Loading ...
Sorry, an error occurred while loading the content.

391Re: Soccer Robot ...

Expand Messages
  • COE
    Oct 5, 2009
    • 0 Attachment
      --- In intellibrain@yahoogroups.com, "Peter Chatterton" <peter@...> wrote:
      >
      > My problem was that I thought you were mapping a 3 dimensional path of the ball from the head-of-view.
      >
      > If you're only trying to put yourself in front of the ball, I don't see a problem.
      >
      > Peter
      >
      >
      > ----- Original Message -----
      > From: Paul King
      > To: intellibrain@yahoogroups.com
      > Sent: Sunday, October 04, 2009 5:12 AM
      > Subject: Re: [intellibrain] Soccer Robot ...
      >
      >
      >
      >
      > converting between coordinate systems is not very computation intensive. probably not more then 5 or 10 floating point multiplies, which would only need to be done a few times per second (every time a new destination is calculated). One would need to use sine and cosine functions, but those are supported in the Math library. There shouldn't need to be any actual computer vision involved, other than what the CMUCam does in hardware, which is to turn a colored object into an x,y coordinate.
      >
      > paul
      >
      >
      >
      > ----- Original Message -----
      > From: Peter Chatterton
      > To: intellibrain@yahoogroups.com
      > Sent: Friday, October 02, 2009 10:37 AM
      > Subject: Re: [intellibrain] Soccer Robot ...
      >
      >
      >
      >
      > I know nothing about computer graphics and the rest, but would be
      > really interested in knowing if you could convert the head-on view
      > of the socces ball into x,y coordinates using the IBrain and its floating
      > point emulation.
      >
      > Peter
      >
      > ----- Original Message -----
      > From: Paul King
      > To: intellibrain@yahoogroups.com
      > Sent: Friday, October 02, 2009 12:50 PM
      > Subject: Re: [intellibrain] Soccer Robot ...
      >
      >
      >
      >
      >
      > Note that the cmucam is not a full computer vision system. All it can tell you is the x,y location of the ball at any given moment (the ball being a brightly colored region to the cmucam, which allows it to return the x,y region center).
      >
      > To compute a trajectory you will need to plot the change in the x,y coordinate over time by collecting periodic samples of the ball position and noting the time on the system clock (System.currentTimeMillis()). With some math from basic physics, the ball's velocity can be calculated, from which predictions can be made about future ball location. These coordinates in front-facing x,y will need to be translated into playing-field x,y coordinates using 3D geometry relating to visual perspective.
      >
      > More math from basic physics will allow you to compute the intersection of the ball trajectory (based on its current position and velocity) and the line of action of the robot (the path along which it moves). The robot can then travel to that point over time, with its position as represented in a model updated as it moves.
      >
      > The robot may want to continue to track the ball as it moves. Future ball positions will need to be translated geometrically relative to the robot's estimated current position, as compensating for this visual parallax is necessary to translate the ball's visual position into accurate playing field x,y coordinates.
      >
      > The robot Java program would need to be a continuous loop that estimates its position, the ball's position, the likely point of intersection of the ball with its path, and makes an adjustment to the robot's current movement speed (or stops).
      >
      > This 2 page article I found online discusses an algorithm for lanning goalie position in robot soccer:
      > http://www.fujipress.jp/finder/preview_download.php?pdf_filename=PRE_JACII000800010009.pdf&frompage=abst_page&pid=199&lang=English
      >
      > Kalman filters are useful math for estimating the velocity of a moving target from several imperfect measurements taken over time. It was developed 50 years ago for target tracking in radar systems.
      > http://en.wikipedia.org/wiki/Kalman_filter
      >
      > Best,
      > Paul (another IntelliBrain user)
      >
      >
      >
      > ----- Original Message -----
      > From: COE
      > To: intellibrain@yahoogroups.com
      > Sent: Friday, October 02, 2009 6:43 AM
      > Subject: [intellibrain] Soccer Robot ...
      >
      >
      >
      > Good day Guys...
      > we bought intellebrain bot and sonar at ridgesoft and cmucmu cam at seattle robotics few weeks ago...
      >
      > I'm going to use that for my project entitled Soccer Robot Goalie Behavior..
      > The rule of the Gaolie is to depend the goal, if the robot in the goal area detect a ball coming to the goal, the robot must calculate a trajectory line of the ball, where the ball possibly pass...if the robot in the goal detect the intersection point of the trajectory line and the line of action in the goal are, the robot must come the to the intersection point ahead of time...
      > we use sensor fusion., the cmu cam 2 and sonar sensor
      >
      > my problem are
      > how does the robot determine the trajectory line of the ball using cmucam?
      > if the robot determine the trajectory line, how does the robot determine the intersection point between the trajectory line of the ball and the line of action?
      > if the robot determine the intersection point, how the does robot able to come to that point, to obstruct the ball???
      >
      > please help us....the intellebrain-bot,sonar and cmucam are expensive...we are in the philippines...
      >

      To Peter :
      The robot is facing the ball because the cmucam is mounted in front of the robot, that serve as the vision of the robot....The ball is moving, so the robot need to predict the trajectory line of the ball, so that the robot (goal keeper) can obstruct the ball in entering the goal...the sonar is also mounted in front of the goal to measure the distance of the moving ball...our instructor said, we need to get the coordinates(x,y) of the moving ball and the coordinates of the robot(x,y) using the global, coordinates....i read the kalman filter...i cannot understand,,its very difficult to make a code in robojde.....do you have any idea in computation, using the cmucam to predict the ball, and about the Global coordinates ????
    • Show all 21 messages in this topic