Our first responders often go into situations with little knowledge of the environment. I was funded to develop a drone that can asses the environment before anyone enters. Giving these heroes the information they need to stay safe when facing dangerous situations.
Cheaper, smaller and low power distributed computing environments are needed to fill a gap that has been growing for many years. These systems can be used in many fields such as fault tolerant AI control of drones or as tools for learning how to use larger scale systems. They can be used as a method of large network monitoring by having many machines watching for potential problems. These are but few of the uses for these types of systems.
Robots have become commonplace in almost all manufacturing industries. Agriculture is at a point that robotics is needed to achieve the output and yet meet sustainability goals needed to bring a clean and healthy future to the planet. This system strives to reach this goal by leveraging 3D mapping, GPU computing, big data, and cloud based services. Automated plant by plant data collection and operations assistance is vital to improving yields and yet maintaining a healthy environment. Current systems have been strictly limited to lab based settings and do not take a holistic approach to the problem.
Jack UI is a web application meant to make the operation of ROS enabled field robots intuitive and modern. Eliminating the cumbersome operator systems for ROS. By leveraging the latest technologies for web applications Jack UI can be used on any device and with any ROS robot.
We have developed the framework for creating an autonomous field scout (AFS) consisting of a ground vehcle for collecting physical samples and an aerial system working that collects images of plants during the growqing season. Images will be processed to creat 3-D structure of plants and then examined over time to look for trends that may indicate early onset plant stress. The ground system (red rover) will then navigate to those locations identified through aerial imaging and experts analysis and collects leaf and/or soil samples as needed. The rover will return to base and the leaf samples examined by an expert and or sent for laboratory analysis to confirm specific pathogens or soil nutrient deficiencies. Ealry detercvtion and more accurate scouting information is a major goal of the system. In the first year of development, we have identified the components and begun assembly of the rover and testing of the robotic arm for leaf and soil sampling. Data will be collected using a tractor, GNSS and a UAS this year until the red rover is ready for operation in year 2. The system will be developed in the ROS, which has integrated OpenCV and Point Cloud Library, for navigation and control.
2015 ASABE Annual International Meeting 152190771.(doi:10.13031/aim.20152190771)
This paper demonstrates a method for implementing wireless sensor networks to monitor temperatures within data centers. Previous methods for monitoring these temperatures are costly and dicult to modify once implemented. Multiple TelosB nodes were placed in strategic locations based on knowledge of basic heat flow in data centers, to collect temperature readings. It was possible to gather data matching the predictions of their placement, and detecting alarming trends in the data center's environment. The result is a portable, cost-eective, and energy ecient method for gathering precise temperature readings from data centers.
This paper presents a solution to the problem of large scale, high cost, energy consuming super computers. It details the construction of a small foot print, cost effective, and energy efficient cluster system. The system uses Raspberry Pi computers to create a cluster that is much less expensive and significantly smaller than traditional super computers. The system does not sacrifice computing power in proportion to its size and energy consumption.
A model for the standardization of design and implementation of HPC clusters to be used in universities is presented. Standardization is achieved by using an open-source operating system, network infrastructure, and software packages. The cluster is configured for universities intending to implement an HPC cluster for research or teaching use. No prior understanding of clusters is assumed but a basic understanding of programming, networking and computers in general is required.
The USDA has been a great support for my research. There labs have been pushing the frontiers in agriculture for many years, bringing many advancements to farming practices and technologies.
Friluftsliv aims to integrate the architectures of buildings, nature, and computation into a regenerative agroecosystem. It is with their support I have been developing robotic technologies to bring this vision to reality.
Nvidia has graciously donated several pieces of equipment to allow my work to continue. They have also been a great resource of information on deep learning and computer vision.
Spring Valley Ecofarms is a non-profit organization focusing on education, research and outreach to promote more ecologically sustainable agriculture.