World Models and Simulation

A low AX=XB residual can coexist with an undetermined mounting offset. Compare pure translations, single-axis ambiguity and a second rotation direction.

Check whether the two front-wheel axle lines meet on the rear-axis line. Equal nonzero steering angles can fail that ideal instantaneous constraint.

A V-block can keep shafts laterally centered while their axes change height. Check whether the ideal tangencies also fall on the finite faces.

Averaging wheel travel gives path length, not a straight world displacement. Follow the finite turn, preserve heading and check the small-angle limit.

Equal edge lengths can hide a reflected asset. Distinguish object scale from changed mesh coordinates, and check a proper rotation before transferring a robot pose.

Validate the same finite-mesh endpoint in the same frame. Compare separate joint perturbations with geometric derivatives before converting tip velocity to joint rates.

A central tensor, an origin tensor and a rotated tensor describe different references. Compare finite assigned-mass cuboids before transferring robot model values.

A mesh can remain in place while the render camera clips it away. Compare actual frames and finite depth bounds, including a slab with no original corners inside.

The same one-pixel correspondence change gives a larger, asymmetric depth interval farther away. Compare audited synthetic rays at two depths and baselines.

A rotating tool can keep its flange coordinates yet move its tip. Compare the same orientation with fixed flange position or a compensated fixed TCP point.