A Real-Time Path Planning Algorithm for AUV in Unknown Underwater Environment Based on Combining PSO and Waypoint...

Area of Science:

• Robotics
• Ocean Engineering
• Artificial Intelligence

Background:

• Autonomous Underwater Vehicles (AUVs) require efficient path planning in unknown environments.
• Key challenges include minimizing travel time, path length, ensuring safety, and trajectory smoothness.

Purpose of the Study:

• To propose a novel real-time path planning approach for AUVs in unknown oceanic environments.
• To address multi-objective optimization challenges in AUV navigation.

Main Methods:

• A hybrid approach combining Particle Swarm Optimization (PSO) and waypoint guidance.
• Utilizing multi-beam Forward Looking Sonar (FLS) for real-time obstacle detection and polygon outlining.
• PSO searches for optimal temporary waypoints considering path planning parameters.

Main Results:

• The proposed algorithm successfully generated optimal paths in simulation experiments.
• Demonstrated superior performance compared to Artificial Potential Field and Genetic Algorithm methods.
• Effectively integrated obstacle avoidance with multi-objective path optimization.

Conclusions:

• The proposed real-time path planning method enhances AUV navigation efficiency and safety in unknown environments.
• The integration of PSO and FLS provides a robust solution for complex AUV path planning tasks.
• This approach offers a significant advancement for autonomous marine exploration and operations.