远程控制采摘机器人手势识别研究——基于势场蚁群算法  

Research on Hand Gesture Recognition of Remote Control Picking Robot Based on Potential Field and Ant Colony Algorithm

作　　者：袁路路[1] 张娓娓[1] 

机构地区：[1]河南工业职业技术学院,河南南阳473000

出　　处：《农机化研究》2017年第5期236-240,共5页Journal of Agricultural Mechanization Research

基　　金：河南省自然科学基金项目(2015ZCB115);南阳市科技攻关项目(2012GG029)

摘　　要：采摘机器人在作业时遇到通过自主导航无法越过的障碍物时,或者在危险的地带无法进行人工采摘作业时,需要借助远程方式进行实时控制,使其成功越过障碍物,并在高危环境中有效地展开采摘作业。为了优化采摘机器人远程控制系统,提出了一种基于手势识别的远程控制方案,并引入了势场蚁群算法,提高了机器人的控制的准确性和高效性。在远程控制方案中,将基于视觉的手势识别与远程控制机械手相结合,通过深度相机采集手势图像并提取手势特征,转换为机械手舵机的控制命令,并通过无线网络发送至采摘机器人控制单元,实现视觉手势对机器人的远程控制。对采摘机器人进行了测试,通过测试发现:基于蚁群算法的手势识别系统可以有效地追踪得到不同的动态手势,且可以准确地识别手势所代表的意义,成功实现了机器人远程控制的手势识别。该方法不仅可以远程实现机器人避障功能,还可以将其应用在山谷、沼泽等危险地带进行采摘作业,实现其非凡的使用价值。When the robot is unable to cross the obstacle in the operation, or when the dangerous area can not be manu- ally picked up, it needs to use the remote method for real-time control, so that it can successfully cross the obstacles, and in the high risk environment to carry out the picking operation effectively. In order to optimize the robot remote con- trol system, a remote control scheme based on gesture recognition is proposed, and the potential field ant colony algorithm is introduced to improve the accuracy and efficiency of the robot. In the remote control scheme, the gesture recognition combined with remote control robot arm based on the depth camera gesture image and extract the gesture features into ma- nipulator servo control commands, and through the wireless network to the picking robot control unit, to realize the re- mote control of the robot visual gestures. Finally, the robot is tested. The recognition system based on ant colony algo- rithm can effectively track the different dynamic gestures, and can accurately identify the meaning of gestures. This meth- od can not only realize the function of obstacle avoidance, but also can be used in the area of the valley, the swamp and so on.

关 键 词：采摘机器人 人工势场 蚁群算法 手势识别 远程控制 

分 类 号：S225[农业科学—农业机械化工程] TP391.41[农业科学—农业工程]