Autonomous Exploration and Mapping of Large Spaces
| Hierarchical simultaneous localization and mapping is a novel method of combining topological and feature based mapping strategies. The topological mapping process is used to organize local feature based methods. The result is an autonomous exploration and mapping strategy that scales well to large environments and possibly higher dimensions while confronting the issue of obstacle avoidance. We have obtained successful results of our approach in an area spanning 5000 square meters. |
| Our Contribution: Hierarchical Atlas Implement a feature-based technique in a topological framework. | ||
 EKF |
 |
 GVG |
|
 |
|
| Embedded Topological Atlas |
 |
| Free Space with Topological Map (GVG) + 2 Edge-maps |
| Experimental Results |
 Odometry |
 Feature-maps tied to meet point locations |
| Local Edge-Map Example |
 |
| Region of interest on the sixth floor of Wean Hall |
| Local Edge-Map Example |
 |
| Embedded edge map |
| The Abstract H-SLAM Atlas |
 |
 Graph Structure |
Go back to: H-SLAM page
© Copyright 2002 Sensor Based Planning Lab, Carnegie Mellon University. All Rights Reserved.