Method and device for detecting tiny obstacles and medium
An obstacle and tiny technology, applied in two-dimensional position/channel control, transportation and packaging, vehicle position/route/altitude control, etc., can solve problems such as difficulty in identifying tiny obstacles and depressions, and difficulty in ensuring horizontal status.
Active Publication Date: 2020-03-27
BEIJING XIAOMI INTELLIGENT TECH CO LTD
View PDF17 Cites 5 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] Existing technical solutions mainly use laser radar or RGBD camera to realize obstacle detection. For indoor mobile robots, planar laser radar is mainly used for detection. This solution can identify obstacles with a certain height, but it is difficult to install the camera on the robot. It is also difficult to ensure that it is completely horizontal, so it is difficult to identify small obstacles and depressions
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0080] Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with this document. Rather, they are merely examples of apparatuses and methods consistent with aspects herein as recited in the appended claims.
[0081] An embodiment of the present disclosure provides a method for detecting tiny obstacles. refer to figure 1 , figure 1 It is a flow chart of a method for detecting tiny obstacles according to an exemplary embodiment. This method is applied to sweeping robots, such as figure 1 As shown, this method includes:
[0082] Step S11, acquiring the first 3D point cloud corresponding to the image data captured by...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a method and device for detecting tiny obstacles and a medium. The method comprises the steps of acquiring a first 3D point cloud corresponding to image data shot by a sweepingrobot; extracting a second 3D point cloud belonging to the ground area from the first 3D point cloud; extracting a third 3D point cloud of which the height value is within a set height range from thesecond 3D point cloud; calculating a ground projection point cloud of the third 3D point cloud; and determining a morphological communication region in the ground projection point cloud, and taking the morphological communication region of which the area is smaller than a preset value as a region where the tiny obstacle is located. According to the method, the ground is effectively recognized, the ground projection point cloud is obtained, the point cloud is processed in an image processing mode, and compared with a mode of directly processing discrete three-dimensional point cloud, the accuracy and real-time performance of the algorithm are improved.
Description
technical field [0001] This article relates to the field of robot control technology, in particular to a method, device and medium for detecting tiny obstacles. Background technique [0002] The field of mobile robot obstacle avoidance is an important part of mobile robots in practical applications. In order to move autonomously in the environment like humans, mobile robots need good obstacle recognition capabilities. The obstacle avoidance methods have been continuously updated and developed. Recently, according to different The corresponding deep learning method is proposed for the sensor, the purpose is to provide a more comprehensive and robust obstacle detection algorithm. [0003] Existing technical solutions mainly use laser radar or RGBD camera to realize obstacle detection. For indoor mobile robots, planar laser radar is mainly used for detection. This solution can identify obstacles with a certain height, but it is difficult to install the camera on the robot. Eve...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G05D1/02G06T7/73
CPCG05D1/0251G05D1/0223G05D1/0221G05D1/0276G06T7/74G06T2207/10028G06T2207/20081G06T2207/20084G06V20/64G06V20/10G05D1/0238G05D1/027G06V20/58G06F18/24147
Inventor 臧宇彤
Owner BEIJING XIAOMI INTELLIGENT TECH CO LTD