Deep Reinforcement Learning Based Three-Dimensional Area Coverage With UAV Swarm

Mou, Zhiyu; Zhang, Yu; Gao, Feifei; Wang, Huangang; Zhang, Tao; Han, Zhu

doi:10.1109/jsac.2021.3088718

Cited by 51 publications

(21 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We construct USNETs obeying IFSs f 1 to f 7 , respectively, and compare the clustering performance between the metric learning 4 and other traditional clustering algorithms, in-4. The GRU network is initialized with meta parameters.…”

Section: On-line Metric Learning Of the Gru Networkmentioning

confidence: 99%

“…U NMANNED aerial vehicle (UAV) swarm network (US-NET) composed of several hierarchical UAV clusters usually has structural advantages over flat UAV swarms in many aspects, including collective management, communication efficiency, and labor divisions [1]. As a result, USNET has become a critical technology to a broad of UAV-aided scenarios, such as data collections [2], [3], area coverage [4] and securities [5]. Generating behaviors of UAVs is an important part in the USNET technique and has been investigated in many literatures.…”

Section: Introductionmentioning

confidence: 99%

“…Generating behaviors of UAVs is an important part in the USNET technique and has been investigated in many literatures. For example, the authors in [2], [4], [6], [7], [8] have studied the trajectory planning algorithms of USNET exhaustively in various scenes, while [9], [10], [11] and [12], [13] have proposed efficient methods on data transmissions and charging schedules for the USNET, respectively. Note that apart from the UAVs themselves, there usually exists another side of agents in practical applications of the USNET technique that respond to the behaviors of UAVs, such like ground users, clients or defenders [14].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Cluster Head Detection for Hierarchical UAV Swarm With Graph Self-supervised Learning

Mou¹,

Li²,

Xiang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

In this paper, we study the cluster head detection problem of a two-level unmanned aerial vehicle (UAV) swarm network (USNET) with multiple UAV clusters, where the inherent follow strategy (IFS) of low-level follower UAVs (FUAVs) with respect to high-level cluster head UAVs (HUAVs) is unknown. We first propose a graph attention self-supervised learning algorithm (GASSL) to detect the HUAVs of a single UAV cluster, where the GASSL can fit the IFS at the same time. Then, to detect the HUAVs in the USNET with multiple UAV clusters, we develop a multi-cluster graph attention self-supervised learning algorithm (MC-GASSL) based on the GASSL. The MC-GASSL clusters the USNET with a gated recurrent unit (GRU)-based metric learning scheme and finds the HUAVs in each cluster with GASSL. Numerical results show that the GASSL can detect the HUAVs in single UAV clusters obeying various kinds of IFSs with over 98% average accuracy. The simulation results also show that the clustering purity of the USNET with MC-GASSL exceeds that with traditional clustering algorithms by at least 10% average. Furthermore, the MC-GASSL can efficiently detect all the HUAVs in USNETs with various IFSs and cluster numbers with low detection redundancies.

show abstract

Section: On-line Metric Learning Of the Gru Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cluster Head Detection for Hierarchical UAV Swarm With Graph Self-supervised Learning

Mou¹,

Li²,

Xiang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The authors of Ref. [47] proposed a two‐level UAV swarm structure and a reinforcement learning algorithm based on group deep Q network (DQN) to reduce redundant coverage.…”

Section: Introductionmentioning

confidence: 99%

“…The authors of Ref. [46] use DRL algorithm to increase the machine score more and can well solve the input problem in the case of high di-mension. The authors of Ref.…”

Section: Introductionmentioning

confidence: 99%

Trajectory Optimization and Power Allocation Scheme Based on DRL in Energy Efficient UAV‐Aided Communication Networks

WANG

Cui

Deng

et al. 2022

Chinese J of Electronics

View full text Add to dashboard Cite

With flexibility, convenience and mobility, unmanned aerial vehicles (UAVS) can provide wireless communication networks with lower costs, easier deployment, higher network scalability and larger coverage. This paper proposes the deep deterministic policy gradient algorithm to jointly optimize the power allocation and flight trajectory of UAV with constrained effective energy to maximize the downlink throughput to ground users. To validate the proposed algorithm, we compare with the random algorithm, Q-learning algorithm and deep Q network algorithm. The simulation results show that the proposed algorithm can effectively improve the communication quality and significantly extend the service time of UAV. In addition, the downlink throughput increases with the number of ground users.

show abstract

A multi‐UAV system for coverage path planning applications with in‐flight re‐planning capabilities

Luna,

Molina,

Da‐Silva‐Gomez

et al. 2024

Journal of Field Robotics

View full text Add to dashboard Cite

This paper presents the development and implementation of a multiple unmanned aerial vehicle system focused on coverage path planning on multiple separated areas capable of re‐planning the collective mission in case of unexpected events. For this purpose, we present a distributed‐centralized architecture that uses heuristic and computationally efficient methods to perform the planning/re‐planning and decision‐making tasks during the control of the mission execution. We performed a computational evaluation of the algorithms, comparing them with other proposals, together with experiments in simulated and real flights. The results show that the system can distribute tasks equitably among the aircraft in an efficient way, even in the middle of the flight, when facing unexpected events; and show a higher computational efficiency when compared to multiple proposals in the state of the art.

show abstract

Deep Reinforcement Learning Based Three-Dimensional Area Coverage With UAV Swarm

Cited by 51 publications

References 38 publications

Cluster Head Detection for Hierarchical UAV Swarm With Graph Self-supervised Learning

Cluster Head Detection for Hierarchical UAV Swarm With Graph Self-supervised Learning

Trajectory Optimization and Power Allocation Scheme Based on DRL in Energy Efficient UAV‐Aided Communication Networks

A multi‐UAV system for coverage path planning applications with in‐flight re‐planning capabilities

Contact Info

Product

Resources

About