Metric measures how articulated objects move and connect accurately
ArticulateArena: A Metric for Articulated Kinematics
RoboticsComputer Vision and Pattern Recognition
Summary
It's hard to compare moving parts of objects because their motion can be described in many ways. The authors created a new way to measure how parts move together that doesn’t depend on how you describe them. This method measures the actual motion caused by joints rather than just the numbers that describe the joint. They also made a big collection of objects with known movements to test their method and found existing ways to evaluate joint motions less accurate.
What this means in practice
- •For 3d model developers: Evaluate the accuracy of simulated movable parts in 3D models using a unified motion-based metric instead of separate parameters.
- •For robotics engineers: Compare and verify robotic joint motions with a metric that directly measures physical movement similarity across different joint types.
Authors
Yumeng He, Yongfei She, Huanyu Chen, Chun Yuan, Peihao Li, Joseph Masterjohn, Yin Yang, Ying Jiang, Chenfanfu Jiang
Abstract
Modern methods reconstruct or generate simulation-ready articulated objects, predicting not only their geometry but also how their parts are connected and allowed to move. Evaluating the geometry is straightforward, but evaluating the predicted articulation is not, because articulation specifies a motion rather than a shape, and there is no agreed distance between two motions. More specifically, existing protocols score joint type, axis direction, origin, and motion limits separately, although these parameters jointly describe a single physical motion, and the same motion can be written as different parameter values. As a result, a joint can score maximally wrong against an equivalent encoding of itself, and several component errors are ill-conditioned or undefined exactly where predictions become accurate. We propose ArticulateArena, a representation-invariant counterpart of Chamfer distance for articulation that compares the motions one-DOF joints induce rather than the parameters that encode them. It represents each joint by the unordered pair of its Lie-algebra endpoint twists, and we prove that the resulting quotient distance is a metric. It unifies fixed, revolute, prismatic, and helical joints, brings continuous joints into the same score through a compactification, and reads as the RMS motion of the moving part in meters when weighted by its mass distribution. A motion-aware tree edit distance lifts the metric to full kinematic trees, pricing structural errors such as spurious or missing joints in the same motion units as joint errors, and for a fixed inner product it remains a metric on trees up to relabeling. Alongside the metric we release ArticulateArena-20K, a new suite of 19,977 articulated objects with verified kinematics, and we re-evaluate published reconstruction methods on it under the new metric. Project page: https://heyumeng.com/ArticulateArena-web/