Collaborative Intelligence for Safety Critical systems

Project Information

CISC

Grant agreement ID: 955901

DOI

10.3030/955901

Project closed

EC signature date 13 August 2020

Start date 1 January 2021

End date 30 June 2025

Funded under

• EXCELLENT SCIENCE - Marie Skłodowska-Curie Actions

Total cost

€ 3 605 548,32

EU contribution

€ 3 605 548,32

Coordinated by

TECHNOLOGICAL UNIVERSITY DUBLIN
Ireland

Periodic Reporting for period 2 - CISC (Collaborative Intelligence for Safety Critical systems)

Reporting period: 2023-01-01 to 2025-06-30

Summary of the context and overall objectives of the project

Collaborative Intelligence for Safety Critical systems is core to the European declared 'human-centric' approach to AI that requires a human capital able to prepare for the socio-economic changes brought about by AI. While the ease of collecting and using field data with AI is increasing, few understand the importance of fully considering how to interface AIs with the humans that are supposed to use them in order to realise the anticipated benefits, and even fewer know how to address these new types of human-machine collaboration and their legal and ethical aspects, In Collaborative Intelligent systems, for instance, humans need to perform three crucial roles. They must train machines to perform certain tasks; explain the outcomes of those tasks, especially when the results are counterintuitive or controversial; and they must sustain the responsible use of machines (by, for example, preventing robots from harming humans). On the other side AI can amplify our cognitive strengths such as filter data to provide us with information about the status of a safety critical plant (e.g. distillation column) & suggest possible procedures to cope with plant status upsets. Furthermore AI systems in collaborative robotics (cobotics) can embody human skills to extend our physical capabilities. In these collaborations the end users should not to be subject to a decision based solely on automated processing and there should always be human oversight. The development of Collaborative Intelligence systems requires an interdisciplinary skillset blending expertise in AI with expertise in Human Factors, Neuroergonomics and System Safety Engineering. The CISC training programme developed Collaborative Intelligence Scientists (1) Using data analytics and AI to create novel human-in-the-loop automation paradigms to support decision making and or anticipate critical scenarios; (2) Designing and implementing processes capable of monitoring interactions between automated systems and the humans destined to use them; (3) Modelling the dynamics of system behaviours for the manufacturing process considering System Safety Engineering; (4) Managing the Legal and Ethical implications of AI algorithms, and the use of physiology recording wearable sensors and human performance data in them.

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 has delivered 18 Key Exploitable Results that advance human-robot collaboration, safety-critical decision-making, and cognitive workload management. These include novel methodologies for mental workload reduction (KER1), explainable AI for alarm management (KER18), and no-code platforms for robot programming (KER6), which collectively enhance productivity, safety, and accessibility in industrial settings. Training initiatives like the Level 9 doctorate program (KER2) foster a new generation of experts in collaborative intelligence.The project aimed at empowering SMEs through tools like the Machine State Explanation Tool (KER7) and PbD platforms, reducing reliance on specialized technical labor. It also supports standardization efforts (KER12) and improves operator performance in high-stress environments (KER15), contributing to safer, more efficient workplaces. Specifically, the results of the CISC project are also informing a new draft for the ISO/TC 159/SC4 Woking Draft 9241-812:2023 "Ergonomics of human-system interaction — Guidance on Artificial Intelligent Systems" as the project coordinator was invited as a contributor. Wider implications of the project results include democratizing access to robotics and AI technologies, promoting inclusive workforce development, and enhancing human-machine interaction in safety-critical industries. The datasets and frameworks developed (KER3, KER11, KER17) enable future research and innovation, while the emphasis on human-in-the-loop systems ensures ethical and transparent AI integration. Overall, the project strengthens Europe's leadership in industrial automation and human factors engineering, with lasting benefits for education, industry, and society.

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)

The CISC project had a positive impact on both ESRs and beneficiaries, derived from the collaboration, knowledge and innovation sharing between all members of the consortium. Besides the creation of a long-lasting collaborative network, the academic and research-oriented beneficiaries benefited from the interdisciplinary scientific skills of the ESRs and their beyond-state-of-the-art contributions to the field, while industrial partners obtained tailored technical solutions to specific problems and technology transfer promoted by the ESRs secondments. Some examples include: (1) the application of theoretical knowledge in model latent spaces by ESR 9 to an industrial partner’s (Iveco) practical use case of paint defect detection, (2) the application of several innovative AI models, based on Bayesian networks and deep reinforcement learning, combined with human factor and ergonomic insights to improve alarm management and decision support in near real-life control room simulator, insights obtained by several ESRs that can be exploited by Yokogawa, (3) the collaboration between industrial and academic partners (University of Kragujevac and MBrainTrain) for the application of a mental workload classification model developed with the expertise of MBrainTrain and ESR 6 to a simulated real world environment of manual assembly line workplace, and (4) the application of ethical principles and frameworks during the development of the socio-technical solutions across the beneficiaries, with the expertise of ESR 10.
Moreover, the CISC team members won a Multidisciplinary Research Team Award at The TU Dublin Research and Innovation Awards 2024. The awards and publications are detailed below for each ESR:

As the Collaborative Intelligence for Safety Critical Systems project concludes, we’re proud to reflect on the measurable impact we’ve made. Over the course of the project, collaborative innovation has translated into tangible outcomes across research, development, and real-world application. Below, we highlight some of the key figures that illustrate the breadth and depth of what the CISC consortium has achieved — together.

10 of 14 Early Stage Researchers have successfully completed their PhDs, with the remaining candidates well on track toward completion.
17 partner and associated organizations collaborated across disciplines, sectors, and countries.
3 innovative Live Labs showcased real-world applications of collaborative intelligence in safety-critical systems.
105+ publications shared our research with the global academic community.
100+ citations highlight the growing influence of CISC’s contributions to the field.
Engaged with 5+ key industry players, ensuring our work remained grounded in real-world needs.
4 intensive European Bootcamps delivered hands-on training and fostered cross-sector innovation.
CISC members contributed to over 45 international events and conferences, shaping conversations and leading sessions in the field.
Award-winning impact: CISC researchers were honored with the Multidisciplinary Research Team Award at the TU Dublin Research and Innovation Awards 2024.
more details can be found on:
https://www.ciscproject.eu/2025/07/31/from-vision-to-impact-cisc-project-key-results/

cisc-key-results.jpg

CISC LOGO