An Autonomous Drone with Object Detection and Tracking Capabilities

Overview

This project develops an autonomous drone that can independently detect objects of interest and then fly closer to the object to take detailed photos. The drone hardware consists of a Holybro X500 drone development kit, a Nvidia Jetson Xavier NX GPU, and a RealSense camera. 3D printed fixtures were used to attach the GPU and camera to the drone frame. In software development, the Robot Operating System (ROS) was used, and three ROS nodes, ICODDA, pose estimation, and navigation control, were developed using Python. The ICODDA node performs image capture, object detection, and distance estimation. The YOLOv4 object detection network is integrated within the ICODDA node. A non-zero block average (NZBA) method was developed to estimate object distance in the presence of invalid and noisy depth data points. The pose estimation node implements a convolutional neural network that estimates the object’s pose based on depth data. It achieves an accuracy of 92% when validated with a dataset collected in the project. Finally, the navigation control node uses three PID (Proportional-Integral-Derivative) controllers to constantly adjust the drone’s speeds in the x, y, and z directions. It also implements a novel method to adjust the yaw speed based on recent pose estimation results. The drone’s autonomous operations were successfully demonstrated in test flights with different objects of interest. It achieves 24.4 frames per second image processing throughput and 0.034 second control latency. The developed technologies can be applied to autonomous drones in surveying, inspection, and search and rescue applications. INDIANA Predicting The USD/CNY Exchange Rate: Models, Forecasts, and Novel Approaches David An Culver Academies, Culver, IN A common goal for all stock investors and traders is to find accurate models they can confidently use to predict future stock values/exchange rates in order to make profits. This project uses both conventional statistical methods such as autoregressive and moving-average models, as well as novel content analyses and probability distributions, to provide accurate forecasts for USD/CNY exchange rates in both quantitative and qualitative terms. Chosen using information gleaned from similar projects, the statistical techniques were coded into RStudio and run through different statistical packages. Accurate models were found after models of different types were evaluated. After analyzing their predictions, periods of significant deviation were identified. Through analyzing the key words in the captions of news articles written on U.S.-China economic relations in each of those periods, interesting conclusions on keyword correlations characteristic of these periods were identified. The Poisson distribution further cautions people against taking drastic actions by notifying them of the chances of a significant deviation occurring. Overall, the findings from this project have resulted in several models that are reliably accurate, with the most accurate being a short-term ARIMA(1, 2, 0) model having an average error of 1.45% and a long-term VAR(4) No Constant model having an average error of 1.37%. Additionally, included are some (to the author’s knowledge) novel qualitative analyses of changes in the exchange rate. This project should also serve as a starting off point to be used to conduct further research into similar topics using comparable quantitative and qualitative methods.