A modeling method of driving area importance weight distribution for intelligent vehicle lidar data processing
An intelligent vehicle and lidar technology, applied in the field of unmanned vehicle environment perception, can solve the problem of failing to consider the difference in the importance of 3D lidar data, and achieve the effect of improving real-time performance and processing efficiency
Active Publication Date: 2022-05-17
JIANGSU UNIV
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Then, based on the preprocessed lidar data, the road environment model of intelligent vehicles is established. When the existing environment perception technology processes point cloud data in the process of road environment modeling, it mainly removes bad data points at different stages to ensure the accuracy of feature extraction and Environmental modeling accuracy, but fails to consider the difference in data importance caused by the original 3D lidar data due to different regional locations
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
[0021] The technical solutions of the present invention will be further described below in conjunction with the accompanying drawings, but the protection scope of the present invention is not limited thereto.
[0022] Such as figure 1 As shown, a method for modeling regional importance weight distribution for intelligent vehicle lidar data processing includes the following steps:
[0023] Step (1), constructing the plane geometric center of the intelligent vehicle ( figure 2 An overhead grid map centered on the midpoint (O), that is, to construct an overhead grid map, and calculate the distance ρ and direction α of each grid center relative to the center point O of the smart vehicle, and the range of values is:
[0024]
[0025] where the maximum distance ρ max Generally, the value is 120m~160m (assumption condition: the maximum driving speed is 50~60km / h).
[0026] The constructed top view raster map is as follows figure 2 As shown, the specific method of construct...
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 driving area importance weight distribution modeling method for smart vehicle laser radar data processing. Firstly, a bird's-eye view grid map centered on the smart vehicle is constructed, and the distance and distance of each grid relative to the vehicle are calculated. direction; then establish a driver's attention area model based on driving speed and front wheel angle, obtain the driver's main attention area and secondary attention area under different driving conditions, and establish a weight distribution based on regional importance based on the prior information of excellent drivers Finally, according to the established overhead grid map, the driver's attention area model and the importance weight distribution model, the importance weight of each grid is calculated, so that the radar point cloud data is differentially processed, and the The area data with high importance weight is given priority processing, and the area data with low importance weight is given simpler processing, which improves the radar data processing efficiency, thereby improving the real-time performance of intelligent vehicles to perceive external environmental information.
Description
technical field [0001] The invention relates to the field of environment perception of unmanned vehicles, in particular to establishing a driving area importance weight distribution modeling method for intelligent vehicle laser radar data processing based on excellent driver behavior data and vehicle driving speed and driving direction. Background technique [0002] Environmental perception technology is the main means for unmanned vehicles to obtain external environmental information, and is the prerequisite and basic basis for intelligent vehicles to achieve autonomous navigation and trajectory planning. At present, intelligent vehicles mainly rely on environmental perception technology to obtain real-time and reliable external information. Lidar, as an active sensor, is widely used in obstacle detection and dynamic obstacle tracking because of its reliability, accuracy, and anti-interference of data information. and environmental mapping. Due to the increasing requiremen...
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): G05D1/02
CPCG05D1/0223G05D1/0257
Inventor 汤传业周亚洲陈建锋赵鑫文陈龙蔡英凤袁朝春
Owner JIANGSU UNIV