A positioning method and system for an unmanned vehicle
A positioning method and technology for unmanned vehicles, applied in the field of unmanned vehicle positioning methods and systems, can solve problems such as large registration errors, insufficient geometric features to stably represent the environment, and large feature deviations, so as to improve accuracy and robustness. awesome effect
Active Publication Date: 2022-04-22
CENT SOUTH UNIV +1
View PDF11 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
For example, when the environment is relatively complex, simple geometric features are not enough to stably represent the environment, and there will also be large deviations in the extracted features, resulting in large registration errors.
[0006] Therefore, in the laser point cloud positioning system, registration based on laser point coordinates or registration based on simple geometric features in the prior art is not a good solution
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
[0028] figure 1 It is the flow chart of the embodiment method of this application, such as figure 1 As shown, the method includes:
[0029] Step S11, obtaining a priori point cloud map of the environment where the unmanned vehicle is located;
[0030] Step S12, obtaining the real-time point cloud of the environment where the unmanned vehicle is located;
[0031] Step S13, extracting the depth features of the input point cloud features in the prior point cloud map and the real-time point cloud respectively;
[0032] Step S14, matching according to the depth feature similarity between the prior point cloud map and the real-time point cloud of the unmanned vehicle, to obtain the transformation relationship between the real-time point cloud and the prior point cloud map, which is the priori point cloud map of the unmanned vehicle. Check the position in the point cloud map;
[0033] Step S15 , smoothing the feature matching and positioning results, and adjusting the positioning...
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 positioning method and system for an unmanned vehicle, which uses a vehicle-mounted laser radar sensor to establish an offline point cloud map of the environment; obtains a real-time point cloud of an unmanned vehicle; and uses a deep network to extract a priori point cloud map and a real-time point cloud respectively. Depth features; matching according to the feature similarity between the offline point cloud map and the real-time point cloud to determine the current position of the unmanned vehicle in the offline point cloud map; smoothing the trajectory of the unmanned vehicle and correcting the positioning results. The present invention can use a deep network to extract deep features instead of manually extracting features, and improve the accuracy and stability of the self-location of the unmanned vehicle.
Description
technical field [0001] The invention relates to the field of positioning of unmanned vehicles, in particular to a positioning method and system for unmanned vehicles. Background technique [0002] Unmanned vehicle positioning is one of the core issues in the research of unmanned vehicle technology, and it is also one of the basic links in the realization of automatic driving functions. Initially, the general positioning scheme used the Global Navigation Satellite System (GNSS), which has the disadvantage of low precision and unstable positioning results. At present, the common positioning scheme in the field of unmanned vehicles generally uses the combined positioning of GNSS, inertial navigation system and laser point cloud positioning system. technology. Among them, GNSS provides a certain degree of reliability of the initial rough position information (longitude, latitude and altitude) of the unmanned vehicle based on the earth coordinate system, and the inertial navigat...
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 Patents(China)
IPC IPC(8): G01B11/00G06T7/33G06T7/73
CPCG01B11/002G06T7/74G06T7/337G06T2207/10028G06T2207/20081G06T2207/20084
Inventor 陈白帆宋宝军赵子硕胡云卿
Owner CENT SOUTH UNIV