Phase-Amplitude Reduction-Based Imitation Learning
This work addresses the need for safer and more predictable imitation learning in robotics, particularly for human-like movement generation, though it appears incremental as it builds on existing dynamical system-based methods.
The authors tackled the problem of enabling robots to imitate human movement trajectories, including transient movements from initial or disturbed states to a limit cycle, resulting in a method that more accurately generates these transient movements compared to a conventional approach, as validated in simulated and real robot arm tasks.
In this study, we propose the use of the phase-amplitude reduction method to construct an imitation learning framework. Imitating human movement trajectories is recognized as a promising strategy for generating a range of human-like robot movements. Unlike previous dynamical system-based imitation learning approaches, our proposed method allows the robot not only to imitate a limit cycle trajectory but also to replicate the transient movement from the initial or disturbed state to the limit cycle. Consequently, our method offers a safer imitation learning approach that avoids generating unpredictable motions immediately after disturbances or from a specified initial state. We first validated our proposed method by reconstructing a simple limit-cycle attractor. We then compared the proposed approach with a conventional method on a lemniscate trajectory tracking task with a simulated robot arm. Our findings confirm that our proposed method can more accurately generate transient movements to converge on a target periodic attractor compared to the previous standard approach. Subsequently, we applied our method to a real robot arm to imitate periodic human movements.