By clicking “Accept,” you agree to the storing of cookies on your device to enhance site navigation, analyze site usage, and assist in our marketing efforts. View our privacy policy for more information.

Wine Glass Picking

MIRAI Case Study

The Task and its Challenges

The task involves a collaborative robot picking wine glasses individually from an unsorted collection and placing each glass on a side table. It is inspired from an actual application at a workstation in a German production facility, where a human operator handpicks wine glasses from a semi-sorted stack and sets them on a moving conveyor belt. This tasks brings three main challenges for a robot:

  • How to find each unpredictably positioned wine glass.
  • How to approach and grab a single wine glass that is translucent and hard to differentiate in a small forest of other glasses.
  • How to handle reflections thrown off the glass, producing additional imagery that a robot must make sense of in order to complete the task.

Classic automation solutions — with or without vision systems — would be either unable to deal with these complexities or very expensive to set up. Even then they would be tailored for this task alone and no others.

The Solution

MIRAI is a vision-based robot control system from Micropsi Industries that, using artificial intelligence, enables robots to deal with complexity in production that would be otherwise impossible or extremely difficult to get around with hand-engineered solutions, prohibitively expensive as well. MIRAI attaches to and augments industrial robots. Once fitted with MIRAI, a robot can perceive its workspace and correct its movement where needed as it performs a task. MIRAI can be easily and quickly trained or retrained for myriad tasks by those with no background in engineering or artificial intelligence.

Compared with other available automation solutions, MIRAI makes it possible for:

  • Industrial robots to deal with all the variance that crops up in production.
  • Workers to use machine vision out of the box. They can set up the system and train a skill in only a few hours.
  • Workers without expert knowledge in robotics programming or artificial intelligence to train robots.

When deployed for a task, the MIRAI system kicks in when needed for a complex step or steps in an application process.

Book a Demo

Would you like to schedule a free MIRAI demo? Want to learn more about the system and what it can do for your operation? Talk to one of our automation experts.

Contact us

The Solution Setup

The solution setup comprises the MIRAI system (including the control box and the camera), a Universal Robots UR5, an OnRobot force-torque sensor, a Robotiq gripper, and a ring light (see the marked-up image below).

What follows are the five process steps (see the illustration to the right). Four of the five steps are governed by the robot’s native control system, while the MIRAI control system takes over during the picking step (step 2).

  • Positioning (UR5 native controller): The robot positions the gripper in front of the semi-sorted wine glasses.
  • Picking (MIRAI controller): The robot — in real-time, using camera vision — identifies and approaches a single glass.
  • Positioning (UR5 native controller): The robot grips the glass by its stem, pulls back, and swings its arm toward the side table.
  • Placing (UR5 native controller): The robot places the glass on the side table.
  • Return (UR5 native controller): The robot returns to step 1.

A MIRAI Controller
B Universal Robots UR5
C OnRobot Force-Torque Sensor
D Robotiq Gripper
E Ximea xiQ USB3 camera
F Effilux ring-light

Return on Investment

The return on investment for this solution (MIRAI plus a collaborative robot) is less than one year. This particular scenario assumes a standard robot cell, a two-shift operation, and a cost of €43,200 for each factory worker.

Book a Demo

Would you like to schedule a free MIRAI demo? Want to learn more about the system and what it can do for your operation? Talk to one of our automation experts.

Contact us