CN-122009249-A - Vehicle control method and electronic device

CN122009249ACN 122009249 ACN122009249 ACN 122009249ACN-122009249-A

Abstract

The application discloses a vehicle control method and electronic equipment. The application relates to the technical field of automatic driving technology and artificial intelligence, wherein the method comprises the steps of evaluating the perceived credibility of a tracking target of a vehicle to obtain a credibility level of the tracking target, predicting motion state vectors at the current moment by using current perception data under the condition that the credibility level is a first level, or predicting motion state vectors at the current moment by using historical track data under the condition that the credibility level is a second level, generating track sequences of the tracking target at a plurality of moments after the current moment by a recursive prediction mode based on the motion state vectors at the current moment and the credibility level, and controlling the running of the vehicle based on the track sequences of the tracking target at the plurality of moments after the current moment. The application solves the technical problem of lower safety degree of vehicle control in the related art.

Inventors

WANG HONGLIN
LIN QIAO
CHEN HUIYONG

Assignees

易控智驾科技股份有限公司

Dates

Publication Date: 20260512
Application Date: 20260415

Claims (10)

1. A vehicle control method characterized by comprising: evaluating the perceived credibility of a tracking target of a vehicle to obtain the credibility level of the tracking target; under the condition that the credibility level is a first level, predicting to obtain a motion state vector of the current moment by using the current perception data, or under the condition that the credibility level is a second level, predicting to obtain a motion state vector of the current moment by using historical track data, wherein the first level is smaller than the second level; generating track sequences of the tracking target at a plurality of moments after the current moment in a recursive prediction mode based on the motion state vector of the current moment and the credibility level; and controlling the vehicle to run based on track sequences of the tracking target at a plurality of moments after the current moment.
2. The method according to claim 1, wherein the motion state vector at the current time includes at least one of a position component, a speed component, a heading angle component, and an angular velocity component, wherein predicting the motion state vector at the current time using the current sense data includes: determining a motion state vector at the current moment based on the boundary box information corresponding to the tracking target in the current perception data; Wherein, when the motion state of the current moment includes the heading angle component, the determining the motion state vector of the current moment based on the bounding box information corresponding to the tracking target in the current perception data includes: Determining the number of vertexes of the geometric shape corresponding to the tracking target based on the current perception data; Determining the heading angle component based on the bounding box information under the condition that the number of the vertexes is larger than or equal to a preset number; And determining the course angle component based on the speed direction of the tracking target under the condition that the vertex number is smaller than the preset number.
3. The vehicle control method according to claim 1, characterized in that the predicting a motion state vector at a current time using the historical trajectory data includes: Determining a target track point closest to the current moment from the historical track data based on the confidence coefficient of the historical track point in the historical track data, wherein the confidence coefficient of the target track point is smaller than a preset threshold value, and the confidence coefficient of the historical track point is used for representing the accuracy of historical perception data corresponding to the historical track point; intercepting track points positioned behind the target track points from the historical track data to obtain a target track point sequence, wherein the length of the target track point sequence is greater than or equal to a preset length, and the confidence coefficient of the track points in the target track point sequence is greater than or equal to the preset threshold; Determining a motion parameter of the tracking target based on the target track point sequence; And determining a motion state vector of the current moment based on the motion parameter and/or the current perception data.
4. The vehicle control method according to claim 3, characterized in that the determining of the motion parameter of the tracking target based on the target trajectory point sequence includes: smoothing the angle value in the target track point sequence based on a sliding window with a preset length to obtain a smoothed track point sequence; determining the motion parameters based on the smoothed track point sequence; preferably, the smoothing processing is performed on the angle value in the target track point sequence based on the sliding window with the preset length to obtain a track point sequence after the smoothing processing, including: and controlling the sliding window to slide from a first track point in the target track point sequence, determining a plurality of angle values positioned in the sliding window in each sliding process of the sliding window, carrying out normalization processing on the angle values to obtain a plurality of normalized angle values, determining an average value of the normalized angle values, and obtaining a smooth angle value in the sliding window until the angle values in the target track point sequence are processed.
5. The vehicle control method according to claim 3, wherein the motion parameters include at least one of a speed parameter, an angular speed parameter, and an angle parameter, and wherein the determining the motion parameters of the tracking target based on the target trajectory point sequence includes one or a combination of: determining the speed parameter based on the total displacement between adjacent track points in the target track point sequence and the total time corresponding to the target track point sequence; Determining the angular velocity parameter based on the total variation of the smooth angle values in the target track point sequence and the total time; determining the angle parameter based on the average angle of the smooth angle values in the target track point sequence; Wherein the angular velocity parameter is located within a first preset angular velocity range.
6. The vehicle control method according to any one of claims 1 to 5, characterized in that the generating of the track sequence of the tracking target at a plurality of times after the current time by way of recursive prediction based on the motion state vector at the current time and the reliability level includes: Determining a target steering mode at the current moment based on the historical angular velocity data of the tracking target; determining a target covariance matrix based on the confidence level; generating track sequences of the multiple moments by a recursive prediction mode through the target steering mode, the target covariance matrix and the motion state vector of the current moment; preferably, the target covariance matrix is a preset matrix when the reliability level is a first level, and the target covariance matrix is a historical covariance matrix when the reliability level is a second level.
7. The vehicle control method according to claim 6, characterized in that the determining the target steering mode at the present time based on the historical angular velocity data of the tracking target includes: Acquiring a preset number of historical angular velocity values closest to the current moment in the historical track data; Determining the target steering mode based on the preset number of historical angular velocity values and the angular velocity value of the tracking target at the current moment in the current perception data; Preferably, the determining the target steering mode based on the preset number of historical angular velocity values and the angular velocity value of the tracking target at the current moment in the current sensing data includes: Performing mutation detection on a target historical angular velocity value in the preset number of historical acceleration values to obtain the preset number of first angular velocity values, wherein the target historical angular velocity value is a historical angular velocity value closest to the current moment in the preset number of historical angular velocity data; Performing outlier processing on the first angular velocity values with the preset number to obtain second angular velocity values with the preset number; And determining the target steering mode based on the preset number of second angular velocity values.
8. The vehicle control method according to claim 7, characterized in that the determining the target steering mode based on the preset number of second angular velocity values includes: determining that the target steering mode is a sharp steering mode under the condition that the preset number of second angular velocity values and the angular velocity value at the current moment meet preset mode judgment conditions; Determining that the target steering mode is a normal steering mode under the condition that the preset number of second angular velocity values and the angular velocity value at the current moment do not meet the preset mode judgment condition; Preferably, the preset mode judgment condition includes: The historical angular velocity values of the preset number are smaller than the preset angular velocity; The historical angular velocity values of the preset quantity do not meet the monotonically increasing condition; The angular velocity value at the current moment is within a second preset angular velocity range.
9. The vehicle control method according to any one of claims 1 to 5, characterized in that the evaluation of the perceived credibility of a tracked target of a vehicle to obtain a credibility level of the tracked target includes: Acquiring tracking data of the tracking target; Determining at least one perception evaluation index of the tracking target based on the tracking data, wherein the at least one perception evaluation index comprises at least one of the duration of historical track data of the tracking target, the tracking time of the tracking target, the time of the tracking target in a motion state, the speed of the tracking target at the current moment and the confidence of the current perception data; Under the condition that any one of the perception evaluation indexes meets a preset evaluation condition corresponding to the perception evaluation index, determining the credibility grade as a first grade; And under the condition that all the at least one perception evaluation index does not meet the preset evaluation condition corresponding to the at least one perception evaluation index, determining the credibility level as a second level.
10. An electronic device, comprising: A memory storing an executable program; a processor for executing the program, wherein the program when run performs the method of any of claims 1 to 9.

