Vehicle reversing trajectory correction method, device, equipment, medium and product

Abstract

Embodiments of the present disclosure disclose a vehicle reversing trajectory correction method, device, equipment, medium and product, comprising: acquiring a real-time distance sequence and a real-time position coordinate sequence of a vehicle when performing a tracking reversing on a target section by using an ultrasonic radar, the real-time distance sequence including a real-time distance between the vehicle and each target obstacle; calculating a difference value between the real-time distance sequence and a historical distance sequence to construct a distance matrix; determining a target path by using a preset algorithm according to the distance matrix; determining a real-time position coordinate and a historical position coordinate corresponding to each path point in the target path respectively based on the real-time position coordinate sequence and the historical position coordinate sequence according to the target path; and correcting a current reversing trajectory based on a deviation of the real-time position coordinate and the historical position coordinate corresponding to each path point to determine a real-time reversing trajectory, thereby realizing real-time correction of a reversing error.

Description

Technical Field

[0001] This disclosure relates to the field of vehicle control technology, and in particular to a method, apparatus, device, medium, and product for correcting a vehicle's reversing trajectory. Background Technology

[0002] The reverse tracking function is a typical feature of vehicle driver assistance systems. It is often used in narrow passages. When the driver drives the vehicle forward at a low speed, the reverse tracking function continuously records the forward driving path. When the driver decides not to continue forward and wants to reverse back, the reverse tracking function controls the vehicle's speed and turning angle to return along the recorded driving path. However, due to wheel slippage, tire lag, and other reasons, the actual return path usually has an error compared to the original driving path, and the error generally increases with the increase of the reversing distance.

[0003] Current trajectory calculation and correction technologies for reversing tracking functions mainly rely on the following two types of schemes, but both have significant drawbacks: 1) Single dead-point calculation scheme: This scheme calculates the historical trajectory solely using wheel speed sensors (to calculate travel distance) and steering wheel angle sensors (to calculate steering angle), directly reproducing the trajectory during playback. When wheels slip (e.g., due to wet ground or slope) or sensors drift (e.g., wheel speed pulse error), the cumulative error increases dramatically with the reversing distance. When the reversing distance reaches 50 meters, the lateral and longitudinal deviations typically exceed [a certain threshold]. 50cm is insufficient to meet parking accuracy requirements. 2) Multi-sensor fusion correction scheme: Some technologies introduce cameras to collect visual feature points (such as parking lines and ground markings), which are then fused with wheel speed and turning angle data to correct the trajectory. In this scheme, visual features are greatly affected by the environment (recognition fails in backlight, low light, and when the ground is dirty), resulting in poor correction robustness; at the same time, additional high-resolution cameras and image processing chips are required, increasing hardware costs and computing power consumption, making it difficult to adapt to low-end and mid-range vehicles; moreover, the correction values ​​are mostly fixed thresholds (e.g., each correction...). (3cm), without considering the impact of reversing distance on the error. When reversing a short distance, a fixed correction value is prone to causing track jitter, while when reversing a long distance, the correction is insufficient. Summary of the Invention

[0004] This disclosure provides a method, apparatus, device, medium, and product for correcting vehicle reversing trajectory, enabling real-time correction of reversing errors.

[0005] Firstly, a method for correcting a vehicle's reversing trajectory is provided, including: The ultrasonic radar is used to acquire the real-time distance sequence and real-time position coordinate sequence of the vehicle when it is reversing along the target road segment. The real-time distance sequence includes the real-time distance between the vehicle and each target obstacle, and the real-time position coordinate sequence includes the real-time position coordinates of the vehicle when each of the real-time distances is acquired. The difference between the real-time distance sequence and the historical distance sequence is calculated to construct a distance matrix; the historical distance sequence includes the historical distance between the vehicle and each target obstacle when the vehicle is moving at a preset speed on the target road segment; Based on the distance matrix, a target path is determined using a preset algorithm. The target path contains at least one path point, and each path point is used to represent a matching relationship between a real-time distance and a historical distance. Based on the target path, the real-time position coordinates and historical position coordinates corresponding to each path point in the target path are determined based on the real-time position coordinate sequence and the historical position coordinate sequence; the historical position coordinate sequence includes the vehicle's historical position coordinates corresponding to each historical distance. The current reversing trajectory is corrected based on the deviation between the real-time and historical position coordinates of each path point to determine the real-time reversing trajectory.

