Metraipolis › archive › dc_d09d274d2d37
F4R: Failure-Driven Recognition, Reconstruction, Refinement, and Redeployment for Continual Robot Self-Improvement — arXiv:2609.35575
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.35575
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T21:03:47.208Z
- SHA-256 of the archived text
af8ff51958a8fa0e5c778cdf1d5f8585c5a834b9aa16867cef0ea414ed946e72- Stable URL of this page
https://metraipolis.com/documento/dc_d09d274d2d37
How to cite
F4R: Failure-Driven Recognition, Reconstruction, Refinement, and Redeployment for Continual Robot Self-Improvement — arXiv:2609.35575 — arXiv (en), https://arxiv.org/abs/2609.35575 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d09d274d2d37 (Metraipolis archive dc_d09d274d2d37, sha256 af8ff51958a8fa0e5c778cdf1d5f8585c5a834b9aa16867cef0ea414ed946e72)
BibTeX
@misc{dcd09d274d2d37,
title = {F4R: Failure-Driven Recognition, Reconstruction, Refinement, and Redeployment for Continual Robot Self-Improvement — arXiv:2609.35575},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.35575},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d09d274d2d37; sha256 af8ff51958a8fa0e5c778cdf1d5f8585c5a834b9aa16867cef0ea414ed946e72},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35575. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The real-world performance of current vision-language-action models is fundamentally constrained by the limited coverage of expert demonstrations and their insufficient understanding of physical interactions. A common remedy is to collect additional real-world demonstrations of newly encountered failures. However, this process is costly, inefficient, potentially unsafe, and difficult to scale. To address this challenge, we propose Failure for Rising (F4R), a failure-driven real-to-sim-to-real closed-loop learning framework that converts real-world failures into targeted policy improvement. F4R first uses an agent to automatically identify and diagnose failures from rollouts. It reconstructs each failure as an interactive, object-centric table-top environment that preserves the task-relevant spatial and physical conditions. The policy is then refined through failure-conditioned sim-real co-training followed by targeted reinforcement learning in the reconstructed environments. The improved policy is subsequently redeployed, while newly observed failures are continuously fed back into the next reconstruction and learning cycle. Real-world evaluations on four manipulation tasks show that F4R achieves 93.75% In-Distribution and 90.0% Out-of-Distribution (OOD) success, outperforming the budget-matched Targeted BC baseline by 18.75 percentage points under OOD conditions without collecting additional real-world corrective demonstrations. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.35575 — 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 2026-10-07T20:29:03.399Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).