UMass Amherst-Led Research Team Receives $749,998 NSF Grant to Use Edge and Cloud Computing to Improve Drone Capabilities

Michael Zink
Michael Zink

AMHERST, Mass. – A research team led by a University of Massachusetts Amherst researcher recently received a $749,998 National Science Foundation (NSF) grant to improve drone capabilities through edge- and cloud computing.

The research team is led by Michael Zink, professor of electrical and computer engineering at UMass Amherst. He is joined by Ewa Deelman from the Information Science Institute at the University of Southern California, Anirban Mandal from the Renaissance Computing Institute at the University of North Carolina at Chapel Hill, and Prasad Calyam from the University of Missouri.

The research team’s goal is to make use of new technologies in edge- and cloud computing, in addition to the ability to process information in the core of a network, to allow researchers and application developers to create workflows that swiftly generate crucial information for the safe and economic operation of drones. Zink says the team’s work would ultimately lead to new advancements such as aiding drones operating safely by navigating around hazardous weather. To achieve this, detailed weather data has to be collected and processed in a time-critical manner. In addition, the team’s work will lead to approaches that intelligently handle data processing and power consumption to assure that drone missions can be carried out safely.

“The uses for drone technology grow by the day,” Zink said. “Imagine you are about to hop on board an air taxi that will autonomously fly you from your destination in the suburbs of New Jersey to a helipad on top of a skyscraper in Manhattan. Or think of the case where a drone is used to fly a donated organ from one hospital to another where a team of doctors is anxiously awaiting the delivery to carry out the final step of an organ transplant. What might sound as science fiction is currently tested in prototype projects around the country. One of the biggest challenges these projects face is the need for very detailed, close-to-the-ground drone operating altitude weather information for safe operations, and that’s where our research will help.”

In the case of detailed weather information, data provided by weather radars and other meteorological sensors have to be collected, processed, and used as a basis to generate safe flight plans for drones. This process has to be executed very fast to allow safe operation in the case of fast developing weather events, such as severe thunderstorms or tornados.

“Drones are also being used for video surveillance in border security and agriculture,” Calyam said. “Drones can be mounted with high-definition video cameras and sophisticated sensors to collect environmental situational awareness data. Farmers could use drones to monitor the health of crops in fields and take pro-active measures to increase yield or improve drought resistance of crops. In both these cases, large amounts of video/image data is generated that needs to be processed. In some cases, the processing needs to be done instantly in order to fully leverage the intelligence being gathered by the drones in a timely manner. The major challenge is that devices such as the drones or ground control stations do not have the necessary computation or networking capabilities to manage such data processing. Consequently, these devices need to be connected in a secure and resilient manner to edge computing or cloud computing resources, while carefully handling battery capacity limitations of the edge devices.”

Edge computing is a new technology that brings computing resources closer to where devices, in this case drones and weather sensors, gather information. This is in contrast to cloud computing, where computer resources can be located far away from devices in large data centers. The close geographic proximity of edge computing to devices allows for much quicker response times, which is critical when it comes to routing drones around weather and other obstacles. While researchers have been using cloud computing resources for their scientific applications for many years, the use of edge computing is just starting. The project will make contributions in this area and aid researchers in creating workflows that contain edge computing resources to support new research applications.

The drone workflows will be set up on new testbeds on major NSF-supported infrastructures such as GENI, POWDER and FABRIC to study novel architectures for configuring computation and networking resources. The testbeds will help the project team to run experiments that provide insights on how to improve the drone control, as well as video and other data processing.

“Today, we run edge computing experiments and cloud computing experiments in an isolated manner due to knowledge limitations in testbed methodologies within the scientific community. With the testbeds being planned in this project, we will be able to create advanced testbed methodologies to integrate the edge and cloud sides of workflows and validate or correct many of the assumptions we are currently making on what affects application performance,” Calyam said. While the team will demonstrate its approach for drone-based applications, other areas such as autonomous vehicles or personalized healthcare can also be supported by the work.

The project team will enable access to a rich set of resources for researchers and educators from a diverse set of institutions, including historically black colleges and universities (HBCU), community colleges, and women’s colleges, to further democratize research. In addition, collaboration with the NSF’s Research Experience for Undergraduates Site in Consumer Networking will promote participation of under-served/under-represented students in project activities.

Information about the project will be available in the future at: