quARtet Marker: A 3D-Printable Multi-Tag Fiducial for Robust Near-Frontal Pose Estimation

2026-10-01

AI Summary

This study addresses the low pose estimation accuracy and frequent grasping conflicts encountered with transparent or reflective laboratory vessels under near-frontal viewpoints. To overcome these challenges, we propose a 3D-printed multi-fiducial marker benchmark that arranges four AprilTags obliquely within a single compact volume to recover perspective cues, innovatively balancing pose consistency with the contact surface requirements of parallel-jaw grippers. By integrating AprilTag detection with a Perspective-n-Point (PnP) solver, the proposed method reduces the mean orientation error from 2.18° to below 0.47° while significantly decreasing positional error. Furthermore, this work reveals the inherent trade-offs between estimation accuracy and graspability across different marker layouts, providing practical design guidelines for robotic manipulation in laboratory environments.

Abstract

Robotic manipulation of labware is difficult when transparent or reflective objects must be identified and localized. Coded planar fiducials are a practical retrofit: easy to print, they leave the marked face flat and graspable. Yet a single planar tag is least reliable in near-frontal views, where perspective cues fade. Non-planar geometries restore those cues but intrude on the flat face that a parallel-jaw gripper must contact. Our idea is to tilt multiple tags within one compact footprint, so that each tag is seen at a non-frontal angle even when the marker faces the camera. We propose the quARtet marker, a 3D-printable fiducial embodying this idea: all detected corners of its four tilted AprilTags enter one Perspective-n-Point solve, and a shared configuration defines the fabricated geometry and the detector model. Because tilting consumes flat area, its three layouts trade pose-estimation consistency against graspability. In robot-referenced, same-setup fixed-camera experiments, all three layouts reduced the mean frontal orientation error from 2.18 degree for a single planar tag to 0.24-0.47 degree and the root-mean-square position error from 1.50 to 0.17-0.20 mm. A robot-mounted-camera pose-hold test confirmed this separation under closed-loop visual feedback. In swing-down trials under identical conditions, the two layouts with flat contact strips retained the object with about 2 mm of in-grasp slip, whereas the layout without flat strips slipped by roughly 100 mm. For the tested conditions, the results support a rule: the layout without flat strips when pose-estimation consistency dominates, a layout with flat strips when the marked face must remain graspable.

Problem

• pose estimation
• planar fiducial
• robotic manipulation
• near-frontal view
• AprilTag

Innovation

• Fiducial Marker
• Pose Estimation
• AprilTag
• 3D-Printable Multi-Tag
• Robotic Manipulation