2022-04761 - Doctorant F/H Virtual Collaborative Jeu de Paume

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 Rennes - Bretagne Atlantique Centre is one of Inria's eight centres 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 R&D and innovation ecosystem: highly innovative PMEs, large industrial groups, competitiveness clusters, research and higher education players, laboratories of excellence, technological research institute, etc.

Contexte et atouts du poste



Mission confiée

Thesis goal

As this PhD thesis aims to develop a collaborative virtual reality environment for “Jeu de Paume” (JDP), for training and learning purposes, we have to consider several scientific questions.

The first question to address in the simulation of JDP for training purposes, is to ensure biofidelity. To do this, we first need to perform a physical characterisation of different elements of this sport, essentially the ball, the raquette and the court. It is also important to collect data on JDP players in order to analyse the movements during sport practice. The M2S team has already a great experience of collecting such data in many sports, including tennis [10]. The rackets used in JDP are asymetric, the balls are 30% heavier than in tennis but with a similar size, the court is asymetric and closed. The court is designed to make the ball bounce on the vertical walls, and on the inclined roofs of the “galleries'' around the ground called “carreau”. Another particularity is the fact that rackets and balls are still made using traditional craft techniques

To propose a realistic digital model of JDP and its environment, we will need to estimate the physical properties of this equipment. To this end, a physical ball model will be adapted from previous tennis and basketball [4] ball to compute realistic ball trajectories. Moreover, we will analyze the mechanical property of the racket, and its interaction with the ball. Hence, knowing the trajectories of the ball and the racket, it will be possible to compute a realistic behavior of the ball after a strike occurs.


The following question, in order to enable distant playing, is to propose a dynamic model of playing able to circumvent the technical impact of delay due to network. Recent works have demonstrated promising performance of deep neural networks, especially Recurrent Neural Network RNN, to predict the end of a human motion knowing the beginning [11]. This approach is promising but requires a huge amount of training data, for very different motions, which will be difficult to collect for this specific context. Thus, we propose to explore and adapt few shot learning techniques [9], while taking the context of the game into account.

Indeed, knowing the trajectory of the ball, the current state of the game (displacement, left/right strike, etc.), it should be possible to help the network to select the most relevant following motion.


The last question is related to the implementation of learning environments for “Jeu de Paume”, and in particular for the complex rules of the game. We will use the scenario engine developed in the Hybrid team for the conception of training environments in industry [1], medical surgery [3], and archaeology [7], in order to formally implement the rules in the virtual reality simulation of the game and to propose learning sessions for new players in order to ease their understanding. This engine implements a petri network based model of description of scenarios associated with a runtime environment to control the progress of a scenario in the simulation with respect to the users’ and autonomous characters’ behaviour and actions.

The specificities of the sportive context of the project brings new challenges to the #SEVEN model, in particular taking into account gestures inside scenario management, which introduced continuous data in a discrete model, and the integration of predictive models in the scenario engine. This scenario engine will also be a key advantage to provide the current state of the game (and the players) and potential following states, to the prediction model.



 [1] B. Berthelot, , Lopez, T., Nouviale, F., Gouranton, V., and Arnaldi, B. (2014). Corvette: Collaborative environment for technical training and experiment. In Virtual Reality (VR),2014 IEEE.

[2] Bideau, Kulpa, R., Vignais, N., Brault, S., Multon, F., & Craig, C. (2009). Using virtual reality to analyze sports performance. IEEE Computer Graphics and Applications, 30(2), 14-21.

[3] Claude, V. Gouranton, B. Caillaud, B. Gibaud, P. Jannin, et al. From Observations to Collaborative Simulation: Application to Surgical Training. ICAT-EGVE 2016 - International Conference on Artificial Reality and Telexistence, Eurographics Symposium on Virtual Environments, Dec 2016, Little Rock, Arkansas, United States. ⟨hal-01391776⟩)

[4] A Covaci, AH Olivier, F Multon (2015) Visual Perspective and Feedback Guidance for VR Free-Throw Training; IEEE Computer Graphics and Applications 35 (5), 55-65

[5] Ishibe, Aihara, S., Hayashi, Y., & Iwata, H. (2020, October). The development of an immersive three-dimensional virtual reality system for identifying hand–eye coordination in badminton. In 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC) (pp. 1778-1784). IEEE.

[6] H. P. Iskandar, L. Gilbert and G. B. Wills, "Reducing latency when using Virtual Reality for teaching in sport," 2008 International Symposium on Information Technology, 2008, pp. 1-5, doi: 10.1109/ITSIM.2008.4632076. -> squash in VR, prediction heuristic

[7] Lécuyer, V. Gouranton, R. Gaugne, T. Nicolas, G. Marchand, B. Arnaldi INSIDE Interactive and Non-destructive Solution for Introspection in Digital Environments. Digital Heritage 2018 - 3rd International Congress & Expo, IEEE, Oct 2018, San Francisco, United States.

[8] Le Noury, Buszard, T., Reid, M., & Farrow, D. (2021). Examining the representativeness of a virtual reality environment for simulation of tennis performance. Journal of Sports Sciences, 39(4), 412-420.

[9] Y. Gui, Yu-Xiong Wang, Deva Ramanan, Jose M. F. Moura (2018) Few-Shot Human Motion Prediction via Meta-Learning. Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 432-450

[10] Martin. Tennis: optimisation de la performance. De Boeck Supérieur, 2018

[11] Wirth et al. "Assessing personality traits of team athletes in virtual reality." 2020 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW). IEEE, 2020.

[12] Martinez, Michael J. Black, Javier Romero (2017) On Human Motion Prediction Using Recurrent Neural Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 2891-2900

[13] Oagaz, Schoun, B., & Choi, M. H. (2021). Performance Improvement and Skill Transfer in Table Tennis Through Training in Virtual Reality. IEEE Transactions on Visualization and Computer Graphics.


  • Subsidized meals
  • Partial reimbursement of public transport costs
  • Possibility of teleworking ( 90 days per year) and flexible organization of working hours
  • Partial payment of insurance costs


Monthly gross salary amounting to 1982 euros for the first and second years and 2085 euros for the third year