Method and device for determining an object in the surroundings of a vehicle

Abstract

The present application relates to a method for determining an object in the surroundings of a vehicle based on an ultrasonic signal. The method comprises obtaining an ultrasonic sample set based on ultrasonic data collected during vehicle movement, wherein each ultrasonic sample in the ultrasonic sample set comprises sample point plane coordinates and sample point ultrasonic signal features; performing a gridding process on the ultrasonic sample set based on the sample point plane coordinates of each ultrasonic sample and at least a portion of the ultrasonic signal features of the sample point; and clustering the gridded ultrasonic sample set based on the gridded sample point plane coordinates of each ultrasonic sample and the at least portion of the ultrasonic signal features of the sample point to obtain one or more sample clusters, wherein each sample cluster corresponds to an object in the surroundings of the vehicle.

Description

[0001] METHOD AND DEVICE FOR DETERMINING AN OBJECT IN THE SURROUNDINGS OF A VEHICLE

[0002] Technical Field

[0003] The present application relates to vehicle automatic control, and more particularly, to a method, a control system, a vehicle, a machine-readable storage medium, and a computer program product for determining an object in the surroundings of a vehicle based on an ultrasonic signal.

[0004] Background

[0005] Accurately identifying objects in a vehicle’s surroundings is crucial for implementing various vehicle auxiliary functions in applications such as autonomous driving systems, automatic parking systems, and driver assistance systems. For instance, sensor signals can be used to detect objects in a vehicle’s surroundings, enabling the vehicle to identify obstacles in real-time and adjust its driving route accordingly. Similarly, in a parking environment, sensor signals can detect obstacles and accurately determine available parking spaces.

[0006] Ultrasonic sensors (USSs) offer a cost-effective solution for object detection. However, the low resolution of data captured by ultrasonic radar prevents conventional detection methods using ultrasonic signals from being effectively applied in complex scenarios. Additionally, the variety of objects present in different vehicle application scenarios necessitates improvements in the accuracy of object detection using ultrasonic signals. Enhancing this accuracy is crucial for optimizing the performance of assisted driving and parking.

[0007] Summary of the Invention

[0008] The following introduction is provided in order to introduce selected concepts in a simple manner, and these concepts will be further described in the detailed description below. The introduction is not intended to highlight the key or necessary features of the claimed subject matter, nor is it intended to limit the scope of the claimed subject matter.

[0009] Generally, in order to detect an object in the surroundings of the vehicle, the obtained ultrasonic data can be used to determine relevant information such as the position of the object. To accurately predict the position of an object in the surroundings of the vehicle, the entire processing flow may involve multiple steps such as data preprocessing, target segmentation, and target position prediction. The operations performed during the data preprocessing stage are essential for achieving precise target segmentation and reliable position prediction. In real application scenarios, there may be many different types of objects in the surroundings of the vehicle, such as other vehicles, ground locks, bushes, railings, walls, curbs, etc. When multiple objects are close to each other on a plane, it is difficult to accurately distinguish them based only on position information such as plane coordinates, which may affect the accuracy of subsequent target segmentation and position prediction.

[0010] Therefore, it is desirable to provide a method for determining an object in the surroundings of a vehicle based on an ultrasonic signal. This method can not only preprocess the collected ultrasonic data based on the planar position information of the ultrasonic data sample points, but also take into account other distinguishable features of the object. This approach will enhance the extraction of relevant features from the ultrasonic data. The ultrasonic data preprocessed by the method disclosed in the present invention may have accuracy and robustness in subsequent target segmentation, and thus may be applied to complex roads or parking scenes. This helps to improve the performance of the vehicle’s assisted driving and parking.

[0011] In one aspect, examples of the present disclosure provide a method for determining an object in the surroundings of a vehicle based on an ultrasonic signal. The method comprises obtaining an ultrasonic sample set based on ultrasonic data collected during vehicle movement, wherein each ultrasonic sample in the ultrasonic sample set comprises sample point plane coordinates and sample point ultrasonic signal features; performing a gridding process on the ultrasonic sample set based on the sample point plane coordinates of each ultrasonic sample and at least a portion of the ultrasonic signal features of the sample point; and clustering the gridded ultrasonic sample set based on the gridded sample point plane coordinates of each ultrasonic sample and the at least portion of the ultrasonic signal features of the sample point to obtain one or more sample clusters, wherein each sample cluster corresponds to an object in the surroundings of the vehicle.

[0012] In another aspect, examples of the present disclosure provide 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, wherein the executable instructions, when executed by the at least one processor, allow the at least one processor to implement the method according to any example of the present disclosure.

[0013] In another aspect, examples of the present disclosure provide a computer-readable medium which stores a computer program comprising instructions that, when executed by a processor, cause one or more units to implement the method according to any example of the present disclosure.

[0014] In another aspect, examples of the present disclosure provide a computer program product, comprising a computer program, wherein the computer program, when executed by the processor, implement the method according to any example of the present disclosure.

[0015] In another aspect, examples of the present disclosure provide a vehicle, the vehicle comprising: an ultrasonic sensor for transmitting and receiving an ultrasonic signal; and one or more units for implementing the method according to any example of the present disclosure.

[0016] Brief Description of the Drawings

[0017] The nature and advantages of the present disclosure may be further implemented by referring to the following accompanying drawings. In the drawings, similar components or features may have the same reference signs.

[0018] FIG. 1 is a schematic diagram of an exemplary vehicle according to examples of the present disclosure.

[0019] FIG. 2 is a schematic diagram of an exemplary control system in a vehicle according to examples of the present disclosure.

[0020] FIG. 3A is a schematic diagram of an application scenario according to examples of the present disclosure.

[0021] FIG. 3B is a schematic diagram of ultrasonic samples according to examples of the present disclosure. FIG. 4 is a schematic diagram of a method and module for determining an object in the surroundings of a vehicle according to examples of the present disclosure.

[0022] FIG. 5A is a schematic diagram of grids of different resolutions according to examples of the present disclosure.

[0023] FIG. 5B is another schematic diagram of grids of different resolutions according to examples of the present disclosure.

[0024] FIG. 6 is a flow chart of a method for determining an object in the surroundings of a vehicle according to examples of the present disclosure.

[0025] FIG. 7 is a block diagram of a control system for a vehicle according to examples of the present disclosure.

