CN-115649195-B - Front target confluence cut-in prediction method and device, electronic equipment and storage medium

CN115649195BCN 115649195 BCN115649195 BCN 115649195BCN-115649195-B

Abstract

The application relates to the technical field of decision planning of vehicles, in particular to a front target confluence cut prediction method, a device, electronic equipment and a storage medium, wherein the method comprises the steps of obtaining position information of a current vehicle and determining a target cut-in vehicle according to the position information of the current vehicle; and when the target cut-in vehicle is in the confluence attitude and the confluence attitude coefficient sum is larger than a preset value, calculating a predicted value of the transverse position of the target cut-in vehicle, and predicting whether the target cut-in vehicle enters the lane where the current vehicle is located according to the predicted value. According to the front target confluence cut-in prediction method provided by the embodiment of the application, the front confluence target vehicle is identified to make advance judgment so as to help the vehicle to conduct deceleration planning in advance and execute braking action, so that collision with the front vehicle is avoided, and the safety and driving comfort are improved.

Inventors

WANG CHENG
KONG ZHOUWEI
REN FAN
TAO XIAOSONG
ZHOU XIAOYU

Assignees

重庆长安汽车股份有限公司

Dates

Publication Date: 20260508
Application Date: 20221027

Claims (10)

1. The front target confluence cut-in prediction method is characterized by comprising the following steps of: acquiring the position information of a current vehicle, and determining that a target cuts into the vehicle according to the position information of the current vehicle; acquiring a plurality of interactive vehicles of which targets cut into the same lane and adjacent lanes of the vehicle, calculating a sum of converging attitude coefficients of the plurality of interactive vehicles when the plurality of interactive vehicles are in a converging attitude, and And when the target cut-in vehicle is in a converging posture and the sum of the converging posture coefficients is larger than a preset value, calculating a predicted value of the transverse position of the target cut-in vehicle, and predicting whether the target cut-in vehicle converges in a lane where the current vehicle is located according to the predicted value.
2. The method of claim 1, further comprising, after determining the target cut into the vehicle based on the current vehicle's location information: judging whether the transverse speed of the target cut-in vehicle relative to the central line of the lane where the current vehicle is positioned is greater than a first preset speed or not, and whether the course angle of the target cut-in vehicle relative to the lane where the current vehicle is positioned at the side lane line of the target cut-in vehicle is greater than a first preset angle value or not; And if the transverse speed of the target cut-in vehicle relative to the central line of the lane where the current vehicle is positioned is greater than the first preset speed, and the course angle of the target cut-in vehicle relative to the lane where the current vehicle is positioned, which is positioned on the lane line of the side of the target cut-in vehicle, is greater than the first preset angle value, judging that the target cut-in vehicle is in a confluence posture.
3. The method of claim 2, wherein the plurality of interactive vehicles includes a forward interactive vehicle, a rear interactive vehicle, and an adjacent lane interactive vehicle of the target cut-in vehicle, the calculating a sum of bus attitude coefficients for the plurality of interactive vehicles when in a bus attitude comprising: Judging whether the front interaction vehicle is in the converging posture or not, and when the front interaction vehicle is in the converging posture, the converging posture coefficient of the front interaction vehicle is a first preset value, otherwise, the converging posture coefficient of the front interaction vehicle is 0; judging whether the rear interaction vehicle is in the converging posture or not, and when the rear interaction vehicle is in the converging posture, the converging posture coefficient of the rear interaction vehicle is a second preset value, otherwise, the converging posture coefficient of the rear interaction vehicle is 0; Judging whether the adjacent lane interactive vehicles are in the converging posture or not, and when the adjacent lane interactive vehicles are in the converging posture, the converging posture coefficient of the adjacent lane interactive vehicles is a third preset value, otherwise, the converging posture coefficient of the adjacent lane interactive vehicles is 0; And obtaining the sum of the bus attitude coefficients according to the sum of the first preset value, the second preset value and the third preset value.
4. The method of claim 3, wherein the determining whether the front interaction vehicle is in the converging attitude comprises: Judging whether the transverse speed of the front interaction vehicle relative to the central line of the lane where the current vehicle is positioned is greater than a second preset speed, whether the course angle of the front interaction vehicle relative to the lane line of the lane where the current vehicle is positioned on the side of the target vehicle is greater than a second preset angle value, whether the longitudinal speed of the front interaction vehicle is greater than a third preset speed, whether the distance between the front interaction vehicle and the target cut-in vehicle is smaller than a first preset distance, and whether the distance between the front interaction vehicle and the central line of the lane where the current vehicle is positioned is smaller than the distance between the target cut-in vehicle and the central line of the lane where the current vehicle is positioned; And if the transverse speed of the front interaction vehicle relative to the central line of the lane where the current vehicle is positioned is greater than the second preset speed, the course angle of the front interaction vehicle relative to the lane where the current vehicle is positioned on the lane line of the target cut-in vehicle side is greater than the second preset angle value, the longitudinal speed of the front interaction vehicle is greater than the third preset speed, the distance between the front interaction vehicle and the target cut-in vehicle is smaller than the first preset distance, and the distance between the front interaction vehicle and the central line of the lane where the current vehicle is positioned is smaller than the distance between the target cut-in vehicle and the central line of the lane where the current vehicle is positioned, judging that the front interaction vehicle is in the confluence state.
