Kinematics Based Joint-Torque Estimation Using Bayesian Particle Filters

Roja Zakeri, Praveen Shankar

2023

Abstract

The aim of this paper is to estimate unknown torque in a 7-DOF industrial robot using Bayesian approach by observing the kinematic quantities. This paper utilizes two PMCMC algorithms (Particle Gibbs and Particle MH algorithms) for estimating unknown parameters of Baxter manipulator including joint torques, measurement and noise errors. The SMC technique has been used to construct the proposal distribution at each time step. The results indicate that for the Baxter manipulator, both PG and PMH algorithms perform well, but PG performs better as the estimated parameters using this technique have less deviation from the true parameters value. And this is due to sampling from parameters conditional distributions.

Paper Citation

in Harvard Style

Zakeri R. and Shankar P. (2023). Kinematics Based Joint-Torque Estimation Using Bayesian Particle Filters. In Proceedings of the 20th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO; ISBN 978-989-758-670-5, SciTePress, pages 188-195. DOI: 10.5220/0012178400003543

in Bibtex Style

@conference{icinco23,
author={Roja Zakeri and Praveen Shankar},
title={Kinematics Based Joint-Torque Estimation Using Bayesian Particle Filters},
booktitle={Proceedings of the 20th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO},
year={2023},
pages={188-195},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012178400003543},
isbn={978-989-758-670-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO
TI - Kinematics Based Joint-Torque Estimation Using Bayesian Particle Filters
SN - 978-989-758-670-5
AU - Zakeri R.
AU - Shankar P.
PY - 2023
SP - 188
EP - 195
DO - 10.5220/0012178400003543
PB - SciTePress