A processing method and apparatus for evaluating the parking performance of a vehicle.

Abstract

This invention relates to a processing method and apparatus for evaluating the parking performance of a vehicle. The method includes: collecting output information from the vehicle's onboard system to refresh the vehicle data queue during the evaluation process; confirming whether a parking phase has begun based on each newly added record in the queue; if confirmed, recording the current time as the start time and tracking the end time of the parking session, and performing an evaluation based on all records within the start and end times in the queue; confirming whether the parking is temporary, and if so, confirming the first and second times after the end time, and performing an evaluation based on all records within the first and second times in the queue; and finally, calculating an evaluation score for the vehicle's parking performance at the end of the evaluation. This invention can improve evaluation efficiency and effectively enhance the real-time performance of the evaluation.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a processing method and apparatus for evaluating the parking performance of vehicles. Background Technology

[0002] Evaluating the perception response performance of autonomous / driverless vehicles requires assessing their parking performance at different locations for different purposes. For example, evaluating the parking performance of private vehicles in parking spaces, and evaluating the parking performance of commercial vehicles in parking spaces and at bus stops. Currently, the conventional approach to evaluating vehicle parking performance in parking spaces / bus stops involves first collecting and saving real-time data for a single evaluation process (normal driving -> parking in a parking space or normal driving -> temporary parking at the bus stop -> exiting the bus stop). Then, after the evaluation process ends, the collected data is analyzed and scored manually or semi-manually according to parking performance evaluation rules. Clearly, this conventional approach, due to the manual operation involved, suffers from poor evaluation efficiency and real-time performance. Summary of the Invention

[0003] The purpose of this invention is to address the shortcomings of existing technologies by providing a processing method, apparatus, electronic device, and computer-readable storage medium for evaluating the parking performance of vehicles. This invention collects real-time perception target information, positioning information, motion information, and path information output by the vehicle system during vehicle evaluation and refreshes the vehicle data queue based on the collected data. When a new record is added to the vehicle data queue, it identifies whether the vehicle has entered the parking phase based on the newly added record. Upon identification that the vehicle has entered the parking phase, the current time is recorded as the start time, and the end time of the parking phase is confirmed through tracking and monitoring. All vehicle data records from the start time to the end time are extracted from the vehicle data queue to form a first record sequence, and a real-time parking performance evaluation is performed based on this sequence. The invention also identifies whether the parking is temporary. If it is temporary, the two time points after the end time are recorded as the first and second times. When the current time reaches the second time, all vehicle data records from the first time to the second time are extracted from the vehicle data queue to form a second record sequence, and a real-time parking performance evaluation is performed based on this sequence. Finally, at the end of the evaluation, the vehicle's parking performance is scored and a corresponding evaluation score is calculated based on the evaluation data queue. This invention can perform real-time anomaly analysis during vehicle evaluation and output the evaluation score immediately upon completion of the evaluation. This invention can not only improve evaluation efficiency but also effectively improve the real-time performance of the evaluation.

[0004] To achieve the above objectives, a first aspect of the present invention provides a method for evaluating the parking performance of a vehicle, the method comprising:

[0005] During the evaluation of the first vehicle, the system connects to the vehicle's onboard system and collects real-time perception target information, positioning information, motion information, and path information output by the onboard system's environmental perception module, navigation and positioning module, path planning module, and driving control module. Based on the collected data, the system generates corresponding vehicle data records and stores them in a preset vehicle data queue.

[0006] When a new record is added to the vehicle data queue, the newly added vehicle data record is taken as the corresponding current record; and the vehicle is identified as having entered the parking stage based on the current record to obtain the corresponding real-time identification result; the real-time identification result includes whether the vehicle has entered or not.

[0007] When the latest real-time identification result indicates entry, the current time is recorded as the start time of this parking session. From this start time, the end time of the vehicle's parking session is tracked and monitored to obtain the corresponding end time. All vehicle data records from the start time to the end time are extracted from the vehicle data queue to form a corresponding first record sequence. A parking performance evaluation is performed based on the first record sequence to obtain corresponding evaluation data records, which are then stored in a preset evaluation data queue. A real-time judgment result is obtained to determine whether the parking is temporary. If the real-time judgment result is temporary, the parking time is... The two time points obtained by adding the current end time to the preset first and second durations are recorded as the corresponding first time and second time. When the current time reaches the second time, all vehicle data records from the first time to the second time are extracted from the vehicle data queue to form a corresponding second record sequence. A parking performance evaluation is performed based on the second record sequence to obtain the corresponding evaluation data record, which is then stored in the evaluation data queue. The real-time judgment result includes temporary and non-temporary results. The first duration is a preset platform stop duration threshold, and the second duration = first duration × a, where a is a preset delay ratio parameter, and a > 1.

[0008] At the end of the evaluation of the first vehicle, the parking performance of the vehicle is scored and calculated based on the evaluation data queue to obtain the corresponding first evaluation score.

[0009] Preferably, the vehicle data queue includes multiple vehicle data records;

[0010] The vehicle data record includes a first timestamp, a first set of perceived targets, a first positioning coordinate, a first planned trajectory, a first vehicle speed, and a first heading angle;

[0011] The first perception target set is the set of perception targets output by the environmental perception module, and consists of one or more first perception targets; the first perception target includes a target identifier, a target type, and a set of target key point coordinates; the target type includes at least parking spaces and platforms; when the target type is a parking space, the corresponding set of target key point coordinates includes the coordinates of the center point of the parking space, the coordinates of the top left corner vertex of the parking space, the coordinates of the top right corner vertex of the parking space, the coordinates of the bottom right corner vertex of the parking space, and the coordinates of the bottom left corner vertex of the parking space; when the target type is a platform, the corresponding set of target key point coordinates includes the coordinates of the top left corner vertex of the outer side of the platform, the coordinates of the bottom left corner vertex of the outer side of the platform, the coordinates of the center point of the outer side of the passenger pick-up area, and the coordinates of the center point of the outer side of the passenger drop-off area.

[0012] The first positioning coordinates are the coordinates of the rear axle center point of the vehicle output by the navigation positioning module;

[0013] The first planned trajectory is the vehicle's planned path output by the path planning module, which is composed of multiple first trajectory points arranged in sequence; each first trajectory point includes the coordinates of the first point and the velocity of the first point; the velocity of the first point is greater than or equal to zero.

[0014] The first vehicle speed and the first heading angle are real-time vehicle speed and heading angle information output by the driving control module; if the first vehicle speed is less than zero, it means that the vehicle is reversing at the corresponding time of the first timestamp.

[0015] The evaluation data queue includes multiple evaluation data records;

[0016] The evaluation data record includes a first abnormal timestamp and a first abnormal type; the first abnormal type includes abnormal parking posture, abnormal reversing behavior, and abnormal parking timeout.

[0017] Preferably, the step of identifying whether the vehicle has entered the parking stage based on the current record to obtain the corresponding real-time identification result specifically includes:

[0018] Step 31: Take the currently recorded first perception target set and first planned trajectory as the corresponding current perception target set and current planned trajectory; and extract the first point coordinates and first point velocity of the last first trajectory point of the current planned trajectory as the corresponding target point coordinates and target point velocity;

[0019] Step 32: Record each first sensing target in the current sensing target set whose target type is parking space as the corresponding first target; record each first sensing target in the current sensing target set whose target type is platform as the corresponding second target; and count the total number of the first and second targets to obtain the corresponding first total number and second total number.

[0020] Step 33: Identify the target point velocity and the first and second totals;

[0021] Step 34: If the target point speed is zero and the first total is greater than zero, then a corresponding first coordinate region is formed by the coordinates of the top left corner vertex, the top right corner vertex, the bottom right corner vertex, and the bottom left corner vertex of each first target parking space; if only one of the obtained first coordinate regions can cover the target point coordinates, then the corresponding real-time recognition result is set as "entered".

[0022] Step 35: If the target point velocity is zero and the second total is greater than zero, then the straight line segment between the coordinates of the upper left corner vertex and the lower left corner vertex of the outer side of the platform for each of the second targets is taken as the corresponding first outer edge; and the vertical distance from the target point coordinates to each of the first outer edges is calculated to obtain the corresponding first edge spacing, and the shortest first edge spacing is recorded as the corresponding current shortest spacing; if the current shortest spacing is less than the preset vehicle-platform parking spacing threshold, then the corresponding real-time recognition result is set as entered;

[0023] Step 36: If the target point velocity is not zero or the first and second totals are both zero, then the corresponding real-time identification result is set to "not entered".

[0024] Preferably, the step of tracking and monitoring the end time of the vehicle's current parking session to obtain the corresponding end time specifically includes:

[0025] When a new record is added to the vehicle data queue, the newly added vehicle data record is taken as the corresponding current record; and it is identified whether the first vehicle speed of the current record is zero; if the first vehicle speed of the current record is zero, all vehicle data records in the vehicle data queue whose first timestamps are within a preset first recent duration are extracted to form a corresponding recent time period record sequence; and it is identified whether all the first vehicle speeds in the recent time period record sequence are zero; if all the first vehicle speeds in the recent time period record sequence are zero, the tracking and monitoring are stopped, and the first timestamp of the first vehicle data record with the first vehicle speed of zero in the recent time period record sequence is extracted as the corresponding end time of this operation.

[0026] Preferably, the step of performing a parking performance evaluation based on the first record sequence and storing the corresponding evaluation data record into a preset evaluation data queue specifically includes:

[0027] Step 51: Record each vehicle data record in the first record sequence where the first vehicle speed is less than zero as the corresponding reversing point record; and count the total number of reversing point records to obtain the corresponding total number of reversing points; and when the total number of reversing points is greater than zero, perform an evaluation record addition operation on the evaluation data queue based on all the reversing point records.

[0028] Step 52: Take the last vehicle data record in the first record sequence as the corresponding parking point record; and identify whether the parking posture of the vehicle is abnormal based on the parking point record, and add the evaluation record to the evaluation data queue when the abnormal posture is identified.

[0029] Furthermore, the step of adding evaluation records to the evaluation data queue based on all the reversing point records specifically includes:

[0030] The first timestamp recorded at each of the reversing points is used as a corresponding first abnormal timestamp; a corresponding first abnormal type is set as reversing behavior abnormal; and each of the first abnormal timestamps and its corresponding first abnormal type is combined to form a corresponding evaluation data record and stored in the evaluation data queue.

