Shipping containers to be unloaded by vision-equipped robots

Share this on social media:

A collaborative research project between academia and industry is exploring how a combination of imaging, machine learning and robotics could be used to automate the unloading of shipping containers, a currently complex and predominately manual task.

The €2.2 million, three-year, ‘Interactive Robotic System for Unloading of Sea Containers’ (IRiS) project, funded by Germany's Federal Ministry of Transport and Digital Infrastructure, is looking to equip robots with imaging technology, machine learning and an innovative grappling system to enable them to independently classify different packing scenarios and unload shipping containers in the most efficient way possible.

IRiS is being undertaken by imaging firm Framos, as well as the Bremen Institute for Production and Logistics at the University of Bremen (BIBA), BLG Handelslogistik, and Schulz Systemtechnik. The development partners aim to relieve the strain on dockworkers, reduce unloading times, and maximise handling capacity and efficiency.

Framos will develop artificial intelligence methods for both the reliable classification of packing scenarios and the analysis of container contents. The firm’s machine learning technology is based on self-learning 3D algorithms and sensor technology such as Intel's latest RealSense offerings.

‘Object recognition is based on 2D/3D image data. It uses state-of-the-art image processing and combines these with machine learning techniques, such as deep learning,’ explained Dr Simon Che'Rose, Framos’ head of engineering. ‘This allows the system to detect whether a container can be unloaded fully automatically, or whether manual control of the robot is required in special situations. The location and orientation of the contents are analysed fully in advance, allowing optimum planning of the unloading process.’

The majority of sea containers shipped worldwide have a capacity of 65 cubic metres and a payload of 26 metric tons, enabling them to hold up to 1,800 parcels weighing up to 35kg each. In today's high-tech logistics chains, emptying these containers is one of the last remaining non-automated processes. In the near future, however, and without changes to the existing infrastructure, a mobile robot could be able to unload these sea containers independently and without manual intervention.

A prototype of the IRiS project is expected to be completed as early as 2019, and will demonstrate the result of reliable cooperation between man and machine in unloading applications.

Such cooperation is already being trialled by the British online supermarket Ocado, which is experimenting with a prototype collaborative robot designed to support human technicians when maintaining and repairing equipment in the company’s automated warehouses.

Related news

Credit: Nataly Reinch _ Shutterstock.com

27 May 2021

The vision devices use Sony's IMX500 sensor, which is able to run AI algorithms on the chip to provide real-time information about free parking spaces and other transport data

Credit: CEA; metamorworks-shutterstock - 2021/01

25 May 2021

The face recognition imager consumes 10,000 times less energy than a typical camera and processor. CEA-Leti is working with STMicroelectronics on the imager

20 April 2021

The Kria K26 SOM is built on top of the Zynq UltraScale+ MPSoC architecture. It has 4GB of DDR4 memory and 245 IOs for connecting sensors

14 April 2021

The platform integrates the Nvidia Jetson TX2NX module with an edge-to-cloud software stack including AWS Panorama Device SDK

Flir Firefly DL. Credit: Flir

26 March 2021

Customers can create deep learning models using Neurala’s Brain Builder software and then upload these to a Flir Firefly DL camera

02 March 2021

Teledyne e2v and Yumain aim to make AI technology more accessible by addressing challenges associated with AI