IDS 3D vision system helps robots assemble flat-pack furniture

As part of a research project, scientists at Nanyang Technological University, Singapore (NTU Singapore) have developed a robot that can independently assemble the individual components of an IKEA chair without interruption in less than 10 minutes. The robot consists of an Ensenso N35 3D camera from IDS and two robot arms equipped with grippers to pick up objects.

The robot hardware is designed to simulate how people mount objects: the "eyes" are replaced by a 3D camera and the "arms" by industrial robot arms capable of moving in six axes. Each arm is equipped with parallel grippers for picking up objects. Force sensors are attached to the wrists to determine how strongly the "fingers" grip and how strongly they bring objects into contact with each other. The robot starts the assembly process by taking 3D images of the parts lying on the ground to create a map of the estimated positions of the various components. This task is performed by an Ensenso 3D camera from IDS. The camera works according to the "projected texture stereo vision" principle (Stereo Vision), which imitates human vision. Two cameras acquire images from the same scene from two different positions. Although the cameras see the same scene content, there are different object positions according to the cameras' projection rays. Special matching algorithms compare the two images, search for corresponding points and visualise all point displacements in a Disparity Map. The Ensenso software can determine the 3D coordination for each individual image pixel or object point, in this case the chair components.

The challenge is to locate the components as precisely, quickly and reliably as possible in a confusing environment. This is ensured by the Ensenso camera's light-intensive projector. This produces a high-contrast texture on the object surface by using a pattern mask, even under difficult light conditions. The projected texture supplements the weak or non-existent object surface structure found on the components of the IKEA chair.

Although not required for this application, the N35 model used here even goes one step further: thanks to the integrated FlexView projector technology the pattern projected on the object surface of the components can be shifted to vary the texture on the surface. Acquiring multiple image pairs with different textures of the same object scene produces a lot more image points. Thus the components of the chair are displayed in 3D in a much higher resolution to make them easier for the robot to recognise. Another advantage is the robot hand-eye calibration function of the Ensenso software. Using a calibration plate, it ensures that the position of the camera coordinate system (in this case the stationary camera) is determined with respect to the base coordinate system (position of the component). This enables the robot's hand to react precisely to the image information and reaches exactly its destination.

Furniture assembly in less than 10 minutes

Professor Pham Quang Cuong of NTU explains: "For a robot, putting together an IKEA chair with such precision is more complex than it looks. The job of assembly, which may come naturally to humans, has to be broken down into different steps, such as identifying where the different chair parts are, the force required to grip the parts, and making sure the robotic arms move without colliding into each other. Through considerable engineering effort, we developed algorithms that will enable the robot to take the necessary steps to assemble the chair on its own."

The result: the NTU robot installs the "Stefan" chair from Ikea in just 8 minutes and 55 seconds. According to Professor Pham Quang Cuong, artificial intelligence will make the application even more independent and promising in the future: "We are looking to integrate more artificial intelligence into this approach to make the robot more autonomous so it can learn the different steps of assembling a chair through human demonstration or by reading the instruction manual, or even from an image of the assembled product."

The robot developed by the scientists at NTU Singapore is used for research into clever manipulation, an area of robotics that requires precise control of the forces and movements of special robot hands or fingers. This requires perfect interaction of all hardware and software components. 3D image processing using Ensenso stereo 3D cameras is the key to the solution. It convinces not only through accuracy, but also in terms of economy and speed. This marks real progress in furniture assembly - and not only here.

Learn more about the Ensenso N35 3D camera from IDS at www.ids-imaging.com.

IDS Imaging Development Systems

Landmark House
Station Road
Hook
RG27 9HA
UNITED KINGDOM

+44 (0)1256 962910

uksales@ids-imaging.com

www.ids-imaging.com

More from IDS Imaging Development Systems

From smallest housed camera with C-mount over 10GigE to AI

Posted 2 weeks ago

High order intake and promising new products

Posted 1 month ago

Triple vision in quest for excellence

Posted 1 month ago

IDS expands Ensenso 3D camera portfolio

Posted 2 months ago

Drive-through control

Posted 2 months ago

Time to take your pick

Posted 3 months ago

Eyeing up the new uEye sensors

Posted 3 months ago

Engage with image processing experts to ‘Capture the Light’

