Mechanical arm self-learning control method based on data driving

The invention belongs to the technical field of robots, and particularly relates to a mechanical arm self-learning control method based on data driving. Comprising the following steps that 1, an n-dimensional mechanical arm data driving model is established; secondly, a mechanical arm self-learning controller based on data driving is designed; and thirdly, an RBF neural network disturbance estimator is designed, and therefore control over self-learning of the mechanical arm is achieved. According to the method, the control and adjustment capacity of the joint angular position of the mechanical arm can be improved, the traditional mode that algorithm design is conducted through a model is changed, the controller is researched through real-time data of the controlled system, and a complex system can also be effectively controlled. 本发明属于机器人技术领域，具体的说是一种基于数据驱动的机械臂自学习控制方法。包括以下步骤：步骤一、建立n维机械臂数据驱动模型；步骤二、设计基于数据驱动的机械臂自学习控制器；步骤三、设计RBF神经网络扰动估计器，从而实现对机械臂自学习进行控制。本发明能够提高机械臂关节角位置的控制调节能力，改变传统依靠模型进行算法设计的方式，并且采用被控系统实时数据研究控制器，使复杂