Solar energy is now a leading source of renewable energy that can replace fossil fuels. There are many solar farms in the world because it is eco-friendly and can generate electricity semi-permanently. However, these farms are costly with maintenance issues which require high-cost detection. Among various methods for detection, this paper adopts the method of thermal imaging with a UAV to detect defects efficiently. Especially, the power generation efficiency varies significantly depending on the installed angle of the solar panel. For this reason, it is important to consider the angle when the solar panel is installed. This work designs a system analyzing the range of angle between a solar panel and thermal camera to detect defective cells of the solar panel effectively. We developed an algorithm which detects defective solar cells using computer vision and captured out the meaningful outcome by analyzing the result of the experiment. The use of UAV and the thermal camera can reduce the cost and improve the efficiency of maintenance by minimizing human labor. In the future, our algorithm can be automated and scaled to apply to solar farms worldwide.

End-to-end approach is one of the frequently used approaches for the autonomous driving system. In this study, we adopt the end-to-end approach because this approach has been approved to lead to a distinguished performance with a simpler system. We build a convolutional neural network (CNN) to map raw pixels from cameras of three different angles and to generate steering commands to drive a car in the Udacity simulator. Our proposed model has a promising result, which is more accurate and has lower loss rate comparing to previous models.

—Agriculture production is a critical task in all parts of the world. The process to grow and harvest crops is very human labor intensive in many parts of the world. Much of the difficult labor of crop production can be automated with intelligent and robotic platforms. We propose an intelligent, agent-oriented robotic team which can enable the process of harvesting, gatherin and collecting crops and fruits, of many types, from agricultural fields. This paper describes a novel robotic organization enabling humans, robots and agents to work together for automation of gathering and collection functions. The focus of the research is a model, called HARMS which can enable humans, software agents, robots, machines and sensors to work together indistiguishably. With this model, any capability-based human-like organization can be considered and modeled, such as manufacturing or agriculture. In this work we model, design and implement an application of knowledge-based robot-to-robot and human-to-robot collaboration for an agricultural gathering and collection function. The gathering and collection functions were chosen as they are some of the most labor intensive and least automated processes in the process acquisition of agricultural products. The use of robotic organizations to can reduce human labor and increase efficiency allowing people to focus on higher level tasks and minimizing the back breaking tasks of agricultural production, in the future. In this work, the HARMS model was applied to three different robotic instances and an integrated test was completed with satisfactory results that show the basic promise of this research.