Researchers developed a brain-inspired AI model that uses cognitive maps, controlled randomness, and reusable information to solve problems without testing every possible path. The system adapted to changing conditions without retraining and successfully handled physical navigation, abstract multidimensional planning, and shape-building tasks. Although still experimental, the low-energy approach could support robots, autonomous vehicles, and edg…
This story is only covered by news sources that have yet to be evaluated by the independent media monitoring agencies we use to assess the quality and reliability of news outlets on our platform. Learn more here.