UAV path planning method for data collection of fixed-point equipment in complex forest environment.

Area of Science:

• Robotics and Automation
• Environmental Monitoring
• Computer Science

Background:

• Traditional forest monitoring relies on manual data collection from ground-fixed devices, which is time-consuming and inefficient.
• Unmanned Aerial Vehicles (UAVs) offer a potential solution for automated data collection, but existing path planning methods are inadequate for complex forest environments.
• Data timeliness is a critical factor in effective forest pest and wildlife detection.

Purpose of the Study:

• To develop advanced UAV path planning strategies for complex forest environments.
• To maximize the freshness of data collected from ground-fixed devices during UAV patrols.
• To address the limitations of existing path planning methods in dynamic and challenging terrains.

Main Methods:

• Proposed a two-point path planning method using chaotic initialization and a co-evolutionary algorithm.
• Developed a multi-point path planning method utilizing simulated annealing for efficient data collection.
• Optimized algorithm parameters using benchmark functions and evaluated performance on simulated maps.

Main Results:

• The proposed UAV path planning methods significantly improve information freshness compared to existing strategies.
• The new methods achieve higher data freshness with fewer iterations and lower computational cost.
• Effectiveness was validated on both simple and complex simulated forest environments.

Conclusions:

• The developed UAV path planning approaches are practical and effective for complex forest monitoring.
• These methods enhance the efficiency and timeliness of data collection for pest detection and wildlife monitoring.
• The study highlights the potential of optimized UAV patrols in ecological surveillance.