Radar-based obstacle detection method and device and electronic equipment

Abstract

The invention provides a radar-based obstacle detection method and device, electronic equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: determining a target environment scene where a radar is located from multiple environment scenes; determining a target distance interval corresponding to the echo signal received by the radar in the target environment scene; determining an obstacle detection threshold corresponding to the target environment scene and the target distance interval; wherein the obstacle detection threshold value is in negative correlation with the noise degree in the environment scene, and the obstacle detection threshold value is in positive correlation with the distance interval; and performing signal analysis on the echo signal according to the determined obstacle detection threshold to obtain an obstacle detection result. The obstacle detection threshold value is adjusted by comprehensively considering the environment scene and the distance interval, and the accuracy of obstacle detection can be improved.

Description

Technical Field

[0001] The present application relates to radar technology, and in particular to a radar-based obstacle detection method, device, electronic device, computer-readable storage medium, and computer program product. Background Art

[0002] The principle of radar is mainly the reflection mechanism of electromagnetic wave signals. The radar transmitter will emit detection signals outward. These detection signals will be reflected when encountering objects, and the reflected echo signals will be captured by the radar receiver. Radar is widely used in many fields, including automobiles, consumer electronics, industrial testing, medical care, and smart homes. For example, in the automotive industry, radar is widely used in assisted driving and autonomous driving systems, such as adaptive cruise control (ACC), collision warning (FCW), blind spot detection (BSD), automatic emergency braking (AEB), etc.

[0003] Obstacle detection is an important application of radar. Specifically, the obstacle situation in the outside world is obtained by analyzing the characteristics of the echo signal received by the radar receiver. However, in the solutions provided by the relevant technologies, a fixed obstacle detection threshold is usually used to implement obstacle detection, which leads to low obstacle detection accuracy and cannot adapt to complex and changing actual situations. Summary of the invention

[0004] The present application provides a radar-based obstacle detection method, device, electronic device, computer-readable storage medium and computer program product, which can improve the accuracy of obstacle detection by adjusting the obstacle detection threshold by comprehensively considering environmental scenarios and distance intervals.

[0005] The technical solution of this application is implemented as follows:

[0006] The present application provides a radar-based obstacle detection method, comprising:

[0007] Determining a target environment scene where the radar is located from a plurality of environment scenes; wherein the plurality of environment scenes respectively contain different noise levels;

[0008] Determining a target distance interval corresponding to an echo signal received by the radar in the target environment scene; wherein the echo signal is obtained by reflecting a detection signal emitted by the radar in the target distance interval; and the target distance interval includes at least part of a plurality of distance intervals;

[0009] Determining an obstacle detection threshold corresponding to the target environment scene and the target distance interval; wherein the obstacle detection threshold is negatively correlated with the noise level in the environment scene, and the obstacle detection threshold is positively correlated with the distance interval;

[0010] The echo signal is analyzed according to the determined obstacle detection threshold to obtain an obstacle detection result.

[0011] The present application provides a radar-based obstacle detection device, comprising:

[0012] An environmental scene determination module, used to determine the target environmental scene where the radar is located from a plurality of environmental scenes; wherein the plurality of environmental scenes respectively contain different noise levels;

[0013] a distance interval determination module, configured to determine, in the target environment scene, a target distance interval corresponding to the echo signal received by the radar; wherein the echo signal is obtained by reflecting the detection signal emitted by the radar in the target distance interval; and the target distance interval includes at least part of a plurality of distance intervals;

[0014] A threshold determination module, used to determine an obstacle detection threshold corresponding to the target environment scene and the target distance interval; wherein the obstacle detection threshold is negatively correlated with the noise level in the environment scene, and the obstacle detection threshold is positively correlated with the distance interval;

[0015] The signal analysis module is used to perform signal analysis on the echo signal according to the determined obstacle detection threshold to obtain an obstacle detection result.

[0016] The present application provides an electronic device, including:

[0017] A memory for storing executable instructions;

[0018] The processor is used to implement the radar-based obstacle detection method provided in the present application when executing the executable instructions stored in the memory.

[0019] The present application provides a computer-readable storage medium storing executable instructions for causing a processor to execute instructions to implement the radar-based obstacle detection method provided by the present application.

[0020] The present application provides a computer program product, which includes executable instructions for causing a processor to execute and implement the radar-based obstacle detection method provided by the present application.

[0021] This application has the following beneficial effects:

[0022] On the one hand, the present application determines the target environment scene where the radar is located from a variety of environment scenes, wherein the multiple environment scenes respectively contain different noise levels, and the obstacle detection threshold is negatively correlated with the noise level in the environment scene; on the other hand, the target distance interval corresponding to the echo signal received by the radar is determined in the target environment scene, wherein the target distance interval includes at least part of a plurality of distance intervals, and the obstacle detection threshold is positively correlated with the distance interval. Then, the obstacle detection threshold corresponding to the target environment scene and the target distance interval is determined, and the echo signal is analyzed according to the determined obstacle detection threshold to obtain an obstacle detection result. The present application adjusts the obstacle detection threshold by comprehensively considering the environment scene and the distance interval, which can improve the degree of compliance of the obstacle detection threshold with the current situation, thereby improving the accuracy of obstacle detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 is a schematic diagram of the architecture of a radar-based obstacle detection system provided in an embodiment of the present application;

[0025] Figure 2 is a structural schematic diagram of a vehicle-mounted device provided in an embodiment of the present application;

[0026] Figure 3A is a first flow chart of a radar-based obstacle detection method provided in an embodiment of the present application;

[0027] Figure 3B is a second flow chart of the radar-based obstacle detection method provided in an embodiment of the present application;

[0028] Figure 4 is a schematic diagram of the distance interval provided in the embodiment of the present application;

[0029] Figure 5 is a third flow chart of the radar-based obstacle detection method provided in an embodiment of the present application;

[0030] Figure 6 is a first schematic diagram of radar deployment provided in an embodiment of the present application;

[0031] Figure 7 is a second schematic diagram of radar deployment provided in an embodiment of the present application;

[0032] Figure 84 is a schematic diagram of a fourth process flow of a radar-based obstacle detection method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0034] In the following description, reference is made to "some embodiments", which describes a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict. In the following description, reference is made to the term "multiple" to mean at least two.

