CN-121973769-A - Vehicle running control method, device, equipment and medium

CN121973769ACN 121973769 ACN121973769 ACN 121973769ACN-121973769-A

Abstract

The application discloses a vehicle running control method, device, equipment and medium, and belongs to the technical field of vehicles. The method comprises the steps of obtaining first prediction track sets corresponding to a plurality of blind area targets in a blind area of a vehicle, judging whether collision risks exist between the blind area targets and the vehicle based on the first prediction track sets corresponding to the blind area targets and target planning tracks of the vehicle, wherein the target planning tracks are tracks along the current running direction of the vehicle in a plurality of candidate planning tracks, the plurality of candidate planning tracks are determined based on state information of the vehicle, determining target track sets corresponding to risk blind area targets with collision risks from the first prediction track sets based on judging results, generating collision information based on the target track sets and the plurality of candidate planning tracks of the vehicle, generating a first control instruction based on the collision information, and controlling the running state of the vehicle based on the first control instruction.

Inventors

KE WEI
LIU JIFENG
WU LIPENG
QIN XILE
LIANG XIANQING

Assignees

岚图汽车科技股份有限公司

Dates

Publication Date: 20260505
Application Date: 20260226

Claims (15)

1. A vehicle travel control method, characterized by comprising: acquiring a first predicted track set corresponding to a plurality of blind area targets in a blind area of a vehicle respectively, wherein the first predicted track set comprises at least one predicted track; Judging whether collision risks exist between the blind zone targets and the vehicle or not based on a first prediction track set corresponding to each blind zone target and a target planning track of the vehicle, wherein the target planning track is a track along the current running direction of the vehicle in a plurality of candidate planning tracks, and the plurality of candidate planning tracks are determined based on the state information of the vehicle; Determining target track sets corresponding to the risk blind zone targets with collision risks respectively from the first predicted track set based on the judging result; generating collision information based on the target track set and a plurality of candidate planned tracks of the vehicle; a first control instruction is generated based on the collision information, and a running state of the vehicle is controlled based on the first control instruction.
2. The method of claim 1, wherein the generating collision information based on the set of target trajectories and the plurality of candidate planned trajectories for the vehicle comprises: The method comprises the steps of constructing an environment model, wherein the environment model comprises attribute information of each environment target which has collision risk with a vehicle in the current environment where the vehicle is located, and the attribute information comprises a first identifier and state information; Associating each target track set with a corresponding environmental target in the environmental model; Respectively taking a target track set associated with each environmental target as a second predicted track set of the environmental target; collision information is generated based on the second set of predicted trajectories and the candidate planned trajectories.
3. The method of claim 2, wherein the building an environmental model comprises: aiming at each risk blind area target, determining estimated collision points of a target track set corresponding to the risk blind area target and the target planning track respectively; Generating state information of an environmental target based on the state information of the estimated collision point, and generating a first identifier of the environmental target based on a second identifier of the risk blind zone target; and constructing the environment model based on the state information of each environment target and the first identifier.
4. A method according to claim 3, wherein associating each set of target trajectories with a corresponding environmental target in the environmental model comprises: Determining matched target identifications from a plurality of second identifications based on the first identifications of the environmental targets for each environmental target in the environmental model; determining a first predicted track set of the blind area target indicated by the target mark; and associating a first predicted track set of the blind area target indicated by the target mark with the environment target.
5. The method of claim 3, wherein generating the state information of the environmental target based on the state information of the predicted collision point comprises: Aiming at each risk blind area target, determining the current prediction state information of the risk blind area target based on the state information of the prediction collision point; based on the predicted state information, state information of the environmental target is generated.
6. The method according to any one of claims 2 to 5, wherein the collision information is a duration between a current time and a time corresponding to a collision of the vehicle, and the generating collision information based on the second predicted trajectory set and the candidate planned trajectory includes: For each environmental target, judging whether collision risk exists between the environmental target and the vehicle based on a second predicted track set corresponding to the environmental target and a candidate planning track of the vehicle; If collision risk exists, determining the current time and the duration between the vehicle and the collision time of the environmental target; and generating the collision information based on the time periods respectively corresponding to the environmental targets.
7. The method of claim 6, wherein the determining the duration between the current time and the time of collision comprises: Determining a target predicted track in a second predicted track set of the environmental target, which is in collision, and a pre-collision planned track in a plurality of candidate planned tracks; Actual collision points of the target predicted track and the pre-collision planning track are truly detected; And determining the duration between the current moment and the moment of collision based on the actual collision point, the target predicted track and the pre-collision planning track.
8. The method of claim 6, wherein generating the collision information based on the respective durations of the respective environmental targets comprises: and determining the minimum duration in the durations corresponding to the environmental targets respectively to obtain collision information.
9. The method of claim 5, wherein the generating a first control instruction based on the collision information comprises: If the minimum duration in the collision information is not greater than a first preset duration, generating a first running control instruction, wherein the first running control instruction comprises a braking instruction or an emergency steering instruction, and the emergency steering instruction is used for indicating that the steering angle is greater than a preset steering angle in a preset unit duration; If the minimum time length in the collision information is longer than the first preset time length and shorter than the second preset time length, determining a final planned track based on the target predicted track and the pre-collision planned track, and generating a second running control instruction based on the final planned track, wherein the second running control instruction comprises a deceleration instruction and/or a smooth steering instruction, and the smooth steering instruction is used for indicating that the steering angle is smaller than the preset steering angle in the preset unit time length.
10. The method of claim 6, wherein after determining whether there is a risk of collision between the environmental target and the vehicle based on the second set of predicted trajectories and the candidate planned trajectories of the vehicle, respectively, the method further comprises: If all the environmental targets and the vehicle have no collision risk, visually displaying state information based on all the environmental targets in the environmental model; and generating a second control instruction based on the state information of each environmental target, and controlling the running state of the vehicle based on the second control instruction.
11. The method of claim 5, wherein generating state information for the environmental target based on the predicted state information comprises: The method comprises the steps of acquiring target configuration parameters, wherein the target configuration parameters are configuration parameters of state information of a real target acquired by a sensor in the vehicle; setting configuration parameters of the predicted state information as the target configuration parameters to obtain state information of the environment target; the target configuration parameters comprise a target format, a transmission interface and acquisition frequency.
12. The method according to any one of claims 2 to 5, wherein obtaining a first predicted trajectory set for each of a plurality of blind zone targets in a blind zone of a vehicle comprises: sending an information acquisition request to a road side unit so that the road side unit can acquire current state information of each blind zone target in the plurality of blind zone targets; Receiving current state information of each blind area target fed back by the road side unit; and aiming at each blind area target, carrying out track prediction on the blind area target based on the current state information of the blind area target to obtain a corresponding first predicted track set.
13. A vehicle travel control apparatus, characterized by comprising: The system comprises an acquisition module, a prediction track acquisition module and a control module, wherein the acquisition module is used for acquiring a first prediction track set corresponding to a plurality of blind area targets in a blind area of a vehicle respectively, and the first prediction track set comprises at least one prediction track; the system comprises a judging module, a judging module and a control module, wherein the judging module is used for judging whether collision risk exists between the blind area target and the vehicle or not based on a first prediction track set corresponding to the blind area target and a target planning track of the vehicle respectively; The determining module is used for determining target track sets corresponding to the risk blind zone targets with collision risk respectively from the first predicted track set based on the judging result; The generation module is used for generating collision information based on the target track set and a plurality of candidate planning tracks of the vehicle; and the control module is used for generating a first control instruction based on the collision information and controlling the running state of the vehicle based on the first control instruction.
14. An electronic device comprising a memory and a processor, the memory and the processor being communicatively coupled to each other, the memory having stored therein computer instructions, the processor executing the computer instructions to perform the method of any of claims 1-12.
15. A computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-12.

