Application of Recent Developments in Deep Learning to ANN-based Automatic Berthing Systems

Abstract

Previous studies on Artificial Neural Network (ANN)-based automatic berthing showed considerable increases in performance by training ANNs with a set of berthing datasets. However, the berthing performance deteriorated when an extrapolated initial position was given. To overcome the extrapolation problem and improve the training performance, recent developments in Deep Learning (DL) are adopted in this paper. Recent activation functions, weight initialization methods, input data-scaling methods, a higher number of hidden layers, and Batch Normalization (BN) are considered, and their effectiveness has been analyzed based on loss functions, berthing performance histories, and berthing trajectories. Finally, it is shown that the use of recent activation and weight initialization method results in faster training convergence and a higher number of hidden layers. This leads to a better berthing performance over the training dataset. It is found that application of the BN can overcome the extrapolated initial position problem.

Investigation of a Multitasking System for Automatic Ship Berthing in Marine Practice Based on an Integrated Neural Controller

“…Generally, the ship states (Ψ REL(t) d 1(t) , v t , r t , u t , D t , d 2(t) ) are used to find out the rudder angle (δ t+1 ) and revolution speed (rps t+1 ) in next time by Equation (15). Besides that, Equation (15) can be rewritten in the following form…”

“…Meanwhile, an efficient neural network approach with feature selection and a genetic algorithm was proposed by Shuai et al (2019) [14] for ship docking. In addition, a deep learning algorithm was applied for automatic ship berthing by Lee et al (2019) [15].…”

Deep learning algorithm evaluation of hypertension classification in less photoplethysmography signals conditions

“…The less data condition is not suitable for deep learning algorithm, how to find the optimal parameters of the models and the precision data format might be the important issues in the future. 11 The other research with deep learning method is also presented, 12 for example an application-based online and offline traffic classification. The remainder of this paper is organized as follows.…”

Optimization-Based Automatic Docking and Berthing of ASVs Using Exteroceptive Sensors: Theory and Experiments

“…For these approaches, an ANN is used as a function approximator for the policy, and is tasked with learning to imitate pre-recorded docking trajectories, and hence learning how to perform the docking maneuvers. More recent learning-based methods have expanded on this by using advances in Deep Learning (DL) [16]- [18]. Additional approaches include docking using a rule-based expert system [19], docking by target tracking [20], and docking using artificial potential fields [21].…”