AnchorHEC improves calibration of wrist and fixed robot cameras
AnchorHEC: Targetless Hand-Eye Calibration of Wrist and Fixed Cameras
Robotics
Summary
Robots often use cameras on their moving arms and fixed locations, but getting precise alignment between these cameras and the robot itself can be tricky without special markers. The authors present AnchorHEC, a method that uses regular images, robot arm data, and known camera details to calibrate both moving and fixed cameras at once, without any special targets. Their approach improves accuracy by using a shared 3D model and refining the arm camera's pose, which then helps calibrate fixed cameras. Tests show significant error reductions in simulations and real robot experiments.
What this means in practice
- •For robotics engineers: Precisely align multiple cameras on robotic systems without using special calibration targets, improving overall perception accuracy.
- •For industrial automation teams: Calibrate vision systems combining fixed and arm-mounted cameras efficiently to enhance robot operation in manufacturing and inspection tasks.
Authors
Guebin Hwang, Taeyeop Lee, Yeonseo Lee, Hyosup Shin, Sungho Jo
Abstract
Recent robot systems combine wrist and fixed cameras, requiring camera-to-robot transforms for both. Most hand-eye calibration methods rely on targets or robot-body observations. Scene-based methods using 3D reconstruction require neither but address only wrist cameras. We introduce AnchorHEC, a targetless hand-eye calibration framework for wrist and fixed cameras in a single procedure using RGB images, forward kinematics (FK), and known camera intrinsics. We initialize both camera types using FK and a shared 3D foundation model reconstruction. FK-constrained wrist-image bundle adjustment reduces the impact of reconstructed pose and scale errors. If this refinement fails or retains too few inliers, we relax the constraints on potentially inaccurate FK poses and lens parameters. We use the refined wrist transform and FK to triangulate metric points and estimate fixed-camera poses. Across three backbones, calibration errors in simulation decrease by 86.4% in translation and 71.6% in rotation, averaged over both camera types, relative to reconstruction-based baselines. We also validate AnchorHEC on a physical robot. Project page: https://hwanggb.github.io/AnchorHEC/