水下作业机械手运动学分析与仿真

针对水下作业机械手难于实现负载能力与灵活性相统一的问题,设计了一种采用欠驱动机构的水下作业机械手,建立了该机械手的三维模型,并对机械手的工作原理和运动学特性进行了分析与仿真.从分析与仿真的结果可以看出,采用欠驱动机构可以解决机械手自由度数目、驱动方式、质量和灵活性之间的矛盾.该机械手采用液压方式实现对机械手11个自由度的驱动,具有驱动力大、结构简单、操作灵活的特点,可适应多种不同任务的水下作业需要.     

局部回归神经网络在水下机器人运动控制中的应用

探讨了水下机器人神经网络运动模型的结构,提出了带有局部回归结构的水下机器人神经网络控制器结构及预测控制的实现方法,给出了该神经网络的教师样本生成方法及学习方法,计算机仿真与水池实验结果验证了本文提出方法的有效性和可行性。     

一种具有柔顺抓取功能的水下作业机械手

建立了机械手的三维模型,对机械手的工作原理和静力学特性进行研究,分析了运动部件之间的相对关系;机械手采用液压驱动方式,驱动力大、结构简单;机械手有三个手指,采用4个驱动元件实现对机械手11个自由度的驱动,三个手指之间的相对位置可根据抓取目标物的形状而改变,抓取物体时具有形状自适应能力.     

Optical fiber based slide tactile sensor for underwater robots

In the underwater environment, many visual sensors don’t work, and many sensors which work well for robots working in space or on land can not be used underwater. Therefore, an optical fiber slide tactile sensor was designed based on the inner modulation mechanism of optical fibers. The principles and structure of the sensor are explained in detail. Its static and dynamic characteristics were analyzed theoretically and then simulated. A dynamic characteristic model was built and the simulation made using the GA based neural network. In order to improve sensor response, the recognition model of the sensor was designed based on the ‘inverse solution’ principle of neural networks, increasing the control precision and the sensitivity of the manipulator.