We’re glad to present the first prototype of monoSLAM working inside jdeRobot platform.
MonoSLAM is for monocular Simultaneous Location And Mapping, a computer vision technique which permits to estimate in real-time the relative position of a moving camera with respect to several landmarks extracted from the environment, using only the image sequence that provides the camera.
It is potentially helpful in visual odometry for robots, specially for those whose mechanical odometry is poor (e.g. legged robotssuch as Nao). It can also be used for augmented reality systems and scene reconstruction from video sequences.
You will always find a video of the latest prototype by following this link:
Now, the user can pause and replay the movement action of the skeleton (Ramón) by the two buttons directly inserted in the virtual scene. This improvement has been done through the Progeo library, that allow to relate the 2D points corresponding to the imagen pixels with the 3D points of the virtual stage. If the line projected from the pixel go through one of the “virtual” buttons, the action is paused or played.
This is a video example of the “skeleton in movement” visualizer that we’re developing. This scheme allows the camera control by mouse and a series of illumination options. Enjoy it.
In this video, we can see a navigation simulation using Gradient Path Planning Algorithm. Under OpenGL we have improved the agility of response to graphical level. We’re design our virtual department; the blue mark represent the virtual robot, and the red mark is the goal (office 113).
