Embedded Visual SLAM for Navigation of an Autonomous Vehicle

Marco A. Moreno-Armendáriz, Carlos A. Duchanoy, Ángel G. Zanatta Juárez, and Carlos A. Cruz-Villar


Embedded system, Visual SLAM, autonomous vehicle


An important objective of an autonomous vehicle is to navigate through an unknown environment. A method used to achieve this objective is to generate a map. A map provides the means to the vehicle to create paths between the visited places autonomously in order to perform a task. A particular problem is to obtain such a map when there is no initial knowledge of the surroundings or not even the initial position of the robot in the environment. The present paper shows a new design of a Visual SLAM processor that solves this problem and it is implemented on an FPGA. The processor is then tested on a differential traction mobile robot with a computer vision system that travels on a controlled unknown environment. The experimental results obtained show a good performance in real time.

Important Links:

Go Back