The navigation process of human is quite different from robots. Semantic meaning is what we used to model the environment. One of the most important elements human uses to model the environment is the vision. The keyframes are the elements that human use to model the environment. Therefore, we do not need a specific coordinate to move around. We can only use vision to navigate to anywhere we want to go. To take advantage of the concept that human model the environment, we propose a method which imitates the mapping and navigation process of the human. We will use computer vision to do the mapping of the environment and wayfinding to navigate it. The environment model is created with data collected with an odometer that identifies the obstacles on the route of the robot. Our research proposal is to create an algorithm to avoid obstacles. In this paper, we focus on reviewing existing solutions to address our research problem which is a system mounted on a biped robot navigating indoor environments on its own, without having to use preset routines. We have reviewed existing literature and presented it to help future researchers who had the same goal and could be used as a starting point.