Capability plot point cloud updating method and device, equipment and storage medium

Abstract

The invention discloses a capability plot point cloud updating method and device, equipment and a storage medium. The method comprises the following steps of obtaining a static capacity map point cloud of a robot at an initial moment, wherein the static capacity map point cloud comprises position information of a sampling point in a movement range of each joint of a mechanical arm of the robot; obtaining a change vector of a camera position from the initial moment to a current moment, wherein a camera is fixed in the robot; determining a pose change vector of the robot according to the changevector of the camera position; and updating the static capacity graph point cloud based on the pose variation vector to obtain a capability plot point cloud at the current moment. According to the technical scheme of the invention, a dynamic updating capability diagram is realized, and the real-time performance and the accuracy of describing a working space are improved.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of machine vision, and in particular, to a method, device, device, and storage medium for updating a capability map point cloud. Background technique [0002] Robots interact with their surroundings primarily through end effectors, the ends of their respective kinematic linkages, such as hands, feet, or heads. The ability map is used to describe the working space of the robot. It is a point set of poses in the environment that its hands, feet or head can reach. It can help the robot obtain information about whether the target object is reachable, and has been widely used. Usually, before the robot performs a grasping task, a capability map is pre-calculated for its dual-arm kinematic chain, which is roughly in the shape of a sphere with the shoulder as the center, and is represented in the form of grid cells. When determining the grasping of the target object After the pose, the robot ...

AI Technical Summary

Problems solved by technology

However, the static capability map is a constant calculated in the preprocessing stage, which is suitable for the description of the grasping task in the local space with the robot as the reference coordinate system. When the robot grasps in a dynamic environment, it involves continuous movement in the indoor environment , the generated static capacity map point cloud is no longer applicable when the displacement changes, and cannot describe the workspace in real time

Images