Metraipolis › archive › dc_105bc1babdae

X2Real: an eXtensive simulation benchmark for real-world generalist policies — arXiv:2609.27449

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.27449
License (as archived)
CC0-1.0
Archived
2026-10-08T12:53:34.364Z
SHA-256 of the archived text
e59b1bee61930d92b11dc03372ca921ba6874e1b5f60ea7c349ef9b54363efba
Stable URL of this page
https://metraipolis.com/documento/dc_105bc1babdae

How to cite

X2Real: an eXtensive simulation benchmark for real-world generalist policies — arXiv:2609.27449 — arXiv (en), https://arxiv.org/abs/2609.27449 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_105bc1babdae (Metraipolis archive dc_105bc1babdae, sha256 e59b1bee61930d92b11dc03372ca921ba6874e1b5f60ea7c349ef9b54363efba)
BibTeX
@misc{dc105bc1babdae,
  title = {X2Real: an eXtensive simulation benchmark for real-world generalist policies — arXiv:2609.27449},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.27449},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_105bc1babdae; sha256 e59b1bee61930d92b11dc03372ca921ba6874e1b5f60ea7c349ef9b54363efba},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27449. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generalist robot manipulation policies have developed rapidly, yet their reliable evaluation remains challenging due to fundamental flaws in existing simulation benchmarks: prominent sim-to-real gaps, narrow task coverage, and unfair evaluation caused by ambiguous training-test pipelines. Prior works only partially resolve these issues and lack simultaneous faithfulness, diversity, and fairness, while static benchmark designs fail to sustain long-term policy development. We present X2Real, an evolvable simulation benchmark for faithfully evaluating the real-world performance of robotic manipulation policies based on Nvidia Isaac Lab-Arena. Following three core principles (faithfulness, diversity, and fairness), X2Real calibrates simulation visual and physical properties to align with real hardware, achieving a 0.84 linear correlation between simulated and real-robot evaluation results. It features a comprehensive taxonomy with 10 capability dimensions and 44 hierarchical long-horizon tasks, covering basic manipulation skills and advanced capacities such as visual grounding, language understanding, and bimanual control. We further adopt multi-axis domain randomization and strictly disjoint training-evaluation pipelines to mitigate benchmark exploitation and ensure credible evaluation. Powered by a custom physical domain-specific language, the Mana simulation ecosystem supports modular task design and iterative performance analysis, alongside a nearly 300-hour annotated simulation trajectory dataset. X2Real offers a faithful, diverse, and fair evolving evaluation infrastructure, effectively bridging the sim-to-real evaluation gap and supporting the advancement of generalist robotic manipulation policies.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-24 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.27449 — 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 2026-10-08T12:21:19.473Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).