Computed torque control with variable gains through Gaussian process regression
Computed torque control with variable gains through Gaussian process regression
复制标题
通过高斯过程回归计算具有可变增益的扭矩控制
DOI：
10.1109/humanoids.2014.7041362
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
F. Stulp
中科院分区：
文献类型：
--
作者：
N. Alberto;M. Mistry;F. Stulp
在计算力矩控制中，机器人的动力学是通过动力学模型来预测的。这使得能够进行更顺应的控制，因为可以降低反馈项的增益，因为补偿机器人动力学的任务从反馈委派到前馈项。前人的工作表明，通过将前馈扭矩设置为高斯过程的平均值，高斯过程回归是学习计算转矩控制的一种有效方法。我们还通过利用高斯过程预测的方差来扩展这项工作，如果方差较低，则降低增益。这使得增益能够自动适应计算的扭矩模型中的不确定性，并随着机器人随着时间的推移学习更准确的模型而导致更符合要求的低增益控制。在一个模拟的7自由度机器人机械手上，我们演示了如何实现准确的跟踪，尽管增益随着时间的推移而降低。
In computed torque control, robot dynamics are predicted by dynamic models. This enables more compliant control, as the gains of the feedback term can be lowered, because the task of compensating for robot dynamics is delegated from the feedback to the feedforward term. Previous work has shown that Gaussian process regression is an effective method for learning computed torque control, by setting the feedforward torques to the mean of the Gaussian process. We extend this work by also exploiting the variance predicted by the Gaussian process, by lowering the gains if the variance is low. This enables an automatic adaptation of the gains to the uncertainty in the computed torque model, and leads to more compliant low-gain control as the robot learns more accurate models over time. On a simulated 7-DOF robot manipulator, we demonstrate how accurate tracking is achieved, despite the gains being lowered over time.