Abstract
Simultaneous Localization And Mapping (SLAM) usually assumes the robot starts without knowledge of the environment. While prior information, such as emergency maps or layout maps, is often available, integration is not trivial since such maps are often out of date and have uncertainty in local scale. Integration of prior map information is further complicated by sensor noise, drift in the measurements, and incorrect scan registrations in the sensor map. We present the Auto-Complete Graph (ACG), a graph-based SLAM method merging elements of sensor and prior maps into one consistent representation. After optimizing the ACG, the sensor map’s errors are corrected thanks to the prior map, while the sensor map corrects the local scale inaccuracies in the prior map. We provide three datasets with associated prior maps: two recorded in campus environments, and one from a fireman training facility. Our method handled up to 40% of noise in odometry, was robust to varying levels of details between the prior and the sensor map, and could correct local scale errors of the prior. In field tests with ACG, users indicated points of interest directly on the prior before exploration. We did not record failures in reaching them.
Highlights
Simultaneous Localization And Mapping (SLAM) usually assumes the robot starts without knowledge of the environment
Prior information that could be used in SLAM is present in most indoor environments: emergency maps are often displayed on the walls, and plans of the building may be available to help visitors navigate the environment
In collaboration with Dortmund’s firemen, we identified that a familiar interface that fits their workflow can be based on emergency maps, and in the present work we take a step toward enabling robots to be part of a first responders team by using the emergency map as prior information for SLAM
Summary
Simultaneous Localization And Mapping (SLAM) usually assumes the robot starts without knowledge of the environment While prior information, such as emergency maps or layout maps, is often available, integration is not trivial since such maps are often out of date and have uncertainty in local scale. Prior information that could be used in SLAM is present in most indoor environments: emergency maps are often displayed on the walls, and plans of the building may be available to help visitors navigate the environment. While this information tends to be outdated or have some local scale inaccuracies, prior maps of the environment are usually topologically accurate since they are made to help human navigation. Since it was typically designed to be easy to interpret for humans, the prior map can be used as an interface for quick operation commands such as navigation goals or trajectory following
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have