3D environment mapping using visual and Lidar sensors
This tool addresses a visual servoing control strategy that uses visual information, acquired by a fiducial system, to solve the regulation to an arbitrary pose problem in differential driven mobile robots. In addition, in order to make this system more robust and immune to occlusion, an Extended Kalman Filter to fuse odometric data and the data acquired from several landmarks.
- Artificial fiducial markers have high detection and low false-positive and false-negative rates.
- The use of fiducial markers is suitable when object recognition or pose determination is needed with high reliability and when the environment can be modified to affix them
- By using information acquired from fiducial landmarks, can guide the robot towards any desired pose
- In spite of granting a better performance, and to make the system immune to occlusion, a Kalman filter will be design to fuse odometric data and those from the visual system.
INESC P&D Brasil