Cognitive Robotics: Lab 4 & Homework 3

Remember at the start of every lab to do a "make" on your workstation and then do "sendtekkotsu" so your robot is running the latest version of the software.

1. We will supply you with colored easter egg halves and rolls of colored tape. Using the ControllerGUI's Seg viewer, determine which colors the robot sees well, given the default RGBK color map.

2. Compose a scene of several easter egg halves for the robot to look at. Write a behavior that uses a MapBuilderNode to look at the scene and extract ellipses, and another node to examine the results and report how many ellipses the robot sees. Note that whenever you write a behavior that uses the Tekkotsu crew (which includes both the Pilot and the MapBuilder), the behavior's parent class must be VisualRoutinesStateNode, not StateNode. The node reporting the results should also be a VisualRoutinesStateNode.

3. What happens if two easter eggs touch? Does the robot still see them as two separate objects, or does it see them as one large ellipse?

4. Modify your behavior so that for every ellipse it finds in the camera image, it constructs another ellipse, centered at the same spot, but with axes that are 50% larger than the original ellipse. The new ellipse should be the same color as the extracted ellipse. When you look in camera space after your behavior has run, and select the rawY image plus all shapes, you should see a collection of ellipse pairs. Hand this in at the end of the lab.

1. Use a strip of colored tape to make a roughly vertical line. Arrange easter egg halves on either side of the line. Verify that you can use the MapBuilder to detect both the line and the easter eggs (as ellipses).

2. Using the online reference pages, look up the pointIsLeftOf() method of the LineData class. Remember to first select the DualCoding name space from the main Reference page before trying a search.

3. Also in the online reference pages, look up the getCentroid() method of EllipseData. What type of object does this method return?

4. Modify your behavior to report how many ellipses appear on each side of the line. If there is no line visible, the behavior should report that instead. If multiple lines are detected, just use the first line. Use the setInfinite() method to convert the line shape from a line segment to an infinite line, and notice how this affects the rendering of the line in the SketchGUI.

You can do this part either on the real robot or in Mirage.

1. Read the documentation for the PolygonData class, focusing on the constructor and the isInside() method.

2. Write a behavior that looks for three ellipses of a given color (your choice) and forms a closed polygon joining their centroids.

3. Extend your behavior to look for a fourth ellipse, which will be of a different color, and report whether that ellipse appears inside or outside the polygon.

1. Consider the Mirage world you built for the ARTSI programming competition, which contains a blue square 750 mm on a side. Based on just the current camera image, how can the robot tell if it is inside the square or outside the square? Run the robot around in the environment to see what it perceives.

2. Write a behavior that extracts blue lines from the camera image and then says either "inside" or "outside" depending on whether the robot is inside or outside the blue square. Hint: To make this determination, think about the following image features:
   • How many lines are visible in the image?

   • What are the orentations of the lines?

   • If two lines are visible, do they form a vee (v), a caret (^), or a < or > sign?

   • Do the lines extend across the vertical midline of the camera image, or are they restricted to just one side of the midline?

   By using some combination of these and similar features, you can formulate a rule for determining whether the robot is inside or outside the square.

3. Are there situations where some piece of at least one blue line is visible in the camera image, but there is not enough information to decide whether the robot is inside or outside the square? Describe these situations.

4. Sometimes, if the robot can't see enough to answer the question, it can get more information by turning its head, or in the case of the Create, rotating its body in place. Modify your behavior to turn the Create and take another camera image when more information is needed. How far should it turn? Are there still locations where the robot cannot answer the qestion, no matter how much it turns in place?

Hand in your source code for all the above problems, plus screen shots of the camera space SketchGUI showing the various cases your code is handling. Due Friday, February 17.