首页> 外国专利> ADAPTIVE AID GRANT FOR EDUCATION

ADAPTIVE AID GRANT FOR EDUCATION

机译:自适应助学金

摘要

An adaptive vision-based controller for controlling a robot arm for example is disclosed. The controller comprising: a camera; a segmenter for analysing images from the camera as regards their content; a tracker, sketcher and ranger responsive inter alia to information from the segmenter for creating a three dimensional segmented data list; a recogniser for receiving the data list and comparing data in the list against a database of plausible objects; and a planner interactive with the recogniser and responsive to task definitions for developing control outputs. The segmenter decomposes the images into regions of approximately uniform hue and the sketcher generates a sketch of the image, the sketch being composed of arcs each of which represents a significant feature in the image. The tracker tracks features and regions of interest through a series of images, and the ranger generates depth and scale information from the multiple views. Thus the job of the ranger is to construct a three dimensional representation of the scene which is invariant with respect to movement of the camera. The recogniser uses scenic information such as feature maps produced by the segmenter, etc., in conjunction with a knowledge base to construct a world model which is a logical representation of the world as seen through the camera. The planner uses the world model and the task definitions to construct a plan in the form of a set of actions for accomplishing the defined task. The planner also generates demands for further information from other subsystems as and when they are required. An action servo is optionally provided to bypass the tracker, sketcher and ranger and the recogniser and pass data from the segmenter directly to the planner once an object has been recognized. By way of the control system, information about how the robot arm is actually performing a task can be quickly compared with the desired task and the desired task can be updated if necessary. Thus the controller provides visual feed back control of the task performed by the robot arm.
机译:例如,公开了一种用于控制机器人手臂的基于自适应视觉的控制器。所述控制器包括:照相机;分割器,用于分析来自摄像机的图像的内容;跟踪器,草绘器和测距仪尤其响应于来自分段器的信息以创建三维分段数据列表;识别器,用于接收数据列表并将列表中的数据与合理对象数据库进行比较;以及与识别器交互并响应任务定义以开发控制输出的计划器。分割器将图像分解成近似均匀的色调区域,草绘器生成图像的草图,该草图由弧组成,每个弧代表图像中的重要特征。跟踪器通过一系列图像跟踪特征和感兴趣的区域,并且测距仪从多个视图生成深度和比例信息。因此,护林员的工作是构造场景的三维表示,该三维表示相对于摄像机的运动是不变的。识别器将风景区信息(例如由分段器生成的特征图等)与知识库一起使用,以构建一个世界模型,该模型是通过相机看到的世界的逻辑表示。计划者使用世界模型和任务定义以一组动作的形式构造计划,以完成定义的任务。计划者还会在需要时从其他子系统生成对更多信息的需求。可选提供动作伺服器,以绕过跟踪器,草绘器和测距仪以及识别器,并在识别出对象后将数据直接从分段器传递到计划器。通过控制系统,可以将与机械臂实际如何执行任务有关的信息与所需任务进行快速比较,并且可以根据需要更新所需任务。因此,控制器提供了对由机器人手臂执行的任务的视觉反馈控制。

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