Accurate on-line 3D occupancy grids using Manhattan world constraints

In this paper we present an algorithm for constructing nearly drift-free 3D occupancy grids of large indoor environments in an online manner. Our approach combines data from an odometry sensor with output from a visual registration algorithm, and it enforces a Manhattan world constraint by utilizing factor graphs to produce an accurate online estimate of the trajectory of a mobile robotic platform. We also examine the advantages and limitations of the octree data structure representation of a 3D environment. Through several experiments in environments with varying sizes and construction we show that our method reduces rotational and translational drift significantly without performing any loop closing techniques.

Authors

• Brian Peasley
• Stan Birchfield
• Alexander Cunningham
• Frank Dellaert

Keywords

• Visualization
• Octrees
• Simultaneous localization and mapping
• Buildings
• Occupancy Grid
• Accurate Online
• Online 3D
• Manhattan World
• 3D Occupancy Grid
• Indoor Environments
• Mobile Robot
• Factor Graph
• Raw Data
• Point Cloud
• Nonlinear Programming
• Leaf Node
• Consecutive Frames
• Pose Estimation
• Map Construction
• Coordinate Frame
• Error Map
• Sensor Readings
• Loop Closure
• Rotation Error
• RGB-D Sensor
• Orientation Of Frame
• Multi-view Stereo
• Robot Pose