Using an attributed 2D-grid for next-best-view planning on 3D environment data for an autonomous robot

The usage of geometrical 3D-models enables humans to plan and design different aspects of indoor environments. This article describes the next-best-view planner for an autonomous 3D modelling robot using a 3D laser scanner. Besides the human user, the constructed 3D-model can also be used by other autonomous robots for navigation and localization tasks. The process of building a 3D-model without any geometrical pre-knowledge leads to a planning scheme which uses the 3D data. This article copes with that problem by using and attributed 2D grid combined with an intelligent action planning scheme for indoor environments.