[0006] Secondly, a device for correcting a vehicle's reversing trajectory is provided, comprising: The real-time information acquisition module is used to acquire the real-time distance sequence and real-time position coordinate sequence of the vehicle when it is reversing along the target road segment using ultrasonic radar. The real-time distance sequence includes the real-time distance between the vehicle and each target obstacle, and the real-time position coordinate sequence includes the real-time position coordinates of the vehicle when each of the real-time distances is acquired. A distance matrix construction module is used to calculate the difference between the real-time distance sequence and the historical distance sequence to construct a distance matrix; the historical distance sequence includes the historical distance between the vehicle and each target obstacle when the vehicle is moving at a preset speed on the target road segment; The target path determination module is used to determine the target path based on the distance matrix using a preset algorithm. The target path contains at least one path point, and each path point is used to represent a matching relationship between a real-time distance and a historical distance. The location coordinate determination module is used to determine the real-time location coordinates and historical location coordinates corresponding to each path point in the target path based on the real-time location coordinate sequence and the historical location coordinate sequence; the historical location coordinate sequence includes the vehicle's historical location coordinates corresponding to each historical distance. The trajectory determination module is used to correct the current reversing trajectory based on the deviation between the real-time position coordinates and the historical position coordinates corresponding to each path point, so as to determine the real-time reversing trajectory.

[0007] Thirdly, an electronic device is provided, comprising: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the vehicle reversing trajectory correction method as described in the first aspect above.

[0008] Fourthly, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method for correcting the vehicle reversing trajectory as described in the first aspect above.

[0009] Fifthly, a computer program product is provided, the computer program product comprising a computer program that, when executed by a processor, implements the vehicle reversing trajectory correction method as described in the first aspect above.

[0010] This disclosure provides a method, apparatus, device, medium, and product for correcting a vehicle's reversing trajectory. The method includes: acquiring a real-time distance sequence and a real-time position coordinate sequence of a vehicle reversing along a target road segment using ultrasonic radar. The real-time distance sequence includes the real-time distance between the vehicle and each target obstacle, and the real-time position coordinate sequence includes the vehicle's real-time position coordinates corresponding to each of the real-time distances; calculating the difference between the real-time distance sequence and a historical distance sequence to construct a distance matrix; the historical distance sequence includes the historical distance between the vehicle and each target obstacle when the vehicle is moving at a preset speed along the target road segment; determining a target path based on the distance matrix using a preset algorithm, the target path containing at least one path point, each path point representing a matching relationship between a real-time distance and a historical distance; determining the real-time position coordinates and historical position coordinates corresponding to each path point in the target path based on the real-time position coordinate sequence and the historical position coordinate sequence; the historical position coordinate sequence includes the vehicle's historical position coordinates corresponding to each of the historical distances; and correcting the current reversing trajectory based on the deviation between the real-time position coordinates and the historical position coordinates corresponding to each path point to determine the real-time reversing trajectory. This technical solution uses ultrasonic radar to collect real-time data on the distance to obstacles and the vehicle's position during reversing, forming a real-time distance and position sequence. This sequence is then compared with historical distance and position sequences when the vehicle is moving forward at a preset speed to construct a distance matrix. An optimization algorithm is used to find the optimal matching path point from the matrix. The deviation between the real-time coordinates and historical coordinates of each matching point is calculated, and the current reversing trajectory is dynamically corrected accordingly. This achieves real-time correction of reversing errors and enables real-time, precise reversing control.

[0011] It should be understood that the description in this section is not intended to identify key or important features of the embodiments of this disclosure, nor is it intended to limit the scope of the embodiments of this disclosure. Other features of the embodiments of this disclosure will become readily apparent from the following description. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a flowchart of a method for correcting a vehicle reversing trajectory provided in Embodiment 1 of this disclosure; Figure 2 This is a schematic diagram of the structure of a vehicle reversing trajectory correction device provided in Embodiment 2 of this disclosure; Figure 3 This is a schematic diagram of the structure of an electronic device provided in Embodiment 3 of this disclosure. Detailed Implementation

[0014] To enable those skilled in the art to better understand the solutions of the embodiments of this disclosure, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the protection scope of the embodiments of this disclosure.

[0015] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0016] Example 1 Figure 1 This is a flowchart of a method for correcting a vehicle reversing trajectory according to Embodiment 1 of this disclosure. This embodiment is applicable to situations where the correction of a vehicle reversing trajectory is required. This method can be executed by a vehicle reversing trajectory correction device, which can be implemented in hardware and / or software. The vehicle reversing trajectory correction device can be configured in an electronic device, including but not limited to computers, terminals, and servers, which are devices with data processing capabilities. Figure 1 As shown, the method includes: S110. Use ultrasonic radar to acquire the real-time distance sequence and real-time position coordinate sequence of the vehicle when it is reversing along the target road segment. The real-time distance sequence includes the real-time distance between the vehicle and each target obstacle, and the real-time position coordinate sequence includes the real-time position coordinates of the vehicle when each real-time distance is acquired.

