Community Research and Development Information Service - CORDIS

H2020

Robolution Report Summary

Project ID: 673690

Periodic Reporting for period 1 - Robolution (Robotic Recycling Revolution)

Reporting period: 2015-07-01 to 2016-03-31

Summary of the context and overall objectives of the project

The increasing scarcity for raw materials, growingly strict regulations and social pressure have turned waste into a resource, making recycling highly attractive. This has created a major market opportunity for new technologies that achieve high purity of sorted materials at a low cost. ZenRobotics Ltd has developed a robotic waste sorting system ZenRobotics Recycler (ZRR) that has the potential to revolutionise waste sorting, replacing low-performing hazardous manual jobs with highly efficient and fast autonomous robotic pickers. Unlike traditional recycling machinery that is based on mechanic and electric components, ZRR is powered by artificial intelligence. It is also the first commercially available robotic waste sorting system which offers one system for multiple tasks.
The key innovation of ZRR is a unique machine-learning based system, which gathers huge amounts of data of its environment, makes smart decisions and moves a robot arm in an unpredictable environment. Given the novelty of the technology, a paradigm shift is necessary in waste management for wide uptake of ZRR.
The general objective of the Robolution project is to revolutionise waste sorting by developing the ZRR prototype into a reliable and commercially attractive robotic sorting system for Commercial and Industrial waste that outperforms all existing sorting technologies in terms of picking speed, purity of sorted materials and investment requirements.
The project focuses on:
• Robot motion control to be able sort faster smaller objects and pick larger and heavier objects.
• Recognition to detect new fractions (plastics, ferrous/non-ferrous metals) with 95% purity and recovery.
• Development of the reporting tool enabling optimization within a waste sorting plant.
• Optimization of the ZRR commissioning and service to shorten time-to-market time.
• Testing and demonstration of the new functionality in real life conditions.
ZenRobotics targets the global waste sorting equipment market currently worth about €1.5-3 billion annually, but thanks to technological advances, the market is likely to explode. The expected annual turnover of the Commercial and Industrial waste ZRR reaches €150 million by 2021.

Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far

The project consists of five technical as well as communication, exploitation and dissemination and management work packages (WPs) that run in parallel to all activities. All WPs started in month 1 of the project and continue till the end, i.e. by month 18.

WP1 Robot motion control
We are progressing well towards optimizing the robot motion control for increased performance and higher versatility for handling new waste types. Operating cost has been optimized. Accuracy of securely grabbing objects and disposing them to the correct chute remains very high. The deliverable D1.2 Movement control is nearly completed.

WP2 New Fractions and Recognition Performance
The objective of this work package is to significantly enhance the material recognition capabilities of ZRR considering the need of our customers. As a result of our robot training we managed to reduce the time required for learning a new fraction from 2 weeks to one day, and later during 2016 to a few hours. The robot was tested to recognize the mixed plastics, plastic pipes, cardboard, plastic bags, limestone, various kinds of bricks and at least six sub-categories of different wood

WP3 Reporting Tool and Object Real-time Weighing
The objective of this work package is to deliver better automated reporting of how well the system performs. During the period we have released on-line reporting tool for our customers. We continue work towards the object real-time weighing.

WP4 ZRR System Commissioning and Service and pre-processing of the ZRR Waste Stream
The objective of this work package is scaling up the number of customer deliveries we are able to perform. We have managed to decrease the time required to set up robot for shipment to a customer from 8 working days to 2 working days.

WP5 Testing
The objective of the work package is to test the new features and prototypes in operational environment. We perform our test with customer waste samples at Viikki and rehearsing the commissioning process at our manufacturing partner's site in Tampere. Given the overall iterative methodology, the feedback obtained from the testing is vital for the success of the project.

WP6 Communication, exploitation and dissemination
Efforts under WP6 during the reporting period include various bigger and smaller demonstration, exploitation and communication activities with the aim to address our main target groups: waste recyclers, stakeholders, policy makers. This has been done mostly at the relevant events (fairs, conferences, etc.) as well as via online media channels. We have attended many events, have constant newsfeed on social media as well as published on article.

WP7 Project management
As ROBOLUTION project is coordinated and consists of solely one beneficiary – ZenRobotics, the management of the first period was smooth, natural and ran inevitable. All involved persons worked closely together for the same purpose.
Regarding to the everyday management the whole team has regular, mostly face-to face communication with each other. As ZenRobotics is the only beneficiary there has been no CA signed, but the project manager kept an eye on the work plan and timing of activities. As soon as there was any input needed from others to go on, this information has been asked and provided in all cases. Also planned periodic reporting enabled the coordinator to keep track of the administrative matters and to overcome the possible obstacles and do the plans for the upcoming months.

Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far)

Both the new material recognition capability and robot motion control rely on applying cutting-edge machine learning algorithms (e.g. deep learning neural networks).
As part of WP1, company submitted an academic paper to the IROS conference (2016 IEEE/RSJ International Conference on Intelligent Robots and Systems, www.iros2016.org). The subject matter is a robot which autonomously learns to sort objects of different color.
Currently, the main obstacle in adopting robots for tedious or hazardous work is that the cost of installation and supporting infrastructure is approximately an order of magnitude greater than the cost of robot itself . Impact of robots autonomously learning to perform manipulation tasks greatly reduces this auxiliary cost of applying robots. This will dramatically lower the adoption threshold of robots for SMEs.

Related information

Record Number: 190164 / Last updated on: 2016-11-09
Follow us on: RSS Facebook Twitter YouTube Managed by the EU Publications Office Top