Ye Fan, Abdulali Arsen, Chu Kai-Fung, Zhang Xiaoping, Iida Fumiya
Department of Engineering, University of Cambridge, Cambridge, UK.
School of Electrical and Control Engineering, North China University of Technology, Beijing, China.
Commun Eng. 2025 Apr 30;4(1):81. doi: 10.1038/s44172-025-00418-1.
Natural behavior emerging in nonlinear dynamical systems enables reservoir computers to control underactuated robots by approximating their inverse dynamics. Unlike other model-free approaches, the reservoir controllers are sample-efficient, meaning a weighted average of the reservoir output can be trained with a limited amount of pre-recorded data. However, developing and testing the reservoir controller relies on repetitive experiments that require researchers' proficiency in both robot and reservoir design. In this paper, we propose a design method for reliable reservoir controllers by synchronizing the timescales of the reservoir dynamics with those observed in the robot. The results demonstrate that our timescale alignment test filters out 99% of ineffective reservoirs. We further applied the selected reservoirs to computational tasks including short-term memory and parity checks, along with control tasks involving robot trajectory tracking. Our findings reveal that a higher computational capability reduces the control failure rate, though it concurrently increases the trajectory-tracking error.
非线性动力系统中出现的自然行为使储层计算机能够通过逼近欠驱动机器人的逆动力学来控制它们。与其他无模型方法不同，储层控制器具有样本高效性，这意味着可以用有限数量的预先记录数据训练储层输出的加权平均值。然而，开发和测试储层控制器依赖于重复性实验，这要求研究人员在机器人和储层设计方面都具备专业技能。在本文中，我们提出了一种通过使储层动力学的时间尺度与在机器人中观察到的时间尺度同步来设计可靠储层控制器的方法。结果表明，我们的时间尺度对齐测试滤除了99%无效的储层。我们进一步将选定的储层应用于包括短期记忆和奇偶校验在内的计算任务，以及涉及机器人轨迹跟踪的控制任务。我们的研究结果表明，更高的计算能力降低了控制失败率，尽管它同时增加了轨迹跟踪误差。
