Identification and Prediction of Ship Maneuvering Motion Based on a Gaussian Process with Uncertainty Propagation

Abstract

Maritime transport plays a vital role in economic development. To establish a vessel scheduling model, accurate ship maneuvering models should be used to optimize the strategy and maximize the economic benefits. The use of nonparametric modeling techniques to identify ship maneuvering systems has attracted considerable attention. The Gaussian process has high precision and strong generalization ability in fitting nonlinear functions and requires less training data, which is suitable for ship dynamic model identification. Compared with other machine learning methods, the most obvious advantage of the Gaussian process is that it can provide the uncertainty of prediction. However, most studies on ship modeling and prediction do not consider the uncertainty propagation in Gaussian processes. In this paper, a moment-matching-based approach is applied to address the problem. The proposed identification scheme for ship maneuvering systems is verified by container ship simulation data and experimental data from the Workshop on Verification and Validation of Ship Maneuvering Simulation Methods (SIMMAN) database. The results indicate that the identified model is accurate and shows good generalization performance. The uncertainty of ship motion prediction is well considered based on the uncertainty propagation technology.

System identification of Vessel Manoeuvring Models

“…The system identification can be applied on full scale data (Åström and Källström, 1976;Perera et al, 2015;Revestido Herrero and Velasco González, 2012) which has the highest uncertainty, both in terms of model uncertainty and measurement uncertainty which is therefore the hardest task, but also the most relevant. The uncertainty can be reduced by instead using model test data as in Araki et al (2012), He et al (2022), Xue et al (2021), Miller (2021) and Luo et al (2016). The uncertainty can be further reduced by using simulated data as in Shi et al (2009), Zhu et al (2017), Wang et al (2021) Luo et al (2016) the potential of new methods with the benefit that the true model is known, but one also has to remember that the objective is to identify real objects, not its mathematical model (Miller, 2021).…”

“…The uncertainty can be further reduced by using simulated data as in Shi et al (2009), Zhu et al (2017), Wang et al (2021) Luo et al (2016) the potential of new methods with the benefit that the true model is known, but one also has to remember that the objective is to identify real objects, not its mathematical model (Miller, 2021). Black-box modeling was used in He et al (2022), using neural network, and in Xue et al (2021), using gaussian process. The nonparametric models are related, where the system structure is known but no parameters are required as seen in Pongduang et al (2020).…”

Experimental Validation of Ellipsoidal Techniques for State Estimation in Marine Applications

“…Model uncertainty and external disturbances are omnipresent when tasks such as trajectory tracking control or the localization of vessels in marine applications are considered [1,2]. This equally holds for surface vessels operated on rivers or the open sea in the areas of passenger and goods transportation, as well as for autonomous (underwater) robots performing tasks such as the inspection and maintenance of pipelines or other offshore infrastructure, such as wind turbines.…”

Maritime Autonomous Vessels

“…The main goal of this book is to address key challenges, thereby promoting research on marine autonomous ships. There are many topics on autonomous vessels involved in this book, for instance, automatic control [1][2][3][4], manoeuvrability [5][6][7][8], collision avoidance [9][10][11], ship target identification [12][13][14][15], motion planning [16], and buckling analysis [17].…”

“…The results of this study can help in conducting simulations and also provide unique parameters of fishing vessels that lead to the development of autonomous vessels. Nonparametric modelling techniques to predict ship manoeuvrability using Gaussian processes were proposed in [8], the Ship Maneuvering Simulation Methods database was used for the validation, and the results indicate that the identified model is accurate and shows good generalization performance.…”