Method and device for determining position of object in surroundings of vehicle

Abstract

To provide a method and a device for determining a position of an object in the surroundings of a vehicle.SOLUTION: The method may include: extracting ultrasound samples that fall within a sliding window; clustering the ultrasound samples to obtain at least one ultrasound sample cluster, where each ultrasound sample cluster corresponds to an object in the surroundings; determining cutting information and corner point prediction information of the at least one ultrasound sample cluster, where the cutting information is used to indicate whether each ultrasound sample cluster is cut in a horizontal direction by the sliding window, and the corner point prediction information is used to indicate predicted positions of two corner points of each ultrasound sample cluster along the horizontal direction; and determining object position information within the sliding window based on the cutting information and the corner point prediction information of the at least one ultrasound sample cluster.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to the field of vehicles, and more particularly to a method, a control system, a vehicle, a machine-readable storage medium and a computer program product for determining the position of an object in a vehicle's surroundings. [Background technology]

[0002] Parking space detection is a key component in enabling vehicle-assisted parking. To achieve parking space detection, sensor signals are typically utilized to identify objects around the vehicle. If the positions of these objects can be accurately detected, the location of available parking spaces can also be accurately determined, thereby enhancing the performance of vehicle-assisted parking. Summary of the Invention [Problem to be solved by the invention]

[0003] Ultrasonic sensors (USS) as a cost-effective method for object detection have gained significant attention and research in the automotive field in recent years. However, effectively implementing object detection using ultrasonic signals in vehicle parking scenarios remains a challenge that still needs to be addressed. [Means for solving the problem]

[0004] The following summary is intended only to introduce some concepts in a simplified form that are further described below in the detailed description. The following summary is not intended to highlight key features or essential features of the claimed subject matter, nor is it intended to limit the scope of the claimed subject matter.

[0005] In one aspect, an embodiment of the present disclosure provides a method for determining a position of an object in the vicinity of a vehicle, the method including: extracting ultrasound samples that fall within a sliding window, the ultrasound samples being obtained based on ultrasound data collected in the vicinity of the vehicle; clustering the ultrasound samples to obtain at least one ultrasound sample cluster, each ultrasound sample cluster corresponding to an object in the vicinity; determining cutting information and corner point prediction information of the at least one ultrasound sample cluster, the cutting information being used to indicate whether each ultrasound sample cluster is cut horizontally by the sliding window, and the corner point prediction information being used to indicate predicted positions of two corner points of each ultrasound sample cluster along the horizontal direction; and determining object position information within the sliding window based on the cutting information and corner point prediction information of the at least one ultrasound sample cluster.

[0006] In another aspect, an embodiment of the present disclosure provides a control system for a vehicle, comprising: at least one processor; and a memory coupled to the at least one processor, the memory storing executable instructions, the executable instructions, when executed by the at least one processor, enabling the at least one processor to perform the method described above.

[0007] In another aspect, an embodiment of the present disclosure provides a vehicle including at least one ultrasonic sensor configured to transmit and receive ultrasonic signals and the control system described above.

[0008] In another aspect, embodiments of the present disclosure provide a machine-readable storage medium storing executable instructions, the executable instructions, when executed by a processor, for performing the above-described method.

[0009] In another aspect, an embodiment of the present disclosure provides a computer program product including a computer program, the computer program being for performing the above-described method when executed by a processor.

[0010] The foregoing and other objects, features, and advantages of the embodiments of the present disclosure will become more apparent through the detailed description of the embodiments, taken in conjunction with the accompanying drawings, in which like reference symbols generally refer to like elements. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 is a schematic diagram of an exemplary vehicle according to some embodiments of the present disclosure. [Figure 2] FIG. 1 is a schematic diagram of an example control system in a vehicle, according to some embodiments of the present disclosure. [Figure 3] FIG. 1 is a schematic diagram of an example of ultrasound sampling using a sliding window. [Figure 4] FIG. 1 is a schematic block diagram of an architecture for determining the position of objects in a vehicle's surroundings, according to some embodiments of the present disclosure. [Figure 5] 1 is a schematic flowchart of a method for determining the position of an object in a vehicle's surroundings, according to some embodiments of the present disclosure. [Figure 6] FIG. 1 is a schematic block diagram of a control system for a vehicle according to some embodiments of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0012] The subject matter described herein will now be discussed with reference to various embodiments. Of course, the discussion of these embodiments does not limit the scope of protection, applicability, or embodiments described in the claims, but is provided to assist those skilled in the art in better understanding and realization of the subject matter described herein. Changes may be made to the function and arrangement of the elements discussed without departing from the scope of protection of the claims. Various processes or assemblies may be omitted, substituted, or added in the various embodiments, as appropriate.

[0013] As used herein, the term "comprising" and variations thereof are open-ended terms that may mean "including, but not limited to." The term "based on" may indicate "based at least in part on." The terms "one embodiment," "an embodiment," etc. may indicate "at least one embodiment." The terms "first," "second," etc. may refer to different objects or may refer to the same object.

[0014] Ultrasonic sensors have attracted significant attention and research in the automotive field due to the advantages of low cost, fast response, and easy integration. However, effectively utilizing ultrasonic sensors for object detection in the automotive field remains one of the current challenges. To address this issue, embodiments of the present disclosure provide a technical solution for object location detection based on ultrasonic data. A detailed description is provided below with reference to specific embodiments.

[0015] 1 is a schematic diagram of an exemplary vehicle according to some embodiments of the present disclosure. It should be understood that the following examples are provided only to enhance the understanding of the present disclosure and are not intended to impose any limitations on the scope of the present disclosure.

[0016] In the embodiment of FIG. 1 , at least one ultrasonic sensor 110 (represented simply as a black dot in FIG. 1 ) may be mounted on the vehicle 100. For example, as shown in FIG. 1 , the ultrasonic sensors 110 may be mounted on the front, rear, left, and right sides of the vehicle 100, i.e., corresponding to the front, rear, left, and right sides of the vehicle 100, respectively. FIG. 1 shows 16 ultrasonic sensors. However, the number and mounting locations of the ultrasonic sensors 110 are not limited to those shown in FIG. 1 . In various implementations, the vehicle 100 may be equipped with either more or fewer ultrasonic sensors, and the mounting locations of the ultrasonic sensors may vary as well.

[0017] The ultrasonic sensors 110 may transmit ultrasonic signals around the vehicle 100. For example, two ultrasonic sensors 110 located on the right front side of the vehicle 100 may transmit ultrasonic signals 120. The ultrasonic signals 120 are described below as an example. During transmission, the ultrasonic signals 120 may encounter various objects, such as obstacles (e.g., other vehicles, ground rock, trees, rails, fences, etc.), objects related to the vehicle's driving operations (e.g., curves, etc.), pedestrians, etc. When encountering an object, the ultrasonic signals 120 may be reflected. After the ultrasonic signals 120 are reflected, the ultrasonic sensors 110 may receive a reflected signal (commonly referred to as an echo signal).

[0018] Various ultrasonic data may be obtained based on the transmitted ultrasonic signals and the received echo signals. These operations may be implemented in various ways. For example, in some implementations, the vehicle 100 may include an ultrasonic sensor module. The ultrasonic sensor module may include an ultrasonic sensor 110 and a processing unit. The ultrasonic sensor 110 may include a transmitter for transmitting ultrasonic signals and a receiver for receiving echo signals. The processing unit may obtain various ultrasonic data based on the transmitted ultrasonic signals and the received echo signals. In addition, the processing unit may also control the transmission and reception of signals by each ultrasonic sensor.

[0019] For example, in FIG. 1 , the two ultrasonic sensors 110 located on the right front side of the vehicle 100 may constitute an ultrasonic sensor module 105 including two ultrasonic sensors for transmitting and receiving ultrasonic signals and a processing unit (not explicitly shown in FIG. 1 ). The processing unit may obtain various ultrasonic data based on the ultrasonic signals transmitted and the echo signals received by the two ultrasonic sensors. Similarly, the two ultrasonic sensors 100 located on the right rear side of the vehicle 110, the two ultrasonic sensors 110 located on the left front side, the two ultrasonic sensors 110 located on the left rear side, the four ultrasonic sensors 110 located on the front side, and the four ultrasonic sensors 110 located on the rear side may all constitute ultrasonic sensor modules having corresponding processing units.

[0020] 1, the four ultrasonic sensors 110 located on the right side of the vehicle 100 and corresponding processing units may constitute an ultrasonic sensor module, and the processing unit may obtain various ultrasonic data based on the ultrasonic signals transmitted by the four sensors and the echo signals received by the four sensors. Similarly, the four ultrasonic sensors 110 located on the left side of the vehicle 100, the four ultrasonic sensors 110 located in the front, and the four ultrasonic sensors 110 located on the right side may all constitute an ultrasonic sensor module with a corresponding processing unit.

[0021] As another example, all the ultrasonic sensors 110 shown in FIG. 1 may constitute an ultrasonic sensor module having a corresponding processing unit, and the processing unit may obtain various ultrasonic data based on the ultrasonic signals transmitted and the echo signals received by all the ultrasonic sensors.

[0022] Of course, an ultrasonic sensor module may include one or more ultrasonic sensors. Although the above example assumes that the ultrasonic sensor module includes multiple ultrasonic sensors, in different implementations, the ultrasonic sensor module may include one ultrasonic sensor. This is not a limitation in this specification. In addition, although ultrasonic sensors and ultrasonic sensor modules are described separately above depending on the context, an ultrasonic sensor may narrowly refer to a sensing unit for transmitting ultrasonic signals and receiving echo signals, or may broadly refer to an ultrasonic sensor module. Those skilled in the art can distinguish the meaning of an ultrasonic sensor in a specific context.

[0023] As described above, the processing unit may obtain various ultrasound data based on the ultrasound signals transmitted and the echo signals received by the ultrasound sensor 110. The ultrasound data may include various associated data.

[0024] In some embodiments, the ultrasonic data may include echo data. The echo data may include information related to the echo signal. For example, the echo data may include an echo timestamp, an echo amplitude, an echo significance, an echo distance, an echo coordinate (e.g., two coordinates), a sensor coordinate (e.g., two coordinates), etc. of the echo signal. In some embodiments, the echo data may be obtained using a centerline method. For example, while the vehicle 100 is moving along the direction 140, the ultrasonic sensor 110 located on the right front side of the vehicle 100 may transmit an ultrasonic signal and receive an echo signal. In the centerline method, a reflection point on a detected object is assumed to lie on the centerline 150 of the ultrasonic arc. Based on this, the processing unit may detect the reflection point of the corresponding ultrasonic signal and use it as the position of the echo signal. This position may be represented, for example, by acoustic coordinates.

[0025] In some embodiments, the ultrasonic data may include intersection data. The intersection data may include information about intersections between different ultrasonic signals. For example, the intersection data may include intersection coordinates (e.g., which may include two coordinates) of the intersections, intersection distances, intersection adjacent distances, intersection adjacent coordinates (e.g., which may include two coordinates), sensor coordinates, etc. For example, while the vehicle 100 is moving along the direction 140, an ultrasonic sensor 110 located on the right front side of the vehicle 100 may transmit an ultrasonic signal and receive an echo signal. The two sensors 110 may transmit two ultrasonic signals 120 and receive corresponding echo signals. According to the known positional relationship of the two ultrasonic sensors 110, the transmission times of the two ultrasonic signals 120, the reception times of the corresponding echo signals, and other information, the processing unit may calculate an intersection 160 of the ultrasonic arcs of the two ultrasonic signals 120, and the intersection 160 may represent a reflection point on a detected object. Accordingly, the intersection data may include information about the intersection 160. In some embodiments, the intersection is not limited to being the intersection of two ultrasonic arcs of ultrasonic signals transmitted by two ultrasonic sensors. For example, the intersection may also be the intersection of two ultrasonic arcs of ultrasonic signals transmitted by the same ultrasonic sensor at different times. Furthermore, the intersection data may be calculated based on the echo data. For example, corresponding intersection data may be obtained based on the ultrasonic arcs of any two echo data within a certain range.

[0026] In some embodiments, the ultrasound data may include the echo data and / or intersection data described above. Of course, the ultrasound data may optionally include other data related to the ultrasound signal, such as data related to the ultrasound signal obtained according to methods known in the art or possible future methods.

[0027] In some embodiments, the processing unit of the ultrasonic sensor module may provide the acquired ultrasonic data to a control unit 130 of the vehicle 100. For example, the control unit 130 may be an electronic control unit (ECU) of the vehicle. In some embodiments, some or all of the operations performed by the processing unit of the ultrasonic sensor module may also be performed by the control unit 130. For example, the control unit 130 may derive echo data and / or intersection data based on the ultrasonic signals transmitted by the ultrasonic sensor 110 and the received echo signals. In some embodiments, the vehicle 100 may also include other processing units for performing such operations.

[0028] In some embodiments, the sensors, processing unit, and control unit may be included in a vehicle control system. The vehicle control system may perform various controls for the vehicle. For ease of understanding, Figure 2 is a schematic diagram of an example control system in a vehicle, according to some embodiments of the present disclosure.

[0029] In the embodiment of Fig. 2, the same reference symbols are used for the same components as those in Fig. 1. Furthermore, it should be understood that Fig. 2 only shows some components related to the technical solution of the present disclosure. In actual implementation, the vehicle control system may also include various other components that are not limited by the present disclosure.

[0030] In the embodiment of FIG. 2, vehicle control system 200 may include ultrasonic sensor modules 105-1 through 105-N. Ultrasonic sensor modules 105-1 through 105-N each include one or more ultrasonic sensors 110 and corresponding processing units 115-1 through 115-N. As discussed above in conjunction with FIG. 1, in some embodiments, a vehicle may include only one ultrasonic sensor module. For example, an ultrasonic sensor module may include multiple ultrasonic sensors and processing units mounted on vehicle 100; in different implementations, a vehicle may include one or more ultrasonic sensor modules, each including one or more ultrasonic sensors and corresponding processing units.

[0031] The control system 200 may further include a control unit 130. The control unit 130 may control the operation of any one of the ultrasonic sensor modules 105-1 to 105-N. For example, the control unit 130 may control the ultrasonic sensor 110 in any one of the ultrasonic sensor modules 105-1 to 105-N to transmit ultrasonic signals and receive echo signals. The control unit 130 may also receive ultrasonic data from any one of the ultrasonic sensor modules 105-1 to 105-N and perform further operations or vehicle control based on the ultrasonic data. As described above, some or all of the operations performed by the processing units in the ultrasonic sensor modules 105-1 to 105-N may also be performed by the control unit 130 or another processing unit.

[0032] The control system 200 may further include a human-machine interface 180. The control unit 130 may output information that may be understood by a user (e.g., a driver) via the human-machine interface 180 and may also receive information input by a user from the human-machine interface. In some embodiments, a user may input a selection regarding entering the assisted parking mode via the human-machine interface 180. After receiving user input to enter the assisted parking mode, the control unit 130 may control the vehicle to operate in the assisted parking mode, for example, to automatically find a parking space and automatically park the vehicle. In some embodiments, the control unit 130 may automatically control the vehicle to enter the assisted parking mode or the automatic parking mode without user input. Regardless of the method for entering the assisted parking mode, in the assisted parking mode, the control unit 130 may detect objects around the vehicle by processing ultrasound data, such as determining object information such as the object's location, type, and height. Based on the object information, the control unit 130 may perform various operations related to parking the vehicle, such as detecting available parking spaces for the vehicle, planning a parking path for the vehicle based on the detected parking spaces, and the like.

