Virtual Audiences Control For VR Tennis Training

Open Human-Computer Interaction Computer Science Games Engineering Bachelor Master Project Thesis No Affiliation

Motivation

The core challenge of mental habituation training for elite and professional tennis players in VR is replicating the unpredictable, high-pressure acoustic and visual environment of modern stadium courts (e.g., Arthur Ashe Stadium, Roland Garros). Unlike standard public speaking or performance scenarios where steady attention is desired, tennis players require extreme focus under shifting crowd dynamics, ranging from synchronized applause between points to sudden movement in the stands, flash photography, or delayed quiet during a serve toss.

This project focuses on the architectural engineering, nonverbal behavior generation, and empirical evaluation of a controllable virtual tennis stadium audience, grounded in established Human-Computer Interaction (HCI), Intelligent Virtual Agent (IVA), and Sports Psychology principles.

Scope & Project Flexibility

This project can be scaled for either a Bachelor’s or Master’s level thesis. The scope can be customized based on student interests and can be discussed in detail during a preliminary meeting to define the final project trajectory.

Project Partners & Supervision Structure

This project is conducted in collaboration with a French university and research labs in Paris. The supervision structure is as follows: the University of Würzburg will provide primary supervision and evaluation, while the French partners will serve as secondary supervisors and collaborate on the project scope and technical requirements

Tasks

System & Behavior Architecture Design

Define Crowd Behavioral States Specific to Tennis:

• Pre-Point Silence: Tense, collective silence during service preparation.
• Point-in-Play Tracking: Head-tracking/eye-gaze synchronization following the ball trajectory.
• Rally Escalation: Building murmur or collective gasps during long or high-risk rallies.
• Post-Point Reactions: Synchronized applause, cheering, standing ovations, or disappointed sighs.
• Hostile / Distracting States: Boo-ing, partisan chanting, whistling, or premature cheering before a point ends.

Define Interfering Events (Disruption & Habituation Trigger Engineering):

• Auditory Disturbances: Late shouts/screams during serve toss, screaming babies, phone ringtones, stadium announcements, echoes/reverberation spikes.
• Visual Disturbances: Flash photography, spectators moving down aisles during play, waving flags/banners, glare reflections.

Performer / Player Profiles & Stress Vectors:

• Pressure Situations: Match point, break point, double-fault history, high-leverage tiebreakers.
• Opponent Styles & Audience Bias: Home-favorite crowd bias vs. neutral or hostile stadium support.

Control & Simulation Implementation (Unity / Unreal Engine / Godot)

3D Tennis Venue Realism & Spatial Acoustics:

• Build an open-air or domed 3D tennis stadium complete with realistic court lighting, ball bounce occlusion, and spatialized 3D audio for crowd positioning relative to court zones.

Operator Control & Adaptation Panel:

• Implement a high-level Control Interface (Wizard-of-Oz GUI or REST API control panel) enabling a sports psychologist or coach to trigger targeted disruptions, modify crowd hostility, or adjust overall decibel levels in real time based on player performance.

Animation & Crowd Dynamics Engine:

• Integrate procedural and clip-based crowd animations displaying micro-behaviors (gaze tracking, moving heads, clapping) and macro-behaviors (waves, stadium-wide reactions).

(Bonus) Social Signal Processing & Biofeedback Integration:

• Integrate real-time biofeedback monitoring (e.g., HMD eye-tracking for target gaze precision, heart rate variability [HRV], skin conductance, or head stability during service routine) to assess player stress levels and automatically adapt crowd difficulty.

Evaluation

• Design an empirical user study comparing conditions (e.g., Static Baseline Crowd vs. Dynamic Reactive Crowd) evaluating established metrics such as presence and plausibility of the simulation.

Literature

• Glémarec, Y., Lugrin, J.-L., Bosser, A.-G., Buche, C., & Latoschik, M. E. (2022). Controlling the Stage: A high-level control system for virtual audiences in virtual reality. Frontiers in Virtual Reality.
• Paton, G., Bosser, A.-G., Ravenet, B., & Le Bigot, N. (2025). Enhancing narrative engagement through virtual crowd modulation in VR storytelling. ACM International Conference on Intelligent Virtual Agents (IVA).
• Ravenet, B., Cafaro, A., Ochs, M., & Pelachaud, C. (2014). Interpersonal attitude of a speaking agent in simulated group conversations. Intelligent Virtual Agents.
• Biancardi, B., Dermouche, S., & Pelachaud, C. (2021). Adaptation mechanisms in human–agent interaction: Effects on user’s impressions and engagement. Frontiers in Computer Science.
• Stinson, C., & Bowman, D. A. (2014). Feasibility of training athletes for high-pressure situations using virtual reality. IEEE Transactions on Visualization and Computer Graphics.
• Vignais, N., Bideau, B., Craig, C., Brault, S., Multon, F., & Kulpa, R. (2015). Virtual reality for sport training: a systematic review of its efficacy and spatial fidelity. Sports Medicine.
• Chollet, M., & Scherer, S. (2021). Perceiving audience behaviors: Expressive virtual audience modeling for public speaking training. IEEE Transactions on Affective Computing.

Contact Persons at the University Würzburg