Inverse Kinematics for Robotic Manipulators via Deep Neural Networks: Experiments and Results

This paper explores the application of Deep Neural Networks (DNNs) to solve the Inverse Kinematics (IK) problem in robotic manipulators. The IK problem, crucial for ensuring precision in robotic movements, involves determining joint configurations for a manipulator to reach a desired position or ori...

Full description

Saved in:
Bibliographic Details
Main Authors: Ana Calzada-Garcia, Juan G. Victores, Francisco J. Naranjo-Campos, Carlos Balaguer
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/13/7226
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849428761248792576
author Ana Calzada-Garcia
Juan G. Victores
Francisco J. Naranjo-Campos
Carlos Balaguer
author_facet Ana Calzada-Garcia
Juan G. Victores
Francisco J. Naranjo-Campos
Carlos Balaguer
author_sort Ana Calzada-Garcia
collection DOAJ
description This paper explores the application of Deep Neural Networks (DNNs) to solve the Inverse Kinematics (IK) problem in robotic manipulators. The IK problem, crucial for ensuring precision in robotic movements, involves determining joint configurations for a manipulator to reach a desired position or orientation. Traditional methods, such as analytical and numerical approaches, have limitations, especially for redundant manipulators, or involve high computational costs. Recent advances in machine learning, particularly with DNNs, have shown promising results and seem fit for addressing these challenges. This study investigates several DNN architectures, namely Feed-Forward Multilayer Perceptrons (MLPs), Convolutional Neural Networks (CNNs), and Recurrent Neural Networks (RNNs), for solving the IK problem, using the TIAGo robotic arm with seven Degrees of Freedom (DOFs). Different training datasets, normalization techniques, and orientation representations are tested, and custom metrics are introduced to evaluate position and orientation errors. The performance of these models is compared, with a focus on curriculum learning to optimize training. The results demonstrate the potential of DNNs to efficiently solve the IK problem while avoiding issues such as singularities, competing with traditional methods in precision and speed.
format Article
id doaj-art-ef578ec01c0846da87bb42ee17cbdd2a
institution Kabale University
issn 2076-3417
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-ef578ec01c0846da87bb42ee17cbdd2a2025-08-20T03:28:36ZengMDPI AGApplied Sciences2076-34172025-06-011513722610.3390/app15137226Inverse Kinematics for Robotic Manipulators via Deep Neural Networks: Experiments and ResultsAna Calzada-Garcia0Juan G. Victores1Francisco J. Naranjo-Campos2Carlos Balaguer3RoboticsLab, Systems and Automation Engineering Department, University Carlos III of Madrid, 28911 Leganés, SpainRoboticsLab, Systems and Automation Engineering Department, University Carlos III of Madrid, 28911 Leganés, SpainRoboticsLab, Systems and Automation Engineering Department, University Carlos III of Madrid, 28911 Leganés, SpainRoboticsLab, Systems and Automation Engineering Department, University Carlos III of Madrid, 28911 Leganés, SpainThis paper explores the application of Deep Neural Networks (DNNs) to solve the Inverse Kinematics (IK) problem in robotic manipulators. The IK problem, crucial for ensuring precision in robotic movements, involves determining joint configurations for a manipulator to reach a desired position or orientation. Traditional methods, such as analytical and numerical approaches, have limitations, especially for redundant manipulators, or involve high computational costs. Recent advances in machine learning, particularly with DNNs, have shown promising results and seem fit for addressing these challenges. This study investigates several DNN architectures, namely Feed-Forward Multilayer Perceptrons (MLPs), Convolutional Neural Networks (CNNs), and Recurrent Neural Networks (RNNs), for solving the IK problem, using the TIAGo robotic arm with seven Degrees of Freedom (DOFs). Different training datasets, normalization techniques, and orientation representations are tested, and custom metrics are introduced to evaluate position and orientation errors. The performance of these models is compared, with a focus on curriculum learning to optimize training. The results demonstrate the potential of DNNs to efficiently solve the IK problem while avoiding issues such as singularities, competing with traditional methods in precision and speed.https://www.mdpi.com/2076-3417/15/13/7226deep learninginverse kinematicsroboticscurriculum learning
spellingShingle Ana Calzada-Garcia
Juan G. Victores
Francisco J. Naranjo-Campos
Carlos Balaguer
Inverse Kinematics for Robotic Manipulators via Deep Neural Networks: Experiments and Results
Applied Sciences
deep learning
inverse kinematics
robotics
curriculum learning
title Inverse Kinematics for Robotic Manipulators via Deep Neural Networks: Experiments and Results
title_full Inverse Kinematics for Robotic Manipulators via Deep Neural Networks: Experiments and Results
title_fullStr Inverse Kinematics for Robotic Manipulators via Deep Neural Networks: Experiments and Results
title_full_unstemmed Inverse Kinematics for Robotic Manipulators via Deep Neural Networks: Experiments and Results
title_short Inverse Kinematics for Robotic Manipulators via Deep Neural Networks: Experiments and Results
title_sort inverse kinematics for robotic manipulators via deep neural networks experiments and results
topic deep learning
inverse kinematics
robotics
curriculum learning
url https://www.mdpi.com/2076-3417/15/13/7226
work_keys_str_mv AT anacalzadagarcia inversekinematicsforroboticmanipulatorsviadeepneuralnetworksexperimentsandresults
AT juangvictores inversekinematicsforroboticmanipulatorsviadeepneuralnetworksexperimentsandresults
AT franciscojnaranjocampos inversekinematicsforroboticmanipulatorsviadeepneuralnetworksexperimentsandresults
AT carlosbalaguer inversekinematicsforroboticmanipulatorsviadeepneuralnetworksexperimentsandresults