公开(公告)号：US20140063241A1

公开(公告)日：2014-03-06

申请号：US14005138

申请日：2012-02-29

申请人： Gang Li ,  Yakup Genc ,  Siddharth Ram Chhatpar ,  Sandeep M. Naik ,  Roy Barr ,  Daniel Sacco ,  Alexander Gelbman

发明人： Gang Li ,  Yakup Genc ,  Siddharth Ram Chhatpar ,  Sandeep M. Naik ,  Roy Barr ,  Daniel Sacco ,  Alexander Gelbman

IPC分类号： G06T7/00 ,  H04N7/18

CPC分类号： G06T7/0044 ,  G06T7/0008 ,  G06T7/001 ,  G06T7/74 ,  G06T7/75 ,  G06T2207/30108 ,  H04N7/18

摘要： A multi-view stereo approach generates an inventory of objects located on an object holder. An object may be a sample tube and an object holder may be a tube rack as used in lab automation for healthcare diagnostics. A processor performs 3D tracking of the object holder and the geo-metric analysis of multiple images generated by a calibrated camera. A homography mapping between images is utilized to warp a second image to a viewpoint of a first image. Plane induced parallax causes a normalized cross-correlation score between the first image and the warped second image of a location on the holder that has an object that is significantly different from a normalized cross-correlation score of a location that has not an object and enables the processor to infer tube inventory and absence or presence of a tube at a location in a rack.

摘要翻译： 多视图立体声方法生成位于对象持有者上的对象的清单。 物体可以是样品管，并且物体保持器可以是用于医疗诊断的实验室自动化中使用的管架。 处理器执行对象持有者的3D跟踪以及由校准的相机产生的多个图像的地理度量分析。 利用图像之间的单应性映射来将第二图像扭曲到第一图像的视点。 平面引起的视差导致第一图像与持有者位置翘曲的第二图像之间的归一化互相关分数，其具有与没有对象并且使能的位置的归一化互相关分数显着不同的对象 处理器用于推断管道库存，并且在机架中的位置处不存在或存在管。

公开(公告)号：US09367918B2

公开(公告)日：2016-06-14

申请号：US14005138

申请日：2012-02-29

申请人： Gang Li ,  Yakup Genc ,  Siddharth Ram Chhatpar ,  Sandeep M. Naik ,  Roy Barr ,  Daniel Sacco ,  Alexander Gelbman

发明人： Gang Li ,  Yakup Genc ,  Siddharth Ram Chhatpar ,  Sandeep M. Naik ,  Roy Barr ,  Daniel Sacco ,  Alexander Gelbman

IPC分类号： G06T7/00 ,  H04N7/18

CPC分类号： G06T7/0044 ,  G06T7/0008 ,  G06T7/001 ,  G06T7/74 ,  G06T7/75 ,  G06T2207/30108 ,  H04N7/18

摘要： A multi-view stereo approach generates an inventory of objects located on an object holder. An object may be a sample tube and an object holder may be a tube rack as used in lab automation for healthcare diagnostics. A processor performs 3D tracking of the object holder and the geometric analysis of multiple images generated by a calibrated camera. A homography mapping between images is utilized to warp a second image to a viewpoint of a first image. Plane induced parallax causes a normalized cross-correlation score between the first image and the warped second image of a location on the holder that has an object that is significantly different from a normalized cross-correlation score of a location that has not an object and enables the processor to infer tube inventory and absence or presence of a tube at a location in a rack.

摘要翻译： 多视图立体声方法生成位于对象持有者上的对象的清单。 物体可以是样品管，并且物体保持器可以是用于医疗诊断的实验室自动化中使用的管架。 处理器执行物体保持器的3D跟踪以及由校准的相机产生的多个图像的几何分析。 利用图像之间的单应性映射来将第二图像扭曲到第一图像的视点。 平面引起的视差导致第一图像与持有者位置翘曲的第二图像之间的归一化互相关分数，其具有与没有对象并且使能的位置的归一化互相关分数显着不同的对象 处理器用于推断管道库存，并且在机架中的位置处不存在或存在管。

公开(公告)号：US20140005829A1

公开(公告)日：2014-01-02

申请号：US14004859

申请日：2012-03-16

申请人： Siddharth Ram Chhatpar ,  Sandeep M. Naik

发明人： Siddharth Ram Chhatpar ,  Sandeep M. Naik

IPC分类号： G05B19/04

CPC分类号： G05B19/04 ,  B25J9/1692 ,  G05B2219/39021 ,  G05B2219/39024

摘要： Disclosed are methods adapted to aid in a calibration of a robotic end effector. The method includes providing a robotic component having an end effector and a light beam sensor provided in a fixed orientation to the end effector fingers, rotating a light beam of the light beam sensor relative to a geometrical calibration feature of a teach tool mounted in an approximately known orientation to an article, and determining a precise location (e.g., center) of the geometrical calibration feature based upon engagement of the light beam with edges of the geometrical calibration feature. In another aspect, a rotational orientation of the fingers of the end effector are calibrated using the teach tool. A novel teach tool and a robot calibration system including the teach tool are disclosed, as are other aspects.

摘要翻译： 公开了适于帮助机器人末端执行器的校准的方法。 该方法包括提供具有端部执行器和光束传感器的机器人部件，光束传感器以固定方向设置在末端执行器指状件上，使光束传感器的光束相对于安装在大致上安装的教导工具的几何校准特征 基于物体的已知取向，以及基于所述光束与所述几何校准特征的边缘的接合来确定所述几何校准特征的精确位置（例如，中心）。 在另一方面，使用教导工具来校准端部执行器的手指的旋转取向。 公开了一种新颖的教学工具和包括教学工具的机器人校准系统，以及其他方面。

公开(公告)号：US09310791B2

公开(公告)日：2016-04-12

申请号：US14004859

申请日：2012-03-16

申请人： Siddharth Ram Chhatpar ,  Sandeep M. Naik

发明人： Siddharth Ram Chhatpar ,  Sandeep M. Naik

IPC分类号： G05B19/401 ,  B25J9/16 ,  G05B19/04

CPC分类号： G05B19/04 ,  B25J9/1692 ,  G05B2219/39021 ,  G05B2219/39024

摘要： Disclosed are methods adapted to aid in a calibration of a robotic end effector. The method includes providing a robotic component having an end effector and a light beam sensor provided in a fixed orientation to the end effector fingers, rotating a light beam of the light beam sensor relative to a geometrical calibration feature of a teach tool mounted in an approximately known orientation to an article, and determining a precise location (e.g., center) of the geometrical calibration feature based upon engagement of the light beam with edges of the geometrical calibration feature. In another aspect, a rotational orientation of the fingers of the end effector are calibrated using the teach tool. A novel teach tool and a robot calibration system including the teach tool are disclosed, as are other aspects.

摘要翻译： 公开了适于帮助机器人末端执行器的校准的方法。 该方法包括提供具有端部执行器和光束传感器的机器人部件，光束传感器以固定方向设置在末端执行器指状件上，使光束传感器的光束相对于安装在大致上安装的教导工具的几何校准特征 基于物体的已知取向，以及基于所述光束与所述几何校准特征的边缘的接合来确定所述几何校准特征的精确位置（例如，中心）。 在另一方面，使用教导工具来校准末端执行器的手指的旋转取向。 公开了一种新颖的教学工具和包括教学工具的机器人校准系统，以及其他方面。