Event-driven bi-fidelity control for efficient and reliable robotic manipulation
This paper proposes a novel bi-fidelity control framework for robotic manipulators that integrates a high-fidelity model predictive control (MPC) scheme with a low-fidelity Long Short-Term Memory (LSTM) neural network surrogate. Unlike conventional fixed-schedule approaches, our method employs an ev...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-06-01
|
| Series: | Results in Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590123025014446 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849309956640079872 |
|---|---|
| author | Fawaz W. Alsaade Mohammed S. Al-zahrani Fuad E. Alsaadi |
| author_facet | Fawaz W. Alsaade Mohammed S. Al-zahrani Fuad E. Alsaadi |
| author_sort | Fawaz W. Alsaade |
| collection | DOAJ |
| description | This paper proposes a novel bi-fidelity control framework for robotic manipulators that integrates a high-fidelity model predictive control (MPC) scheme with a low-fidelity Long Short-Term Memory (LSTM) neural network surrogate. Unlike conventional fixed-schedule approaches, our method employs an event-triggered mechanism that dynamically selects the appropriate controller based on a real-time error metric. This mechanism ensures that the computationally intensive MPC is invoked only when the LSTM approximation deviates beyond acceptable bounds. We rigorously established the near-optimal performance and closed-loop stability of our approach via Lyapunov analysis under mild assumptions, instilling confidence in its reliability. The simulation results on a three-arm manipulator, subject to low-frequency sinusoidal and high-frequency chirp trajectories, demonstrate that the proposed approach achieves up to 80–90% reduction in MPC calls, significantly improving the accuracy of the follow-up and computational efficiency. These findings highlight the potential of integrating learning-based approximations with conventional optimization-based control to achieve reliable and time-efficient performance in complex robotic manipulation tasks. |
| format | Article |
| id | doaj-art-7db9a91f5df842e3a54ad2a75a5bb73f |
| institution | Kabale University |
| issn | 2590-1230 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Engineering |
| spelling | doaj-art-7db9a91f5df842e3a54ad2a75a5bb73f2025-08-20T03:53:56ZengElsevierResults in Engineering2590-12302025-06-012610537410.1016/j.rineng.2025.105374Event-driven bi-fidelity control for efficient and reliable robotic manipulationFawaz W. Alsaade0Mohammed S. Al-zahrani1Fuad E. Alsaadi2Department of Computer Science, College of Computer Sciences and Information Technology, King Faisal University, Al-Ahsa 31982, Saudi ArabiaDepartment of Computer Networks and Communications, College of Computer Sciences and Information Technology, King Faisal University, Al-Ahsa 31982, Saudi ArabiaCommunication Systems and Networks Research Group, Department of Electrical and Computer Engineering, Faculty of Engineering, King Abdulaziz University, Jeddah, Saudi Arabia; Corresponding author.This paper proposes a novel bi-fidelity control framework for robotic manipulators that integrates a high-fidelity model predictive control (MPC) scheme with a low-fidelity Long Short-Term Memory (LSTM) neural network surrogate. Unlike conventional fixed-schedule approaches, our method employs an event-triggered mechanism that dynamically selects the appropriate controller based on a real-time error metric. This mechanism ensures that the computationally intensive MPC is invoked only when the LSTM approximation deviates beyond acceptable bounds. We rigorously established the near-optimal performance and closed-loop stability of our approach via Lyapunov analysis under mild assumptions, instilling confidence in its reliability. The simulation results on a three-arm manipulator, subject to low-frequency sinusoidal and high-frequency chirp trajectories, demonstrate that the proposed approach achieves up to 80–90% reduction in MPC calls, significantly improving the accuracy of the follow-up and computational efficiency. These findings highlight the potential of integrating learning-based approximations with conventional optimization-based control to achieve reliable and time-efficient performance in complex robotic manipulation tasks.http://www.sciencedirect.com/science/article/pii/S2590123025014446Bi-fidelity controlOptimal controlLSTM neural networksEvent-triggered controlRobotic manipulatorHybrid control systems |
| spellingShingle | Fawaz W. Alsaade Mohammed S. Al-zahrani Fuad E. Alsaadi Event-driven bi-fidelity control for efficient and reliable robotic manipulation Results in Engineering Bi-fidelity control Optimal control LSTM neural networks Event-triggered control Robotic manipulator Hybrid control systems |
| title | Event-driven bi-fidelity control for efficient and reliable robotic manipulation |
| title_full | Event-driven bi-fidelity control for efficient and reliable robotic manipulation |
| title_fullStr | Event-driven bi-fidelity control for efficient and reliable robotic manipulation |
| title_full_unstemmed | Event-driven bi-fidelity control for efficient and reliable robotic manipulation |
| title_short | Event-driven bi-fidelity control for efficient and reliable robotic manipulation |
| title_sort | event driven bi fidelity control for efficient and reliable robotic manipulation |
| topic | Bi-fidelity control Optimal control LSTM neural networks Event-triggered control Robotic manipulator Hybrid control systems |
| url | http://www.sciencedirect.com/science/article/pii/S2590123025014446 |
| work_keys_str_mv | AT fawazwalsaade eventdrivenbifidelitycontrolforefficientandreliableroboticmanipulation AT mohammedsalzahrani eventdrivenbifidelitycontrolforefficientandreliableroboticmanipulation AT fuadealsaadi eventdrivenbifidelitycontrolforefficientandreliableroboticmanipulation |