[0017] In this embodiment, the target road segment can be a scenario during reversing, such as a narrow passage where the vehicle is turning. Ultrasonic radar is a sensor that measures the distance between the vehicle and obstacles by emitting and receiving ultrasonic signals; it is commonly used for reversing assistance and low-speed obstacle avoidance. In this embodiment, the ultrasonic radar can be a standard side-mounted ultrasonic radar (typically four) that is standard on the vehicle.

[0018] Specifically, lateral ultrasonic radar can be triggered at fixed time intervals to detect distances and obtain real-time distance sequences and real-time position coordinate sequences when the vehicle is reversing along the target road segment. The real-time distance sequence includes the real-time distance between the vehicle and each target obstacle, and the real-time position coordinate sequence includes the vehicle's real-time position coordinates at each distance. The target obstacles can be static obstacles around the vehicle, such as curbs, walls, or adjacent vehicles.

[0019] For example, ultrasonic radar can be used to acquire the real-time distance and position of a vehicle reversing along a target road segment, thereby obtaining a real-time distance sequence and a real-time position coordinate sequence. The real-time distance sequence can be represented as T, then: If the real-time position coordinate sequence can be represented as Q, then: Where m can represent the number of times the vehicle has reversed from the start of reversing to the current moment, i.e., the number of dynamic anchor points.

[0020] S120. Calculate the difference between the real-time distance sequence and the historical distance sequence to construct a distance matrix; the historical distance sequence includes the historical distance between the vehicle and each target obstacle when the vehicle is moving at a preset speed on the target road segment.

[0021] In this embodiment, after obtaining the real-time distance sequence, the difference between each real-time distance in the real-time distance sequence and each historical distance in the historical distance sequence can be calculated, and a distance matrix can be constructed based on each difference. The historical distance sequence includes the historical distances between the vehicle and each target obstacle when the vehicle is traveling at a preset speed on the target road segment.

[0022] For example, the historical distance sequence can be represented as S, then: Where n can represent the number of anchor points (the number of target obstacles) recorded by the vehicle during its journey on the target road segment. This can represent the historical distance between a vehicle and the nth target obstacle when the vehicle is traveling at a preset speed on a target road segment. It can calculate the "distance difference" between each pair of elements in the historical distance sequence S and the real-time distance sequence T, thus constructing... The distance matrix D, where the matrix elements can be represented as: It can represent real-time distance. Distance from history The absolute deviation is the distance between the two points; the smaller the deviation, the higher the matching degree. For example, the distance matrix D can be represented as: ; S130. Based on the distance matrix, determine the target path using a preset algorithm. The target path contains at least one path point, and each path point is used to represent a matching relationship between a real-time distance and a historical distance.

[0023] In this embodiment, the preset algorithm can be a pre-defined algorithm, such as dynamic programming. The target path can be a regularized path, which can be an ordered path. The regularized path can be obtained by searching the distance matrix using a dynamic programming algorithm. The dynamic programming algorithm finds a target path that minimizes the cumulative distance on the target path by recursively calculating the cumulative distance of each path point. The target path can contain at least one path point, where each path point represents a matching relationship between a real-time distance and a historical distance.

[0024] For example, a regularized path can be represented as (k can be the path length, satisfying) ),in It can represent the first in the real-time distance sequence T. The element and the historical distance sequence S in the nth element For element matching, the normalized path needs to satisfy the following constraints: boundary constraints, monotonicity constraints, and continuity constraints. The boundary constraints can be expressed as: (Starting point matching) (Endpoint matching); Monotonicity constraints can be expressed as: and Continuity constraints can be expressed as: and .

[0025] Specifically, the target path with the minimum cumulative distance can be determined using dynamic programming algorithms. The formula for calculating the cumulative distance can be expressed as: ,in , minimum The corresponding path is the target path (optimal regularized path).

[0026] S140. Based on the target path, determine the real-time position coordinates and historical position coordinates corresponding to each path point in the target path based on the real-time position coordinate sequence and the historical position coordinate sequence; the historical position coordinate sequence includes the vehicle's historical position coordinates corresponding to each historical distance.

[0027] Specifically, after determining the target path, based on the matching relationship between a real-time distance and a historical distance for each path point in the target path, the real-time location coordinates corresponding to the real-time distance in the real-time location coordinate sequence can be determined as the real-time location coordinates of the path point, and the historical location coordinates corresponding to the historical distance in the historical location coordinate sequence can be determined as the historical location coordinates of the vehicle corresponding to the path point. For example, after determining the target path, the real-time distance sequence T along the target path can be... Matching with historical distance sequence S Bind and extract the corresponding real-time location coordinates. with historical location coordinates .

