How can robots perceive the world and their movements in order to perform navigation and manipulation tasks? In this module we will study how images and videos captured by robot-mounted cameras are transformed into representations such as features and optical flow
Such 2D representations then allow us to extract 3D information about where the camera is and in which direction the robot is moving
You will come to understand how grabbing objects is facilitated by calculating the 3D pose of objects, and navigation can be accomplished by visual odometry and landmark-based localization.
Start: 06/06/2022
End: 00/01/1900
This course is online
Contacts: Contact form
Start date:
06/06/2022
End date:
30/12/1899