[0026] Specific Embodiments

[0027] The subject matter described herein will now be discussed with reference to exemplary embodiments. It should be understood that discussions about these embodiments are provided to aid those skilled in the art in better understanding and thereby implementing the subject matter described herein rather than limiting the scope of protection, applicability, or examples described in the Claims. Changes may be made to the functions and arrangements of the elements discussed without departing from the scope of protection of the content of the present disclosure. Various processes or components may be omitted, substituted, or added in the various examples as needed. For instance, the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. In addition, features described in relation to some examples may also be combined in other examples.

[0028] As used herein, the term “comprising” and its variations are open terms, which mean “including but not limited to”. The term “based on” indicates “at least partially based on”. The terms “one example” and “an example” indicate “at least one example”. The term “another example” indicates “at least one other example”. The terms “first”, “second”, etc. may refer to different or same objects. Unless explicitly stated in the context, the definition of one term is consistent throughout the description.

[0029] Ultrasonic sensors have garnered significant attention and research in the automotive field due to their advantages of low cost, rapid response, and ease of integration. However, effectively utilizing ultrasonic sensors for object detection in the automotive field remains one of the current challenges. To address this issue, the examples of the present disclosure offer a technical solution for determining an object in the surroundings of a vehicle based on an ultrasonic signal. A detailed description is given below with reference to the specific examples.

[0030] FIG. 1 is a schematic diagram of an exemplary vehicle according to examples of the present disclosure. It should be understood that the following examples are provided solely to enhance understanding of the present disclosure and do not impose any limitations on the scope of the present disclosure.

[0031] In the example of FIG. 1 , at least one ultrasonic sensor 110 (simply represented as a black dot in FIG. 1 ) may be installed on a vehicle 100. For example, as shown in FIG. 1 , the ultrasonic sensor 110 may be installed on the front side, rear side, left side, and right side of the vehicle 100, that is, corresponding to the front, rear, left side, and right side of the vehicle 100, respectively. FIG. 1 shows 16 ultrasonic sensors. However, the number and installation positions 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 installation positions of the ultrasonic sensors may vary as well.

[0032] The ultrasonic sensor 110 may transmit an ultrasonic signal toward the surroundings of the vehicle 100. For example, two ultrasonic sensors 110 located on the right front side of the vehicle 100 may transmit an ultrasonic signal 120. The ultrasonic signal 120 will be described below as an example. The ultrasonic signal 120 may encounter various objects during transmission, such as obstacles (e.g., other vehicles, ground locks, trees, railings, fences, etc.), objects related to the driving operation of the vehicle (e.g., curbs, etc.), pedestrians, etc. When encountering an object, the ultrasonic signal 120 may be reflected. After the ultrasonic signal 120 is reflected, the ultrasonic sensor 110 may receive the reflected signal (also commonly referred to as an echo signal).

[0033] Various ultrasonic data may be obtained based on the transmitted ultrasonic signal and the received echo signal. These operations may be implemented in various ways. For example, in some implementations, the vehicle 100 may comprise an ultrasonic sensor module. The ultrasonic sensor module may comprise an ultrasonic sensor 110 and a processing unit. The ultrasonic sensor 110 may comprise a transmitter that transmits an ultrasonic signal and a receiver that receives an echo signal. The processing unit may obtain various ultrasonic data based on the transmitted ultrasonic signal and the received echo signal. In addition, the processing unit may also control the transmission and reception of signals by each ultrasonic sensor.

[0034] For example, in FIG. 1 , two ultrasonic sensors 110 located on the right front side of the vehicle 100 may constitute an ultrasonic sensor module 105, which comprises 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 by the two ultrasonic sensors and the echo signals received. Similarly, the two ultrasonic sensors 100 located on the right rear side, 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 of the vehicle 110 may all constitute an ultrasonic sensor module with the corresponding processing units.

[0035] Or, for another example, a single ultrasonic sensor 110 of the vehicle 100 may constitute an ultrasonic sensor module with a corresponding processing unit, and the processing unit may obtain various ultrasonic data based on the ultrasonic signal transmitted by the single sensor and the echo signal received. For another example, in FIG. 1 , the four ultrasonic sensors 110 located on the right side of the vehicle 100 and the corresponding processing units may constitute an ultrasonic sensor module, and the processing units may obtain various ultrasonic data based on the ultrasonic signals transmitted by the four sensors and the echo signals received. Similarly, the four ultrasonic sensors 110 located on the left side of the vehicle 100 may each constitute an ultrasonic sensor module with the corresponding processing unit. For another example, all the ultrasonic sensors 110 shown in FIG. 1 may constitute an ultrasonic sensor module with corresponding processing units, and the processing units may obtain various ultrasonic data based on the ultrasonic signals transmitted by all these ultrasonic sensors and the echo signals received.

[0036] Although the ultrasonic sensor and the ultrasonic sensor module are described separately above, according to the context, the ultrasonic sensor may narrowly represent a sensing unit for transmitting an ultrasonic signal and receiving an echo signal, or may broadly represent an ultrasonic sensor module. Those skilled in the art are able to distinguish the meaning of the ultrasonic sensor in a specific context.

[0037] As described above, the processing unit may obtain various ultrasonic data based on the ultrasonic signal transmitted by the ultrasonic sensor 110 and the echo signal received, and the ultrasonic data may comprise various related data.

[0038] In some examples, the ultrasonic data may comprise echo data. The echo data may comprise information related to the echo signal. For example, the echo data may comprise an echo timestamp, an echo amplitude, an echo significance, an echo distance, an echo height, echo coordinates (for example, two coordinates may be comprised), sensor coordinates (for example, two coordinates may be comprised), etc. of the echo signal. In some examples, the echo data may be obtained using the center line method. For example, while the vehicle 100 is traveling 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 center line method, it is assumed that the reflection point on the detected object is on the center line 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 denoted, for example, by the echo coordinates.

[0039] In some examples, the ultrasonic data may comprise echo intersection data. The echo intersection data may comprise information related to intersections between different echo signals. For example, the echo intersection data may comprise echo intersection coordinates (for example, may comprise two coordinates), an echo intersection distance, adjacent echo intersection coordinates (for example, may comprise two coordinates), an adjacent echo intersection height, an adjacent echo intersection distance, an adjacent echo intersection deflection, sensor coordinates, etc. For example, while the vehicle 100 is traveling 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. 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 time of the two ultrasonic signals 120, the reception time of the corresponding echo signals, and other information, the processing unit may calculate an echo intersection 160 of the two ultrasonic signals 120, and the echo intersection 160 may represent the reflection point on the detected object. Accordingly, the echo intersection data may comprise information about the intersection 160. In some examples, the echo intersection is not limited to being the intersection of the two echoes of ultrasonic signals transmitted by the two ultrasonic sensors. For example, the echo intersection may also be the intersection of the two echoes of ultrasonic signals transmitted by the same ultrasonic sensor at different times during movement. Moreover, the echo intersection data may be calculated based on the echo data. For example, based on the ultrasonic arcs of any two echo data within a certain range, the corresponding echo intersection data may be obtained.

