首页|Patent Application Titled 'Method For Ascertaining A Descriptor Image For An Ima ge Of An Object' Published Online (USPTO20240331213)
Patent Application Titled 'Method For Ascertaining A Descriptor Image For An Ima ge Of An Object' Published Online (USPTO20240331213)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
Reporters obtained the following quote from the background information supplied by the inventors: “In order to enable flexible production or processing of the o bjects by a robot, it is desirable for the robot to be able to handle an object regardless of the position in which the object is placed in the workspace of the robot. The robot should therefore be able to recognize which parts of the objec t are in which positions, so that it can, for instance, grab the object at the c orrect location, for example to fasten it to another object or weld the object a t the current location. This means that the robot should be able to recognize th e pose (position and orientation) of the object, for example from one or more im ages taken by a camera attached to the robot, or ascertain the position of locat ions for picking up or processing. One approach to achieving this is determining descriptors, i.e., points (vectors) in a predefined descriptor space, for parts of the object (i.e. pixels of the object represented in an image plane), wherei n the robot is trained to assign the same descriptors to the same parts of an ob ject regardless of a current pose of the object and thus recognize the topology of the object in the image, so that it is then known, for example, where which c orner of the object is located in the image. Knowing the pose of the camera then makes it possible to infer the pose of the object. The recognition of the topol ogy can be realized with a machine learning model (ML model) that is trained acc ordingly.
NETL
NSTL