[0033] In some implementations, to detect objects around the vehicle, the vehicle may need to drive through the objects, and then use the obtained ultrasound data to determine the location of the objects and other relevant information. In such implementations, driving through the objects may take a certain amount of time, and the amount of ultrasound data to be processed may be relatively large, which may cause significant delays, which significantly affect the performance of the vehicle's assisted parking and also affect the user experience.

[0034] In the technical solution of the present disclosure, the sliding window may be used in combination with clustering and prediction techniques to detect the positions of objects around the vehicle. For example, a sliding window may be set, and ultrasound samples falling within the sliding window may be processed using clustering and prediction techniques to obtain object position information within the sliding window. Compared to starting to process ultrasound data after the vehicle has passed the entire object, the number of ultrasound samples within the sliding window is significantly smaller. This enables faster determination of object position information within the sliding window, and by employing clustering and prediction techniques, the accuracy and reliability of the object position information are enhanced. Furthermore, the positions of objects around the vehicle can be determined efficiently and accurately. As a result, the assisted parking performance of the vehicle and the user experience can be significantly improved.

[0035] FIG. 3 is a schematic diagram of one embodiment of ultrasound sampling using a sliding window.

[0036] As described above, the ultrasonic data may be obtained based on ultrasonic signals and / or echo signals. For example, the ultrasonic data may be obtained based on ultrasonic signals and / or echo signals of one or more ultrasonic sensors. The ultrasonic data may include echo data and / or intersection data. The ultrasonic samples may be obtained based on the ultrasonic data. The ultrasonic samples may be characterized in various ways. For example, the ultrasonic samples may be characterized in the time domain, e.g., each ultrasonic sample may be characterized by the distance between the object and the vehicle at a particular time. In other examples, the ultrasonic samples may be characterized in the spatial domain, e.g., each ultrasonic sample may be characterized by the distance between the object and the vehicle at a particular location.

[0037] The ultrasound samples may include echo samples and / or intersection samples, where each echo sample may include information such as a corresponding echo timestamp, echo amplitude, echo intensity, echo distance, echo coordinates, sensor coordinates, etc., and each intersection sample may include information such as a corresponding intersection coordinates, intersection distance, intersection adjacent distance, intersection adjacent coordinates, sensor coordinates, etc.

[0038] The horizontal size of the sliding window may be defined appropriately based on the characterization method of the ultrasound samples. If the ultrasound samples are characterized in the time domain, the horizontal size of the sliding window may be defined by a duration. That is, ultrasound samples within a certain duration may be extracted through the sliding window. If the ultrasound samples are characterized in the spatial domain, the horizontal size of the sliding window may be defined by a spatial distance. That is, ultrasound samples within a certain spatial distance may be extracted through the sliding window.

[0039] In the embodiment of FIG. 3 , it is assumed that the ultrasound samples are characterized in the spatial domain. For example, the horizontal axis X represents a position, and the vertical axis Y represents a distance between an object and a vehicle. Each triangle may represent an ultrasound sample that may represent a distance between an object and a vehicle at a specific position. In this case, the sliding window may correspond to a specific spatial distance, which may be set according to factors such as an actual application scenario and business requirements. For example, the sliding window may correspond to 50 centimeters in the X-axis direction, and the corresponding spatial distance in the Y-axis direction may be set to cover the maximum distance between the object and the vehicle.

[0040] The sliding window may slide horizontally (i.e., along the X-axis) according to a predetermined step length. The step length may generally be equal to or less than the horizontal size of the sliding window so as not to miss any ultrasound samples. For example, as shown in FIG. 3 , as vehicle 100 moves in direction 140, the sliding window may slide accordingly. For convenience of illustration and description, three slidings of the sliding window are shown in FIG. 3 , and the sliding windows after the three slidings are denoted as 302(1), 302(2), and 302(3), respectively. In this manner, as vehicle 100 moves in direction 140, ultrasound samples that fall within the sliding window may be continuously extracted. Because the sample size within the sliding window is relatively small, the ultrasound samples may be quickly processed to determine object position information. Furthermore, by combining object position information within the sliding windows after multiple sliding (e.g., sliding windows 302(1), 302(2), and 302(3)), objects in the vehicle's surroundings can be quickly determined, and then assisted parking, etc., can be quickly performed.

[0041] Therefore, it can be seen that by setting the horizontal size and step size of the sliding window, it is possible to complete these processes in real time or near real time, i.e., to determine objects around the vehicle in real time or near real time.

[0042] Furthermore, the size of the sliding window may be fixed or may be variable (eg, dynamically adjusted according to vehicle operating conditions).

