KEF Robotics uses digital twins to plan system to guide tethered drones
By DRONELIFE Features Editor Jim Magill
Drones tethered to mobile vehicles can provide an enormous profit to military forces, by with the ability to provide warfighters with visual and other forms of information from a bird’s-eye perspective, in a wide range of environments and situations.
One downside to having drones tethered to moving vehicles, nevertheless, is the hazard that potential obstacles resembling tree limbs or low-hanging traffic lights could impose, potentially causing damage to the drone, the tether or the vehicle itself. A small, Pittsburgh-based software company is developing an answer to this problem, using artificial intelligence (AI) and machine-learning algorithms to assist the drone “see” the obstacles from a secure distance and avoid them.
KEF Robotics is using funding from the U.S. Department of Defense (DoD) to develop a sensible system for safely guiding tethered drones. The corporate has implemented the Falcon simulator, produced by Duality AI, to create different scenarios to coach its autonomy systems to avoid obstacles in real-world situations.
Working under a program established by the U.S. Army’s Next Generation Combat Vehicle Group, KEF is developing a comparatively inexpensive infrared and electro-optical camera-based system that may detect power lines and other hazards in the trail of a vehicle and attached tethered drone.
“The DOD wants to maneuver these through difficult urban environments at high speeds, and we’re constructing a system that may detect hazards far enough away you could plan the trail of the aircraft and fly underneath the hazards or otherwise avoid them,” Fraser Kitchell, CEO of KEF Robotics, said in an interview.
KEF is considered one of a handful of corporations competing to develop such a system for the Army. The event of the KEF system is somewhere between the laboratory testing phase and the verification phase of conducting a prototype demonstration in an operational environment, Kitchell said.
“We’ve deployed the algorithms on ground vehicles, but we haven’t yet flown with a tethered aircraft and a ground vehicle processing all the knowledge at the identical time,” he said. “That could be a critical step.”
The system includes a lot of cameras, allowing the operator to construct a really complex map of the environment as they’re moving through it. Processing that volume of information in real time is considered one of the most important challenges that system designers face.
Employing drones tethered to vehicles provides many benefits compared with other types of surveillance, resembling using untethered UAVs.
“The tethered aircraft means that you can keep the aircraft up nearly perpetually because you’ll be able to power it off a ground vehicle,” Kitchell said. “And you’ve this secure data link between the aircraft and the bottom vehicle. You possibly can capture data on board the aircraft and send it down an ethernet cable to the bottom vehicle.”
For the Army to deploy tethered drones together with its next generation of combat vehicles, currently under development, requires solving the obstacle-avoidance problem.
“The Army first got here to us and so they said, ‘We wish to know how we are able to use state-of-the art computer-vision techniques to enhance the range at which we are able to detect hazards,’” Kitchell said. The Army’s charge to its vendors was to develop a low-cost navigation system that could possibly be easily and inexpensively adapted to be deployed on multiple vehicles. What the military wants to perform through its next-generation combat vehicle program is to supply each vehicle with “its own tiny air force,” he said.
A lot of vendors are vying for the DoD contract to supply the next-generation combat vehicles, with the choice expected to happen sometime next 12 months or early in 2025.
Kitchell said which means that field testing of the KEF system on the newly produced vehicles might be three or 4 years in the long run.
KEF researchers employ Duality’s simulators to create digital twins of real-world environments to show the software the right way to avoid obstacles that the tethered drone might encounter.
“The foundational level of this project for us to create these environments, drive through them with our system and our sensors a lot of times, after which assess which algorithms and which sensors could be prone to perform going forward,” he said.
One in every of the constraints the Army placed on potential software vendors was to maintain the per-unit cost of their systems low.
“Don’t go on the market and use that $100,000 infrared camera. Attempt to use the $7,000 infrared camera and the $600 EO camera and the pc you could buy on the local ironmongery shop or the local computer store,” Kitchell said.
So as to satisfy the Army’s budget-minded requirements, KEF employs high-resolution cameras that capture visual images, fairly than costlier and more sophisticated data-recording technology resembling LiDAR or radar.
“We wish to have solutions that don’t emit radio frequencies or electromagnetic frequencies. We attempt to be a passive, simpler system, a lower-cost system.”
Recent advances in cell-phone technology have resulted in the event of smaller and more powerful cameras which can be also relatively inexpensive. The corporate is currently experimenting with different camera types, fields of view and camera modalities to find out one of the best camera configuration to make use of to create a system that may detect hazards at an optimal range.
“Say you desired to detect an influence line at 2 kilometers away. What sort of camera do you would like? What should the sector of view be? Is that camera available off the shelf today?” Kitchell asked.
Although the DoD is the most important funding contributor to the tethered drone software project and the initial use of the software will probably be a military application, he said the corporate’s ultimate goal is to develop a system that may be offered to business markets.
“We’re absolutely attempting to commercialize the whole lot we do at KEF. And Duality could be very serious about that too,” he said.
Read more: