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
-
![AUSA 2024: Quantum-Systems targets big 2025 with UAS developments]()
AUSA 2024: Quantum-Systems targets big 2025 with UAS developments
Quantum-Systems has been upgrading its UAS family, with new versions of the Vector, Reliant and Twister drones set for release throughout 2025.
-
![US Army accelerates acquisition and field of company-level sUAS]()
US Army accelerates acquisition and field of company-level sUAS
The service has been using a Directed Requirement (DR) approach to speed up the deployment of a Medium Range Reconnaissance capability.
-
![AeroVironment to display eVTOL P550 at AUSA 2024]()
AeroVironment to display eVTOL P550 at AUSA 2024
AeroVironment’s portfolio will grow thanks to the eVTOL P550 aimed at battalion-level tactical forces.
-
![Australia’s air force aims its UAV fleet northwards]()
Australia’s air force aims its UAV fleet northwards
The Royal Australian Air Force is advancing its unmanned aerial vehicle (UAV) capabilities across three key programmes as it works with the likes of Boeing and Northrop Grumman to reshape Australia’s defence strategy.
-
![FTUAS competitor trials were “very successful”, says US Army official]()
FTUAS competitor trials were “very successful”, says US Army official
Prototypes from Griffon Aerospace and Textron Systems recently passed through MOSA conformance trials and flight tests.
-
![Pentagon adds Replicator 2 to budget request with focus on C-sUAS capabilities]()
Pentagon adds Replicator 2 to budget request with focus on C-sUAS capabilities
Funds for the second phase of this effort will be allocated in the US Department of Defense (DoD) FY2026 budget request.
