A method and system for multi-layer path planning of unmanned aerial vehicles in a three-dimensional dynamic environment
By combining differential evolution algorithm and distributed model predictive control model with virtual agent technology, the problem of trajectory generation and tracking of fixed-wing UAV swarms in three-dimensional dynamic environment is solved, achieving efficient and safe path planning and meeting the dynamic flight constraints of UAVs.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- NORTHWESTERN POLYTECHNICAL UNIV
- Filing Date
- 2026-04-29
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies struggle to effectively address the trajectory generation and tracking issues of fixed-wing UAV swarms in three-dimensional dynamic environments, especially when static and dynamic obstacles are combined. These technologies suffer from problems such as high computational load, poor real-time performance, complex dynamic models, and difficulty in meeting UAV flight constraints.
A global reference trajectory is generated using a differential evolution algorithm. Combined with a distributed model predictive control model, an optimization model is constructed that includes trajectory tracking, formation, and obstacle avoidance costs. Dynamic obstacles are handled through virtual agent technology, and a UAV dynamics model is introduced for real-time control to generate a locally optimal control sequence.
It improves the computational efficiency and flight safety of fixed-wing UAV swarms in complex dynamic environments, ensures that trajectories conform to the dynamic constraints of UAVs, and enhances adaptability and mission execution efficiency in complex terrain.
Smart Images
Figure CN122411554A_ABST