Method for robot to intelligently avoid human under man-machine cooperation scene

Abstract

The invention discloses a method for a robot to intelligently avoid human under a man-machine cooperation scene, comprising steps of constructing a robot column model of a simulation scene through robot D-H parameters, (2) obtaining RGB images of the real scene and skeleton data of an operator through Kinect, and constructing the column model of the simulation scene operator, 3) corresponding calibrations of the robot and the simulator in the real scene and the simulation scene , and 4) performing real-time detection collision of the robot model and the operator model. By using the method disclosed by the invention, the operator can freely move in the space where the robot operates, but the operator can avoid the obstacle according to the operator information obtained by the Kinect.

Description

technical field [0001] The present invention relates to the technical field of robot movement, in particular to a method for robots to intelligently avoid humans in a human-machine collaboration scene. Background technique [0002] The intersection and integration of intelligent robots and other fields have produced many scenarios that require the cooperation of humans and robots. Intelligent robots participate in the human working environment, and can effectively liberate human labor under the premise of ensuring work efficiency. In special cases, they can also replace human beings to complete high-risk tasks. In the context of close collaboration between humans and robots, how to ensure human safety is a crucial issue. This invention proposes a method for robot modeling and obstacle avoidance in a human-machine collaboration scenario. This method constructs a robot cylinder model based on the D-H parameters of the robot, and uses the Kinect sensor to collect the position ...

AI Technical Summary

Problems solved by technology

However, traditional robot collision avoidance research is mainly on object collision avoidance. Unlike environmental objects, humans have their own structural characteristics, and the state and movement of the human body are also unpredictable. Therefore, robots need to recognize the human body in real time.

[0005] Before the appearance of Kinect, human body information collection technology based on multi-vision cameras was relatively popular, but this method requires perspective images, and the relative cost is relatively high

In the marker-based multi-vision camera human body recognition technology, the human body has to wear specific clothing or equipment, and is in a restricted state during activities, which limits the application of this technology

The unmarked human body information extraction and collection technology needs to match prior knowledge such as human body images, 3D information and objective functions. The matching process requires a sufficient number of samples, otherwise the recognition accuracy will be low and it will be difficult to ensure real-time performance.

Images