Using robots to assemble parts has always been a research hotspot, but the traditional analysis model of assembly mainly focuses on establishing the linear equation between the feedback force and the relative position of the peg and hole, which leads to high requirements for the material properties and geometric parameters of the assembly parts. In this paper, a new assembly strategy is proposed that learns skills from manual teaching to carry out the assembly process. A Gauss mixture model and regression is used to fit the teaching data, and then, the compliance control method is applied to conduct assembly when the geometric profile parameters and material elastic parameters of the assembly are inaccurate. Finally, the experiment was implemented under the tolerance is 0.18 mm, and the success rate reaches 100%. These findings verified the effectiveness of the compliance control method.

使用机器人组装零件一直是研究的热点，但是传统的组装分析模型主要着眼于建立反馈力与销钉和孔的相对位置之间的线性方程，这对材料性能和对材料的要求很高。装配零件的几何参数。在本文中，提出了一种新的组装策略，该策略将从手工教学中学习技能以执行组装过程。使用高斯混合模型和回归模型拟合教学数据，然后在装配的几何轮廓参数和材料弹性参数不准确时，采用柔性控制方法进行装配。最后，在0.18mm的公差下进行了实验，成功率达到了100％。