[0031] Furthermore, the step of identifying whether the vehicle's parking posture is abnormal based on the parking point records and adding evaluation records to the evaluation data queue when an abnormal posture is identified specifically includes:

[0032] Step 71: The first set of perceived targets, the first positioning coordinates, and the first heading angle recorded at the parking point are taken as the corresponding current set of perceived targets, current positioning coordinates, and current heading angle; and each first perceived target in the current set whose target type is parking space is recorded as the corresponding third target; and each first perceived target in the current set whose target type is platform is recorded as the corresponding fourth target; and the total number of the third and fourth targets is counted to obtain the corresponding third total number and fourth total number; and the corresponding first parking location type is initialized to parking space.

[0033] The first parking location type includes parking spaces and platforms;

[0034] Step 72: If the total number of the third targets is greater than zero, a corresponding second coordinate region is formed by the coordinates of the top left corner vertex, the top right corner vertex, the bottom right corner vertex, and the bottom left corner vertex of each third target; and when there is only one second coordinate region among all the obtained second coordinate regions that can cover the current positioning coordinates, the first parking location type is set to parking space; and the third target corresponding to this second coordinate region that can cover the current positioning coordinates is taken as the corresponding current parking location target.

[0035] Step 73: If the total number of fourth targets is greater than zero, then the straight line segment between the coordinates of the upper left corner vertex and the lower left corner vertex of the outer side of each fourth target is taken as the corresponding second outer edge; and the vertical distance from the current positioning coordinate to each second outer edge is calculated to obtain the corresponding second edge spacing, and the shortest second edge spacing is recorded as the corresponding current shortest spacing; and when the current shortest spacing is less than the preset vehicle-platform parking spacing threshold, the first parking position type is set to platform; and the fourth target corresponding to the current shortest spacing is taken as the corresponding current parking position target.

[0036] Step 74: Record the target type of the current parking location target as the corresponding current parking location type; and identify the current parking location type;

[0037] Step 75: If the current parking location type is a parking space, then based on the current positioning coordinates, the current heading angle, and the vehicle model parameters of the first vehicle, identify the ground projection coordinates of the four wheel center points, the apex of the front of the vehicle, and the apex of the rear of the vehicle to obtain the corresponding left front wheel contact point coordinates, right front wheel contact point coordinates, right rear wheel contact point coordinates, left rear wheel contact point coordinates, the ground coordinates of the apex of the front of the vehicle, and the ground coordinates of the apex of the rear of the vehicle; and use the ground projection point coordinates corresponding to the current positioning coordinates as the corresponding ground coordinates of the rear axle center point; and based on the left front wheel contact point coordinates, the right front wheel contact point coordinates, the right rear wheel contact point coordinates, the left rear wheel contact point coordinates, the ground coordinates of the apex of the front of the vehicle, the ground coordinates of the apex of the rear of the vehicle, the ground coordinates of the rear axle center point, and the target of the current parking location, identify whether the parking posture of the vehicle in the parking space is abnormal, and add an evaluation record to the evaluation data queue when an abnormal posture is identified;

[0038] The vehicle parameters include at least the vehicle width parameter, vehicle length parameter, front axle position parameter, rear axle position parameter, center axle position parameter, left front wheel position parameter, left rear wheel position parameter, right front wheel position parameter, right rear wheel position parameter, left front door position parameter, left rear door position parameter, right front door position parameter, and right rear door position parameter.

[0039] Step 76: If the current parking location type is a platform, then based on the current positioning coordinates, the current heading angle, and the vehicle model parameters of the first vehicle, the ground projection coordinates of the center points of the front and rear right wheels and the center points of the front and rear right doors of the vehicle are identified to obtain the corresponding ground coordinates of the right front wheel contact point, the right rear wheel contact point, the center point of the right front door, and the center point of the right rear door; and based on the ground coordinates of the right front wheel contact point, the right rear wheel contact point, the center point of the right front door, the center point of the right rear door, and the target of the current parking location, whether the parking posture of the vehicle on the platform side is abnormal is identified, and when an abnormal posture is identified, an evaluation record is added to the evaluation data queue.

[0040] More preferably, the step of identifying whether the vehicle's parking posture in the parking space is abnormal based on the coordinates of the left front wheel contact point, the right front wheel contact point, the right rear wheel contact point, the left rear wheel contact point, the ground coordinates of the apex of the vehicle's front, the apex of the vehicle's rear, the ground coordinates of the rear axle center point, and the target of the current parking position, and adding an evaluation record to the evaluation data queue when an abnormal posture is identified, specifically includes:

[0041] Step 81: Based on the coordinates of the top left, top right, bottom right, and bottom left corners of the parking space, and the center point of the current parking location, confirm the four edges and center line of the current parking space to obtain the corresponding left edge, top edge, right edge, bottom edge, and center line; and calculate the width w1 and length h1 of the current parking space based on the coordinates of the top left, top right, bottom right, and bottom left corners of the parking space; and record the vehicle width and length parameters of the vehicle model parameters as the corresponding width w. c and length h c ;

[0042] Step 82: Record the horizontal and vertical distance between the coordinates of the left front wheel contact point and the left side edge as the corresponding distance d1; record the horizontal and vertical distance between the coordinates of the right front wheel contact point and the right side edge as the corresponding distance d2; record the horizontal and vertical distance between the coordinates of the right rear wheel contact point and the right side edge as the corresponding distance d3; record the horizontal and vertical distance between the coordinates of the left rear wheel contact point and the left side edge as the corresponding distance d4; record the vertical distance between the ground coordinates of the vehicle apex and the top edge as the corresponding distance d5; record the vertical distance between the ground coordinates of the rear apex and the bottom edge as the corresponding distance d6; and record the horizontal and vertical distance between the ground coordinates of the rear axle center point and the parking space center line as the corresponding distance d7.

[0043] Step 83, based on the spacings d1, d2, d3, d4 and the widths w1, w c Calculate the corresponding lateral deviation ratio p1; and based on the distances d5 and d6, the lengths h1 and h2... c Calculate the corresponding longitudinal deviation ratio p2; and calculate the corresponding center offset ratio p3 based on the spacing d7 and the width w1;

[0044] in,

[0045] The closer the lateral deviation ratio p1 is to zero, the smaller the lateral deviation; the closer the longitudinal deviation ratio p2 is to zero, the smaller the longitudinal deviation; and the closer the center offset ratio p3 is to zero, the smaller the centerline offset.

[0046] Step 84: Compare the lateral deviation ratio p1, the longitudinal deviation ratio p2, and the center offset ratio p3 based on preset lateral deviation range, longitudinal deviation range, and center offset range; if the lateral deviation ratio p1 does not meet the corresponding lateral deviation range, or the longitudinal deviation ratio p2 does not meet the corresponding longitudinal deviation range, or the center offset ratio p3 does not meet the corresponding center offset range, then the first timestamp recorded at the parking point is taken as a corresponding first abnormal timestamp, and a corresponding first abnormal type is set as parking pose abnormality. The first abnormal timestamp and the first abnormal type obtained this time are combined to form a corresponding evaluation data record and added to the evaluation data queue.

[0047] More preferably, the step of identifying whether the vehicle's parking posture on the platform side is abnormal based on the coordinates of the right front wheel contact point, the coordinates of the right rear wheel contact point, the ground coordinates of the center point of the right front door, the ground coordinates of the center point of the right rear door, and the target of the current parking position, and adding an evaluation record to the evaluation data queue when an abnormal posture is identified, specifically includes:

[0048] Step 91: Based on the coordinates of the upper left corner vertex and the lower left corner vertex of the outer side of the platform of the current parking location target, confirm the outer edge line of the current platform to obtain the corresponding outer edge line of the platform; and record the perpendicular line from the coordinates of the outer center point of the passenger pick-up area of ​​the current parking location target to the outer edge line of the platform as the corresponding center line of the passenger pick-up area; and record the perpendicular line from the coordinates of the outer center point of the passenger drop-off area of ​​the current parking location target to the outer edge line of the platform as the corresponding center line of the passenger drop-off area.

[0049] Step 92: Record the horizontal and vertical distance between the coordinates of the right front wheel contact point and the first outer edge line as the corresponding distance d8; record the horizontal and vertical distance between the coordinates of the right rear wheel contact point and the first outer edge line as the corresponding distance d9; and record the horizontal and vertical distance between the coordinates of the center point of the right front door and the first outer edge line as the corresponding distance d. 10 The horizontal and vertical distance between the ground coordinates of the center point of the right rear door and the first outer edge line is recorded as the corresponding distance d. 11 The vertical distance between the ground coordinates of the center point of the right front door and the center line of the boarding area is recorded as the corresponding distance d. 12 The vertical distance between the ground coordinates of the center point of the right rear door and the center line of the drop-off area is recorded as the corresponding distance d. 13 ;

[0050] Step 93, based on the preset platform stopping distance range, adjust the distances d8, d9, and d... 10 d 11 Perform a comparison; if the stated spacings d8, d9, d 10 d 11 If at least one of the intervals does not meet the platform stopping interval range, then the first timestamp recorded at the parking point is used as a corresponding first abnormal timestamp, and a corresponding first abnormal type is set as parking posture abnormal. The first abnormal timestamp and the first abnormal type obtained this time are combined to form a corresponding evaluation data record and added to the evaluation data queue.

[0051] Step 94, adjust the spacing d based on the preset passenger pick-up and drop-off area offset range. 12 d 13 Perform a comparison; if the distance d 12 d 13If at least one of the spacings does not meet the offset range of the passenger pick-up and drop-off area, then the first timestamp recorded at the parking point is used as a corresponding first abnormal timestamp, and a corresponding first abnormal type is set as parking posture abnormal. The first abnormal timestamp and the first abnormal type obtained this time are combined to form a corresponding evaluation data record and added to the evaluation data queue.

[0052] Preferably, the step of determining whether the parking is temporary to obtain a corresponding real-time determination result specifically includes:

[0053] The last vehicle data record in the first recording sequence is taken as the corresponding parking point record; the first positioning coordinate of the parking point record is taken as the corresponding current vehicle coordinate; and each of the first sensing targets in the first sensing target set of the parking point record whose target type is parking space or platform is recorded as the corresponding fifth target or sixth target; when the number of the fifth targets is not zero, the straight-line distance between the center point coordinate of the parking space of each fifth target and the current vehicle coordinate is calculated and the calculation result is taken as a corresponding first distance; when the number of the sixth targets is not zero, the straight-line distance between the center point coordinate of the outer side of the passenger pick-up area of ​​each sixth target and the current vehicle coordinate is calculated and the calculation result is taken as a corresponding first distance; and the fifth target or sixth target corresponding to the shortest first distance is taken as the corresponding current target; and the target type of the current target is taken as the corresponding current target type; and the current target type is identified; if the current target type is parking space, the corresponding real-time judgment result is set to non-temporary; if the current target type is platform, the corresponding real-time judgment result is set to temporary.

