Since the Third Industrial Revolution, robots are commonly used in many industries, including the automotive industry. For safety reasons, these robots operate in cages – as they are programmed to follow the exact same path over and over, no matter what kind of external force is exerted (even if it touches a human co-worker, for instance).
Facilitated by the imec.icon research program, the ‘ClaXon’ project gathered a consortium of researchers and industry experts that developed new insights and technologies to improve the collaboration and interaction between people and robots in industrial production facilities. A first prerequisite for having robots work alongside human operators is the use of compliant (flexible) robots that are equipped with features such as springs to avoid that swaying robot arms hurt people nearby. But this comes at the expense of robots’ accuracy. Hence, ClaXon resulted in new adaptive control software that increases the accuracy of compliant robots by 60 percent.
A second ClaXon research track studied new approaches for humans to communicate – and exchange knowledge – with cobots. This resulted in technology that allows human operators to demonstrate a complex task, after which that task can flexibly be performed by the cobot. Uniquely as well, the cobot recognizes the operators and receives its instructions via gestures.
“Safety and accuracy are crucial for the commercial uptake of cobots in production facilities,” underlines An Jacobs (imec - VUB). “However, the human factor is very important as well – with many social and operational questions to be answered in order to understand how cobots can best support humans in their daily routines. The ClaXon project has started to answer these questions by means of an extensive living lab user study, in which we tested various scenarios with real cobot prototypes and operators, in a real production environment.”
“In our factory we now have a fully operational cobot, working alongside our operators in a very efficient way,” says Patrick Danau, General Director Audi Brussels. “Using multimodal sensors such as heat, depth and color cameras and electrical current sensors, the cobot observes in great detail the operators and the factory environment. Thanks to deep learning technology from Robovision, it can recognize its human co-workers and interpret gestures and movements so that operators can make quick and on-the-fly adaptations to a robot’s actions. Moreover, the cobot has been equipped with a face that is used to communicate with the operators; to acknowledge, for instance, that it has understood a given instruction.”
“Deep learning allows robots to interpret reality and select what is really important; in other words: this no longer needs to be programmed by the software engineer. We believe that this notion will fundamentally reshape the worldwide robotics industry,” adds Jonathan Berte, CEO of Robovision.
“We are at the dawn of the Fourth Industrial Revolution, which is characterized by concepts such as automation, human-computer interaction, the Internet of Things and cloud computing,” comments Luc Van den hove, president and CEO of imec. “It’s a revolution that invites companies to fundamentally rethink their products, processes and business models to deliver greater value. Through ClaXon, Audi has demonstrated that this rethinking opens the door to product optimization and increased efficiency, while laying the foundation for truly ‘smart industries’. Imec is at the forefront of building the technologies – and gathering the insights – that companies require to reinvent themselves and successfully ride the wave of the Fourth Industrial Revolution.”
ClaXon – a research project within the imec.icon program – ran from January 2015 till December 2016. It brought together academic researchers (from imec - EDM - UHasselt, imec - SMIT - VUB and the Robotics & MultiBody Mechanics Research Group of VUB) with a number of industry partners: AMS, Audi Brussels, Melexis Technologies, Robovision and SoftKinetic. The ClaXon project was co-financed by imec (iMinds) and received project support from Flanders Innovation & Entrepreneurship and Innoviris. More info
Imec is the world-leading research and innovation hub in nano-electronics and digital technologies. The combination of our widely acclaimed leadership in microchip technology and profound software and ICT expertise is what makes us unique. By leveraging our world-class infrastructure and local and global ecosystem of partners across a multitude of industries, we create groundbreaking innovation in application domains such as healthcare, smart cities and mobility, logistics and manufacturing, and energy.
As a trusted partner for companies, start-ups and universities we bring together close to 3,500 brilliant minds from over 70 nationalities. Imec is headquartered in Leuven, Belgium and also has distributed R&D groups at a number of Flemish universities, in the Netherlands, Taiwan, USA, China, and offices in India and Japan. In 2015, imec's revenue (P&L) totaled 415 million euro and of iMinds which is integrated in imec as of September 21, 2016 52 million euro. Further information on imec can be found at http://www.imec-int.com/.
Imec is a registered trademark for the activities of IMEC International (a legal entity set up under Belgian law as a "stichting van openbaar nut”), imec Belgium (IMEC vzw supported by the Flemish Government), imec the Netherlands (Stichting IMEC Nederland, part of Holst Centre which is supported by the Dutch Government), imec Taiwan (IMEC Taiwan Co.) and imec China (IMEC Microelectronics (Shanghai) Co. Ltd.) and imec India (Imec India Private Limited), imec Florida (IMEC USA nanoelectronics design center).
The Audi Group, with its brands Audi, Ducati and Lamborghini, is one of the most successful manufacturers of automobiles and motorcycles in the premium segment. It is present in more than 100 markets worldwide and produces at 16 locations in 12 countries. 100 percent subsidiaries of AUDI AG include Audi Sport GmbH (Neckarsulm), Automobili Lamborghini S.p.A. (Sant’Agata Bolognese, Italy) and Ducati Motor Holding S.p.A. (Bologna, Italy).
In 2016, the Audi Group delivered to customers about 1.868 million automobiles of the Audi brand, 3,457 sports cars of the Lamborghini brand and 55,451 motorcycles of the Ducati brand. In the 2016 fiscal year, AUDI AG achieved total revenue of €59.3 billion and an operating profit of €3.1 billion. At present, approximately 88,000 people work for the company all over the world, more than 60,000 of them in Germany. Audi focuses on sustainable products and technologies for the future of mobility.
The Robovision group is specialized in image processing based on artificial intelligence. Worldwide our software is being used in agricultural robots and manufacturing. In 2016 there was a breakthrough driven by overseas growth (USA, Australia, Brazil). With an international team of 12 specialists, located in Gent, Robovision is designing AI systems of the future. In 2016 a turnover of €1M was realized. http://www.robovision.be/