EUVIMEDEUVIMED entdecken
Crossref

Performing the Inverse Kinematics of an ABB 6 DOF Robotic Arm with LSTM, Feedforward and Recurrent Neural Networks

Christopher O. Okoh, Neil Buckley, Emanuele Lindo Seccco

Journal of Artificial Intelligence & Control Systems · 13.11.2026 · 80

DOI: 10.66967/jaics.2026.v2i202 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Artificial Intelligence & Control Systems, online erschienen am 13.11.2026. Verfasst von Christopher O. Okoh und 2 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Conventional numerical Inverse Kinematics (IK) methods—such as the Jacobian Pseudo-inverse, Levenberg-Marquardt (LM), and Newton-Raphson algorithms—are known to be applied when solving the non-linear IK problems of a robot arm. This is done by taking an initial guess of the joint angles and iteratively or sequentially calculating small adjustments using the robot's Jacobian matrix until the end-effector converges onto the target 6-DoF pose. While highly accurate, these traditional techniques suffer from several funda-mental limitations such as high computational cost and slower inference, high dependency on initial guess and inability to handle mul-ti-modal solutions and thus make them challenging to deploy in dynamic, real-time, or highly complex robotic environments. This paper leverages on the dataset of an ABB IRB120 6 Degree Of Freedom (DOF) robot arm from Kaggle where end-effectors’ positions ob-tained by means of Forward Kinematics (FK) are fed into the neural network models. And the derived joint angles were mapped to the end-effectors’ position thereby showing a faster method of providing IK solutions. The datasets were trained individually on Long-Short Term Memory (LSTM) neural network, Feed-forward Neural Network (FNN), and Recurrent Neural Network (RNN) using Keras on Tensor Flow. According to a performance analysis of the results, the LSTM model showed an MSE of 0.0001 rad2 with an execution time of 0.4 secs which translates into a highly precise inverse mapping capable of accurately guiding the robot through its Cartesian trajectory while satisfying latency constraints during robot deployment. Other experimental evaluations made are the MAE, R2 score and the End-effector error (Mean/Max) to show a high precision and minimal Euclidean distance error of the End-effector’s 3D Cartesian coor-dinates (x, y, z). Comparisons were made with previous results that performed IK evaluations using neural networks.

Zitieren

APA

Okoh, C. O., Buckley, N., & Seccco, E. L. (2026). Performing the Inverse Kinematics of an ABB 6 DOF Robotic Arm with LSTM, Feedforward and Recurrent Neural Networks. Journal of Artificial Intelligence & Control Systems, 80. https://doi.org/10.66967/jaics.2026.v2i202

Vancouver

Okoh CO, Buckley N, Seccco EL. Performing the Inverse Kinematics of an ABB 6 DOF Robotic Arm with LSTM, Feedforward and Recurrent Neural Networks. Journal of Artificial Intelligence & Control Systems. 2026:80. doi:10.66967/jaics.2026.v2i202

BibTeX
@article{Okoh2026,
  author = {Okoh, Christopher O. and Buckley, Neil and Seccco, Emanuele Lindo},
  title = {Performing the Inverse Kinematics of an ABB 6 DOF Robotic Arm with LSTM, Feedforward and Recurrent Neural Networks},
  journal = {Journal of Artificial Intelligence & Control Systems},
  year = {2026},
  pages = {80},
  doi = {10.66967/jaics.2026.v2i202}
}
Kostenlos starten →