Description

Vehicle control method and electronic device Technical Field The application relates to the technical field of automatic driving and artificial intelligence, in particular to a vehicle control method and electronic equipment. Background In a mine automatic driving scene, track prediction is a key step of automatic driving control, and peripheral traffic situation changes can be perceived in advance through the track prediction, so that the rationality, the foresight and the safety of an automatic driving decision are improved. However, under actual complex working conditions, the problems of transient jump of course angle, missing tracking data, unstable motion state and the like often occur to the target due to perceived noise, shielding, low-speed movement or transient static state, so that the track prediction deviates seriously from the actual motion track, thereby improving the collision risk of the vehicle and further lowering the safety degree of vehicle control. In view of the above problems, no effective solution has been proposed at present. Disclosure of Invention The embodiment of the application provides a vehicle control method and electronic equipment, which are used for at least solving the technical problem of low safety degree of vehicle control in the related technology. According to one aspect of the embodiment of the application, a vehicle control method is provided, which comprises the steps of evaluating the perceived credibility of a tracking target of a vehicle to obtain a credibility level of the tracking target, predicting a motion state vector at a current moment by using current perception data under the condition that the credibility level is a first level, or predicting the motion state vector at the current moment by using historical track data under the condition that the credibility level is a second level, wherein the first level is smaller than the second level, generating track sequences of the tracking target at a plurality of moments after the current moment by recursively predicting the track sequences of the tracking target at a plurality of moments after the current moment based on the motion state vector at the current moment and the credibility level, and controlling the running of the vehicle based on the track sequences of the tracking target at the plurality of moments after the current moment. Further, the motion state vector at the current moment comprises at least one of a position component, a speed component, a course angle component and an angular speed component, the motion state vector at the current moment is obtained through prediction by using the current perception data, the motion state vector at the current moment is determined based on boundary box information corresponding to a tracking target in the current perception data, the motion state vector at the current moment is determined based on boundary box information corresponding to the tracking target in the current perception data when the motion state at the current moment comprises the course angle component, the motion state vector at the current moment is determined based on the boundary box information corresponding to the tracking target in the current perception data, the number of vertexes is determined based on the boundary box information when the number of vertexes is larger than or equal to a preset number, and the course angle component is determined based on the speed direction of the tracking target when the number of vertexes is smaller than the preset number. Further, the motion state vector at the current moment is obtained by means of prediction of historical track data, wherein the motion state vector comprises the steps of determining a target track point closest to the current moment from the historical track data based on the confidence coefficient of the historical track point in the historical track data, the confidence coefficient of the target track point is smaller than a preset threshold value, the confidence coefficient of the historical track point is used for representing the accuracy of historical perception data corresponding to the historical track point, the track point located behind the target track point is intercepted from the historical track data, a target track point sequence is obtained, the length of the target track point sequence is larger than or equal to the preset length, the confidence coefficient of the track point in the target track point sequence is larger than or equal to the preset threshold value, the motion parameter of a tracking target is determined based on the target track point sequence, and the motion state vector at the current moment is determined based on the motion parameter and/or the current perception data. Further, the motion parameters of the tracking target are determined based on the target track point sequence, the motion parameters are determined based on the sliding window with the preset length, the angle values i