31 juillet 2018 | International, C4ISR

DARPA’s Fast Lightweight Autonomy program tests the scouting software of tomorrow’s wars

By:

Every map is an outdated map. Buildings change, people relocate, and what was accurate a decade ago may mean nothing to someone on patrol today. Which is one reason the Defense Advanced Research Projects Agency is pursuing Fast Lightweight Autonomy, a program designed to teach drones to effortlessly scout and map unfamiliar locations, without the help of GPS or external guidance tools, so that the military can rely on the freshest scouting information possible.

For Phase II of the program, DARPA split the task into three parts. One team worked on better flight outdoors in a natural environment at full speed. Another team pursued drone flight in an urban environment, with the drone building a semantic map of the cars and buildings it encountered, while a third team focused on navigating indoors. Taken together, the teams are demonstrating in part the way robots can do what humans do when in unfamiliar terrain, but then speed it up and transmit that information back to humans following behind.

First and foremost are the military applications. If DARPA's program results in workable code and sensors, future missions equipped with quadcopters could let the robots scout a contested area before putting any humans at risk. And that area could include dense woods, civilian-lined streets in an area that's seen some insurgent action, or even shelled-out buildings that may be hiding snipers or other traps. The robot explores and informs, and then the humans can follow afterwards, with fresh information loaded onto their tablets and guiding their movements.

There are applications for the technology beyond a shooting war. Rescue workers could use drones based on this software to see if a damaged building is safe enough to send rescuers into, or to see if there are even people alive inside who might need rescuing. Drones that can fly quickly through forests could seek out lost hikers, shifting the human energy from search to rescue.

Some of this, notes FLA program manager Jean-Charles Ledé, could be done at present by skilled human pilots, the kind that race drones with first-person view goggles. But, says Ledé, “We don't want to deploy a world-class FPV racer with every search and rescue team.”

Drones that can navigate by software alone reduce the skill needed to manage the flying robots. In a pinch, the algorithm is a substitute for expertise, and far more scalable a solution.

https://www.c4isrnet.com/unmanned/2018/07/30/darpas-fast-lightweight-autonomy-program-tests-the-scouting-software-of-tomorrows-wars/

Sur le même sujet

  • Space Development Agency wants someone to launch its first 28 satellites

    9 octobre 2020 | International, C4ISR, Sécurité

    Space Development Agency wants someone to launch its first 28 satellites

    Nathan Strout WASHINGTON — Now that the Space Development Agency has selected four contractors to build its first 28 satellites, the organization is looking for a launch provider to ferry them into orbit. According to a solicitation posted Oct. 6, the agency plans to select one company to provide launch services for all 28 satellites, with the first launch taking place in September 2022. Those 28 satellites will comprise tranche 0 of SDA's National Defense Space Architecture, a new proliferated constellation providing a whole host of services primarily from low Earth orbit. Among other things, the NDSA is anticipated to provide beyond-line-of-site targeting, hypersonic missile warning and tracking, and a space-based mesh network that will connect all of the services as part of the Pentagon's new Combined Joint All-Domain Command and Control (CJADC2) approach. The constellation will ultimately include hundreds of satellites, but SDA isn't putting them all up at once. Rather, the agency has adopted a spiral development approach, where the most mature and ready technology is added to the constellation in two year tranches. This launch solicitation covers the first tranche, otherwise known as tranche 0. Slated to go into orbit in fall 2022, tranche 0 is what SDA calls its “war fighter immersion tranche.” “Its goal is to provide the data in a format that the war fighters are used to seeing on tactical timelines that they can be expected to see once we actually become operational,” SDA Director Derek Tournear told C4ISRNET. “The whole purpose of tranche 0 is to allow the war fighters to start to train and develop tactics, techniques and procedures so that they can create operational plans for a battle where they would actually incorporate these data.” With just 28 satellites, tranche 0 will not provide global, persistent coverage. Instead, it will provide periodic, regional capabilities. Tranche 0 will feature the inaugural satellites in the transport and tracking layers. The 20 transport layer satellites will form the base of a space-based mesh network, passing data from satellites to weapon systems along a high-speed, on-orbit corridor. Tournear has previously stated that the transport layer will serve as the space component of CJADC2, the Pentagon's effort to connect sensors to shooters across domains and services. The inaugural tracking layer will be made up of eight satellites. The tracking layer will be used to detect and track hypersonic threats, working with the transport layer to pass tracking data and custody from satellite to satellite—collaborating to keep an eye on globe-traversing missiles that can evade current missile warning capabilities. SDA has selected Lockheed Martin and York Space Systems to each build 10 of the transport layer satellites, while SpaceX and L3 Harris will split the eight tracking layer satellites. Because the SDA has given vendors flexibility in the designs of their satellites, there is some variety to the weight of the space vehicles being launched into orbit. While all 20 transport layer satellites will weigh approximately 200 kilograms, give or take 20 kilograms, there is a significant difference in the size of the eight tracking layer satellites. One vendor—either SpaceX or L3 Harris—will be contributing four tracking layer space vehicles weighing approximately 1,068 kg each. The other vendor's space vehicles will be significantly lighter at just 249 kg. In total, SDA is looking to put as much as 10,164 kg of hardware into orbit. The agency wants all 28 satellites delivered to two circular, 950 km near-polar orbits, with the tranche divided evenly into two planes of 14 satellites. The launch provider has until March 31, 2023, to put all payloads on orbit and has discretion as to how many launches it will use to do that. The goal is to have as many satellites up as close to September 2022 as possible. Proposals are due by Nov. 5 at 4 p.m. EST. https://www.c4isrnet.com/battlefield-tech/space/2020/10/08/space-development-agency-wants-someone-to-launch-their-first-28-satellites/

