剖析数据稀缺机器人插装中的运动先验正则化
Dissecting Motion-Prior Regularization for Data-Scarce Robotic Insertion
浏览论文内容
中文总结 AI 辅助
本研究通过真实机器人实验比较多种运动先验正则化对数据稀缺插装任务的影响，发现最小加加速度正则化简单有效，联合正则化无额外增益。
中文摘要 AI 辅助
本研究探讨在仅从15个演示中学习扩散策略时，训练时的运动先验正则化能否提高插装成功率。最小加加速度（minimum jerk）抑制预测平移加速度的突变；速度-曲率正则化则将运动速度与路径几何耦合。这些是任务完成的候选机制，而非安全保证。我们分别及联合比较这些先验、无先验以及通用平滑性，每种设置进行80次真实机器人试验，结果汇总自四类记录条件。联合设置和仅最小加加速度设置均达到70/80次成功（87.5%），而仅速度-曲率设置为69/80次（86.3%），无先验为66/80次（82.5%），通用平滑性为67/80次（83.8%）。成功率和Wilson 95%置信区间以可视化形式呈现以供直接比较。联合正则化比无先验高出5.0个百分点，但相比仅最小加加速度未观察到增益。结果支持最小加加速度作为更简单的复现候选，但未确立协同效应、生物力学特异性、安全性改进或分布偏移鲁棒性。
英文摘要
This study asks whether training-time motion-prior regularization can improve insertion success when a diffusion policy is learned from only 15 demonstrations. Minimum jerk discourages abrupt changes in predicted translational acceleration; speed-curvature regularization instead couples movement speed to path geometry. These are candidate mechanisms for task completion, not safety guarantees. We compare the priors individually and jointly, neither prior, and generic smoothness, with 80 real-robot trials per setting pooled over four recorded condition classes. Joint and minimum-jerk-only settings each achieved 70/80 successes (87.5%), versus 69/80 (86.3%) for speed-curvature only, 66/80 (82.5%) for neither prior, and 67/80 (83.8%) for generic smoothness. Success rates and Wilson 95% confidence intervals are visualized for direct comparison. Joint regularization exceeded neither by 5.0 percentage points but provided no observed gain over minimum jerk alone. The results motivate minimum jerk as the simpler candidate for replication, without establishing synergy, biomechanical specificity, improved safety, or distribution-shift robustness.
发表机构
- University of Tennessee（田纳西大学）
- University of Florida（佛罗里达大学）
机构由 AI 辅助整理，请以论文原文为准。
