no code implementations • 14 Feb 2024 • Agnes Ngina Mwange, Dimas Maulana Rachman, Rin Suyama, Atsuo Maki
Autonomous ships are essentially designed and equipped to perceive their internal and external environment and subsequently perform appropriate actions depending on the predetermined objective(s) without human intervention.
no code implementations • 7 Dec 2023 • Rin Suyama, Rintaro Matsushita, Ryo Kakuta, Kouki Wakita, Atsuo Maki
The results show that, in all cases, the accuracy of the maneuvering simulation is improved by applying the tuned parameters to the MMG model, and the validity of the proposed parameter fine-tuning method is confirmed.
no code implementations • 25 Oct 2023 • Rin Suyama, Satoshi Satoh, Atsuo Maki
To derive this system, hyperbolic tangent ($\tanh$) function and auxiliary variables are introduced to deal with the input constraints.
no code implementations • 30 May 2023 • Kouki Wakita, Yoshiki Miyauchi, Youhei Akimoto, Atsuo Maki
In this paper, we improve the generalization performance of the dynamic model for the automatic berthing and unberthing controller by introducing data augmentation.
no code implementations • 28 Mar 2023 • Atsuhiro Miyagi, Yoshiki Miyauchi, Atsuo Maki, Kazuto Fukuchi, Jun Sakuma, Youhei Akimoto
In this study, we consider a continuous min--max optimization problem $\min_{x \in \mathbb{X} \max_{y \in \mathbb{Y}}}f(x, y)$ whose objective function is a black-box.
no code implementations • 19 Dec 2022 • Dimas M. Rachman, Yusuke Aoki, Yoshiki Miyauchi, Naoya Umeda, Atsuo Maki
It is designed upon an assumption that the forces due to the interaction between the rudders, the propeller, and the hull are linear with the rudder angles within a range around the hover rudder angle.
no code implementations • 13 Dec 2022 • Kouki Wakita, Youhei Akimoto, Dimas M. Rachman, Yoshiki Miyauchi, Umeda Naoya, Atsuo Maki
This paper proposes a training method based on reinforcement learning for a trajectory tracking controller that reduces the probability of collisions with static obstacles.
no code implementations • 22 Dec 2021 • Dimas M. Rachman, Atsuo Maki, Yoshiki Miyauchi, Naoya Umeda
This article demonstrates that the balance between the feasibility of the reference trajectory and the computational time can be achieved for an underactuated vessel in a disturbed and restricted environment.
no code implementations • 11 Nov 2021 • Yoshiki Miyauchi, Atsuo Maki, Naoya Umeda, Dimas M. Rachman, Youhei Akimoto
The main contributions of this study are as follows: (i) construct the system-based mathematical model on berthing by optimizing system parameters with a reduced amount of model tests than the CMT-based scheme; (ii) Find the favorable choice of objective function and type of training data for optimization.
no code implementations • 11 Nov 2021 • Kouki Wakita, Atsuo Maki, Umeda Naoya, Yoshiki Miyauchi, Tohga Shimoji, Dimas M. Rachman, Youhei Akimoto
A new system identification method for generating a low-speed maneuvering model using recurrent neural networks (RNNs) and free running model tests is proposed in this study.
no code implementations • 25 May 2021 • Youhei Akimoto, Yoshiki Miyauchi, Atsuo Maki
We propose an approach to saddle point optimization relying only on oracles that solve minimization problems approximately.