Korean researchers have developed a new “Physical AI” technology that mimics human forgetting to improve the navigation of autonomous mobile robots in logistics centres and smart factories.

The findings, published in the Journal of Industrial Information Integration, outline a system developed by Korea's Daegu Gyeongbuk Institute of Science and Technology (DGIST). The tech models the “spread and forgetting of social issues," enabling robots to distinguish between important, real-time obstacles and unnecessary, outdated information using this human-like forgetting method.

“We have mimicked the social principle of forgetting unnecessary information while retaining only important information to enable efficient movement. This study is significant in that it shows how Physical AI is evolving to resemble human behaviour,” said Professor Kyung-Joon Park, the study author.

Autonomous Mobile Robots (AMRs) are widely used in logistics and manufacturing but are often slowed by temporary obstacles. Conventional systems continue to reroute around blockages even after they are removed, cutting productivity.

To overcome the challenge of inefficient routing, Park’s team implemented a collective intelligence algorithm based on a human social phenomenon. This modeling allows the autonomous robots to immediately share only key information, such as the location of a sudden obstruction. Simultaneously, it naturally allows a robot to forget unnecessary, outdated details, like an obstacle that has since been cleared.

The researchers said the technique could optimise the machine’s “cooperative navigation” skills. Route optimisation and delay reduction could also lead to direct savings for companies in operating costs, power consumption, and equipment maintenance.

The team used the Gazebo simulator to test this model, which modeled a logistics centre. The results showed a clear performance upgrade compared to conventional ROS 2 navigation (Robot Operating System 2). Interestingly, the average driving time was reduced by up to 30.1 percent and task throughput increased by up to 18 percent.

The researchers said the method could cut costs by saving energy and reducing wear on equipment. It requires only 2D LiDAR sensors and is available as a plugin for ROS 2, making it easy to adopt.

They added that the approach could extend beyond factories to logistics robots, autonomous vehicles, drone swarms, smart city traffic management and large-scale exploration and rescue operations.