[0054] Preferably, the step of performing a parking performance evaluation based on the second record sequence and storing the corresponding evaluation data record in the evaluation data queue specifically includes:

[0055] The system identifies whether all the first vehicle speeds in the second record sequence are zero; if so, the first moment is used as a corresponding first abnormal timestamp, and a corresponding first abnormal type is set as parking timeout abnormal. The first abnormal timestamp and the first abnormal type obtained this time are combined to form a corresponding evaluation data record and added to the evaluation data queue.

[0056] Preferably, the step of calculating the corresponding first evaluation score by scoring the vehicle's parking performance based on the evaluation data queue specifically includes:

[0057] The total number of each type of anomaly in the evaluation data queue is statistically analyzed to obtain the corresponding total number of parking posture anomalies, total number of reversing behavior anomalies, and total number of parking timeout anomalies; and the anomaly type corresponding to each non-zero anomaly total is recorded as a corresponding evaluation anomaly item.

[0058] Based on each of the aforementioned evaluation anomalies, a preset first correspondence table is queried. The first deduction value field of the first correspondence record in the first correspondence table that matches the first anomaly type field with each of the aforementioned evaluation anomalies is extracted as the corresponding anomaly deduction value. The total deduction value is calculated by summing all the obtained anomaly deduction values. The first correspondence table is a correspondence table that reflects the correspondence between anomaly types and anomaly deduction values. The first correspondence table includes three first correspondence records. Each first correspondence record includes a first anomaly type field and a first deduction value field. The first anomaly type field includes abnormal parking posture, abnormal reversing behavior, and abnormal parking timeout. The first deduction value field is an integer score.

[0059] The first evaluation score is calculated based on the preset full score and the total deduction score: full score - total deduction score.

[0060] A second aspect of the present invention provides an apparatus for implementing the processing method for evaluating the parking performance of a vehicle as described in the first aspect above. The apparatus includes: a data acquisition module, a data storage module, a parking stage identification module, a real-time evaluation module, and a scoring calculation module.

[0061] The data storage module is connected to the data acquisition module, the parking stage identification module, the real-time evaluation module, and the scoring calculation module, respectively; the parking stage identification module is connected to the real-time evaluation module.

[0062] The data acquisition module is used to connect with the vehicle system of the first vehicle during the evaluation process of the first vehicle; and to collect real-time perceived target information, positioning information, motion information and path information output by the environmental perception module, navigation and positioning module, path planning module and driving control module of the vehicle system, and to generate corresponding vehicle data records based on the collected data and store them in the vehicle data queue.

[0063] The data storage module is used to store the vehicle data queue and the evaluation data queue;

[0064] The parking phase identification module is used to take each newly added vehicle data record as the corresponding current record when a new record is added to the vehicle data queue; and to identify whether the vehicle has entered the parking phase based on the current record to obtain the corresponding real-time identification result; the real-time identification result includes whether the vehicle has entered or not.

[0065] The real-time evaluation module is used to record the current time as the start time when the latest real-time identification result is "entered"; and to track and monitor the end time of the vehicle's current parking from the start time to obtain the corresponding end time; to extract all vehicle data records from the vehicle data queue from the start time to the end time to form a corresponding first record sequence; to perform a parking performance evaluation based on the first record sequence to obtain corresponding evaluation data records and store them in the evaluation data queue; and to determine whether the parking is temporary to obtain a corresponding real-time judgment result; if the real-time judgment result is temporary... Then, the two time points obtained by adding the current end time to the preset first and second durations are recorded as the corresponding first time and second time; when the current time reaches the second time, all vehicle data records from the first time to the second time in the vehicle data queue are extracted to form the corresponding second record sequence; and a parking performance evaluation is performed based on the second record sequence to obtain the corresponding evaluation data record, which is stored in the evaluation data queue; the real-time judgment result includes temporary and non-temporary; the first duration is a preset platform stopping duration threshold, the second duration = the first duration × a, where a is a preset delay ratio parameter, and a>1;

[0066] The scoring calculation module is used to calculate the parking performance of the vehicle based on the evaluation data queue at the end of the evaluation of the first vehicle to obtain the corresponding first evaluation score.

[0067] A third aspect of the present invention provides an electronic device, including: a memory, a processor, and a transceiver;

[0068] The processor is used to couple with the memory, read and execute instructions in the memory to implement the steps of the method described in the first aspect above;

[0069] The transceiver is coupled to the processor, and the processor controls the transceiver to send and receive messages.

[0070] A fourth aspect of the present invention provides a computer-readable storage medium storing computer instructions that, when executed by a computer, cause the computer to perform the instructions described in the first aspect.

[0071] This invention provides a processing method, apparatus, electronic device, and computer-readable storage medium for evaluating the parking performance of a vehicle. As described above, in the vehicle evaluation process, this invention collects real-time perception target information, positioning information, motion information, and path information output by the vehicle system and refreshes the vehicle data queue based on the collected data. When a new record is added to the vehicle data queue, the system identifies whether the vehicle has entered the parking phase based on the newly added record. Upon identification that the vehicle has entered the parking phase, the current time is recorded as the start time, and the end time of the parking phase is confirmed through tracking and monitoring. All vehicle data records from the start time to the end time are extracted from the vehicle data queue to form a first record sequence, and a real-time parking performance evaluation is performed based on this sequence. The system also identifies whether the parking is temporary. If it is temporary, the two time points after the end time are recorded as the first and second times. When the current time reaches the second time, all vehicle data records from the first time to the second time are extracted from the vehicle data queue to form a second record sequence, and a real-time parking performance evaluation is performed based on this sequence. Finally, at the end of the evaluation, the vehicle's parking performance is scored and a corresponding evaluation score is calculated based on the evaluation data queue. The embodiments of the present invention can perform real-time anomaly analysis during vehicle evaluation and output the evaluation score immediately at the end of the evaluation; the embodiments of the present invention not only improve the evaluation efficiency, but also improve the real-time performance of the evaluation. Attached Figure Description

[0072] Figure 1 This is a schematic diagram of a processing method for evaluating the parking performance of a vehicle according to Embodiment 1 of the present invention;

[0073] Figure 2 This is a schematic diagram of seven types of spacing in a parking space scenario according to Embodiment 1 of the present invention;

[0074] Figure 3 This is a schematic diagram of six types of spacing in a platform scenario according to Embodiment 1 of the present invention;

[0075] Figure 4 This is a module structure diagram of a processing device for evaluating the parking performance of a vehicle, provided in Embodiment 2 of the present invention.

[0076] Figure 5 This is a schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention. Detailed Implementation

[0077] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0078] Embodiment 1 of the present invention provides a processing method for evaluating the parking performance of a vehicle, such as... Figure 1 The schematic diagram of a processing method for evaluating the parking performance of a vehicle according to Embodiment 1 of the present invention is shown, including the following main steps:

[0079] Step 1: During the evaluation of the first vehicle, connect to the vehicle's onboard system; collect real-time perception target information, positioning information, motion information and path information output by the onboard system's environmental perception module, navigation and positioning module, path planning module and driving control module, and generate corresponding vehicle data records based on the collected data and store them in a preset vehicle data queue.

[0080] Here, the first vehicle in this embodiment of the invention is an autonomous or driverless vehicle; the onboard system is the autonomous or driverless system of the first vehicle; the environmental perception module, navigation and positioning module, path planning module, and driving control module are essential modules for most autonomous or driverless systems, which can be understood through publicly available literature on autonomous or driverless systems, and will not be elaborated further here. It should be noted that the type of the first vehicle can be a private vehicle, such as a sedan or van; or a commercial vehicle, such as a small or medium-sized bus or a large public bus; if it is a private vehicle, only the parking performance of the first vehicle in a parking space needs to be evaluated, and the planned trajectory output by the path planning module of this type of vehicle will not include a bus stop as the target parking location; if it is a commercial vehicle, the parking performance of the first vehicle in both parking spaces and bus stops needs to be evaluated, and the planned trajectory output by the path planning module of this type of vehicle will include a bus stop or parking space as the target parking location.

[0081] In this embodiment of the invention, the vehicle data queue constructed through data acquisition is emptied at the start of each evaluation process and updated through subsequent data acquisition. This vehicle data queue includes multiple vehicle data records; each vehicle data record includes a first timestamp, a first set of perceived targets, first positioning coordinates, a first planned trajectory, a first vehicle speed, and a first heading angle; wherein:

[0082] 1) The first timestamp corresponds to the collection time of the current record;

[0083] 2) The first perception target set is the set of perception targets output by the environmental perception module, consisting of one or more first perception targets; each first perception target includes a target identifier, a target type, and a set of target key point coordinates; among them, the target type includes at least parking spaces and platforms; when the target type is a parking space, the corresponding target key point coordinate set includes the coordinates of the center point of the parking space, the coordinates of the top left corner vertex of the parking space, the coordinates of the top right corner vertex of the parking space, the coordinates of the bottom right corner vertex of the parking space, and the coordinates of the bottom left corner vertex of the parking space; when the target type is a platform, the corresponding target key point coordinate set includes the coordinates of the top left corner vertex of the outer side of the platform, the coordinates of the bottom left corner vertex of the outer side of the platform, the coordinates of the center point of the outer side of the passenger pick-up area, and the coordinates of the center point of the outer side of the passenger drop-off area;

[0084] 3) The first positioning coordinates are the coordinates of the rear axle center point of the vehicle output by the navigation positioning module;

[0085] 4) The first planned trajectory is the self-planned path output by the path planning module, which is composed of multiple first trajectory points arranged in sequence; each first trajectory point includes the first point coordinates and the first point velocity; the first point velocity is greater than or equal to zero;

[0086] 5) The first vehicle speed and the first heading angle are real-time vehicle speed and heading angle information output by the driving control module; it should be noted that if the first vehicle speed is less than zero, it means that the vehicle is reversing at the corresponding time of the first timestamp.

[0087] Step 2: When a new record is added to the vehicle data queue, the newly added vehicle data record is taken as the corresponding current record; and the current record is used to identify whether the vehicle has entered the parking stage to obtain the corresponding real-time identification result.

