Optimized Trajectory Tracking for ROVs Using DNN + ENMPC Strategy DOI Creative Commons

Guanghao Yang,

Weidong Liu, Le Li

et al.

Journal of Marine Science and Engineering, Journal Year: 2024, Volume and Issue: 12(10), P. 1827 - 1827

Published: Oct. 13, 2024

This study introduces an innovative double closed-loop 3D trajectory tracking approach, integrating deep neural networks (DNN) with event-triggered nonlinear model predictive control (ENMPC), specifically designed for remotely operated vehicles (ROVs) under external disturbance conditions. In contrast to single-loop control, the proposed system operates in two distinct phases: (1) The outer loop controller uses a DNN replace LMPC controller, overcoming uncertainties kinematic while reducing computational burden. (2) inner velocity is using (NMPC) algorithm its stability proven. A + ENMPC method proposed, threshold-triggered mechanism into inner-loop NMPC reduce iterations sacrificing only small amount of performance. Finally, simulation results indicate that compared algorithm, can better track desired trajectory, thruster oscillations, and further minimize load.

Language: Английский

Advancements in Spacecraft Rendezvous: Leveraging Koopman Theory Over Clohessy-Wiltshire Equations DOI
George Nehma, Madhur Tiwari, Manasvi Lingam

et al.

AIAA SCITECH 2022 Forum, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 3, 2025

Language: Английский

Citations

1
Horizontal Plane Trajectory Tracking of Underwater Vehicle Based on Exponential Backstepping and Continuous Sliding Mode Control DOI
Dan Wang, Haolin Li,

Xiaozheng Jin

et al.

Lecture notes in networks and systems, Journal Year: 2025, Volume and Issue: unknown, P. 3 - 13

Published: Jan. 1, 2025

Language: Английский

Citations

0
Optimal DMD Koopman Data-Driven Control of a Worm Robot DOI Creative Commons
Mehran Rahmani, Sangram Redkar

Biomimetics, Journal Year: 2024, Volume and Issue: 9(11), P. 666 - 666

Published: Nov. 1, 2024

Bio-inspired robots are devices that mimic an animal's motions and structures in nature. Worm inspired by the movements of worm This robot has different applications such as medicine rescue plans. However, control is a challenging task due to high-nonlinearity dynamic model external noises applied robot. research uses optimal data-driven controller First, data obtained from nonlinear Then, Koopman theory used generate linear The mode decomposition (DMD) method operator. Finally, quadratic regulator (LQR) for simulation results verify performance proposed method.

Language: Английский

Citations

1
Deep neural data-driven Koopman fractional control of a worm robot DOI
Mehran Rahmani, Sangram Redkar

Expert Systems with Applications, Journal Year: 2024, Volume and Issue: 256, P. 124916 - 124916

Published: July 29, 2024

Language: Английский

Citations

0
Optimized Trajectory Tracking for ROVs Using DNN + ENMPC Strategy DOI Creative Commons

Guanghao Yang,

Weidong Liu, Le Li

et al.

Journal of Marine Science and Engineering, Journal Year: 2024, Volume and Issue: 12(10), P. 1827 - 1827

Published: Oct. 13, 2024

This study introduces an innovative double closed-loop 3D trajectory tracking approach, integrating deep neural networks (DNN) with event-triggered nonlinear model predictive control (ENMPC), specifically designed for remotely operated vehicles (ROVs) under external disturbance conditions. In contrast to single-loop control, the proposed system operates in two distinct phases: (1) The outer loop controller uses a DNN replace LMPC controller, overcoming uncertainties kinematic while reducing computational burden. (2) inner velocity is using (NMPC) algorithm its stability proven. A + ENMPC method proposed, threshold-triggered mechanism into inner-loop NMPC reduce iterations sacrificing only small amount of performance. Finally, simulation results indicate that compared algorithm, can better track desired trajectory, thruster oscillations, and further minimize load.

Language: Английский

Citations

0