Implementation of vision-based autonomous mobile platform to control by A∗ algorithm

Abstract

Aiming at rareness of navigation solutions for vehicle platform in unapplicable-GPS or low quality of GPS environment, this paper investigated an approach of vision-based path planning and navigation by a stereo camera. Firstly, camera is calibrated to get its parameters. In this stage, host PC must deterime locations of all objects in working area. When start point and target point is given out, host based on A∗ algorithm generates trajectory for mobile platform to prevent obstacles. Later, vehicle is driven to track the path planning. Additionally, host is able to update status and re-construct trajectory to avoid dynamic obstacles. The low-cost hardware architecture of mobile platform is built-in to verify the design. From the experiments, it can be seen clearly that vehicle runs on the optimized trajectory and navigated successfully.