International audienceThe aim of this paper is to present the principles and results about case-based reasoning adapted to real- time interactive simulations, more precisely concerning retrieval mechanisms. The article begins by introducing the constraints involved in interactive multiagent-based simulations. The second section pre- sents a framework stemming from case-based reasoning by autonomous agents. Each agent uses a case base of local situations and, from this base, it can choose an action in order to interact with other auton- omous agents or users' avatars. We illustrate this framework with an example dedicated to the study of dynamic situations in football. We then go on to address the difficulties of conducting such simulations in real-time and propose a model for case and for case base. Using generic agents and adequate case base structure associated with a dedicated recall algorithm, we improve retrieval performance under time pressure compared to classic CBR techniques. We present some results relating to the performance of this solution. The article concludes by outlining future development of our project

La simulation participative et la réalité virtuelle offrent des perspectives innovantes pour la recherche et la formation en sport. L’objectif de cet article est de proposer une réflexion sur la méthodologie de conception de simulateurs dans le domaine du sport, dans le but d’en améliorer la crédibilité. Un état de l’art présente l’intérêt, les propriétés et les limites des simulateurs actuellement développés pour la recherche et l’entraînement sportif. Nous présentons ensuite une expérience originale de développement d’une simulation participative en sport collectif : une approche ergonomique de l’activité en situation naturelle permet d’obtenir une modélisation de la prise de décision de joueurs de football experts ; celle-ci est utilisée pour guider le choix de modèles informatiques implémentés pour développer un environnement virtuel, CoPeFoot (Coopérative Perception in Football). Cette méthodologie et les résultats obtenus sont discutés à l’aune du paradigme de l’énaction. La crédibilité de la simulation pour l’usager reposerait sur un équilibre entre régularité et surprise dans l’émergence des comportements des agents (joueurs) virtuels.

Motivation -The purpose of this study was to explore and describe the thought processes of football decision-makers in natural setting. Research approach -Twelve French football players were observed during a specially designed study favourising counter-attacks. Players then watched a videotaped recording of their performance and provided the researcher with a verbal description of their cognitive activity during the situation. Findings/Design -A content analysis conducted in context identified recurrent meanings produced by the experts and revealed the use of 16 schemata. Research limitations/Implications -Results highlight three aspects concerning experts' decision-making processes: experts' recognition of typical situations, the flexibility of schemata in decision-making, and the evolution of the activity on the basis of contextual cues. Originality/Value -Modele obtained has been used for the development of the virtual environment CoPeFoot (Collective Perception Football). Take away message -This study provides a deeper understanding of complex football decision-making activity during dynamical situation.

Abstract

This article presents advantages of using context to set up a pedagogical assistance for recognition of collectives situations in Virtual Environment for Training (VET). We are focusing on generation of explanations to the learner. Two assistances types have been envisaged thanks to context using, the first one consists in guiding the learner before action and the second can be used during action. Those assistances have been set up thanks to contextual graph and consists of animations in the virtual environment.