MOBILITY ENGINEERING Produced by SAE Media Group
MOBILITY ENGINEERING
Magazines
Magazine cover

Current Issue

Archives

Magazine cover

Current Issue

Archives

Magazine cover

Current Issue

Archives

Magazine cover

Current Issue

Archives

Lockheed Martin and Drone Racing League Pit AI-Enabled UAS Against Human Pilots

The implications of highly responsive, artificially intelligent unmanned aircraft systems (UAS) will have a major impact across multiple industries – and most prominently, Lockheed Martin’s military defense projects.

(Image source: Lockheed Martin)

Lockheed Martin  of Bethesda, Md. and the Drone Racing League  (DRL) is challenging the engineering community with a new twist on drone enthusiast racing competition: develop artificial intelligence (AI) technology that will enable an autonomous UAS to race a pilot-operated drone and win against human first-person view (FPV) operators. The call for advanced autonomy, dubbed the AlphaPilot Innovation Challenge  , came during the TechCrunch Disrupt technology startup conference in San Francisco.

While SAE International usually doesn’t cover the world of consumer or racing drones – mainly sticking news concerning the larger unmanned aerial vehicles (UAVs) used by commercial entries or defense and science agencies – the pursuit of advanced AI piloting could have a significant impact on UAV usage that may ripple through the numerous industries where those vehicles are accelerating toward ubiquity.

Lockheed Martin Chief Technology Officer Keoki Jackson announced the AlphaPilot Innovation Challenge and multiyear partnership with the globally recognized DRL circuit, inviting university students, technologists, programmers, and drone enthusiasts to push the boundaries of AI, machine learning (ML), and fully autonomous flight. Through the AlphaPilot Innovation Challenge, participating teams will compete in a series of events for their share of over $2 million in prizes, including an extra $250,000 award for the first team that outperforms a professional DRL human-piloted drone.

“At Lockheed Martin, we are working to pioneer state-of-the-art, AI-enabled technologies that can help solve some of the world's most complex challenges – from fighting wildfires and saving lives during natural disasters to exploring the farthest reaches of deep space,” says Jackson. “Now, we are inviting the next generation of AI innovators to join us with our AlphaPilot Innovation Challenge. Competitors will have an opportunity to define the future of autonomy and AI and help our world leverage these promising technologies to build a brighter future.”

The AlphaPilot challenge aims to accelerate the development and testing of fully autonomous drone technologies. Lockheed Martin engineers and AI specialists will serve as mentors to challenge teams, and DRL will supply standardized quadcopter drones. From there, participants will design an AI/ML framework capable of flying a drone – without any preprogramming or human intervention – through multidimensional race courses in DRL's new Artificial Intelligence Robotic Racing (AIRR) Circuit.

With a high-voltage powertrain and diffused polycarbonate shell, the Racer3 – DRL’s latest standard competition drone – accelerates from 0 to 80 miles per hour in under one second. (Image source: DRL)

“Since 2016, DRL has been the proving ground for the world's most talented human pilots, showcasing their abilities to race remotely piloted drones at high speeds. This challenge changes the game,” says DRL CEO and Founder Nicholas Horbaczewski. “How close is AI performance to the world's best human piloting? We're excited to find out next year when AlphaPilot drones compete in adrenaline-packed, futuristic drone races on complex courses in the AIRR Circuit. Our collaboration with Lockheed Martin will both accelerate AI innovation and redefine the sport of the future.”

The AlphaPilot teams will leverage Santa Clara, Calif.-based NVIDIA  ’s Jetson platform  , the most advanced platform for AI-powered, autonomous machines. Jetson processor boards are low-power, on-board edge devices that provide fast, accurate data inference in robots and drones in network-constrained environments. The Jetson TK1, TX1, and TX2 models all carry NVIDIA Tegra processors; however, NVIDIA’s latest Jetson processor board, powered by the new Xavier processor, is packaged as a developer kit for autonomous machines. NVIDIA officials claim it will deliver more than 20 times the performance and 10 times the energy efficiency of the TX2 with an open-source tensor processing unit (TPU) called a deep learning accelerator (DLA).

William Kucinski  is content editor at SAE International, Aerospace Products Group in Warrendale, Pa. Previously, he worked as a writer at the NASA Safety Center in Cleveland, Ohio and was responsible for writing the agency’s System Failure Case Studies. His interests include literally anything that has to do with space, past and present military aircraft, and propulsion technology.

Contact him regarding any article or collaboration ideas by e-mail at This email address is being protected from spambots. You need JavaScript enabled to view it..

Topics:
Aircraft Aircraft Automated Vehicles Automotive Autonomous vehicles Autonomy Aviation Defense Highly automated vehicles Rotary-wing aircraft Unmanned Air Vehicles/Systems (UAV/UAS) Unmanned aerial vehicles Vehicles Vertical take-off and landing (VTOL)

More From SAE Media Group

    Top Stories

    INSIDERElectronics & Computers

    Feature Image Microsoft, PsiQuantum Designing Quantum Computer Prototypes for DARPA US2QC...

    INSIDERCommunications

    Feature Image Aitech’s New Palm-Sized Satellite Enables Space-Based AI Processing

    Technology ReportMaterials

    Feature Image Lighter, Recyclable Body Seal from Cooper Standard Wins SAA Award

    INSIDERPower

    Feature Image Two Startups Partner to Expand Hydrogen-Powered Drone Production

    NewsSoftware

    Feature Image Artificial Intelligence Being Schooled for Mining Applications

    INSIDERAerospace

    Feature Image Supersonic X-59 Completes Cruise Control Engine Speed Test Ahead of First Flight

    Webcasts