[0028] S150. Based on the deviation between the real-time position coordinates and historical position coordinates corresponding to each path point, the current reversing trajectory is corrected to determine the real-time reversing trajectory.

[0029] Specifically, after obtaining the real-time and historical position coordinates of each path point in the target path, the deviation can be calculated based on the real-time and historical position coordinates of each path point. The current reversing trajectory of the vehicle can be corrected in real time based on the calculated deviation, thereby determining the corrected real-time reversing trajectory.

[0030] It should be noted that during each reversing process, the real-time distance and real-time position coordinates can be continuously updated, the distance matrix can be recalculated, and the target path can be searched again through dynamic programming algorithm to ensure that the vehicle always plans and corrects its path based on the latest detection data during the reversing process.

[0031] This embodiment provides a method for correcting a vehicle's reversing trajectory, comprising: acquiring a real-time distance sequence and a real-time position coordinate sequence of the vehicle while reversing along a target road segment using ultrasonic radar; the real-time distance sequence including the real-time distance between the vehicle and each target obstacle, and the real-time position coordinate sequence including the vehicle's real-time position coordinates corresponding to each of the real-time distances; calculating the difference between each real-time distance and each historical distance in the historical distance sequence to construct a distance matrix; the historical distance sequence including the historical distance between the vehicle and each target obstacle when the vehicle is moving at a preset speed along the target road segment; determining a target path using a preset algorithm based on the distance matrix; the target path containing at least one path point, each path point representing a matching relationship between a real-time distance and a historical distance; determining the real-time position coordinates and historical position coordinates corresponding to each path point in the target path based on the real-time position coordinate sequence and the historical position coordinate sequence; the historical position coordinate sequence including the vehicle's historical position coordinates corresponding to each of the historical distances; and correcting the current reversing trajectory based on the deviation between the real-time position coordinates and the historical position coordinates corresponding to each path point to determine the real-time reversing trajectory. This technical solution relies solely on the vehicle's existing standard ultrasonic radar to improve the accuracy of line-following reversing. It eliminates the need for additional cameras or lidar sensors, and avoids the need to import existing camera data for matching and positioning. Therefore, it requires less computing power during function execution. Furthermore, the maximum correction value dynamically increases with the reversing distance, avoiding the problem of "overcorrection" at the initial stage of reversing (when the reversing distance is short), thus achieving real-time and precise line-following reversing control.

[0032] As an optional implementation of this embodiment, the vehicle reversing trajectory correction method provided in this embodiment further includes, before determining the real-time distance sequence and real-time position coordinate sequence corresponding to the vehicle reversing along the target road segment using ultrasonic radar: 1) The ultrasonic radar is used to acquire an initial data set corresponding to the vehicle moving at a preset speed on the target road segment. The initial data set contains multiple data pairs, and each data pair includes a historical distance and the historical position coordinates of the vehicle when the historical distance is acquired.

[0033] Specifically, as the vehicle moves along the target road segment, ultrasonic radar can be used to acquire an initial data set corresponding to the vehicle's movement at a preset speed. The preset speed can be a speed that meets preset conditions, such as the vehicle's speed being lower than a pre-set threshold. The preset threshold can be... The initial dataset may contain multiple data pairs, each of which may include a historical distance and the historical position coordinates of the vehicle when the historical distance was obtained. The historical distance may be the distance to target obstacles around the vehicle.

[0034] For example, lateral ultrasonic radar can be triggered at fixed time intervals to detect the distance between the vehicle and surrounding static obstacles (such as curbs, walls, adjacent vehicles, etc.) in real time, filter out stable distance values ​​(historical distances), and exclude dynamic obstacles, such as pedestrians and moving vehicles. This allows the acquisition of the historical distance between the vehicle and each target obstacle, as well as the vehicle's position coordinates at that historical distance (historical position coordinates).

[0035] It should be noted that the initial dataset may also include detection timestamps, ultrasonic radar identifiers, and other information.

[0036] 2) Sort multiple data pairs according to the numerical value of each historical distance to obtain the sorted initial data set.

[0037] Specifically, after obtaining the initial data set, multiple data pairs can be sorted according to the magnitude of each historical distance to obtain the sorted initial data set.

[0038] 3) Based on the sorted initial data set, generate the historical distance sequence and the historical location coordinate sequence.

[0039] Specifically, after obtaining the sorted data set, the historical distance sequence and the historical position coordinate sequence can be generated based on the sorted initial data set, wherein each historical distance in the historical distance sequence corresponds to each historical position coordinate in the historical position coordinate sequence.

[0040] For example, the historical distance sequence can be represented as S, then: ,in, This can represent the historical distance between a vehicle and the nth target obstacle when the vehicle is traveling at a preset speed on the target road segment. The historical position coordinate sequence can be represented as P, then: , It can represent the historical position coordinates of a vehicle when obtaining the historical distance between the vehicle and the nth target obstacle.

