Variable-Frequency Imitation Learning for Variable-Speed Motion

TL;DR

Experimental results showed that the proposed variable-frequency imitation learning (VFIL) improved the velocity-wise accuracy along both the interpolated and extrapolated frequency labels, in addition to a 12.5 % increase in the overall success rate.

Abstract

Conventional methods of imitation learning for variable-speed motion have difficulty extrapolating speeds because they rely on learning models running at a constant sampling frequency. This study proposes variable-frequency imitation learning (VFIL), a novel method for imitation learning with learning models trained to run at variable sampling frequencies along with the desired speeds of motion. The experimental results showed that the proposed method improved the velocity-wise accuracy along both the interpolated and extrapolated frequency labels, in addition to a 12.5 % increase in the overall success rate.

Figures (11)

• Figure 1: Flow of the conventional and the proposed methods.
• Figure 2: Adjustment of time steps between the learning model and control loop.
• Figure 3: Block diagrams of four-channel bilateral control and bilateral control-based imitation learning.
• Figure 4: Procedure of the wiping task taught through bilateral control.
• Figure 5: CRANE-X7 manipulator with a cross-structured hand.