Image-Based Visual Servoing for Nonholonomic Mobile Robots Using Epipolar Geometry

Abstract

Abstract-We present an image-based visual servoing strategy for nonholonomic mobile robot equipped with a central catadioptric camera. This kind of vision sensor combines lens and mirrors to enlarge the field of view. The proposed approach, which exploits the epipolar geometry defined by the current and the desired camera views, does not need any knowledge of the 3-D scene geometry. The control scheme is divided in two steps. In the first one, the epipoles are used used together with an approximate input-output linearizing feedback to align the robot with the goal. Feature points are then used in the second translation step to reach the desired configuration. Global asymptotic convergence is proven. Simulation and experimental results show the effectiveness of the proposed control scheme.

Visual navigation with obstacle avoidance

“…Visual servoing is a well known method that uses vision directly in the control loop, and that has been applied on mobile robots in [7 -9]. In [7] and [8], the epipoles are exploited to drive a nonholonomic robot to a desired configuration. Trajectory tracking is tackled in [9] by merging differential flatness and predictive control.…”

On-board and Ground Visual Pose Estimation Techniques for UAV Control

“…Additionally, in other successful works, it has been demonstrated that the visual information can be used in tasks such as servoing and guiding of robot manipulators and mobile robots [7,8] combining the image processing and control techniques in such a way that the visual information is used within the control loop. This área, known as Visual Servoing [9], is used in this paper to take advantage of the variety of information that can be recovered by a visión system and use it directly in the UAV control loop.…”

Coarsely calibrated visual servoing of a mobile robot using a catadioptric vision system

“…To keep a robot on a desired or predefined path, a homography between the reference and the current image can be used to define adequate visual features for navigation [2]. It is also possible to exploit the epipolar geometry between the reference and the current image to drive the robot to a desired position [3]. An image memory can be used to guide the robot on a pretaught path [4].…”

“…The set decouples the control of the robot rotation from the robot translation. Although the proposed set does not control the pose of the robot, the set enables a simple pure rotation of the robot around its inertia axis which is not the case of the epipolar geometry-based control method proposed in [3]. In Section IV, using the selected set of features, a classical control law is shown to be robust in the presence of point range errors.…”