  • Fighter jets without pilots?  | Defense News Weekly Full Episode, 7.30.22

    2 août 2022 | International, Aérospatial

    Fighter jets without pilots? | Defense News Weekly Full Episode, 7.30.22

    A look at the future of unmanned aerial combat and fighter wings, plus inside access to the Korean War Veterans Memorial's emotional new feature, the Wall of...

  • Air Force hopes to train 1,500 new pilots each year by 2022 to help solve shortage

    11 octobre 2018 | International, Aérospatial

    Air Force hopes to train 1,500 new pilots each year by 2022 to help solve shortage

    By: Stephen Losey The Air Force hopes to be able to train 1,500 new pilots each year by fiscal 2022 as part of its effort to solve its troubling shortage of aviators. Air Force Secretary Heather Wilson said at a Senate Armed Services readiness and management support subcommittee hearing Wednesday that the Air Force trained 1,160 new pilots in fiscal 2017, and expects to train 1,311 in fiscal 2019, before expanding further. The Air Force has taken several steps to try to improve air crew's quality of life and quality of service, and solve problems that might be leading some to choose to leave the Air Force. Wilson highlighted efforts to reduce operating tempos, revitalize squadrons and restore support staffs so air crew can concentrate on flying, as well as generous incentive pay and bonuses. The Air Force is also working on testing a “fly-only” technical track for interested airmen, and giving air crew greater input on assignments. But, Wilson said, “retention efforts alone will not solve the aircrew shortage," leading the Air Force to beef up its training capacity. Increased pilot training capacity could become even more important as the Air Force seeks to increase its number of operational squadrons from 312 to 386 by the end of 2030. Wilson told lawmakers that restoring readiness must be a top priority of the Air Force. The service is focusing on fixing readiness in the 204 operational squadrons that would be most important in a high-end fight. By the end of 2020, she said the Air Force hopes 80 percent of those units will have the right number of properly trained and equipped airmen. And two years after that, Wilson hopes 80 percent of all 312 operational squadrons will be ready. The Air Force has already made significant progress in cutting the maintainer shortage, Wilson said. Two years ago, the Air Force was short 4,000 maintainers, but by December, that gap is expected to be completely eliminated. But the Air Force's work on maintenance isn't done. Wilson said these new, green maintainers must be seasoned until they have enough experience to do more complicated or unsupervised work. Full article: https://www.airforcetimes.com/news/your-air-force/2018/10/10/air-force-hopes-to-train-1500-new-pilots-each-year-by-2022-to-help-solve-shortage

Toutes les nouvelles