Inverse Kinematics for Robotic Manipulators via Deep Neural Networks: Experiments and Results
Open Access
- 26 June 2025
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 15 (13) , 7226
Abstract
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.Keywords
Funding Information
- Consejería de Sanidad, Comunidad de Madrid (TEC 2024/TEC-62, DTS22/00105)
- Instituto de Salud Carlos III (TEC 2024/TEC-62, DTS22/00105)
- EU Structural Funds (TEC 2024/TEC-62, DTS22/00105)
This publication has 27 references indexed in Scilit:
- Generative Graphical Inverse KinematicsIEEE Transactions on Robotics, 2024
- Artificial Neural Networks for inverse kinematics problem in articulated robotsEngineering Applications of Artificial Intelligence, 2023
- Deep neural networks in the cloud: Review, applications, challenges and research directionsNeurocomputing, 2023
- Analytical and deep learning approaches for solving the inverse kinematic problem of a high degrees of freedom robotic armEngineering Applications of Artificial Intelligence, 2023
- A Deep Learning Approach to Navigating the Joint Solution Space of Redundant Inverse Kinematics and Its Applications to Numerical IK ComputationsIEEE Access, 2023
- The choice of scaling technique matters for classification performanceApplied Soft Computing, 2022
- Learning Constrained Distributions of Robot Configurations With Generative Adversarial NetworkIEEE Robotics and Automation Letters, 2021
- An analytical and a Deep Learning model for solving the inverse kinematic problem of an industrial parallel robotComputers & Industrial Engineering, 2021
- Arithmetic and geometric solutions for average rigid-body rotationMechanism and Machine Theory, 2010
- Metrics for 3D Rotations: Comparison and AnalysisJournal of Mathematical Imaging and Vision, 2009