Visual Servoing Based on 3D Features: Design and Implementation for Robotic Insertion Tasks

TL;DR

This paper introduces a feature-based visual servoing method for robotic insertion tasks that uses 3D features and a simplified Jacobian calculation, improving accuracy and safety in industrial robot applications.

Contribution

It presents a novel feature-based visual servoing approach utilizing 3D features and an easily computed Jacobian, enhancing insertion task precision and robustness.

Findings

Successful implementation on industrial robots

Improved accuracy in hole insertion tasks

Effective handling of robot velocity constraints

Abstract

This paper proposes a feature-based Visual Servoing (VS) method for insertion task skills. A camera mounted on the robot's end-effector provides the pose relative to a cylinder (hole), allowing a contact-free and damage-free search of the hole and avoiding uncertainties emerging when the pose is computed via robot kinematics. Two points located on the hole's principal axis and three mutually orthogonal planes defining the flange's reference frame are associated with the pose of the hole and the flange, respectively. The proposed VS drives to zero the distance between the two points and the three planes aligning the robot's flange with the hole's direction. Compared with conventional VS where the Jacobian is difficult to compute in practice, the proposed featured-based uses a Jacobian easily calculated from the measured hole pose. Furthermore, the feature-based VS design considers the robot's maximum cartesian velocity. The VS method is implemented in an industrial robot and the experimental results support its usefulness.