Ground segmentation method for mobile robot in off-road environment based on three-dimensional laser radar
A mobile robot, three-dimensional laser technology, applied in the fields of instruments, image analysis, computer parts, etc., can solve problems such as increasing the computational burden and affecting the segmentation effect.
Pending Publication Date: 2022-04-01
INNER MONGOLIA UNIV OF TECH
View PDF0 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
During the moving process of the mobile robot, there are a large number of invalid or outlier points in the acquired point cloud data caused by radar jitter due to uneven roads or mutual occlusion of objects. If they are not filtered out in time, the segmentation effect will be affected; at the same time, There is a large amount of ground point cloud information, and the ground point cloud is an invalid point in the process of target detection and recognition, which increases the computational burden
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
[0060] The specific technical solutions of the present invention are described in conjunction with the drawings and embodiments.
[0061] 1. Point cloud outlier filtering for adaptive density clustering
[0062] Such as Figure 6 As shown, the method steps are as follows:
[0063] S1: Grid-based initial point selection, gridding the point cloud data, dividing the received point cloud into n×m blocks through the grid, and numbering each area, traversing the point cloud, and corresponding to each point Put it into the area, record the number of points in each area, and finally select the area with the largest number as the initial point selection area to become the area with the highest density. figure 1 The area where point p is located is the area with the highest density; in the area with the highest density, k-neighborhood search is performed to determine the initial point p, then point p is the core point, figure 1 Point p in the area with the highest density is the sele...
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 provides a ground segmentation method for a mobile robot in a cross-country environment based on a three-dimensional laser radar, and the method comprises the steps: carrying out the meshing of obtained point cloud data, searching a maximum density region, determining a maximum density point as a clustering initial point, searching a core point in the point cloud according to a density clustering algorithm, and carrying out the clustering of the core point; and searching density reachable points around according to the clustering radius of each core point by taking the initial point as a first point of density clustering, finally finishing clustering, and judging points which cannot be clustered as outliers for filtering. Downsampling processing is carried out on point clouds by using voxel filtering based on an adjacent gravity center point, disordered point clouds are ordered according to a radius and a vertical angle, an expected distance in an actual road condition is obtained through a relationship between a slope angle and the vertical angle, a local threshold height and a global threshold height are obtained through a relationship between the expected distance, a radar installation height and the slope angle, and the global threshold height is calculated. And judging the radius of each point and the actual expected distance, and the height of each point and the global threshold and local threshold heights to obtain whether the point belongs to the ground or non-ground.
Description
technical field [0001] The invention relates to the technical field of mobile robot off-road environment perception, in particular to a three-dimensional laser radar-based method for ground segmentation in a mobile robot off-road environment. [0002] technical background [0003] Environmental perception technology is one of the key technologies for mobile robots to safely drive in off-road environments. Environmental perception technology uses various sensors to collect data from the environment, obtain driving environment information and the relative distance between the robot and surrounding obstacles, relative speed and other information, and then provide information basis for various control decisions. It is the prerequisite and foundation for mobile robots to achieve advanced intelligent behaviors such as obstacle avoidance and path planning. [0004] At this stage, the sensors used for mobile robot environment perception mainly include 3D lidar and camera. The use o...
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): G06T7/136G06T17/20G06V10/762G06K9/62G01S17/93
Inventor 苏建强陶泽宇刘利强齐咏生任凯斌董丹婷李艳明单馨平
Owner INNER MONGOLIA UNIV OF TECH