As autonomous vehicles begin to move towards full autonomy, the controllers and software within them are becoming incredibly more complex to deal with any plausible scenario. Automotive manufacturers must balance the need for safety with the customers' desire for performance and features. A robust set of tools is a necessity to develop vehicle control protocols and navigation strategies. Vehicle to everything communication protocols and path planning are two aspects of autonomous vehicles that need a large amount of development effort. The MathWorks has put a great amount of effort in developing a robust simulation tool for autonomous vehicles. However, it currently lacks a method to develop V2X communication and path routing. In this thesis, I developed an extension for the Mathworks Simulink autonomous driving toolbox to incorporate graph-based path planning and vehicle to vehicle communication. The navigation system models each road using standard civil engineering techniques, to calculate the intersection points and bounding areas for regions of interest. Based on these regions, a directed graph is created to aid in calculating the shortest path. The navigation system also provides a redundant method for path planning for poorly marked areas and intersections. The vehicle to vehicle communication system emulates the 802.11p protocol and deals with practical challenges such as latency to provide developers with a realistic environment in which to develop vehicle communication protocols. The final result is a simulation where multiple vehicles drive safely and efficiently throughout a city network, sending messages at regions of interest and follow computed paths to their desired destinations. / Thesis / Master of Applied Science (MASc) / Vehicle to Everything communication protocols and path planning are two aspects of autonomous vehicles that need a robust framework to aid in their development. I developed an extension for the Mathworks Simulink autonomous driving toolbox to incorporate graph-based path planning and vehicle to vehicle communication. The navigation system models each road using standard civil engineering techniques, to calculate the intersection points and bounding areas for regions of interest. Based on these regions, a directed graph is created to aid in calculating the shortest path. The navigation system also provides a redundant method for path planning for poorly marked areas and intersections. The vehicle to vehicle communication system emulates the 802.11p protocol and realistic effects such as latency to provide developers with a realistic environment to develop vehicle communication protocols. The final result is a simulation where multiple vehicles drive throughout a city network, sending messages at regions of interest and follow a computed path to their desired destination.

As autonomous vehicles (AVs) evolve, ensuring their safety extends beyond traditional met- rics. While current nominal safety scores focus on the timeliness of AV responses like latency or instantaneous response time, this paper proposes expanding the concept to include spatial configurations formed by obstacles with respect to the ego-vehicle. By analyzing these spatial relationships, including proximity, density and arrangement, this research aims to demon- strate how these factors influence the safety force field around the AV. The goal is to show that beyond meeting Responsibility-Sensitive Safety (RSS) metrics, spatial configurations significantly impact the safety force field, particularly affecting path planning capability. High spatial occupancy of obstacle configurations can impede easy maneuverability, thus challenging safety-critical modules like path planning. This paper aims to capture this by proposing a safety score that leverages the ability of modern computer vision techniques, par- ticularly image segmentation models, to capture high and low levels of spatial and contextual information. By enhancing the scope of nominal safety to include such spatial analysis, this research aims to broaden the understanding of drivable space and enable AV designers to evaluate path planning algorithms based on spatial configuration centric safety levels. / Master of Science / As self-driving cars become more common, ensuring their safety is crucial. While current safety measures focus on how quickly these cars can react to dangers, this paper suggests that understanding the spatial relationships between the car and obstacles is just as important, and needs to be explored further. Prior metrics use velocity and acceleration of all the actors, to determine the safe-distance of obstacles from the vehicle, and determine how fast the car should react before a predicted collision. This paper aims to extend the scope of how safety is viewed during normal operating conditions of the vehicle by considering the arrangement of obstacles around it as an influencing factor to safety. By using advanced computer vision techniques, particularly models that can understand images in detail, this research proposes a new spatial safety metric. This score considers how well the car navigates through dense environments by understanding the spatial configurations that obstacles form. By studying these factors, I wish to introduce a metric that improves how self-driving cars are designed to navigate and path plan safely on the roads.

