Whole-Body Elasto-Geometrical Calibration of Wheeled Humanoid Robots Using a Shared-Waist Dual-Chain Model
Whole-Body Elasto-Geometrical Calibration of Wheeled Humanoid Robots Using a Shared-Waist Dual-Chain Model
This research introduces a shared-waist dual-chain calibration framework for wheeled humanoid robots equipped with arms on a single actuated waist and lacking torque sensors.
The study presents a shared-waist dual-chain calibration method for wheeled humanoid robots that reduces end-effector positioning errors from 11.3-31.1 mm to 0.50-1.11 mm on held-out poses by modeling waist compliance and arm/arm torques, outperforming adaptations of two published whole-body calibration methods across training-set sizes from 20 to all poses.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
mean error reduction
0.5–1.11
View original evidence
mplements. On two robots with different waists, each without and with a payload, calibration reduces the mean errors on held-out poses from 11.3-31.1 mm to 0.50-1.11 mm. For every training-set size from 20 poses to all, the method has 17-63% lower mean errors than adaptations of two published whole-body calibration methods, mainly through the waist compliance. Independent calibration yields two waist models; using ei
Open source S4mean error reduction
11.3–31.1
View original evidence
mplements. On two robots with different waists, each without and with a payload, calibration reduces the mean errors on held-out poses from 11.3-31.1 mm to 0.50-1.11 mm. For every training-set size from 20 poses to all, the method has 17-63% lower mean errors than adaptations of two published whole-body calibration methods, mainly through the waist compliance. Independent calibration yields two waist models; using ei
Open source S4error increase
≤3.21
View original evidence
ther for both arms raises the other arm's error to up to 3.21 mm.
Open source S5training set size
20
View original evidence
mplements. On two robots with different waists, each without and with a payload, calibration reduces the mean errors on held-out poses from 11.3-31.1 mm to 0.50-1.11 mm. For every training-set size from 20 poses to all, the method has 17-63% lower mean errors than adaptations of two published whole-body calibration methods, mainly through the waist compliance. Independent calibration yields two waist models; using ei
Open source S4
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
mplements. On two robots with different waists, each without and with a payload, calibration reduces the mean errors on held-out poses from 11.3-31.1 mm to 0.50-1.11 mm. For every training-set size from 20 poses to all, the method has 17-63% lower mean errors than adaptations of two published whole-body calibration methods, mainly through the waist compliance. Independent calibration yields two waist models; using ei
Open source S4
ther for both arms raises the other arm's error to up to 3.21 mm.
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org