Application of improved ant colony optimization in mobile robot trajectory planning

Area of Science:

• Artificial Intelligence
• Optimization Algorithms
• Robotics

Background:

• Traditional ant colony optimization (ACO) faces challenges like slow convergence and local optima.
• These limitations hinder its effectiveness in complex environments.

Purpose of the Study:

• To propose an improved ant colony optimization (ACO) algorithm.
• To address the limitations of traditional ACO, including slow convergence and local optima.
• To enhance performance in obstacle avoidance tasks.

Main Methods:

• Adaptively adjusting the volatility coefficient to expand search range and avoid local optima.
• Implementing a roulette operation in the state transition rule to improve solution quality and convergence speed.
• Utilizing elite selection and node crossover operations for better pathfinding and global search efficiency.

Main Results:

• The improved ACO algorithm demonstrates enhanced search ability and expanded exploration range.
• Significant improvements in solution quality and convergence speed were observed.
• Experimental application to obstacle avoidance in static and dynamic environments validated the algorithm's effectiveness.

Conclusions:

• The proposed enhanced ant colony optimization algorithm effectively overcomes the limitations of traditional ACO.
• The algorithm shows feasibility and effectiveness for obstacle avoidance tasks.
• The improvements contribute to more efficient and robust optimization solutions.