Cooperative multi-target hunting by unmanned surface vehicles based on multi-agent reinforcement learning

Xia, Jiawei; Luo, Yasong; Liu, Zhikun; Zhang, Yalun; Shi, Haoran; Liu, Zhong

doi:10.1016/j.dt.2022.09.014

Cited by 26 publications

(11 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this case, the communication burden will increase. The solution of Equation (1) can be described as following form (6).…”

Section: Dynamic Event-triggered Mechanismmentioning

confidence: 99%

“…Based on the characteristic of the leader and Equation ( 6), we can easily obtain the state of the leader at any moment by using (6). Then, an estimator can be established in the neighboring followers of leader.…”

Section: Dynamic Event-triggered Mechanismmentioning

confidence: 99%

“…In recent years, MASs have become a hot topic because of their widespread application in different areas, 1–3 such as manufacturing systems, 4 traffic and transportation systems, 5 deep reinforcement learning (RL), 6 and so on. Consensus, as the most fundamental problem of MASs, has drawn numerous scholars 7–10 .…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Dynamic event‐triggered control for the leader‐following consensus of multi‐agent systems with input time delay

Pu,

Hou,

2024

Adaptive Control & Signal

View full text Add to dashboard Cite

SummaryIn this article, the leader‐following consensus of a kind of linear homogeneous MASs (multi‐agent systems) with input time delay is investigated. To realize leader‐following consensus, a novel distributive input control protocol based on dynamic event‐triggered mechanism is proposed. In this novel protocol, internal dynamic variables are employed to reduce the burden of communication and exclude the Zeno phenomenon. By utilizing the graph algebra, stability analysis and Lyapunov theory, some sufficient conditions have been obtained for the consensus of this MASs. The effectiveness of our approach is illustrated by some simulation examples. Compared with the given achievements, the obtained results have better ability in accelerating convergence rate and reducing the burden of communication.

show abstract

“…In this case, the communication burden will increase. The solution of Equation (1) can be described as following form (6).…”

Section: Dynamic Event-triggered Mechanismmentioning

confidence: 99%

Section: Dynamic Event-triggered Mechanismmentioning

confidence: 99%

See 1 more Smart Citation

Dynamic event‐triggered control for the leader‐following consensus of multi‐agent systems with input time delay

Pu,

Hou,

2024

Adaptive Control & Signal

View full text Add to dashboard Cite

show abstract

“…The authors implement the proposed technique on multiple simulated search environments including offices and museums, as well as on real robots. Another study in a similar application domain is done by Xia et al [ 127 ]. Specifically, the authors have used MADRL for the multi-agent multi-target hunting problem.…”

Section: Multi-robot System Applications Of Multi-agent Deep Reinforc...mentioning

confidence: 99%

Multi-Agent Deep Reinforcement Learning for Multi-Robot Applications: A Survey

Orr

Dutta

2023

Sensors

View full text Add to dashboard Cite

Deep reinforcement learning has produced many success stories in recent years. Some example fields in which these successes have taken place include mathematics, games, health care, and robotics. In this paper, we are especially interested in multi-agent deep reinforcement learning, where multiple agents present in the environment not only learn from their own experiences but also from each other and its applications in multi-robot systems. In many real-world scenarios, one robot might not be enough to complete the given task on its own, and, therefore, we might need to deploy multiple robots who work together towards a common global objective of finishing the task. Although multi-agent deep reinforcement learning and its applications in multi-robot systems are of tremendous significance from theoretical and applied standpoints, the latest survey in this domain dates to 2004 albeit for traditional learning applications as deep reinforcement learning was not invented. We classify the reviewed papers in our survey primarily based on their multi-robot applications. Our survey also discusses a few challenges that the current research in this domain faces and provides a potential list of future applications involving multi-robot systems that can benefit from advances in multi-agent deep reinforcement learning.

show abstract

“…However, it lacks in-depth discussion on the issue of tracking task allocation, which may hinder maneuverability in the process of multi-target tracking. Regarding the collaborative multi-target pursuit of unmanned surface vehicles (USVs), Xia et al [21] modeled the collaborative hunting problem of USV fleets as a decentralized, partially observable Markov decision process. They proposed a distributed partially observable multi-target hunting proximal strategy optimization algorithm suitable for USVs.…”

Section: Introductionmentioning

confidence: 99%

Dynamic Multi-Target Self-Organization Hunting Control of Multi-Agent Systems

He,

Wang,

Liu

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

In this paper, we present a novel coordinated method tailored to address the dynamic multi-target hunting control problem in multi-agent systems, offering significant practical value. Our approach encompasses several key components: initially, we introduce a task allocation model that integrates a fuzzy inference system with a particle swarm optimization algorithm. This hybrid model efficiently allocates hunting tasks for scattered evading targets, effectively transforming the dynamic multi-target hunting problem into multiple dynamic single-target-hunting problems. This transformation enhances the speed and efficacy of task allocation. Subsequently, we propose an attraction/repulsive model grounded in potential field theory. This model facilitates the coordinated hunting of each target by organizing agents into subgroups. Relying solely on relative position and velocity information between agents and targets, our model simplifies computation, while maintaining effectiveness. Furthermore, the coordination of hunting activities for each target is achieved through a series of agent subgroups, guided by our proposed motion model. This systematic approach ensures a cohesive and efficient hunting strategy. Finally, we validate the effectiveness and feasibility of our proposed method through simulation results. These results provide empirical evidence of the method’s efficacy and potential applicability in real-world scenarios.

show abstract

Cooperative multi-target hunting by unmanned surface vehicles based on multi-agent reinforcement learning

Cited by 26 publications

References 14 publications

Dynamic event‐triggered control for the leader‐following consensus of multi‐agent systems with input time delay

Dynamic event‐triggered control for the leader‐following consensus of multi‐agent systems with input time delay

Multi-Agent Deep Reinforcement Learning for Multi-Robot Applications: A Survey

Dynamic Multi-Target Self-Organization Hunting Control of Multi-Agent Systems

Contact Info

Product

Resources

About