UBtech's industrial humanoid robots implement "collective intelligence" through collaborative training at the Zeeker 5G smart factory.

UBtech, a high-tech company based in Beijing E-Town, has made history by hosting the world's first multi-robot collaborative training in multiple scenarios and tasks at the cutting-edge Zeeker 5G smart factory. This training aims to explore a universal humanoid robot collective operation solution for multi-task industrial scenarios and promote the evolution of humanoid robots from single-machine autonomy to collective intelligence.

UBtech's industrial humanoid robots implement "collective intelligence" through collaborative training at the Zeeker 5G smart factory.

In industrial settings, the tasks at the production line level pose new challenges and tests for the level of multi-robot collaborative operations with humanoid robots. Advancing the technology of collective intelligence for humanoid robots is a crucial step towards achieving large-scale industrial applications.

UBtech has for the first time introduced collective intelligence technology into humanoid robots to enable multi-robot collaborative operations. Using a cluster of humanoid robots as the physical carrier, it is exploring the evolution of high-level embodied intelligence through group behavior and intensive interaction with the external physical environment.

To achieve this goal, UBtech innovatively proposed the "BrainNet" software architecture for humanoid robot group intelligence and designed the Internet of Humanoids (IoH) as the central nervous system for humanoid intelligence networking, providing a path for the implementation of collective intelligence in both software and hardware.

UBtech's industrial humanoid robots implement "collective intelligence" through collaborative training at the Zeeker 5G smart factory.

In the factory, these robots are deployed in various complex scenarios such as the final assembly workshop, SPS instrument area, quality inspection area, and car door assembly area.

They successfully achieved tasks like collaborative sorting, handling, and precision assembly through multi-task collaborative operations.

During the training process, the humanoid robots innovatively applied cross-domain pure visual perception technology and intelligent hybrid decision-making technology. They overcame challenges such as uneven load distribution, complex motion trajectories, and adaptation to dynamic environments, which has demonstrated their exceptional ability in agile manipulation of soft objects.