A controller for reaching and unveiling a partially occluded object of interest with an eye-in-hand robot

TL;DR

This paper presents a control scheme for an eye-in-hand robot to approach and unveil partially occluded objects using only point cloud data from an in-hand camera, demonstrated on a grapevine setup.

Contribution

It introduces a novel control method that enables a robot to progressively unveil an object of interest based solely on classified point cloud data.

Findings

Successfully approaches and unveils objects in simulation and real experiments.

Achieves progressive unveiling of the object of interest.

Effective in a grapevine stem unveiling scenario.

Abstract

In this work, a control scheme for approaching and unveiling a partially occluded object of interest is proposed.The control scheme is based only on the classified point cloud obtained by the in-hand camera attached to the robot's end effector. It is shown that the proposed controller reaches in the vicinity of the object progressively unveiling the neighborhood of each visible point of the object of interest. It can therefore potentially achieve the complete unveiling of the object. The proposed control scheme is evaluated through simulations and experiments with a UR5e robot with an in-hand RealSense camera on a mock-up vine setup for unveiling the stem of a grape.