This dissertation describes the design, analysis, planning, and control of a self-reconfigurable modular robotic system. The proposed robotic system mainly contains three major types of robotic modules: load carrier, manipulation module, and locomotion module. Each module is capable of navigation and interaction with the environment individually. In addition, the robotic system is proposed to reassemble autonomously into various configurations to perform complex tasks such as humanoid configuration to enable enhanced functionality to reconfigure into a configuration that would enable the system to cross over a ditch. A non-back drivable active docking mechanism with two Degrees of Freedom (DOFs) was designed to fit into the tracked units of the robot modules for achieveing the reconfiguration. The quantity and location of the docking mechanisms are customizable and selectable to satisfy various mission requirements and adapt to different environments. During the reconfiguration process, the target coupling mechanism of each module reconfigurable with each other autonomously. A Lyapunov function-based precision controller was developed to align the target docking mechanisms in a close range and high precision for assembling the robot modules autonomously into other configurations. Additionally, an trajectory optimization algorithm was developed to help the robot determine when to switch the locomotion modes and find the fastest path to the destination with the desired pose. / Doctor of Philosophy / Though the capabilities of individual robot platforms have advanced greatly from their original rigid construction to more modern reconfigurable platforms, it is still difficult to build a singular platform capable of adapting to all situations and environments that users may want or need it to function in. To help improve the versatility of robot systems, modular robots have become an active area of research. These modular robotic systems are made up of multiple robotic platforms capable of docking together, breaking apart, or otherwise reconfiguring to form a multitude of shapes to overcome and adapt to many diverse challenges and environments. This dissertation describes the design of a new modular robotic system with autonomous docking and reconfiguration. Existing technologies and motivations for the creation of a new modular robotic system are covered. Then the physical design, with a primary focus on the docking mechanism, is reviewed. A validation of the proposed robotic system in a virtual environment with real physical properties is demonstrated. Following this, the development of a Lyapunov function-based controller to autonomously align the docking mechanisms is presented. The overall docking process was also preliminarily verified using a prototype of a locomotion module and an active docking mechanism. In addition, the trajectory optimization and tracking methods are presented in the end.

Strategies for topology optimization of trusses and plane stress domains for minimum weight subject to stress and displacement constraints by Simultaneous Analysis and Design (SAND) are considered. The ground structure approach is used. For the truss topology optimization, a penalty function formulation of SAND is compared with an augmented Lagrangian formulation. The efficiency of SAND in handling combinations of general constraints for truss topology optimization is tested. A strategy for obtaining an optimal topology by minimizing the compliance of the truss is compared with a direct weight minimization solution to satisfy stress and displacement constraints. It is shown that for some problems, starting from the ground structure and using SAND is better than starting from a minimum compliance topology design and optimizing only the cross sections for minimum weight under stress and displacement constraints. One case where the SAND approach could not predict a singular topology obtained by compliance minimization is discussed in detail. A member elimination strategy to save CPU time is developed. For the plane stress topology optimization problem, the ground structure is obtained by using 3 noded constant stress triangular elements. A chess board pattern is observed in the optimal topologies which may be attributed to the triangular elements. Some suggestions for future research are made. / Ph. D.

