Data-Driven Object Pose Estimation in a Practical Bin-Picking Application

Abstract

This paper addresses the problem of pose estimation from 2D images for textureless industrial metallic parts for a semistructured bin-picking task. The appearance of metallic reflective parts is highly dependent on the camera viewing direction, as well as the distribution of light on the object, making conventional vision-based methods unsuitable for the task. We propose a solution using direct light at a fixed position to the camera, mounted directly on the robot’s gripper, that allows us to take advantage of the reflective properties of the manipulated object. We propose a data-driven approach based on convolutional neural networks (CNN), without the need for a hard-coded geometry of the manipulated object. The solution was modified for an industrial application and extensively tested in a real factory. Our solution uses a cheap 2D camera and allows for a semi-automatic data-gathering process on-site.

Multiple-Object Grasping Using a Multiple-Suction-Cup Vacuum Gripper in Cluttered Scenes

“…Mantriota [33] analyzed the suction force and friction coefficient to grasp and hold a large object with a four-cup vacuum gripper. Kozák [34] et al used a deep neural network to estimate the pose of a round part and then used a six-cup vacuum gripper to grasp it. Tanaka et al [35] designed a two-surface vacuum gripper in which each surface was equipped with multiple cups.…”

Bin picking: a review of recent developments

“…Highly reflective parts such as metal components pose difficulties for conventional vision-based methods as their appearance is highly dependent on the camera viewing angle and key geometrical features are frequently unclear. This problem has been addressed in a system developed by a group from the Czech Technical University (Kozák et al , 2021). This comprises a simple and inexpensive 2D camera and an annular, LED-based light source, both mounted directly on the robot’s gripper which is equipped with six vacuum suction cups with integrated springs, allowing a 20 mm compression (Figure 5).…”

Object Detection and Pose Estimation with RGB-D Camera for Supporting Robotic Bin-Picking

“…This issue is due to the camera's limitations, which can only capture objects in 2D. The 2D camera has been used by (Kozák et al, 2021) in their research on object detection and poses estimation. (Kozák et al, 2021) combined feature description with a Convolutional Neural Network (CNN) to process 2D data.…”

“…The 2D camera has been used by (Kozák et al, 2021) in their research on object detection and poses estimation. (Kozák et al, 2021) combined feature description with a Convolutional Neural Network (CNN) to process 2D data. The feature description is used to segment objects, while CNN is used as a pose estimator.…”