Seminal
The magazine and atlas of EU-funded researchA new publication from the web and AI team at Scott Charnley

Atlas / France

Marie Skłodowska-Curie Action · Ended early

SNABS Social Navigation with Adaptive Behavior Sets

Coordinator
Institut National De Recherche En Informatique Et Automatique, France
Runs
1 September 2026 to 28 February 2030
Status
Ended early
EU funding
€391k
Total cost
—
Partners
5 organisations in 4 countries
Type
Marie Skłodowska-Curie Action
Grant agreement
101200240

What the project is doing

In the project's own words, from its summary on CORDIS.

The global issue of aging populations (by 2050, a 60% increase in the proportion of persons aged above 65 is projected) places great strain on healthcare systems while simultaneously leading to a decrease in the active labor pool. Social robots have the potential to mitigate the problem by assisting and relieving workers in their basic tasks, such as delivering items or guiding people. To allow this, robots need human-aware navigation to move safely among humans, join, follow, or guide them.

However, a major research challenge is the adaptability of the navigation behavior to quickly changing social contexts and environments, such as between areas where more safety space should be given than in others (e.g. hospitals compared to offices). For this purpose, SNABS (Social Navigation with Adaptive Behavior Sets) investigates a machine learning framework (Adaptive Behavior Sets for Transfer Reinforcement Learning) that promises quick adaptations by learning an extensive library of potential behaviors.

Being in a new context, it selects the best behavior among them. However, the existing framework suffers from problems hindering its use for real-world applications. This includes the prediction of its behaviors’ outcomes in complex navigation scenarios with human trajectories and the identification of the best behavior in real-time. SNABS aims to overcome these problems by investigating new generative AI models for predicting future outcomes and by introducing new selection strategies for the behaviors.

The project further researches how to successfully use the framework to train an adaptive social navigation controller for social robots. The controller will be evaluated in realistic healthcare scenarios. During a final placement at a European robotics manufacturer, the controller will be transferred to their robotic platforms and publicly shared to be directly applicable in the envisioned target scenarios in health and elderly care.

Topics

Who is involved

OrganisationCityCountryRole
Institut National De Recherche En Informatique Et AutomatiqueLe Chesnay CedexFranceCoordinator
The Governors of the University of AlbertaEdmontonCanadaAssociatedpartner
Pal Robotics SluBarcelonaSpainAssociatedpartner
Universite Grenoble AlpesGrenobleFranceAssociatedpartner
National University Corporation Kyoto UniversityKyotoJapanAssociatedpartner

Source: CORDIS, European Commission. Data of 5 Nov 2026, reused under the Commission's reuse policy. View on CORDIS · Grant DOI