Soft formation control for unmanned surface vehicles under environmental disturbance using multi-task reinforcement learning

Jin, Kefan; Wang, Jian; Wang, Jian; Liang, Xiaofeng; Guo, Yanan; Wang, Mianjin; Yang, Hong

doi:10.1016/j.oceaneng.2022.112035

Cited by 14 publications

(6 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A comprehensive training framework encompassing multiple tasks has been formulated for the management of formation control, tailored to the dynamic behavior of Unmanned Surface Vehicles and employing the leader-follower approach. Within this framework, the Soft Actor-Critic (SAC) reinforcement learning algorithm has been modified to facilitate the development of agent constructs [89].…”

Section: Extended Endurance and Resiliencementioning

confidence: 99%

A Bibliometric Analysis and Overall Review of the New Technology and Development of Unmanned Surface Vessels

Yang,

Xue,

2024

JMSE

View full text Add to dashboard Cite

With the significant role that Unmanned Surface Vessels (USVs) could play in industry, the military and the transformation of ocean engineering, a growing research interest in USVs is attracted to their innovation, new technology and automation. Yet, there has been no comprehensive review grounded in bibliometric analysis, which concentrates on the most recent technological advancements and developments in USVs. To provide deeper insight into the relevant research trends, this study employs a bibliometric analysis to examine the basic features of the literature from 2000 to 2023, and identifies the key research hotspots and modeling techniques by reviewing their current statuses and the recent efforts made in these areas. Based on the analysis of the temporal and spatial trends, disciplines and journals’ distribution, institutions, authors and citations, the publications relating to the new technology of USVs are assessed based on their keywords and the term analysis in the literature; six future research directions are proposed, including enhanced intelligence and autonomy, highly integrated sensor systems and multi-modal task execution, extended endurance and resilience, satellite communication and interconnectivity, eco-friendly and sustainable practices and safety and defense. The scientific literature is reviewed in a systematic way using a comparative analysis of existing tools, and the results greatly contribute to understanding the overall situation of new technology in USVs. This paper is enlightening to students, international scholars and institutions, as it can facilitate partnerships between industry and academia to allow for concerted efforts to be made in the domain of USVs.

show abstract

Section: Extended Endurance and Resiliencementioning

confidence: 99%

A Bibliometric Analysis and Overall Review of the New Technology and Development of Unmanned Surface Vessels

Yang,

Xue,

2024

JMSE

View full text Add to dashboard Cite

show abstract

“…Usually, the information will be gathered by the USV designated as the leader. The leader makes collision avoidance decisions and updates the formation based on global information, and sends these decisions and formation information to the members of the formation [4][5][6].…”

Section: Introductionmentioning

confidence: 99%

“…Many scholars have considered the effects of these interferences in the research of multiple-USV collaborative formations [12]. With the development of artificial intelligence, biomimetic optimization algorithms and artificial intelligence methods based on learning and gaming have made significant progress [4,[13][14][15]. As a type of ship, USVs must comply with maritime traffic regulations in practical applications.…”

Section: Introductionmentioning

confidence: 99%

A Formation Control and Obstacle Avoidance Method for Multiple Unmanned Surface Vehicles

Liu,

Wen,

Long

et al. 2023

JMSE

View full text Add to dashboard Cite

This study introduces a method for formation control and obstacle avoidance for multiple unmanned surface vehicles (USVs) by combining an artificial potential field with the virtual structure method. The approach involves a leader–follower formation structure, where the leader autonomously avoids collisions using an artificial potential field based on the target’s position as a reference. It also determines the ideal position of each follower in the formation based on its own position, heading angle, and the formation structure. To effectively avoid obstacles and maintain formation, the follower selects the position of the target or its ideal position as a reference during movement, depending on whether it is being repelled by obstacles. Additionally, this paper modifies the attractive force model of the traditional artificial potential field method to restrict the maximum magnitude of the attractive force when encountering repulsive forces, thus expediting departure from obstacle areas. The dynamic characteristics of USVs are taken into account by constraining the maximum linear speed and angular speed. Formation stability is ensured by maintaining a constant speed for the leader, while the linear speed of the follower varies based on the distance to the reference object during movement. Simulation experiments demonstrated that this method can effectively avoid obstacles and maintain formation.

show abstract

“…Huang developed a bounded-feedback adaptive law [8]. In reference [9], the trajectory communication systems and policy-sharing mechanisms were designed to improve the obstacle avoidance ability of USV with leaderfollower method. For the problem of significant tracking errors, Fu H. et al created the formation controller by applying the virtual leader strategy [10].An et al proposed a nonevent-triggered reference governor for adaptive adjustment of transient tracking errors [11].…”

mentioning

confidence: 99%

“…Pan et al propose a predefined-time adaptive neural control method for MASs that enables the followers to accurately track the desired trajectory with predefined time [17].However, in reference [5]- [8], the modelling scheme of the proposed controller is complicated with low computational efficiency. Moreover, in reference [9]- [14], the desired convergence velocity cannot be controlled during convergence.…”

mentioning

confidence: 99%

DAT-Based Formation Control With Different Scale Factor of Relative Information Measurement

Fu,

Wang,

Huang

et al. 2024

IEEE Access

View full text Add to dashboard Cite

This paper proposes an unmanned surface vehicles (USVs) formation control method based on distributed average tracking (DAT) with different relative information measurement scale factors. Firstly, the DAT algorithm is designed in the controller to control the time when the system reaches stability. Then, the relative position information of adjacent USVs is measured by installing distance sensors and direction sensors on each USV, and different scale factors are used to control the formation of USVs, and improve the stability and robustness of its control system. Finally, the effectiveness of the method proposed in this paper is verified by numerical simulation experiments. INDEX TERMS DAT, different scale factor, information measurement I. INTRODUCTION

show abstract

Soft formation control for unmanned surface vehicles under environmental disturbance using multi-task reinforcement learning

Cited by 14 publications

References 23 publications

A Bibliometric Analysis and Overall Review of the New Technology and Development of Unmanned Surface Vessels

A Bibliometric Analysis and Overall Review of the New Technology and Development of Unmanned Surface Vessels

A Formation Control and Obstacle Avoidance Method for Multiple Unmanned Surface Vehicles

DAT-Based Formation Control With Different Scale Factor of Relative Information Measurement

Contact Info

Product

Resources

About