Research on real-time positioning and map construction technology of intelligent car based on ROS

Abstract

Real-time localization and map construction (SLAM) is a key technology to realize autonomous navigation of smart cars, which mainly solves the problems of mobile robots in mapping, positioning and path planning. This paper introduces and analyzes SLAM. By comparing three different mapping algorithms, gmapping, hector, and cartographer, and through analysis and comparison experiments, the gmapping-based algorithm is finally used for mapping. On the basis of AMCL positioning, global and local path planning is carried out through A* algorithm and DWA algorithm to realize autonomous navigation and obstacle avoidance functions. And the experimental verification was carried out under the autolabor smart car. The experiment proved that using this algorithm, autolabor can perform accurate pose estimation, map construction and autonomous navigation in an unfamiliar environment.