[0088] Specifically, this includes: Step 21, when a new record is added to the vehicle data queue, the newly added vehicle data record is used as the corresponding current record;

[0089] Step 22, and based on the current record, identify whether the vehicle has entered the parking stage to obtain the corresponding real-time identification result;

[0090] The real-time identification results include whether the user has entered or not.

[0091] Specifically, this includes: step 221, taking the currently recorded first perception target set and first planned trajectory as the corresponding current perception target set and current planned trajectory; and extracting the first point coordinates and first point velocity of the last first trajectory point of the current planned trajectory as the corresponding target point coordinates and target point velocity;

[0092] Step 222: Record each first sensing target in the current sensing target set whose target type is parking space as the corresponding first target; record each first sensing target in the current sensing target set whose target type is platform as the corresponding second target; and count the total number of the first and second targets to obtain the corresponding first total number and second total number.

[0093] Step 223: Identify the target point velocity and the first and second totals;

[0094] Step 224: If the target point velocity is zero and the first total is greater than zero, then a corresponding first coordinate region is formed by the coordinates of the top left corner vertex, top right corner vertex, bottom right corner vertex, and bottom left corner vertex of each first target parking space; if there is only one first coordinate region among all the obtained first coordinate regions that can cover the target point coordinates, then the corresponding real-time recognition result is set as entered.

[0095] Step 225: If the target point velocity is zero and the second total is greater than zero, then the straight line segment between the coordinates of the upper left corner vertex of the outer side of each second target and the coordinates of the lower left corner vertex of the outer side of the platform is taken as the corresponding first outer edge; and the vertical distance from the target point coordinates to each first outer edge is calculated to obtain the corresponding first edge spacing, and the shortest first edge spacing is recorded as the corresponding current shortest spacing; if the current shortest spacing is less than the preset vehicle-platform parking spacing threshold, then the corresponding real-time recognition result is set as entered;

[0096] Step 226: If the target point velocity is not zero or the total of the first and second points is zero, then set the corresponding real-time recognition result to "not entered".

[0097] Step 3: When the latest real-time identification result indicates entry, record the current time as the start time of this operation; from this start time, track and monitor the end time of the vehicle's current parking to obtain the corresponding end time; extract all vehicle data records from the vehicle data queue from the start time to the end time to form the corresponding first record sequence; perform a parking performance evaluation based on the first record sequence to obtain the corresponding evaluation data record and store it in the preset evaluation data queue; determine whether the parking is temporary to obtain the corresponding real-time judgment result; if the real-time judgment result is temporary, add the end time to the preset first and second durations respectively to obtain the two time points as the corresponding first and second moments; when the current time reaches the second moment, extract all vehicle data records from the vehicle data queue from the first moment to the second moment to form the corresponding second record sequence; perform a parking performance evaluation based on the second record sequence to obtain the corresponding evaluation data record and store it in the evaluation data queue.

[0098] Specifically, this includes: Step 31, when the latest real-time identification result indicates that entry has been made, the current time is recorded as the start time of this operation;

[0099] Step 32, and starting from the start time of this parking, track and monitor the end time of the vehicle's parking to obtain the corresponding end time of this parking;

[0100] Specifically, this includes: when a new record is added to the vehicle data queue, the newly added vehicle data record is taken as the corresponding current record; and it is identified whether the first vehicle speed of the current record is zero; if the first vehicle speed of the current record is zero, all vehicle data records in the vehicle data queue with first timestamps within a preset first recent duration are extracted to form a corresponding recent time period record sequence; and it is identified whether the first vehicle speeds in the recent time period record sequence are all zero; if the first vehicle speeds in the recent time period record sequence are all zero, the tracking and monitoring are stopped, and the first timestamp of the first vehicle data record with a first vehicle speed of zero in the recent time period record sequence is extracted as the corresponding end time of this operation.

[0101] Here, the first most recent duration is a preset time length parameter, such as the most recent 5 seconds;

[0102] Step 33, and extract all vehicle data records from the current start time to the current end time in the vehicle data queue to form the corresponding first record sequence;

[0103] Step 34: Perform a parking performance evaluation based on the first record sequence to obtain the corresponding evaluation data record and store it in the preset evaluation data queue;

[0104] Here, in this embodiment of the invention, the evaluation data queue constructed through real-time evaluation is emptyed at the start of each evaluation process and updated through subsequent real-time evaluations; the evaluation data queue includes multiple evaluation data records; each evaluation data record includes a first abnormal timestamp and a first abnormal type; the first abnormal type includes abnormal parking posture, abnormal reversing behavior, and abnormal parking timeout.

[0105] The current step 34 specifically includes:

[0106] Step 341: Record each vehicle data record in the first record sequence where the first vehicle speed is less than zero as the corresponding reversing point record; and count the total number of reversing point records to obtain the corresponding total number of reversing points; and when the total number of reversing points is greater than zero, add evaluation records to the evaluation data queue based on all reversing point records.

[0107] Specifically, this includes: step 3411, recording each vehicle data record in the first record sequence where the first vehicle speed is less than zero as the corresponding reversing point record; and counting the total number of reversing point records to obtain the corresponding total number of reversing points;

[0108] Step 3412, and when the total number of reversing points is greater than zero, add evaluation records to the evaluation data queue based on all reversing point records;

[0109] Specifically, this includes: using the first timestamp recorded at each reversing point as a corresponding first abnormal timestamp; setting a corresponding first abnormal type as reversing behavior abnormality; and storing a corresponding evaluation data record composed of each first abnormal timestamp and its corresponding first abnormal type into the evaluation data queue.

[0110] Step 342: Take the last vehicle data record of the first record sequence as the corresponding parking point record; and identify whether the parking posture of the vehicle is abnormal based on the parking point record, and add the evaluation record to the evaluation data queue when the posture is abnormal.

[0111] Specifically, this includes: step 3421, taking the last vehicle data record of the first record sequence as the corresponding parking point record;

[0112] Step 3422: Based on the parking point records, identify whether the vehicle's parking posture is abnormal, and add evaluation records to the evaluation data queue when abnormal posture is identified.

[0113] Specifically, it includes:

[0114] Step 34221: The first set of perceived targets, the first positioning coordinates, and the first heading angle recorded at the parking point are used as the corresponding current set of perceived targets, the current positioning coordinates, and the current heading angle; the first perceived targets of the current set whose target type is parking space are recorded as the corresponding third targets; the first perceived targets of the current set whose target type is platform are recorded as the corresponding fourth targets; the total number of the third and fourth targets is counted to obtain the corresponding total number of the third and fourth targets; and the corresponding first parking location type is initialized to parking space.

[0115] The first type of parking location includes parking spaces and platforms;

[0116] Step 34222: If the total number of third targets is greater than zero, then a corresponding second coordinate region is formed by the coordinates of the top left corner vertex, top right corner vertex, bottom right corner vertex, and bottom left corner vertex of each third target parking space; and when there is only one second coordinate region among all the obtained second coordinate regions that can cover the current positioning coordinates, the first parking location type is set to parking space; and the third target corresponding to this second coordinate region that can cover the current positioning coordinates is taken as the corresponding current parking location target.

[0117] Here, as we know from the previous text, when the first vehicle is a private vehicle, the planned trajectory output by the path planning module of this type of vehicle will not include a bus stop as the target parking location, that is, it will only output a parking space as the target parking location. Therefore, for a private vehicle, its current parking location target will only be a parking space. However, for the first vehicle, which is an operational vehicle, the planned trajectory output by the path planning module of this type of vehicle may include a parking space or a bus stop. Therefore, the current parking location target of this type of vehicle can be either a parking space or a bus stop.

[0118] Step 34223: If the total number of fourth targets is greater than zero, then the straight line segment between the coordinates of the upper left corner vertex and the lower left corner vertex of the outer side of each fourth target is taken as the corresponding second outer edge; and the vertical distance from the current positioning coordinate to each second outer edge is calculated to obtain the corresponding second edge spacing, and the shortest second edge spacing is recorded as the corresponding current shortest spacing; and when the current shortest spacing is less than the preset vehicle-platform parking spacing threshold, the first parking position type is set to platform; and the fourth target corresponding to the current shortest spacing is taken as the corresponding current parking position target.

[0119] Here, the vehicle-to-platform parking distance threshold is a pre-set distance parameter;

[0120] Step 34224: Record the target type of the target at the current parking location as the corresponding current parking location type; and identify the current parking location type.

[0121] Here, the current parking location type includes parking spaces and bus stops;

[0122] Step 34225: If the current parking location type is a parking space, then based on the current positioning coordinates, current heading angle, and vehicle model parameters, identify the ground projection coordinates of the four wheel center points, the apex of the front of the vehicle, and the apex of the rear of the vehicle to obtain the corresponding left front wheel contact point coordinates, right front wheel contact point coordinates, right rear wheel contact point coordinates, left rear wheel contact point coordinates, the ground coordinates of the apex of the front of the vehicle, and the ground coordinates of the apex of the rear of the vehicle; and use the ground projection point coordinates corresponding to the current positioning coordinates as the corresponding ground coordinates of the rear axle center point; and based on the left front wheel contact point coordinates, right front wheel contact point coordinates, right rear wheel contact point coordinates, left rear wheel contact point coordinates, the ground coordinates of the apex of the front of the vehicle, the ground coordinates of the apex of the rear of the vehicle, the ground coordinates of the rear axle center point, and the target of the current parking location, identify whether the parking posture of the vehicle in the parking space is abnormal, and add the evaluation record to the evaluation data queue when an abnormal posture is identified;

[0123] Specifically, this includes: Step 342251, if the current parking location type is a parking space, then based on the current positioning coordinates, the current heading angle, and the vehicle model parameters of the first vehicle, the ground projection coordinates of the four wheel center points, the front apex, and the rear apex of the vehicle are identified to obtain the corresponding left front wheel ground contact point coordinates, right front wheel ground contact point coordinates, right rear wheel ground contact point coordinates, left rear wheel ground contact point coordinates, front apex ground coordinates, and rear apex ground coordinates;

[0124] Among them, the vehicle parameters include at least the vehicle width parameter, vehicle length parameter, front axle position parameter, rear axle position parameter, center axle position parameter, left front wheel position parameter, left rear wheel position parameter, right front wheel position parameter, right rear wheel position parameter, left front door position parameter, left rear door position parameter, right front door position parameter, and right rear door position parameter;

[0125] It should be noted that if the first vehicle is a private vehicle, then all eight parameters in the vehicle model parameters, namely the left front wheel position parameter, left rear wheel position parameter, right front wheel position parameter, right rear wheel position parameter, left front door position parameter, left rear door position parameter, right front door position parameter, and right rear door position parameter, can be empty; if the first vehicle is a commercial vehicle, then all parameters in the vehicle model parameters cannot be empty.

