CN-121989994-A - Control method, system, equipment and medium for vehicle down-ramp lane change

Abstract

The application discloses a control method, a system, equipment and a medium for a lane change of a vehicle, and relates to the technical field of decision and control of intelligent driving automobiles, wherein the method comprises the steps of generating a plurality of first candidate strategies if a speed difference between a vehicle and a neighboring vehicle of a target lane is detected to be smaller than or equal to a preset speed difference threshold value and the overlapping time of the position of the vehicle and the neighboring vehicle in the longitudinal direction is larger than or equal to a first preset time length under the condition that a lane change request before the lane change is received; the method comprises the steps of obtaining estimated consumption distance required by each first candidate strategy and the residual distance between the current position of the vehicle and a ramp mouth, determining the first candidate strategy as a second candidate strategy if the estimated consumption distance is smaller than or equal to the residual distance, evaluating the second candidate strategy based on a plurality of preset dimensions according to each second candidate strategy to obtain an evaluation value of the second candidate strategy, and controlling a lane change before the vehicle is down-ramp based on the target strategy by taking the second candidate strategy with the highest evaluation value as the target strategy.

Inventors

• Meng Xingzhao
• YANG GENG

Assignees

• 岚图汽车科技股份有限公司

Dates

Publication Date

20260508

Application Date

20260323

Claims (10)

