具身开发者社区

外观

论文arXiv 2610.1357819 天前

RARA：通过检索锚定的表示对齐实现机器人操作的鲁棒策略微调 ​

RARA通过检索锚定表示对齐来适配少量示范，在仿真与真机操作任务上验证了微调成功率提升。

AI 整理
  • 数据与采集
  • 具身模型
  • 端侧部署

原文链接：RARA: Robust Policy Fine-Tuning through Retrieval-Anchored Representation Alignment for Robotic Manipulation（arXiv 2610.13578 · 发布日期：2026-10-09）

RARA: Robust Policy Fine-Tuning through Retrieval-Anchored Representation Alignment for Robotic Manipulation

RARA通过检索锚定表示对齐来适配少量示范，在仿真与真机操作任务上验证了微调成功率提升。

核心要点 ​

  • 预训练机器人策略适合通用操作，但少量示范适配新任务时易削弱分布外泛化。
  • RARA先检索意图和运动相似的预训练表示，并与目标示范表示对齐。
  • 随后在目标示范上微调，同时限制检索示范表示变化以减少不必要漂移。
  • 在Diffusion Policy和GR00T的13个任务中，RARA优于所有比较基线。

验证范围与局限：验证范围包括RoboTwin、RoboCasa仿真任务和真实机器人上的13个任务。

英文摘要 (Abstract) ​

Pre-trained robot policies, such as Vision-Language-Action (VLA) models, provide a strong foundation for generalist robotic manipulation, but adapting them to new tasks with only a few demonstrations remains challenging. Directly fine-tuning a pre-trained policy often achieves strong in-distribution performance, yet it can distort the representations learned during pre-training and weaken the model's generalization ability under out-of-distribution shifts. We propose Retrieval-Anchored Representation Alignment (RARA), a two-stage adaptation method, to address this issue. First, RARA retrieves representation features from pretraining with similar task intent and motion, and aligns the policy's representations of the target demonstrations with the pre-trained representations of the retrieved demonstrations. Second, RARA fine-tunes the policy on the target demonstrations while limiting how much its representations of the retrieved demonstrations change during fine-tuning. By reducing the representation mismatch before action learning and preserving pre-trained knowledge during adaptation, RARA limits unnecessary representation drift during fine-tuning. Experiments with Diffusion Policy and GR00T on 13 tasks in RoboTwin, RoboCasa, and on a real robot show that RARA improves the average success of fine-tuning by 9.5 points in-distribution and 13.6 points out-of-distribution, and outperforms all compared baselines. Project page: https://shua-kang.github.io/RARA_robot/

作者：Xuhui Kang, Sung-Wook Lee, Zhuang Yan, Tianle Zhong, Yen‐Ling Kuo

来源

本页事实对应的公开页面，以原文为准。

  1. arXiv 2610.13578：RARA: Robust Policy Fine-Tuning through Retrieval-Anchored Representation Alignment for Robotic Manipulation访问 2026-10-21