[0040] In some examples, the ultrasonic data may comprise the above-mentioned echo data and / or echo intersection data. Of course, the ultrasonic data may optionally comprise other data related to the ultrasonic signal, such as data related to the ultrasonic signal obtained based on methods known in the art or possible methods in the future.

[0041] In some examples, the processing unit of the ultrasonic sensor module may provide the obtained 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 examples, part 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 obtain echo data and / or echo intersection data based on the ultrasonic signal transmitted by the ultrasonic sensor 110 and the echo signal received. In some examples, the vehicle 100 may also comprise other processing units to perform such operations.

[0042] In some implementations, the sensors, processing units, and control units mentioned above may be comprised in the control system of the vehicle. The control system of the vehicle may perform various controls on the vehicle. For ease of understanding, FIG. 2 is a schematic diagram of an exemplary control system in a vehicle according to examples of the present disclosure.

[0043] In the example of FIG. 2, the same reference signs are used for the same components as those in FIG. 1. Moreover, it should be understood that FIG. 2 only shows some components related to the technical solution of the present disclosure. In actual implementation, the control system of the vehicle may also comprise various other components, which are not limited by the present disclosure.

[0044] In the example of FIG. 2, the control system 200 of the vehicle may comprise ultrasonic sensor modules 105-1 to 105-N. The ultrasonic sensor modules 105-1 to 105- N comprise one or more ultrasonic sensors 110 and corresponding processing units 115- 1 to 115-N, respectively. As described above in conjunction with FIG. 1 , in some implementations, the vehicle may comprise only one ultrasonic sensor module. For example, the ultrasonic sensor module comprises multiple ultrasonic sensors and processing units installed on the vehicle 100; in different implementations, the vehicle may comprise one or more ultrasonic sensor modules, each of which may comprise one or more ultrasonic sensors and corresponding processing units.

[0045] The control system 200 may further comprise 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 signal and receive echo signal; the control unit 130 may receive ultrasonic data from any one of the ultrasonic sensor modules 105-1 to 105-N, and perform further operations or control the vehicle based on the ultrasonic data, etc. 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 other processing units.

[0046] The control system 200 may further comprise 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 receive information input by the user from the human-machine interface. In some examples, the user may input a selection regarding entering the assisted parking mode or an autonomous driving mode via the humanmachine interface 180. The control unit 130, upon receiving user input to enter the assisted parking mode or the autonomous driving mode, may control the vehicle to operate in the assisted parking mode or the autonomous driving mode. For example, in the assisted parking mode, the vehicle is controlled to automatically find a parking space and automatically park. For another example, in the autonomous driving mode, the vehicle is controlled to plan a route and avoid obstacles. In some examples, the control unit 130 may automatically control the vehicle to enter the assisted / automatic parking mode or the assisted / autonomous driving mode without user input. Regardless of which mode is entered by which method, the control unit 130 may detect an object in the surroundings of the vehicle by processing ultrasonic data, such as determining object information such as the position, type, and height of the object. Based on the object information, the control unit 130 may perform various operations related to vehicle parking or path planning, such as detecting available parking spaces for the vehicle, planning a parking route for the vehicle based on the detected parking spaces, planning a driving route for the vehicle based on the detected obstacles, and the like.

[0047] Generally, in order to detect an object in the surroundings of a vehicle based on an ultrasonic signal, multiple processing steps are required, including data preprocessing, target segmentation, and target position prediction. The operations performed during the data preprocessing stage are essential for achieving precise target segmentation and reliable position prediction. In real application scenarios, there may be many different types of objects in the surroundings of the vehicle, such as other vehicles, ground locks, bushes, railings, walls, curbs, etc. When multiple objects of different types are close to each other on a plane, they may not be accurately segmented into multiple objects during the target segmentation stage, resulting in inaccuracies in subsequent position prediction. This limitation significantly impacts the performance of the vehicle’s assisted driving and parking, as well as the user experience.

[0048] In the technical solution of the present disclosure, various technologies may be used to preprocess the ultrasonic data. For example, an ultrasonic sample set corresponding to a spatial range may be obtained based on the ultrasonic data, wherein each ultrasonic sample may comprise other ultrasonic signal features in addition to the sample point plane coordinates, such as ultrasonic signal features that can reflect the height, surface material and / or distance of the object. By performing other subsequent processing such as clustering based on other ultrasonic signal features in addition to the sample point plane coordinates, more accurate and reliable target segmentation and target position prediction may be achieved. As a result, the vehicle assisted driving / parking performance and user experience can be greatly improved. FIG. 3A is a schematic diagram of an application scenario according to examples of the present disclosure.

[0049] In the example shown in FIG. 3A, for example, in a parking lot, the ultrasonic sensor 310 in the ultrasonic sensor module transmits an ultrasonic signal 320 while the vehicle 330 is traveling in the direction of the arrow to collect ultrasonic data, and ultrasonic samples are obtained based on the ultrasonic data to detect an object in the surroundings of the vehicle. As shown in FIG. 3A, there may be various types of objects in the surroundings of the vehicle 330, such as other vehicles 340-1 and 340-2, ground protrusions 350, small bushes or grass 360, and walls 370-1 to 370-4. There may also be other types of objects (not shown) in the surroundings of the vehicle 330, such as railings, curbs, etc. The obtained ultrasonic samples may contain information about the position of the object and ultrasonic signal features reflecting various relevant features, and the position, type, etc. of the object may be subsequently predicted based on the ultrasonic signal features. FIG. 3B is a schematic diagram of ultrasonic samples obtained according to examples of the present disclosure.

[0050] In the example shown in FIG. 3B, the ultrasonic samples obtained based on collected ultrasonic data in a spatial range are shown, wherein the spatial range shown in FIG. 3B may correspond to the spatial range shown in FIG. 3A, and the ultrasonic samples may comprise echo samples and echo intersection samples. In FIG. 3B, one ultrasonic sample represents one echo data sample point or one echo intersection data sample point, and a circular sample point represents an echo data sample point, and a triangular sample point represents an echo intersection data sample point. Each ultrasonic sample may comprise plane coordinates indicating the position of the sample point and several multidimensional ultrasonic signal features. In FIG. 3B, the sample points are shown in a spatial range based on the plane coordinates. In fact, each sample point can be understood as a high-dimensional data point. For example, each echo sample point may comprise echo coordinates (e.g., may comprise two coordinates), sensor coordinates (e.g., may comprise two coordinates), an echo timestamp of the echo signal, an echo amplitude, an echo significance, an echo distance, an echo height, etc. For example, each echo intersection sample point may comprise echo intersection coordinates (for example, may comprise two coordinates), sensor coordinates, an echo intersection distance, an echo intersection height, an echo intersection deflection, an echo intersection amplitude, an echo intersection significance, adjacent echo intersection coordinates (for example, may comprise two coordinates), an adjacent echo intersection height, an adjacent echo intersection distance, an adjacent echo intersection deflection, etc., wherein features such as an echo intersection height, an echo intersection amplitude, and an echo intersection significance may be described by corresponding features of two or more echoes that generate the echo intersection.

[0051] Those skilled in the art will appreciate that, in addition to the features of the echo samples and echo intersection samples exemplified above, the echo samples and echo intersection samples may also comprise other features related to ultrasonic signals, and the features of the echo samples and echo intersection samples known in the art and that may be adopted in the future may all be applied to the technical solution of the present disclosure. Those skilled in the art will appreciate that, in addition to the exemplified echo samples and echo intersection samples, the ultrasonic data may also comprise other data related to the ultrasonic signal, such as data related to the ultrasonic signal obtained based on methods known in the art or possible methods in the future. Those skilled in the art will appreciate that FIG. 3B is merely a schematic diagram of ultrasonic samples for illustrative purposes. In various practical applications, the number of ultrasonic samples within a specific spatial range will be greater and the distribution will be more complex.

[0052] In one example, the ultrasonic samples shown in FIG. 3B may be obtained based on ultrasonic data collected by an ultrasonic sensor within a period of time when the vehicle moves. In another example, the ultrasonic samples shown in FIG. 3B may be obtained based on ultrasonic data collected by an ultrasonic sensor within a certain distance moved by the vehicle. For example, the ultrasonic samples shown in FIG. 3B may be obtained by fusing data captured by the ultrasonic sensor during multiple sliding windows based on a sliding window mechanism. The size of the sliding window may be fixed or variable, and the size of the sliding window corresponds to the actual spatial range covered by the ultrasonic signal 320.

[0053] In one example, the ultrasonic data collected by the ultrasonic sensor may be cached in a cache or memory of the vehicle’s processing system, and the vehicle’s control unit 130 or other processing units may subsequently process the cached ultrasonic data to obtain ultrasonic samples. In one example, the ultrasonic samples may be cached in a cache or memory of the vehicle’s processing system, and the vehicle’s control unit 130 or other processing unit may subsequently process the cached ultrasonic samples to determine the position and / or type of the object. In one example, the control unit 130 or other processing unit of the vehicle may plan a vehicle driving route based on the determined position and / or type of the object, such as assisting the vehicle in parking or driving.

[0054] For example, clustering may be performed based on the ultrasonic samples shown in FIG.3B to obtain one or more sample clusters. Each sample cluster may be considered to correspond to an object in the surroundings of the vehicle, and target segmentation is performed based on one or more sample clusters, and then object type recognition and / or position prediction are performed on each segmented target. Usually, clustering of the ultrasonic samples is performed based solely on the planar positions of the sample points. For example, the set of sample points shown in the dotted box 380 in FIG. 3B may be clustered into the same sample cluster because their planar coordinates are close to each other, and thus are considered to correspond to the same object in subsequent operations. However, there are problems with this processing approach.

[0055] Referring to FIG. 3A in conjunction with FIG. 3B, it can be seen that the set of sample points shown in the dashed box 380 may correspond to multiple objects, for example, ground protrusion 350, lawn 360, vehicle 340-1 , and wall 370-1. Due to the close plane distance of the above objects and the sparsity of the ultrasonic signal itself, clustering based solely on plane position information cannot accurately distinguish multiple objects. Furthermore, the ground protrusion 350 and the lawn 360 are of relatively low height and have no substantial impact on the driving of the vehicle, while the vehicle 340-1 and the wall 370-1 are of relatively high height and are obstacles that the vehicle needs to avoid when driving. It is expected that the areas and obstacles in which the vehicle can travel can be accurately distinguished. For example, the corner positions A and B of the vehicle 340-1 and the corner positions of the wall 370-2 (not shown) can be identified. However, due to the problems described above, the vehicle, lawn and wall may be identified as the same obstacle, and inaccurate corner positions E and F may be identified, thereby affecting the accuracy of subsequent vehicle assisted driving or parking.

[0056] FIG. 4 is a schematic diagram of a method and module for determining an object in the surroundings of a vehicle according to examples of the present disclosure. As shown in FIG. 4, it may comprise an up / down-sampling module 410, a gridding module 420, a preprocessing module 430 and a clustering module 440, wherein the dashed box represents an optional module.

[0057] In the example shown in FIG. 4, an ultrasonic sample set such as that shown in FIG. 3B may be used as an input to the up / down-sampling module 410, and the up / down- sampling module 410 may perform up / down-sampling based on the ultrasonic sample set. Each ultrasonic sample in the ultrasonic sample set may comprise at least the plane coordinates of the sample point and the ultrasonic signal features associated with the sample point, such as the various ultrasonic signal features described in conjunction with FIG. 3B.

[0058] In one example, the up / down-sampling module 410 may process the ultrasonic sample set using a down-sampling algorithm. To address the problem of disequilibrium in the classification of ultrasonic echo raw data, part of data can be selected from a majority set to be recombined with a minority set into a new data set, and such a manner is known as down-sampling. For example, commonly used down-sampling algorithms include, but are not limited to, random down-sampling, EasyEnsemble, BalanceCascade, or NearMiss, etc.

[0059] In another example, the up / down-sampling module 410 may process the ultrasonic sample set using an up-sampling algorithm. To address the problem of disequilibrium in the classification of ultrasonic echo raw data, data from a minority set can be expanded to the same number as data from a majority set, and such a manner is known as up- sampling. For example, commonly used up-sampling algorithms include, but are not limited to, interpolation, transposation convolution, up-pooling, etc.

