A UAV Path Planning Algorithm Based on GRU and DDPG

Lvyuan Wu; Haolei Huang; Da Xu; Yang Liu; Zheng Zheng; Hongwei Zhang

doi:10.1109/DDCLS66240.2025.11065254

A UAV Path Planning Algorithm Based on GRU and DDPG

Lvyuan Wu^*
, Haolei Huang
, Da Xu
, Yang Liu
, Zheng Zheng
, Hongwei Zhang

^*Corresponding author for this work

School of Automation Science and Electrical Engineering

Beihang University
Xi'an Polytechnic University
Beijing Jiaotong University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The stability of UAV path planning algorithms is crucial for ensuring efficient task completion. In response to the issue of poor training stability in deep reinforcement learning algorithms for UAV path planning tasks in high-dimensional and complex spaces, this paper proposes a UAV path planning algorithm combining GRU and DDPG. First, the UAV action space is designed based on the concept of Artificial Potential Fields (APF). Second, GRU is incorporated to endow the DDPG network with memory capability, enabling it to make decisions based on previous states. Additionally, a new reward mechanism is proposed to address the problem of sparse rewards in traditional algorithms, which leads to poor planning performance. Finally, the effectiveness of the proposed method is validated through simulation experiments. The results demonstrate that the proposed algorithm significantly enhances the convergence and stability of the learning process and improves the performance of path planning.

Original language	English
Title of host publication	Proceedings of 2025 IEEE 14th Data Driven Control and Learning Systems Conference, DDCLS 2025
Editors	Mingxuan Sun, Ronghu Chi
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1270-1275
Number of pages	6
ISBN (Electronic)	9798350357318
DOIs	https://doi.org/10.1109/DDCLS66240.2025.11065254
State	Published - 2025
Event	14th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2025 - Wuxi, China Duration: 9 May 2025 → 11 May 2025

Publication series

Name	Proceedings of 2025 IEEE 14th Data Driven Control and Learning Systems Conference, DDCLS 2025

Conference

Conference	14th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2025
Country/Territory	China
City	Wuxi
Period	9/05/25 → 11/05/25

Keywords

DDPG
Deep reinforcement learning
Path planning
Unmanned aerial vehicle

Access to Document

10.1109/DDCLS66240.2025.11065254

Cite this

Wu, L., Huang, H., Xu, D., Liu, Y., Zheng, Z., & Zhang, H. (2025). A UAV Path Planning Algorithm Based on GRU and DDPG. In M. Sun, & R. Chi (Eds.), Proceedings of 2025 IEEE 14th Data Driven Control and Learning Systems Conference, DDCLS 2025 (pp. 1270-1275). (Proceedings of 2025 IEEE 14th Data Driven Control and Learning Systems Conference, DDCLS 2025). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/DDCLS66240.2025.11065254

Wu, Lvyuan ; Huang, Haolei ; Xu, Da et al. / A UAV Path Planning Algorithm Based on GRU and DDPG. Proceedings of 2025 IEEE 14th Data Driven Control and Learning Systems Conference, DDCLS 2025. editor / Mingxuan Sun ; Ronghu Chi. Institute of Electrical and Electronics Engineers Inc., 2025. pp. 1270-1275 (Proceedings of 2025 IEEE 14th Data Driven Control and Learning Systems Conference, DDCLS 2025).

@inproceedings{ee76ba5042064018880d12361f50bbbb,

title = "A UAV Path Planning Algorithm Based on GRU and DDPG",

abstract = "The stability of UAV path planning algorithms is crucial for ensuring efficient task completion. In response to the issue of poor training stability in deep reinforcement learning algorithms for UAV path planning tasks in high-dimensional and complex spaces, this paper proposes a UAV path planning algorithm combining GRU and DDPG. First, the UAV action space is designed based on the concept of Artificial Potential Fields (APF). Second, GRU is incorporated to endow the DDPG network with memory capability, enabling it to make decisions based on previous states. Additionally, a new reward mechanism is proposed to address the problem of sparse rewards in traditional algorithms, which leads to poor planning performance. Finally, the effectiveness of the proposed method is validated through simulation experiments. The results demonstrate that the proposed algorithm significantly enhances the convergence and stability of the learning process and improves the performance of path planning.",

keywords = "DDPG, Deep reinforcement learning, Path planning, Unmanned aerial vehicle",

author = "Lvyuan Wu and Haolei Huang and Da Xu and Yang Liu and Zheng Zheng and Hongwei Zhang",

