Path Optimization of Intelligent Wheelchair Based on an Improved Ant Colony Algorithm

Abstract

This paper presents an improved ant colony optimization algorithm for solving intelligent wheelchair path planning problem. The existing ant colony algorithm has many problems in solving intelligent wheelchair path planning problem, such as the extra corners of raster maps and the irregularity of corners. In this paper, the improved ant colony optimization algorithm which can effectively remove the extra corners and smooth the corners with three Bezier curves, combining the constraints of wheelchair physical conditions and environmental conditions was proposed. MATLAB software is used to verify the feasibility and effectiveness of algorithm. Meanwhile, we use the virtual reality technology provided by ROS system to establish GAZEBO physical simulation experiment platform to verify the practicability and feasibility of the algorithm in the mobile robot system. Finally, the effectiveness of the improved algorithm is verified by the movement of the mobile robot in the actual test environment. The results of the proposed algorithm are found to be satisfactory.