Beckhoff at the Hanover Fair
When machines learn with natural language
A key topic for Beckhoff at Hannover Messe 2026 is the fusion of artificial intelligence and conventional machine control as the basis for physical AI. In hall 27 at stand G56, the automation specialist will be demonstrating how large language models (LLMs) can directly influence real motion sequences via standardized interfaces. The potential that can be developed in this way will be demonstrated in a playful way in the accompanying exhibit. A foretaste of this can already be seen at the Hannover Messe Press Preview on February 25.
The integration of physical AI marks a paradigm shift in the manufacturing industry: a direct coupling of AI models with deterministic control technology enables machines to no longer just process static commands, but to react to complex requirements in a contextual and autonomous manner.
Beckhoff is providing an initial tangible impression at the Hannover Messe with a compact demo cell. It combines the XPlanar planar motor drive system with the TwinCAT CoAgent AI tool and an audio interface for voice commands. Visitors can experience a physical AI application in which the hovering movers can be controlled using natural speech and initiate the next movement sequence on command. This playfully demonstrates how simple and intuitive collaboration between man and machine can be in the future: Complex automation tasks can then be carried out without specific programming knowledge.
At Hannover Messe 2026 from April 20 to 24, Beckhoff will be scaling this scenario to a fully integrated industrial application. The focus is on the modular industrial robot ATRO, which is programmed and controlled via the TwinCAT CoAgent for Operations using voice commands. Based on the Model Context Protocol (MCP), the controller acts as an intelligent agent that translates human speech into machine commands, orchestrates path planning and performs diagnostic tasks. The Physical AI application is demonstrated in a playful way by the exhibit playing chess against trade fair visitors.
With tools such as TwinCAT CoAgent and TwinCAT Machine Learning Creator, Beckhoff already offers an ecosystem that serves as an enabler for this new era of automation. The tools support machine builders throughout the entire life cycle - from code generation in engineering through to error analysis during operation.
"We are bringing AI from the chat windows directly into the machine and enabling language models to access the real world of control through new standards such as MCP," says Hans Beckhoff, managing owner of Beckhoff, describing the current development. "Technical inventions have always determined the development of society. Artificial intelligence and physical AI will take on this role with the same scope as the steam engine and electricity once did."










