An improved ant colony algorithm for integrating global path planning and local obstacle avoidance for mobile robot...

Area of Science:

• Robotics and Artificial Intelligence
• Computational Intelligence
• Path Planning Algorithms

Background:

• Traditional ant colony optimization (ACO) algorithms face challenges in search efficiency and path optimization.
• Existing obstacle avoidance strategies struggle with dynamic obstacles of varying shapes and motion states.

Purpose of the Study:

• To enhance the path optimization effect and search efficiency of the ant colony algorithm.
• To develop improved strategies for dynamic obstacle avoidance in complex environments.

Main Methods:

• Proposed an improved ant colony algorithm incorporating a collar path generation for early-stage planning.
• Introduced ending and turning point effects to enhance heuristic information for improved search efficiency.
• Implemented adaptive adjustment of pheromone intensity and parameter control strategies for balancing convergence and global search.
• Developed novel obstacle avoidance strategies for dynamic obstacles with diverse characteristics.

Main Results:

• The improved ACO algorithm demonstrated greater effectiveness and robustness in complicated and large-scale simulated environments compared to existing methods.
• The proposed dynamic obstacle avoidance strategies resulted in higher path quality post-avoidance.
• The new strategies exhibited lower sensor performance requirements and enhanced safety during obstacle avoidance.

Conclusions:

• The enhanced ant colony algorithm offers significant improvements in path optimization and search efficiency.
• The developed dynamic obstacle avoidance strategies are effective, safe, and adaptable to various obstacle types and motions.
• This research contributes a more robust and efficient solution for autonomous navigation in complex and dynamic environments.