|
|
This experiment was setup the same way as the previous edge map goal experiments,
with the robot being placed opposite the conference room door, such that the robot turns not towards its
given start node location (N2), but towards a different node (N1).
The robot drives to node 1 and since nodes 1 and 2 are similar, it believes that it is at node 2 having arrived on
edge 0. In fact the robot has arrived at node 1 on edge 1. The robot plans its path to node 4, and departs along
edge 1:2 under the belief that it is departing on edge 2:1. Upon arriving at node 12 on edge 1, the robot finds
a mismatch between the expected path and the observed information, and so uses the observed information to localize.
Now that the robot is aware of its true location, the path to the goal is re-calculated, and the robot drives to
node 4 without incident, and again successfully departs the GVG edge 4:2 and drives to its edge map goal coordinate.
Go back to: H-SLAM Experiments Page | H-SLAM page
Jump to: People | Robots | Research | Events | Projects | Education | Papers | Software | Links
© Copyright 2002 Sensor Based Planning Lab, Carnegie Mellon University. All Rights Reserved.
 |
 |
 |