[0126] Step 342252, and use the ground projection point coordinates corresponding to the current positioning coordinates as the ground coordinates of the corresponding rear axis center point;

[0127] Step 342253: Based on the coordinates of the left front wheel contact point, the right front wheel contact point, the right rear wheel contact point, the left rear wheel contact point, the ground coordinates of the top of the front of the vehicle, the ground coordinates of the top of the rear of the vehicle, the ground coordinates of the center point of the rear axle, and the target of the current parking position, identify whether the parking posture of the vehicle in the parking space is abnormal, and add the evaluation record to the evaluation data queue when the posture is abnormal.

[0128] Specifically, it includes:

[0129] Step 342253-1: Based on the coordinates of the top left corner vertex, top right corner vertex, bottom right corner vertex, bottom left corner vertex, and center point of the current parking space, confirm the four edge lines and center line of the current parking space to obtain the corresponding left edge line, top edge line, right edge line, bottom edge line, and center line of the parking space.

[0130] Step 342253-2 involves calculating the width w1 and length h1 of the current parking space based on the coordinates of the top left, top right, bottom right, and bottom left corners of the target parking space. The vehicle width and length parameters from the vehicle model parameters are then recorded as the corresponding width w. c and length h c ;

[0131] Step 342253-3: Record the horizontal and vertical distance between the left front wheel contact point coordinates and the left side edge line as the corresponding distance d1; record the horizontal and vertical distance between the right front wheel contact point coordinates and the right side edge line as the corresponding distance d2; record the horizontal and vertical distance between the right rear wheel contact point coordinates and the right side edge line as the corresponding distance d3; record the horizontal and vertical distance between the left rear wheel contact point coordinates and the left side edge line as the corresponding distance d4; record the vertical distance between the vehicle apex ground coordinates and the top edge line as the corresponding distance d5; record the vertical distance between the rear apex ground coordinates and the bottom edge line as the corresponding distance d6; and record the horizontal and vertical distance between the rear axle center point ground coordinates and the parking space center line as the corresponding distance d7.

[0132] Here, the spacings d1, d2, d3, d4, d5, d6, and d7 in this embodiment of the invention are as follows: Figure 2 The diagram illustrates seven types of spacing in a parking space scenario according to Embodiment 1 of the present invention.

[0133] Steps 342253-4, based on the spacing d1, d2, d3, d4 and the width w1, w c Calculate the corresponding lateral deviation ratio p1; and based on the spacing d5, d6, length h1, h c Calculate the corresponding longitudinal deviation ratio p2; and calculate the corresponding center offset ratio p3 based on the spacing d7 and width w1.

[0134] in,

[0135] Here, the closer the lateral deviation ratio p1 is to zero, the smaller the lateral deviation; the closer the longitudinal deviation ratio p2 is to zero, the smaller the longitudinal deviation; and the closer the center offset ratio p3 is to zero, the smaller the centerline offset.

[0136] Step 342253-5: Based on the preset lateral deviation range, longitudinal deviation range, and center offset range, compare the lateral deviation ratio p1, longitudinal deviation ratio p2, and center offset ratio p3. If the lateral deviation ratio p1 does not meet the corresponding lateral deviation range, or the longitudinal deviation ratio p2 does not meet the corresponding longitudinal deviation range, or the center offset ratio p3 does not meet the corresponding center offset range, then the first timestamp recorded at the parking point is taken as a corresponding first abnormal timestamp, and a corresponding first abnormal type is set as parking pose abnormal. The first abnormal timestamp and the first abnormal type obtained this time form a corresponding evaluation data record and add it to the evaluation data queue.

[0137] Here, the lateral deviation range, longitudinal deviation range, and center offset range are three preset numerical ranges;

[0138] Step 34226: If the current parking location type is a platform, then based on the current positioning coordinates, current heading angle, and vehicle model parameters of the first vehicle, identify the ground projection coordinates of the center points of the front and rear right wheels and the center points of the front and rear right doors of the vehicle to obtain the corresponding ground coordinates of the right front wheel contact point, the right rear wheel contact point, the center point of the right front door, and the center point of the right rear door; and based on the ground coordinates of the right front wheel contact point, the right rear wheel contact point, the center point of the right front door, the center point of the right rear door, and the center point of the right rear door, identify whether the parking posture of the vehicle on the platform side is abnormal, and add evaluation records to the evaluation data queue when abnormal posture is identified;

[0139] Specifically, step 342261 involves identifying the ground projection coordinates of the center points of the front and rear right wheels and the center points of the front and rear right doors of the vehicle based on the current positioning coordinates, the current heading angle, and the vehicle model parameters of the first vehicle. This process yields the corresponding ground coordinates of the ground points of the front right wheel, the rear right wheel, the center point of the front right door, and the center point of the rear right door.

[0140] Step 342262, and based on the coordinates of the right front wheel ground contact point, the coordinates of the right rear wheel ground contact point, the ground coordinates of the center point of the right front door, the ground coordinates of the center point of the right rear door, and the target of the current parking position, identify whether the parking posture of the vehicle on the platform side is abnormal, and add evaluation records to the evaluation data queue when abnormal posture is identified;

[0141] Specifically, it includes:

[0142] Step 342262-1: Based on the coordinates of the upper left corner vertex and the lower left corner vertex of the platform outside the current parking location target, confirm the outer edge line of the current platform to obtain the corresponding outer edge line; and record the perpendicular line from the coordinates of the outer center point of the current parking location target's boarding area to the outer edge line of the platform as the corresponding boarding area center line; and record the perpendicular line from the coordinates of the outer center point of the current parking location target's alighting area to the outer edge line of the platform as the corresponding alighting area center line.

[0143] Step 342262-2: Record the horizontal and vertical distance between the coordinates of the right front wheel contact point and the first outer edge line as the corresponding distance d8; record the horizontal and vertical distance between the coordinates of the right rear wheel contact point and the first outer edge line as the corresponding distance d9; and record the horizontal and vertical distance between the coordinates of the center point of the right front door and the first outer edge line as the corresponding distance d. 10 The horizontal and vertical distance between the center point of the right rear door and the first outer edge line is recorded as the corresponding distance d. 11 The vertical distance between the center point of the right front door and the center line of the boarding area is recorded as the corresponding distance d. 12 The vertical distance between the center point of the right rear door and the center line of the drop-off area is recorded as the corresponding distance d. 13 ;

[0144] Here, the spacings d8, d9, and d in the embodiments of the present invention 10 d 11 d 12 d 13 like Figure 3 The diagram shows six types of spacing in a platform scenario according to Embodiment 1 of the present invention.

[0145] Step 342262-3, based on the preset platform stopping distance range, adjust the distances d8, d9, and d... 10 d 11 Perform a comparison; if the spacing d8, d9, d 10 d 11 If at least one of the intervals does not meet the platform stopping interval range, the first timestamp recorded at the parking point will be used as a corresponding first abnormal timestamp, and a corresponding first abnormal type will be set as parking posture abnormal. The first abnormal timestamp and the first abnormal type obtained this time will be combined to form a corresponding evaluation data record and added to the evaluation data queue.

[0146] Here, the platform stopping interval is a pre-set distance range;

[0147] Step 342262-4, adjust the spacing d based on the preset passenger pick-up and drop-off area offset range. 12 d 13 Perform a comparison; if the spacing d 12d 13 If at least one of the gaps does not meet the offset range of the passenger pick-up and drop-off area, then the first timestamp recorded at the parking point is taken as a corresponding first abnormal timestamp, and a corresponding first abnormal type is set as parking pose abnormal. The first abnormal timestamp and the first abnormal type obtained this time are combined to form a corresponding evaluation data record and added to the evaluation data queue.

[0148] Here, the passenger pick-up and drop-off area offset range is a preset distance range;

[0149] Step 35, and determine whether the parking is temporary to obtain the corresponding real-time judgment result;

[0150] The real-time judgment results include both temporary and non-temporary results;

[0151] Specifically, this includes: using the last vehicle data record in the first record sequence as the corresponding parking point record; using the first positioning coordinate of the parking point record as the corresponding current vehicle coordinate; recording each first sensing target in the first sensing target set of the parking point record that is a parking space or a platform as the corresponding fifth or sixth target; when the number of fifth targets is not zero, calculating the straight-line distance between the center point coordinates of the parking space of each fifth target and the current vehicle coordinate, and using the calculation result as a corresponding first distance; when the number of sixth targets is not zero, calculating the straight-line distance between the center point coordinates of the outer side of the boarding area of ​​each sixth target and the current vehicle coordinate, and using the calculation result as a corresponding first distance; using the fifth or sixth target corresponding to the shortest first distance as the corresponding current target; using the target type of the current target as the corresponding current target type; and identifying the current target type; if the current target type is a parking space, setting the corresponding real-time judgment result to non-temporary; if the current target type is a platform, setting the corresponding real-time judgment result to temporary;

[0152] Step 36: If the real-time judgment result is temporary, then add the current end time to the preset first and second durations respectively to obtain the two time points as the corresponding first time and second time.

[0153] Wherein, the first duration is a preset platform stop duration threshold, the second duration = the first duration × a, a is a preset delay ratio parameter, a>1;

[0154] Step 37, and when the current time reaches the second moment, extract all vehicle data records from the first moment to the second moment from the vehicle data queue to form the corresponding second record sequence;

[0155] Step 38, and perform a parking performance evaluation based on the second record sequence to obtain the corresponding evaluation data record and store it in the evaluation data queue;

[0156] Specifically, this includes: identifying whether all first vehicle speeds in the second record sequence are zero; if so, the first moment is taken as a corresponding first abnormal timestamp, and a corresponding first abnormal type is set as parking timeout abnormal. The first abnormal timestamp and the first abnormal type obtained this time are combined to form a corresponding evaluation data record and added to the evaluation data queue.

[0157] Step 4: At the end of the evaluation of the first vehicle, the parking performance of the vehicle is scored and calculated based on the evaluation data queue to obtain the corresponding first evaluation score.

[0158] Specifically, this includes: Step 41, statistically analyzing the total number of various anomaly types in the evaluation data queue to obtain the corresponding total number of parking posture anomalies, total number of reversing behavior anomalies, and total number of parking timeout anomalies; and recording the anomaly type corresponding to each non-zero anomaly total as a corresponding evaluation anomaly item.

