Skip to content

论文arXiv 2611.176316 天前

插入任务策略学习验证:接触中心表征优于通用视觉基础模型 ​

本文由 AI 根据公开内容整理,可能有误,请以原文为准:On the Utility of Pre-Trained Visual Representations for Policy Learning of Contact-Rich Insertion Tasks(arXiv 2611.17631)

核心内容 ​

针对机器人视动模仿学习中数据效率低及对视觉漂移敏感的问题,该研究聚焦富接触插入任务,系统评估了预训练视觉表征的实用性。实验对比了主流视觉基础模型与显式接触中心表征,在两个高度相似的插入任务中引入遮挡与物理公差等受控扰动轴进行测试。结果表明任务依赖性比既往宽泛评估更微妙,即便在近同任务间最优表征也存在差异,且微小环境变化会导致性能趋势发生不可预测的偏移。

尽管存在变异性,仿真与真机实验一致证实空间接地特别是接触中心信息对富接触策略学习具有独特价值。然而研究同时揭示,在真实视觉复杂度与传感器噪声条件下,可靠估计此类接触线索极其困难。这指出当前通用视觉表征在处理精密装配等强交互场景时的局限,强调未来需深化接触感知技术及其与视动策略学习的深度融合,而非单纯依赖互联网规模数据的通用先验。

关键看点 ​

  • 任务敏感性:即使两个插入任务高度相似,最优视觉表征选择仍不同,微小扰动导致性能趋势不可预测
  • 表征对比:在受控遮挡与物理公差扰动下,显式接触中心表征在插入任务中优于通用视觉基础模型
  • 核心优势:空间接地与接触中心信息被证实对富接触操作策略学习具有不可替代的独特价值
  • 工程瓶颈:在真实视觉复杂度与传感器噪声环境下,可靠估计接触线索仍是制约落地的关键难点

工程与产业观察 ​

该研究为具身智能算法选型提供关键实证:在精密装配等富接触场景中,盲目套用通用视觉大模型可能失效。工程师应优先构建或集成显式接触感知模块,将几何与力学约束作为策略学习的核心输入。同时提示数据采集需覆盖高保真接触状态与噪声分布,以解决Sim-to-Real中接触估计不准的工程痛点。

英文摘要 (Abstract) ​

Visuomotor imitation learning has become a predominant paradigm for real-world robotic manipulation, yet it remains data-inefficient and brittle to task-irrelevant visual shifts. Pre-trained visual representations promise to ease this burden by distilling priors from internet-scale data, but the ``right'' representation for robotics remains unresolved: existing studies span broad but sparse task distributions and reach conclusions that vary and even conflict, pointing to strong task and setting dependence. We examine this question by bringing a magnifying glass to a common contact-rich manipulation task: insertion. We compare representations from widely used vision foundation models against an explicit contact-centric representation on two closely related insertion tasks, perturb each along controlled axes of occlusion and physical tolerance, and test whether conclusions transfer to the real world. Task dependence proves to be more subtle than previous, broadly scoped evaluations revealed: the best representation differs even between our near-identical tasks, and small changes shift trends in unpredictable ways. Despite this variability, results across simulation and real-world experiments demonstrate the distinct value of spatially-grounded, and in particular, contact-centric information for contact-rich policy learning, while underscoring how difficult it is to estimate such cues reliably under realistic visual complexity and sensor noise. We hope these findings motivate further study of representations in contact-rich manipulation, along with advances in contact perception and its integration into visuomotor policy learning.

作者:Leon Kim, Dinesh Jayaraman, Michael Posa

基于本页技术方向关联的整机参数、核心零部件、实测报告与同赛道选型横评。

外部来源

本页事实对应的公开页面,以原文为准。(点击将离开本站)

  1. arXiv 2611.17631:On the Utility of Pre-Trained Visual Representations for Policy Learning of Contact-Rich Insertion Tasks ↗访问 2026-11-16