In collaboration with the Pentagon’s Defense Advanced Research Projects Agency (DARPA), Sikorsky Aircraft (Booth 8209) recently completed the first autonomous—and uncrewed—S-70 Black Hawk flight. The milestone mission last month lasted 30 minutes at the U.S. Army's Fort Campbell base in Kentucky.
The unmanned helicopter was part of DARPA’s Alias—for Aircrew Labor In-Cockpit Automation System—program. Sikorsky’s Matrix hardware and software autonomy technologies are at the heart of Alias, and Igor Cherepinsky, director of Sikorsky Innovations, is at the center of Matrix.
In addition to the military applications such as Alias, Cherepinsky sees Matrix as a game-changer for high-risk civil missions, including night-time aerial firefighting and over-water search and rescue (SAR). Lockheed Martin subsidiary Sikorsky is presently working with the FAA to certify the system, which uses a plethora of onboard sensors, lidar, and cameras mated to proprietary hardware and software.
The system comes with a kit that converts virtually any aircraft to varying degrees of add-on fly-by-wire control that Cherepinsky likens to “lane assist” on cars. “Depending on the type of steering it has, some cars do well with lane assistance and some cars do not so well,” he said.
Key to Matrix "doing well" is Sikorsky’s proprietary algorithms, which differentiate it from the guidance systems aboard existing drones that Cherepinsky characterizes as “sophisticated autopilots following waypoints.” Matrix can be flown both line-of-sight and beyond-line-of-sight, and an aircraft equipped with it can have its mission changed from an operator “in the cockpit, backseat, Oklahoma, or the moon,” he said.
With Matrix, an operator gives the system goals and mission constraints, “and the machine produces a plan that it will follow. If you can’t talk to it, it will still produce a plan and it will handle contingencies if something deviates from the norm," Cherepinsky said. "It is not an end-all, be-all sort of intelligence, but it is fairly robust.”
As an example, as Matrix continuously runs through the aircraft checklist, if something drops off the minimum equipment list in flight and is mission-critical, the system can land the aircraft expeditiously. “We have demonstrated this return-to-base functionality and in short order will be doing more demonstrations of that,” Cherepinsky added.
Despite all this functionality, he said Matrix does not rely on artificial intelligence in terms of machine learning when critical flight decisions need to be made “where the failure would mean that something terrible would happen.” Nor would any military application of it be used to make weapons decisions.
However, he said it could be used to assist in targeting “for safe operation of the aircraft.” For example, “If the aircraft is in a degraded visual environment, Matrix will make sure the aircraft can continue safe flight, but completely independent of the weapons systems.”
Matrix is designed to be modular from both a hardware and software perspective to facilitate ease of maintenance and updating, and the architecture is scalable down to eVTOLs or “even smaller aircraft than that,” Cherepinsky said. But he added that the system cannot be updated wirelessly.
“Technologically, it could, but from cybersecurity and other concerns it probably shouldn’t be, so it is not designed to do that,” he said. But Cherepinsky added that third parties will be able to write apps and fly the aircraft.
Sikorsky is also exploring a wider window of man-machine interfaces for the system, including the possible development of wrap-around, one-piece touchscreen cockpit displays that are simple and intuitive. Cherepinsky hinted that Sikorsky is developing such a display for its S-76B Sara (Sikorsky Autonomy Research Aircraft) Matrix platform and has also run demonstrations with Matrix using voice commands to secondary functions for tasks, including change of radio frequencies and running checklists.
But it is Matrix’s ability to speed overwater SAR missions that is perhaps its most impactful utility, something Cherepinsky calls “super search.” Rather than setting an autopilot to fly grid patterns, Matrix can be told to look for a boat, person, or something even smaller.
“Matrix knows what sensors you have on the aircraft and builds a map model of that. It understands the environment and it actively creates a search pattern that to a human may look random, but that in flight test and simulation [can find the target] about 30 percent faster compared to [flying] a typical search pattern,” he said.
Notably, Matrix can calculate the drift of an object in the water over time, locate and calculate the approximate search area, and then use lidar and cameras to locate the object. “If someone is in the water, every minute matters,” Cherepinsky said.