Phd Position F - M Local Crowd Simulation And Authoring In Augmented Reality For Large-Scale Event Planning H/F - INRIA

A propos d'Inria

Inria, l'institut national de recherche dans les sciences et technologies du numérique, est en appui de l'État pour les stratégies nationales de recherche et d'innovation du numérique en tant qu'Agence de programmes. Inria mène plus de 300 projets de recherche et d'innovation avec ses 3500 scientifiques, ingénieurs et personnels d'appui, en partenariat avec les universités et l'écosystème numérique (entreprises, entrepreneurs, acteurs publics). Ensemble, nous explorons des domaines clés comme l'intelligence artificielle, la cybersécurité, l'informatique quantique, le Cloud, la transformation numérique de la santé, les jumeaux numériques ou encore les technologies numériques pour la défense. Nous construisons des solutions concrètes telles que des logiciels, des startups technologiques, des partenariats avec les entreprises du tissu national et des formations de pointe. Notre objectif : l'impact scientifique, technologique et industriel au service de la souveraineté numérique de la France.

PhD Position F/M Local Crowd Simulation and Authoring in Augmented Reality for Large-Scale Event Planning
Le descriptif de l'offre ci-dessous est en Anglais
Type de contrat : CDD

Niveau de diplôme exigé : Bac +5 ou équivalent

Fonction : Doctorant

A propos du centre ou de la direction fonctionnelle

The Inria center at the University of Rennes is one of eight Inria centers and has more than thirty research teams. The Inria center is a major and recognized player in the field of digital sciences. It is at the heart of a rich ecosystem of R&D and innovation, including highly innovative SMEs, large industrial groups, competitiveness clusters, research and higher education institutions, centers of excellence, and technological research institutes.

Contexte et atouts du poste

Large-scale events - music festivals, sporting ceremonies, urban celebrations - are organised with increasing frequency and scale, and their planning routinely raises complex crowd management questions regarding layout, capacity and safety. Crowd simulation is one of the few tools currently available to support this planning stage, allowing organisers to anticipate crowd flows or evaluate evacuation procedures. However, it remains fundamentally limited to a global, external, desk-based perspective: a simulation is configured with parameters set at the scale of an entire site - density, flow directions, entry and exit points - run as a whole, and observed from the outside, typically through 2D visualisations or bird's-eye 3D renderings. This paradigm is well suited to large-scale planning, but it cannot capture how a crowd interacts with the specific physical layout of a venue, how attendees experience being immersed within it, or how staff should be trained to navigate and make decisions in complex, situated crowd configurations.

This PhD position is part of PEAR, a collaborative ANR PRCI project between Inria, the Luxembourg Institute of Science and Technology (LIST) and the firefighter department of the Laboratoire Central de la Préfecture de Police de Paris (LCPP), with Hellfest Productions and Paléo Arts & Spectacles as festival partners. PEAR is driven by the hypothesis that combining realistic virtual crowd simulation with immersive eXtended Reality (XR) can fundamentally change how large-scale events are planned, by shifting the perspective from a global, external view of crowds to an embodied, first-person, on-site experience of crowd dynamics. Rather than configuring a simulation from a desk and observing its output from outside, users would be physically present within a virtually populated version of a real environment, through Augmented Reality (AR), and explore crowd scenarios locally and interactively, directly on-site.

The prototypes developed within PEAR will be confronted with concrete, real-world use-cases. The primary evaluation ground is the New Year's Eve celebration on the Champs-Élysées, led by the LCPP, which brings together over one million people in a dense urban environment each year and requires revising layout configurations, barrier placement and field team deployment for every edition. Findings will subsequently be generalised to the Hellfest and Paléo festival sites, to validate the applicability of the approaches developed in this position across different event formats, scales and physical configurations.

Mission confiée

Within PEAR, this PhD focuses specifically on how crowd scenarios can be simulated, authored and configured locally and interactively, directly on-site through AR - as opposed to being configured globally from a desk. It is structured around three complementary objectives.

The first objective is to design a local crowd authoring paradigm in AR: enabling users to move from a globally pre-computed crowd simulation, configured from plans and site maps, to a local, interactive exploration and configuration of crowd behaviours at a specific, physical location. This requires decoupling local crowd behaviour from global simulation consistency, so that local modifications - e.g., increasing density in front of a stage, or repositioning a barrier at an entrance - remain plausible without a full re-computation of the whole-site simulation.

The second objective is to ground this local authoring in the real environment itself, without requiring the full topology of the site to be known or modelled in advance. The candidate will explore how representations such as Interaction Fields [Colas 2022] can be extended to infer local constraints from real-world semantic cues sensed through AR, and how on-site interaction paradigms can be designed to remain intuitive and accessible to non-expert users such as event organisers or safety officers.

The third objective is to contribute the underlying simulation and integration layer that makes on-site authoring possible in practice - in close collaboration with the AR platform development led within PEAR - and to evaluate the usability and effectiveness of the resulting local authoring paradigm: whether non-expert users can intuitively configure and explore meaningful crowd scenarios on-site, measured for instance through task completion time, NASA-TLX cognitive load, or SUS usability scores.

Principales activités

Project Organisation

- Year 1: state of the art on crowd simulation, crowd authoring and AR-based interaction; contribution to the AR-ready integration platform and its shared data interface; first design of the local, on-site crowd authoring paradigm (initial demonstrator).
- Year 2: development and refinement of the local authoring paradigm, in particular the grounding of authored behaviours in real-world semantic cues; integration into the AR platform; first usability evaluation with non-expert users.
- Year 3: completion of the usability evaluation of the local authoring paradigm; contribution to the construction of the Champs-Élysées digital twin and to the immersive evaluation of crowd planning scenarios with the LCPP; participation in on-site evaluations at Hellfest and/or Paléo; thesis writing.

Compétences

- Strong programming skills (C++ and/or C# recommended)
- Solid background in computer graphics, crowd simulation, or virtual/augmented reality
- Prior experience with Unity or Unreal Engine would be beneficial
- Interest in human-computer interaction, interaction design, and usability evaluation with human participants
- Proficiency in English (orally and in writing) to interact with the different international project partners

Avantages

- Subsidized meals
- Partial reimbursement of public transport costs
- Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
- Possibility of teleworking (after 6 months of employment) and flexible organization of working hours
- Professional equipment available (videoconferencing, loan of computer equipment, etc.)
- Social, cultural and sports events and activities
- Access to vocational training
- Social security coverage

Rémunération

monthly gross salary 2300 euros