The presented research concerns the control of unmanned vehicles. The results introduced in this dissertation provide a solid control framework for a wide class of nonlinear uncertain systems, with a special emphasis on issues related to implementation, such as control input amplitude and rate saturation, or partial state measurements availability. More specifically, an adaptive control framework, allowing to enforce amplitude and rate saturation of the command, is developed. The motion control component of this framework, which works in conjunction with a saturation algorithm, is then specialized to different types of vehicles. Vertical take-off and landing aerial vehicles and a general class of autonomous marine vehicles are considered. A nonlinear control algorithm addressing the tracking problem for a class of underactuated, non-minimum phase marine vehicles is then introduced. This motion controller is extended, using direct and indirect adaptive techniques, to handle parametric uncertainties in the system model. Numerical simulations are used to illustrate the efficacy of the algorithms. Next, the output feedback control problem is treated, for a large class of nonlinear and uncertain systems. The proposed solution relies on a novel nonlinear observer which uses output measurements and partial knowledge of the system's dynamics to reconstruct the entire state for a wide class of nonlinear systems. The observer is then extended to operate in conjunction with a full state feedback control law and solve both the output feedback control problem and the state observation problem simultaneously. The resulting output feedback control algorithm is then adjusted to provide a high level of robustness to both parametric and structural model uncertainties. Finally, in a natural extension of these results from motion control of a single system to collaborative control of a group of vehicles, a cooperative control framework addressing limited communication issues is introduced. / Ph. D.

Autonomous vehicles are the subject of intense research because they are a safe and convenient alternative to present-day vehicles. Human drivers base their navigational decisions primarily on visual information and researchers have been attempting to use computers to do the same. The current challenge in using computer vision lies not in the collection or transmission of visual data, but in the perception of visual data to extract from it useful information. The focus of this thesis is on the use of computer vision to navigate an autonomous vehicle that will participate in the Intelligent Ground Vehicle Competition (IGVC.) This document starts with a description of the IGVC and the software design of an autonomous vehicle. This thesis then focuses on the weakest link in the system - the computer vision module. Vehicles at the IGVC are expected to autonomously navigate an obstacle course. Competing vehicles need to recognize and stay between lines painted on grass or pavement. The research presented in this document describes two methods used for boundary line extraction: color-based object extraction, and shape analysis for line recognition. This is the first time a combination of these methods is being applied to the problem of line recognition in the context of the IGVC. The most significant contribution of this work is a method for extracting lines in a binary image even when the line is attached to a shape that is not a line. Novel methods have been used to simplify camera calibration, and for perspective correction of the image. The results give promise of vastly improved autonomous vehicle performance. / Master of Science

<p dir="ltr">Motion planning for Autonomous Vehicles (AVs) and Connected Autonomous Vehicles (CAVs) involves the crucial task of translating road environmental data obtained from sensors and connectivity devices into a sequence of executable vehicle actions. This task is critical for AVs and CAVs, because the efficacy of their driving decisions and overall performance depend on the quality of motion planning.</p><p dir="ltr">In the context of motion planning technologies, several fundamental questions and challenges remain despite the widespread adoption of advanced learning-based methods, including deep learning (DL) and deep reinforcement learning (DRL). In this regard, the following critical questions need to be answered: 1) How to design suitable DL architectures to comprehensively understand the driving scenario by integrating data from diverse sources including sensors and connectivity devices? 2) How to effectively use the fused information to make improved driving decisions, accounting for various optimality criteria? 3) How to leverage vehicle connectivity to generate cooperative decisions for multiple CAVs, in a manner that optimizes system-wide utility? 4) How to address the inherent interpretability limitations of DL-based methods to enhance user trust in AVs and CAVs? 5) Is it possible to extend learning-based approaches to operational-level decisions in a way that overcomes the inherent disadvantage of low explainability and lack of safety guarantee?</p><p dir="ltr">In an effort to address these questions and expand the existing knowledge in this domain, this dissertation introduces several learning-based motion planning frameworks tailored towards different driving scenarios of AV and CAV. Technically, these efforts target on developing trustworthy AI systems with a focus on the information fusion, “explainable AI” or XAI and safety critical AI. From a computational perspective, these frameworks introduce new learning-based models with state-of-the-art (SOTA) structures, including Convolutional Neural Network (CNN). Recurrent Neural Networks (RNN), Graph Neural Networks (GNN), Attention networks, and Transformers. They also incorporate reinforcement learning (RL) agents, such as Deep Q Networks (DQN) and Model-based RL. From an application standpoint, these developed frameworks can be deployed directly in AVs and CAVs at Level 3 and above. This can enhance the AV/CAV performance in terms of individual and system performance metrics, including safety, mobility, efficiency, and driving comfort.</p>

