores existing battery reconfigurable topology designs and proposes a new reconfigurable topology for battery balancing.

Integrated modeling of vehicle, tire and terrain is a fundamental challenge to be addressed for off-road autonomous navigation. The complexities arise due to lack of tools and techniques to predict the continuously varying terrain and environmental conditions and the resultant non-linearities. The solution to this challenge can now be found in the plethora of data driven modeling and control techniques that have gained traction in the last decade. Data driven modeling and control techniques rely on the system’s repeated interaction with the environment to generate a lot of data and then use a function approximator to fit a model for the physical system with the data. Getting good quality and quantity of data may involve extensive experimentation with the physical system impacting developer’s resource. The process is computationally expensive, and the overhead time required is high.

The application of virtual engineering methods can streamline the product design process through improved collaboration opportunities among the technical staff and facilitate additive manufacturing processes. A product digital twin can be created using the available computer-aided design and analytical mathematical models to numerically explore the current and future system performance based on operating cycles. The strategic decision to implement a digital twin is of interest to companies, whether the required financial and workforce resources will be worthwhile. In this paper, two metrics are introduced to assist management teams in evaluating the technology potential. The usefulness and time savings metrics will be presented with accompanying definitions. A case study highlights the usefulness metric for the “Deep Orange” prototype vehicle, an innovative off-road hybrid vehicle designed and fabricated at Clemson University.

Autonomous vehicles (AV) are sophisticated systems comprising various sensors, powerful processors, and complex data processing algorithms that navigate autonomously to their respective goals. Out of several functions performed by an AV, one of the most important is developing situational intelligence to predict collision-free future trajectories. As an AV operates in environments consisting of various entities, such as other AVs, human-driven vehicles, and static obstacles, developing situational intelligence will require a collaborative approach. The recent developments in artificial intelligence (AI) and deep learning (DL) relating to AVs have shown that DL-based models can take advantage of information sharing and collaboration to develop such intelligence.

Semantic segmentation is an integral component in many autonomous vehicle systems used for tasks like path identification and scene understanding. Autonomous vehicles must make decisions quickly enough so they can react to their surroundings, therefore, they must be able to segment the environment at high speeds. There has been a fair amount of research on semantic segmentation, but most of this research focuses on achieving higher accuracy, using the mean intersection over union (mIoU) metric rather than higher inference speed. More so, most of these semantic segmentation models are trained and evaluated on urban areas instead of off-road environments. Because of this there is a lack of knowledge in semantic segmentation models for use in off-road unmanned ground vehicles.

In this paper, a reinforcement learning-based method is proposed to adapt autonomous vehicle passengers’ expectation of comfort through in-situ human-vehicle interaction. Ride comfort has a significant influence on the user’s experience and thus acceptance of autonomous vehicles. There is plenty of research about the motion planning and control of autonomous vehicles. However, limited studies have explicitly considered the comfort of passengers in autonomous vehicles. This paper studies the comfort of humans in autonomous vehicles longitudinal autonomous driving. The paper models and then improves passengers’ feelings about autonomous driving behaviors. This proposed approach builds a control and adaptation strategy based on reinforcement learning using human’s in-situ feedback on autonomous driving. It also proposes an adaptation of humans to autonomous vehicles to account for improper human driving expectations.

Modeling and simulation of ground vehicles can be a computationally expensive problem due to the complexity of high-fidelity vehicle models. Often to determine mobility metrics, multiple stochastic simulations need to be evaluated. Surrogate models, or models of models, offer a means to reduce the computational cost of these simulation efforts. Since various types of surrogate models are available to the user, choosing the best surrogate model for a simulation is mostly the challenging process. In this paper, the process of selecting surrogate models and its uses based on model metafeatures is presented. The approach formulates this decision as a trade-off among three main drivers, required dataset size (how much information is necessary to compute the surrogate model), surrogate model accuracy (how accurate the surrogate model must be) and total computational time (how much time is required for the surrogate modeling process).

