通过迭代学习控制提升模仿学习在变速运动中的频率外推精度
VFILC: Accurate Frequency Extrapolations in Imitation Learning via Sampling Frequency ILC
- 结合采样频率与运动频率的反馈机制，动态校正频率误差
- 在双倍训练速度下，擦除任务频率误差降低81%，摇动任务降低50%
- 适用于复杂摩擦场景，较基线方法提升27%精度，适合高精度机器人运动生成
传统的基于神经网络的变速运动模仿学习方法要么仅限于插值速度，要么在超出训练速度范围时产生不可预测的运动。变量频率模仿学习（VFIL）通过将神经网络模型的采样频率与运动频率关联，实现了速度外推，但其开环结构在高频外推场景中仍存在频率误差。本文提出基于前馈-反馈结构的变量频率模仿学习与迭代学习控制结合方法（VFILC），其中前馈部分利用VFIL，反馈部分用于修正频率误差。实验表明，该方法在三项任务中均成功实现运动速度的准确外推，且反馈机制显著降低频率误差：在双倍平均训练速度下，擦除任务误差降低81%，摇动任务降低50%；在受复杂摩擦影响的接触密集型搅拌任务中，精度相比VFIL提升27%。
原文摘要 · Abstract (English)
Conventional neural network (NN)-based imitation learning methods for variable-speed motion either restricted their scope to interpolated speeds, or generated unpredictable motions when extrapolating beyond trained velocity ranges. Variable-frequency imitation learning (VFIL) enabled extrapolations of speeds by linking the NN model's sampling frequency to the motion frequency, whereas its open-loop configuration caused frequency errors, especially in the extrapolated high-frequency settings. This study proposes variable-frequency imitation learning with iterative learning control (VFILC) based on a combination of VFIL and iterative learning control (ILC) with both feedforward and feedback parts, the former taking advantage of VFIL and the latter adjusting the frequency errors. The experimental results showed that the proposed method successfully and accurately extrapolated motion speeds and reduced frequency errors in all three tasks, and that the feedback especially reduced the frequency errors by a remarkable 81% in the wiping task and 50% in the shaking task, both compared to simple feedforward VFIL, when extrapolating at double the average speed in the training data. The proposed method also improved accuracy by 27% compared with VFIL even at an interpolated frequency for a contact-rich mixing task affected by complex friction traits.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。