Autonomous robots are set to become ubiquitous in the future, with applications ranging from autonomous cars to assistive household robots. These systems must operate in close proximity of dynamic and static objects, including humans and other non-autonomous systems, adding complexity to their decision-making processes. The behaviour of such objects is often stochastic and hard to predict. Making robust decisions under such uncertain scenarios can be challenging for these autonomous robots. In the past, researchers have used deterministic approach to predict the motion of surrounding objects. However, these approaches can be over-confident and do not capture the stochastic behaviour of surrounding objects necessary for safe decision-making. In this dissertation, we show the importance of probabilistic prediction of surrounding dynamic objects and their incorporation into planning for safety-critical decision making. We utilise Bayesian inference models such as Monte Carlo dropout and deep ensemble to probabilistically predict the motion of surrounding objects. Our probabilistic trajectory forecasting model showed improvement over standard deterministic approaches and could handle adverse scenarios such as sensor noise and occlusion during prediction. The uncertainty-inclusive prediction of surrounding objects has been incorporated into planning. The inclusion of predicted states of surrounding objects with associated uncertainty enables the robot make proactive decisions while avoiding collisions. / Doctor of Philosophy / In future, humans will greatly rely on the assistance of autonomous robots in helping them with everyday tasks. Drones to deliver packages, cars for driving to places autonomously and household robots helping with day-to-day activities. In all such scenarios, the robot might have to interact with their surrounding, in particular humans. Robots working in close proximity to humans must be intelligent enough to make safe decisions not affecting or intruding the human. Humans, in particular make abrupt decisions and their motion can be unpredictable. It is necessary for the robot to understand the intention of human for navigating safely without affecting the human. Therefore, the robot must capture the uncertain human behaviour and predict its future motion so that it can make proactive decisions. We propose to capture the stochastic behaviour of humans using deep learning based prediction models by learning motion patterns from real human trajectories. Our method not only predicts future trajectory of humans but also captures the associated uncertainty during prediction. In this thesis, we also propose how to predict human motion under adverse scenarios like bad weather leading to noisy sensing as well as under occlusion. Further, we integrate the predicted stochastic behaviour of surrounding humans into the planning of the robot for safe navigation among humans.

The dynamic approach to fractional Brownian motion (FBM) establishes a link between non-Poisson renewal process with abrupt jumps resetting to zero the system's memory and correlated dynamic processes, whose individual trajectories keep a non-vanishing memory of their past time evolution. It is well known that the recrossing times of the origin by an ordinary 1D diffusion trajectory generates a distribution of time distances between two consecutive origin recrossing times with an inverse power law with index m=1.5. However, with theoretical and numerical arguments, it is proved that this is the special case of a more general condition, insofar as the recrossing times produced by the dynamic FBM generates process with m=2-H. Later, the model of ballistic deposition is studied, which is as a simple way to establish cooperation among the columns of a growing surface, to show that cooperation generates memory properties and, at same time, non-Poisson renewal events. Finally, the connection between trajectory and density memory is discussed, showing that the trajectory memory does not necessarily yields density memory, and density memory might be compatible with the existence of abrupt jumps resetting to zero the system's memory.

Trajectory planning is an important component of autonomous driving. It takes the result of route-level navigation plan and generates the motion-level commands that steer an autonomous passenger vehicle (APV). Prior work on solving this problem uses either a sampling-based or optimization-based trajectory planner, accompanied by some high-level rule generation components.

Fish behaviour analysis is a fundamental research area in marine ecology as it is helpful for detecting environmental changes by observing unusual fish patterns or new fish behaviours. The traditional way of analysing fish behaviour is by visual inspection using human observers, which is very time consuming and also limits the amount of data that can be processed. Therefore, there is a need for automatic algorithms to identify fish behaviours by using computer vision and machine learning techniques. The aim of this thesis is to help marine biologists with their work. We focus on behaviour understanding and analysis of detected and tracked fish with unusual behaviour detection approaches. Normal fish trajectories exhibit frequently observed behaviours while unusual trajectories are outliers or rare trajectories. This thesis proposes 3 approaches to detecting unusual trajectories: i) a filtering mechanism for normal fish trajectories, ii) an unusual fish trajectory classification method using clustered and labelled data and iii) an unusual fish trajectory classification approach using a clustering based hierarchical decomposition. The rule based trajectory filtering mechanism is proposed to remove normal fish trajectories which potentially helps to increase the accuracy of the unusual fish behaviour detection system. The aim is to reject normal fish trajectories as much as possible while not rejecting unusual fish trajectories. The results show that this method successfully filters out normal trajectories with a low false negative rate. This method is useful to assist building a ground truth data set from a very large fish trajectory repository, especially when the amount of normal fish trajectories greatly dominates the unusual fish trajectories. Moreover, it successfully distinguishes true fish trajectories from false fish trajectories which result from errors by the fish detection and tracking algorithms. A key contribution of this thesis is the proposed flat classifier, which uses an outlier detection method based on cluster cardinalities and a distance function to detect unusual fish trajectories. Clustered and labelled data are used to select feature sets which perform best on a training set. To describe fish trajectories 10 groups of trajectory descriptions are proposed which were not previously used for fish behaviour analysis. The proposed flat classifier improved the performance of unusual fish detection compared to the filtering approach. The performance of the flat classifier is further improved by integrating it into a hierarchical decomposition. This hierarchical decomposition method selects more specific features for different trajectory clusters which is useful considering the trajectory variety. Significantly improved results were obtained using this hierarchical decomposition in comparison to the flat classifier. This hierarchical framework is also applied to classification of more general imbalanced data sets which is a key current topic in machine learning. The experiments showed that the proposed hierarchical decomposition method is significantly better than the state of art classification methods, other outlier detection methods and unusual trajectory detection methods. Furthermore, it is successful at classifying imbalanced data sets even though the majority and minority classes contain varieties, and classes overlap which is frequently seen in real-world applications. Finally, we explored the benefits of active learning in the context of the hierarchical decomposition method, where active learning query strategies choose the most informative training data. A substantial performance gain is possible by using less labelled training data compared to learning from larger labelled data sets. Additionally, active learning with feature selection is investigated. The results show that feature selection has a positive effect on the performance of active learning. However, we show that random selection can be as effective as popular active learning query strategies in combination with active learning and feature selection, especially for imbalanced set classification.

