Sandia LabNews

Future hypersonics could be artificially intelligent

A test launch for a hypersonic weapon — a long-range missile that flies a mile per second and faster — takes weeks of planning, and it's uncertain how useful test systems will be against urgent, mobile or evolving threats. But Sandia's hypersonics developers think artificial intelligence and autonomy could slash these weeks to minutes for deployed systems.

Sandia spiking tool improves artificially intelligent devices

Whetstone, a software tool that sharpens the output of artificial neurons, has enabled neural computer networks to process information up to a hundred times more efficiently than the current industry standard. The software, created by Sandia neuroscientists, greatly reduces the amount of circuitry needed to perform autonomous tasks and is expected to increase the penetration of artificial intelligence into numerous markets.

Sandia researchers win five R&D 100 awards

Sandia inventions and co-inventions have captured five R&D 100 Awards for 2018. Competitors for the awards include an international pool of universities, corporations and government labs, and the sole criterion for winning is “demonstrable technological significance compared with competing products and technologies.” Since 1976, Sandia has earned a total of 124 awards. Read more to learn about this year's winners.

CRADA boom spurs innovation, collaboration with Sandia Labs

Sandia signed 42 CRADAs in fiscal year 2018, more Cooperative Research and Development Agreements than in any previous year this century, sparking dozens of new collaborations and potential technological innovations. A CRADA is an agreement between a government agency and a nonfederal entity to work together on research and development.

Majority rules when looking for earthquakes, explosions

Finding the ideal settings for each sensor in a network to detect seismic activity can be a painstaking and manual process. Sandia researchers are working to change that. They have developed an algorithm that automatically adjusts seismic activity detection levels for each network sensor, tuning out everyday vibrations such as traffic or footsteps to better detect earthquakes and explosions.