Adaptive Visual Trajectory Tracking of Nonholonomic Mobile Robots based on Trifocal Tensor

This paper presents a trifocal tensor based approach for the visual trajectory tracking task of a nonholonomic mobile robot, which is equipped with a roughly installed monocular camera. A set of pre-recorded images are used to express the desired trajectory, and the robot is regulated to track the desired trajectory using visual feedback. Trifocal tensor is exploited to obtain the orientation and scaled position information, which is used in the control system. Conventional methods require that there exist enough corresponding feature points in the start, current and final images, while this requirement can be easily violated in large workspace, especially for perspective cameras with limited field of view. In this paper, key frame strategy is proposed to loosen this requirement, extending the workspace of the system. Considering the unknown depth and extrinsic parameters, an adaptive controller is developed based on Lyapunov methods. Simulation results are provided to show the effectiveness of the proposed approach.