[0159] Step 42: Based on each evaluation anomaly, query the preset first correspondence table, extract the first deduction value field of the first correspondence record that matches the first anomaly type field with each evaluation anomaly in the first correspondence table as the corresponding anomaly deduction value; and sum all the obtained anomaly deduction values ​​to calculate the corresponding total deduction value.

[0160] The first correspondence table is a correspondence table that reflects the relationship between anomaly types and anomaly deduction values; the first correspondence table includes three first correspondence records; each first correspondence record includes a first anomaly type field and a first deduction value field; the first anomaly type field includes abnormal parking posture, abnormal reversing behavior, and abnormal parking timeout; the first deduction value field is an integer score.

[0161] Here, the current step calculates the total deduction value by summing the deduction values ​​of all abnormal items. This calculation method can be adjusted according to actual needs. One adjusted calculation method is to calculate the weighted sum of the deduction values ​​of all abnormal items and use the result as the total deduction value. Another adjusted calculation method is to multiply the deduction value of each abnormal item by the corresponding total number of abnormal items to obtain the corresponding total score for the abnormal item, and then sum or calculate the weighted sum of all the total scores for abnormal items and use the result as the total deduction value.

[0162] Step 43, and calculate the corresponding first evaluation score based on the preset full score and total deductions: Full score - Total deductions. Here, the full score is a preset score, such as 10 points, 100 points, etc.

[0163] Figure 4This is a module structure diagram of a processing device for evaluating the parking performance of a vehicle according to Embodiment 2 of the present invention. This device can be a terminal device or server implementing the aforementioned method embodiment, or it can be a device that enables the aforementioned terminal device or server to implement the aforementioned method embodiment. For example, the device can be a device or chip system of the aforementioned terminal device or server. Figure 4 As shown, the processing device 200 for evaluating the parking performance of a vehicle provided in Embodiment 2 of the present invention includes: a data acquisition module 2001, a data storage module 2002, a parking stage identification module 2003, a real-time evaluation module 2004, and a scoring calculation module 2005.

[0164] The data storage module 2002 is connected to the data acquisition module 2001, the parking stage identification module 2003, the real-time evaluation module 2004, and the scoring calculation module 2005, respectively; the parking stage identification module 2003 is connected to the real-time evaluation module 2004.

[0165] The data acquisition module 2001 is used to connect with the vehicle system of the first vehicle 100 during the evaluation process of the first vehicle; and to collect real-time perceived target information, positioning information, motion information and path information output by the environmental perception module, navigation and positioning module, path planning module and driving control module of the vehicle system, and to generate corresponding vehicle data records based on the collected data and store them in the vehicle data queue.

[0166] The data storage module 2002 is used to store vehicle data queues and evaluation data queues.

[0167] The parking phase identification module 2003 is used to take the newly added vehicle data record as the corresponding current record when a new record is added to the vehicle data queue; and to identify whether the vehicle has entered the parking phase based on the current record to obtain the corresponding real-time identification result; the real-time identification result includes whether the vehicle has entered or not.

[0168] The real-time evaluation module 2004 records the current time as the start time when the latest real-time identification result indicates entry; it then tracks and monitors the end time of the vehicle's current parking session from this start time to obtain the corresponding end time; it extracts all vehicle data records from the vehicle data queue from the start time to the end time to form a corresponding first record sequence; it performs a parking performance evaluation based on the first record sequence to obtain corresponding evaluation data records, which are then stored in the evaluation data queue; and it determines whether the parking session is temporary, obtaining a corresponding real-time judgment result; if the real-time judgment result... If it is temporary, the two time points obtained by adding the current end time to the preset first and second durations are recorded as the corresponding first and second time points; when the current time reaches the second time point, all vehicle data records from the first time point to the second time point are extracted from the vehicle data queue to form the corresponding second record sequence; and a parking performance evaluation is performed based on the second record sequence to obtain the corresponding evaluation data record, which is stored in the evaluation data queue; the real-time judgment result includes temporary and non-temporary; the first duration is the preset platform stopping time threshold, the second duration = the first duration × a, where a is the preset delay ratio parameter, a>1.

[0169] The scoring calculation module 2005 is used to calculate the parking performance of the vehicle based on the evaluation data queue at the end of the evaluation of the first vehicle to obtain the corresponding first evaluation score.

[0170] The processing device for evaluating the parking performance of a vehicle provided in this embodiment of the invention can execute the method steps in the above method embodiment, and its implementation principle and technical effect are similar, so they will not be described again here.

[0171] It should be noted that the division of the various modules in the above device is merely a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, these modules can be implemented entirely in software via processing element calls; they can be fully implemented in hardware; or some modules can be implemented by processing element calls to software, while others are implemented in hardware. For example, the data acquisition module can be a separate processing element, or it can be integrated into a chip in the above device. Alternatively, it can be stored as program code in the memory of the above device, and called and executed by a processing element of the device. The implementation of other modules is similar. Moreover, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element described here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each of the above modules can be completed through integrated logic circuits in the hardware of the processor element or through software instructions.

[0172] For example, these modules can be one or more integrated circuits configured to implement the above methods, such as one or more Application Specific Integrated Circuits (ASICs), one or more Digital Signal Processors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs). As another example, when a module is implemented using processing element scheduler code, the processing element can be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. Furthermore, these modules can be integrated together as a System-on-a-Chip (SOC).

[0173] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. This computer program product includes one or more computer instructions. When these computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the foregoing method embodiments are generated. The computer described above can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The aforementioned computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the aforementioned computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, Bluetooth, microwave, etc.) means. The aforementioned computer-readable storage medium can be any available medium that a computer can access, or a data storage device such as a server or data center that integrates one or more available media. The aforementioned available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state disks (SSDs)).

[0174] Figure 5 This is a schematic diagram of an electronic device provided in Embodiment 3 of the present invention. This electronic device can be a terminal device or server implementing the methods of the aforementioned embodiments, or it can be a terminal device or server connected to the aforementioned terminal device or server implementing the methods of the aforementioned embodiments. Figure 5As shown, the electronic device may include: a processor 301 (e.g., CPU), a memory 302, and a transceiver 303; the transceiver 303 is coupled to the processor 301, and the processor 301 controls the transmission and reception operations of the transceiver 303. The memory 302 may store various instructions for performing various processing functions and implementing the processing steps described in the foregoing embodiments. Preferably, the electronic device involved in the embodiments of the present invention further includes: a power supply 304, a system bus 305, and a communication port 306. The system bus 305 is used to realize communication connections between components. The communication port 306 is used for communication between the electronic device and other peripherals.

[0175] exist Figure 5 The system bus 305 mentioned can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This system bus can be divided into address bus, data bus, control bus, etc. For ease of representation, it is represented by only one thick line in the figure, but this does not indicate that there is only one bus or one type of bus. The communication interface is used to enable communication between the database access device and other devices (e.g., clients, read-write libraries, and read-only libraries). Memory may include Random Access Memory (RAM) and may also include non-volatile memory, such as at least one disk storage device.

[0176] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), graphics processing units (GPUs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0177] It should be noted that the embodiments of the present invention also provide a computer-readable storage medium storing instructions that, when run on a computer, cause the computer to perform the methods and processes provided in the above embodiments.

[0178] This invention provides a processing method, apparatus, electronic device, and computer-readable storage medium for evaluating the parking performance of a vehicle. As described above, in the vehicle evaluation process, this invention collects real-time perception target information, positioning information, motion information, and path information output by the vehicle system and refreshes the vehicle data queue based on the collected data. When a new record is added to the vehicle data queue, the system identifies whether the vehicle has entered the parking phase based on the newly added record. Upon identification that the vehicle has entered the parking phase, the current time is recorded as the start time, and the end time of the parking phase is confirmed through tracking and monitoring. All vehicle data records from the start time to the end time are extracted from the vehicle data queue to form a first record sequence, and a real-time parking performance evaluation is performed based on this sequence. The system also identifies whether the parking is temporary. If it is temporary, the two time points after the end time are recorded as the first and second times. When the current time reaches the second time, all vehicle data records from the first time to the second time are extracted from the vehicle data queue to form a second record sequence, and a real-time parking performance evaluation is performed based on this sequence. Finally, at the end of the evaluation, the vehicle's parking performance is scored and a corresponding evaluation score is calculated based on the evaluation data queue. The embodiments of the present invention can perform real-time anomaly analysis during vehicle evaluation and output the evaluation score immediately at the end of the evaluation; the embodiments of the present invention not only improve the evaluation efficiency, but also improve the real-time performance of the evaluation.

[0179] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0180] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented in hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0181] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A processing method for evaluating the parking performance of a vehicle, characterized in that, The method includes: During the evaluation of the first vehicle, the system connects to the vehicle's onboard system and collects real-time perception target information, positioning information, motion information, and path information output by the onboard system's environmental perception module, navigation and positioning module, path planning module, and driving control module. Based on the collected data, the system generates corresponding vehicle data records and stores them in a preset vehicle data queue. When a new record is added to the vehicle data queue, the newly added vehicle data record is taken as the corresponding current record; and the vehicle is identified as having entered the parking stage based on the current record to obtain the corresponding real-time identification result; the real-time identification result includes whether the vehicle has entered or not. When the latest real-time identification result indicates entry, the current time is recorded as the start time of this parking session. From this start time, the end time of the vehicle's parking session is tracked and monitored to obtain the corresponding end time. All vehicle data records from the start time to the end time are extracted from the vehicle data queue to form a corresponding first record sequence. A parking performance evaluation is performed based on the first record sequence to obtain corresponding evaluation data records, which are then stored in a preset evaluation data queue. A real-time judgment result is obtained to determine whether the parking is temporary. If the real-time judgment result is temporary, the parking time is... The two time points obtained by adding the current end time to the preset first and second durations are recorded as the corresponding first time and second time. When the current time reaches the second time, all vehicle data records from the first time to the second time are extracted from the vehicle data queue to form a corresponding second record sequence. A parking performance evaluation is performed based on the second record sequence to obtain the corresponding evaluation data record, which is then stored in the evaluation data queue. The real-time judgment result includes temporary and non-temporary results. The first duration is a preset platform stop duration threshold, and the second duration = first duration × a, where a is a preset delay ratio parameter, and a > 1. At the end of the evaluation of the first vehicle, the parking performance of the vehicle is scored and calculated based on the evaluation data queue to obtain the corresponding first evaluation score.

