Autonomous piloting and berthing based on Long Short Time Memory neural networks and nonlinear model predictive control algorithm

Wang, Shengzheng; Sun, Zhaoyang; Yuan, Qiumeng; Sun, Zhen; Wu, Zhizheng; Hsieh, Tsung-Hsuan

doi:10.1016/j.oceaneng.2022.112269

Cited by 22 publications

(7 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The improved cost function 𝐽 𝑖𝑚𝑝𝑟𝑜𝑣𝑒𝑑 (𝑘) consist of F (ρ 2 ,𝛥τ) (k) and J (φ,𝛥𝛿) (k), k is the current moment, N p is the number of predicted steps, 𝑁 𝑐 is the number of control steps, Q 1 , R 1 , Q φ , R φ are weight matrix. The constraint expression of the ship control quantity τ and 𝛿 and the constraint expression of the control increment 𝛥τ and 𝛥𝛿 , is shown in Equation (18). The goal of optimization is to find the optimal amount of control for each step, as shown in Equation (19).…”

Section: Improved Cost Functionmentioning

confidence: 99%

Ship Path Tracking with Real Disturbance and Exponential Cost Function

Zhang¹,

Li²,

Liu³

et al. 2023

Preprint

View full text Add to dashboard Cite

Section: Improved Cost Functionmentioning

confidence: 99%

Ship Path Tracking with Real Disturbance and Exponential Cost Function

Zhang¹,

Li²,

Liu³

et al. 2023

Preprint

View full text Add to dashboard Cite

“…The improved cost function 𝐽 (𝑘) consist of F , (k) and J ( , ) (k), k is the current moment, N is the number of predicted steps, 𝑁 is the number of control steps, Q ,R ,Q ,R are weight matrix. The constraint expression of the ship control quantity τ and 𝛿 and the constraint expression of the control increment 𝛥τ and 𝛥𝛿, is shown in Equation (18). The goal of optimization is to find the optimal amount of control for each step, as shown in Equation ( 19).…”

Section: ⎩ ⎪ ⎪ ⎨ ⎪ ⎪ ⎧ τ (𝑘) ≤τ(𝑘) ≤τ (𝑘) 𝛿 (𝑘) ≤𝛿(𝑘) ≤𝛿 (𝑘) 𝛥τ (𝑘) ≤...mentioning

confidence: 99%

Ship Path-Tracking with Real Disturbance and Exponential Cost Function

Zhang,

Li,

Luo

et al. 2023

Preprint

View full text Add to dashboard Cite

Intelligent ship technology is currently an international research hotspot, and model predictive control is widely used in the path-tracking control of intelligent vehicles. To construct an intelligent ship anti-disturbance path-tracking control method, firstly, an environmental disturbance model was constructed with the actual meteorological data of the target sea area. Secondly, the Fossen ship equation of motion is linearized and discretized as the ship motion model. Thirdly, the expression of the prediction equation is derived from the ship motion model. Fourthly, the cost function is constructed by using the polar diameter and polar angle values of the ship. Fifth, the power function in the cost function is replaced with an exponential function to obtain an improved cost function. Sixthly, according to the Lyapunov theory and the MPC terminal constraint theory, the stability of the improved cost function is verified. Seventh, different test paths are set up, the environmental disturbance model is taken as the external disturbance, the ship motion model, the prediction equation, and the improved cost function are used to design the anti-disturbance path-tracking control algorithm according to the model prediction control idea for simulation experiments. Finally, different MATLAB simulation results show that the improved cost function can resist disturbance of the external wave, current, and wind, and effectively track the target path. Therefore, this study provides a reference for improving the navigation safety of ship path-tracking.

show abstract

“…A multiple shooting algorithm [4] has been introduced to give the sub-optimal solution for the minimum-time optimization problem. An artificial neutral network (ANN) [5][6][7][8] has been proposed to learn how to navigate from the starting position to the berthing quay. The ANN was trained using the simulated data under different wind conditions.…”

Section: Introductionmentioning

confidence: 99%

Graph Search-Based Path Planning for Automatic Ship Berthing

Liu,

Hu,

Yang

et al. 2024

JMSE

View full text Add to dashboard Cite

Ship berthing is one of the most challenging operations for crews, involving optimal trajectory generation and intricate harbor maneuvering at low speed. In this paper, we present a practical path-planning method that generates smooth trajectories for an underactuated surface vehicle (USV) traveling in a confined harbor environment. Our approach introduces a Generalized Voronoi Diagram (GVD)-based path planner to handle the unberthing phase. The hybrid A* search-based path finding method is used for the transportation phase. A simple planner based on a Bézier curve is proposed for the berthing phase. To track the target path, an adaptive pure pursuit method and proportional-derivative (PD) controller is used. The performance of the given method is tested numerically and experimentally on a catamaran with a pair of non-steerable thrusters. The results demonstrate that the proposed algorithm can achieve a successful berthing operation through static obstacle handling and smooth trajectory generation.

show abstract

Autonomous piloting and berthing based on Long Short Time Memory neural networks and nonlinear model predictive control algorithm

Cited by 22 publications

References 25 publications

Ship Path Tracking with Real Disturbance and Exponential Cost Function

Ship Path Tracking with Real Disturbance and Exponential Cost Function

Ship Path-Tracking with Real Disturbance and Exponential Cost Function

Graph Search-Based Path Planning for Automatic Ship Berthing

Contact Info

Product

Resources

About