Enhancing Team Robustness under Stress through XR and Collective Behaviour Analytics

🔬📊

📈 The limits of pure performance

In a constantly evolving world of work, the traditional obsession with pure « performance » is showing its limits. With stress, performance pressure, and the risk of burnout surging, affecting over 28% of workers in Belgium alone (Securex, 2024), we need a paradigm shift. Optimizing a system for peak efficiency can actually make it fragile and rigid when facing unexpected crises (Hamant, 2022). Our research proposes moving away from the « ratchet effect » of endless performance optimization towards the concept of team robustness (Hamant, 2024). Robustness is the capacity of a team to absorb shocks and maintain its essential functions, often by leveraging apparent internal weaknesses or « sub-optimalities » (such as redundancy, hesitation, or informal chatter) as mechanisms for adaptability (Hamant, 2022).

🌐 From individuals to networks

Historically, team success was analyzed through individual attributes like age, gender, or personality traits (Leonardi & Contractor, 2018). However, recent scientific literature demonstrates that relational variables are far stronger predictors of a team’s success in stressful environments. Concepts such as shared mental models (DeChurch & Mesmer-Magnus, 2010), distributed leadership (Lungeanu et al., 2022), and the density of communication networks are essential to understanding how a team coordinates without explicit communication (Bell et al., 2015). By modeling the team as a communication network, we can better understand how information, trust, and resilience flow between members (Leenders et al., 2016).

🎯 Core research objectives

The main objective of this doctoral project is to develop an innovative, integrated scientific model capable of evaluating and enhancing team performance, resilience, and robustness in stressful environments. As a crucial first step, the research will define the emerging concept of team robustness and identify its specific « info-communicational observables ». By moving beyond the traditional performance paradigm, we seek to understand how apparent sub-optimalities (such as redundancy, hesitation, or heterogeneity) sustain collective adaptability. By capturing multimodal data (video, audio, and psychometric signals) during XR immersions and processing it through Social Signal Processing (SSP) and graph theory, we aim to translate these theoretical observables into measurable network variables. Ultimately, this research will elevate our current analytical capabilities, advancing our Technology Readiness Level (TRL) from 2 to 4, allowing us to accurately profile teams and generate concrete, predictive, and evidence-based improvement plans.

📆 The three main phases of the project

2025-2026: Identification of the key variables underlying performance and resilience, based on scientific literature and stakeholder input. Development of initial algorithms and implementation of first experimental tests.

2026-2027: In-depth investigation of the concept of robustness, which remains relatively underexplored in scientific research. Core research question: How can robustness be measured and how can it be improved?

2027-2028: Dynamic modelling of teams to generate semi-automated, personalised recommendations. Development of an initial prototype of a team digital twin.

🤝 Our partners

This PhD project is driven by researcher Audrey Loos and supervised by Professor François Lambotte from the Institute for Language and Communication (ILC) at UCLouvain, alongside Professor Raphaël Jungers from the Information and Communication Technologies, Electronics, and Applied Mathematics institute (ICTEAM) at UCLouvain. The project team is strengthened by experts from Teamersive to ensure effective transfer to real-world applications. This research is proudly co-funded by the Wallonia Region via the Win4Doc program.

#UCLouvain #Teamersive #Win4Doc #TeamRobustness #GraphTheory #SocialSignalProcessing #DataDrivenCoaching

📖 References

Bell, S. T., Brown, S. G., Outland, N. B., & Abben, D. R. (2015). Critical Team Composition Issues for Long-Distance and Long-Duration Space Exploration: A Literature Review, an Operational Assessment, and Recommendations for Practice and Research (No. NASA/TM-2015-218568).

DeChurch, L. A., & Mesmer-Magnus, J. R. (2010). Measuring shared team mental models: A meta-analysis. Group Dynamics: Theory, Research, and Practice, 14(1), 1-14. https://doi.org/10.1037/a0017455

Edmonson, C., & Zelonka, C. (2019). Our Own Worst Enemies: The Nurse Bullying Epidemic. Nursing Administration Quarterly, 43(3), 274-279. https://doi.org/10.1097/NAQ.0000000000000353

Hamant, O. (2022). La Troisième Voie du vivant. Odile Jacob.

Hamant, O. (2024). De l’incohérence : Philosophie politique de la robustesse. Odile Jacob.

Leenders, R. Th. A. J., Contractor, N. S., & DeChurch, L. A. (2016). Once upon a time: Understanding team processes as relational event networks. Organizational Psychology Review, 6(1), 92-115. https://doi.org/10.1177/2041386615578312

Leonardi, P., & Contractor, N. (2018). Better people analytics. Harvard Business Review, 2018(November-December).

Lungeanu, A., DeChurch, L. A., & Contractor, N. S. (2022). Leading teams over time through space: Computational experiments on leadership network archetypes. The Leadership Quarterly, 33(5), 101595. https://doi.org/10.1016/j.leaqua.2021.101595

Pantic, M., & Vinciarelli, A. (2015). Social Signal Processing. In R. Calvo, S. D’Mello, J. Gratch, & A. Kappas (Éds.), The Oxford Handbook of Affective Computing (p. 0). Oxford University Press. https://doi.org/10.1093/oxfordhb/9780199942237.013.027

Securex. (2024). Burn-out : Un ouvrier belge sur trois dans la zone à risque. Securex. https://press.securex.be/fr/burn-out–un-ouvrier-belge-sur-trois-dans-la-zone-a-risque

Suzuki, N., Shoda, H., Sakata, M., & Inada, K. (2016). Essential Tips for Successful Collaboration – A Case Study of the “Marshmallow Challenge”. In S. Yamamoto (Éd.), Human Interface and the Management of Information : Applications and Services (p. 8189). Springer International Publishing. https://doi.org/10.1007/978-3-319-40397-7_9

Vinciarelli, A., Pantic, M., & Bourlard, H. (2009). Social signal processing : Survey of an emerging domain. Image and Vision Computing, Visual and multimodal analysis of human spontaneous behaviour:, 27(12), 17431759. https://doi.org/10.1016/j.imavis.2008.11.007