Approved for public release, distribution is unlimited / problem, with engine thrust as the only possible perturbation. The optimal control problems are solved using the general purpose dynamic optimization software, DIDO. The dynamical model together with the fuel optimal control problem is validated by simulating several well known orbit transfers. By replicating the single satellite model, this thesis shows that a multi-satellite model which optimizes all vehicles concurrently can be easily built. The specific scenario under study involves the injection of multiple satellites from a common launch vehicle; however, the methods and model are applicable to spacecraft formation problems as well. / Major, United States Air Force

Nowadays, with the development of electronic and communication technologies, more and more low-cost vehicles such as small, light-weight aircraft are widely applied in all kinds of fields. Ground Station is an essential part of low cost vehicles for the operator to control and monitor the vehicles. In this thesis, Ground Station Display and Flight Management System for Low-Cost Vehicles have been developed.The major objective of this project is to design an intuitive and easy operative Human Machine Interface for displaying and monitoring the flight data and traffic information on ground. Meanwhile, a Graphic User Interface for the Flight Management System has been developed for realizing the waypoints input and flight plan for the vehicles. To fulfill this task, a low-cost hardware and software architecture is presented. Moreover, some COTS tools such as VAPS and MATLAB are applied for the software development because of their Object-Oriented and Rapid Prototype design methods. At the end of project, simulation has been done for the display HMI to test the behaviours of objects and the impacts of display. The trajectory simulation of flight management control panel is also implemented to test the waypoints creation, trajectory generation and smoothing.

High-flying unmanned reconnaissance and surveillance systems are now being used extensively in the United States military. Current development programs are producing demonstrations of next-generation unmanned flight systems that are designed to perform combat missions. Their use in first-strike combat operations will dictate operations in densely cluttered environments that include unknown obstacles and threats, and will require the use of terrain for masking. The demand for autonomy of operations in such environments dictates the need for advanced trajectory optimization capabilities. In addition, the ability to coordinate the movements of more than one aircraft in the same area is an emerging challenge. This thesis examines using an analytical reduced order formulation for trajectory generation for minimum time and terrain masking cases. First, pseudo-3D constant velocity equations of motion are used for path planning for a single vehicle. In addition, the inclusion of winds, moving targets and moving threats is considered. Then, this formulation is increased to using 3D equations of motion, both with a constant velocity and with a simplified varying velocity model. Next, the constant velocity equations of motion are expanded to include the simultaneous path planning of an unspecified number of vehicles, for both aircraft avoidance situations and formation flight cases.

In this paper, we present a novel approach to mine moving object group patterns from object movement database. At first, our approaches summarize the raw data in the source object movement database into trajectories, and then discover valid 2-groups mainly from the trajectory-based object movement database. We propose two trajectory conversion methods, namely linear regression and vector conversion. We further propose a trajectory based mobile group mining algorithm that is intended to reduce the overhead of mining 2-Group Patterns. The use of trajectories allows valid 2-groups to be mined using smaller number of summarized records (in trajectory model) and examining smaller number of candidate 2-groups. Finally, we conduct series of comprehensive experiments to evaluate and compare the performances of the proposed methods with existing approaches that use source object movement database or other summarization techniques. The experimental results demonstrate the superior performance of our proposed approach.