Obstacle avoidance method based on biped robot

Currently, most robots choose the path again to avoid obstacle. This paper proposed a new obstacle avoidance method for biped robots. When lower obstacle exists in the road, this paper will calculate the obstacle´s three-dimensional information instead of using the traditional method of re-select the path, so that the biped robot will avoid obstacles successfully by crossing the obstacle. Calculating the obstacle´s real 3-d information is to 3-d reconstruct the obstacle. In 3-d reconstruction, the stereo matching is complex, and has large time consumption. Therefore, the method of this paper has a combination of color segmentation and height detection, extracts obstacle´s region accurately to reduce detection range of matching, then improves the real-time of reconstruction.