Metraipolis › archive › dc_4d585348fa25
Learning Agile Humanoid Dodgeball with Onboard Monocular Vision — arXiv:2611.01197
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.01197
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:57:07.353Z
- SHA-256 of the archived text
863af68d6fd488f9c1c7edbabac50fa76d03066d75673a5d358056a3842ee153- Stable URL of this page
https://metraipolis.com/documento/dc_4d585348fa25
How to cite
Learning Agile Humanoid Dodgeball with Onboard Monocular Vision — arXiv:2611.01197 — arXiv (en), https://arxiv.org/abs/2611.01197 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4d585348fa25 (Metraipolis archive dc_4d585348fa25, sha256 863af68d6fd488f9c1c7edbabac50fa76d03066d75673a5d358056a3842ee153)
BibTeX
@misc{dc4d585348fa25,
title = {Learning Agile Humanoid Dodgeball with Onboard Monocular Vision — arXiv:2611.01197},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.01197},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4d585348fa25; sha256 863af68d6fd488f9c1c7edbabac50fa76d03066d75673a5d358056a3842ee153},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01197. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Humanoid robots operating in shared, dynamic environments must respond to rapidly approaching objects while maintaining balance. We study dodgeball as a controlled test of this capability, coupling visual threat assessment with whole-body evasion, recovery, and target reacquisition. We develop a system that integrates onboard monocular perception, temporal ball-state and threat-flag estimation, and learned whole-body control. A ball detector supplies bounding-box histories, and a temporal estimator predicts relative ball position and a binary threat flag. Separate dodge/recovery and search/track policies share this interface and are composed to support repeated encounters. A three-stage curriculum first trains control with privileged ball states, then starts estimator supervision from stable policy rollouts, and finally replaces the actor's privileged inputs with estimator outputs. Analytic projection and perception randomization provide detector-like training observations without image rendering. Across approach-angle bins in controlled simulation, dodge success ranges from 97.8--100.0% for 5.0 m launches at 6 m/s to 33.2--40.8% for 2.5 m launches at 10 m/s, with 1000 throws per speed--distance condition. On a physical Unitree G1, controlled single-throw success exceeds 85% over more than 15 trials. A hardware sequence demonstrates full-azimuth target reacquisition followed by another dodge. These results demonstrate an integrated onboard-monocular-vision system under highly dynamic 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/2611.01197 — 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 2026-11-03T18:17:07.726Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).