基于体感交互的仿上肢采摘机器人系统设计与仿真  

Design and simulation of artificial limb picking robot based on somatosensory interaction

作　　者：许常蕾 王庆[1] 陈洪[1] 梅树立[1] 杜利强[1] 

机构地区：[1]中国农业大学信息与电气工程学院,北京100083

出　　处：《农业工程学报》2017年第S1期49-55,共7页Transactions of the Chinese Society of Agricultural Engineering

基　　金：国家科技支撑计划项目(2015BAH28F00);北京市自然科学基金资助项目(4172034)

摘　　要：为提高农业自动化程度,保持农业机械化水平,提高农业生产效率,该文设计了一种基于仿生学,能够实时模仿人类上肢采摘行为的果实采摘机器人系统。该文首先分析了当操作者的采摘动作发生时,系统利用深度相机Kinect采集人体关节骨架信息,通过空间向量计算,计算出关节的位置偏移量和骨骼转动角度等信息,利用这些特征构建人体三维骨架模型;其次分析了人体上肢的生理学结构和自由度,依据仿生学的特点建立了人体上肢五自由度运动学模型。系统将识别到的动作指令发送到动作执行模块,带动机械臂的转动。最后,为了验证模型的有效性,进行了机器人动作模仿仿真试验,统计了系统对动作的识别率。分析结果表明,系统对采摘动作的平均识别率为90%以上,从而验证了原理设计的有效性。该系统设计可为五自由度机械臂模型的开发和控制提供参考。In order to improve the automation degree in agriculture, reduce the workload of farmers, enhance labor efficiency and product quality and ensure that the fruit can be harvested in real time, we designed a robot system which can imitate human picking behavior and pick fruits in real time. In this paper, we first analyzed the physiological characteristics of human upper limb and built a motion model according to human upper limb movement. In the model we selected the key joints and bones as the acquisition object, while the acquisition information includes its location, angle, speed and some other information. In addition, based on the bionics characteristics, we built a motion model of the robot manipulator. The system can gather the skeleton information of the human body using the depth camera Kinect device when the human picking movement occurs. After that the system calculates the position deviation of the joint and the rotation angle of the skeleton by calculating the space vector. At the same time, the system calculates the robot arm for each joint position and rotation angle information. According to the information of instructions, the system can translate the mathematical information into many instructions and send them to the robot manipulator. The robot manipulator will follow the instruction and fulfill the task of picking in real time when instructions have been received correctly. The action system includes 3 main sub-modules: information acquisition module, instruction transition module and instruction execution module. The information acquisition module uses a depth camera Kinect device and acquires the desired three-dimensional(3D) physiological data from the human behavior. The degree of mechanical freedom of human arm is 7 while five-axis robot limb is enough to arrive anywhere human limb can arrive. So the paper built a model with 5 degrees of mechanical freedom to imitate the human picking behavior. The 3D information includes 3 kinds of physiological parameters: position, velocity and angle i

关 键 词：机器人 交互 模型 运动获取 动作翻译 骨架模型 机械臂 体感交互 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]