Menu
WE'RE HIRING
Free Demo
BUY NOW
Fizyr_robotic_parcel_sortation

Fizyr

Handling unknown objects in logistics with 3D vision

Quick facts

Company
Fizyr

Application
Parcel sorting
Material handling
Robot guidance
De-palletization
Automated picking

Features
Robot-mounted 3D color vision for robotics
3D color (RGB)
Deep Learning software

3D camera
Zivid Two
Zivid One+

At a glance 

Challenge

Logistics is a high-paced real-time operation with any number of boxes, parcels and packages moving, at speed through logistics facilities. It is a very unpredictable situation with no prior knowledge of what will arrive and need to be sorted and sent on to its destination. These demands necessitate a highly adaptable and intelligent solution that can make decisions and learn as it goes, over time a system understands more of what it sees and becomes even faster at differentiating between items.

Solution

Fizyr are experts in pick and place solutions for the logistics industry. With a solid understanding of the challenges involved. Together with Zivid 3D camera technology they have developed, and deployed systems that are operating at some of the biggest logistics facilities on the planet. This is all about recognition, making a decision, acting correctly on that decision. Fizyr excel at software that can perform this task. But the data into any system will determine its efficacy. That is why they use Zivid 3D vision for robots. With their unparalleled point cloud fidelity in color. They are able to depend on what the robot is seeing and make informed decisions about automated picking and sorting.

Result

Fizyr solutions are being used extensively in some of the largest, fastest-moving picking and sorting operations on the globe. Fizyr detection and picking software, together with Zivid's machine vision cameras are proving themselves each and everyday making rapid decisions with a first-time-right solution essential for such a demanding application.

 

Fizyr’s software product enables the automated picking and 3D stacking of unknown items and parcels in real-life logistics environments. Accurate point clouds are necessary in order for picking robots to move robustly and efficiently. This is why we rely on Zivid’s high-quality robot vision cameras, that can reliably deliver the accurate and detailed point clouds that our deep-learning algorithms require."

Herbert ten Have, CEO of Fizyr

Schedule a Zivid demo

01 Story

The logistics industry is the backbone of our modern world. It is a marvel of complexity and efficiency. Today, packages and boxes can ship door to door, from Memphis to Mumbai in a few days, it is an astonishing feat. Beneath the convenience and satisfaction that this just in time world brings is a deeply complex array of systems and processes that work together to make it happen.

Fizyr software is an example one of these elements that help glue the supply chain together. They were originally founded by Professor Martijn Wisse as Delft Robotics in 2014, as a system integrator for robotic picking and material handling cells. With a strong track record in the then nascent field of deep learning they won the prestigious Amazon Picking Challenge, not once, but twice.

The year was 2017 and saw Delft Robotics re-brand as Fizyr (meaning: rifle scope) and pivot towards the future of computer vision systems augmented with deep learning intelligence, essentially the brains of the new era of robotics. They knew such systems were going to be an essential part of the future of intelligent automated logistics.

 

02 Challenges

Logistics is unlike many other robotics applications in that rarely will packages or objects look the same in a picking warehouse. In an industrial bin-picking situation you will often have a bin full of the same parts and this presents an easier task in terms of object detection, material handling and recognition. It is this huge variety and variability that led Fizyr to understand deep learning techniques were likely the only way to address the challenge. In a system where unpredictability is so high such as a parcel sorting center only an intelligent system that becomes smarter by the day, indeed by the hour can step up to the challenge and be successful.

Fizyr_robotic_parcel_sortation

“Fizyr’s software product enables the automated picking and 3D stacking of unknown items and parcels in real-life logistics environments. Accurate point clouds are necessary in order for picking robots to move robustly and efficiently. This is why we rely on Zivid’s high-quality cameras, that can reliably deliver the accurate and detailed point clouds that our deep-learning algorithms require.

Herbert ten Have
CEO of Fizyr

03 Solution

Fizyr is a pure-play software company. Zivid is a pure-play 3D camera company. This created a perfect opportunity to develop truly ground-breaking solutions for automated logistics without conflict or compromise. Fizyr take the very high-quality point clouds that Zivid 3D cameras deliver and then feed them into their ‘brains’ software. As anyone who has worked in the field of deep learning knows the quality of your input data is amongst your very highest priorities, and this is what Zivid 3D vision brings to the party. Fizyr from there do a lot of clever work around detection and segmentation to understand scenes, pick poses, the gaps between tightly stacked boxes, all the things that are a challenge in robotic picking solutions for logistics.

Label Detection Fizyr

04 Result

Fizyr has already earned a reputation in the logistics automation world as having a best-in-class solution that performs reliably and at speed. And speed matters in logistics, Fizyr have developed a system that is sophisticated and capable yet can make accurate decisions in under 300 milliseconds. System integrators deploying automated logistics solutions around the world are choosing Fizyr software when speed, accuracy and reliability really matters. We are proud that Fizyr choose Zivid when the very best solution is necessary.

Schedule a Zivid demo

 

About Fizyr

Fizyr deliver the brains for robots in logistics. They began life as Delft robotics supplying robotic automated solutions. Since 2017 as Fizyr they are focused on the software solutions that leverage their expertise in deep learning techniques with the focus on logistic applications. They are based in Delft, the Netherlands.

→ fizyr.com

Zivid Two cameras

Contact Sales

Read more

Case Studies →

Watch more

Videos →

Browse

Point Clouds →

Share the story!