[0060] In one example, the up / down-sampling module 410 is optional and may be omitted and the ultrasonic sample set is directly input into the gridding module 420.

[0061] In the example shown in FIG.4, the up / down-sampled ultrasonic sample set may be used as an input of the gridding module 420 , and the gridding module 420 performs gridding based on the up / down-sampled ultrasonic sample set. Gridding refers to dividing the spatial range into grids of a certain size, and integrating the features of zero or more sample points falling into each grid into high-dimensional feature data to characterize the grid. Gridding of data helps to integrate high-dimensional feature data for subsequent processing.

[0062] In one example, the gridding module 420 may perform gridding based not only on the sample point plane coordinates of each ultrasonic sample, but also on a portion of the ultrasonic signal features associated with the sample point. For example, a portion of the ultrasonic signal features associated with the sample point may comprise ultrasonic signal features that can reflect the height of the object, such as echo height or echo intersection height, etc.; ultrasonic signal features that can reflect the surface material of the object, such as echo amplitude or echo intersection amplitude, echo significance or echo intersection significance, etc.; or ultrasonic signal features that can reflect the distance between the object and the sensor, such as echo signal round-trip time, echo distance, echo intersection distance, etc.

[0063] In one example, the resolution of the gridding may be fixed. For example, the grid size is fixed to 10X10 cm. In another example, to balance the accuracy and efficiency of the calculation, the resolution of the gridding may be flexibly adjusted based on a predetermined threshold condition. For example, when the computing resources are sufficient, the grid size may be 5x5 cm, and when the computing resources are tight, the grid size may be 20x20 cm. Other possible threshold conditions may be the accuracy of the calculation, the accuracy of the data required for the calculation, etc., which are not limited in the present application. In addition, the grid is not necessarily square, but may also be rectangular.

[0064] In one example, the gridding module 420 may perform gridding on the sample point plane coordinates of each ultrasonic sample and a portion of the ultrasonic signal features associated with the sample point at the same resolution. Additionally or alternatively, the gridding module 420 may perform gridding on the sample point plane coordinates of each ultrasonic sample and a portion of the ultrasonic signal features associated with the sample point at different resolutions.

[0065] FIG. 5A is a schematic diagram of grids of different resolutions according to examples of the present disclosure. As shown in FIG. 5A, gridding may be performed at a first resolution A based on the plane coordinates of the sample points, for example, a grid size of 10x10 cm. To more clearly distinguish objects with similar plane coordinate distances, it may be considered that the ultrasonic signal features associated with the height and / or material of the object may provide more information in the subsequent clustering, and therefore the ultrasonic signal features associated with the height and / or material of the object may be gridded with a second resolution B smaller than the first resolution A, for example, a grid size of 5x5 cm. Considering that the ultrasonic signal features reflecting the distance between the object and the sensor are already partially reflected in the sample point plane coordinates, in order to reduce the amount of calculation, the ultrasonic signal features associated with the object distance may be gridded with a third resolution C larger than the first resolution A, for example, a grid size of 20x20 cm. The resolution to be used for gridding may be determined based on part or all of the ultrasonic signal features associated with the sample point, and this application does not limit this.

[0066] In one example, the gridding module 420 may perform gridding based only on one of the following: the ultrasonic echo samples in the ultrasonic sample set or the ultrasonic echo intersection samples in the ultrasonic sample set. In another example, the gridding module 420 may perform gridding based on both the ultrasonic echo samples in the ultrasonic sample set and the ultrasonic echo intersection samples in the ultrasonic sample set.

[0067] In the example shown in FIG. 4, the gridded ultrasonic sample set may be used as the input of the preprocessing module 430, and the preprocessing module 430 performs various data-related operations on the gridded ultrasonic sample set to generate an ultrasonic sample set that is more suitable for subsequent operations.

[0068] In one example, the preprocessing module 430 may perform normalization on the gridded portion of the ultrasonic signal features associated with the sample point to avoid the order of magnitude difference between the several multidimensional features of the sample point. In addition, the preprocessing module 430 may also perform normalization on the gridded sample point plane coordinates. For example, commonly used normalization algorithms include but are not limited to min-max normalization, z- normalization, nonlinear normalization, etc. In one example, the preprocessing module 430 may smooth the gridded sample point plane coordinates and a portion of the ultrasonic signal features associated with the sample point to remove redundant information and further integrate feature data, thereby reducing the number of parameters. For example, commonly used smoothing algorithms include, but are not limited to, maximum pooling, minimum pooling, average pooling, overlapping pooling, pyramid pooling, bilinear pooling, etc.

[0069] In one example, smoothing may be performed after normalization. Additionally or alternatively, only one of normalization and smoothing may be performed.

[0070] In one example, in particular, when gridding is performed on the sample point plane coordinates of the ultrasonic sample and a portion of the ultrasonic signal features associated with the sample point at corresponding resolutions, normalization and / or smoothing may also be performed on the sample point plane coordinates and part of the ultrasonic signal features associated with the sample point at corresponding resolutions. Continuing with the example in FIG. 5A, the gridding module 420 may previously perform gridding based on the sample point plane coordinates at the first resolution A (grid size of 10x10 cm), based on the ultrasonic signal features associated with the height and / or material of the object at the second resolution B (grid size of 5x5 cm), and based on the ultrasonic signal features associated with the distance of the object at the third resolution C (for example, grid size of 20x20 cm), and then normalization or smoothing may be performed on each gridded feature with different resolutions.

[0071] After that, features with different resolutions may be aggregated based on the same resolution. In one example, features with different resolutions may be aggregated based on the minimum resolution among the different resolutions. For example, as shown in the example in FIG. 5A, with the second resolution B as a reference, plane coordinates of each sample point that are gridded by the first resolution A may be corresponded to four ultrasonic signal features associated with the object height and / or material that are gridded by the second resolution B, and each ultrasonic signal feature associated with the object distance that is gridded by the third resolution C may be corresponded to sixteen ultrasonic signal features associated with the object height and / or material that are gridded by the second resolution. That is, the features of the grids B1 to B4 comprise their respective ultrasonic signal features associated with the object height and / or material, but all comprise the same coordinates from the grid A1 , and the same ultrasonic signal features associated with the object distance from the grid C1 .

