Researchers from the CISC project will participate in the 66th ESReDA Seminar, set to take place on May 22-23, 2025, at the University of Salento in Lecce, Italy. This year’s seminar, themed “Transformative Safety and Resilience Models in a Smart Digital and Sustainable World,” will bring together experts, practitioners, and researchers from across Europe to explore innovative approaches to enhancing resilience and safety in critical infrastructure. The CISC researchers will share insights from their latest work, addressing the pressing challenges of safeguarding critical infrastructure in an era defined by rapid digital transformation and increased sustainability demands. 

Collaborative intelligence and Human in the loop for the future of safety critical systems: key lessons learned and future directions 

“Organizations that use machines merely to displace workers through automation will miss the full potential of AI…Tomorrow’s leader will instead be those that embrace collaborative intelligence, transforming their operations, their industries and –no less important-their workforces.”

H.J. Wilson and P.R. Daugherty (Human + Machine: Reimagining Work in the Age of AI Harvard Business Review Press, 2018) 

 The need for human in the loop automation is particularly relevant for safety critical industry where industrial accidents related to technological malfunctioning have been diminishing leaving the human error responsible for up to 80% of the accidents (Stanton et al., 2009). However, even if one of the main aims of introducing automation is often to improve safety by reducing or eliminating human errors; it is often argued that this may simply induce new types of errors. 

To take full advantage of human machine collaboration, companies must understand how humans can most effectively augment machines, how machines can enhance what humans do best, and how to redesign business processes to support the partnership. 

The opportunity is that the proliferation of wearable sensors that can track human factors in a non-intrusive manner coupled with the abilities of modern AI systems to integrate heterogeneous data to identify anomalies and safety critical situation can now transform the role of the human in the loop for safety critical systems also. 

To address this changing and exciting landscape there is a need to consider the followings multidisciplinary aspects:  

1. Capability to understand our own limitation as human being and cope/use them as another element of live data for Industry 4.0 (to understand what aspect of human performance can be assessed and monitored considering the new capabilities offered by Neuroergonomics tool such as EEG and Eye tracking and what can be considered a legitimate and ethical aspect to assess. Whether for mutual performance monitoring in a teaming environment or for also self-monitoring and feedback.) 
2. Capability to harness and analyse live data from for industry 4.0  for control of safety critical process to train new AI algorithms to anticipate safety critical scenarios. 
3. Capability to create novel hybrid collaborative intelligence frameworks to combine the two main key live data sources to support decision and or anticipate critical scenarios in Human-machine Performance optimizations, whereby the human and the intelligent and or autonomous agents can really work as a team. 

During the session, CISC researchers will  briefly present some areas of application and the key challenges and opportunities they raise in terms of function allocation, dependability and overall system performance. In this sense a collaborative intelligent creative gesture is an innovation that required a combined effort from an intelligent, robotic or autonomous agent and a human.  We will conclude a session with an interactive session using pooling system to gather insights and feedback also form the audience.

Agenda:

14:45: Session introduction: Human AI teaming & Collaborative Intelligence for Safety Critical Systems  (Micaela Demichela, Maria Chiara Leva, Ammar Abbas) 

14:45: Analysing” Human-in-the-Loop” for Advances in Process Safety: Key Factors and Lessons Learned in control room scenario (Chidera Winifred Amazu, Joseph Mietkiewicz, Ammar N. Abbas, Andres Alonso Perez, Houda Briwa)  

15:00: Evaluating the Impact of Collaborative Intelligence Technologies on Worker Wellbeing ​in the EU Manufacturing Landscap (Naira López Cañellas) 

15:15: Enhancing Human Capabilities in Painting Defect Detection in automation and decision support system for anomaly detection (Carlos Albarrán Morillo, Doaa Almhaitawi, Devesh Jawla) 

15:30: Using physiological signal to provide insight into mental workload and operators engagement. Use of ML for helping to move towards real time EEG signal feedback (Milos Pusica)

15:45: Exploring Adaptive Human-Robot Collaboration: collaborative intelligence for cobotics and telerobotics (Carlo Caiazzo - co-written with Marija Savkovic, Milos Pusica, Nastasija Nikolic, Ivan Macuzic and Marko Djapan - Aayush Jain, Shakra Mehak, Ines Filipa Ramos) 

16:00: Engaging end user in collaborative intelligence: what are the strength and weakness and opportunities for future applications and research  (Interactive session with online pooling: Maria Chiara Leva, Ammar Abbas, Micaela Demichela, Loredana Bucseneanu)

For participants that want to attend online, registrations are available  via Eventbrite here.

ABOUT THE PROJECT

"Collaborative Intelligence for Safety Critical Systems" (CISC) is a Marie Curie Training Network funded by the European Commission to hire and train Early Stage Researchers (ESR) or PhD student as Collaborative Intelligence Scientists with the expertise and skillset necessary to carry-out the major tasks required to develop a Collaborative Intelligence system

The training to be developed in the network will prepare the ESR for the following tasks:

1. Modelling the dynamics of system behaviours for the production processes, IoT systems, and critical infrastructures (System Safety Engineering);
2. Designing and implementing processes capable of monitoring interactions between automated systems and the humans destined to use them (Human Factors/ Neuroergonomics);
3. Using data analytics and AI to create novel human-in-the-loop automation paradigms to support decision making and/or anticipate critical scenarios;
4. Managing the Legal and Ethical implications in the use of physiology-recording wearable sensors and human performance data in AI algorithms.