Method for predicting safe driving based on trajectory of vehicles around vehicle
A technology for predicting surrounding vehicles and trajectories, applied in image data processing, image enhancement, instruments, etc., can solve problems such as unfavorable driving safety and improvement, and achieve improved robustness and safety, flexible driving guarantee, and improved rationality and The effect of accuracy
Inactive Publication Date: 2019-11-05
SOUTHEAST UNIV
View PDF4 Cites 31 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
This function can only alarm when the surrounding vehicles are very close to the own vehicle. Sometimes the reaction time left for the driver is very small, which is not conducive to the improvement of driving safety. At the same time, many safety route planning needs to comprehensively consider the certain range of the own vehicle. driving environment
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 1
[0036] Such as figure 1 , figure 2 As shown, the present invention considers 9 types of different types of vehicle route planning, corresponding to figure 1 There are 9 different driving routes. As shown in Table 1.
[0037] Table 1: Types of vehicle routing planning
[0038] LF F RF LM M RM LB B RB
[0039] The definition of compliance in the table is shown in Table 2:
[0040] Table 2 Path Type Definition
[0041]
[0042] Capture the surrounding vehicles through the camera equipped on the vehicle, track all the vehicles within 30m of the longitudinal distance from the vehicle, perform motion analysis and prediction, and then map the position of the tracked vehicle to the reference coordinate system of the own vehicle to generate the trajectory of the surrounding vehicles History; Sampling the own trajectory and the surrounding vehicle trajectory to obtain the 8-second driving trajectory with a frequency of 5Hz, and using the GRU re...
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 for predicting safe driving based on the trajectory of vehicles around a vehicle, comprising the following steps: capturing surrounding vehicles through a camera equipped on the vehicle, and generating the trajectory history of the surrounding vehicles; using a GRU recurrent neural network to perform motion coding on the driving tracks of the own vehicle and the surrounding vehicles; constructing a Social Tensor according to the motion coding result of the surrounding vehicles; respectively carrying out feature extraction and time sequence analysis on the Social Tensor and the own motion coding tensor through a convolutional neural network and a full-connection neural network; outputting a feasible maneuvering strategy for the current scene through a softmax layer, and meanwhile, obtaining safe driving route probability distribution within 5 seconds later through a GRU recurrent neural network; and an appropriate loss function is selected for optimization training, and perception of a safe driving route is realized. The follow-up safe driving route of the vehicle is predicted by comprehensively considering the driving tracks of the vehicle and surrounding vehicles, so that the vehicle advanced driving assistance system has the capabilities of understanding the driving environment and sensing the safe route.
Description
technical field [0001] The invention relates to the fields of advanced driving assistance technology and automatic driving technology, in particular to a method for predicting safe driving based on vehicle trajectories around the vehicle. Background technique [0002] In urban and high-speed traffic environments, in order to improve vehicle driving safety, drivers need to predict the future movement of surrounding vehicles, discover potential risks in time, and plan safe driving routes to help drivers decide when to switch lanes and when to switch lanes. to accelerate or decelerate. Safe driving route planning is an important ability for drivers to drive safely. It is the driver's long-term accumulation of experience and plays a very important role in driving safety. , in order to improve the safe driving ability of many novice drivers, at present, the advanced driving assistance technology has the function of line merging assistance (LCA), which provides an early warning t...
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 IPC IPC(8): G06T7/20G06N3/04B60W30/095
CPCG06T7/20B60W30/0956G06T2207/20081G06T2207/20084G06N3/045
Inventor 秦文虎方阳孙立博
Owner SOUTHEAST UNIV