The research presented in this dissertation pertains to the development of a real time SLAM solution that can be performed by a low cost autonomous underwater vehicle equipped with low cost and memory constrained computing resources. The design of a custom rangefinder for underwater applications is presented. The rangefinder makes use of two laser line generators and a camera to measure the unknown distance to objects in an underwater environment. A visual odometry algorithm is introduced that makes use of a downward facing camera to provide our underwater vehicle with localization information. The sensor suite composed of the laser rangefinder, downward facing camera, and a digital compass are verified, using the Extended Kalman Filter based solution to the SLAM problem along with the particle filter based solution known as FastSLAM, to ensure that they provide in- formation that is accurate enough to solve the SLAM problem for out low cost underwater vehicle. Next, an extension of the FastSLAM algorithm is presented that stores the map of the environment using an occupancy grid is introduced. The use of occupancy grids greatly increases the amount of memory required to perform the algorithm so a version of the Fast- SLAM algorithm that stores the occupancy grids using the Haar wavelet representation is presented. Finally, a form of the FastSLAM algorithm is presented that stores the occupancy grid in compressed form to reduce the amount memory required to perform the algorithm. It is shown in experimental results that the same result can be achieved, as that produced by the algorithm that stores the complete occupancy grid, using only 40% of the memory required to store the complete occupancy grid. / Ph. D.

Autonomous navigation of mobile robots through unstructured terrain presents many challenges. The task becomes even more difficult with increasing obstacle density, at higher speeds, and when a priori knowledge of the terrain is not available. Reactive navigation schemas are often dismissed as overly simplistic or considered to be inferior to deliberative approaches for off-road navigation. The Potential Field algorithm has been a popular reactive approach for low speed, highly maneuverable mobile robots. However, as vehicle speeds increase, Potential Fields becomes less effective at avoiding obstacles. The traditional shortcomings of the Potential Field approach can be largely overcome by using dynamically expanding perception zones to help track objects of immediate interest. This newly developed technique is hereafter referred to as the Dynamic Expanding Zones (DEZ) algorithm. In this approach, the Potential Field algorithm is used for waypoint navigation and the DEZ algorithm is used for obstacle avoidance. This combination of methods facilitates high-speed navigation in obstacle-rich environments at a fraction of the computational cost and complexity of deliberative methods. The DEZ reactive navigation algorithm is believed to represent a fundamental contribution to the body of knowledge in the area of high-speed reactive navigation. This method was implemented on the Virginia Tech DARPA Grand Challenge vehicles. The results of this implementation are presented as a case study to demonstrate the efficacy of the newly developed DEZ approach. / Master of Science

