A hybrid path planning algorithm combining A* and improved ant colony optimization with dynamic window approach for...

Area of Science:

• Robotics and Automation
• Artificial Intelligence
• Operations Research

Background:

• Warehouse automation relies on efficient path planning for robotic systems.
• Existing algorithms often struggle with dynamic environments and energy optimization.
• Hybrid approaches are being explored to combine the strengths of different planning strategies.

Purpose of the Study:

• To develop and evaluate a novel hybrid path planning algorithm for enhanced energy efficiency in warehouse environments.
• To combine the heuristic search of A*, the optimization of Ant Colony Optimization (ACO), and the dynamic adaptability of the Dynamic Window Approach (DWA).
• To demonstrate the superiority of the proposed IACO+A*+DWA algorithm over existing hybrid methods.

Main Methods:

• A novel hybrid path planning algorithm integrating A*, Ant Colony Optimization (ACO), and Dynamic Window Approach (DWA) was developed.
• The algorithm, termed IACO+A*+DWA, was tested in complex warehouse scenarios.
• Performance was evaluated based on energy consumption, path length, number of turns, and time to goal, with statistical analysis using ANOVA.

Main Results:

• The IACO+A*+DWA algorithm achieved an average energy consumption of 89.8 J, 13.3% lower than ACO+A*+DWA.
• It resulted in a shorter path length (95.94 m) with fewer turns (43) compared to other hybrid methods.
• The algorithm was 1.5% faster in reaching the goal than GA+A*+DWA, demonstrating improved time efficiency.

Conclusions:

• The IACO+A*+DWA algorithm significantly minimizes energy consumption and optimizes path characteristics in warehouse environments.
• Its superior performance in energy efficiency, path length, and speed makes it highly suitable for real-time applications in dynamic settings.
• Future research will explore further optimization and integration of machine learning for enhanced adaptability.