An Intelligently Enhanced Ant Colony Optimization Algorithm for Global Path Planning of Mobile Robots in Engineering...

Area of Science:

• Robotics
• Artificial Intelligence
• Optimization Algorithms

Background:

• Global path planning is crucial for mobile robot navigation.
• Ant Colony Optimization (ACO) is a common swarm intelligence approach.
• Standard ACO has limitations in efficiency and premature convergence.

Purpose of the Study:

• To propose an intelligently enhanced Ant Colony Optimization (IEACO) algorithm.
• To address the limitations of traditional ACO in mobile robot path planning.
• To improve search efficiency, exploration-exploitation balance, and path quality.

Main Methods:

• Implemented non-uniform initial pheromone distribution for faster initial search.
• Utilized the ε-greedy strategy to balance exploration and exploitation.
• Introduced adaptive dynamic adjustment of exponents α and β.
• Developed a multi-objective heuristic function considering distance and turning angle.
• Designed a dynamic global pheromone update strategy to avoid local optima.
• Transformed path planning into a multi-objective optimization problem.

Main Results:

• Simulations confirmed the effectiveness of each enhancement within IEACO.
• IEACO demonstrated superior performance compared to other path planning algorithms.
• Experimental results validated the practical applicability of IEACO for mobile robots.

Conclusions:

• The proposed IEACO algorithm significantly improves global path planning for mobile robots.
• IEACO overcomes limitations of standard ACO, offering more comprehensive path optimization.
• The enhanced algorithm shows practical value and superior performance in real-world applications.