Obstacle avoidance of legged robot without 3D reconstruction of the surroundings

Abstract

An obstacle detection and avoidance system that uses a stereo pair of cameras but needs no 3D reconstruction of the surroundings is described. The system is designed for a challenging mobile platform: a legged robot, whose locomotion is not as smooth as the wheeled robots' and thus induces more disturbance to the visual data. The concept of the image-to-image mapping named homography induced by the ground is exploited for detecting obstacles. The described system takes advantage of the fact that obstacles are not on the ground and thus their projections in the images would not agree with such a mapping. Such a homography is allowed to change over time as the legged motion takes place. Obstacles can thus be detected in terms of a 2D distribution on the ground we call the local obstacle map (LOM). Based on the LOM which is further time-delay compensated, a fuzzy control mechanism is then used to command the robot motion. Experiments show that the system is effective for avoiding walls, making turns at corners, and withdrawing from dead-ends during navigation in textured environments, in real-time.