5. The method of claim 3, wherein the determining whether the rear interactive vehicle is in the converging attitude comprises: Judging whether the transverse speed of the rear interaction vehicle relative to the central line of the lane where the current vehicle is positioned is greater than a fourth preset speed, whether the course angle of the rear interaction vehicle relative to the lane where the current vehicle is positioned on the side of the target vehicle is greater than a third preset angle value, whether the longitudinal speed of the rear interaction vehicle is greater than a fifth preset speed, whether the distance between the rear interaction vehicle and the target cut-in vehicle is smaller than a second preset distance, and whether the distance between the rear interaction vehicle and the central line of the lane where the current vehicle is positioned is greater than the distance between the target cut-in vehicle and the central line of the lane where the current vehicle is positioned; And if the transverse speed of the rear interaction vehicle relative to the central line of the lane where the current vehicle is located is greater than the fourth preset speed, the course angle of the rear interaction vehicle relative to the lane line of the lane where the current vehicle is located on the target vehicle side is greater than the third preset angle value, the longitudinal speed of the rear interaction vehicle is greater than the fifth preset speed, the distance between the rear interaction vehicle and the target cut-in vehicle is smaller than the second preset distance, and the distance between the rear interaction vehicle and the central line of the lane where the current vehicle is located is greater than the distance between the target cut-in vehicle and the central line of the lane where the current vehicle is located, determining that the rear interaction vehicle is in the converging state.
6. The method of claim 3, wherein the determining whether the adjacent lane-interacting vehicle is in the merge pose comprises: Judging whether the transverse speed of the adjacent lane interactive vehicle relative to the central line of the lane where the current vehicle is positioned is greater than a sixth preset speed, whether the course angle of the adjacent lane interactive vehicle relative to the lane line of the lane target vehicle side where the current vehicle is positioned is greater than a fourth preset angle value, whether the longitudinal speed of the adjacent lane interactive vehicle is greater than a seventh preset speed, and whether the distance of the target cut-in vehicle of the adjacent lane interactive vehicle is smaller than a third preset distance; And if the transverse speed of the adjacent lane interactive vehicle relative to the central line of the lane where the current vehicle is located is greater than the sixth preset speed, the course angle of the adjacent lane interactive vehicle relative to the lane line of the lane target vehicle side where the current vehicle is located is greater than the fourth preset angle value, the longitudinal speed of the adjacent lane interactive vehicle is greater than the seventh preset speed, and the distance of the target cut-in vehicle of the adjacent lane interactive vehicle is smaller than the third preset distance, judging that the adjacent lane interactive vehicle is in the confluence posture.
7. The method of claim 1, wherein the calculating a lateral position prediction of the target cut-in vehicle comprises: calculating a predicted value of the transverse position of the target cut into the vehicle based on a preset prediction formula, wherein the preset prediction formula is as follows: L_Lat_Pred=L_Lat+V_Lat×T; Wherein L_Lat_pred is a predicted value of the relative transverse position of the target cut-in vehicle, L_Lat is the relative transverse position of the target cut-in vehicle, V_Lat is the relative transverse speed of the target cut-in vehicle, and T is the predicted time period.
8. The method of claim 7, wherein predicting whether the target cut-in vehicle merges into the lane in which the current vehicle is located based on the predicted value comprises: And if the predicted value is in the lane where the current vehicle is located, judging that the target cut-in vehicle can sink into the lane where the current vehicle is located, otherwise, judging that the target cut-in vehicle cannot sink into the lane where the current vehicle is located.
9. A front target confluence cut-in prediction apparatus, comprising: the acquisition module is used for acquiring the position information of the current vehicle and determining that the target cuts into the vehicle according to the position information of the current vehicle; A calculation module for acquiring a plurality of interactive vehicles with targets cut into the same lane and adjacent lanes of the vehicle, calculating a sum of converging attitude coefficients of the interactive vehicles when the interactive vehicles are in the converging attitude, and And the prediction module is used for calculating a predicted value of the transverse position of the target cut-in vehicle when the target cut-in vehicle is in a confluence posture and the confluence posture coefficient sum is larger than a preset value, and predicting whether the target cut-in vehicle is converged into a lane where the current vehicle is located according to the predicted value.
10. A computer readable storage medium having stored thereon a computer program, wherein the program is executed by a processor for implementing the front target confluence cut prediction method of any one of claims 1-8.

