Manufacturing Physical AI specialist CarbonSix has launched a standardised toolkit based on robot imitation learning, which can be deployed directly on the factory floor.

SigmaKit enables manufacturers to implement AI-powered robotics without requiring specialised expertise or additional equipment. The toolkit leverages imitation learning to eliminate the burdensome process of system configuration and constant adjustments traditionally required by human operators.

SigmaKit combines hardware and software to address challenges that face manufacturers in achieving full automation. CarbonSix argues that to date, conventional robots have struggled to adapt flexibly to unstructured environments. To address these challenges, SigmaKit incorporates AI algorithms tailored to manufacturing processes, sensor modules for adaptive recognition, precision robotic grippers for delicate manipulation, and an intuitive teaching tool for simplified operation.

Imitation learning allows AI systems to learn directly from human demonstrations. This enables robots to reproduce complex actions and adapt flexibly to variable tasks. Unlike conventional programming approaches, it makes automation possible for unstructured and non-routine processes once considered beyond the reach of robotics.

“Sigma Kit is the first commercially available industrial robot AI solution based on imitation learning, capable of handling non-standardised and delicate tasks such as film attachment/removal, assembly, machine tending, cable fastening, and hanging operations. It can be applied across a wide range of industries including mobile, consumer electronics, automotive components, food, and materials. Since its launch, we have already received sales inquiries and reservations, and we are currently conducting PoC projects with major global manufacturers,” said Jehyuk Kim, CarbonSix Co-CEO, who led the development of Sigma Kit.