Multi-UAV cooperative reconnaissance mission planning novel method under multi-radar detection

Area of Science:

• Aerospace Engineering
• Artificial Intelligence
• Operations Research

Background:

• Traditional swarm intelligence algorithms struggle with slow convergence and complex constraints in Unmanned Aerial Vehicle (UAV) path planning.
• Existing methods are inadequate for the sophisticated demands of Multi-UAV Cooperative Reconnaissance Mission Planning (MUCRMP), especially with multi-radar detection.

Purpose of the Study:

• To develop a global optimization model for MUCRMP addressing shorter distances within radar detection range.
• To incorporate UAV imaging characteristics and minimum turning radius into the planning model.
• To propose an improved synthetic heuristic algorithm for generating effective reconnaissance mission plans.

Main Methods:

• Formulation of a global optimization model for UAV path planning in reconnaissance missions.
• Integration of UAV imaging characteristics and minimum turning radius constraints.
• Development and application of an improved synthetic heuristic algorithm to solve the proposed model.

Main Results:

• A valuable reconnaissance mission plan was generated using the improved synthetic heuristic algorithm.
• The model and algorithm demonstrated validity and feasibility in a case study with 68 target points.
• The improved algorithm showed enhanced convergence speed and better anti-radar attributes for UAVs compared to existing methods.

Conclusions:

• The proposed global optimization model and improved synthetic heuristic algorithm effectively address limitations in UAV path planning for MUCRMP.
• The method provides superior anti-radar capabilities and faster convergence for reconnaissance missions.
• This research offers a significant advancement for cooperative multi-UAV operations in complex environments.