Map merging for distributed robot navigation

A set of robots mapping an area can potentially combine their information to produce a distributed map more efficiently than a single robot alone. We describe a general framework for distributed map building in the presence of uncertain communication. Within this framework, we then present a technical solution to the key decision problem of determining relative location within partial maps.

Authors

• Kurt Konolige
• Dieter Fox
• Benson Limketkai
• Jonathan Ko
• Benjamin Stewart

Keywords

• Merging
• Navigation
• Robot kinematics
• Robot sensing systems
• Intelligent robots
• Artificial intelligence
• Robustness
• Solids
• Centralized control
• Communication system control
• Map Merging
• Relative Location
• Decision Problem
• Part Of The Map
• Single Robot
• False Positive
• Receiver Operating Characteristic Curve
• Types Of Interactions
• Geometric Features
• Use Of Features
• Indoor Environments
• Small Patches
• Hypothesis Generation
• Feature Matching
• Minimum Ratio
• Different Types Of Interactions
• Single Patch
• Hypothesis Verification
• Individual Robots