Description

Front target confluence cut-in prediction method and device, electronic equipment and storage medium Technical Field The application relates to the technical field of decision planning of vehicles, in particular to a front target confluence cut-in prediction method, a device, electronic equipment and a storage medium. Background The automatic driving technology mainly comprises three parts of environment sensing, decision planning and control execution. With the continuous development of automatic driving, the requirements on the urban automatic driving function are gradually increased, and meanwhile, higher requirements on the decision planning capability of the automatic driving vehicle are also provided. In order to improve the decision planning capability of the vehicle under the working conditions of urban roads and urban expressways without high-precision map coverage, the behaviors of other targets around the vehicle, particularly forward converging targets, need to be identified and predicted so as to ensure the rationality and advance of decision planning, and sufficient processing time is reserved for a control execution part so as to improve driving safety and comfort. In the related art, the method for identifying the converging target mainly comprises the following three steps: (1) Based on the high-precision map or the ADAS (ADVANCED DRIVER ASSISTANCE SYSTEM, advanced driving assistance system) map, the position of the vehicle in the map output by the positioning module detects whether the vehicle is in a confluence region, thereby identifying a confluence target. (2) Based on the camera, it is detected by the image detection device that there is an entrance or an exit in front of the road, thereby identifying the confluence target. (3) Based on V2X (vehicle to everything, vehicle-to-outside information exchange), the central controller identifies whether the vehicle enters a convergence region based on real-time information of the intelligent network-connected vehicle, thereby identifying a convergence target. However, the above-described bus bar object recognition method has the following drawbacks: (1) The automatic driving vehicle is required to be equipped with a high-precision map or an ADAS map, and the vehicle is required to be in a map coverage range, so that the vehicle configuration requirement is high and the application range is limited. (2) The camera is required to have stronger image recognition capability, so that a large amount of image data of the sink is required to be collected for algorithm training, and a large amount of manpower and material resources are consumed. (3) The vehicle needs to be equipped with V2X equipment for automatic driving, and the vehicle needs to be in V2X coverage, so that the vehicle configuration requirement is high and the application range is limited. Disclosure of Invention The application provides a front target confluence cutting prediction method, a device, electronic equipment and a storage medium, which are used for solving the problems that in the prior art, when a vehicle performs target confluence cutting, whether the vehicle is in a confluence area or not is detected through a map, a camera or V2X equipment, so that the vehicle needs high configuration requirements, the application range is limited, and a large amount of manpower and material resources are consumed. An embodiment of a first aspect of the application provides a front target confluence cut-in prediction method, which comprises the steps of obtaining position information of a current vehicle, determining a target cut-in vehicle according to the position information of the current vehicle, obtaining a plurality of interactive vehicles of the same lane and adjacent lanes of the target cut-in vehicle, calculating a confluence attitude coefficient sum when the plurality of interactive vehicles are in a confluence attitude, and calculating a lateral position predicted value of the target cut-in vehicle when the target cut-in vehicle is in the confluence attitude and the confluence attitude coefficient sum is larger than a preset value, and predicting whether the target cut-in vehicle is converged into the lane where the current vehicle is located according to the predicted value. According to the technical means, the forward converging target vehicle is identified, whether the converging vehicle enters the lane or not is judged in advance, the longitudinal planning part of the automatic driving vehicle is helped to conduct deceleration planning in advance and execute braking action, collision with the front vehicle is avoided, running safety is guaranteed, emergency braking is avoided, and driving comfort is improved. Further, in one embodiment of the application, after determining the target cut-in vehicle according to the position information of the current vehicle, the method further comprises the steps of judging whether the transverse speed of the target cut-in vehicle r