[0043] FIG. 4 is a schematic block diagram of an architecture for determining the position of objects in a vehicle's surroundings, according to some embodiments of the present disclosure.

[0044] In the embodiment of FIG. 4, the architecture 400 may include a sample extraction module 410 , a clustering module 412 , a cutting module 414 , a corner point prediction module 416 , and a fusion module 418 .

[0045] Sample extraction module 410 may extract ultrasound samples that are processed using a sliding window. As described above, the ultrasound samples may be obtained based on ultrasound data collected around the vehicle. For example, sample extraction module 410 may extract ultrasound samples within sliding window 302(1), 302(2), or 302(3).

[0046] The clustering module 412 may cluster the extracted ultrasound samples to obtain at least one ultrasound sample cluster. Clustering the ultrasound samples may actually be understood as segmenting objects. Thus, each ultrasound sample cluster may correspond to an object in the vehicle's surroundings. The clustering module 412 may use various applicable clustering algorithms to perform the clustering operation. For example, the clustering module 412 may use density-based spatial clustering of noise-containing applications (DBSCAN) to cluster the extracted ultrasound samples. Generally, the environment in which a vehicle is driven or parked may be complex. For example, a parking lot may contain obstacle areas of various shapes and sizes, the collected ultrasound data may contain various noises, and the number of objects appearing in a sliding window may vary from a single object to multiple objects. Then, using DBSCAN can effectively deal with such situations. As is known, BSCAN is a density-based clustering algorithm that defines a cluster as a maximal set of density-connected points, divides areas with sufficient density into clusters, and can find clusters of arbitrary shape in a noisy spatial database. DBSCAN does not require prior knowledge of the number of clusters to be formed, can identify clusters of arbitrary shape, and has the ability to detect noise points. Therefore, the clustering module 412 can use DBSCAN to effectively segment objects within a sliding window. DBSCAN is a clustering method known in the art. Therefore, its specific details are not described in detail.

[0047] The cutting module 414 may determine cutting information for at least one ultrasound sample cluster. The cutting information may indicate whether each ultrasound sample cluster is cut horizontally by a sliding window. This, in effect, also determines whether the object segmented by the clustering module 412 is cut horizontally by the sliding window. For example, the cutting module 414 may determine whether each ultrasound sample cluster is cut by a horizontal starting edge and / or a horizontal ending edge of the sliding window, such as determining whether the contour line of each ultrasound sample cluster intersects with the horizontal starting edge and / or the horizontal ending edge of the sliding window. In that case, the ultrasound sample cluster may be considered to be cut by the sliding window, and vice versa. In this manner, the cutting module 414 may generate a cutting flag for each ultrasound sample cluster. The cutting information may include a cutting flag for each ultrasound sample cluster. The cutting flag may indicate whether the left and / or right sides of the ultrasound sample cluster are cut. For example, in the embodiment of FIG. 3, the ultrasound samples within sliding window 302(1) may form an ultrasound sample cluster, and the right side of the ultrasound sample cluster is truncated by sliding window 302(1), but the left side of the ultrasound sample cluster is not truncated by sliding window 302(1); then, the truncation flag for the ultrasound sample cluster may indicate that the right side of the ultrasound sample cluster is truncated and the left side of the ultrasound sample cluster is not truncated, or may indicate only that the right side of the ultrasound sample cluster is truncated.

[0048] The corner point prediction module 416 may determine corner point prediction information for at least one ultrasound sample cluster. The corner point prediction information may indicate predicted positions of two corner points of each ultrasound sample cluster along the horizontal direction. The corner points of an ultrasound sample cluster may be understood as the end points of the ultrasound sample cluster. The two corner points of an ultrasound sample cluster along the horizontal direction may include the left and right end points of the ultrasound sample cluster. Since the ultrasound sample cluster may represent an object, the end points or corner points of the ultrasound sample cluster may correspond to the end points or corner points of the object.

[0049] The corner point prediction module 416 may determine corner point prediction information in various applicable manners. For example, the corner point prediction module 416 may include a feature extraction submodule 416A and a prediction submodule 416B. The feature extraction submodule 416A may extract feature information for each ultrasound sample cluster. The feature information for each ultrasound sample cluster may include echo feature information, intersection feature information, and / or statistical feature information of the ultrasound sample cluster. The echo feature information of the ultrasound sample cluster may include echo features associated with the ultrasound sample cluster, such as echo timestamp, echo amplitude, echo intensity, number of echoes, echo distance, echo coordinates, sensor coordinates, etc. The intersection feature information of the ultrasound sample cluster may include intersection features associated with the ultrasound sample cluster, such as intersection coordinates, intersection distance, intersection neighbor distance, intersection neighbor coordinates, sensor coordinates, etc. The statistical feature information of the ultrasound sample cluster may include statistical features associated with the ultrasound sample cluster, such as statistics of the echo features and / or intersection features of the ultrasound samples in the ultrasound sample cluster, such as the mean, minimum, maximum, variance, quantile, kurtosis, etc.

