Seeing Through the Displaced Frame: Privileged Noise Distillation for Vision-Force Precision Assembly
作者: Ching-Hsiang Chang, Tzu-Yu Chuang, Yi-Hsiu Lee, Yi-Ting Chen, Yuan-Fu Yang, Min Sun
分类: cs.RO
发布日期: 2026-10-06
备注: 8 pages
🔗 代码/项目: PROJECT_PAGE
💡 一句话要点
提出特权噪声蒸馏以解决精密装配中的姿态误差问题
🎯 匹配领域: 支柱二:RL算法与架构 (RL & Architecture)
关键词: 姿态误差 精密装配 特权教师 噪声蒸馏 行为克隆 机器人学习 鲁棒性
📋 核心要点
- 现有方法在处理姿态误差时,无法有效识别和补偿坐标框架的偏移,导致精密装配的成功率显著下降。
- 论文提出通过特权教师和重新标记的干净演示来补充缺失的信息,从而提高机器人在姿态噪声下的表现。
- 实验结果显示,采用特权路径的学生在高噪声环境下的成功率显著高于传统基于状态的方法,验证了提出方法的有效性。
📝 摘要(中文)
在精密装配中,姿态误差不仅会影响机器人观察的内容,还会干扰其行动的坐标框架。在FORGE基准测试中,官方基于状态的策略在真实姿态下的成功率为97%至99%,但在$σ=5$ mm的姿态噪声设置下仅为32%至60%。为了解决这一问题,论文提出了两种方法来补充缺失的信息:一是通过特权教师在模拟中观察偏移,二是将干净的演示重新标记为位移框架。实验结果表明,采用特权路径的学生在$σ=0$到5 mm的任务中成功率保持在92%至99%,而六个非特权基线的成功率仅为2%至80%。
🔬 方法详解
问题定义:论文要解决的问题是姿态误差对精密装配的影响,现有方法在姿态噪声下表现不佳,导致成功率显著下降。
核心思路:论文的核心思路是通过引入特权教师和干净演示的重新标记,提供额外的信息来补偿姿态偏移,从而提高机器人的精度和鲁棒性。
技术框架:整体架构包括特权教师在模拟环境中观察偏移、干净演示的重新标记、以及学生模型的行为克隆训练和DAgger轮次。主要模块包括数据收集、模型训练和测试阶段。
关键创新:最重要的技术创新点在于通过特权教师提供的额外信息和重新标记的演示,显著提高了机器人在高噪声环境下的成功率,与现有方法相比具有本质的区别。
关键设计:关键设计包括特权教师的构建、演示数据的处理方式、损失函数的选择,以及学生模型的网络结构设计,确保模型能够有效学习到姿态补偿的能力。
🖼️ 关键图片
📊 实验亮点
实验结果显示,采用特权路径的学生在$σ=0$到5 mm的任务中成功率保持在92%至99%,而六个非特权基线的成功率仅为2%至80%。在相同的学生架构和训练程序下,使用特权和重新标记的演示成功率分别达到88.7%和95.8%,显示出显著的性能提升。
🎯 应用场景
该研究的潜在应用领域包括工业机器人精密装配、自动化生产线和智能制造等。通过提高机器人在复杂环境下的鲁棒性,能够显著提升生产效率和产品质量,具有重要的实际价值和未来影响。
📄 摘要(原文)
Pose error in precision assembly can corrupt not only what a robot observes but also the coordinate frame in which it acts. On the FORGE benchmark, the official state-based policy succeeds in 97% to 99% of episodes with the true pose but only 32% to 60% at the benchmark's $σ=5$ mm pose-noise setting. The same estimated pose enters the observation and anchors the action frame, making the offset unidentifiable from proprioceptive state alone before contact. We supply this missing information during training in two ways. A privileged teacher observes the offset in simulation, while clean demonstrations can instead be relabelled into the displaced frame in closed form. The deployed student is trained with behaviour cloning followed by one DAgger round and receives only noisy state, a raw wrench window, and two RGB cameras at test time. On the unmodified FORGE tasks, the teacher-route student maintains 92% to 99% success across $σ=0$ to 5 mm, while six non-privileged baselines fall to 2% to 80%. A matched behaviour-cloning experiment isolates the source of this robustness. With the same student architecture, data budget, and training procedure, demonstrations generated without offset access yield only 31.5% success at $σ=5$ mm, whereas privileged and relabelled demonstrations reach 88.7% and 95.8%. Deployed zero-shot on a Franka, the student reaches 83.3% pooled success at $σ=5$ mm against 34.4% for the strongest state-based policy. Deployable sensing alone is insufficient. Robustness requires supervision that encodes compensation for the latent frame offset.Project page: https://drychang.github.io/displaced-frame/