Air Force advisers study use of satellites for tracking moving targets

Sur le même sujet

• 

  19 juin 2019 | International, C4ISR, Autre défense

  Can AI help limited information have endless potential?

  By: Kelsey D. Atherton Humans are remarkably good at choosing to act on limited information. Computers, less so. A new DARPA program wants to train artificial intelligence to process and evaluate information like humans do, and produce actionable results on far smaller datasets than presently done. It's a program of such important DARPA's giving it VIP status, or a least VIP as an acronym: Virtual Intelligence Processing. “Successful integration of next-generation AI into DoD applications must be able to deal with incomplete, sparse and noisy data, as well as unexpected circumstances that might arise while solving real world problems,” reads a solicitation posted June 14. “Thus, there is need for new mathematical models for computing leading to AI algorithms that are efficient and robust, can learn new concepts with very few examples, and can guide the future development of novel hardware to support them.” To create these mathematical models, DARPA wants partners to look inward, creating AI inspired by the robust and massive parallelism seen in the human neocortex. If it is the architecture of the brain that makes humans so especially skilled at processing information quickly, then it is an architecture worth studying. “In order to reverse engineer the human brain,” the solicitation continues, calmly, “we need to apply new mathematical models for computing that are complete and transparent and can inform next-generation processors that are better suited for third-wave AI.” It is DARPA's nature to inject funding into problem areas it sees as both yielding future results and not presently served by the market, and this is not different. The solicitation explicitly asks for mathematical models that have not already been the focus of AI development. It's also looking for models that can inform the development of future hardware, rather than programs that can run on existing machines. DARPA is interested in how the hardware works in simulation, but wants partners to hold off on actually making the hardware for the model. So, the plan goes: create a mathematical model, inspired by brains, to process information on a small and limited data set, and then design it for hardware that doesn't exist yet. Easy as that sounds, the solicitation also asks proposers to talk about the limitations of the algorithms when applied to military tasks, and specifically limitations related to accuracy, data, computing power and robustness. Working from limited information is an expected future of military machines going forward. Between electronic warfare, denied environments and the very nature of battlefield events as rare and hard to record moments, doing more with on-board processing of limited data should enable greater autonomy. Even in the rare case where a weapon system transmits data back for algorithm refinement, that data set will be orders of magnitude smaller than the big data sets used to train most commercial machine learning tools. Should a proposer's idea be accepted and they follow through both Phase 1 and Phase 2 of the project, the total award is set at $1 million. A tidy sum, for anyone who can figure out the math to make a future computer run on sparse information as effectively as a human brain. https://www.c4isrnet.com/artificial-intelligence/2019/06/18/can-brain-inspired-ai-run-on-lean-data/

• 

  11 mars 2022 | International, Terrestre

  DoD SBIR 22.4 Annual BAA Topic Pre-Release: Army Topic Release 2 – A224-004, A224-005, and A224-006

  The DoD Small Business and Technology Partnerships Office announces the pre-release of the following DoD SBIR 22.4 Annual Broad Agency Announcement (BAA) topics: Department of the Army A224-004: Advanced Tire Technology for Manned and Unmanned Systems A224-005: M997A3 Chassis Suspension Improvements A224-006: Variable Speed Engine Cooling Fan for Acoustic Detection Management Full topic descriptions and instructions are available on DSIP at https://www.dodsbirsttr.mil/submissions/login and at https://rt.cto.mil/rtl-small-business-resources/sbir-sttr/. IMPORTANT DATES: March 10, 2022: Topics pre-release March 24, 2022: Topics open, begin submitting proposals in DSIP April 12, 2022: Topic Q&A closes to new questions at 12:00 p.m. ET April 26, 2022: Topics close, full proposals must be submitted in DSIP no later than 12:00 p.m. ET Topic Q&A Topic Q&A is now available on the Topics and Topic Q&A page in DSIP. Proposers may submit technical questions through Topic Q&A page at https://www.dodsbirsttr.mil/submissions/login. During pre-release, proposers can contact TPOCs directly or submit questions via Topic Q&A. Once DoD begins accepting proposals on March 24, 2022, no further direct contact between proposers and topic authors is allowed. All questions and answers are posted electronically for general viewing. Topic Q&A will close to new questions on April 12, 2022 at 12:00 p.m. ET, but will remain active to view questions and answers related to the topics until the BAA close. Questions submitted through the Topic Q&A are limited to technical information related to improving the understanding of a topic's requirements. Any other questions, such as those asking for advice or guidance on solution approach, or administrative questions, such as SBIR or STTR program eligibility, technical proposal/cost proposal structure and page count, budget and duration limitations, or proposal due date WILL NOT receive a response. Refer to the Component-specific instructions given at the beginning of that Component's topics for help with an administrative question. Proposers are advised to monitor Topic Q&A during the BAA period for questions and answers and frequently monitor DSIP for updates and amendments to the topics.

• 

  29 janvier 2020 | International, Aérospatial

  US Defense Department launches Gremlins drone from a mothership for the first time

  WASHINGTON — The U.S. Defense Department is one step closer to having swarming drones that it can launch from military planes and recover in midair, having successfully conducted the first flight of the Gremlins aircraft in November. The test, which occurred at Dugway Proving Ground, Utah, proved that a C-130A could successfully launch an X-61A Gremlins Air Vehicle, said Tim Keeter, who manages the program for Dynetics. The company won the Gremlins contract from the Defense Advanced Research Projects Agency in 2018. “It gives us a lot of confidence going forward that this vehicle can fly where it's supposed to fly, how it's supposed to fly,” Keeter said during a Jan. 21 phone call with reporters. “Now the team can be principally focused on the other portion of our program plan ... which is to successfully rendezvous with a C-130, dock with our docking system ... and safely recover the vehicle.” During the test, which lasted 1 hour and 41 minutes, the X-61A flew with no anomalies and the DARPA-Dynetics team completed all test objectives, including transitioning the X-61A from a cold-engine start to stable flight; validating the Gremlins' data links and handing off control of the drone between air and ground control stations; deploying the docking arm; and collecting data on the air vehicle. However, during the recovery process, the drone crashed to the ground and was destroyed. The drogue parachute, which deployed first to slow the air vehicle, functioned as planned, Keeter explained. However, the larger main parachute — which would soften the landing of the air vehicle so that the drone could be reused — did not correctly deploy due to a mechanical issue. Dynetics has built four other Gremlins vehicles, leaving enough drones to accomplish the program's primary requirement to fly and recover four Gremlins in 30 minutes, said Scott Wierzbanowski, DARPA's Gremlins program manager. The next demonstration, set for sometime this spring, will verify whether the Gremlins can be successfully recovered by the C-130 while in flight. Wierzbanowski characterized this test as critical for proving that the Gremlins can be reused over multiple missions — a key point for bearing out the cost-effectiveness of the concept. "If I have an expendable vehicle, at some point I'm not going to want to be able to use those things because they're just too expensive,” he said. “But if I can recover them and then amortize the cost of that vehicle over 10 or 20 or 30 sorties, maybe there's a bend in the curve somewhere that really will allow us to benefit from these smaller, more affordable, attritable systems." During the recovery process, the C-130 will lower a towed capture device that will mate with the Gremlins drone, thus avoiding the turbulence generated by the wake of the larger aircraft, Keeter said. Once the drone is stabilized by the capture device, an engagement arm deploys, docking with the X-61A and bringing it inside the C-130 cargo bay to be stowed. https://www.defensenews.com/industry/techwatch/2020/01/28/us-defense-department-launches-gremlins-drone-from-a-mothership-for-the-first-time/