Defense Advanced Research Projects AgencyTagged Content List

Size, Weight and Power Constraints

Making technologies smaller, lighter and more power-efficient to increase military effectiveness

Showing 5 results for SWAP + Processing RSS
09/13/2016
Airspace for the flying public today is perpetually congested yet remarkably safe, thanks in no small part to a well-established air traffic control system that tracks, guides and continuously monitors thousands of flights a day. When it comes to small unmanned aerial systems (UAS) such as commercial quadcopters, however, no such comprehensive tracking system exists.
September 26, 2016,
DARPA Conference Center
DARPA’s Strategic Technology Office (STO) will host a Proposers Day conference on the Aerial Dragnet on September 26, 2016, at the DARPA Conference Center, 675 North Randolph Street, Arlington, Virginia, from 12:00 PM to 6:00 PM (EDT). The purpose of this conference is to provide information on the Aerial Dragnet program, promote additional discussion of the topic Aerial Dragnet is addressing, and address questions from potential proposers.
Airspace for the flying public today is perpetually congested yet remarkably safe, thanks in no small part to a well-established air traffic control system that tracks, guides and continuously monitors thousands of flights a day. When it comes to small unmanned aerial systems (UAS) such as commercial quadcopters, however, no such comprehensive tracking system exists. And as off-the-shelf UAS become less expensive, easier to fly, and more adaptable for terrorist or military purposes, U.S. forces will increasingly be challenged by the need to quickly detect and identify such craft—especially in urban areas, where sight lines are limited and many objects may be moving at similar speeds.
The past decade has seen explosive growth in development and training of artificial intelligence (AI) systems. However, as AI has taken on progressively more complex problems, the amount of computation required to train the largest AI systems has been increasing ten-fold annually. While AI advances are beginning to have a deep impact in digital computing processes, trade-offs between computational capability, resources and size, weight, and power consumption (SWaP) will become increasingly critical in the near future.
Computational capability is an enabler for nearly every military system, but increases in this capability are limited by available system power and constraints on the ability to dissipate heat. This is a challenge for embedded applications such as soldier-borne applications, UAVs and command and control systems on submarines. Today’s intelligence, surveillance and reconnaissance (ISR) systems have sensors that collect far more information than they can process in real time; as a result, what could be invaluable real-time intelligence data in the hands of our warfighters is simply discarded, or perhaps recorded and processed hours or days after it was collected.