Obstacle avoidance is the core problem for mobile robots. Its objective is to allow mobile robots to explore an unknown environment without colliding into other objects. It is the basis for various tasks, e.g. surveillance and rescue, etc. Previous approaches mainly focused on geometric models (such as constructing local cost-maps) which could be regarded as low-level intelligence without any cognitive process. Recently, deep learning has made great breakthroughs in computer vision, especially for recognition and cognitive tasks. It takes advantage of the hierarchical models inspired by human brain structures. However, it is a fact that deep learning, up till now, has seldom been used for controlling and decision making. Inspired by the advantages of deep learning, we take indoor obstacle avoidance as example to show the effectiveness of a hierarchical structure that fuses a convolutional neural network (CNN) with a decision process. It is a highly compact network structure that takes raw depth images as input, and generates control commands as network output, by which a model-less obstacle avoidance behavior is achieved. We test our approach in real-world indoor environments. The new findings and results are reported at the end of the paper. © 2016 IEEE.