CAMBRIDGE, MA—The burgeoning commercial space industry has attracted billions of dollars in investment. Upwards of 1,000 satellites circle the Earth, beaming down data and images every minute. All of this technology promises to let astronauts, businesses and space tourists alike gather more information from and about space than ever before.
But according to Eric Robinson, a Mobility Pilot in the U.S. Air Force, there may be an unintended consequence to all of this discovery. “There’s going to be a huge and growing demand for satellite data,” he said, “but mechanisms for coordinating data gathering among satellites, which would vastly increase the utility that can be gained from these assets, are nonexistent.” To put it in industry parlance: Houston, we’ve got a data problem.
But for Robinson, the promise of richer data presents an opportunity. He found a way to optimize the tasking of data collection across separately managed satellites. His method overcomes the current practice of keeping information “stovepiped” and out of the hands of others. “Even within organizations, including branches of the Department of Defense and NASA, there may be separate, generally unshared, collection assets. That creates inefficiencies that could be avoided through coordinated planning,” Robinson said.
To improve data gathering, Robinson developed a set of algorithms that taps into the satellite schedule planners and builds a way to ensure the “asks” for data collection and allocation are efficient and optimized, unlike the manual intervention that would be required to coordinate that today. He used machine learning to automatically find patterns and structures in the satellite data in order to identify hidden uncertainties and the information needed to complete an imagery collect by a given satellite.
In recognition of his achievement, the Air Force Association honored Robinson with its Theodore Von Karman Award during a recent ceremony at the Air Force Association’s Air, Space & Cyber Conference.
One of the potential payoffs for all of this data sharing could be better weather forecasting, according to Draper engineer Mark Abramson. “Predicting and managing the response to severe weather events, like hurricanes, gets easier when you have a system that gives you simultaneous measurements, persistent surveillance, minimal information gaps and soonest-possible observations. By linking satellites in a web of information, we can help improve the accuracy of, for example, how scientists monitor the ozone levels near the poles, measure atmospheric and oceanic properties and examine both emitted and reflected radiation from Earth’s surface.”
Robinson’s research was conducted while he was a member of the Draper Fellow Program under the guidance of Abramson and Stephen Kolitz, also of Draper, and as a graduate student in the MIT Aeronautical and Astrophysical department under Associate Professor Hamsa Balakrishnan. Since the 1970s, Draper has guided and supported more than 1,200 Draper Fellows, who have come from both civilian and military backgrounds and contribute all over the world in technical, corporate, government, academia and entrepreneurship sectors. Draper Fellow alumni have gone on to serve as high-ranking members in the DoD, astronauts for NASA, leaders in industry and faculty members in engineering and the sciences.
Robinson’s work continues Draper’s decades-long support of NASA, including support for NASA’s Hurricane and Severe Storm Sentinel (HS3) mission and NASA’s Earth Science Technology Office’s Advanced Information System Technology program. Robinson’s thesis work was completed under Draper’s fourth NASA-funded AIST project.