Application of neural networks in inverse dynamics based contact force estimation
Application of neural networks in inverse dynamics based contact force estimation
复制标题
神经网络在逆动力学接触力估计中的应用
DOI：
--
复制
发表时间：
2005
期刊：
影响因子：
--
通讯作者：
K. Hashtrudi
中科院分区：
文献类型：
--
作者：
Andrew C. Smith;K. Hashtrudi
在大多数机器人应用中，包括操纵和人-机器人交互，需要监测和控制接触力。合规控制器要求通过商业化的力/扭矩传感器提供高精度的力测量。然而，这些传感器价格昂贵，体积较大，容易受到冲击力的影响。解决这一困境的一个常见方法是使用力观测器，它利用系统动力学的全部知识来估计外力。然而，一些机器人系统具有复杂的动力学，这些动力学可能完全和准确地知道，也可能不完全知道。在这些情况下，实施动态观察员将不会导致准确的部队估计。本文提出在基于逆动力学的力观测中使用神经网络，而不需要完全确定系统动力学。我们还表明，对于软环境中的慢速操作，观测器在没有加速度输入的情况下估计外力
In the majority of robotic applications, including manipulation and human-robot interaction, contact force needs to be monitored and controlled. Compliance controllers demand high precision force measurement that can be delivered by commercial force/torque sensors. However, these sensors are expensive, rather bulky and vulnerable to impact forces. A common solution to this dilemma is the use of force observers, which estimate external forces using full knowledge about system dynamics. However, some robotic systems have complicated dynamics that may or may not be known entirely and precisely. In these situations the implementation of dynamic observers would not result in accurate force estimation. This paper proposes the use of neural networks in an inverse dynamics based force observation without the need for complete determination of system dynamics. We also show that for slow operations on soft environments, the observer estimates external forces without acceleration input