Obstacle detection method, device, self-propelled robot and storage medium

Abstract

An embodiment of the present disclosure provides an obstacle detection method and device, a self-propelled robot and a storage medium, and an obstacle detection method, including: converting the obstacle information collected by the image acquisition device into a depth image; converting the above depth image into a point cloud image , and determine the coordinate data of each reference point on the above obstacle; select the effective analysis range in the height direction in the above point cloud image; based on the coordinate data of each reference point, analyze whether there is an obstacle in the above effective analysis range. This method can detect any object in the route of the self-propelled robot, which breaks through the limitations of the existing methods on the types of obstacles. Improvement, increasing the obstacle avoidance performance of the self-propelled robot.

Description

technical field [0001] The present disclosure relates to the technical field of self-propelled robots, and in particular to an obstacle detection method and device, a self-propelled robot and a storage medium. Background technique [0002] With the development of artificial intelligence technology, various intelligent robots have emerged, such as sweeping robots, mopping robots, vacuum cleaners, and weeding machines. These cleaning robots can automatically identify obstacles around them during work and perform obstacle avoidance operations on them. These cleaning robots not only liberate labor, save labor costs, but also improve cleaning efficiency. [0003] However, the image acquisition device of the existing sweeping robot can only recognize limited types of obstacles, often by matching the captured obstacle images with the images stored in the previous database, and when the matching is successful, the shooting target is recognized as Certain kinds of obstacles, such as...

AI Technical Summary

Problems solved by technology

[0003] However, the image acquisition device of the existing sweeping robot can only recognize limited types of obstacles, often by matching the captured obstacle images with the images stored in the previous database, and when the matching is successful, the shooting target is recognized as Certain kinds of obstacles, such as shoes, etc.

In addition, the sweeping robot can also identify obstacles through the laser equipment, but the laser equipment is usually set on the top surface of the sweeping robot, and the laser equipment emits in the horizontal direction and recognizes the obstacles around the sweeping robot after receiving the signal. Since the sweeping robot itself has a certain height , and the laser device also has a certain height, so that the laser device can only detect obstacles that are higher than the height of the sweeping robot body, so some obstacles with low heights will be touched by mistake, and the user experience is not good

Images