Vehicle positioning method with multi-position joint particle filters
A technology of particle filtering and vehicle positioning, which is applied in the field of navigation and positioning of intelligent vehicles, can solve problems such as accumulation, achieve accurate positioning, and eliminate cumulative errors
Inactive Publication Date: 2018-12-11
ZHEJIANG UNIV
View PDF8 Cites 12 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, since visual odometry calculates vehicle position incrementally, small errors are introduced every frame and accumulate over time
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
[0062] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.
[0063] The embodiment implemented according to the complete method of content of the present invention is as follows:
[0064] (1) Establish a road network map of the vehicle driving area, such as figure 1 As shown in , the road network map is composed of a topology graph structure including nodes and edges, and the location of the starting point of the vehicle in the road network map is known;
[0065] (2) Obtain the vehicle position at each moment in real time through the dead reckoning method to form the original vehicle trajectory; detect the anchor points in the original vehicle trajectory in real time, mark each anchor point and connect the anchor points in sequence to form vehicle segments track, such as figure 2 shown.
[0066] (2.1) Obtain the current vehicle position in real time through the dead reckoning method, and connect the current v...
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 vehicle positioning method with multi-position joint particle filters. The vehicle positioning method comprises the following steps of establishing a road network map of a vehicle driving region, acquiring a vehicle position through a dead reckoning method in real time, and detecting anchor points to form an initial vehicle segmented driving track; as for an anchor pointdetected each time, using a pile of particles to express the position corresponding to each anchor point in the road network map, calculating and updating a weight of each pile of particles through joint particle filters in real time; and as for each pile of particles, by taking the particles with maximal weight as positioning points of the corresponding anchor points in the road network map, sequentially connecting the positioning points as a vehicle segmented driving track after correction. The vehicle positioning method provided by the invention can effectively correct an accumulative errorgenerated by the dead reckoning method such as a visual odometer, can acquire good positioning accuracy in vehicle long-distance driving process and is low in calculation cost and strong in real-timeperformance.
Description
technical field [0001] The invention relates to a navigation and positioning technology method of an intelligent vehicle, in particular to a vehicle positioning method based on multi-position joint particle filter. Background technique [0002] Localization refers to the ability of a vehicle to determine its own location, and reliable and accurate vehicle localization is a prerequisite for autonomous vehicle navigation. In order to solve this problem, traditional navigation systems such as GPS and wheel odometers have been widely used. However, due to the well-known "urban canyon" effect, GPS is prone to occlusion in urban environments and cannot obtain good positioning accuracy. In this case, an expensive GPS / INS system is usually required to provide the vehicle position. The wheel odometer will also be affected by wheel slippage and other effects during long distances, resulting in errors. At present, many vision-based 2D and 3D localization methods have been continuous...
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): G01C21/20G01C21/16
CPCG01C21/165G01C21/20
Inventor 项志宇顾淑霞张易钱琦
Owner ZHEJIANG UNIV