Metraipolis › archive › dc_72e498a69bae
Humanoid Dodgeball: Learning Fast Dynamic Obstacle Avoidance Motions for Humanoids — arXiv:2610.40003
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.40003
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T02:45:45.342Z
- SHA-256 of the archived text
8cfaf04059b7f45f80769c004c9dad8b4c1f64099f439903b10f9c5daf51e24c- Stable URL of this page
https://metraipolis.com/documento/dc_72e498a69bae
How to cite
Humanoid Dodgeball: Learning Fast Dynamic Obstacle Avoidance Motions for Humanoids — arXiv:2610.40003 — arXiv (en), https://arxiv.org/abs/2610.40003 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_72e498a69bae (Metraipolis archive dc_72e498a69bae, sha256 8cfaf04059b7f45f80769c004c9dad8b4c1f64099f439903b10f9c5daf51e24c)
BibTeX
@misc{dc72e498a69bae,
title = {Humanoid Dodgeball: Learning Fast Dynamic Obstacle Avoidance Motions for Humanoids — arXiv:2610.40003},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.40003},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_72e498a69bae; sha256 8cfaf04059b7f45f80769c004c9dad8b4c1f64099f439903b10f9c5daf51e24c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40003. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Humanoids have become increasingly agile and capable in real-world environments. To operate safely in dynamic scenarios, they must rapidly evade fast-moving obstacles while maintaining stability and physically feasible whole-body motion. Learning such behaviors remains challenging due to the high-dimensional dynamics of humanoid systems and the need to jointly balance reactive obstacle avoidance, motion naturalness, and control robustness. In this work, we present Humanoid Dodgeball, a reinforcement learning (RL) framework for agile dynamic obstacle avoidance in humanoids. Our method enables highly dynamic whole-body evasive maneuvers against incoming projectiles through threat-aware reward shaping, while multiple direction-specific adversarial motion priors regularize the learned behaviors toward stable and diverse human-like motions. Extensive simulation and hardware experiments demonstrate that the proposed framework substantially improves dynamic obstacle avoidance performance across diverse obstacle speeds and launch distances, while preserving robust and physically plausible humanoid motions. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.RO, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2610.40003 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-01T02:16:58.674Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).