[0072] In another example, features with different resolutions may be aggregated based on the first resolution used by the sample point plane coordinates. For example, as shown in the example of FIG. 5A, with the first resolution A as a reference, four ultrasonic signal features associated with the height and / or material of the object that are gridded by the second resolution B may be corresponded to plane coordinates of a single sample point that are gridded by the first resolution A, and a single ultrasonic signal feature associated with the distance to the object that is gridded by the third resolution C may be corresponded to four sample point plane coordinates gridded by the first resolution A . That is, the features of the grid A1 comprise its own plane coordinates, ultrasonic signal features associated with the height and / or material of the object from the grids B1 to B4, and ultrasonic signal features associated with the distance to the object from the grid C1 . When it comes to the case of corresponding multiple grids to one grid, for example, when the ultrasonic signal features associated with the object height and / or material from the grids B1 to B4 are to be used as the ultrasonic signal features associated with the object height and / or material of the grid A1 , various pooling operations, averaging or weighted averaging operations may be used again to process the data from multiple grids to remove redundancy.

[0073] Additionally or alternatively, when the grids generated by multiple different resolutions do not maintain an integer multiple relationship, the boundaries between grids of different resolutions may not align. As a result, some grids may overlap with multiple grids of other resolutions. FIG. 5B is another schematic diagram of grids of different resolutions according to examples of the present disclosure. As shown in FIG. 5B, the grid size of the first resolution A may be 10x10 cm, and the grid size of the second resolution B may be 15x15 cm. When the features gridded at the second resolution are aggregated based on the first resolution, a smaller grid may overlap with multiple larger grids. For example, the grid A4 may cover different area sizes from the grids B1 to B4. In this case, methods such as various pooling operations, averaging or weighted averaging operations (for example, weighting by the overlapping area of the grids) may be used again to process the data from multiple grids.

[0074] Additionally or alternatively, when the sample point plane coordinates and a portion of the ultrasonic signal features associated with the sample point are gridded at corresponding resolutions, the preprocessing module 430 may first aggregate the gridded feature data of different resolutions in a manner similar to that described above, and then normalize or smooth the aggregated feature data.

[0075] In one example, the preprocessing module 430 is optional and may be omitted and the gridded ultrasonic sample set is directly input into the clustering module 440.

[0076] In the example shown in FIG. 4, the preprocessed ultrasonic sample set may be used as the input of the clustering module 440, and the clustering module 440 performs clustering based on the gridded sample point plane coordinates of each ultrasonic sample in the ultrasonic sample set and a portion of the ultrasonic signal features associated with the sample point to obtain sample clusters C1 to C7.

[0077] In one example, the gridded or further preprocessed ultrasonic sample set may have a variety of different representations. For example, the ultrasonic sample set may be represented as a two-dimensional graph, wherein each point in the two-dimensional graph represents a grid, each point may have several features, each feature may have multiple dimensions, and the multiple features may comprise the gridded or further preprocessed sample point plane coordinates obtained in combination with the above-described operations and a portion of the ultrasonic signal features associated with the sample point. For another example, the ultrasonic sample set may be represented as a high-dimensional array, and the data in a single grid may have, for example, the following array form: [X coordinate, Y coordinate, echo round-trip distance, echo height, echo amplitude, echo significance, ...]. If the corresponding data item does not exist in the current grid, the item is set to zero. For another example, the ultrasonic sample set may be represented as a sparse matrix, the data of which is essentially a multi-dimensional tensor, which can be regarded as a collection of multi-dimensional arrays of all grids corresponding to the current spatial range in the previous example.

[0078] The clustering module 440 may perform clustering based on the preprocessed sample point plane coordinates and at least a portion of the ultrasonic signal features associated with the sample points. Specifically, the clustering module 440 may determine a group of sample points as a sample cluster not only based on the sufficiently close plane positions of samples, but also based on the sample points having sufficiently close features such as height, echo amplitude / significance, echo distance, etc.

[0079] In one example, the clustering module 440 may cluster one or more of the ultrasonic echo samples and the ultrasonic echo intersection samples. When the gridding and / or preprocessing is performed based on the ultrasonic echo samples, the ultrasonic echo intersection samples may be first calculated based on the processed ultrasonic echo samples, and then the clustering may be performed. Since the density of the ultrasonic echo intersection data is greater and the distance between different ultrasonic echo intersection data is greater, clustering based on the ultrasonic echo intersection data may have certain advantages over clustering based on both the ultrasonic echo data and the ultrasonic echo intersection data, which is conducive to obtaining better clustering results and making it easier to eliminate noise.

[0080] In one example, the clustering module 440 may use Density-Based Spatial Clustering of Applications with Noise (DBSCAN) to cluster at least part of the ultrasonic data. DBSCAN is a density-based clustering algorithm that defines a cluster as the largest set of density-connected points, can divide areas with sufficiently high density into clusters, and can find clusters of any shape in a noisy spatial database. DBSCAN does not require prior knowledge of the number of clusters to be formed, can identify clusters of any shape, and is capable of detecting noise points. Given the complex environments that the technical solution of the present disclosure may encounter in specific application scenarios, for example, parking lots may contain obstacle areas of various shapes and sizes, the collected ultrasonic data may contain various noises, and the number of objects within the spatial range can vary, with the possibility of having zero or more obstacles. The above-mentioned characteristics of DBSCAN are therefore particularly well-suited to the technical solution of the present disclosure. DBSCAN is a clustering method known in the art. Therefore, its specific details are not described in detail. It can be understood that other appropriate clustering methods may also be used in the clustering module 440, and the technical solution of the present disclosure is not limited to DBSCAN.

[0081] The clustered ultrasonic sample set may comprise zero or more sample clusters. When zero sample clusters are included in the spatial range, it indicates that there is no object in the current surroundings of the vehicle. When one or more sample clusters are included in the spatial range, each sample cluster may correspond to an object in the surroundings of the vehicle. As shown in FIG. 4, sample clusters C1 , C2, C3 and C4 may correspond to walls 370-1 to 370-4 in FIG. 3A, sample clusters C5 and C6 may correspond to vehicles 340-1 and 340-2 in FIG. 3A, and sample cluster C7 may correspond to a portion of lawn 360 in FIG. 3A. Since in the clustering of the present disclosure, not only the planar position information of the sample points but also the ultrasonic signal features of the sample points with respect to the object are considered, compared with the dotted line frame 380 shown in FIG. 3B, the sample clusters C1 to C7 shown in FIG. 4 more accurately distinguish the sample points for different objects.