[0050] For each ultrasound sample cluster, the prediction sub-module 416B may generate predicted positions of its two corner points along the horizontal direction based on the feature information. The prediction sub-module 416B may use various applicable prediction algorithms to generate predicted positions of the two corner points of the ultrasound sample cluster along the horizontal direction. For example, for each ultrasound sample cluster, the prediction sub-module 416B may use a regression model to process the feature information of the ultrasound sample cluster, thereby predicting the positions of the two corner points of the ultrasound sample cluster along the horizontal direction. Here, the regression model may be a pre-trained model, such as by offline or online training. In some embodiments, the regression model may include an eXtreme Gradient Boosting (XGboost) model. In other embodiments, other models may also be used to predict the positions of the corner points of the ultrasound sample cluster along the horizontal direction. This is not a limitation in this specification.

[0051] The fusion module 418 may determine object position information within the sliding window based on the cutting information output by the cutting module 414 and the corner point prediction information output by the corner point prediction module 416. For example, for each ultrasound sample cluster, if the cutting information indicates that the ultrasound sample cluster is not cut horizontally by the sliding window, the fusion module 418 may include the predicted positions of the two corner points of the ultrasound sample cluster along the horizontal direction in the object position information; if one side of the ultrasound sample cluster is cut horizontally by the sliding window, the fusion module 418 may include the predicted position of the first of the two corner points of the ultrasound sample cluster along the horizontal direction in the object position information, where the first corner point may be located on the other side of the ultrasound sample cluster that is not cut by the sliding window; if both sides of the ultrasound sample cluster are cut horizontally by the sliding window, the fusion module 418 does not include the predicted positions of the two corner points of the ultrasound sample cluster along the horizontal direction in the object position information.

[0052] As described above, the sliding window may slide horizontally according to a predetermined step length. Then, for each sliding window after sliding, the above process may be performed to determine object position information within the sliding window. In this manner, object position information within the sliding window after multiple sliding (e.g., consecutive sliding) may be obtained for the vehicle's surroundings. Final object position information for the vehicle's surroundings may be determined based on the object position information within the sliding window after multiple sliding. The final object position information may indicate the position of at least one object in the surroundings. For example, in the embodiment of FIG. 3 , object position information may be determined for sliding windows 302(1), 302(2), and 302(3), respectively, and then final object position information may be determined based on the object position information within sliding windows 302(1), 302(2), and 302(3). The determination of the final object position information may be performed by a processing module other than the architecture 400 of FIG. 4 or may be performed by the fusion module 418. For example, in some embodiments, the fusion module 418 may cache the object position information within the sliding window after each sliding until the object position information within the sliding window is obtained after multiple slidings, and then determine the final object position information based on the information. In this case, the fusion module 418 may output the final position information instead of outputting the object position information within the sliding window after each sliding. For other embodiments, in some embodiments, the fusion module 418 may output the object position information within the sliding window after each sliding to another processing module other than the architecture 400 of FIG. 4, and the processing module determines the final object position information after obtaining the object position information within the sliding window after multiple slidings.The specific implementation method may depend on factors such as actual application scenarios and business requirements, which are not limited herein.

[0053] In some embodiments, an available parking space may also be detected in combination with object aiding information. For example, the object aiding information may be determined in various applicable manners, and the object aiding information may indicate the type and / or height of at least one object associated with the final object position information. An available available parking space for the vehicle may then be detected based on the final object position information and the object aiding information. In some embodiments, a path for the vehicle to enter the available parking space may also be planned based on the available parking space. The above operations may be performed by other processing modules other than architecture 400.

[0054] FIG. 5 is a schematic flowchart of a method for determining the position of an object in the surroundings of a vehicle, according to some embodiments of the present disclosure.

[0055] Ultrasound samples that fall within a sliding window may be extracted in step 502. The ultrasound samples may be obtained based on ultrasound data collected around the vehicle.

[0056] In step 504, the ultrasound samples may be clustered to obtain at least one ultrasound sample cluster, where each ultrasound sample cluster may correspond to an object in the surroundings.

[0057] In step 506, cutting information and corner point prediction information of at least one ultrasound sample cluster may be determined. The cutting information may be used to indicate whether each ultrasound sample cluster is cut horizontally by a sliding window. The corner prediction information may be used to indicate predicted locations of two corner points of each ultrasound sample cluster along the horizontal direction.

[0058] In step 508, the target location information within the sliding window may be determined based on the cutting information and corner point prediction information of at least one ultrasound sample cluster.

[0059] In an embodiment of the present disclosure, the ultrasound samples within the sliding window may be clustered to obtain at least one ultrasound sample cluster, and then the object position information within the sliding window may be determined based on whether the ultrasound sample cluster is cut off by the sliding window in the horizontal direction and at the predicted position of the corner point. Compared to starting to process the ultrasound data after the vehicle has passed the entire object, the number of ultrasound samples within the sliding window is significantly smaller. This allows for faster determination of the object position information within the sliding window, and by employing clustering and prediction techniques, the accuracy and reliability of the object position information are enhanced. Furthermore, the positions of objects around the vehicle can be determined efficiently and accurately. As a result, the assisted parking performance of the vehicle and the user experience can be significantly improved.

[0060] In some embodiments, the ultrasonic data may include echo data and / or intersection data, and the echo data may include echo information of multiple ultrasonic signals transmitted by ultrasonic sensors on the vehicle, and the intersection data may include intersection information between different ultrasonic signals.

