Cargando…

Using Deep Neural Networks to Improve Contact Wrench Estimation of Serial Robotic Manipulators in Static Tasks

Reliable force-driven robot-interaction requires precise contact wrench measurements. In most robot systems these measurements are severely incorrect and in most manipulation tasks expensive additional force sensors are installed. We follow a learning approach to train the dependencies between joint...

Descripción completa

Detalles Bibliográficos
Autores principales: Osburg, Jonas, Kuhlemann, Ivo, Hagenah, Jannis, Ernst, Floris
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9106527/
https://www.ncbi.nlm.nih.gov/pubmed/35572376
http://dx.doi.org/10.3389/frobt.2022.892916
_version_ 1784708306889080832
author Osburg, Jonas
Kuhlemann, Ivo
Hagenah, Jannis
Ernst, Floris
author_facet Osburg, Jonas
Kuhlemann, Ivo
Hagenah, Jannis
Ernst, Floris
author_sort Osburg, Jonas
collection PubMed
description Reliable force-driven robot-interaction requires precise contact wrench measurements. In most robot systems these measurements are severely incorrect and in most manipulation tasks expensive additional force sensors are installed. We follow a learning approach to train the dependencies between joint torques and end-effector contact wrenches. We used a redundant serial light-weight manipulator (KUKA iiwa 7 R800) with integrated force estimation based on the joint torques measured in each of the robot’s seven axes. Firstly, a simulated dataset is created to let a feed-forward net learn the relationship between end-effector contact wrenches and joint torques for a static case. Secondly, an extensive real training dataset was acquired with 330,000 randomized robot positions and end-effector contact wrenches and used for retraining the simulated trained feed-forward net. We can show that the wrench prediction error could be reduced by around 57% for the forces compared to the manufacturer’s proprietary force estimation model. In addition, we show that the number of high outliers can be reduced substantially. Furthermore we prove that the approach could be also transferred to another robot (KUKA iiwa 14 R820) with reasonable prediction accuracy and without the need of acquiring new robot specific data.
format Online
Article
Text
id pubmed-9106527
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-91065272022-05-14 Using Deep Neural Networks to Improve Contact Wrench Estimation of Serial Robotic Manipulators in Static Tasks Osburg, Jonas Kuhlemann, Ivo Hagenah, Jannis Ernst, Floris Front Robot AI Robotics and AI Reliable force-driven robot-interaction requires precise contact wrench measurements. In most robot systems these measurements are severely incorrect and in most manipulation tasks expensive additional force sensors are installed. We follow a learning approach to train the dependencies between joint torques and end-effector contact wrenches. We used a redundant serial light-weight manipulator (KUKA iiwa 7 R800) with integrated force estimation based on the joint torques measured in each of the robot’s seven axes. Firstly, a simulated dataset is created to let a feed-forward net learn the relationship between end-effector contact wrenches and joint torques for a static case. Secondly, an extensive real training dataset was acquired with 330,000 randomized robot positions and end-effector contact wrenches and used for retraining the simulated trained feed-forward net. We can show that the wrench prediction error could be reduced by around 57% for the forces compared to the manufacturer’s proprietary force estimation model. In addition, we show that the number of high outliers can be reduced substantially. Furthermore we prove that the approach could be also transferred to another robot (KUKA iiwa 14 R820) with reasonable prediction accuracy and without the need of acquiring new robot specific data. Frontiers Media S.A. 2022-04-28 /pmc/articles/PMC9106527/ /pubmed/35572376 http://dx.doi.org/10.3389/frobt.2022.892916 Text en Copyright © 2022 Osburg, Kuhlemann, Hagenah and Ernst. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Robotics and AI
Osburg, Jonas
Kuhlemann, Ivo
Hagenah, Jannis
Ernst, Floris
Using Deep Neural Networks to Improve Contact Wrench Estimation of Serial Robotic Manipulators in Static Tasks
title Using Deep Neural Networks to Improve Contact Wrench Estimation of Serial Robotic Manipulators in Static Tasks
title_full Using Deep Neural Networks to Improve Contact Wrench Estimation of Serial Robotic Manipulators in Static Tasks
title_fullStr Using Deep Neural Networks to Improve Contact Wrench Estimation of Serial Robotic Manipulators in Static Tasks
title_full_unstemmed Using Deep Neural Networks to Improve Contact Wrench Estimation of Serial Robotic Manipulators in Static Tasks
title_short Using Deep Neural Networks to Improve Contact Wrench Estimation of Serial Robotic Manipulators in Static Tasks
title_sort using deep neural networks to improve contact wrench estimation of serial robotic manipulators in static tasks
topic Robotics and AI
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9106527/
https://www.ncbi.nlm.nih.gov/pubmed/35572376
http://dx.doi.org/10.3389/frobt.2022.892916
work_keys_str_mv AT osburgjonas usingdeepneuralnetworkstoimprovecontactwrenchestimationofserialroboticmanipulatorsinstatictasks
AT kuhlemannivo usingdeepneuralnetworkstoimprovecontactwrenchestimationofserialroboticmanipulatorsinstatictasks
AT hagenahjannis usingdeepneuralnetworkstoimprovecontactwrenchestimationofserialroboticmanipulatorsinstatictasks
AT ernstfloris usingdeepneuralnetworkstoimprovecontactwrenchestimationofserialroboticmanipulatorsinstatictasks