The majority of drones are extremely simple, their functions include flight and sometimes recording video and audio. While drone technology has continued to improve these functions, particularly flight, additional functions have not been added to mainstream drones. Although these basic functions serve as a good framework for drone designs, it is now time to extend off from this framework. With this Honors Thesis project, we introduce a new function intended to eventually become common to drones. This feature is a grasping mechanism that is capable of perching on branches and carrying loads within the weight limit. This concept stems from the natural behavior of many kinds of insects. It paves the way for drones to further imitate the natural design of flying creatures. Additionally, it serves to advocate for dynamic drone frames, or morphing drone frames, to become more common practice in drone designs.

The research presented in this Honors Thesis provides development in machine learning models which predict future states of a system with unknown dynamics, based on observations of the system. Two case studies are presented for (1) a non-conservative pendulum and (2) a differential game dictating a two-car uncontrolled intersection scenario. In the paper we investigate how learning architectures can be manipulated for problem specific geometry. The result of this research provides that these problem specific models are valuable for accurate learning and predicting the dynamics of physics systems.<br/><br/>In order to properly model the physics of a real pendulum, modifications were made to a prior architecture which was sufficient in modeling an ideal pendulum. The necessary modifications to the previous network [13] were problem specific and not transferrable to all other non-conservative physics scenarios. The modified architecture successfully models real pendulum dynamics. This case study provides a basis for future research in augmenting the symplectic gradient of a Hamiltonian energy function to provide a generalized, non-conservative physics model.<br/><br/>A problem specific architecture was also utilized to create an accurate model for the two-car intersection case. The Costate Network proved to be an improvement from the previously used Value Network [17]. Note that this comparison is applied lightly due to slight implementation differences. The development of the Costate Network provides a basis for using characteristics to decompose functions and create a simplified learning problem.<br/><br/>This paper is successful in creating new opportunities to develop physics models, in which the sample cases should be used as a guide for modeling other real and pseudo physics. Although the focused models in this paper are not generalizable, it is important to note that these cases provide direction for future research.

The seamless integration of autonomous vehicles (AVs) into highly interactive and dynamic driving environments requires AVs to safely and effectively communicate with human drivers. Furthermore, the design of motion planning strategies that satisfy safety constraints inherit the challenges involved in implementing a safety-critical and dynamics-aware motion planning algorithm that produces feasible motion trajectories. Driven by the complexities of arriving at such a motion planner, this thesis leverages a motion planning toolkit that utilizes spline parameterization to compute the optimal motion trajectory within a dynamic environment. Our approach is comprised of techniques originating from optimal control, vehicle dynamics, and spline interpolation. To ensure dynamic feasibility of the computed trajectories, we formulate the optimal control problem in relation to the intrinsic state constraints derived from the bicycle state space model. In addition, we apply input constraints to bound the rate of change of the steering angle and acceleration provided to the system. To produce collision-averse trajectories, we enforce extrinsic state constraints extracted from the static and dynamic obstacles in the circumambient environment. We proceed to exploit the mathematical properties of B-splines, such as the Convex Hull Property, and the piecewise composition of polynomial functions. Second, we focus on constructing a highly interactive environment in which the con- figured optimal control problem is deployed. Vehicle interactions are categorized into two distinct cases: Case 1 is representative of a single-agent interaction, whereas Case 2 is representative of a multi-agent interaction. The computed motion trajectories per each case are displayed in simulation.

Visual odometry (VO) plays a crucial role in determining the position and orientation of an autonomous vehicle as it navigates through its environment. However, the performance of visual odometry can be significantly affected by errors in disparity estimation and LIDAR depth measurements. This thesis investigates the use of LIDAR depth correction and Stereo disparity matching, combined with stronger match filtering, to improve the accuracy and reliability of VO estimations. The study utilizes a dataset consisting of a sequence of image frames, ground truth position data, and a range of feature detection, description, and matching techniques. Results indicate that the proposed approach significantly improves the accuracy of VO estimations, providing a valuable contribution to the development of reliable and safe autonomous navigation systems. The proposed method consists of two main components: (1) an advanced disparity matching algorithm to obtain more accurate and robust disparity estimations, and (2) a LIDAR depth correction module that employs a sensor fusion approach to refine the depth information generated by LIDAR sensors. The LIDAR depth correction module combines data from multiple sensors, including LIDAR, camera, and inertial measurement unit (IMU), to produce a more accurate depth estimation. The performance of the proposed approach is evaluated using real-world datasets and benchmark visual odometry challenges. Results demonstrate that the proposed method significantly improves the accuracy and robustness of visual odometry, leading to better localization and navigation performance for autonomous vehicles. This research contributes to the ongoing development of autonomous vehicle technology by addressing critical challenges in visual odometry and offering a practical solution for more accurate and reliable self-localization