Posted 4 months ago

Eyes on the uEye XLE models

Posted 4 months ago

It takes a lot of bottle to fight the pandemic

Posted 5 months ago

Precision vision aids productivity

Posted 5 months ago

Making space for additive manufacturing

Posted 7 months ago

Real know-how when picking the unknown

Posted 8 months ago

New industrial vision online channel sees the light of day

Posted 9 months ago

Affordable, compact and powerful new camera family

Posted 10 months ago

New C-Mount lenses bring focus for machine and system builders

Posted 1 year ago

IDS extends Ensenso N3D camera series

Posted 1 year ago

5 megapixels polarisation cameras reveal hidden details

Posted 1 year ago

Learn how to create an intelligent camera

Posted 1 year ago

IDS NXT ocean - unique all-in-one AI-based image processing

Posted 1 year ago

IDS launches industrial cameras with 20 MP Sony sensor

Posted 1 year ago

Modular uEye ACP for developing customised industrial cameras

Posted 1 year ago

Ensenso XR 3D camera family features integrated data processing

Posted 2 years ago

Board-level cameras with liquid lenses and autofocus

Posted 2 years ago

IDS launches more than 100 new models of USB3 Vision camera

Posted 2 years ago

On a voyage of discovery with IDS cameras

Posted 2 years ago

Vision app-based cameras now available from IDS

Posted 2 years ago

Registration opens for IDS UK Industrial Vision Days

Posted 2 years ago

uEye CP camera with high-resolution 12 MP rolling shutter sensor

Posted 2 years ago

Sony sensor: excellent image quality under difficult conditions

Posted 2 years ago

Board-level cameras feature liquid lenses and Active Focus

Posted 2 years ago

IDS achieves sales increase well above industry average

Posted 2 years ago

Self-programmed camera functions meet GenICam standard

Posted 2 years ago

3D vision system creates data twice as fast

Posted 2 years ago

IDS NXT rio and rome industrial cameras are AI-ready

Posted 2 years ago

IDS unveils Ensenso XR 3D camera with onboard processing

Posted 2 years ago

IDS unveils 10 GigE uEye FX high-speed camera with PoE

Posted 2 years ago

IDS strengthens presence in South Korea

Posted 3 years ago

IDS at the world's leading trade fair for machine vision

Posted 3 years ago

New USB 3.1 board-level cameras with liquid lens control

Posted 3 years ago

IDS delivers its millionth camera

Posted 3 years ago

GigE Vision camera firmware 1.5 with new trigger modes

Posted 3 years ago

IDS NXT vegas model with colour sensor and further developments

Posted 3 years ago

3D camera system from IDS wins VSD Award

Posted 3 years ago

App-based industrial cameras now with colour sensors

Posted 3 years ago

EnsensoSDK 2.2 makes 3D image processing even more convenient

Posted 3 years ago

IDS introduces app-based vision sensors and cameras

Posted 3 years ago

See new app-based cameras and 3D cameras at UKIVA event

Posted 3 years ago

uEye Python interface for interactive programming of IDS cameras

Posted 3 years ago

How to simplify the prototyping of embedded vision systems

Posted 3 years ago

Robust 3D camera with IP65/67 for harsh ambient conditions

Posted 3 years ago

Versatile industrial camera with GigE or USB 3.1 Type-C port

Posted 4 years ago

New Gigabit Ethernet industrial cameras with CMOS sensors

Posted 4 years ago

IDS Vision Suite: easy evaluation, setup of GigE Vision cameras

Posted 4 years ago

IDS: successful in the vision market for two decades

Posted 4 years ago

Robust IP65/67 GigE uEye FA industrial cameras with PoE

Posted 4 years ago

IDS presents GigE uEye CP Gigabit Ethernet machine vision camera

Posted 4 years ago

New USB 3.1 Gen 1 cameras with the PYTHON 480 sensor

Posted 4 years ago

3D camera system is easier to implement and more versatile

Posted 4 years ago

IDS highlights embedded vision at UKIVA Conference

Posted 4 years ago

New USB 3.0 industrial camera models with Sony sensors from IDS

Posted 4 years ago

IDS enhances presence in Great Britain and Ireland

Posted 4 years ago

GigE industrial cameras from IDS for use in harsh environments

Posted 4 years ago

IDS adds GigE vision interface support to industrial cameras

Posted 4 years ago

IDS shows new products and developments at VISION show 2016

Posted 5 years ago

First USB 3.1 Gen 1 machine vision cameras with Type-C connector

Posted 5 years ago

IDS Imaging Development Systems among the top 100

Posted 5 years ago

USB 3.0 industrial cameras with next-generation CMOS sensors

Posted 5 years ago

USB 3 uEye XC machine vision camera wins Red Dot Award

Posted 5 years ago

New TechTip: use of sequencer to vary image acquisition settings

Posted 5 years ago

New version 4.80 of the IDS Software Suite available

Posted 5 years ago

New IDS USB3 cameras with fast Python CMOS sensors

Posted 5 years ago

USB 3.0 single-board camera with 18 MP Aptina colour sensor

Posted 5 years ago

Adaptive Vision machine vision software available from IDS in UK

Posted 5 years ago

GigE and USB 3.0 cameras with Sony IMX249 sensor from IDS

Posted 5 years ago

50m cable lengths for USB 3.0 cameras approach GigE capabilities

Posted 5 years ago

High-performance CMOSIS sensors for IDS USB3 industrial cameras

Posted 5 years ago

New lenses extend applications for IDS uEye XC 13 MP USB3 camera

Posted 5 years ago

New robust 3D stereo cameras are sealed to IP65/67

Posted 6 years ago

Daniel Seiler joins IDS management board

Posted 6 years ago

IDS and Stemmer Imaging to end collaboration

Posted 6 years ago

UVC version of USB 3 autofocus industrial camera released by IDS

Posted 6 years ago

IDS to host Future Vision Day in UK on 17 June 2015

Posted 6 years ago

Platform-independent, board-level USB industrial cameras

Posted 6 years ago

IDS pushes forward with CMOS industrial cameras

Posted 6 years ago

New technical note for multicast configuring of IDS GigE cameras

Posted 6 years ago

High-performance CMOS sensors for IDS USB 3.0 CP cameras

Posted 6 years ago

Technical note on new methodology for high-speed imaging

Posted 7 years ago

IDS to launch two new USB 3.0 cameras at VISION 2014

Posted 7 years ago

GigE 3D stereo camera for 3D and robot vision applications

Posted 7 years ago

IDS extends its USB 3.0 camera portfolio with three new families

Posted 7 years ago

GigE industrial cameras with 2.2 and 4.2 MP CMOS sensors

Posted 7 years ago

Ensenso 3D camera makes bin picking easy and cost efficient

Posted 7 years ago

More applications

Login / Sign up