A Frame-to-Frame Scan Matching Algorithm for 2D Lidar Based on Attention

Abstract

The frame-to-frame scan matching algorithm is the most basic robot localization and mapping module and has a huge impact on the accuracy of localization and mapping tasks. To achieve high-precision localization and mapping, we propose a 2D lidar frame-to-frame scanning matching algorithm based on an attention mechanism called ASM (Attention-based Scan Matching). Inspired by human navigation, we use a heuristic attention selection mechanism that only considers the areas covered by the robot’s attention while ignoring other areas when performing frame-to-frame scan matching tasks to achieve a similar performance as landmark-based localization. The selected landmark is not switched to another one before it becomes invisible; thus, the ASM cannot accumulate errors during the life cycle of a landmark, and the errors will only increase when the landmark switches. Ideally, the errors accumulate every time the robot moves the distance of the lidar sensing range, so the ASM algorithm can achieve high matching accuracy. On the other hand, the number of involved data during scan matching applications is small compared to the total number of data due to the attention mechanism; as a result, the ASM algorithm has high computational efficiency. In order to prove the effectiveness of the ASM algorithm, we conducted experiments on four datasets. The experimental results show that compared to current methods, ASM can achieve higher matching accuracy and speed.