Method for calibrating an articulated end effector employing a remote digital camera

摘要

A method for calibrating an articulable end effector of a robotic arm employing a digital camera includes commanding the end effector to achieve a plurality of poses. At each commanded end effector pose, an image of the end effector with the digital camera is captured and a scene point cloud including the end effector is generated based upon the captured image of the end effector. A synthetic point cloud including the end effector is generated based upon the commanded end effector pose, and a first position of the end effector is based upon the synthetic point cloud, and a second position of the end effector associated with the scene point cloud is determined. A position of the end effector is calibrated based upon the first position of the end effector and the second position of the end effector for the plurality of commanded end effector poses.

主权项

1. A method for calibrating an articulable end effector of a robotic arm employing a digital camera, the method comprising:
commanding the end effector to achieve a plurality of poses; for each commanded end effector pose:
capturing an image of the end effector with the digital camera,generating a scene point cloud including the end effector based upon the captured image of the end effector,generating a synthetic point cloud including the end effector based upon the commanded end effector pose,determining a first position of the end effector based upon the synthetic point cloud and the scene point cloud, anddetermining a second position of the end effector associated with the robotic arm; and calibrating a position of the end effector based upon the first position of the end effector and the second position of the end effector for the plurality of commanded end effector poses; wherein determining the first position of the end effector based upon the synthetic point cloud and the scene point cloud for each of the commanded end effector poses comprises:
computing Fast Point Feature Histogram (FPFH) features for the synthetic point cloud and the scene point cloud,employing a Sample Consensus-Initial Alignment (SAC-IA) method to find a rough pose of the end effector in a field of view (FOV) of the camera based upon the FPFH features for the synthetic point cloud and the scene point cloud;segmenting the scene point cloud to a partial scene by a first spherical filter at the rough pose of the end effector found by the SAC-IA,computing FPFH features for the partial scene,employing the SAC-IA method to find the pose of the end effector in the partial scene,segmenting the partial scene to a refined scene by a second spherical filter at the pose of the end effector in the partial scene found by the SAC-IA, andemploying an iterative closest point routine to estimate a pose of the end effector in the refined scene.