Feature-based visual target following for a nonholonomic wheeled mobile robot with a single camera

Abstract

This paper addresses a visual target following problem for a nonholonomic wheeled mobile robot with a single camera. For the problem, we propose a control scheme composed of vision-based trajectory planning and tracking control. We present on-line trajectory planning based on feature-based visual servoing. The key idea is to compensate the target object motion. In particular we focus on visual feature motion without 3D reconstruction in consideration of the odometry error. Tracking control to the generated trajectory can therefore achieve visual target following precisely even if the target object is moving. The effectiveness of the control system is evaluated experimentally.