January 9, 2010
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:
September 22, 2008
I’ve finished my project. Our approach specifically addresses issues such as safe navigation in unmodified and dynamic environments, like Departamental II of this university. We’ve solved the following problems:
- Navigation in dynamic environments. Public places are often packed with people. People behave not necessarily cooperatively. Our approach provides means for safe and effective navigation through crowds.
- Navigation in unmodified environments. No modification of the environment is necessary for the robot’s operation.
- Localization. In every operation, our robot continuously tracks its position using its maps. Position estimates are necessary for the robot to know where to move when navigating to a specific goal, and to ensure the robot does not accidentally leave its operational area.
To navigate reliably in indoor environments, a mobile robot must know where it is. Thus, reliable position estimation is a key problem in mobile robotics. We believe that probabilistic approaches are among the most promising candidates to providing a comprehensive and real-time solution to the robot localization problem.
So, in this video we’ve used Monte Carlo localization method where we represent the probability density involved by maintaining a set of samples that are randomly drawn from it. We show experimentally that the resulting method is able to efficiently localize a mobile robot without knowledge of its starting location.
Link for more information: http://jde.gsyc.es/index.php/jmvega_guide_robot