[0041] As an optional implementation of this embodiment, the step of correcting the current reversing trajectory based on the deviation between the real-time position coordinates and historical position coordinates corresponding to each path point to determine the real-time reversing trajectory further includes: 1) Determine the first deviation based on the real-time and historical location coordinates of each path point.

[0042] Specifically, after obtaining the real-time and historical location coordinates of each path point, the difference between the real-time and historical location coordinates can be used as the first deviation. The first deviation can include the lateral deviation and the longitudinal deviation. The lateral deviation can be the difference between the lateral value in the real-time location coordinates and the lateral value in the historical location coordinates, and the longitudinal deviation can be the difference between the longitudinal value in the real-time location coordinates and the longitudinal value in the historical location coordinates.

[0043] For example, real-time location coordinates can be represented as Historical location coordinates can be represented as The first deviation may include the lateral deviation. and longitudinal deviation Then we have: lateral deviation Longitudinal deviation .

[0044] 2) Determine the second deviation based on the first deviation corresponding to each path point.

[0045] Specifically, after obtaining the first deviation for each path point, the first deviations for all path points can be summed and averaged to determine the second deviation. The second deviation may include the lateral deviation. and longitudinal deviation Then we have: , , where k can represent the number of path points.

[0046] 3) Determine the target correction value based on the second deviation and the vehicle's real-time reversing distance.

[0047] In this embodiment, the real-time reversing distance can be the distance between the vehicle's starting position and its current position. For example, if the vehicle's starting position is A and its current parking position is B, the real-time reversing distance can be the distance between position A and position B.

[0048] As described above, a target correction value can be determined based on the second deviation and the real-time reversing distance. The target correction value may include a lateral target correction value and a longitudinal target correction value. For example, the second deviation may include a lateral deviation. and longitudinal deviation The target correction value can be expressed as the lateral target correction value. and longitudinal target correction value Then we have: Where d can be the real-time reversing distance of the vehicle, and k can be a set proportional coefficient, which can be determined through actual vehicle calibration, such as k=0.02, with units of 1.5m. .

[0049] 4) Correct the current reversing trajectory based on the target correction value to determine the real-time reversing trajectory.

[0050] Specifically, after obtaining the target correction value, the current reversing trajectory can be corrected based on the target correction value to determine the real-time reversing trajectory.

[0051] For example, the target correction value may include a lateral target correction value and a longitudinal target correction value. The lateral correction value can be used to adjust the vehicle's lateral position deviation and can be converted into a steering wheel angle adjustment amount. For example, if the lateral target correction value is positive, it means the vehicle can be adjusted to the right; if the lateral target correction value is negative, it means the vehicle can be adjusted to the left. The steering wheel angle conversion formula can be expressed as follows: Then we have: ,in, It can be the distance between the two wheels of a vehicle. A positive value means the vehicle's steering wheel turns to the right; a negative value means the vehicle's steering wheel turns to the left.

[0052] As described above, the longitudinal target correction value can be used to adjust the longitudinal position deviation of the vehicle. The longitudinal target correction value can be converted into a forward or backward adjustment amount for the vehicle. For example, if the longitudinal target correction value is positive, it indicates that the vehicle needs to be adjusted forward; if it is negative, it indicates that the vehicle needs to be adjusted backward.

[0053] As an optional implementation of this embodiment, the step of correcting the current reversing trajectory according to the target correction value to determine the real-time reversing trajectory further includes: Determine whether the target correction value is greater than a preset correction threshold; if not, correct the current reversing trajectory based on the target correction value to determine the real-time reversing trajectory.

[0054] In this embodiment, the preset correction threshold can be a pre-set correction threshold. The preset correction threshold may include a horizontal preset correction threshold and a vertical preset correction threshold. The horizontal preset correction threshold and the vertical preset correction threshold can be the same or different. For example, the horizontal preset correction threshold can be... 5cm, the preset vertical correction threshold can be 3cm. After obtaining the target correction value, it can be determined whether the target correction value is greater than the preset correction threshold. If the target correction value is not greater than the preset correction threshold, the current reversing trajectory can be corrected according to the determined target correction threshold, and thus the corrected real-time reversing trajectory can be obtained.

[0055] As an optional implementation of this embodiment, the vehicle reversing trajectory correction method provided in this embodiment further includes: if so, correcting the current reversing trajectory according to the preset correction threshold to determine the real-time reversing trajectory.

[0056] As we know, if the target correction value is greater than the preset correction threshold, the current reversing trajectory can be corrected according to the preset correction threshold to determine the real-time reversing trajectory.

