Control-Oriented Real-Time Trajectory Planning for Heterogeneous UAV Formations
Aiming at the trajectory planning problem for heterogeneous UAV formations in complex environments, a trajectory prediction model combining Convolutional Neural Networks (CNNs) and Long Short-Term Memory networks (LSTM) is designed, and a real-time trajectory planning method is proposed based on thi...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Drones |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-446X/9/2/78 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849718969063178240 |
|---|---|
| author | Weichen Qian Wenjun Yi Shusen Yuan Jun Guan |
| author_facet | Weichen Qian Wenjun Yi Shusen Yuan Jun Guan |
| author_sort | Weichen Qian |
| collection | DOAJ |
| description | Aiming at the trajectory planning problem for heterogeneous UAV formations in complex environments, a trajectory prediction model combining Convolutional Neural Networks (CNNs) and Long Short-Term Memory networks (LSTM) is designed, and a real-time trajectory planning method is proposed based on this model. By pre-training trajectory prediction networks for various types of UAVs, the traditional physics-based models are replaced for flight trajectory prediction. Inspired by Model Predictive Control (MPC), in the trajectory planning stage, the method generates multi-step trajectory points using an improved artificial potential field (APF) method, estimates the actual formation trajectory using the prediction network, and optimizes the trajectory through a multi-objective particle swarm optimization (MOPSO) algorithm after evaluating the planning costs. During actual flight, the optimized parameters generate trajectory points for the formation to follow. Unlike conventional path planning based on simple constraints, the proposed method directly plans trajectory points based on trajectory tracking performance, ensuring high feasibility for the formation to follow. Experimental results show that the CNN-LSTM network outperforms other networks in both short-term and long-term trajectory prediction. The proposed trajectory planning method demonstrates significant advantages in formation maintenance, trajectory tracking, and real-time obstacle avoidance, ensuring flight stability and safety while maintaining high-speed flight. |
| format | Article |
| id | doaj-art-8872a7cd4d5f477098363c8376fc45f9 |
| institution | DOAJ |
| issn | 2504-446X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Drones |
| spelling | doaj-art-8872a7cd4d5f477098363c8376fc45f92025-08-20T03:12:14ZengMDPI AGDrones2504-446X2025-01-01927810.3390/drones9020078Control-Oriented Real-Time Trajectory Planning for Heterogeneous UAV FormationsWeichen Qian0Wenjun Yi1Shusen Yuan2Jun Guan3National Key Laboratory of Transient Physics, Nanjing University of Science and Technology, Nanjing 210094, ChinaNational Key Laboratory of Transient Physics, Nanjing University of Science and Technology, Nanjing 210094, ChinaNational Key Laboratory of Transient Physics, Nanjing University of Science and Technology, Nanjing 210094, ChinaSchool of Automation, Jiangsu University of Science and Technology, Zhenjiang 212100, ChinaAiming at the trajectory planning problem for heterogeneous UAV formations in complex environments, a trajectory prediction model combining Convolutional Neural Networks (CNNs) and Long Short-Term Memory networks (LSTM) is designed, and a real-time trajectory planning method is proposed based on this model. By pre-training trajectory prediction networks for various types of UAVs, the traditional physics-based models are replaced for flight trajectory prediction. Inspired by Model Predictive Control (MPC), in the trajectory planning stage, the method generates multi-step trajectory points using an improved artificial potential field (APF) method, estimates the actual formation trajectory using the prediction network, and optimizes the trajectory through a multi-objective particle swarm optimization (MOPSO) algorithm after evaluating the planning costs. During actual flight, the optimized parameters generate trajectory points for the formation to follow. Unlike conventional path planning based on simple constraints, the proposed method directly plans trajectory points based on trajectory tracking performance, ensuring high feasibility for the formation to follow. Experimental results show that the CNN-LSTM network outperforms other networks in both short-term and long-term trajectory prediction. The proposed trajectory planning method demonstrates significant advantages in formation maintenance, trajectory tracking, and real-time obstacle avoidance, ensuring flight stability and safety while maintaining high-speed flight.https://www.mdpi.com/2504-446X/9/2/78heterogeneous UAV swarmtrajectory planningmulti-objective particle swarm optimization (MOPSO)trajectory predictiondeep learningartificial potential field (APF) |
| spellingShingle | Weichen Qian Wenjun Yi Shusen Yuan Jun Guan Control-Oriented Real-Time Trajectory Planning for Heterogeneous UAV Formations Drones heterogeneous UAV swarm trajectory planning multi-objective particle swarm optimization (MOPSO) trajectory prediction deep learning artificial potential field (APF) |
| title | Control-Oriented Real-Time Trajectory Planning for Heterogeneous UAV Formations |
| title_full | Control-Oriented Real-Time Trajectory Planning for Heterogeneous UAV Formations |
| title_fullStr | Control-Oriented Real-Time Trajectory Planning for Heterogeneous UAV Formations |
| title_full_unstemmed | Control-Oriented Real-Time Trajectory Planning for Heterogeneous UAV Formations |
| title_short | Control-Oriented Real-Time Trajectory Planning for Heterogeneous UAV Formations |
| title_sort | control oriented real time trajectory planning for heterogeneous uav formations |
| topic | heterogeneous UAV swarm trajectory planning multi-objective particle swarm optimization (MOPSO) trajectory prediction deep learning artificial potential field (APF) |
| url | https://www.mdpi.com/2504-446X/9/2/78 |
| work_keys_str_mv | AT weichenqian controlorientedrealtimetrajectoryplanningforheterogeneousuavformations AT wenjunyi controlorientedrealtimetrajectoryplanningforheterogeneousuavformations AT shusenyuan controlorientedrealtimetrajectoryplanningforheterogeneousuavformations AT junguan controlorientedrealtimetrajectoryplanningforheterogeneousuavformations |