Metraipolis › archive › dc_b11d36e577a6
FRAM: Trajectory-Guided Visual Feature Selection for Compact Language-Conditioned Robot Manipulation — arXiv:2609.30965
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.30965
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T03:14:55.948Z
- SHA-256 of the archived text
548c24564d64593048e7debe8eb9b58716792a3e1af514cb0d3b45010fcc6565- Stable URL of this page
https://metraipolis.com/documento/dc_b11d36e577a6
How to cite
FRAM: Trajectory-Guided Visual Feature Selection for Compact Language-Conditioned Robot Manipulation — arXiv:2609.30965 — arXiv (en), https://arxiv.org/abs/2609.30965 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b11d36e577a6 (Metraipolis archive dc_b11d36e577a6, sha256 548c24564d64593048e7debe8eb9b58716792a3e1af514cb0d3b45010fcc6565)
BibTeX
@misc{dcb11d36e577a6,
title = {FRAM: Trajectory-Guided Visual Feature Selection for Compact Language-Conditioned Robot Manipulation — arXiv:2609.30965},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.30965},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b11d36e577a6; sha256 548c24564d64593048e7debe8eb9b58716792a3e1af514cb0d3b45010fcc6565},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30965. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Vision-Language-Action models achieve strong performance in robot manipulation, but often require large numbers of parameters. In this work, we propose the Future Representation Action Model (FRAM), a small policy that explicitly links the future end-effector trajectory to the current visual input. FRAM uses the image coordinates of the predicted trajectory as spatial pointers and reads local visual features related to the motion from the current image. This organizes the information for action generation into the reference position (Where), the visual state (What), and the future motion (Future). Trajectory labels are generated automatically from demonstrations and camera geometry, so no manual annotation is needed. With 138.7M parameters, including a frozen language encoder, FRAM reaches an average success rate of 92.2% over the four standard LIBERO suites, close to the 94.2% of $\pi_0$ with 3.3B parameters. Without extra training, it also reaches an average of 67.3% on LIBERO-Plus. Ablations confirm that both the future trajectory and the local visual features improve performance and robustness. On a real dual-arm UR5e, FRAM stacks cups using only wrist cameras, including choosing and switching between the left and right arms. These results show that selecting visual information based on future motion is an effective way to obtain both high performance and robustness in a small robot policy. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-28 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.30965 — 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 2026-10-08T02:58:08.911Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).