[0061] In some embodiments, if the ultrasound samples are characterized in the time domain, the horizontal size of the sliding window may be defined by a length of time, or if the ultrasound samples are characterized in the spatial domain, the horizontal size of the sliding window may be defined by a spatial distance.

[0062] In some embodiments, in step 504, the ultrasound samples may be clustered using a DBSCAN algorithm.

[0063] In some embodiments, in step 506, it may be determined whether each ultrasound sample cluster is truncated by a horizontal starting edge and / or a horizontal ending edge of the sliding window to generate a truncation flag for each ultrasound sample cluster, and the truncation information includes a truncation flag for each ultrasound sample cluster.

[0064] In some embodiments, feature information of the at least one ultrasound sample cluster may be extracted in step 506. Corner point prediction information for the at least one ultrasound sample cluster may be generated based on the feature information of the at least one ultrasound sample cluster.

[0065] In some embodiments, the feature information of the at least one ultrasound sample cluster may include echo feature information, intersection feature information, and / or statistical feature information of the at least one ultrasound sample cluster.

[0066] In some embodiments, for each ultrasound sample cluster, the feature information of the ultrasound sample cluster may be processed using a regression model to generate predicted positions of two corner points of the ultrasound sample cluster along the horizontal direction.

[0067] In some embodiments, the regression model may include an XGboost model.

[0068] In some embodiments, in step 508, for each ultrasound sample cluster, if the ultrasound sample cluster is not cut horizontally by a sliding window, the predicted positions of the two corner points of the ultrasound sample cluster along the horizontal direction may be included in the object position information; if one side of the ultrasound sample cluster is cut horizontally by a sliding window, the predicted position of the first of the two corner points of the ultrasound sample cluster along the horizontal direction may be included in the object position information, and the first corner point may be located on the other side of the ultrasound sample cluster that is not cut by the sliding window; if both sides of the ultrasound sample cluster are cut horizontally by a sliding window, the predicted positions of the two corner points of the ultrasound sample cluster along the horizontal direction may not be included in the object position information.

[0069] In some embodiments, the sliding window may slide along a horizontal direction according to a predetermined step length. The method of Figure 5 may further include: after multiple slidings are obtained for the surroundings, determining object position information in the sliding window after each sliding until object position information in the sliding window is obtained; and determining final object position information for the surroundings based on the object position information in the sliding window after the multiple slidings, where the final object position information is used to indicate a position of at least one object in the surroundings.

[0070] In some embodiments, the method of FIG. 5 may further include determining object assistance information, where the object assistance information is used to indicate a type and / or height of at least one object; and detecting an available vacant parking space for the vehicle based on the final object position information and the object assistance information.

[0071] In some embodiments, the method of FIG. 5 may further include planning a route for the vehicle to enter the available parking space based on the available parking space.

[0072] FIG. 6 is a schematic block diagram of a control system for a vehicle according to some embodiments of the present disclosure.

[0073] Control system 600 may include one or more processors 610 and memory 620. Memory 620 may store executable instructions. Processor 610 may execute the executable instructions stored or coded within memory 620 to thereby perform the various operations and / or functions described above in conjunction with Figures 1-5. Although not shown in Figure 6, those skilled in the art will appreciate that control system 600 may include various other components, such as various communication modules, bus modules, and possible user interface modules, and the like.

[0074] In some embodiments, the control system 600 may include the control unit 130 and / or the processing unit 115 shown in FIGS.

[0075] An embodiment of the present disclosure also provides a vehicle. The vehicle may include an ultrasonic sensor, such as that shown in FIG. 1, used to transmit and receive ultrasonic signals. The vehicle may also include a control system 600 of FIG. 6.

[0076] Embodiments of the present disclosure also provide a machine-readable storage medium. The machine-readable storage medium may store executable instructions that, when executed by a processor, may implement various operations and / or functions described above in conjunction with Figures 1-5. For example, the machine-readable storage medium may include, but is not limited to, a random access memory (RAM), a read-only memory (ROM), an electrically erasable read-only memory (EEPROM), a static random access memory (SRAM), a hard disk, a flash memory, and the like.

[0077] Embodiments of the present disclosure also provide a computer program product, which may comprise a computer program that, when executed by a processor, may perform various operations and / or functions described above in conjunction with FIGS.

[0078] Specific embodiments of the present disclosure have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the examples and still achieve desirable results. In addition, the processes depicted in the figures do not necessarily require a particular or sequential sequence to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or advantageous.

[0079] Not all steps and units illustrated in the above flowcharts and system diagrams are required, and certain steps or units may be omitted based on actual needs. The device structures described in the above embodiments may be physical structures or logical structures. That is, some units may be realized by the same physical entity, while other units may be realized by multiple physical entities, or may be realized together by certain components in multiple separate devices.

[0080] Throughout this specification, the term "exemplary" means "serving as an example, instance, or illustration," but does not imply "preferred" or "advantageous" over other embodiments. Specific embodiments include specific details to facilitate an understanding of the described technology. However, these technologies may be implemented without these specific details. In some instances, well-known structures and devices are shown in block diagram form in order to avoid obscuring the concepts of the described embodiments.

