Event-driven bi-fidelity control for efficient and reliable robotic manipulation

• Published in: Results in engineering Vol. 26; p. 105374
• Main Authors: Alsaade, Fawaz W., Al-zahrani, Mohammed S., Alsaadi, Fuad E.
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.06.2025; Elsevier
• Subjects: Bi-fidelity control; Event-triggered control; Hybrid control systems; LSTM neural networks; Optimal control; Robotic manipulator; LSTM neural networks; Hybrid control systems; Robotic manipulator; Event-triggered control; Bi-fidelity control; Optimal control
• ISSN: 2590-1230; 2590-1230
• DOI: 10.1016/j.rineng.2025.105374

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. •Introduced a bi-fidelity control strategy combining high-fidelity MPC and low-fidelity LSTM for robotic manipulation.•Event-triggered mechanism selects the controller based on real-time tracking error, reducing MPC computations.•Theoretical stability guarantees ensure system safety and convergence to the desired state under mild assumptions.•Tested on a 3-DOF robotic manipulator, achieving accurate tracking on both slow (sinusoidal) and fast (chirp) paths.•Achieved up to 90% reduction in MPC calls, with RMSE improvement of up to 52% and lower integrated torque.