Adaptive Visual Servoing Control Barrier Function of Robotic Manipulators with Uncalibrated Camera
Jianing Zhao, Mingyang Feng, Yuepeng Zhang, Siqi Wang, Xiang Yin
Abstract
This paper investigates the problem of safe visual servoing control of manipulators using an uncalibrated eye-in-hand camera based on control barrier functions (CBFs). Traditional CBFs are defined in the workspace, corresponding to the global coordinates of the base frame. However, when the camera’s position or orientation is adjusted for a better field of view, it becomes uncalibrated, making it challenging to obtain the precise positions of the robot and obstacles using onboard sensors like a camera. To address this, we propose a novel visual servoing control barrier function (VS-CBF) for manipulators, which depends only on the image and depth data sensed by an RGB-D camera. Given an uncalibrated camera, we develop an adaptive estimator for the unknown camera parameters. Based on this estimator, we also design a kinematic visual servoing control law as a nominal controller, ensuring the convergence of the robotic system. The safe controller is then obtained by solving a quadratic programming problem that incorporates the designed VS-CBF and the nominal controller. Finally, experimental results conducted on a UR3 manipulator are presented to demonstrate the effectiveness of our approach.
BibTeX
@inproceedings{iros2025_adaptivevisualse,
title = {Adaptive Visual Servoing Control Barrier Function of Robotic Manipulators with Uncalibrated Camera},
author = {Jianing Zhao and Mingyang Feng and Yuepeng Zhang and Siqi Wang and Xiang Yin},
booktitle = {IROS 2025},
year = {2025}
}