2. The processing method for evaluating the parking performance of a vehicle according to claim 1, characterized in that, The vehicle data queue includes multiple vehicle data records; The vehicle data record includes a first timestamp, a first set of perceived targets, a first positioning coordinate, a first planned trajectory, a first vehicle speed, and a first heading angle; The first sensing target set is the set of sensing targets output by the environmental sensing module, and consists of one or more first sensing targets; the first sensing target includes a target identifier, a target type, and a set of target key point coordinates; the target type includes at least parking spaces and platforms; When the target type is a parking space, the corresponding target key point coordinate set includes the coordinates of the center point of the parking space, the coordinates of the top left corner vertex of the parking space, the coordinates of the top right corner vertex of the parking space, the coordinates of the bottom right corner vertex of the parking space, and the coordinates of the bottom left corner vertex of the parking space; when the target type is a platform, the corresponding target key point coordinate set includes the coordinates of the top left corner vertex of the outer side of the platform, the coordinates of the bottom left corner vertex of the outer side of the platform, the coordinates of the center point of the outer side of the passenger pick-up area, and the coordinates of the center point of the outer side of the passenger drop-off area. The first positioning coordinates are the coordinates of the rear axle center point of the vehicle output by the navigation positioning module; The first planned trajectory is the vehicle's planned path output by the path planning module, which is composed of multiple first trajectory points arranged in sequence; each first trajectory point includes the coordinates of the first point and the velocity of the first point; the velocity of the first point is greater than or equal to zero. The first vehicle speed and the first heading angle are real-time vehicle speed and heading angle information output by the driving control module; if the first vehicle speed is less than zero, it means that the vehicle is reversing at the corresponding time of the first timestamp. The evaluation data queue includes multiple evaluation data records; The evaluation data record includes a first abnormal timestamp and a first abnormal type; the first abnormal type includes abnormal parking posture, abnormal reversing behavior, and abnormal parking timeout.

3. The processing method for evaluating the parking performance of a vehicle according to claim 2, characterized in that, The step of identifying whether a vehicle has entered the parking phase based on the current record to obtain the corresponding real-time identification result specifically includes: Step 31: Take the currently recorded first perception target set and first planned trajectory as the corresponding current perception target set and current planned trajectory; and extract the first point coordinates and first point velocity of the last first trajectory point of the current planned trajectory as the corresponding target point coordinates and target point velocity; Step 32: Record each first sensing target in the current sensing target set whose target type is parking space as the corresponding first target; record each first sensing target in the current sensing target set whose target type is platform as the corresponding second target; and count the total number of the first and second targets to obtain the corresponding first total number and second total number. Step 33: Identify the target point velocity and the first and second totals; Step 34: If the target point speed is zero and the first total is greater than zero, then a corresponding first coordinate region is formed by the coordinates of the top left corner vertex, the top right corner vertex, the bottom right corner vertex, and the bottom left corner vertex of each first target parking space; if only one of the obtained first coordinate regions can cover the target point coordinates, then the corresponding real-time recognition result is set as "entered". Step 35: If the target point velocity is zero and the second total is greater than zero, then the straight line segment between the coordinates of the upper left corner vertex and the lower left corner vertex of the outer side of the platform for each of the second targets is taken as the corresponding first outer edge; and the vertical distance from the target point coordinates to each of the first outer edges is calculated to obtain the corresponding first edge spacing, and the shortest first edge spacing is recorded as the corresponding current shortest spacing; if the current shortest spacing is less than the preset vehicle-platform parking spacing threshold, then the corresponding real-time recognition result is set as entered; Step 36: If the target point velocity is not zero or the first and second totals are both zero, then the corresponding real-time identification result is set to "not entered".

4. The processing method for evaluating the parking performance of a vehicle according to claim 2, characterized in that, The process of tracking and monitoring the end time of the vehicle's current parking session to obtain the corresponding end time specifically includes: When a new record is added to the vehicle data queue, the newly added vehicle data record is taken as the corresponding current record; and it is identified whether the first vehicle speed of the current record is zero; if the first vehicle speed of the current record is zero, all vehicle data records in the vehicle data queue whose first timestamps are within a preset first recent duration are extracted to form a corresponding recent time period record sequence; and it is identified whether all the first vehicle speeds in the recent time period record sequence are zero; if all the first vehicle speeds in the recent time period record sequence are zero, the tracking and monitoring are stopped, and the first timestamp of the first vehicle data record with the first vehicle speed of zero in the recent time period record sequence is extracted as the corresponding end time of this operation.

5. The processing method for evaluating the parking performance of a vehicle according to claim 2, characterized in that, The step of performing a parking performance evaluation based on the first record sequence and storing the corresponding evaluation data record into a preset evaluation data queue specifically includes: Step 51: Record each vehicle data record in the first record sequence where the first vehicle speed is less than zero as the corresponding reversing point record; and count the total number of reversing point records to obtain the corresponding total number of reversing points; and when the total number of reversing points is greater than zero, perform an evaluation record addition operation on the evaluation data queue based on all the reversing point records. Step 52: Take the last vehicle data record in the first record sequence as the corresponding parking point record; and identify whether the parking posture of the vehicle is abnormal based on the parking point record, and add the evaluation record to the evaluation data queue when the abnormal posture is identified.

6. The processing method for evaluating the parking performance of a vehicle according to claim 5, characterized in that, The step of adding evaluation records to the evaluation data queue based on all the reversing point records specifically includes: The first timestamp recorded at each of the reversing points is used as a corresponding first abnormal timestamp; a corresponding first abnormal type is set as reversing behavior abnormal; and each of the first abnormal timestamps and its corresponding first abnormal type is combined to form a corresponding evaluation data record and stored in the evaluation data queue.

7. The processing method for evaluating the parking performance of a vehicle according to claim 5, characterized in that, The step of identifying whether the vehicle's parking posture is abnormal based on the parking point records and adding evaluation records to the evaluation data queue when an abnormal posture is identified specifically includes: Step 71: The first set of perceived targets, the first positioning coordinates, and the first heading angle recorded at the parking point are taken as the corresponding current set of perceived targets, current positioning coordinates, and current heading angle; and each first perceived target in the current set whose target type is parking space is recorded as the corresponding third target; and each first perceived target in the current set whose target type is platform is recorded as the corresponding fourth target; and the total number of the third and fourth targets is counted to obtain the corresponding third total number and fourth total number; and the corresponding first parking location type is initialized to parking space. The first parking location type includes parking spaces and platforms; Step 72: If the total number of the third targets is greater than zero, a corresponding second coordinate region is formed by the coordinates of the top left corner vertex, the top right corner vertex, the bottom right corner vertex, and the bottom left corner vertex of each third target; and when there is only one second coordinate region among all the obtained second coordinate regions that can cover the current positioning coordinates, the first parking location type is set to parking space; and the third target corresponding to this second coordinate region that can cover the current positioning coordinates is taken as the corresponding current parking location target. Step 73: If the total number of fourth targets is greater than zero, then the straight line segment between the coordinates of the upper left corner vertex and the lower left corner vertex of the outer side of each fourth target is taken as the corresponding second outer edge; and the vertical distance from the current positioning coordinate to each second outer edge is calculated to obtain the corresponding second edge spacing, and the shortest second edge spacing is recorded as the corresponding current shortest spacing; and when the current shortest spacing is less than the preset vehicle-platform parking spacing threshold, the first parking position type is set to platform; and the fourth target corresponding to the current shortest spacing is taken as the corresponding current parking position target. Step 74: Record the target type of the current parking location target as the corresponding current parking location type; and identify the current parking location type; Step 75: If the current parking location type is a parking space, then based on the current positioning coordinates, the current heading angle, and the vehicle model parameters of the first vehicle, identify the ground projection coordinates of the four wheel center points, the apex of the front of the vehicle, and the apex of the rear of the vehicle to obtain the corresponding left front wheel contact point coordinates, right front wheel contact point coordinates, right rear wheel contact point coordinates, left rear wheel contact point coordinates, the ground coordinates of the apex of the front of the vehicle, and the ground coordinates of the apex of the rear of the vehicle; and use the ground projection point coordinates corresponding to the current positioning coordinates as the corresponding ground coordinates of the rear axle center point; and based on the left front wheel contact point coordinates, the right front wheel contact point coordinates, the right rear wheel contact point coordinates, the left rear wheel contact point coordinates, the ground coordinates of the apex of the front of the vehicle, the ground coordinates of the apex of the rear of the vehicle, the ground coordinates of the rear axle center point, and the target of the current parking location, identify whether the parking posture of the vehicle in the parking space is abnormal, and add an evaluation record to the evaluation data queue when an abnormal posture is identified; The vehicle parameters include at least the vehicle width parameter, vehicle length parameter, front axle position parameter, rear axle position parameter, center axle position parameter, left front wheel position parameter, left rear wheel position parameter, right front wheel position parameter, right rear wheel position parameter, left front door position parameter, left rear door position parameter, right front door position parameter, and right rear door position parameter. Step 76: If the current parking location type is a platform, then based on the current positioning coordinates, the current heading angle, and the vehicle model parameters of the first vehicle, the ground projection coordinates of the center points of the front and rear right wheels and the center points of the front and rear right doors of the vehicle are identified to obtain the corresponding ground coordinates of the right front wheel contact point, the right rear wheel contact point, the center point of the right front door, and the center point of the right rear door; and based on the ground coordinates of the right front wheel contact point, the right rear wheel contact point, the center point of the right front door, the center point of the right rear door, and the target of the current parking location, whether the parking posture of the vehicle on the platform side is abnormal is identified, and when an abnormal posture is identified, an evaluation record is added to the evaluation data queue.

