Reliable real-time change detection and mapping for 3D LiDARs

A common scenario in Search and Rescue robotics is to map and patrol a disaster site to assess the situation and plan potential missions of rescue teams. Particular importance has to be given to changes in the environment as these may correspond to critical events like building collapses, movement of objects, etc. This paper presents a change detection pipeline for LiDAR-equipped robots to assist humans in detecting those changes. The local 3D point cloud data is compared to an octree-based occupancy map representation of the environment by computing the Mahalanobis distance to the closest voxel in the map. The thresholded distance is processed by a clustering algorithm to obtain a set of change candidates. Finally, outliers in these sets are filtered using a random forest classifier. Changes are continuously mapped during a sortie based on their classification score and number of occurrences. Changes are reported in real time during robot operation.