Multi-uav regional detection full coverage task planning method
By dividing the task area into polygonal task sub-regions and using genetic algorithms and grid methods to plan paths, combined with KD-Tree nearest neighbor search, the resource allocation and path planning in multi-UAV cooperative operations are optimized. This solves the problem of resource waste and inefficiency caused by the differences in detection capabilities of different types of UAVs, and achieves efficient regional detection coverage.
CN117369515BActive Publication Date: 2026-07-24THE 54TH RESEARCH INSTITUTE OF CHINA ELECTRONICS TECHNOLOGY GROUP CORPORATION
View PDF 2 Cites 0 Cited by
Patent Information
- Authority / Receiving Office
- CN Β· China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- THE 54TH RESEARCH INSTITUTE OF CHINA ELECTRONICS TECHNOLOGY GROUP CORPORATION
- Filing Date
- 2023-11-13
- Publication Date
- 2026-07-24
AI Technical Summary
Technical Problem
Existing technologies fail to effectively consider the differences in detection capabilities among different types of drones in multi-drone collaborative operations, resulting in resource waste and inefficiency.
Method used
By dividing the task area into multiple polygonal task sub-regions, combining genetic algorithms and grid methods to plan UAV paths, and utilizing the KD-Tree nearest neighbor search method to optimize the UAV task execution order and path planning, resource consumption is reduced and coverage efficiency is improved.
Benefits of technology
It enables optimized resource allocation and path planning in multi-UAV collaborative operations, improves regional detection coverage and operational efficiency, and reduces the number of UAVs.
β¦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN117369515B_ABST
Abstract
The application discloses a multi-unmanned aerial vehicle regional detection full-coverage task planning method, which comprises the following steps: for a non-fixed point task region, a task region is divided into multiple polygonal task sub-regions in combination with unmanned aerial vehicles with different detection capabilities, and the task sub-regions corresponding to each type of unmanned aerial vehicle are obtained; based on the task sub-regions corresponding to each type of unmanned aerial vehicle, a genetic algorithm is utilized, the minimum moving distance of all task sub-regions of each type of unmanned aerial vehicle is taken as an optimization target, and the optimal task execution sequence of the task sub-regions of each type of unmanned aerial vehicle is solved; the task sub-regions are rasterized, the center points of the grids are regarded as unmanned aerial vehicle driving path points, a comb-shaped mode is adopted to connect the path points to complete internal detection path planning of the task sub-regions, and the two end points of the path are taken as circumscribed path points of the task sub-regions; and a KD-Tree nearest neighbor search method is utilized to find the nearest distance of two circumscribed path points of adjacent task sub-regions, and path planning between different task sub-regions of the same type of unmanned aerial vehicle is completed.
Need to check novelty before this filing date? Find Prior Art