1. 1. A method for controlling an off-ramp lane change of a vehicle, the method comprising: under the condition that a lane change request before an off-ramp is received, if a speed difference between a host vehicle and an adjacent vehicle of a target lane is detected to be smaller than or equal to a preset speed difference threshold value, and the position overlapping time of the host vehicle and the adjacent vehicle in the longitudinal direction is larger than or equal to a first preset duration, generating a plurality of first candidate strategies for the off-ramp lane change, wherein the target lane is a lane which is close to one side of a ramp mouth and is adjacent to the lane where the host vehicle is located; obtaining an estimated consumption distance required by each first candidate strategy and a residual distance between the current position of the own vehicle and a ramp mouth, and determining the first candidate strategy as a second candidate strategy if the estimated consumption distance is smaller than or equal to the residual distance, wherein the estimated consumption distance is a distance required by the own vehicle from the current position until the ramp is successful; evaluating each second candidate strategy based on a plurality of preset dimensions to obtain an evaluation value of the second candidate strategy; And taking the second candidate strategy with the highest evaluation value as a target strategy, and controlling the vehicle to change the lane before the down-ramp based on the target strategy.
2. 2. The method of controlling an on-ramp of a vehicle according to claim 1, comprising, prior to generating a plurality of first candidate strategies for the on-ramp,: obtaining a reference distance, wherein the reference distance is the minimum distance required by the self-vehicle to decelerate from the current speed to the ramp target speed at a preset deceleration; The generating a plurality of first candidate strategies for the down-ramp lane change includes: and comparing the reference distance with the residual distance, and generating a corresponding first candidate strategy according to a comparison result.
3. 3. The method for controlling an on-ramp lane change of a vehicle according to claim 2, wherein the plurality of first candidate strategies includes m first sub-strategies and n second sub-strategies, m and n being integers greater than or equal to 1, the comparing the reference distance with the remaining distance, and generating a corresponding first candidate strategy according to the comparison result, including: if the remaining distance is greater than the reference distance, generating m first sub-strategies, wherein the m first sub-strategies comprise an acceleration overtaking strategy, a deceleration yielding strategy, a deceleration cutting-in strategy and a speed maintaining and intention expressing strategy; If the remaining distance is smaller than or equal to the reference distance, generating n second sub-strategies, wherein the n second sub-strategies comprise a speed reduction yielding strategy, a speed reduction cutting-in strategy and a speed maintaining and intention expressing strategy.
4. 4. The method for controlling an on-ramp according to claim 1, wherein said first candidate strategy includes a target vehicle speed, and said obtaining estimated consumption distance required for each of said first candidate strategies includes: The method comprises the steps of obtaining a plurality of consumption sub-distances required by a first candidate strategy, wherein the plurality of consumption sub-distances comprise a speed adjusting distance, a stable clearance searching distance and a final deceleration distance, the speed adjusting distance is a distance travelled by a self-vehicle from a current speed to a target speed, the stable clearance searching distance is a distance travelled by the self-vehicle within a second preset duration at the target speed, and the final deceleration distance is a distance travelled by the self-vehicle from the target speed to a ramp target speed; and combining the distance between each consumption sub-and the preset safety margin distance to obtain the estimated consumption distance.
5. 5. The method for controlling an on-ramp lane change according to claim 1, wherein the dimensions include a safety dimension, an execution efficiency dimension, and an environment adaptation dimension, and the evaluating the second candidate policy based on a plurality of preset dimensions for each of the second candidate policies to obtain an evaluation value of the second candidate policy includes: Taking the difference value between the residual distance and the estimated consumption distance as an initial allowance distance; taking the ratio of the safety margin distance to the residual distance as a safety score; Inputting the target speed, the relative speed between the own vehicle and the adjacent vehicle and the relative distance between the own vehicle and the adjacent vehicle into a preset success rate prediction model to obtain an efficiency score, wherein the success rate prediction model is obtained by training a deep learning network to be trained based on a plurality of historical target speeds, the historical relative speeds between the own vehicle and the adjacent vehicle and the historical relative distance between the own vehicle and the adjacent vehicle; evaluating the success ratio of the lane change of the vehicle based on a robustness evaluation method, and taking the ratio as a robustness score, wherein the robustness evaluation method comprises a Monte Carlo simulation method and an empirical table look-up method; And carrying out weighted summation on the safety score, the efficiency score and the robustness score to obtain an evaluation value of the second candidate strategy.
6. 6. The control method of an off-ramp lane change of a vehicle according to claim 1, wherein the target strategy includes a target clearance between a host vehicle and a neighboring vehicle of a target lane, and the controlling the lane change of the vehicle before the off-ramp based on the target strategy includes: in the process of controlling the vehicle to change lanes before the down-ramp based on the target strategy, acquiring the residual safety distance between the own vehicle and the adjacent vehicle of the target lane; And when the target clearance is detected to disappear so that the target strategy cannot be executed or the residual safety distance is lower than a preset safety threshold value, interrupting the execution of the target strategy, and re-executing the step of generating a plurality of first candidate strategies for the down-ramp variation.
7. 7. The control method of a vehicular on-ramp lane change according to claim 2, characterized by comprising, after taking a second candidate strategy having a highest evaluation value as a target strategy, controlling the lane change before the vehicle on-ramp based on the target strategy: If the remaining distance is larger than the reference distance, the speed of the own vehicle is recovered from the current speed to the main road cruising speed, and the speed of the own vehicle is switched from the main road cruising speed to the ramp target speed until the remaining distance is smaller than or equal to the reference distance; If the remaining distance is smaller than or equal to the reference distance, the speed of the own vehicle is switched from the current speed to the ramp target speed.
8. 8. The system is characterized by comprising a strategy generation module, a strategy evaluation module and a strategy screening module; the strategy generation module is configured to generate a plurality of first candidate strategies for the down-ramp lane change if a speed difference between a host vehicle and a neighboring vehicle of a target lane is detected to be smaller than or equal to a preset speed difference threshold value and the position overlapping time of the host vehicle and the neighboring vehicle in the longitudinal direction is larger than or equal to a first preset duration under the condition of receiving a lane change request before the down-ramp, wherein the target lane is a lane close to one side of a ramp mouth and adjacent to the lane where the host vehicle is located; The strategy evaluation module is configured to acquire an estimated consumption distance required by each first candidate strategy and a residual distance from the current position of the own vehicle to the ramp mouth, and determine that the first candidate strategy is a second candidate strategy if the estimated consumption distance is smaller than or equal to the residual distance, wherein the estimated consumption distance is a distance required by the own vehicle from the current position until the lane change succeeds; The strategy screening module is configured to evaluate each second candidate strategy based on a plurality of preset dimensions to obtain an evaluation value of the second candidate strategy, and control the lane change before the vehicle goes down the ramp based on a target strategy by taking the second candidate strategy with the highest evaluation value as the target strategy.
9. 9. An electronic device comprising a memory and a processor, characterized in that the processor is adapted to carry out the steps of a method for controlling a vehicle under-ramp-change as claimed in any one of claims 1-7 when executing a computer program stored in the memory.
10. 10. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, carries out the steps of a method for controlling a vehicle under-ramp as defined in any one of claims 1-7.

