- Register

 
 

Home >Vision of a software-driven future
ARTICLE

Vision of a software-driven future

11 October 2019

Nearly two years ago, CDA predicted that it would soon be commonplace to download a ready-made “App” to program and configure a smart vision sensor, perfect for a specific application. Now that prediction is coming true. And machine-builders and systems integrators, in particular, are starting to reap the rewards

SICK’s groundbreaking AppSpace software development platform is reaching maturity. While, it can, and will, be a model that could be applied to all kinds of smart sensor, it offers the tantalising prospect of being a game-changer to demystify and democratise the field of machine vision, and 3D vision in particular.

SICK has rolled out more AppSpace-compatible smart vision cameras, with high-resolution and powerful on-board processing. At the same time, a growing ‘basket’ of Apps is being developed both by SICK’s own R&D teams, as well as by specialist market-focused integrators.

It might seem curious for a sensor company to be taking the lead in the field of software. Yet, according to SICK, once sensors become smart and programmable, it makes perfect sense. SICK believes advances in hardware have prompted a change of paradigm in software and systems delivery that points the way towards greater accessibility and ease-of-use for both designers and end-users, as well as the opportunity to offer customers complete solutions. 

advances in hardware have prompted a change of paradigm in software and systems delivery

It’s not surprising that machine vision has been an early focus for developers, says Neil Sandhu, SICK’s UK product manager for Imaging, Measurement, and Ranging. “Machine vision has historically required specialist programming expertise with expensive systems, huge processing power and bulky complex hardware. AppSpace offers more flexibility for vision engineers and programmers because they can customise a SICK camera or sensor for themselves, with full access to standard image libraries such as Halcon.

“Rather than having to use pre-developed proprietary software, AppSpace’s open software platform enables system integrators and machinebuilders to develop and share their own tailor-made solutions.

“The AppSpace concept means you simply pull down an application onto the camera and configure it through an easy to use web-based graphical user interface,” explains Sandhu. “So, it can be virtually plug and play.”

What is AppSpace?

Using SICK AppStudio, developers can create customer-specific applications and use the SICK AppManager to import Apps into the sensor and adapt it to the task in hand. The SICK AppPool cloud service makes it easy to install, manage and download sensor Apps to programmable SICK devices anywhere in the world.

This is all being made possible by greater accessibility to ‘all-in-one’ intelligent vision sensors, such as SICK’s fully-programmable TrispectorP1000 3D vision camera. As a compact, stand-alone, programmable 3D camera, SICK TriSpectorP 1000 masters on-board evaluation and processing of dimension, volume and true shape data in mm. 

Robot guidance

Using the SICK TriSpectorP 1000 enables reliable, continuous in-line product detection that can be easily customised for robotic belt picking applications, for example. Height-based profiling of products on a moving conveyor ensures gentle and efficient robot picking, whatever the shape of the product or colour of the pack design, even where there is minimal contrast or colour difference between the product and the belt background.

The SICK TriSpector P1000 is available either as a stand-alone unit for customised programming or supported by the SICK Belt Pick Toolkit App. The SICK Trispector P Beltpick is a complete vision-guided belt-picking solution for industrial and collaborative robots, developed in AppSpace by SICK. It offers the improved z-axis control available through 3D vision, so products with complex profiles can be picked from variable heights without risk of damage.

Sandhu continues: “We are on a mission to demystify vision for robot guidance and simplify its use for a growing number of adopters including the opportunities presented by collaborative robots and ‘cobots’.

“In a typical cobot application developed in AppSpace, a single camera with an app, talks to the robot.  It can be ‘trained’ to find a shape of a part or product, tell the robot how to pick it up and where to place it, very accurately.  Critically, the camera talks directly to the robot and there is no control system in between.”

Also developed using AppSpace, the SICK PLOC2D is an easy set-up 2D vision system based on the SICK Inspector P vision sensor, combining high-performance image processing with a powerful SICK-developed algorithm to deliver ‘out of the box’ integration with pick and place robots. It can be used for 2D localisation of parts, products or packages to be picked from a static workstation, moving belt, or bowl feeder system and is well suited to handling a variety of small parts.

SICK has collaborated with Universal Robots to develop the SICK Inspector PIM60 URCap, an entry-level vision-guided cobot system that integrates SICK’s Inspector PIM60 2D vision sensors with Universal Robots’ UR3, UR5 or UR10 robots. It is quick and easy to program and configure, without the need for a separate PC or specialist software expertise.

Earlier this year, SICK launched the PLB 520 3D robot-guidance system for bin picking of smaller objects in more confined containers than was previously possible. Now typical tasks such as picking specific small parts like bolts from a deep mixed parts bin and placing them on a conveyor, or selecting part-completed items and placing on a press or machining centre, have become more feasible.

Label inspection

Among the first integrators to successfully exploit the opportunities of SICK AppSpace has been AutoCoding Systems. Their new 4Sight Automatic Print Inspection System is an error-proof solution for high-speed inspection of printed codes such as dates, batch and line numbers.

Operating on SICK’s Inspector P smart camera, AutoCoding’s breakthrough innovation powered in AppSpace has enabled a directly networked connection to any brand of printer using standard inkjet, laser or thermal transfer technologies.

The 4Sight software is able to self-optimise the code inspection process and eliminates the need to teach numerous images and fonts, as well as the context of the surrounding packaging design affecting the inspection. The AutoCoding system knows exactly the printed message it is looking for and adjusts automatically when the printer changes to a new job. There can be no false reads as a result of the packaging background, or due to natural variation in the location of the printed code.

Snapshot vision

In the latest development, an AppSpace programmable version of SICK’s Visionary T 3D imaging cameras is soon to be launched. Using Time-of–Flight (TOF) measurement technology, the Visionary T captures high-resolution real-time 3D images with one shot of light, dispensing with the need to profile a moving object through laser triangulation. 

the Visionary T captures high-resolution real-time 3D images with one shot of light

The Visionary T-AP will be launched with a number of ready-made Apps already available. One is an automated solution for guiding AGV forklifts to pick up pallets.  The Visionary T-AP is mounted on the AGV and integrated with the vehicle’s control system to guide the forks safely into the pallet pockets, reducing the risk of damage or accidents.

“Solutions like the pallet picking application demonstrate the versatility of the AppSpace platform, and the opportunities for system integrators and machinebuilders to provide more flexible, easy-to-use solutions for their customers.”

Key Points

  • SICK has rolled out more AppSpace-compatible smart vision cameras, with high-resolution and powerful on-board processing
  • Using SICK AppStudio, developers can create customer-specific applications and use the SICK AppManager to import Apps into the sensor
  • SICK has collaborated with UR to develop the SICK Inspector PIM60 URCap, an entry-level vision-guided cobot system

 
OTHER ARTICLES IN THIS SECTION
FEATURED SUPPLIERS
 
 
TWITTER FEED