Zero-Shot Parameter Learning of Robot Dynamics Using Bayesian Statistics and Prior Knowledge

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Reiners, Carsten, Trinh, Minh, Gründel, Lukas, Tauchmann, Sven, Bitterolf, David, Petrovic, Oliver, Brecher, Christian
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915357511385088
author Reiners, Carsten
Trinh, Minh
Gründel, Lukas
Tauchmann, Sven
Bitterolf, David
Petrovic, Oliver
Brecher, Christian
author_facet Reiners, Carsten
Trinh, Minh
Gründel, Lukas
Tauchmann, Sven
Bitterolf, David
Petrovic, Oliver
Brecher, Christian
contents Inertial parameter identification of industrial robots is an established process, but standard methods using Least Squares or Machine Learning do not consider prior information about the robot and require extensive measurements. Inspired by Bayesian statistics, this paper presents an identification method with improved generalization that incorporates prior knowledge and is able to learn with only a few or without additional measurements (Zero-Shot Learning). Furthermore, our method is able to correctly learn not only the inertial but also the mechanical and base parameters of the MABI Max 100 robot while ensuring physical feasibility and specifying the confidence intervals of the results. We also provide different types of priors for serial robots with 6 degrees of freedom, where datasheets or CAD models are not available.
format Preprint
id arxiv_https___arxiv_org_abs_2506_19350
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Zero-Shot Parameter Learning of Robot Dynamics Using Bayesian Statistics and Prior Knowledge
Reiners, Carsten
Trinh, Minh
Gründel, Lukas
Tauchmann, Sven
Bitterolf, David
Petrovic, Oliver
Brecher, Christian
Robotics
Systems and Control
Inertial parameter identification of industrial robots is an established process, but standard methods using Least Squares or Machine Learning do not consider prior information about the robot and require extensive measurements. Inspired by Bayesian statistics, this paper presents an identification method with improved generalization that incorporates prior knowledge and is able to learn with only a few or without additional measurements (Zero-Shot Learning). Furthermore, our method is able to correctly learn not only the inertial but also the mechanical and base parameters of the MABI Max 100 robot while ensuring physical feasibility and specifying the confidence intervals of the results. We also provide different types of priors for serial robots with 6 degrees of freedom, where datasheets or CAD models are not available.
title Zero-Shot Parameter Learning of Robot Dynamics Using Bayesian Statistics and Prior Knowledge
topic Robotics
Systems and Control
url https://arxiv.org/abs/2506.19350