SBP Lab 2 Slam Experiment : 05.24.2003

Experiment of May 24, 2003 : SBP Lab 2

Conducted by Deryck Morales (deryck@alumni.cmu.edu)

This experiment was conducted in SBP lab 2 here at Carnegie Mellon

This is the first experiment to demonstrate results of a re-visited node comparison on the Scout2.
The environment consisted of cardboard walls configured to create a reduced GVG with 2 meetpoints, one of which has a self-loop connecting two of its edges.
The environment formed the shape of a lower case "b", in other words, and photos are shown below.

Environment Photo 0 Environment Photo 1 The corresponding graph

Environment Photo 2 Environment Photo 3

Results:

Short Quicktime movie clips of the experiment are available here:
(files are about 3.5Mb each, please be patient)
The scout homes in on Node 1
The scout probing at Node 1
The scout homes in on a weak meetpoint

The 'b' environment as sensed The resultant graph

Nodes 1 and 0 Mismatch

Nodes 2 and 0 Mismatch Nodes 2 and 1 Match

Discussion

Note that I use the words "node" and "meetpoint" interchangeably; the meetpoint exists in the environment, and corresponds to a node in the graph computed by the software.

The comparison of nodes consists of the following tests:
1. The degree of the node
2. Average minima distance : this value captures a sense of environment scale for the meetpoint. (This experiment used an equivalence range of 6 inches)
3. Relative edge angles : the leave angles of the edges of a meetpoint relative to each other. (This experiment used an equivalence angle range of 9 degrees)

The robot accessed the GVG from the position shown in the environment photos above. The robot then homed in on the first meetpoint, probed and recorded the details as node 0.

The robot then proceeded out of the "tail of the b" towards the second meetpoint, homed in on it and created node 1 to store the results.
The graph and comparison results are shown above ("Nodes 1 and 0 Mismatch"). The nodes failed to match for tests 2 and 3.

The robot then departed node 1 on edge 1 and traversed the "loop of the b" homing on and rejecting three weak meetpoints along the way.
Upon arriving back to node 1 on edge 2, the robot created node 2 and compared this newest node to the existing set.
The results of these comparisons are shown above ("Nodes 2 and 0 Mismatch", "Nodes 2 and 1 Match").

Below is the terminal output from the run. At present you will notice that the software prompts for a user command when deciding whether a node is a valid matching candidate.
This will be removed to allow full autonomy when the complete matching procedure is tested to our satisfaction.
Also of note is that the correct edge angle fit was found. ("Node 2 edge 0 corresponds to Node 1 edge 2")

Go back to: H-SLAM Experiments Page | H-SLAM page