Saved in:
Bibliographic Details
Main Authors: Das, Ersin, Touma, Thomas, Burdick, Joel W.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.10802
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912259335258112
author Das, Ersin
Touma, Thomas
Burdick, Joel W.
author_facet Das, Ersin
Touma, Thomas
Burdick, Joel W.
contents This paper develops a Bayesian optimal experimental design for robot kinematic calibration on ${\mathbb{S}^3 \!\times\! \mathbb{R}^3}$. Our method builds upon a Gaussian process approach that incorporates a geometry-aware kernel based on Riemannian Matérn kernels over ${\mathbb{S}^3}$. To learn the forward kinematics errors via Bayesian optimization with a Gaussian process, we define a geodesic distance-based objective function. Pointwise values of this function are sampled via noisy measurements taken using fiducial markers on the end-effector using a camera and computed pose with the nominal kinematics. The corrected Denavit-Hartenberg parameters are obtained using an efficient quadratic program that operates on the collected data sets. The effectiveness of the proposed method is demonstrated via simulations and calibration experiments on NASA's ocean world lander autonomy testbed (OWLAT).
format Preprint
id arxiv_https___arxiv_org_abs_2409_10802
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Bayesian Optimal Experimental Design for Robot Kinematic Calibration
Das, Ersin
Touma, Thomas
Burdick, Joel W.
Robotics
This paper develops a Bayesian optimal experimental design for robot kinematic calibration on ${\mathbb{S}^3 \!\times\! \mathbb{R}^3}$. Our method builds upon a Gaussian process approach that incorporates a geometry-aware kernel based on Riemannian Matérn kernels over ${\mathbb{S}^3}$. To learn the forward kinematics errors via Bayesian optimization with a Gaussian process, we define a geodesic distance-based objective function. Pointwise values of this function are sampled via noisy measurements taken using fiducial markers on the end-effector using a camera and computed pose with the nominal kinematics. The corrected Denavit-Hartenberg parameters are obtained using an efficient quadratic program that operates on the collected data sets. The effectiveness of the proposed method is demonstrated via simulations and calibration experiments on NASA's ocean world lander autonomy testbed (OWLAT).
title Bayesian Optimal Experimental Design for Robot Kinematic Calibration
topic Robotics
url https://arxiv.org/abs/2409.10802