8. The processing method for evaluating the parking performance of a vehicle according to claim 7, characterized in that, The process involves identifying whether the vehicle's parking posture in the parking space is abnormal based on the coordinates of the left front wheel contact point, the right front wheel contact point, the right rear wheel contact point, the left rear wheel contact point, the ground coordinates of the apex of the vehicle's front, the apex of the vehicle's rear, the ground coordinates of the rear axle center point, and the target parking position. When an abnormal posture is identified, an evaluation record is added to the evaluation data queue. Specifically, this includes: Step 81: Based on the coordinates of the top left, top right, bottom right, and bottom left corners of the parking space, and the center point of the current parking location, confirm the four edges and center line of the current parking space to obtain the corresponding left edge, top edge, right edge, bottom edge, and center line; and calculate the width w1 and length h1 of the current parking space based on the coordinates of the top left, top right, bottom right, and bottom left corners of the parking space; and record the vehicle width and length parameters of the vehicle model parameters as the corresponding width w. c and length h c ; Step 82: Record the horizontal and vertical distance between the coordinates of the left front wheel contact point and the left side edge as the corresponding distance d1; record the horizontal and vertical distance between the coordinates of the right front wheel contact point and the right side edge as the corresponding distance d2; record the horizontal and vertical distance between the coordinates of the right rear wheel contact point and the right side edge as the corresponding distance d3; record the horizontal and vertical distance between the coordinates of the left rear wheel contact point and the left side edge as the corresponding distance d4; record the vertical distance between the ground coordinates of the vehicle apex and the top edge as the corresponding distance d5; record the vertical distance between the ground coordinates of the rear apex and the bottom edge as the corresponding distance d6; and record the horizontal and vertical distance between the ground coordinates of the rear axle center point and the parking space center line as the corresponding distance d7. Step 83, based on the spacings d1, d2, d3, d4 and the widths w1, w c Calculate the corresponding lateral deviation ratio p1; and based on the distances d5 and d6, the lengths h1 and h2... c Calculate the corresponding longitudinal deviation ratio p2; and calculate the corresponding center offset ratio p3 based on the spacing d7 and the width w1; in, The closer the lateral deviation ratio p1 is to zero, the smaller the lateral deviation; the closer the longitudinal deviation ratio p2 is to zero, the smaller the longitudinal deviation; and the closer the center offset ratio p3 is to zero, the smaller the centerline offset. Step 84: Compare the lateral deviation ratio p1, the longitudinal deviation ratio p2, and the center offset ratio p3 based on preset lateral deviation range, longitudinal deviation range, and center offset range; if the lateral deviation ratio p1 does not meet the corresponding lateral deviation range, or the longitudinal deviation ratio p2 does not meet the corresponding longitudinal deviation range, or the center offset ratio p3 does not meet the corresponding center offset range, then the first timestamp recorded at the parking point is taken as a corresponding first abnormal timestamp, and a corresponding first abnormal type is set as parking pose abnormality. The first abnormal timestamp and the first abnormal type obtained this time are combined to form a corresponding evaluation data record and added to the evaluation data queue.

9. The processing method for evaluating the parking performance of a vehicle according to claim 7, characterized in that, The process of identifying whether the vehicle's parking posture on the platform side is abnormal based on the coordinates of the right front wheel contact point, the right rear wheel contact point, the ground coordinates of the center point of the right front door, the ground coordinates of the center point of the right rear door, and the target of the current parking position, and adding evaluation records to the evaluation data queue when an abnormal posture is identified, specifically includes: Step 91: Based on the coordinates of the upper left corner vertex and the lower left corner vertex of the outer side of the platform of the current parking location target, confirm the outer edge line of the current platform to obtain the corresponding outer edge line of the platform; and record the perpendicular line from the coordinates of the outer center point of the passenger pick-up area of ​​the current parking location target to the outer edge line of the platform as the corresponding center line of the passenger pick-up area; and record the perpendicular line from the coordinates of the outer center point of the passenger drop-off area of ​​the current parking location target to the outer edge line of the platform as the corresponding center line of the passenger drop-off area. Step 92: Record the horizontal and vertical distance between the coordinates of the right front wheel contact point and the first outer edge line as the corresponding distance d8; record the horizontal and vertical distance between the coordinates of the right rear wheel contact point and the first outer edge line as the corresponding distance d9; and record the horizontal and vertical distance between the coordinates of the center point of the right front door and the first outer edge line as the corresponding distance d. 10 The horizontal and vertical distance between the ground coordinates of the center point of the right rear door and the first outer edge line is recorded as the corresponding distance d. 11 The vertical distance between the ground coordinates of the center point of the right front door and the center line of the boarding area is recorded as the corresponding distance d. 12 The vertical distance between the ground coordinates of the center point of the right rear door and the center line of the drop-off area is recorded as the corresponding distance d. 13 ; Step 93, based on the preset platform stopping distance range, adjust the distances d8, d9, and d... 10 d 11 Perform a comparison; if the stated spacings d8, d9, d 10 d 11 If at least one of the intervals does not meet the platform stopping interval range, then the first timestamp recorded at the parking point is used as a corresponding first abnormal timestamp, and a corresponding first abnormal type is set as parking posture abnormal. The first abnormal timestamp and the first abnormal type obtained this time are combined to form a corresponding evaluation data record and added to the evaluation data queue. Step 94, adjust the spacing d based on the preset passenger pick-up and drop-off area offset range. 12 d 13 Perform a comparison; if the distance d 12 d 13 If at least one of the spacings does not meet the offset range of the passenger pick-up and drop-off area, then the first timestamp recorded at the parking point is used as a corresponding first abnormal timestamp, and a corresponding first abnormal type is set as parking posture abnormal. The first abnormal timestamp and the first abnormal type obtained this time are combined to form a corresponding evaluation data record and added to the evaluation data queue.

10. The processing method for evaluating the parking performance of a vehicle according to claim 2, characterized in that, The process of determining whether the parking is temporary and obtaining the corresponding real-time judgment result specifically includes: The last vehicle data record in the first recording sequence is taken as the corresponding parking point record; the first positioning coordinate of the parking point record is taken as the corresponding current vehicle coordinate; and each of the first sensing targets in the first sensing target set of the parking point record whose target type is parking space or platform is recorded as the corresponding fifth target or sixth target; when the number of the fifth targets is not zero, the straight-line distance between the center point coordinate of the parking space of each fifth target and the current vehicle coordinate is calculated and the calculation result is taken as a corresponding first distance; when the number of the sixth targets is not zero, the straight-line distance between the center point coordinate of the outer side of the passenger pick-up area of ​​each sixth target and the current vehicle coordinate is calculated and the calculation result is taken as a corresponding first distance; and the fifth target or sixth target corresponding to the shortest first distance is taken as the corresponding current target; and the target type of the current target is taken as the corresponding current target type; and the current target type is identified; if the current target type is parking space, the corresponding real-time judgment result is set to non-temporary; if the current target type is platform, the corresponding real-time judgment result is set to temporary.

11. The processing method for evaluating the parking performance of a vehicle according to claim 2, characterized in that, The step of performing a parking performance evaluation based on the second record sequence and storing the corresponding evaluation data record in the evaluation data queue specifically includes: The system identifies whether all the first vehicle speeds in the second record sequence are zero; if so, the first moment is used as a corresponding first abnormal timestamp, and a corresponding first abnormal type is set as parking timeout abnormal. The first abnormal timestamp and the first abnormal type obtained this time are combined to form a corresponding evaluation data record and added to the evaluation data queue.

12. The processing method for evaluating the parking performance of a vehicle according to claim 2, characterized in that, The step of calculating the corresponding first evaluation score by scoring the vehicle's parking performance based on the evaluation data queue specifically includes: The total number of each type of anomaly in the evaluation data queue is statistically analyzed to obtain the corresponding total number of parking posture anomalies, total number of reversing behavior anomalies, and total number of parking timeout anomalies; and the anomaly type corresponding to each non-zero anomaly total is recorded as a corresponding evaluation anomaly item. Based on each of the aforementioned evaluation anomalies, a preset first correspondence table is queried. The first deduction value field of the first correspondence record in the first correspondence table that matches the first anomaly type field with each of the aforementioned evaluation anomalies is extracted as the corresponding anomaly deduction value. The total deduction value is calculated by summing all the obtained anomaly deduction values. The first correspondence table is a correspondence table that reflects the correspondence between anomaly types and anomaly deduction values. The first correspondence table includes three first correspondence records. Each first correspondence record includes a first anomaly type field and a first deduction value field. The first anomaly type field includes abnormal parking posture, abnormal reversing behavior, and abnormal parking timeout. The first deduction value field is an integer score. The first evaluation score is calculated based on the preset full score and the total deduction score: full score - total deduction score.

13. An apparatus for performing the processing method for evaluating the parking performance of a vehicle as described in any one of claims 1-12, characterized in that, The device includes: a data acquisition module, a data storage module, a parking phase identification module, a real-time evaluation module, and a scoring calculation module; The data storage module is connected to the data acquisition module, the parking stage identification module, the real-time evaluation module, and the scoring calculation module, respectively; the parking stage identification module is connected to the real-time evaluation module. The data acquisition module is used to connect with the vehicle system of the first vehicle during the evaluation process of the first vehicle; and to collect real-time perceived target information, positioning information, motion information and path information output by the environmental perception module, navigation and positioning module, path planning module and driving control module of the vehicle system, and to generate corresponding vehicle data records based on the collected data and store them in the vehicle data queue. The data storage module is used to store the vehicle data queue and the evaluation data queue; The parking phase identification module is used to take each newly added vehicle data record as the corresponding current record when a new record is added to the vehicle data queue; and to identify whether the vehicle has entered the parking phase based on the current record to obtain the corresponding real-time identification result; the real-time identification result includes whether the vehicle has entered or not. The real-time evaluation module is used to record the current time as the start time when the latest real-time identification result is "entered"; and to track and monitor the end time of the vehicle's current parking from the start time to obtain the corresponding end time; to extract all vehicle data records from the vehicle data queue from the start time to the end time to form a corresponding first record sequence; to perform a parking performance evaluation based on the first record sequence to obtain corresponding evaluation data records and store them in the evaluation data queue; and to determine whether the parking is temporary to obtain a corresponding real-time judgment result; if the real-time judgment result is temporary... Then, the two time points obtained by adding the current end time to the preset first and second durations are recorded as the corresponding first time and second time; when the current time reaches the second time, all vehicle data records from the first time to the second time in the vehicle data queue are extracted to form the corresponding second record sequence; and a parking performance evaluation is performed based on the second record sequence to obtain the corresponding evaluation data record, which is stored in the evaluation data queue; the real-time judgment result includes temporary and non-temporary; the first duration is a preset platform stopping duration threshold, the second duration = the first duration × a, where a is a preset delay ratio parameter, and a>1; The scoring calculation module is used to calculate the parking performance of the vehicle based on the evaluation data queue at the end of the evaluation of the first vehicle to obtain the corresponding first evaluation score.

14. An electronic device, characterized in that, include: Memory, processor, and transceiver; The processor is configured to be coupled to the memory, read and execute instructions in the memory to implement the method according to any one of claims 1-12; The transceiver is coupled to the processor, and the processor controls the transceiver to send and receive messages.

15. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a computer, cause the computer to perform the method according to any one of claims 1-12.

Images