New AI technology helps soldiers learn and adapt faster in combat situations
StaffGeneral Defense AI machine learning U.S. Army
Researchers at the U.S. Army Research Laboratory developed a technology to help decipher hints of information faster in deploy solutions.
Soldiers often go into some of the most dangerous situations and are tasked with making snap decisions that could save people’s lives.
A team of scientists at the U.S. Army Research Laboratory have developed a new technology that will enable soldiers to learn 13 times faster than conventional methods.
Even with limited resources, the new tech makes it possible to help decipher hints of information faster and more quickly deploy solutions.
This new tech is part of the Army’s larger focus on artificial intelligence and machine learning research initiatives. The goal is to gain a strategic advantage and ensure warfighter superiority with applications such as on-field adaptive processing and tactical computing.
According to the team, they relied on low-cost, lightweight hardware and implemented collaborative filtering, a well-known machine learning technique on a state-of-the-art, low-power Field Programmable Gate Array platform to achieve a 13.3 times speedup of training compared to a state-of-the-art optimized multi-core system and 12.7 times speedup for optimized GPU systems.
Another advantage of this type of system is that it consumes far less power, making this a potentially useful component of adaptive, lightweight tactical computing systems.
The goal of this new technology is to embed it on the next generation of combat vehicles, explains Dr. Rajgopal Kannan, an ARL researcher. This will provide cognitive services and devices for warfighters in distributed coalition environments.
ARL and University of Southern California, namely Prof. Viktor Prasanna and students from the data science and architecture lab are working to accelerate and optimize tactical learning applications on heterogeneous low-cost hardware through ARL’s – West Coast open campus initiative.
Kannan said he is working on developing several techniques to speed up AI/ML algorithms through innovative designs on state-of-the-art inexpensive hardware.