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 14th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2025 ; Conference date: 09-05-2025 Through 11-05-2025",

year = "2025",

doi = "10.1109/DDCLS66240.2025.11065254",

language = "英语",

series = "Proceedings of 2025 IEEE 14th Data Driven Control and Learning Systems Conference, DDCLS 2025",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1270--1275",

editor = "Mingxuan Sun and Ronghu Chi",

booktitle = "Proceedings of 2025 IEEE 14th Data Driven Control and Learning Systems Conference, DDCLS 2025",

address = "美国",

}

Wu, L, Huang, H, Xu, D, Liu, Y, Zheng, Z & Zhang, H 2025, A UAV Path Planning Algorithm Based on GRU and DDPG. in M Sun & R Chi (eds), Proceedings of 2025 IEEE 14th Data Driven Control and Learning Systems Conference, DDCLS 2025. Proceedings of 2025 IEEE 14th Data Driven Control and Learning Systems Conference, DDCLS 2025, Institute of Electrical and Electronics Engineers Inc., pp. 1270-1275, 14th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2025, Wuxi, China, 9/05/25. https://doi.org/10.1109/DDCLS66240.2025.11065254

A UAV Path Planning Algorithm Based on GRU and DDPG. / Wu, Lvyuan; Huang, Haolei; Xu, Da et al.
Proceedings of 2025 IEEE 14th Data Driven Control and Learning Systems Conference, DDCLS 2025. ed. / Mingxuan Sun; Ronghu Chi. Institute of Electrical and Electronics Engineers Inc., 2025. p. 1270-1275 (Proceedings of 2025 IEEE 14th Data Driven Control and Learning Systems Conference, DDCLS 2025).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A UAV Path Planning Algorithm Based on GRU and DDPG

AU - Wu, Lvyuan

AU - Huang, Haolei

AU - Xu, Da

AU - Liu, Yang

AU - Zheng, Zheng

AU - Zhang, Hongwei

PY - 2025

Y1 - 2025

N2 - The stability of UAV path planning algorithms is crucial for ensuring efficient task completion. In response to the issue of poor training stability in deep reinforcement learning algorithms for UAV path planning tasks in high-dimensional and complex spaces, this paper proposes a UAV path planning algorithm combining GRU and DDPG. First, the UAV action space is designed based on the concept of Artificial Potential Fields (APF). Second, GRU is incorporated to endow the DDPG network with memory capability, enabling it to make decisions based on previous states. Additionally, a new reward mechanism is proposed to address the problem of sparse rewards in traditional algorithms, which leads to poor planning performance. Finally, the effectiveness of the proposed method is validated through simulation experiments. The results demonstrate that the proposed algorithm significantly enhances the convergence and stability of the learning process and improves the performance of path planning.

AB - The stability of UAV path planning algorithms is crucial for ensuring efficient task completion. In response to the issue of poor training stability in deep reinforcement learning algorithms for UAV path planning tasks in high-dimensional and complex spaces, this paper proposes a UAV path planning algorithm combining GRU and DDPG. First, the UAV action space is designed based on the concept of Artificial Potential Fields (APF). Second, GRU is incorporated to endow the DDPG network with memory capability, enabling it to make decisions based on previous states. Additionally, a new reward mechanism is proposed to address the problem of sparse rewards in traditional algorithms, which leads to poor planning performance. Finally, the effectiveness of the proposed method is validated through simulation experiments. The results demonstrate that the proposed algorithm significantly enhances the convergence and stability of the learning process and improves the performance of path planning.

KW - DDPG

KW - Deep reinforcement learning

KW - Path planning

KW - Unmanned aerial vehicle

UR - https://www.scopus.com/pages/publications/105011816235

U2 - 10.1109/DDCLS66240.2025.11065254

DO - 10.1109/DDCLS66240.2025.11065254

M3 - 会议稿件

AN - SCOPUS:105011816235

T3 - Proceedings of 2025 IEEE 14th Data Driven Control and Learning Systems Conference, DDCLS 2025

SP - 1270

EP - 1275

BT - Proceedings of 2025 IEEE 14th Data Driven Control and Learning Systems Conference, DDCLS 2025

A2 - Sun, Mingxuan

A2 - Chi, Ronghu

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 14th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2025

Y2 - 9 May 2025 through 11 May 2025

ER -

Wu L, Huang H, Xu D, Liu Y, Zheng Z, Zhang H. A UAV Path Planning Algorithm Based on GRU and DDPG. In Sun M, Chi R, editors, Proceedings of 2025 IEEE 14th Data Driven Control and Learning Systems Conference, DDCLS 2025. Institute of Electrical and Electronics Engineers Inc. 2025. p. 1270-1275. (Proceedings of 2025 IEEE 14th Data Driven Control and Learning Systems Conference, DDCLS 2025). doi: 10.1109/DDCLS66240.2025.11065254

A UAV Path Planning Algorithm Based on GRU and DDPG

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this