Description

Vehicle running control method, device, equipment and medium Technical Field The present application relates to the field of vehicle technologies, and in particular, to a vehicle driving control method, device, equipment, and medium. Background In the running process of the vehicle, a plurality of sight-blocking areas caused by building structures exist around the vehicle, the areas can be called blind areas, other targets such as vehicles and pedestrians exist in the blind areas, and collision accidents between the targets and the vehicle can be caused by slight carelessness, so that casualties and property loss are caused. Therefore, it is necessary to provide a solution capable of preventing a collision between a vehicle and a blind area target in a scene of the blind area target where a collision risk may exist, and improving driving safety. Disclosure of Invention In view of the above problem of how to prevent a vehicle from colliding with a blind area target to improve driving safety, the present application has been made to provide a vehicle running control method, apparatus, device, and medium that solve the above problem, and can prevent a vehicle from colliding with a blind area target to improve driving safety. In a first aspect, the present application provides a vehicle running control method, the method comprising: acquiring a first predicted track set corresponding to a plurality of blind area targets in a blind area of a vehicle respectively, wherein the first predicted track set comprises at least one predicted track; Judging whether collision risks exist between the blind zone targets and the vehicle or not based on a first prediction track set corresponding to each blind zone target and a target planning track of the vehicle, wherein the target planning track is a track along the current running direction of the vehicle in a plurality of candidate planning tracks, and the plurality of candidate planning tracks are determined based on the state information of the vehicle; Determining target track sets corresponding to the risk blind zone targets with collision risks respectively from the first predicted track set based on the judging result; generating collision information based on the target track set and a plurality of candidate planned tracks of the vehicle; a first control instruction is generated based on the collision information, and a running state of the vehicle is controlled based on the first control instruction. In one embodiment, the generating collision information based on the target trajectory set and the plurality of candidate planned trajectories of the vehicle includes: The method comprises the steps of constructing an environment model, wherein the environment model comprises attribute information of each environment target which has collision risk with a vehicle in the current environment where the vehicle is located, and the attribute information comprises a first identifier and state information; Associating each target track set with a corresponding environmental target in the environmental model; Respectively taking a target track set associated with each environmental target as a second predicted track set of the environmental target; collision information is generated based on the second set of predicted trajectories and the candidate planned trajectories. In one embodiment, the building the environmental model includes: aiming at each risk blind area target, determining estimated collision points of a target track set corresponding to the risk blind area target and the target planning track respectively; Generating state information of an environmental target based on the state information of the estimated collision point, and generating a first identifier of the environmental target based on a second identifier of the risk blind zone target; and constructing the environment model based on the state information of each environment target and the first identifier. In one embodiment, associating each target track set with a corresponding environmental target in the environmental model includes: Determining matched target identifications from a plurality of second identifications based on the first identifications of the environmental targets for each environmental target in the environmental model; determining a first predicted track set of the blind area target indicated by the target mark; and associating a first predicted track set of the blind area target indicated by the target mark with the environment target. In one embodiment, the generating the state information of the environmental target based on the state information of the estimated collision point includes: Aiming at each risk blind area target, determining the current prediction state information of the risk blind area target based on the state information of the prediction collision point; based on the predicted state information, state information of the environmental target is generated. In one