CSR: Small: Virtual Sky: Morphable Geo-Spatial Computing for the Internet of Planes

点击翻译按钮获取中文摘要

In the near future, a majority of aircraft will be equipped with sophisticated technology to sense flight conditions and to directly communicate with nearby aircraft. By sharing information, each plane can provide mission critical information to its pilot beyond what can be perceived by a single aircraft. An example is warning of dangerous weather conditions just outside of an aircraft's sensing range. This project will create a Virtual Sky platform that enables the network of planes, called the Internet of Planes (IoP), to fuse and analyze sensed data correctly, reliably, and quickly, to support safer and more efficient air travel. The project is divided into two thrusts. The first is to create distributed algorithms for planes to learn a consistent, accurate estimate of flight conditions. Contributions will include analysis of the correctness and performance of the algorithms and a study of their theoretical limits in global-scale dynamic networks like the IoP. The second research thrust is the development and evaluation of a large-scale prototype of the Virtual Sky that uses real-time aircraft and weather data. The prototype also integrates a flight simulator, which will be used to study the benefits of the application with a human pilot in the loop.The solutions developed for this project have applications in many other data-rich mobile computing platforms, including ground vehicle networks, to provide real-time information on road and traffic conditions, and autonomous drone networks, for search and rescue or wildfire monitoring, for example. This project also includes curriculum development and outreach activities in mobile and edge computing, including a Raspberry Pi hackathon that will provide students with hands-on learning with sensors and edge computing devices. All research products of this project, including data, source code, publications, and other project artifacts will be made publicly available at the project repository: http://nsl.cs.rpi.edu/iop. The prototype software will be published as an open source repository on github.com under the GPL license. The research products will be maintained for a period of no less than three years after the end of the project.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.