	US 12,283,188 B1
	Method for scheduling cars at narrow curve based on parking space for temporary avoidance
Zhiquan Liu, Guangzhou (CN); Yong Ma, Guangzhou (CN); Yongli Hu, Shenzhen (CN); Feiran Huang, Guangzhou (CN); Pengtao Xia, Shenzhen (CN); Jingjing Guo, Guangzhou (CN); Junhong Wen, Shenzhen (CN); and Senting Ma, Guangzhou (CN)
Assigned to Jinan University, Guangzhou (CN); and Shenzhen Lanyou Technology Co., Ltd., Shenzhen (CN)
Filed by Jinan University, Guangzhou (CN); and Shenzhen Lanyou Technology Co., Ltd., Shenzhen (CN)
Filed on Dec. 12, 2024, as Appl. No. 18/978,146.
Claims priority of application No. 202311732817.3 (CN), filed on Dec. 18, 2023.
Int. Cl. G08G 1/00 (2006.01); G08G 1/01 (2006.01); G08G 1/048 (2006.01); G08G 1/14 (2006.01)

CPC G08G 1/142 (2013.01) [G08G 1/0112 (2013.01); G08G 1/048 (2013.01)]

13 Claims

1. A method for scheduling cars at a narrow curve based on a parking space for temporary avoidance, comprising:

fusing car data obtained by laser radar and millimeter wave radar, so as to predict car states and driving trajectories of meeting cars;

computing an expected meeting point of the cars through prediction of the driving trajectories of the cars; and

executing, on the basis of the expected meeting point, different car avoidance strategies according to road conditions and a number of parking spaces for temporary avoidance, so as to implement car avoidance and scheduling of car meeting at the narrow curve, wherein

the fusing car data obtained by laser radar and millimeter wave radar, so as to predict car states and driving trajectories of meeting cars comprises:

predicting the car states with the car data obtained by the laser radar through Kalman filtering; and

updating measurement of the car state with the car data obtained by the millimeter wave radar through extended Kalman filtering, changing a coordinate system through a nonlinear measurement function h(x), setting a measurement noise covariance matrix R, and computing a new jacobian matrix H_j, such that measurement updating is implemented, wherein

in a prediction stage, after the car data carData collected by the laser radar is received, a predicted value custom character

of the car data is computed through a state prediction formula;

in an updating stage, a filter compares the predicted value custom character

of the car data with a measured value, and conducts data fusion, such that updated car data, that is, an optimal estimated value custom character

is obtained; and

after time Δt, measured values of the laser radar and the millimeter wave radar are received again, and a next round of prediction and updating is started;

wherein the state prediction formula is:

=F*

+B*u+W

in the formula, F denotes a state transition matrix configured to predict a next state value, custom character

denotes an optimal estimated value obtained through comprehensive prediction and measurement of the cars at a last moment, B denotes a control matrix, u denotes a control variable, and w denotes a noise term; and

B*u=0 is set, and influence of acceleration and the noise term w are added, and are represented by a process noise vector noise,

that is:

=F*

+noise.