Time Series Motion Generation Considering Long Short-Term Motion
This work addresses the problem of enabling robots to perform adaptive, long-term motion tasks in human interaction, but it is incremental as it builds on prior imitation learning and multi-decimation methods.
The paper tackled the challenge of generating robot motions for tasks involving long-term (slow) movements, such as writing with a pen, by proposing a method that separates and infers short-term and long-term motion components using a multi-decimation approach. The result experimentally verified the method's validity, showing differences in suitable sampling periods for position and force information.
Various adaptive abilities are required for robots interacting with humans in daily life. It is difficult to design adaptive algorithms manually; however, by using end-to-end machine learning, labor can be saved during the design process. In our previous research, a task requiring force adjustment was achieved through imitation learning that considered position and force information using a four-channel bilateral control. Unfortunately, tasks that include long-term (slow) motion are still challenging. Furthermore, during system identification, there is a method known as the multi-decimation (MD) identification method. It separates lower and higher frequencies, and then identifies the parameters characterized at each frequency. Therefore, we proposed utilizing machine learning to take advantage of the MD method to infer short-term and long-term (high and low frequency, respectively) motion. In this paper, long-term motion tasks such as writing a letter using a pen fixed on a robot are discussed. We found differences in suitable sampling periods between position and force information. The validity of the proposed method was then experimentally verified, showing the importance of long-term inference with adequate sampling periods.