Mobile robot localization and map building based on laser ranging and PTAM

We propose an effective localization and map building method for mobile robot using a monocular camera and Laser Range Finder (LRF). To compensate for the insufficient information gathered by LRF, we improved a state of the art vision-based SLAM algorithm so-called parallel tracking and mapping (PTAM) system which uses an optimized parallel implementation for localization of mobile robot with high accuracy, and integrate the laser scanning data into local map using an effective combination approach. A reliable spatial model is produced for mobile robot path planning or obstacle avoidance. Compared with the traditional method, the proposed approach can acquire more features in environment of mobile robot and build the map with high speed and improved accuracy in localization. Finally, the effectiveness of proposal is verified by some real experimental results.