At the 2026 World Robot Conference (WRC), CHINGMU, in collaboration with the Beijing Municipal Culture and Tourism Bureau and the Chinese Academy of Inspection and Quarantine (CAIQ), presented a demonstration of the RoboEval robot motion assessment platform at a sub-venue. Using the approach of "quantifying every movement, verifying every delivery," it completes the final link in the "data-to-action" chain. Built on CHINGMU's high-precision optical motion capture and multi-source data fusion capabilities, RoboEval performs quantitative analysis on robot motion trajectories, 6DoF posture stability, response speed, repeatability, and execution deviation, and can simultaneously integrate data from force plates, video, and other sources.
Targeting scenarios such as R&D validation, factory inspection, return-to-factory retesting, and version regression, the platform establishes a motion quality assessment closed-loop from R&D to delivery. It supports real-time online browsing of data reports or one-click export of assessment reports, enabling deviations, jitter, and instability issues to be localized and quantified, further feeding back into algorithm optimization. This means that robot "motion capability" is transitioning from subjective observation to a data-driven, standardized validation phase: not only should the robot complete the action, but it should also be possible to accurately know whether the action is stable, precise, and how far it is from the target — providing a reliable quality benchmark for mass production delivery and continuous iteration of robots.