history key frames (history submap for loop closure)

History key frames, also known as history submaps or sliding windows, are a technique used in visual simultaneous localization and mapping (SLAM) to improve loop closure detection.

In visual SLAM, the system estimates the trajectory of a robot and builds a map of the environment using visual information from cameras mounted on the robot. Loop closure occurs when the robot revisits a previously visited location and the system detects that it has returned to that location. This is important for accurate mapping and localization.

The history key frames technique involves storing a fixed number of key frames, or submaps, from the past trajectory of the robot. When the robot revisits a location, the system compares the current submap to the stored submaps to detect loop closure. By comparing multiple submaps, the system can better handle changes in the environment over time.

The use of history key frames can improve the accuracy of loop closure detection, which in turn improves the accuracy of the map and the robot's localization. However, it also increases the computational cost and memory usage of the SLAM system.