Metraipolis › archive › dc_34e73f28c838

HitMem: Hierarchical Temporal 3D Memory with Multi-Modal Context-Aware Retrieval for Dynamic Environments — arXiv:2609.00950

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.00950
License (as archived)
CC0-1.0
Archived
2026-10-17T07:18:25.992Z
SHA-256 of the archived text
e62a21f87779d99fa2685e5f812c71b49ec3131e7e6e2f55435b21a422a1d37a
Stable URL of this page
https://metraipolis.com/documento/dc_34e73f28c838

How to cite

HitMem: Hierarchical Temporal 3D Memory with Multi-Modal Context-Aware Retrieval for Dynamic Environments — arXiv:2609.00950 — arXiv (en), https://arxiv.org/abs/2609.00950 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_34e73f28c838 (Metraipolis archive dc_34e73f28c838, sha256 e62a21f87779d99fa2685e5f812c71b49ec3131e7e6e2f55435b21a422a1d37a)
BibTeX
@misc{dc34e73f28c838,
  title = {HitMem: Hierarchical Temporal 3D Memory with Multi-Modal Context-Aware Retrieval for Dynamic Environments — arXiv:2609.00950},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00950},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_34e73f28c838; sha256 e62a21f87779d99fa2685e5f812c71b49ec3131e7e6e2f55435b21a422a1d37a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00950. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Executing long-term tasks in dynamic environments requires embodied agents to maintain robust and adaptive 3D scene representations. However, most existing 3D memory frameworks rely on static world assumptions. When objects are displaced by human activities or unobserved events, agents encounter memory-observation conflicts and often require costly geometric recomputations or inefficient global re-exploration. To address this, we propose HitMem, a hierarchical temporal 3D memory framework with a multi-modal context-aware retrieval mechanism. Through continuous perception, HitMem unifies semantic and spatial information into a lightweight topological graph that captures support relationships, while a temporal decay mechanism dynamically regulates memory activeness to mitigate the impact of stale representations. In addition, the multi-modal context-aware retrieval mechanism defaults to filtering candidates using integrated semantic, spatial, and temporal memory features, and activates a specialized two-stage retrieval process when object displacement is detected. This process combines spatial constraints inferred from external agent trajectories with semantic common sense grounded in class affinities, efficiently identifying high-probability candidate regions. Extensive evaluations on our constructed Dyna-THOR benchmark demonstrate that HitMem significantly improves object relocation accuracy, reduces exploration costs, and enhances task execution performance in dynamic environments.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-02 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.00950 — 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 2026-10-17T07:06:32.696Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).