[0057] For example, the preset correction threshold can be expressed as and For example, the horizontal preset correction threshold can be 5cm, the preset vertical correction threshold can be 3cm; if the lateral target correction value in the target correction value and longitudinal target correction value Not exceeding the maximum threshold The vehicle will then directly adjust its reversing trajectory in real time by adjusting the steering wheel angle according to the target correction value; if and If the preset correction threshold is exceeded, the vehicle will be corrected using the preset correction threshold.

[0058] As an optional implementation of this embodiment, the preset algorithm is a dynamic time warping algorithm; the step of determining the target path using the preset algorithm based on the distance matrix includes: 1) Based on the distance matrix, a cumulative distance matrix is ​​constructed using a dynamic time warping algorithm. The value of each current position in the cumulative distance matrix is ​​determined based on the difference between the corresponding positions in the distance matrix and the sum of the target value. The target value is the value of the current position in the cumulative distance matrix that satisfies a preset condition among the values ​​of the adjacent upper, adjacent left and adjacent upper left positions.

[0059] Specifically, after obtaining the distance matrix, a cumulative distance matrix can be constructed using a dynamic time warping algorithm. The value of each current position in the cumulative distance matrix is ​​determined based on the difference between the corresponding positions in the distance matrix and the target value. The target value is the value of the current position among the values ​​of its adjacent above, left, and upper left positions in the cumulative distance matrix that satisfies a preset condition. The preset condition can be selecting the minimum value among the values ​​of the current position's adjacent above, left, and upper left positions in the cumulative distance matrix. By adding the minimum cumulative distance value among adjacent positions to the current distance difference, it can be guaranteed that the final path is the target path with the minimum cumulative distance. Each element in the cumulative distance matrix represents the minimum cumulative distance from the start point of the sequence to the current position, which is obtained by adding the current position's distance value to the minimum cumulative distance among the adjacent positions above, left, or upper left. It should be noted that the starting position (upper left corner) of the cumulative distance matrix can be determined by definition, such as: the starting position of the cumulative distance matrix can be equal to the value of the distance matrix at the top left corner. The value of the position.

[0060] For example, each difference in the distance matrix can be treated as a local cost. The distance matrix can be traversed from left to right and from top to bottom using the dynamic time warping algorithm: when it reaches any cell, its own difference is added to the cumulative cost of its three neighbors above, to the left and to the upper left that meet the preset conditions (usually the minimum), and written into the same position in the cumulative distance matrix. Thus, a "minimum cumulative cost map from the starting point to each cell" is obtained, which is the cumulative distance matrix.

[0061] 2) Based on the cumulative distance matrix, the target path is determined by a preset path planning rule.

[0062] Specifically, the preset path planning rules can be pre-defined. After obtaining the cumulative distance matrix, one can start backtracking from the end point of the cumulative distance matrix (the lower right corner of the cumulative distance matrix), selecting the direction with the smallest cumulative distance among the adjacent positions above, to the left, and to the upper left, and sequentially determining each point on the path until returning to the starting point (the upper left corner of the cumulative distance matrix). Connecting these points together yields the target path. Each element on this path represents the matching relationship between an element in the real-time distance sequence and an element in the static distance sequence.

[0063] Example 2 Figure 2 This is a schematic diagram of the structure of a vehicle reversing trajectory correction device provided in Embodiment 2 of this disclosure; as shown Figure 2 As shown, the device includes: a real-time information acquisition module 210, a distance matrix construction module 220, a target path determination module 230, a position coordinate determination module 240, and a trajectory determination module 250.

[0064] The real-time information acquisition module 210 is used to acquire the real-time distance sequence and real-time position coordinate sequence of the vehicle when it is reversing along the target road section using ultrasonic radar. The real-time distance sequence includes the real-time distance between the vehicle and each target obstacle, and the real-time position coordinate sequence includes the real-time position coordinates of the vehicle when each of the real-time distances is acquired. The distance matrix construction module 220 is used to calculate the difference between the real-time distance sequence and the historical distance sequence to construct a distance matrix; the historical distance sequence includes the historical distance between the vehicle and each target obstacle when the vehicle is moving at a preset speed on the target road segment; The target path determination module 230 is used to determine the target path according to the distance matrix using a preset algorithm. The target path includes at least one path point, and each path point is used to represent a matching relationship between a real-time distance and a historical distance. The location coordinate determination module 240 is used to determine the real-time location coordinates and historical location coordinates corresponding to each path point in the target path based on the real-time location coordinate sequence and the historical location coordinate sequence; the historical location coordinate sequence includes the vehicle's historical location coordinates corresponding to each historical distance. The trajectory determination module 250 is used to correct the current reversing trajectory based on the deviation between the real-time position coordinates and the historical position coordinates corresponding to each path point, so as to determine the real-time reversing trajectory.

