15-494/694 Cognitive Robotics: Lab 4

Part 1: TagCourse Demo

1. Read the wiki page on the TagCourse Maze.

2. Start Mirage using TagCourse.mirage and explore the world. Notice the green dot at the origin, which is the robot's starting point, and the red dot that mark's the intended stopping point.

3. Run Tekkotsu in Mirage.

4. Park the simulated robot's arm by doing to Root Control > File Access > Load Posture > calliope2sp and loading park1.pos, then park2.pos.

5. Run Root Control > Framework Demos > Navigation > TagCourse. Display the world map and watch how the robot adds AprilTags to the map as it goes. Also notice how the particle cloud slowly disperses as the robot moves around the world.

6. Study the source code at /usr/local/Tekkotsu/Behaviors/Demos/Navigation/TagCourse.cc.fsm to understand how the behavior is implemented.

7. TagCourse is built on top of PilotDemo, so you can use PilotDemo commands to control the robot. Now that the robot has found all the AprilTags, let's use the tags as landmarks to demonstrate localization. Take screenshots as you go.
   1. Type "msg rand" to randomize the particles, and refresh the world map.

   2. Drive the robot to a new position somewhere within the course by using PilotDemo commands such as "F" to go forward and "L" to turn left. Refresh the world map as the robot moves. Note that both the robot's position and the particles' positions continue to update via odometry.

   3. Use the head controller to move the camera so that no AprilTags are visible.

   4. Type "msg loc" to tell the Pilot to localize. The resulting particle cloud may still be somewhat diffuse. Type "msg loc" again and see what happens.

   5. The Pilot needs to see at least two landmarks to localize, but it can get better results if it sees more landmarks. Use the head controller to point the camera at a different pair of AprilTags and try "msg loc" again. What is the effect on the particle cloud?

Part 2: Improvements to TagCourse

1. If the robot gets slightly off course, either due to inaccurate motion or a minor collision, it might see more than two AprilTags the next time it examines its camera image. The tags it's "supposed" to see will be near the center of the image, but there may be other tags visible at the edges as a result of the heading being off. Currently, the TagCourse behavior refuses to move if there aren't exactly two tags visible.

2. Verify this behavior in Mirage. Start with the robot at the origin (press "r" in the Mirage window to reload). Run Root Control > Framework Demos > Navigation > PilotDemo and give the command "msg l" to turn 10 degrees to the left. Then run the TagCourse demo. Examine the representations in both the world and camera shape spaces.

3. Modify TagCourse to make it more robust. It should not be upset by tags at the edges of the camera image if it can see two good tags near the center of the image. Note: to test your modified code you must change the name of the behavior and edit the REGISTER_BEHAVIOR call so that you don't clash with the built-in TagCourse demo.

Part 3: Navigation on the Real Robot

1. Implement a navigation task where the robot looks for some landmarks (use the red and green cylinders) and then uses them to define a destination. Specifically, if it sees a red cylinder ahead and to the left, and a green cylinder ahead and to the right, it can calculate an angle to turn and a distance to travel in order to put itself on the line joining the two cylinders, equidistant from both. It should use the Pilot to execute this two-step trajectory. Use the cylinder shape, not the blob shape, so that the MapBuilder can calculate distance information (it assumes the cylinder is standing on the ground plane.)

2. Note: to see the green cylinder you may need to change the camera settings. Specifically, try using domino.plist but also, using the Tekkotsu command line, do "set Drivers.Camera.Options.Saturation=255". To reset the camera to its default settings you will have to unplug it and then plug it in again.

3. Now have the robot head away from the cylinders, and then turn around so it can see them both. Print out its estimate position. Then have the Pilot localize (it will use the cylinders as landmarks), and print out the updated position.

What to Hand In

• For Part 1, hand in your screen shots.
• For Part 2, hand in your modified TagCourse source code.
• For Part 3, hand in your source code and a screenshot showing the output (robot's position estimate before and after localization).

Due Friday, February 13, 2015.