Neural Network based 3D Mapping Using Depth Image Camera

Mapping is a crucial task for robot navigation. Especially, in order to develop a fully autonomous robot that can interact well with human, the map is not only required to contain geometry but also the semantic contents. Building a detailed map of the environment, makes it easy for the robot complete its mission. In this paper, we propose a method for environment 3D map building using the depth image camera. A Feed-Forward neural network is trained to convert the depth image into real-world coordination. The results show good performance of the proposed algorithm.