[0065] Embodiment 2 of this disclosure provides a vehicle reversing trajectory correction device, which realizes real-time correction of reversing errors.

[0066] Furthermore, the device also includes: The acquisition module is used to acquire an initial data set corresponding to the vehicle moving at a preset speed on the target road segment using the ultrasonic radar. The initial data set contains multiple data pairs, and each data pair includes a historical distance and the historical position coordinates of the vehicle when the historical distance is acquired. The sorting module is used to sort multiple data pairs according to the numerical value of each historical distance to obtain the sorted initial data set; The sequence generation module is used to generate the historical distance sequence and the historical location coordinate sequence based on the sorted initial data set.

[0067] Furthermore, the trajectory determination module 250 also includes: The first deviation determination unit is used to determine the first deviation based on the real-time position coordinates and historical position coordinates of each path point. The second deviation determination unit is used to determine the second deviation based on the first deviation corresponding to each path point. The target correction value determination unit is used to determine the target correction value based on the second deviation and the real-time reversing distance of the vehicle. The trajectory correction unit is used to correct the current reversing trajectory according to the target correction value in order to determine the real-time reversing trajectory.

[0068] Furthermore, the trajectory correction unit is also used for: Determine whether the target correction value is greater than a preset correction threshold; If not, the current reversing trajectory is corrected according to the target correction value to determine the real-time reversing trajectory.

[0069] Furthermore, the device also includes: The correction module is used to correct the current reversing trajectory according to the preset correction threshold if the condition is met, so as to determine the real-time reversing trajectory.

[0070] Furthermore, the preset algorithm is a dynamic time warping algorithm; the target path determination module 230 is also used for: Based on the distance matrix, a cumulative distance matrix is ​​constructed using a dynamic time warping algorithm. The value of each current position in the cumulative distance matrix is ​​determined based on the difference between the corresponding positions in the distance matrix and the sum of the target value. The target value is the value of the current position in the cumulative distance matrix that satisfies a preset condition among the values ​​of the adjacent upper, adjacent left, and adjacent upper left positions. Based on the cumulative distance matrix, the target path is determined using preset path planning rules.

[0071] The vehicle reversing trajectory correction device provided in this disclosure can execute the vehicle reversing trajectory correction method provided in any embodiment of this disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

[0072] Example 3 Figure 3 A schematic diagram of the structure of an electronic device 10 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the embodiments of the present disclosure described and / or claimed herein.

[0073] like Figure 3As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0074] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0075] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microprocessor, etc. Processor 11 performs the various methods and processes described above, such as methods for correcting a vehicle's reversing trajectory.

[0076] In some embodiments, the method for correcting the vehicle reversing trajectory may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the vehicle reversing trajectory correction method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the vehicle reversing trajectory correction method by any other suitable means (e.g., by means of firmware).

[0077] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0078] Computer programs for implementing the methods of embodiments of this disclosure may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0079] In the context of embodiments of this disclosure, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0080] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0081] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0082] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0083] It should be understood that the various forms of processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the embodiments of this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of the embodiments of this disclosure can be achieved, and this document does not impose any limitations.

[0084] The specific embodiments described above do not constitute a limitation on the scope of protection of the embodiments disclosed herein. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the embodiments disclosed herein should be included within the scope of protection of the embodiments disclosed herein.

[0085] This disclosure also provides a computer program product, including a computer program and / or instructions, which, when executed by a processor, implements the vehicle reversing trajectory correction method provided in any embodiment of this application.

[0086] In implementing a computer program product, computer program code for performing the operations of the embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0087] Note that the above are merely preferred embodiments and the technical principles applied in this disclosure. Those skilled in the art will understand that this disclosure is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the protection scope of this disclosure. Therefore, although the embodiments of this disclosure have been described in detail above, this disclosure is not limited to the above embodiments. More other equivalent embodiments may be included without departing from the concept of this disclosure, and the scope of this disclosure is determined by the scope of the appended claims.

