A Robot Obstacle Avoidance Method Using Merged CNN Framework
Nai-Hsiang Chang, Yi-Hsing Chien, Hsin‐Han Chiang, Wei‐Yen Wang, Chen-Chien James Hsu · 2019
In this paper, a merged convolution neural network (CNN) framework is proposed to automatically avoid obstacles. Although there are many methods for avoiding obstacles, previous methods mostly contain high energy-consuming and high cost. This paper aims to realize an image-based method with a monocular webcam. The experimental results illustrate that the proposed method can effectively avoid obstacles in mobile robot navigation.