SRI to develop continuously learning AI
SRI International has been selected by DARPA to develop a next-generation artificial intelligence (AI) system that will be able to learn continuously and apply that learning to become better and more reliable at performing new tasks, the company announced on 16 June.
Currently available AI systems are not able to handle new scenarios that they are not trained on and repeatedly make the same mistakes. Even with retraining, today’s systems are prone to 'catastrophic forgetting' when a new item disrupts previously learned knowledge.
As part of the DARPA’s Lifelong Learning Machines (L2M) programme, the SRI team will develop AI algorithms based on biological mechanisms in memory consolidation and replay. With this AI technology, future cognitive systems such as autonomous robots may be able to continually learn after initial deployment, improving execution performance and overall safety.
Biological memory transfer is a complex sequence of dynamic processes, with local and global synchronisation patterns. These processes support memories with flexibility in expression for future thinking, foresight,
planning and creativity.
Sek Chai, technical director in the Center for Vision Technologies, SRI International, said: ‘Our goal is to address these limitations by enabling AI systems to know what to learn and when. Since memory is a key element of cognitive function, our research is focused on understanding and applying biological memory transfers to new AI algorithms that can fundamentally improve their performance throughout their fielded lifetime experience.’More from Uncrewed Vehicles
-
Tekever unveils new swarm-controlling UAS
Tekever has manufactured the AR3, AR4 and AR5 UAS with all systems sharing common electronics and software architecture, which has enabled the reuse of ground segment elements within the new ARX UAS.
-
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.