3D vision-guided robot solutions provider Pickit was facing the challenge of providing a robot that was able to pick smaller and more difficult parts during automated picking. At the same time, the robot also had to keep up with the required shorter cycle times and quicker part detection rates.
At the time, Pickit had only released two products on the market. Pickit L, which was for picking large objects from pallets and bins. And Pickit M, for picking medium-sized items from bins, boxes, and tables.
To meet the market demand for a means to pick smaller and more difficult items, Pickit needed a more capable 3D camera, which is where the Zivid One+ Medium camera came in.
About Pickit
Pickit was founded in Leuven, Belgium in 2016. It is a plug-and-play vision-guided robot solutions provider that first emerged as a spin-out from Intermodalics with the desire to help simplify the manufacturing automation process for companies.
It took only three years for Pickit to release its first plug-and-play product. The company’s products can be used on a variety of applications, as Pickit combines a 3D camera and 3D vision software, pre-installed on an industrial processor. Pickit’s award-winning technology has successfully simplified robot vision software and made the technology more accessible with less training required.
The development of the Pickit M-HD
After extensive research, Pickit chose the Zivid One+ Medium camera for its new product, the Pickit M-HD. The robot was designed to fill the gap in Pickit's product offering, with the release focusing on the picking of smaller, more complex parts.
“Zivid One+ Medium proved itself more than capable of providing the optical performance we needed. In terms of signal-to-noise ratio, its colour acquisition and image resolution, it really is best in class. Importantly, it has helped ensure we keep our promise to provide off-the-shelf machine vision robots that are both ultra-reliable and very easy to use,” said Peter Soetens, CEO of Pickit.
He continued, “Combining a new high-speed rack-mounted processor unit, upgraded state-of-the-art machine vision software and Zivid’s high-definition 3D camera, Pickit’s third ground-breaking product has succeeded in attracting an even broader audience to applying easy-to-teach robots in smaller, more flexible, collaborative robot cells.”
While the Zivid camera is based on the structured light measurement technique, similar to other 3D cameras Pickit had already utilised, it provides 1.25x faster detections, 30x more accuracy, and detects 10x smaller objects, compared to its counterparts. The measurement technique also allows the avoidance of time-domain and spatial-domain technical limitations.
Zivid One+ Key Facts
- The Zivid One+ Medium 3D camera is based on the structured light measurement technique.
- The camera is supported by Zivid Studio, the company's free user interface which displays the actual 3D image, point cloud, and height map direct from the camera.
- Additionally, the camera also features preconfigured APIs which provide an interface for most machine vision software, operating systems, and programming languages including C++, C#, and .NET.
- To optimise Zivid's camera, Picket incorporated a 2.0 rack-mounted processor, a separate GTX graphics card, and a 20% faster CPU into its Picket M-HD product.
How the Pickit M-HD impacted the market
The Belgium company's latest vision-guided robot, the Pickit M-HD, is 30 times more accurate and 25% quicker than its predecessors, whilst being able to detect parts that are 10 times smaller.
The robot works by following this three-step process:
- The Zivid One+ Medium 3D camera shows the object(s) to be picked, then the gripper tool will proceed with the picking.
- The Picket M-HD is told both the location of the picking bin and the best way to grip the object.
- When it's time to move on to picking the next part, the robot will evaluate the best object to pick next, ensuring that it avoids collisions and obstacles.
The Pickit M-HD combines the Zivid One+ Medium 3D camera with a high-speed rack-mounted processor unit and upgraded machine vision software, to attract a wider audience who are looking for smaller and more flexible robot cells.
“We aim to remain ‘best in breed’ in the whole area of automated pick-and-place and we believe that the introduction of the Pickit M-HD helps us achieve that,” said Soetens. “We do need to be mindful though of even greater challenges ahead, as manufacturers release the true benefits to be gained from even wider application of machine vision and safe artificial intelligence.”
He continued, “Optimised picking needs to be matched in performance terms by optimised placing for example, and so there’s plenty of scope yet for machine vision robots to make further improvements in this regard and achieve even faster overall cycle times. Solving complex manufacturing problems, which in turn improves the quality of workers’ lives, is a worthy objective for us all. Smarter, more human-friendly machine vision-guided robots will continue to help us do just that.”