[0082] In one example, target segmentation may be further performed based on one or more sample clusters to perform subsequent operations such as object position prediction. Compared with clustering based on only the planar position information of the sample points, clustering based on the ultrasonic signal features of the sample points may provide more accurate and reliable sample clusters, thereby improving the performance of the vehicle’s assisted driving / parking and user experience.

[0083] FIG. 6 is a flow chart of a method for determining an object in the surroundings of a vehicle according to examples of the present disclosure.

[0084] At step 610, an ultrasonic sample set may be obtained based on ultrasonic data collected during vehicle movement, wherein each ultrasonic sample in the ultrasonic sample set comprises sample point plane coordinates and sample point ultrasonic signal features.

[0085] In one example, the ultrasonic data may be collected by an ultrasonic sensor while the vehicle moves for a period of time, and / or the ultrasonic data may be collected by an ultrasonic sensor while the vehicle moves for a distance. The ultrasonic sensor may vary in quantity, ranging from a single sensor to multiple sensors.

[0086] In one example, the ultrasonic sample set may comprise ultrasonic echo samples and / or ultrasonic echo intersection samples. The ultrasonic echo samples may comprise echo coordinates, sensor coordinates, an echo timestamp of the echo signal, an echo amplitude, an echo significance, an echo distance, an echo height, etc., and the ultrasonic echo intersection samples may comprise echo intersection coordinates, sensor coordinates, an echo intersection distance, an echo intersection height, an echo intersection deflection, an echo intersection amplitude, an echo intersection significance, adjacent echo intersection coordinates, an adjacent echo intersection height, an adjacent echo intersection distance, an adjacent echo intersection deflection, etc.

[0087] At step 620, optionally, a down-sampling or up-sampling algorithm may be used to process the ultrasonic sample set. In one example, the up-sampling algorithm includes but is not limited to interpolation, transposed convolution, up-pooling, and the downsampling algorithm includes but is not limited to random down-sampling, EasyEnsemble, BalanceCascade, or NearMiss, etc.

[0088] At step 630, the ultrasonic sample set may be gridded based on the sample point plane coordinates of each ultrasonic sample and at least a portion of the ultrasonic signal features of the sample point.

[0089] In one example, at least a portion of the ultrasonic signal features of the sample point may comprise ultrasonic signal features associated with the height of the object, such as echo height or echo intersection height, etc.; ultrasonic signal features associated with the material of the object, such as echo amplitude or echo intersection amplitude, echo significance or echo intersection significance, etc.; or ultrasonic signal features associated with the distance of the object, such as echo signal round-trip time, echo distance, echo intersection distance, etc.

[0090] In one example, the sample point plane coordinates of each ultrasonic sample and each of the ultrasonic signal features of at least a portion of the ultrasonic signal features of the sample point may be gridded at the same resolution.

[0091] In one example, the sample point plane coordinates of each ultrasonic sample and each of the ultrasonic signal features of at least a portion of the ultrasonic signal features of the sample point may be gridded at a corresponding resolution.

[0092] In one example, optionally, based on the sample point plane coordinates gridded at the corresponding resolutions and each of the ultrasonic signal features of at least a portion of the ultrasonic signal features of the sample point, aggregation may be performed as a gridded ultrasonic sample set at a minimum resolution among the corresponding resolutions or at a corresponding resolution for the sample point plane coordinates. At step 640, the gridded ultrasonic sample set may be preprocessed, optionally.

[0093] In one example, the aggregated sample point plane coordinates gridded at corresponding resolutions and at least a portion of the ultrasonic signal features of the sample point may be preprocessed, and the preprocessing may comprise normalization and / or smoothing.

[0094] In one example, each of the at least portion of the ultrasonic signal features of the gridded sample point of each ultrasonic sample may be normalized. Additionally, the gridded sample point plane coordinates of each ultrasonic sample may be normalized. For example, commonly used normalization algorithms include but are not limited to min-max normalization, z-normalization, nonlinear normalization, etc.

[0095] In one example, the gridded sample point plane coordinates of each ultrasonic sample and each of the ultrasonic signal features of at least a portion of the ultrasonic signal features of the sample point may be smoothed. For example, commonly used smoothing algorithms include, but are not limited to, maximum pooling, minimum pooling, average pooling, overlapping pooling, pyramid pooling, bilinear pooling, etc.

[0096] In one example, the respective preprocessed sample point plane coordinates and each of the at least portion of ultrasonic signal features of the sample point may be aggregated at a minimum resolution among the corresponding resolutions or at a corresponding resolution for the sample point plane coordinates to form a preprocessed ultrasonic sample set.

[0097] In one example, the gridded or preprocessed ultrasonic sample set has the form of any of the following: a two-dimensional map, a high-dimensional array, or a sparse matrix.

[0098] At step 650, the gridded ultrasonic sample set may be clustered based on the gridded sample point plane coordinates of each ultrasonic sample and at least a portion of the ultrasonic signal features of the sample point to obtain one or more sample clusters, wherein each sample cluster corresponds to an object in the surroundings of the vehicle.

[0099] In one example, the gridded ultrasonic sample set is further preprocessed, as described in step 640.

[0100] In one example, the gridded ultrasonic sample set is clustered by Density-Based Spatial Clustering of Applications with Noise (DBSCAN).

[0101] In one example, target segmentation is further performed based on one or more sample clusters to identify one or more objects in the surroundings of the vehicle. The vehicle’s driving route may be planned based on the identified one or more objects. For example, an empty parking space available for the vehicle may be detected based on the position prediction information of the object, and a route for the vehicle to enter the empty parking space may be planned. For another example, an obstacle may be detected based on the position prediction information of the object, and a vehicle route may be planned to avoid the obstacle.

[0102] FIG. 7 is a block diagram of a control system for a vehicle according to examples of the present disclosure.

[0103] The control system 700 may comprise one or more processors 710 and a memory 720. The memory 720 may store executable instructions. The processor 710 may execute the executable instructions stored or encoded in the memory 720, thereby implementing the various operations and / or functions described above in conjunction with FIGs. 1 to 6. Although not shown in FIG. 7, those skilled in the art may appreciate that the control system 700 may comprise various other components, such as various communication modules, bus modules, and possible user interface modules, and the like.

[0104] In some examples, the control system 700 may comprise the control unit 130 and / or the processing unit 115 shown in FIGs. 1 and 2.

