Robo‐Saber: Generating and Simulating Virtual Reality Players
Abstract We present the first motion generation system for playtesting virtual reality (VR) games. Our player model generates VR headset and handheld controller movements from in‐game object arrangements, guided by style reference gameplay examples. We train on the large BOXRR‐23 dataset and apply our framework on the popular VR game Beat Saber . The resulting model Robo‐Saber reproduces skilled performance and captures diverse player behaviors present in the training data. Robo‐Saber demonstrates promise in synthesizing rich gameplay data for predictive applications and enabling whole‐body physics‐based VR playtesting.
Authors
- M. J. Liu (ORCID: https://orcid.org/0009-0009-6936-4017)
- N. H. Kim (ORCID: https://orcid.org/0000-0002-9172-624X)
- J. Lehtinen (ORCID: https://orcid.org/0000-0001-9418-4944)
- P. Hämäläinen (ORCID: https://orcid.org/0000-0001-7764-3459)
- J. F. O'Brien (ORCID: https://orcid.org/0000-0001-9513-0542)
- X. B. Peng (ORCID: https://orcid.org/0000-0002-3677-5655)
Institutions
- Simon Fraser University (CA)
- University of California, Berkeley (US)
- Aalto University (FI)
Publication Details
- Journal
- Computer Graphics Forum
- Published
- 2026-04-30
- DOI
- https://doi.org/10.1111/cgf.70353
- Primary Topic
- Artificial Intelligence in Games
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Finnish Center for Artificial Intelligence
- Natural Sciences and Engineering Research Council of Canada