Functional object mapping of kitchen environments

In this paper we investigate the acquisition of 3D functional object maps for indoor household environments, in particular kitchens, out of 3D point cloud data. By modeling the static objects in the world into hierarchical classes in the map, such as cupboards, tables, drawers, and kitchen appliances, we create a library of objects which a household robotic assistant can use while performing its tasks. Our method takes a complete 3D point cloud model as input, and computes an object model for it. The objects have states (such as open and closed), and the resultant model is accurate enough to use it in physics-based simulations, where the doors can be opened based on their hinge position. The model is built through a series of geometrical reasoning steps, namely: planar segmentation, cuboid decomposition, fixture recognition and interpretation (e. g. handles and knobs), and object classification based on object state information.

Authors

• Radu Bogdan Rusu
• Zoltán-Csaba Márton
• Nico Blodow
• Mihai Emanuel Dolha
• Michael Beetz

Keywords

• Robots
• Robot kinematics
• Three dimensional displays
• Meteorology
• Floors
• Manipulators
• Logic gates
• Point Cloud
• Object Classification
• Classification Maps
• Hierarchical Classification
• Point Cloud Data
• Objects In The World
• Point Cloud Model
• Magnetometer
• Semantic Information
• Cognitive Map
• Indoor Environments
• Environmental Model
• Convex Hull
• System Overview
• Segmented Regions
• Surface Curvature
• Neighboring Points
• Laser Ranging
• Dishwasher
• Planar Regions
• Segmentation Module
• Types Of Queries
• Candidate Objects
• Walls Of The Room
• Small Curvature
• Direction Of Curvature
• Surface Normals
• Environment Map