Efficient Loop Closure Detection Method for Lidar SLAM in Challenging Environment

Abstract

With the development of automatic driving cars, simultaneous localization and mapping (SLAM) becomes a widely discussed topic. Loop closure detection, as an important module in lidar slam, can provide strong constraint for localization and mapping. In classical lidar SLAM algorithm, traditional loop closure detection method often fails to find out the matching nodes, or even has false positive results, especially in challenging environment like the crossroads or sharp turns. In this paper, a lidar SLAM loop closure detection method using adjacent nodes to check the reliability is introduced. A series of experiments is implemented to verify the effectiveness of the method.