Space Development Agency experiment demonstrates on-orbit data processing
WASHINGTON — A data processor launched to orbit by the Space Development Agency has performed an early demonstration of autonomous data fusion in space, said one of the companies supporting the experiment.
Scientific Systems Company Inc. (SSCI) developed an artificial intelligence-enabled edge computer for the experiment known as POET, short for prototype on-orbit experimental testbed.
The POET payload rode to orbit on a Loft Orbital satellite that launched June 30 on the SpaceX Transporter-2 rideshare mission.
Autonomous data processing in space is a key technology sought by SDA so its satellites can analyze data ingested from third-party sources and send it back to users.
SDA’s satellites will be used by the U.S. military to detect and track targets on the ground, at sea or in the air. Raw data collected by satellites typically is sent to ground stations and crunched by human analysts before it’s routed to commanders in the field. SDA wants to move more data processing to orbit and shorten the cycle so data is more timely.
For the POET experiment, SSCI integrated a software application that detects and segments out clouds from images collected by electro-optical imaging sensors. “This is the first step towards an initial edge-processing demonstration of multi-intelligence data fusion,” the company said Feb. 8 in a news release. “Future experiments include uploading progressively more complex executions of third-party software.”
SSCI initially developed the autonomous edge computer payload for the Defense Advanced Research Projects Agency to fly a demonstration for the Blackjack program’s Pit Boss mission system. SDA took over the experiment and renamed it POET.
The computer runs “collaborative mission autonomy” software that allows a user to send a request for tactical information directly to the spacecraft and receive the desired information back, said SSCI. For instance, a Navy commander on a ship could ask the spacecraft: ‘tell me the location and classification of every ship in this box I’ve drawn on my computer screen.’
The request would trigger the system to task Loft Orbital’s YAM-3 satellite to point at that specified region of the ocean and direct an electro-optical imaging payload to collect an image. Then the system would activate a hosted application to process the image using automatic target recognition algorithms, and then would task the YAM-3 communications system to transmit the data back to the Navy user.
The satellite has an expected five-year lifetime and the payload can be regularly uploaded with new mission software, said Raman Mehra, president and CEO of SSCI.