Martinez Santiago, Garcia-Haro Juan Miguel, Victores Juan G, Jardon Alberto, Balaguer Carlos
System Engineering and Automation Department, University Carlos III, Av de la Universidad, 30, Madrid 28911, Spain.
Sensors (Basel). 2018 Mar 11;18(3):836. doi: 10.3390/s18030836.
The computational complexity of humanoid robot balance control is reduced through the application of simplified kinematics and dynamics models. However, these simplifications lead to the introduction of errors that add to other inherent electro-mechanic inaccuracies and affect the robotic system. Linear control systems deal with these inaccuracies if they operate around a specific working point but are less precise if they do not. This work presents a model improvement based on the Linear Inverted Pendulum Model (LIPM) to be applied in a non-linear control system. The aim is to minimize the control error and reduce robot oscillations for multiple working points. The new model, named the Dynamic LIPM (DLIPM), is used to plan the robot behavior with respect to changes in the balance status denoted by the zero moment point (ZMP). Thanks to the use of information from force-torque sensors, an experimental procedure has been applied to characterize the inaccuracies and introduce them into the new model. The experiments consist of balance perturbations similar to those of push-recovery trials, in which step-shaped ZMP variations are produced. The results show that the responses of the robot with respect to balance perturbations are more precise and the mechanical oscillations are reduced without comprising robot dynamics.
通过应用简化的运动学和动力学模型，类人机器人平衡控制的计算复杂度得以降低。然而，这些简化会引入误差，这些误差会叠加到其他固有的机电不精确性上，并影响机器人系统。如果线性控制系统在特定工作点附近运行，它们可以处理这些不精确性，但如果不在该工作点附近运行，则精度较低。这项工作提出了一种基于线性倒立摆模型（LIPM）的模型改进方法，以应用于非线性控制系统。目的是最小化控制误差并减少机器人在多个工作点的振荡。新模型名为动态LIPM（DLIPM），用于根据零力矩点（ZMP）表示的平衡状态变化来规划机器人行为。由于使用了来自力 - 扭矩传感器的信息，已应用一种实验程序来表征不精确性并将其引入新模型。实验包括类似于推 - 恢复试验的平衡扰动，其中会产生阶跃状的ZMP变化。结果表明，机器人对平衡扰动的响应更精确，并且在不影响机器人动力学的情况下减少了机械振荡。
