Robust Photogeometric Localization over Time for Map-Centric Loop Closure
This work addresses the critical issue of loop closure in map-centric SLAM, which is essential for long-term mapping in robotics, but it is incremental as it builds on existing sensor fusion approaches.
The paper tackles the problem of loop closure in map-centric SLAM by presenting a tightly coupled photogeometric metric localization method that combines LiDAR and camera constraints with sequential validation, resulting in improved accuracy and robustness to incorrect initial poses compared to conventional global ICP methods.
Map-centric SLAM is emerging as an alternative of conventional graph-based SLAM for its accuracy and efficiency in long-term mapping problems. However, in map-centric SLAM, the process of loop closure differs from that of conventional SLAM and the result of incorrect loop closure is more destructive and is not reversible. In this paper, we present a tightly coupled photogeometric metric localization for the loop closure problem in map-centric SLAM. In particular, our method combines complementary constraints from LiDAR and camera sensors, and validates loop closure candidates with sequential observations. The proposed method provides a visual evidence-based outlier rejection where failures caused by either place recognition or localization outliers can be effectively removed. We demonstrate the proposed method is not only more accurate than the conventional global ICP methods but is also robust to incorrect initial pose guesses.