Lifelong deep learning-based control of robot manipulators

DOI10.1002/ACS.3678MaRDI QIDQ6493615zbMATH OpenFDO

Authors Irfan Ganie, Sarangapani Jagannathan

Publication date 29 April 2024

Published in International Journal of Adaptive Control and Signal Processing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1002/ACS.3678

zbMATH Keywords

catastrophic forgettingdeep neural networkselastic weight consolidationlifelong learningroboticssingular value decomposition

Mathematics Subject Classification ID

Systems theory; control (93-XX)

Recommendations

• Neural learning control of flexible joint manipulator with predefined tracking performance and application to Baxter robot
• Robot control policy transfer based on progressive neural network
• Adaptive learning tracking control of robotic manipulators with uncertainties
• Dynamic learning from adaptive neural control of uncertain robots with guaranteed full-state tracking precision
• Improved recurrent neural network-based manipulator control with remote center of motion constraints: experimental results

Cites work

• Deep belief networks are compact universal approximators
• Dying ReLU and initialization: theory and numerical examples
• Overcoming catastrophic forgetting in neural networks

This page was built for publication: Lifelong deep learning-based control of robot manipulators

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6493615)