Robotics New Evaluation Model Classifies Humanoid Robots

Source: Fraunhofer IPA | Translated by AI 1 min Reading Time

The model makes humanoids comparable, makes it easier to find the right humanoid for an application and highlights open issues in technology development.

With the Humanoid Capabilities Navigator, Fraunhofer IPA offers industry a practical tool for realistically evaluating the potential of humanoid robots.(Image: Fraunhofer IPA/Photo Rainer Bez)
With the Humanoid Capabilities Navigator, Fraunhofer IPA offers industry a practical tool for realistically evaluating the potential of humanoid robots.
(Image: Fraunhofer IPA/Photo Rainer Bez)

The Fraunhofer Institute for Manufacturing Engineering and Automation IPA has presented the "Humanoid Capabilities Navigator", an evaluation model that systematically compares the technical capabilities of humanoid robots. According to a press release, the model is intended to support companies in realistically evaluating the application potential of humanoid systems and making more informed investment decisions.

Until now, there has been no standardized benchmark for objectively classifying the performance and maturity of different systems. This is precisely where the approach developed at the Heilbronn site, which was created as part of the Fraunhofer Heilbronn Research and Innovation Centers (HNFIZ), comes in.

Manufacturer-Independent Basis for Comparison

The Navigator is conceptually based on the automation levels of autonomous driving and evaluates humanoids on the basis of four capability fields: Mobility, Manipulation, Cognition and Safety and Security. Individual capabilities are classified on a scale of 0 to 4, from non-existent to highly autonomous at human level or above. According to the researchers, this creates a manufacturer-independent basis for comparison for the first time.

In the white paper, the research team demonstrates the application using typical industrial processes such as loading and unloading, order picking, machine operation and maintenance. While complex logistics tasks place high demands on cognition, manipulation and safety, structured activities are easier to automate.

According to Fraunhofer, a practical test with the humanoid robot G1 from Unitree Robotics shows significant progress in areas such as mobility, but at the same time there is still a need for development for industrial applications. The model makes such technological gaps visible and helps to derive research priorities and better assess market developments.

Subscribe to the newsletter now

Don't Miss out on Our Best Content

By clicking on „Subscribe to Newsletter“ I agree to the processing and use of my data according to the consent form (please expand for details) and accept the Terms of Use. For more information, please see our Privacy Policy. The consent declaration relates, among other things, to the sending of editorial newsletters by email and to data matching for marketing purposes with selected advertising partners (e.g., LinkedIn, Google, Meta)

Unfold for details of your consent