Description

Control method, system, equipment and medium for vehicle down-ramp lane change Technical Field The application relates to the technical field of intelligent driving automobile decision and control, in particular to a control method, a system, equipment and a medium for a vehicle down-ramp lane change. Background At present, along with the commercialization of high-level automatic driving, the function of highway navigation auxiliary driving has become the core competition field of each large vehicle enterprise. The automatic ramp-down is used as a key capability of navigation auxiliary driving, and extremely high requirements are put on decision and control level of a system. The vehicle needs to complete the lateral displacement from the high-speed lane to the ramp within a limited residual distance and synchronously and comfortably reduce the vehicle speed from a higher cruising value to the ramp speed limit. However, in the process of continuously changing lanes to the right, social vehicles with the own vehicle being very easy to be similar to the target lane speed form a parallel dead office state with long-time longitudinal position overlapping and speed balance, so that lane changing windows cannot appear, and the lane changing success rate is reduced. Disclosure of Invention In the summary, a series of concepts in a simplified form are introduced, which will be further described in detail in the detailed description. The summary of the application is not intended to define the key features and essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter. In a first aspect, an embodiment of the present application provides a method for controlling an on-ramp of a vehicle, where the method includes: under the condition that a lane change request before an off-ramp is received, if a speed difference between a host vehicle and an adjacent vehicle of a target lane is detected to be smaller than or equal to a preset speed difference threshold value, and the position overlapping time of the host vehicle and the adjacent vehicle in the longitudinal direction is larger than or equal to a first preset duration, generating a plurality of first candidate strategies for the off-ramp lane change, wherein the target lane is a lane which is close to one side of a ramp mouth and is adjacent to the lane where the host vehicle is located; obtaining an estimated consumption distance required by each first candidate strategy and a residual distance between the current position of the own vehicle and a ramp mouth, and determining the first candidate strategy as a second candidate strategy if the estimated consumption distance is smaller than or equal to the residual distance, wherein the estimated consumption distance is a distance required by the own vehicle from the current position until the ramp is successful; evaluating each second candidate strategy based on a plurality of preset dimensions to obtain an evaluation value of the second candidate strategy; And taking the second candidate strategy with the highest evaluation value as a target strategy, and controlling the vehicle to change the lane before the down-ramp based on the target strategy. In one embodiment of the invention, prior to generating the first plurality of candidate strategies for the down-ramp variation, the method comprises: obtaining a reference distance, wherein the reference distance is the minimum distance required by the self-vehicle to decelerate from the current speed to the ramp target speed at a preset deceleration; The generating a plurality of first candidate strategies for the down-ramp lane change includes: and comparing the reference distance with the residual distance, and generating a corresponding first candidate strategy according to a comparison result. In one embodiment of the present invention, the plurality of first candidate policies includes m first sub-policies and n second sub-policies, m and n are integers greater than or equal to 1, the comparing the reference distance with the remaining distance, and generating a corresponding first candidate policy according to a comparison result, including: if the remaining distance is greater than the reference distance, generating m first sub-strategies, wherein the m first sub-strategies comprise an acceleration overtaking strategy, a deceleration yielding strategy, a deceleration cutting-in strategy and a speed maintaining and intention expressing strategy; If the remaining distance is smaller than or equal to the reference distance, generating n second sub-strategies, wherein the n second sub-strategies comprise a speed reduction yielding strategy, a speed reduction cutting-in strategy and a speed maintaining and intention expressing strategy. In one embodiment of the present invention, the first candidate strategies include a target vehicle speed, and the obtaining the estimated consumption dis