Raytheon working on Competency Aware Machine Learning
Raytheon has received a $6 million contract from the Defense Advanced Research Projects Agency (DARPA) to developing machine learning technology, the company announced on 13 January.
As part of DARPA’s Competency Aware Machine Learning programme, systems will be able to communicate the abilities they have learned, the conditions under which the abilities were learned, the strategies they recommend and the situations for which those strategies can be used.
The system will learn from a video game like process. Instead of giving the system rules, the researchers will tell the system what choices it has in the game and what the ultimate goal is. By repeatedly playing the game, the system will learn the most effective ways to meet the goal.
The system will explain itself by recording the conditions and strategies it used to come up with successful outcomes.
Once the system has developed these skills, the team will apply it to a simulated search and rescue mission. Users will create the conditions surrounding the mission, while the system will make recommendations and give users information about its competence in those particular conditions. For example, the system might say, ‘In the rain, at night, I can distinguish between a person and an inanimate object with 90 percent accuracy, and I have done this over 1,000 times.’
More from Uncrewed Vehicles
-
Ready for the race: Air separation drone swarms vs. air defence systems
As the dynamics of aerial combat rapidly evolve, Chinese scientists have engineered a sophisticated air separation drone model that can fragment into up to six drones, each capable of executing distinct battlefield roles and challenging the efficacy of current anti-drone defences such as the UK’s Dragonfire laser system.
-
Israel’s MALE UAVs ‘must adapt’ to Iranian-made air defences
Advancements in air defence technologies have begun to reshape aerial combat dynamics in the Middle East, as illustrated by recent events involving the Israeli Air Force and Hezbollah.
-
Hundreds more UAS sent to Ukraine forces with thousands more on the way
Both sides of the Russia-Ukraine war have been using UAS for effective low-cost attacks, as well as impactful web and social media footage. Thousands more have now been committed to Ukrainian forces.
-
AI and software companies selected for US Army Robotic Combat Vehicle subsystems
The US Army has intentions to develop light, medium and heavy variants of the Robotic Combat Vehicle (RCV) as part of the branche’s Next Generation Combat Vehicle family.
-
DroneShield to improve software of DroneSentry-X C-UAS system under new contract
DroneSentry-X, a cross-vehicle compatible, automated 360° C-UAS detect and defeat device, can offer 360° awareness and protection using integrated sensors. According to its manufacturer, it is suitable for mobile operations, on-site surveillance and on-the-move missions.
-
Ukraine takes delivery of new indigenous C-UAS systems
Funded by the country’s former president, the new C-UAS systems will be sent to the frontline where they have already been tested against Russian invading forces.