Researching | UAV UV Information Collection Method Based on Deep Reinforcement Learning

Acta Photonica Sinica, Volume. 54, Issue 1, 0106003(2025)

UAV UV Information Collection Method Based on Deep Reinforcement Learning

Taifei ZHAO1...2,*, Jiahao GUO1, Yu XIN1 and Lu WANG1 |Show fewer author(s)

Author Affiliations

¹Institute of Automation and Information Engineering，Xi'an University of technology，Xi'an 710048，China

²Xian Key Laboratory of Wireless Optical Communication and Network Research，Xi'an 710048，China

show less

Abstract Get PDF(in Chinese)

Figures&Tables (13)

References (23)

Paper Information

Figures & Tables(13)

Fig. 1. UAV information collection diagram

Download full size

View in Article

Fig. 2. Geometric relationship between drone and ground sensor

Download full size

View in Article

Fig. 3. Schematic diagram of drone movement

Download full size

View in Article

Fig. 4. Improved DDQN algorithm framework

Download full size

View in Article

Fig. 5. Algorithm convergence analysis

Download full size

View in Article

Fig. 6. Trajectories of improved DDQN algorithm and DDQN algorithm with 20 ground sensors

Download full size

View in Article

Fig. 7. Effects of different UV T_X full beam angle on Information Collection time and energy consumption

Download full size

View in Article

Fig. 8. Effects of different UV RX FOV on information collection time and energy consumption

Download full size

View in Article

Fig. 9. Effect of different sensor quantities on information collection time and energy consumption

Download full size

View in Article

Fig. 10. Effect of different sensor data volumes on information collection time and energy consumption

Download full size

View in Article

Fig. 11. Effect of different UAV flight altitudes on information collection time and energy consumption

Download full size

View in Article

Table 1. Ultraviolet light communication parameters

View in Article

Table 1. Ultraviolet light communication parameters

Parameters	Value
UV wavelength $(λ)$	260 nm
Transmit power $(P_{t})$	200 mW
Atmospheric absorption coefficient $(K)$	0.9 $\times$ 10^-3 km^-1
Mie scattering coefficient $(K_{s}^{R a y})$	0.24 $\times$ 10^-3 km^-1
Rayleigh scattering coefficient $(K_{s}^{M i e})$	0.25 $\times$ 10^-3 km^-1
Filter transmittance $(η_{f})$	0.1
Detector quantum efficiency $(η_{r})$	0.2
Receiver aperture $(A_{r})$	0.25 $\times$ 10^-4 m²

Table 2. Deep reinforcement learning training parameters

View in Article

Table 2. Deep reinforcement learning training parameters

Parameters	Value
Learning Rate $(l r)$	0.000 1
Discount Factor $(γ)$	0.99
Batch size $(K)$	128
Maximum number of training rounds $(E)$	2 000
Number of hidden layers in neural network	3
Number of hidden layer neurons	512
Initial greedy exploration probability	0.8
Termination of greedy exploration probability	0.001
Soft update factor $(τ)$	0.01
Experience buffer capacity	50 000

Tools

Get Citation

Copy Citation Text

Taifei ZHAO, Jiahao GUO, Yu XIN, Lu WANG. UAV UV Information Collection Method Based on Deep Reinforcement Learning[J]. Acta Photonica Sinica, 2025, 54(1): 0106003

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Fiber Optics and Optical Communications

Received: Jul. 17, 2024

Accepted: Aug. 26, 2024

Published Online: Mar. 5, 2025

The Author Email: ZHAO Taifei (zhaotaifei@163.com)

DOI:10.3788/gzxb20255401.0106003

Topics

laser devices and laser physics

Lasers and Laser Optics

laser manufacturing

Instrumentation, Measurement and Metrology