[0105] Examples of the present disclosure also provides a vehicle. The vehicle may have an ultrasonic sensor such as that shown in FIG. 1 , which is used to transmit and receive ultrasonic signals. The vehicle may also have the control system 700 of FIG. 7.

[0106] The examples of the present disclosure also provide a machine-readable storage medium. The machine-readable storage medium may store executable instructions, and the executable instructions may implement the various operations and / or functions described above in conjunction with FIGs. 1 to 6 when executed by the processor. For example, the machine-readable storage medium may include, but is not limited to, Random Access Memory (RAM), Read-Only Memory (ROM), Electrically-Erasable Programmable Read-Only Memory (EEPROM), Static Random Access Memory (SRAM), hard disk, flash memory, and the like.

[0107] Examples of the present disclosure also provide a computer program product. The computer program product may comprise a computer program. The computer program, when executed by a processor, may implement the various operations and / or functions described above in conjunction with FIGs. 1 to 6.

[0108] The above-described specific examples of the present disclosure have been described. Other examples are within the scope of the appended Claims. In some cases, actions or steps described in the Claims can be performed in a different order than that of the examples and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require specific or continuous sequences to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or advantageous.

[0109] Not all steps and units depicted in the above-mentioned flowcharts and system diagrams are required; certain steps or units may be omitted based on actual needs. The device structures described in the above-mentioned examples can be physical or logical structures. That is, some units may be realized by the same physical entity, while others may be realized by multiple physical entities or may be jointly realized by certain components in multiple separate devices.

[0110] Throughout the present Description, the term “exemplary” means “serving as an example, instance, or illustration” and does not imply “preferred” or “advantageous” over other examples. Specific examples comprise specific details to facilitate understanding of the described technology. However, these technologies may be implemented without these specific details. In some instances, to avoid causing difficulties in understanding the concepts of the described examples, known structures and devices are shown in block diagram form.

[0111] The aforementioned description of the present disclosure is provided to allow any person of ordinary skill in the art to implement or use the present disclosure. Various modifications to the present disclosure will be apparent to those of ordinary skill 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 examples and designs described herein but is consistent with the broadest scope defined by the principles and novel features disclosed herein.

Claims

CLAIMS1. A method for determining an object in the surroundings of a vehicle based on an ultrasonic signal, comprising: obtaining an ultrasonic sample set based on ultrasonic data collected during vehicle movement, wherein each ultrasonic sample in the ultrasonic sample set comprises sample point plane coordinates and sample point ultrasonic signal features; gridding the ultrasonic sample set based on the sample point plane coordinates of each ultrasonic sample and at least a portion of the ultrasonic signal features of the sample point; and clustering the gridded ultrasonic sample set based on the gridded sample point plane coordinates of each ultrasonic sample and the at least portion of the ultrasonic signal features of the sample point to obtain one or more sample clusters, wherein each sample cluster corresponds to an object in the surroundings of the vehicle.

2. The method according to Claim 1 , wherein the ultrasonic data is collected by an ultrasonic sensor when the vehicle moves for a period of time, and / or the ultrasonic data is collected by an ultrasonic sensor when the vehicle moves a distance.

3. The method according to Claim 1 , wherein the ultrasonic samples comprise ultrasonic echo samples and / or ultrasonic echo intersection samples.

4. The method according to Claim 1 , wherein the gridding of the ultrasonic sample set based on the sample point plane coordinates of each ultrasonic sample and at least a portion of the ultrasonic signal features of the sample point comprises: gridding the sample point plane coordinates of each ultrasonic sample and the at least portion of the ultrasonic signal features of the sample point at a corresponding resolution.

5. The method according to Claim 4, further comprising: based on the sample point plane coordinates gridded at the correspondingresolutions and each of the ultrasonic signal features of the at least portion of the ultrasonic signal features of the sample point, aggregating at the minimum resolution among the corresponding resolutions or at a corresponding resolution for the sample point plane coordinates as the gridded ultrasonic sample set.

6. The method according to Claim 1 , wherein the at least portion of the ultrasonic signal features of the sample point comprise one or more of the following: an ultrasonic signal feature associated with the height of the object; an ultrasonic signal feature associated with the material of the object; or an ultrasonic signal feature associated with the distance from the object.

7. The method according to Claim 1 , further comprising: at least normalizing each of the ultrasonic signal features of the at least portion of the ultrasonic signal features of the sample point of each ultrasonic sample; wherein, clustering the ultrasonic sample set based on the gridded sample point plane coordinates of each ultrasonic sample and the at least portion of ultrasonic signal features of the sample point comprises: clustering based on the normalized ultrasonic sample set.

8. The method according to Claim 1 , further comprising: smoothing the gridded sample point plane coordinates of each ultrasonic sample and each of the ultrasonic signal features of the at least portion of ultrasonic signal features of the sample point; wherein, clustering the ultrasonic sample set based on the gridded sample point plane coordinates of each ultrasonic sample and the at least portion of ultrasonic signal features of the sample point comprises: clustering based on the smoothed ultrasonic sample set.

9. The algorithm according to Claim 1 , wherein the gridded ultrasonic sample set has the form of any one of the following: a two-dimensional map, a high-dimensional array, or a sparse matrix.

10. The algorithm according to Claim 1 , further comprising: processing the ultrasonic sample set using a down-sampling or up-sampling algorithm, and gridding based on the down-sampled or up-sampled ultrasonic sample set.

11. The method according to Claim 1 , wherein clustering the gridded ultrasonic sample set based on the gridded sample point plane coordinates of each ultrasonic sample and the at least portion of ultrasonic signal features of the sample point comprises: clustering the gridded ultrasonic sample set by Density-Based Spatial Clustering of Applications with Noise (DBSCAN).

12. The method according to Claim 1 , further comprising: performing target segmentation based on the one or more sample clusters to identify one or more objects in the surroundings of the vehicle.

13. 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, wherein the executable instructions, when executed by the at least one processor, allow the at least one processor to implement the method according to any one of Claims 1 to 12.

14. A computer-readable medium storing a computer program comprising instructions, wherein the instructions, when executed by the processor, cause one or more units to perform the method according to any one of Claims 1 to 12.

15. A computer program product comprising a computer program, wherein the computer program, when executed by a processor, implement the method according to any one of Claims 1 to 12.

16. A vehicle, comprising:an ultrasonic sensor for transmitting and receiving an ultrasonic signal; and one or more units for performing the method according to any one of Claims 1 to 12.

Images