FRAMOS Develops Machine Learning Technologies for Shipping Robots

Published: 31 Jan 2018

Shipping container unloadingFRAMOS, a specialist in industrial image processing, has announced that it is developing state-of-the-art methods, such as 3D cameras, depth modules, and intelligent algorithms, for the IRiS artificial intelligence project for the reliable classification of packing scenarios and the analysis of container contents by intelligent robots.

The IRiS project (Interactive Robotic System for Unloading of Sea Containers), being undertaken by FRAMOS, the Bremen Institute for Production und Logistics, and partners BLG Handelslogistik and Schulz Systemtechnik, is conducting research on the automated unloading of standard 40-foot containers. In the future, intelligent robots will carry out this difficult and predominantly manual task automatically. Germany’s Federal Ministry of Transport and Digital Infrastructure (BMVI) is funding the three-year project with 2.2 million euros; and, TÜV Rheinland is on board as sponsor of the project.

The majority of all sea containers shipped worldwide are unloaded and discharged in the port itself. These containers, with a capacity of 65 cubic meters (2295 cft) and a payload of 26 metric tons, can hold up to 1,800 parcels weighing up to 35 kg 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 an innovative 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 possible way.

“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, Head of Engineering at FRAMOS. “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 analyzed 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 task advantage minimizes the risk of costly system downtimes. A prototype of the IRiS project will be completed as early as 2019. It will demonstrate the innovative result of reliable cooperation between man and machine when it comes to unloading shipping containers. Therefore, all development partners of the IRiS project are focusing their efforts on relieving the strain on dockworkers, reducing unloading times, and maximizing handling capacity and efficiency.

The machine learning technology created by FRAMOS is based on self-learning 3D algorithms and innovative sensor technology; for example, the IRiS project employs Intel’s latest 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.

Posted by Mike Ball Mike is our resident technical editor here at Unmanned Systems Technology. Combining his passions for teaching, advanced engineering and all things unmanned, Mike keeps a watchful eye over everything related to the unmanned technical sector. With over 10 years’ experience in the unmanned field and a degree in engineering, Mike’s been heading up our technical team here for the last 8 years.