addressalign-toparrow-leftarrow-rightbackbellblockcalendarcameraccwchatcheckchevron-downchevron-leftchevron-rightchevron-small-downchevron-small-leftchevron-small-rightchevron-small-upchevron-upcircle-with-checkcircle-with-crosscircle-with-pluscrosseditemptyheartexportfacebookfolderfullheartglobegmailgoogleimageimagesinstagramlinklocation-pinmagnifying-glassmailminusmoremuplabelShape 3 + Rectangle 1outlookpersonplusprice-ribbonImported LayersImported LayersImported Layersshieldstartickettrashtriangle-downtriangle-uptwitteruseryahoo

Let's implement a partially observable world (AIMA ch. 4).

We're going to break up 4.11 into several subproblems; the first of which is to implement a partially observable world containing disjoint, convex polygons and which has the following properties:

  • The percept will be a list of the positions, relative to the agent, of the visible vertices.
  • The percept does not include the position of the robot! The robot must learn its own position from the map; for now, you can assume that each location has a different 'view."
  • Each action will be a vector describing a straight-fine path to follow. If the path is unobstructed, the action succeeds; otherwise, the robot stops at the point where its path first intersects an obstacle. If the agent returns a zero motion vector and is at the goal (which is fixed and known), then the environment teleports the agent to a random location (not inside an obstacle).
  • The performance measure charges the agent l point for each unit of distance traversed and awards 1000 points each time the goal is reached.

Join or login to comment.

  • Glenn B.

    I just learned about the CCW (counter-clockwise) test for line segments intersecting. Very nice. http://compgeom.cs.uiuc.edu/~jeffe/teaching/373/notes/x06-sweepline.pdf

    January 30, 2013

    • Peter D.

      That's pretty cool; did you handle the degenerate cases? Also, I think I have PTSD with respect to the word "sweepline" from trying to implement Fortune's algorithm for Voronois.

      January 31, 2013

  • Glenn B.

    Great conversation clarified the problem, and has led to some cool code.

    January 30, 2013

  • Peter D.

    Great; we made some great progress planning out the partially observable world. Prasan had a pretty good proof-of-concept, too.

    January 29, 2013

  • Nesim S.

    what's the google
    hangout link?
    can't make it there physically

    January 28, 2013

    • Peter D.

      Sorry, Nesim; we'll set one up next week!

      January 28, 2013

  • Glenn B.

    Be there in fifteen.

    January 28, 2013

  • Prasan S.

    On my way

    January 28, 2013

  • Prasan S.

    On my way

    January 28, 2013

  • Patrick N

    Crud. Had to cancel because I'm behind on a project. By the way, does everyone in the group have their own copy of the Russell/Norvig book?

    January 28, 2013

    • Peter D.

      Some of us do; but most of us just use the PDF. Should I send it to you?

      January 28, 2013

  • Prasan S.

    In

    January 26, 2013

5 went

People in this
Meetup are also in:

Sign up

Meetup members, Log in

By clicking "Sign up" or "Sign up using Facebook", you confirm that you accept our Terms of Service & Privacy Policy