An improve crested porcupine algorithm for UAV delivery path planning in challenging environments.

Area of Science:

• Drone Engineering
• Artificial Intelligence
• Optimization Algorithms

Background:

• Traditional path planning algorithms struggle with complex environments and often fall into local optima.
• Advancements in drone technology necessitate more efficient and robust path planning solutions.
• Existing methods face challenges in dynamic terrains, obstacle avoidance, and energy consumption.

Purpose of the Study:

• To introduce an Improved Crown Porcupine Optimizer (ICPO) for enhanced drone path planning.
• To improve obstacle avoidance, optimize flight paths, and reduce energy consumption for drones.
• To address the limitations of traditional algorithms in complex and dynamic environments.

Main Methods:

• Development of the Improved Crown Porcupine Optimizer (ICPO) inspired by porcupine defense mechanisms.
• Adoption of a visuo-auditory synergy perspective for improved early convergence.
• Implementation of a good point set population initialization strategy for enhanced diversity.
• Introduction of a novel periodic retreat strategy to avoid local optima in later stages.

Main Results:

• ICPO demonstrated robustness and stability, achieving near-optimal values on the IEEE CEC2022 test set.
• In complex mountainous terrain, ICPO achieved optimal values of 778.1775 and 954.0118.
• In urban terrain, ICPO achieved optimal values of 366.2789 and 910.1682, ranking first among compared algorithms.
• ICPO proved effective and reliable for drone delivery path planning.

Conclusions:

• The Improved Crown Porcupine Optimizer (ICPO) offers a significant advancement in drone path planning.
• ICPO effectively navigates complex terrains, enhances safety, and optimizes energy consumption.
• This algorithm shows great potential for future applications in drone navigation and delivery services.