论文研究
arxiv.org ·
FRAM：面向紧凑语言条件机器人操作的轨迹引导视觉特征选择
该论文提出 Future Representation Action Model（FRAM），一种小型机器人操作策略，通过将预测的未来末端执行器轨迹映射为图像坐标作为空间指针，从当前图像中读取与运动相关的局部视觉特征，把动作生成信息组织为参考位置（Where）、视觉状态（What）和未来运动（Future）。轨迹标签由演示与相机几何自动生成，无需人工标注。FRAM 含冻结语言编码器共 138.7M 参数，在 LIBERO 四个标准套件上平均成功率 92.2%，接近 3.3B 参数 π0 的 94.2%；在 LIBERO-Plus 上无需额外训练平均达 67.3%。消融实验表明未来轨迹与局部视觉特征均提升性能与鲁棒性。在真实双臂 UR5e 上，FRAM 仅用腕部相机完成叠杯，并能选择与切换左右臂。
AI推荐理由 arXiv 机器人方向新论文，提出 FRAM 小型策略：用预测的未来末端轨迹图像坐标作为空间指针，从当前图像读取局部视觉特征，将动作生成信息组织为 Where/What/Future 三部分；轨迹标签由演示和相机几何自动生成，无需人工标注。以 138.7M 参数（含冻结语言编码器）在 LIBERO 四个标准套件平均成功率 92.2%，接近 3.3B 参数的 π0 的 94.2%，并在 LIBERO-Plus 上零额外训练达 67.3%；消融显示未来轨迹与局部视觉特征均有贡献，并在真实双臂 UR5e 上仅用腕部相机完成叠杯及左右臂选择切换。局限在于摘要未给出与更多基线或更大规模真实任务的对比，真实实验仅描述单一叠杯场景，效果仍需复现验证。
78
正文
Computer Science > Robotics
arXiv:2609.30965 (cs)
[Submitted on 25 Sep 2026]
Title:FRAM: Trajectory-Guided Visual Feature Selection for Compact Language-Conditioned Robot Manipulation
Authors:Hiroshi Ito, Hyogo Hiruma, Yoshiki Kanai, Takahiro Yoshida, Akira Kanazawa, Hiroki Yamada
View a PDF of the paper titled FRAM: Trajectory-Guided Visual Feature Selection for Compact Language-Conditioned Robot Manipulation, by Hiroshi Ito and 5 other authors
View PDF
HTML (experimental)
Abstract: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.
Subjects:
Robotics (cs.RO)
Cite as:
arXiv:2609.30965 [cs.RO]
(or
arXiv:2609.30965v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2609.30965
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Hiroshi Ito [view email]
[v1]
Fri, 25 Sep 2026 08:16:16 UTC (5,248 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled FRAM: Trajectory-Guided Visual Feature Selection for Compact Language-Conditioned Robot Manipulation, by Hiroshi Ito and 5 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.RO
new
|
recent
| 2026-09
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)