Metraipolis › archive › dc_2c14f7d2fb5f
HINT: Human-Intent Inception for Long-Horizon Robot Manipulation — arXiv:2609.02653
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.02653
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T05:51:19.242Z
- SHA-256 of the archived text
9b7711492dfe28b35fd5423c1d132d69cb80f576d6d1ac16e64de647232e83af- Stable URL of this page
https://metraipolis.com/documento/dc_2c14f7d2fb5f
How to cite
HINT: Human-Intent Inception for Long-Horizon Robot Manipulation — arXiv:2609.02653 — arXiv (en), https://arxiv.org/abs/2609.02653 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2c14f7d2fb5f (Metraipolis archive dc_2c14f7d2fb5f, sha256 9b7711492dfe28b35fd5423c1d132d69cb80f576d6d1ac16e64de647232e83af)
BibTeX
@misc{dc2c14f7d2fb5f,
title = {HINT: Human-Intent Inception for Long-Horizon Robot Manipulation — arXiv:2609.02653},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.02653},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2c14f7d2fb5f; sha256 9b7711492dfe28b35fd5423c1d132d69cb80f576d6d1ac16e64de647232e83af},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02653. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Humans can perform complex manipulations given a simple intent through an overall instruction, while continuously adapting to evolving visual observations. However, current vision-language action (VLA) models and other action policies struggle to realize this high-level intelligent behavior under dense, evolving visual inputs and sparse language guidance. Visual correlations can then dominate semantic intent, leading actions to follow visual shortcuts rather than human goals. We present HINT (Human-INTent INcepTion), an agentic framework inspired by the human manipulation principles: semantic intent changes sparsely at manipulation-pattern transitions, whereas continuous control primarily depends on the evolving object-hand relationship. HINT invokes semantic reasoning only at pattern transitions to resolve the current subtask and target, then maintains this commitment through multi-view grounding and visual tracking. We explore two visual interfaces-image-space semantic highlighting and attention-prior injection-to communicate the tracked intent to the action policy without introducing additional trainable parameters into the foundation action model. Experiments across three long-horizon tasks and out-of-distribution variants show that HINT substantially improves intent understanding, task progress, and end-to-end success across two foundation policies while preserving low-latency control. Project page: this https URL Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-03 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.02653 — 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 2026-10-17T05:39:02.698Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).