Designed to navigate freely and dynamically amongst a human workforce, TORU operates between regular shelves, picking a wide range of objects.
A ‘pick-by-robot’ solution using a perception-controlled logistic robot called TORU
Frederik Brantner | Magazino
What is Magazino?
Launched in 2014, we’re one of the first companies in the world developing and building perception-controlled, mobile robots, which are designed to navigate freely and dynamically among a human workforce. With our technology, individual objects can be identified on shelves, localised by 2D and 3D cameras, securely grasped, and placed precisely at their desired destination.
How did the idea for founding Magazino first come about?
The idea came to me when I was visiting a friend who just installed an automated storage robot in her pharmacy. I immediately thought something like this would be very useful for organising personal chaos at home. As it turned out, such a machine would be far too expensive for the consumer market, but the idea of a robot who could handle individual and single items, and not just a whole box or tray, was born. After a brainstorming / creative thinking weekend, my friends Nikolas Engelhard and Lukas Zanger joined the enterprise and became my cofounders.
After only a short time of working on TORU, we caught the attention of Siemen’s Novel Businesses investment arm and gained their backing which allows us to continue innovating and elevating our robots to the highest level.
What problem does Magazino seek to address?
Current warehouse picking systems operate under either ‘Man to Goods’ or ‘Goods to Man’ models. The former requires workers to walk to shelving areas and manually pick goods, which has a high dependence on the staff hired, with high salary and processing costs. ‘Goods to Man’ systems address some of these issues by mechanically bringing shelving units to the front of warehouses for goods to be picked. These are typically inflexible in design, difficult to scale beyond initial specifications, and represent a high upfront investment for owners.
At Magazino, we have developed a third ‘pick-by-robot’ solution through its perception-controlled logistic robot, TORU. Designed to navigate freely and dynamically amongst a human workforce, TORU operates between regular shelves, picking a wide range of objects.
What advantages does Magazino's robot, TORU, have over existing warehouse picking systems?
Current warehouse picking systems are typically picking units operating on rails. They use standardised carriers and complete recurring tasks set within very precise parameters. They are highly structured, and operate in static environments with absolutely minimised uncertainty in regard to how items are stacked and where they need to be placed. The obvious downside of such systems is their inflexibility to changing needs, as well as the high upfront cost for owners. Additionally, as the processes for picking in these systems are highly prescribed and predetermined, should there be any failure of any one step then the whole chain is broken and picking stops. Humans are also unable to directly work alongside these systems, as they would create too many variables for the highly structured environments needed, which in the worst cases can lead to industrial accidents.
By contrast, TORU is designed to navigate freely between shelves designed for humans, complementing the regular workforce, and able to operate in and around environments with high levels of uncertainty. TORU’s inherent flexibility allows it to adapt to novel objects, tasks and any warehouse in which it is placed. Its self contained nature makes them easily scalable, from one unit to as many as are required. TORU’s inbuilt task editor, database connectivity, and incorporation of cloud infrastructure makes it easy to adapt to new environments and changing needs as required.
Can you run us through a typical application where TORU is used in a factory operation?
When TORU arrives at its new warehouse, a Magazino employee will create a 3D model of the entire space, including the shelves and tables where it will pick and place items. Next, TORU will drive around the warehouse and create a 2D map of the environment using its laser sensors as a radar; this can then be shared and stored on other robots.
With the interface between the warehouse management system and the robots now established, the orders - that were sent to a human workforce via PC or printed paper list - will be sent to the robot. Once informed, the robot will then plan its route through the warehouse to pick the desired item and deliver it where requested.
When picking, TORU brings his gripper to the right level and looks into the compartment using its camera. Using the cross-laser to adjust itself to the centre of the object, TORU will notice if the item is displaced slightly and adjust its positioning accordingly. Then TORU will measure the dimensions and orientation of the item by analysing the image it sees through the its camera - with this information it will calculate the movements of its gripper before grasping the object and storing it in its internal shelves for transit. TORU can then go on to retrieve further items using the same process before delivering them to their destinations.
What is currently changing in the world of robotics?
The world of robotics is one of the fastest moving industries out there, with robots becoming more and more intelligent each day. Sensors and computer chips are becoming cheaper and providing better performance, new programming languages are being established and evolving, but most importantly, the actions of robots are no longer predetermined at the time of programming and building them. The robots of the new generation are perception driven; they are reacting on behalf of what they sense from their environment, which is particularly interesting when it comes to warehouse robotics as it means that humans and robots are able to work together in a much more succinct and productive fashion.
What does the term Industry 4.0 mean to your business interests and how does it affect the future?
Industry 4.0 signals an exciting time for the industrial sector. From Magazino’s standpoint, we’ll be introducing robots into the working environment to complement the role of the human in a safe manner. The evolution of technology is allowing industry to achieve things faster and smarter - it’s a radical new era.
Where are you finding new markets and in which industries are your primary customers?
TORU has been built for primary use in intralogistics, but can serve everywhere were batchsize one is common. TORU can operate in the warehouse where individual orders are picked manually - this also includes processes in factories where TORU can bring individual objects and components from storage direct to the production line. Early stage customers include DHL and Sigloch.
Is there anything else you would like to talk about here?
TORU currently comes in three distinct formats; TORU Cube, TORU Box, and TORU Flex. While the first two focus on picking individual items from shelves using precision instruments designed to grip and carry box shaped items and other cuboid objects, TORU Flex uses a 6-axis arm with different end-effectors/grippers. E.g. a suction gripper or three articulated digits for complex products (cosmetic products, wrapped clothing, soft objects). With this kind of gripper it’s also possible to retract objects that are not only placed on a plane surface or stacked over each other, but also placed inside a container or box.
The content & opinions in this article are the author’s and do not necessarily represent the views of RoboticsTomorrow
This post does not have any comments. Be the first to leave a comment below.
Post A Comment
You must be logged in before you can post a comment. Login now.