Search Results

In the next 20 years fully autonomous vehicles are expected to be in the market. The advance on their development is creating paradigm shifts on different automotive related research areas. Vehicle interiors design and human vehicle interaction are evolving to enable interaction flexibility inside the cars. However, most of today’s vehicle manufacturers’ autonomous car concepts maintain the steering wheel as a control element. While this approach allows the driver to take over the vehicle route if needed, it causes a constraint in the previously mentioned interaction flexibility. Other approaches, such as the one proposed by Google, enable interaction flexibility by removing the steering wheel and accelerator and brake pedals. However, this prevents the users to take control over the vehicle route if needed, not allowing them to make on-route spontaneous decisions, such as stopping at a specific point of interest.

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.

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.

Image segmentation has historically been a technique for analyzing terrain for military autonomous vehicles. One of the weaknesses of image segmentation from camera data is that it lacks depth information, and it can be affected by environment lighting. Light detection and ranging (LiDAR) is an emerging technology in image segmentation that is able to estimate distances to the objects it detects. One advantage of LiDAR is the ability to gather accurate distances regardless of day, night, shadows, or glare. This study examines LiDAR and camera image segmentation fusion to improve an advanced driver-assistance systems (ADAS) algorithm for off-road autonomous military vehicles. The volume of points generated by LiDAR provides the vehicle with distance and spatial data surrounding the vehicle.

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.

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.

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.

Vehicle dynamics simulation is one of the newest and most valuable technologies being applied in the racing world today. Professional designers and race teams are investing heavily to test and improve the dynamics of their suspension systems through this new technology. This paper discusses the testing of one of Clemson University's most recent Formula SAE racecars on a seven-poster vehicle dynamics simulator; commonly known as a “shaker rig.” Testing of the current dampers using a shock dynamometer was conducted prior to testing and results are included for further support of conclusions. The body of the paper is a discussion of the setup and testing procedures involved with the dynamic simulator. The results obtained from the dynamic simulator tests are then analyzed in conjunction with the shock dynamometer results. Conclusions are formed from test results and methods for future improvements to be applied in Formula SAE racing are suggested.

In the U.S., the teenage driving population is at the highest risk of being involved in a crash. Teens often demonstrate poor vehicle control skills and poor ability to identify hazards, thus proper understanding of automotive indicators and warnings may be even more critical for this population. This research evaluates teen drivers’, between 15 to 17 years of age, understanding of symbols from vehicles featuring advanced driving assistant systems and multiple powertrain configurations. Teen drivers’ (N=72) understanding of automotive symbols was compared to three other groups with specialized driving experience and technical knowledge: automotive engineering graduate students (N=48), driver rehabilitation specialists (N=16), and performance driving instructors (N=15). Participants matched 42 symbols to their descriptions and then selected the five symbols they considered most important.

Drive cycles are a core piece of vehicle development testing methodology. The control and calibration of the vehicle is often tuned over drive cycles as they are the best representation of the real-world driving the vehicle will see during deployment. To obtain general performance numerous drive cycles must be generated to ensure final control and calibration avoids overfitting to the specifics of a single drive cycle. When real-world driving cycles are difficult to acquire methods can be used to create statistically similar synthetic drive cycles to avoid the overfitting problem. This subject has been well addressed within the passenger vehicle domain but must be expanded upon for utilization with tracked off-road vehicles. Development of hybrid tracked vehicles has increased this need further. This study shows that turning dynamics have significant influence on the vehicle power demand and on the power demand on each individual track.

Adiabatic heating during plastic straining can slow the diffusionless shear transformation of austenite to martensite in steels that exhibit transformation induced plasticity (TRIP). However, the extent to which the transformation is affected over a strain rate range of relevance to automotive stamping and vehicle impact events is unclear for most third-generation advanced high strength TRIP steels. In this study, an 1180MPa minimum tensile strength TRIP steel with carbide-free bainite is evaluated by measuring the variation of retained austenite volume fraction (RAVF) in fractured tensile specimens with position and strain. This requires a combination of servo-hydraulic load frame instrumented with high speed stereo digital image correlation for measurement of strains and ex-situ synchrotron x-ray diffraction for determination of RAVF in fractured tensile specimens.

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.

Spark-assisted compression ignition (SACI) leverages flame propagation to trigger autoignition in a controlled manner. The autoignition event is highly sensitive to several parameters, and thus, achieving SACI in production demands a high tolerance to variations in conditions. Limited research is available to quantify the combustion response of SACI to these variations. A simulation study is performed to establish trends, limits, and control implications for SACI combustion over a wide range of conditions. The operating space was evaluated with a detailed chemical kinetics model. Key findings were synthesized from these results and applied to a 1-D engine model. This model identified performance characteristics and potential actuator positions for a production-viable SACI engine. This study shows charge preparation is critical and can extend the low-load limit by strengthening flame propagation and the high-load limit by reducing ringing intensity.

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.

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).

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.

Modern turbocharged spark-ignition engines are being equipped with an increasing number of control actuators to meet fuel economy, emissions, and performance targets. The response time variations between engine control actuators tend to be significant during transients and necessitate highly complex actuator scheduling routines. Model Predictive Control (MPC) has the potential to significantly reduce control calibration effort as compared to the current methodologies that are based on decentralized feedback control strategies. MPC strategies simultaneously generate all actuator responses by using a combination of current engine conditions and optimization of a control-oriented plant model. To achieve real-time control, the engine model and optimization processes must be computationally efficient without sacrificing effectiveness. Most MPC systems intended for real-time control utilize a linearized model that can be quickly evaluated using a sub-optimal optimization methodology.

It’s important to predict human actions in the industry assembly process. Foreseeing future actions before they happened is an essential part for flexible human-robot collaboration and crucial to safety issues. Vision-based human action prediction from videos provides intuitive and adequate knowledge for many complex applications. This problem can be interpreted as deducing the next action of people from a short video clip. The history information needs to be considered to learn these relations among time steps for predicting the future steps. However, it is difficult to extract the history information and use it to infer the future situation with traditional methods. In this scenario, a model is needed to handle the spatial and temporal details stored in the past human motions and construct the future action based on limited accessible human demonstrations.

This article presents a pointing gesture-based point of interest computation method via pointing rays’ intersections for situated awareness interactions in vehicles. The proposed approach is compared with two alternative methods: (a) a point of interest identification method based on the intersection of the pointing ray with the point cloud (PoC) resulting from the vehicle sensors, and (b) the traditional ray-casting approach, where the point of interest is computed based on the first intersection of the pointing rays with locations stored in a 2D annotated map. Simulation results show that the presented method outperforms by 36.25% the traditional ray casting one. However, as it was expected, the sensor-based computation method is more accurate. The validation of our approach was conducted by experiments performed in a test track facility.

Low pressure (LP) and cooled EGR systems are capable of increasing fuel efficiency of turbocharged gasoline engines, however they introduce control challenges. Accurate exhaust pressure modeling is of particular importance for real-time feedforward control of these EGR systems since they operate under low pressure differentials. To provide a solution that does not depend on physical sensors in the exhaust and also does not require extensive calibration, a coupled temperature and pressure physics-based model is proposed. The exhaust pipe is split into two different lumped sections based on flow conditions in order to calculate turbine-outlet pressure, which is the driving force for LP-EGR. The temperature model uses the turbine-outlet temperature as an input, which is known through existing engine control models, to determine heat transfer losses through the exhaust.