German researchers hope to develop robots to unload sea containers
February 1, 2018
A German research project hopes to develop robots that can automatically unload sea containers.
The Iris project is being carried out at the Bremen Institute for Production & Logistics at the University of Bremen (BIBA), with development partners BLG Handelslogistik, Schulz Systemtechnik and imaging company Framos.
They are conducting research on the automated unloading of standard 40ft (12m) containers. In the future, intelligent robots will carry out this difficult and predominantly manual task, automatically.
Germany's Federal Ministry of Transport & Digital Infrastructure (BMVI) is funding the three-year project with €2.2m and TÜV Rheinland is on-board as the sponsor of the project.
Most sea containers shipped worldwide are unloaded and discharged in the port itself. These containers, with a capacity of 65 cubic metres and a payload of 26 metric tons, can hold up to 1800 parcels weighing up to 35kg each. In today's high-tech logistics chains, emptying these standard containers is one of the last remaining non-automated processes.
The high level of complexity, and the challenging loading and unloading scenarios have made fully automated unloading impossible, until now.
The objective of the Iris project is to improve working conditions and make container-handling operations at seaports more efficient. In the very near future, and without changes to the existing infrastructure, a mobile robot will be able to unload these sea containers independently, without manual intervention.
The robot will be equipped with a grappling system that will move autonomously between the gates and drive directly into the container. The robot, equipped with machine learning methods, will independently classify different packing scenarios and use this information to unload the containers in the best way.
Industrial image processing firm Framos is developing methods for the project based on artificial intelligence for the reliable classification of both packing scenarios and the analysis of container contents.
"Object recognition is based on 2D and 3D image data," said Simon Che'Rose, head of engineering at Framos. “It uses state-of-the-art image processing and combines these with machine learning techniques, such as deep learning. 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."
Man-machine interfaces permit simple and agile interactions between robots and employees, in addition to the intuitive monitoring and control of one or more robots. Employees can monitor the robots from a control room at any time, and intervene quickly in the event of a malfunction, even without special programming knowledge. This reduces the risk of costly system downtimes.
A prototype of the Iris project should be completed as early as 2019. It will demonstrate the result of cooperation between human and machine when it comes to unloading shipping containers. Therefore, all development partners of the project are focusing their efforts on relieving the strain on dockworkers, reducing unloading times, and increasing handling capacity and efficiency.
The machine learning technology created by Framos is based on self-learning 3D algorithms and sensor technology. For example, the Iris project uses Intel's RealSense technology. The 3D cameras, depth modules and intelligent algorithms developed by Framos can be transferred to a wide variety of scenarios in all industrial sectors.
The detection, measurement and analysis of scenarios and objects with artificial intelligence and 3D technology supports industrial automation and robotics, quality control, safety and surveillance.