A new path planning strategy integrating improved ACO and DWA algorithms for mobile robots in dynamic environments

Area of Science:

• Robotics
• Artificial Intelligence
• Computer Science

Background:

• Path planning for mobile robots in dynamic environments presents significant challenges.
• Existing algorithms often struggle with real-time obstacle avoidance and efficiency.

Purpose of the Study:

• To propose a novel integrated path planning strategy for mobile robots.
• To enhance path optimality and efficiency in dynamic environments.

Main Methods:

• An improved Ant Colony Optimization (ACO) algorithm was developed for static environments, focusing on pheromone initialization, heuristic functions, and updates.
• A modified Dynamic Window Approach (DWA) was implemented for dynamic environments, incorporating node deletion, initial orientation optimization, and an improved evaluation function.
• Simulations were conducted in various environments to validate the proposed algorithms.

Main Results:

• The improved ACO algorithm generated shorter paths with fewer turning points in fewer iterations.
• The modified DWA effectively avoided moving obstacles, resulting in more efficient paths.
• The integrated approach demonstrated superior performance compared to existing methods.

Conclusions:

• The proposed integrated path planning strategy effectively addresses the challenges of mobile robot navigation in dynamic environments.
• The combination of improved ACO and modified DWA offers a robust and efficient solution for path planning.