New type of voice assistant for production works according to the rules of AI ethics
Successful: COALA project with 14 partners from 5 countries | 5.7 million euros in EU funding | trustworthy use of artificial intelligence also for economic gain
Brussels, Bremen. Quick help even with complex problems: In future, an intelligent voice assistant will be able to help people in production. COALA relies on the trustworthy use of artificial intelligence. The system can support the work, training and knowledge transfer of employees via smartphone or tablet and reduce costs and time. This is the result of the COALA R&D project with 14 partners from 5 nations. In Germany, BIBA - Bremer Institut für Produktion und Logistik and the Institute of Technology and Education (ITB) at the University of Bremen were involved. BIBA was responsible for coordinating the 5.7 million euro EU project.
Unique and trustworthy
Transparency and protection of employees and companies - the use of artificial intelligence (AI) in management and production processes is increasingly raising ethical questions. AI ethics was a key focus of COALA research and development. The COALA project partners are confident that their system is one of Europe's first trustworthy digital voice assistants for the manufacturing industry. They have made the project results available at Zenodo, an open repository that can be used primarily for storing scientific data sets, and at the European AI community via the AI4Europe platform, for example.
The COALA solution is based on the privacy-focussed open assistant Mycroft. Among other things, it enables the rapid generation of data analyses and the provision of information for individual workstations based on the company's complex, distributed data.
The COALA assistant is also supported by a new type of explanatory software, the WHY engine. It enables the assistant to explain its predictions. This enables users to better understand why and on what basis the assistant has given a certain answer.
Benefits for vocational training too
Another important pillar of the project was the successful application of the voice assistant in vocational training. To achieve this, a didactic concept was developed by the Institute of Technology and Education (ITB) at the University of Bremen using the textile industry as an example. The on-the-job training assistant shortens onboarding times for new staff and also supports the transfer of implicit knowledge. A user-defined dialogue model and the cognitive advisor service make it possible to determine the worker's current level of knowledge and advise them on preparing and operating a machine, for example.
Three use cases analysed
The consortium researched and developed three exemplary use cases from the textile, chemical and white goods industries: at the production sites and with data from the project partners Fratelli Piacenza (Italy), Diversey Netherlands Production (Netherlands) and Whirlpool Management EMEA (Italy). The Biella Textile Academy (Italy) was also involved with its wide range of training programmes for skilled workers.
Result: Partly "significant improvements“
Among other things, COALA helps to simplify and speed up training times on machines and systems and to avoid quality problems. According to projections based on the field test at Whirlpool, defects identified with COALA support can be reduced by more than 50 per cent in some cases. Due to a lower number of calls per plant and a lower number of service calls to end customers, the company was also able to achieve a 20 percent reduction in organisational costs in this area with COALA.
In addition, evaluations at CittaStudi (Textile Academy) showed a significant improvement in task performance by 42 per cent compared to the basic scenario without COALA. The COALA assistant implemented at project partner Diversey achieved the highest value in the transfer of implicit knowledge according to the field tests and evaluations, followed by a 30 per cent reduction in the time required to process problems and a 50 per cent reduction in training time.
Key data on the COALA project
The 3-year COALA project (COgnitive Assisted agile manufacturing for a LAbor force supported by trustworthy Artificial Intelligence) involved 14 research and industrial partners from five nations. They come from Italy, the Netherlands, Greece, France and Germany. The consortium, led by BIBA - Bremer Institut für Produktion und Logistik at the University of Bremen, has developed a voice-based digital intelligent assistant for industry that supports workers in production and can be used via smartphone or tablet, for example. A particular focus of the research was on the trustworthy use of artificial intelligence in accordance with the guidelines of AI ethics. The project was funded by the EU with 5.7 million euros.
