Generic NDT mapping in dynamic environments and its application for lifelong SLAM

• We present a new mapping approach that combines normal distribution transform (NDT) and occupancy mapping.
• The mapping approach is fully generic and suitable for 2D and 3D mapping with different sensors.
• We describe a method for detecting and handling dynamic objects to allow mapping in highly dynamic environments.
• Based on the mapping algorithm a graph based SLAM algorithm is described.
• The presented SLAM approach allows lifelong mapping and localization in real world applications.

In this paper, we present a new, generic approach for Simultaneous Localization and Mapping (SLAM). First of all, we propose an abstraction of the underlying sensor data using Normal Distribution Transform (NDT) maps that are suitable for making our approach independent from the used sensor and the dimension of the generated maps. We present several modifications for the original NDT mapping to handle free-space measurements explicitly. We additionally describe a method to detect and handle dynamic objects such as moving persons. This enables the usage of the proposed approach in highly dynamic environments. In the second part of this paper we describe our graph-based SLAM approach that is designed for lifelong usage. Therefore, the memory and computational complexity is limited by pruning the pose graph in an appropriate way.