A Data-Driven Packet Routing Algorithm for an Unmanned Aerial Vehicle Swarm: A Multi-Agent Reinforcement Learning Approach

Qiu, Xiulin; Xu, Lei; Wang, Ping; Yang, Yuwang; Liao, Zhenqiang

doi:10.1109/lwc.2022.3195963

Cited by 18 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The complexity is greatly reduced compared to the high complexity of centralized routing algorithms facing large-scale networks. Similarly, Qiu et al [102] continue to adapt multi-intelligent reinforcement learning to the complex and variable FANET environment by using LSTMs instead of the fully connected layers of actor-critic networks. The algorithm starts with an LSTM-based behavioral network that performs an output operation based on the current state, followed by an intelligent body that operates, receives a reward and evolves to a new state, and finally updates the parameters of the judging network using a loss function and updates the parameters of the behavioral network using a gradient ascent algorithm.…”

Section: Environment Agentmentioning

confidence: 99%

UAV Ad Hoc Network Routing Algorithms in Space–Air–Ground Integrated Networks: Challenges and Directions

Zhang

Igorevich

et al. 2023

Drones

View full text Add to dashboard Cite

With the rapid development of 5G and 6G communications in recent years, there has been significant interest in space–air–ground integrated networks (SAGINs), which aim to achieve seamless all-area, all-time coverage. As a key component of SAGINs, flying ad hoc networks (FANETs) have been widely used in the agriculture and transportation sectors in recent years. Reliable communication in SAGINs requires efficient routing algorithms to support them. In this study, we analyze the unique communication architecture of FANETs in SAGINs. At the same time, existing routing protocols are presented and clustered. In addition, we review the latest research advances in routing algorithms over the last five years. Finally, we clarify the future research trends of FANET routing algorithms in SAGINs by discussing the algorithms and comparing the routing experiments with the characteristics of unmanned aerial vehicles.

show abstract

Section: Environment Agentmentioning

confidence: 99%

UAV Ad Hoc Network Routing Algorithms in Space–Air–Ground Integrated Networks: Challenges and Directions

Zhang

Igorevich

et al. 2023

Drones

View full text Add to dashboard Cite

show abstract

“…However, the existing UAVs are inadequately intelligent for performing difficult activities, and still major of them require people's real-time control [3]. A single UAV could only execute moderately easy tasks, nonetheless, the UAV set could effectively perform several laborious and complex tasks after acceptable task planning [4]. The task distribution issue is identical to the combinatorial optimizer decision issue for many UAVs.…”

mentioning

confidence: 99%

Design of Hybrid Snake Optimizer Based Route Selection Approach for Unmanned Aerial Vehicles Communication

Alkahtani,

Mahgoub,

Alotaibi

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The effective usage of energy becomes crucial for the successful deployment and operation of unmanned aerial vehicles (UAVs) in different applications, such as surveillance, transportation, and communication networks. The increasing demand for UAVs in different industries such as agriculture, logistics, and emergency response has led to the development of more sophisticated and advanced UAVs. However, the limited onboard energy resource of UAVs poses a major problem for their long-term operation and endurance. In addition, artificial intelligence (AI) and machine learning (ML) could allow UAVs to make more informed and intelligent decisions regarding their operations, resulting in sustainable and more energyefficient UAV deployment. This article designs a Hybrid Snake Optimizer-based Route Selection Approach for Unmanned Aerial Vehicles Communication (HSO-RSAUAVC) technique. The goal of the HSO-RSAUAVC technique is to explore and select optimal routes for UAV communication. In the presented HSO-RSAUAVC technique, the SO algorithm is integrated with Bernoulli Chaotic Mapping and Levy flight (LF) for enhanced performance. In addition, the HSO-RSAUAVC method derives a fitness function including residual energy (RE), distance, and UAV degree. By incorporating the HSO-RSAUAVC technique, we can dynamically adapt UAV paths to overcome obstacles, decrease communication interference, and optimize energy utilization. To validate the performance of the proposed model, a series of simulations were performed. The comparative result analysis illustrates the better performance of the HSO-RSAUAVC technique in improving the performance and reliability of UAV communication.INDEX TERMS Unmanned aerial vehicles; Routing; Snake optimizer; Energy efficiency; Fitness function I. INTRODUCTIONRecently, with the fast growth of unmanned aerial vehicle (UAV) technology, UAVs have been extensively utilized in numerous domains [1]. Various kinds of UAVs can support people to accomplish some comparatively risky, impossible, and urgent tasks, like map reconstruction, ocean exploration, environmental analysis, aerial photography, and material distribution [2]. However, the existing UAVs are inadequately intelligent for performing difficult activities, and still major of them require people's real-time control [3]. A single UAV could only execute moderately easy tasks, nonetheless, the UAV set could effectively perform several laborious and complex tasks after acceptable task planning [4]. The task distribution issue is identical to the combinatorial optimizer decision issue for many UAVs. It is an integration method developed to satisfy UAV efficiency and limitations. The

show abstract

Fixed‐time formation control of second‐order nonlinear multi‐agent systems using the neural network dynamic sliding mode

Luo,

Huang,

Cao

et al. 2024

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

The problem of fixed‐time formation control for a class of second‐order nonlinear multi‐agent systems is studied. For a class of such systems, a control algorithm is proposed to maintain the connections among the agents while avoiding collisions. Furthermore, a radial basis function neural network is used in the design to precisely approximate the nonlinear function for the nonlinear terms in the model. Then, a dynamic sliding mode control method is proposed to suppress the chattering phenomenon that may arise due to the sliding mode control. A sufficient condition for the system to achieve fixed‐time formation is obtained by using different methods, such as Lyapunov stability. Finally, the effectiveness of the proposed algorithm is verified by example. Simulation experiments reveal that the proposed method has faster error convergence and better robust control than conventional algorithms.

show abstract

A Data-Driven Packet Routing Algorithm for an Unmanned Aerial Vehicle Swarm: A Multi-Agent Reinforcement Learning Approach

Cited by 18 publications

References 9 publications

UAV Ad Hoc Network Routing Algorithms in Space–Air–Ground Integrated Networks: Challenges and Directions

UAV Ad Hoc Network Routing Algorithms in Space–Air–Ground Integrated Networks: Challenges and Directions

Design of Hybrid Snake Optimizer Based Route Selection Approach for Unmanned Aerial Vehicles Communication

Fixed‐time formation control of second‐order nonlinear multi‐agent systems using the neural network dynamic sliding mode

Contact Info

Product

Resources

About