The integration of sensors, actuators, and real-time control in transportation systems enables intelligent system operation to minimize energy consumption and maximize occupant safety and vehicle reliability. The operating cycle of military ground vehicles can be on- and off-road in harsh weather and adversarial environments, which demands continuous subsystem functionality to fulfill missions. Onboard diagnostic systems can alert the operator of a degraded operation once established fault thresholds are exceeded. An opportunity exists to estimate vehicle maintenance needs using model-based predicted trends and eventually compiled information from fleet operating databases. A digital twin, created to virtually describe the dynamic behavior of a physical system using computer-mathematical models, can estimate the system behavior based on current and future operating scenarios while accounting for past effects.

Artificial intelligence (AI) enhanced control system deployments are emerging as a viable substitute to more traditional control system. In particular, deep learning techniques offer an alternate approach to tune the ever increasing sets of control system parameters to extract performance. However, the systematic verification and validation (to establish the reliability and robustness) of deep learning based controllers in actual deployments remains a challenge. This is exacerbated by the need to evaluate and optimize control systems embedded within an operational environment (with its own sets of additional unknown or uncertain parameters). Existing literature comparisons of deep learning against traditional controllers, where they may exist, do not offer structured approaches to comparative performance evaluation and improvement. It is also crucial to develop a standardized controlled test environment within which various controllers are evaluated against a common metric.

Recent trends in autonomy have emphasized end-to-end deep-learning-based methods that have shown a lot of promise in overcoming the requirements and limitations of feature-engineering. However, while promising, the black-box nature of deep-learning frameworks now exacerbates the need for testing with end-to-end deployments. Further, as exemplars of systems-of-systems, autonomous vehicles (AVs) engender numerous interconnected component-, subsystem and system-level interactions. The ensuing complexity creates challenges for verification and validation at the various component, subsystem- and system-levels as well as end-to-end testing. While simulation-based testing is one promising avenue, oftentimes the lack of adequate fidelity of AV and environmental modeling limits the generalizability. In contrast, full-scale AV testing presents the usual limitations of time-, space-, and cost.

This study investigates the use of machine learning methods for the selection of energy storage devices in military electrified vehicles. Powertrain electrification relies on proper selection of energy storage devices, in terms of chemistry, size, energy density, and power density, etc. Military vehicles largely vary in terms of weight, acceleration requirements, operating road environment, mission, etc. This study aims to assist the energy storage device selection for military vehicles using the data-drive approach. We use Machine Learning models to extract relationships between vehicle characteristics and requirements and the corresponding energy storage devices. After the training, the machine learning models can predict the ideal energy storage devices given the target vehicles design parameters as inputs. The predicted ideal energy storage devices can be treated as the initial design and modifications to that are made based on the validation results.

Non-linear model predictive engine control (nMPC) systems have the ability to reduce calibration effort while improving transient engine response. The main drawback of nMPC for engine control is the computational power required to realize real-time operation. Most of this computational power is spent linearizing the non-linear plant model at each time step. Additionally, the effectiveness of the nMPC system relies heavily on the accuracy of the model(s) used to predict the future system behavior, which can be difficult to model physically. This paper introduces a hybrid modeling approach for internal combustion engines that combines physics-based and machine learning techniques to generate accurate models that can be linearized with low computational power. This approach preserves the generalization and robustness of physics-based models, while maintaining high accuracy of data-driven models. Advantages of applying the proposed model with nMPC are discussed.

Learning only from a small set of examples remains a huge challenge in machine learning. Despite recent breakthroughs in the applications of neural networks, the applicability of these techniques has been limited by the requirement for large amounts of training data. What’s more, the standard supervised machine learning method does not provide a satisfactory solution for learning new concepts from little data. However, the ability to learn enough information from few samples has been demonstrated in humans. This suggests that humans may make use of prior knowledge of a previously learned model when learning new ones on a small amount of training examples. In the area of autonomous driving, the model learns to drive the vehicle with training data from humans, and most machine learning based control algorithms require training on very large datasets. Collecting and constructing training data set takes a huge amount of time and needs specific knowledge to gather relevant information.