[0081] The preceding description of the present disclosure is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to the present disclosure will be apparent to those skilled in the art, and the general principles defined herein may be applied to other variations without departing from the scope of protection of the present disclosure. Therefore, the present disclosure is not limited to the exemplary embodiments and designs described herein, but is to be accorded the widest scope defined by the principles and novel features disclosed herein.

Claims

1. 1. A method for determining the position of an object in the vicinity of a vehicle, comprising: Extracting ultrasound samples that fall within a sliding window, the ultrasound samples being obtained based on ultrasound data collected around the vehicle; clustering the ultrasound samples to obtain at least one ultrasound sample cluster, each ultrasound sample cluster corresponding to an object in the surroundings; determining cutting information and corner point prediction information of the at least one ultrasound sample cluster, wherein the cutting information is used to indicate whether each ultrasound sample cluster is cut by the sliding window in a horizontal direction, and the corner point prediction information is used to indicate predicted positions of two corner points of each ultrasound sample cluster along the horizontal direction; determining object position information within the sliding window based on the cutting information and the corner point prediction information of the at least one ultrasound sample cluster; A method comprising:

2. If the ultrasound samples are characterized in the time domain, the horizontal size of the sliding window is defined by a length of time; The method of claim 1 , wherein when the ultrasound sample is characterized in the spatial domain, the lateral size of the sliding window is defined by a spatial distance.

3. Clustering the ultrasound samples comprises: The method of claim 1 , comprising clustering ultrasound samples using a density-based spatial clustering of noisy applications (DBSCAN) algorithm using density-based spatial clustering.

4. determining the disconnection information 2. The method of claim 1, comprising: determining whether each ultrasound sample cluster is truncated by a horizontal starting edge and / or a horizontal ending edge of the sliding window to generate a truncation flag for each ultrasound sample cluster, wherein the truncation information includes the truncation flag for each ultrasound sample cluster.

5. Determining the corner point prediction information includes: extracting feature information of the at least one ultrasound sample cluster; generating corner point prediction information for the at least one ultrasound sample cluster based on the feature information of the at least one ultrasound sample cluster; The method of claim 1 , comprising:

6. The method of claim 5 , wherein the feature information of the at least one ultrasound sample cluster comprises at least one of echo feature information, intersection feature information, and / or statistical feature information.

7. generating the corner point prediction information includes:

6. The method of claim 5, comprising: for each ultrasound sample cluster, processing the feature information of the ultrasound sample cluster using a regression model to generate the predicted positions of the two corner points of the ultrasound sample cluster along the horizontal direction.

8. The method of claim 7 , wherein the regression model comprises an eXtreme Gradient Boosting (XGboost) model.

9. Determining the object position information includes: For each ultrasonic sample cluster, If the ultrasound sample cluster is not cut in the horizontal direction by the sliding window, the predicted positions of the two corner points of the ultrasound sample cluster along the horizontal direction are included in the object position information; When one side of the ultrasound sample cluster is cut horizontally by the sliding window, the predicted position of a first of the two corner points of the ultrasound sample cluster along the horizontal direction is included in the object position information, and the first corner point is located on the other side of the ultrasound sample cluster that is not cut by the sliding window; 2. The method of claim 1, wherein when both sides of the ultrasound sample cluster are cut horizontally by the sliding window, the predicted positions of the two corner points of the ultrasound sample cluster along the horizontal direction are not included in the object position information.

10. 2. The method of claim 1, wherein the ultrasonic data includes echo data and / or intersection data, the echo data including echo information of multiple ultrasonic signals transmitted by ultrasonic sensors of the vehicle, and the intersection data including intersection information between different ultrasonic signals.

11. the sliding window slides along the horizontal direction according to a predetermined step length; The method comprises: After a plurality of slidings are obtained for the surroundings, determining the object position information within the sliding window after each sliding until the object position information within the sliding window is obtained; determining final object position information relative to the surroundings based on the object position information within the sliding window after multiple slidings, wherein the final object position information is used to indicate the position of at least one object in the surroundings; and The method of claim 1 further comprising:

12. determining object supplementary information, the object supplementary information being used to indicate a type and / or a height of the at least one object; Detecting an available vacant parking space for the vehicle based on the final object position information and the object assistance information; The method of claim 11 further comprising:

13. The method of claim 12 , further comprising planning a route for the vehicle to enter the vacant parking space based on the vacant parking space.

14. 1. A control system for a vehicle, comprising: at least one processor; a memory coupled to the at least one processor, the memory storing executable instructions that, when executed by the at least one processor, enable the at least one processor to perform the method of any one of claims 1 to 13; and A control system comprising:

15. A vehicle, at least one ultrasonic sensor configured to transmit and receive ultrasonic signals; A control system according to claim 14; A vehicle equipped with:

16. 14. A machine-readable storage medium storing executable instructions that, when executed by a processor, perform a method according to any one of claims 1 to 13.

17. A computer program product comprising a computer program which, when executed by a processor, performs the method of any one of claims 1 to 13.

Images