Metraipolis › archive › dc_48ded3debaa8

ReCAT: Remember, Count, and Time: Structured Recurrent Memory for Robot Manipulation — arXiv:2609.35200

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.35200
License (as archived): CC0-1.0
Archived: 2026-10-07T21:03:22.529Z
SHA-256 of the archived text: 0ed33bbb994f7abd996538820b48f4cee7ad6e6ddf76d84878ecb5a42f01895e
Stable URL of this page: https://metraipolis.com/documento/dc_48ded3debaa8

How to cite

ReCAT: Remember, Count, and Time: Structured Recurrent Memory for Robot Manipulation — arXiv:2609.35200 — arXiv (en), https://arxiv.org/abs/2609.35200 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_48ded3debaa8 (Metraipolis archive dc_48ded3debaa8, sha256 0ed33bbb994f7abd996538820b48f4cee7ad6e6ddf76d84878ecb5a42f01895e)

BibTeX

@misc{dc48ded3debaa8,
  title = {ReCAT: Remember, Count, and Time: Structured Recurrent Memory for Robot Manipulation — arXiv:2609.35200},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35200},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_48ded3debaa8; sha256 0ed33bbb994f7abd996538820b48f4cee7ad6e6ddf76d84878ecb5a42f01895e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35200. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Memory-dependent manipulation requires robots to make decisions using information that is no longer available to their current sensors, such as recalling an earlier visual cue, tracking task progress, counting repeated events, or estimating elapsed time. We present ReCAT, a language-conditioned policy with structured recurrent memory. An instruction-conditioned encoder forms features from the current observation. A recurrent memory integrates the observation stream through Mamba-2 layers and one causal attention layer. A flow-matching Transformer decoder reads the current and the historical representation through separate cross-attention in every block. ReCAT reaches 95.3\% average success on LIBERO and 62.4\% on RMBench, with the best or tied-best result on six of nine tasks. On three real-robot tasks probing spatial recall, event counting, and interval timing, the best ReCAT variant reaches 66.7\% average success, against 8.3\% for the strongest short-history baseline. Controlled comparisons within ReCAT show that the observation encoder and every-block memory conditioning are needed for this performance. They also show that update rules developed for efficient sequence modeling behave differently as robot memory: additive updates have the highest observed success on counting and timing, and delta-rule updates on spatial recall. Project website is at this https URL

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); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.35200 — 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 2026-10-07T20:29:03.287Z 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).