Claims

1. A method for correcting a vehicle's reversing trajectory, characterized in that, include: The ultrasonic radar is used to acquire the real-time distance sequence and real-time position coordinate sequence of the vehicle when it is reversing along the target road segment. The real-time distance sequence includes the real-time distance between the vehicle and each target obstacle, and the real-time position coordinate sequence includes the real-time position coordinates of the vehicle when each of the real-time distances is acquired. The difference between the real-time distance sequence and the historical distance sequence is calculated to construct a distance matrix; the historical distance sequence includes the historical distance between the vehicle and each target obstacle when the vehicle is moving at a preset speed on the target road segment; Based on the distance matrix, a target path is determined using a preset algorithm. The target path contains at least one path point, and each path point is used to represent a matching relationship between a real-time distance and a historical distance. Based on the target path, the real-time position coordinates and historical position coordinates corresponding to each path point in the target path are determined based on the real-time position coordinate sequence and the historical position coordinate sequence; the historical position coordinate sequence includes the vehicle's historical position coordinates corresponding to each historical distance. The current reversing trajectory is corrected based on the deviation between the real-time position coordinates and the historical position coordinates corresponding to each path point in order to determine the real-time reversing trajectory. The process of correcting the current reversing trajectory based on the deviation between the real-time and historical position coordinates of each path point to determine the real-time reversing trajectory includes: The first deviation is determined based on the real-time and historical location coordinates of each path point. The second deviation is determined based on the first deviation for each path point; The target correction value is determined based on the second deviation and the vehicle's real-time reversing distance; The current reversing trajectory is corrected based on the target correction value to determine the real-time reversing trajectory.

2. The method according to claim 1, characterized in that, Before acquiring the real-time distance sequence and real-time position coordinate sequence of the vehicle during reversing along the target road segment using ultrasonic radar, the method further includes: The ultrasonic radar is used to acquire an initial data set corresponding to the vehicle moving at a preset speed on the target road segment. The initial data set contains multiple data pairs, and each data pair includes a historical distance and the historical position coordinates of the vehicle when the historical distance is acquired. Sort multiple data pairs according to the magnitude of each historical distance to obtain the sorted initial data set; Based on the sorted initial data set, the historical distance sequence and the historical location coordinate sequence are generated.

3. The method according to claim 1, characterized in that, The step of correcting the current reversing trajectory based on the target correction value to determine the real-time reversing trajectory includes: Determine whether the target correction value is greater than a preset correction threshold; If not, the current reversing trajectory is corrected according to the target correction value to determine the real-time reversing trajectory.

4. The method according to claim 3, characterized in that, The method further includes: If so, the current reversing trajectory is corrected according to the preset correction threshold to determine the real-time reversing trajectory.

5. The method according to claim 1, characterized in that, The preset algorithm is a dynamic time warping algorithm; The step of determining the target path using a preset algorithm based on the distance matrix includes: Based on the distance matrix, a cumulative distance matrix is ​​constructed using a dynamic time warping algorithm. The value of each current position in the cumulative distance matrix is ​​determined based on the difference between the corresponding positions in the distance matrix and the sum of the target value. The target value is the value of the current position in the cumulative distance matrix that satisfies a preset condition among the values ​​of the adjacent upper, adjacent left, and adjacent upper left positions. Based on the cumulative distance matrix, the target path is determined using preset path planning rules.

6. A device for correcting the reversing trajectory of a vehicle, characterized in that, include: The real-time information acquisition module is used to acquire the real-time distance sequence and real-time position coordinate sequence of the vehicle when it is reversing along the target road segment using ultrasonic radar. The real-time distance sequence includes the real-time distance between the vehicle and each target obstacle, and the real-time position coordinate sequence includes the real-time position coordinates of the vehicle when each of the real-time distances is acquired. A distance matrix construction module is used to calculate the difference between the real-time distance sequence and the historical distance sequence to construct a distance matrix; the historical distance sequence includes the historical distance between the vehicle and each target obstacle when the vehicle is moving at a preset speed on the target road segment; The target path determination module is used to determine the target path based on the distance matrix using a preset algorithm. The target path contains at least one path point, and each path point is used to represent a matching relationship between a real-time distance and a historical distance. The location coordinate determination module is used to determine the real-time location coordinates and historical location coordinates corresponding to each path point in the target path based on the real-time location coordinate sequence and the historical location coordinate sequence; the historical location coordinate sequence includes the vehicle's historical location coordinates corresponding to each historical distance. The trajectory determination module is used to correct the current reversing trajectory based on the deviation between the real-time position coordinates and the historical position coordinates corresponding to each path point, so as to determine the real-time reversing trajectory. The trajectory determination module also includes: The first deviation determination unit is used to determine the first deviation based on the real-time position coordinates and historical position coordinates of each path point. The second deviation determination unit is used to determine the second deviation based on the first deviation corresponding to each path point. The target correction value determination unit is used to determine the target correction value based on the second deviation and the real-time reversing distance of the vehicle. The trajectory correction unit is used to correct the current reversing trajectory according to the target correction value in order to determine the real-time reversing trajectory.

7. An electronic device, characterized in that, include: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the vehicle reversing trajectory correction method as described in any one of claims 1-5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the vehicle reversing trajectory correction method as described in any one of claims 1-5.

9. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the vehicle reversing trajectory correction method as described in any one of claims 1-5.

Images