Hierarchical Object Map Estimation for Efficient and Robust Navigation

We propose a hierarchical representation of objects, where the representation of each object is allowed to change based on the quality of accumulated measurements. We initially estimate each object as a 2D bounding box or a 3D point, encoding only the geometric properties that can be well-constrained using limited viewpoints. With additional measurements, we allow each object to become a higher dimensional 3D volumetric model for improved reconstruction accuracy and collision-testing. Our Hierarchical Object Map Estimation (HOME) is robust to deficiencies in viewpoints and allows planning safe and efficient trajectories around object obstacles using a monocular camera. We demonstrate the advantages of our approach on a real-world TUM dataset and during visual-inertial navigation of a quad-rotor in simulation.

Authors

• Kyel Ok
• Katherine Liu
• Nicholas Roy

Keywords

• Visualization
• Solid modeling
• Three-dimensional displays
• Navigation
• Volume measurement
• Conferences
• Estimation
• Posterior Mode
• Hierarchical Map
• Map Objects
• Robust Navigation
• Geometric Properties
• Bounding Box
• Real-world Datasets
• Monocular
• Reconstruction Accuracy
• 3D Point
• Objective Function
• Object Detection
• Object Classification
• Level Of Abstraction
• RGB Images
• Hierarchical Levels
• Jacobian Matrix
• 3D Volume
• Geometric Information
• Reconstruction Quality
• Hierarchy Model
• Abstract Representations
• Scene Graph
• Camera Pose
• Orbital Motion
• Representative Points
• Machine Vision
• Online Optimization
• Object Reconstruction
• Update Function