(Sabine Nollmann)
Further information and contact
www.biba.uni-bremen.de
www.itb.uni-bremen.de
https://zenodo.org/records/8268928
www.ai4europe.eu/ai-community/projects/coala
Prof. Dr.-Ing. habil. Klaus-Dieter Thoben
telephone: +49 421 218-50 005, e-mail: tho@biba.uni-bremen.de
Dipl.-Inform. Karl A. Hribernik
telephone: +49 421 218-50 108, e-mail: hri@biba.uni-bremen.de
Dipl.-Wirtsch.-Ing. Stefan Wellsandt
telephone: +49 421 218-50 166, e-mail: wel@biba.uni-bremen.de
Selection of scientific publications
Wellsandt, S. et al. (2023). Fostering Human-AI Collaboration with Digital Intelligent Assistance in Manufacturing SMEs. In: Alfnes, E., Romsdal, A., Strandhagen, J.O., von Cieminski, G., Romero, D. (eds) Advances in Production Management Systems. Production Management Systems for Responsible Manufacturing, Service, and Logistics Futures. APMS 2023. IFIP Advances in Information and Communication Technology, vol 689. Springer, Cham.
https://doi.org/10.1007/978-3-031-43662-8_46
Samuel Kernan Freire, Evangelos Niforatos, Chaofan Wang, Santiago Ruiz-Arenas, Mina Foosherian, Stefan Wellsandt, and Alessandro Bozzon. 2023. Lessons Learned from Designing and Evaluating CLAICA: A Continuously Learning AI Cognitive Assistant. In Proceedings of the 28th International Conference on Intelligent User Interfaces (IUI '23). Association for Computing Machinery, New York, NY, USA, 553–568.
https://doi.org/10.1145/3581641.3584042
Samuel Kernan Freire, Mina Foosherian, Chaofan Wang, and Evangelos Niforatos. 2023. Harnessing Large Language Models for Cognitive Assistants in Factories. In Proceedings of the 5th International Conference on Conversational User Interfaces (CUI '23). Association for Computing Machinery, New York, NY, USA, Article 44, 1–6.
https://doi.org/10.1145/3571884.3604313
Naumann, J., Foosherian, M. (2022). KI gestützte Weiterbildung von Produktionsfacharbeiter*innen mittels eines Sprachassisstenten: Einsatz von Lernnuggets, IPW - 16. Ingenieurpädagogische Jahrestagung , 14. Mai 2022 , Dortmund.
www.itb.uni-bremen.de/ccm/publications/vortraege/ki-gestuetzte-weiterbildung-von-produktionsfacharbeiterinnen-mittels-eines-sprachassisstenten-einsatz-von-lernnuggets.de
Wellsandt, Stefan; Rusak, Zoltan; Ruiz Arenas, Santiago; Aschenbrenner, Doris; Hribernik, Karl A.; Thoben, Klaus-Dieter: Concept of a Voice-Enabled Digital Assistant for Predictive Maintenance in Manufacturing (2020). TESConf 2020 - 9th International Conference on Through-life Engineering Services
http://dx.doi.org/10.2139/ssrn.3718008
Image selection for the press release
The images are - only with copyright notice! - free for publication. If you have any questions or would like more pictures, please contact
Indah Lengkong, M. Sc. (BIBA)
telephone: 0421 218-50 189
e-mail: len@biba.uni-bremen.de
or
Sabine Nollmann (Wissenschaftskommunikation | kontexta)
telephone: +49 421 330 47 61
mobile: +49 170 904 11 67
e-mail: mail@kontexta.de, pr@biba.uni-bremen.de
You can download the following images and others, together with image references, summarised in print quality as a ZIP file here: 20240304_Pressebilder_COALA.zip (8,6 MB).
COALA use-case-support WHIRLPOOL Foto BIBA-MinaFoosherian.jpg
COALA use-case-support WHIRLPOOL Foto BIBA-MinaFoosherian.jpgApplication studies at Whirlpool Management EMEA (Italy): Extensive tests of the COALA system at the project partner have shown that the use of the intelligent assistant reduces the workload for employees and also has economic relevance. Image: BIBA/Mina FoosherianCOALA Implementation-Cognitive-Assistant Diversey Foto TU-Delft-SamuelKernan.jpg
COALA Implementation-Cognitive-Assistant Diversey Foto TU-Delft-SamuelKernan.jpgDelft University of Technology has used COALA's AI-supported cognitive assistant and on-the-job training in two different use cases: in factories at Diversey (Netherlands) and Fratelli Piacenza (Italy). Image: TU-Delft/Samuel KernCOALA digital-assistant-production test-BIBA Foto BIBA-MinaFoosherian.jpg
COALA digital-assistant-production test-BIBA Foto BIBA-MinaFoosherian.jpgTesting the voice-based digital intelligent assistant in the BIBA Shop Floor Lab. The COALA system was developed for industry. It supports workers in production via smartphone or tablet. Image: BIBA/Mina Foosherian