Humanoid robots calibrate sensors and joints without external targets
OmniCalib: Target-Free, Task-Structured Self-Calibration for Humanoid Robots
Robotics
Summary
Humanoid robots need precise information about how their sensors and joints are arranged to move and see accurately. Over time, assembling parts or wear can cause this information to become inaccurate. The authors present OmniCalib, a method that lets robots recalibrate their sensors and joint positions using only their own movements and onboard cameras, without relying on special markers or external devices. This technique works for upper limbs, lower limbs, and multi-camera heads, showing accurate results in recovering joint and sensor positions.
What this means in practice
- •For robotics engineers: Calibrate humanoid robot sensors and joints using only onboard motion and cameras, eliminating the need for external fiducial targets.
- •For manufacturing automation teams: Maintain accurate robot calibration after component replacement or wear without halting production for manual recalibration.
Authors
Kaixiang Lu, Haiyu Lan, Chunxiao Qiao, You Li, Enyu Li, Yehao Lu, Jiarui Yang, Peiwen Lin, Chuang Wang
Abstract
Assembly, wear, and component replacement perturb the sensor extrinsics and joint zeros encoded by a humanoid CAD model. Existing procedures calibrate one sensor pair or require external fiducials. Using only robot-native motion and onboard sensing, we present OmniCalib, a target-free workflow that calibrates the full upper limbs---all 14 arm joint zeros and the extrinsics of both wrist and chest cameras---as well as lower limbs and the multi-camera head rig. Each module matches a robot-native task to a parameter block, checks observability, and writes only supported corrections to the CAD model. Our depth ICP method recovers all 14 arm joint zeros and calibrates all RGB-D camera extrinsics without any calibration target. Relative to CAD, the estimated extrinsic corrections are 10.56 mm and 1.74 degrees for the left wrist, 6.33 mm and 1.25 degrees for the right wrist, and 9.81 mm and 0.929 degrees for the chest RGB-D camera. ICP point-to-plane residual is 2.09 mm. On the same injected offsets, ICP and ArUco recover all 14 joint zeros below the 0.1-degree encoder-resolution reference. On an AGIBOT A3 Ultra humanoid, four static double-support stances recover all 12 lower-limb joint-zero offsets injected with an RMS error of 0.063 degrees. The head module combines multi-camera visual odometry with legged odometry and dynamic compensation through the live ROS transform tree. Using only planar walking, it attains a mean SO(3) error of 1.061 degrees across three sequences. The best sequence reaches 0.775 degrees, competitive with iKalibr at 0.902 degrees from rich 6-DOF excitation. Rig-relative angles repeat within 0.140 degrees. Injection recovery and held-out tests validate each observable block.