空间智能软体机械臂动力学建模与控制

Dynamical modeling and intelligent control of space soft manipulator

空间智能软体机械臂因其结构轻巧、灵活可变、可折叠收缩等特性,在航天器在轨服务任务中,将具有广阔的应用前景。首先提出了一种全向驱动的模块化软体机械臂设计方案,利用刚柔耦合动力学理论建立了气控驱动的软体机械臂动力学模型,基于深度回归卷积神经网络理论建立了空间非合作目标检测与识别算法,为空间软体机械臂智能控制奠定了技术基础。进一步地,设计并研制了软体机械臂地面原理样机及其试验系统,通过地面试验,对软体机械臂的自主运动控制和识别算法进行了初步验证。

Space intelligent soft manipulator shows a broad prospect in the application of on-orbit service,due to its lightweight,dexterity and foldability.In this paper,a design of a modular soft manipulator with omnidirectional drivers was proposed.The dynamical model of the proposed soft manipulator was developed based on the rigid-flexible coupling system dynamics.The detection and recognition algorithm for space non-cooperative objects was designed based on deep regression convolution neural network.Both the dynamical model and the algorithm are the foundation for the intelligent control of the soft manipulator.Moreover,an experiment system of the soft manipulator was designed and developed,and the autonomous motion control and the recognition algorithm were validated.