In this dissertation, we seek to improve the dynamic modeling and control of autonomous underwater vehicles (AUVs). We address nonlinear hydrodynamic modeling, simplifying modeling assumptions, and robust control for AUVs. In the literature, various hydrodynamic models exist with varying model complexity and with no universally accepted model. We compare various hydrodynamic models traditionally employed to predict the motion of AUVs by estimating model coefficients using least-squares and adaptive identifier techniques. Additionally, we derive several dynamic models for an AUV employing varying sets of simplifying assumptions. We experimentally assess the efficacy of invoking typical assumptions to simplify the equations of motion. For robust control design, we develop a procedure for designing robust attitude controllers based on loop-shaping ideas. We specifically address the challenge of adjusting the desired actuator bandwidth in a loop-shaping design framework. Finally, we present a novel receding horizon H-infinity control algorithm to improve the control of autonomous vehicle systems working in high-disturbance environments, employing a Markov jump linear system framework to model the stochastic and non-stationary disturbances experienced by the vehicle. Our main results include a new Bounded Real Lemma for stability analysis and an output feedback H-infinity control synthesis algorithm. This work uses numerical simulations and extensive field trials of autonomous underwater vehicles to identify and verify dynamic models and to validate control algorithms developed herein. / Ph. D. / In this dissertation, we seek to improve the dynamic modeling and control of autonomous underwater vehicles (AUVs). We compare different models employed to predict the motion of AUVs, and we derive several dynamic models for an AUV employing varying sets of simplifying assumptions. We experimentally assess the efficacy of invoking typical assumptions to simplify the equations of motion. For robust control design, we develop a procedure for designing robust controllers that do not produce excessive fin movements. Finally, we present a novel robust control algorithm to improve the control of autonomous vehicle systems working in high-disturbance environments. This work uses numerical simulations and extensive field trials of autonomous underwater vehicles to identify and verify dynamic models and to validate control algorithms developed herein.

Students at Virginia Tech have been developing autonomous vehicles for the past five years. The purpose of these vehicles has been primarily for entry in the annual international Intelligent Ground Vehicle Competition (IGVC), however further applications for autonomous vehicles range from UneXploded Ordinance (UXO) detection and removal to planetary exploration. Recently, Virginia Tech developed a successful autonomous vehicle named Navigator. Navigator was developed primarily for entry in the IGVC, but also intended for use as a research platform. For navigation, Navigator uses a local obstacle avoidance method known as the Vector Field Histogram (VFH). However, in order to form a complete navigation scheme, the local obstacle avoidance algorithm must be coupled with a global map. This work presents a simple algorithm for developing a quasi-free space global map. The algorithm is based on the premise that the robot will be given multiple attempts at a particular goal. During early attempts, Navigator explores using solely local obstacle avoidance. While exploring, Navigator records where it has been and uses this information on subsequent attempts. Further, this thesis outlines the look-ahead method by which the global map is implemented. Finally, both simulated and experimental results are presented. The aforementioned global map building algorithm uses a common method of localization known as odometry. Odometry, also referred to as dead reckoning, is subject to inaccuracy caused by systematic and non-systematic errors. In many cases, the most dominant source of inaccuracy is systematic errors. Systematic errors are inherent to the vehicle; therefore, the dead reckoning inaccuracy grows unbounded. Fortunately, it is possible to largely eliminate systematic errors by calibrating the parameters such that the differences between the nominal dimensions and the actual dimensions are minimized. This work presents a method for calibration of mobile robot parameters using optimization. A cost function is developed based on the well-known UMBmark (University of Michigan Benchmark) test pattern. This method is presented as a simple time efficient calibration tool for use during startup procedures of a differentially driven mobile robot. Results show that this tool consistently gives greater than 50% improvement in overall dead reckoning accuracy on an outdoor mobile robot. / Master of Science

Research in mobile robotics, unmanned systems, and autonomous man-portable vehicles has grown rapidly over the last decade. This push has taken the problems of robot cognition and behavioral control out of the lab and into the field. Two good examples of this are the DARPA Urban Challenge autonomous vehicle race and the RoboCup robot soccer competition. In these challenges, a mobile robot must be capable of completing complex, sophisticated tasks in a dynamic, partially observable and unpredictable environment. Such conditions necessitate a behavioral programming approach capable of performing high-level action selection in the presence of multiple goals of dynamically changing importance, and noisy, incomplete perception data. In this thesis, an approach to behavioral programming is presented that provides the designer with an intuitive method for building contextual intelligence while preserving the qualities of emergent behavior present in traditional behavior-based programming. This is done by using a modified hierarchical state machine for behavior arbitration in sequence with a command fusion mechanism for cooperative and competitive control. The presented approach is analyzed with respect to portability across platforms, missions, and functional requirements. Specifically, two landmark case-studies, the DARPA Urban Challenge and the International RoboCup Competition are examined. / Master of Science