首页> 外国专利> SYSTEM AND METHOD FOR DETERMINING GRASPING POSITIONS FOR TWO-HANDED GRASPS OF INDUSTRIAL OBJECTS

SYSTEM AND METHOD FOR DETERMINING GRASPING POSITIONS FOR TWO-HANDED GRASPS OF INDUSTRIAL OBJECTS

机译:确定工业对象的两手抓握的抓握位置的系统和方法

摘要

A system (100) and method (300) is provided for determining grasping positions for two- handed grasps of industrial objects. The system may include a processor configured to determine a three dimensional (3D) voxel grid (136) for a 3D model (150) of a target object (120). In addition, the processor may be configured to determine at least one pair of spaced apart grasping positions (126, 128) on the target object at which the target object is capable of being grasped with two hands at the same time based on processing the 3D voxel grid for the target object with a neural network (138) trained to determine grasping positions for two-handed grasps of target objects using training data (140). Such training data may include 3D voxel grids (142) of a plurality of 3D models (144) of training objects (206) and grasping data (146) including corresponding pairs of spaced-apart grasping positions (208) for two-handed grasps of the training objects. Also, the processor may be configured to provide output data (124) that specifies the determined grasping positions (126, 128) on the target object for two-handed grasps.
机译:提供一种用于确定工业物品的双手抓握的抓握位置的系统(100)和方法(300)。该系统可以包括处理器,该处理器被配置为确定目标对象(120)的3D模型(150)的三维(3D)体素网格(136)。另外,处理器可以被配置为基于对3D的处理,确定能够用两只手同时抓住目标物体的目标物体上的至少一对间隔的抓握位置(126、128)。具有训练的神经网络的目标网络的体素网格(138),用于使用训练数据(140)确定目标对象的双手抓握的抓握位置。这样的训练数据可以包括训练对象(206)的多个3D模型(144)的3D体素网格(142)和包括用于双手抓握的相应的成对的间隔开的抓握位置(208)的抓握数据(146)。训练对象。而且,处理器可被配置为提供输出数据(124),该输出数据指定用于双手抓握的目标物体上确定的抓握位置(126、128)。

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号