[0035] In the following description, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0036] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0037] The embodiments of the present application provide a radar-based obstacle detection method, device, electronic device, computer-readable storage medium, and computer program product, which can improve the accuracy of obstacle detection by adjusting the obstacle detection threshold by comprehensively considering the environmental scene and the distance interval. The following describes an exemplary application of the electronic device provided by the embodiments of the present application. The electronic device provided by the embodiments of the present application can be implemented as various types of terminal devices, such as an independent radar system or a vehicle-mounted device connected to a vehicle-mounted radar, etc.; the electronic device can also be implemented as a server.

[0038] Take the deployment of radar on a vehicle as an example, see Figure 1 , Figure 1 It is a schematic diagram of the architecture of the radar-based obstacle detection system 100 provided in an embodiment of the present application. The vehicle-mounted device 400 is connected to the server 200 via the network 300, wherein the network 300 can be a wide area network or a local area network, or a combination of the two.

[0039] In some embodiments, taking the electronic device as a terminal device as an example, the obstacle detection method based on radar provided in the embodiment of the present application can be implemented by the terminal device. For example, the vehicle-mounted device 400 determines the target environment scene where the radar is located from a variety of environment scenes; determines the target distance interval corresponding to the echo signal received by the radar in the target environment scene; determines the obstacle detection threshold corresponding to the target environment scene and the target distance interval; and performs signal analysis on the echo signal according to the determined obstacle detection threshold to obtain the obstacle detection result. The vehicle-mounted device 400 can use the obstacle detection result for assisted driving and automatic driving systems, such as adaptive cruise control (ACC), collision warning (FCW), blind spot detection (BSD), automatic emergency braking (AEB), etc. Taking the door opening obstacle avoidance as an example, when the vehicle-mounted device 400 receives the door opening operation for the vehicle, it determines whether the current obstacle detection result meets the door opening condition, and when the current obstacle detection result meets the door opening condition, controls the vehicle door to open, so that the safety of the door opening can be guaranteed and the accidental bump of the door can be avoided. In the above method, the vehicle-mounted device 400 implements obstacle detection locally without transmitting data to a remote server for processing, which can greatly reduce the time and delay of data transmission; it is not restricted by network conditions, which is especially important when the network environment is unstable or the network cannot be connected, and can ensure the availability of the obstacle detection function.

[0040] In some embodiments, taking the electronic device as a server as an example, the radar-based obstacle detection method provided in the embodiment of the present application can be implemented by the server. For example, the vehicle-mounted device 400 can send radar-related data (such as echo signals) to the server 200 so that the server 200 can perform obstacle detection. The server 200 can send the obstacle detection result to the vehicle-mounted device 400 so that the vehicle-mounted device 400 generates and executes a vehicle control instruction (such as an instruction to control the opening of the vehicle door) according to the obstacle detection result; or, the server 200 can generate a vehicle control instruction according to the obstacle detection result, and send the vehicle control instruction to the vehicle-mounted device 400 so that the vehicle-mounted device 400 executes it. In the above manner, the server 200 usually has powerful computing power and storage resources, can realize efficient obstacle detection, and can provide obstacle detection functions for multiple vehicle-mounted devices at the same time; the vehicle-mounted device 400 is mainly responsible for data collection, data transmission, and instruction execution, etc., without having to undertake complex computing tasks, which can reduce the computing pressure of the vehicle-mounted device 400 and expand the scope of application.

[0041] In some embodiments, the vehicle-mounted device 400 or the server 200 can implement the radar-based obstacle detection method provided in the embodiments of the present application by running a computer program. For example, the computer program can be a native program or software module in the operating system; it can be a native application (APP, Application), that is, a program that needs to be installed in the operating system to run; it can also be a small program, that is, a program that can be run only by downloading it to a browser environment; it can also be a small program that can be embedded in any APP, and the small program can be controlled to run or closed by the user. In short, the above-mentioned computer program can be an application, module or plug-in in any form.

[0042] In some embodiments, the electronic device may also be implemented as an independent radar system, which includes the radar itself and electronic devices for calculating radar-related data (such as echo signals). The radar system can independently implement obstacle detection and can communicate data with other electronic devices (such as vehicle-mounted devices), such as receiving obstacle detection instructions sent by other electronic devices (obstacle detection instructions are used to trigger obstacle detection) and / or sending obstacle detection results to other electronic devices.

[0043] It is worth noting that in the embodiments of the present application, the radar can be regarded as a part of the electronic device, or the radar can be regarded as an external device independent of the electronic device.

[0044] Taking the electronic device provided in the embodiment of the present application as an example, which is a vehicle-mounted device, it can be understood that in the case where the electronic device is a server, Figure 2 Parts of the structure shown in FIG. 1 (such as a user interface, a presentation module, and an input processing module) may be omitted. Figure 2 , Figure 2 is a structural diagram of a vehicle-mounted device 400 provided in an embodiment of the present application, Figure 2 The vehicle-mounted device 400 shown includes: at least one processor 410, a memory 450, at least one network interface 420 and a user interface 430. The various components in the vehicle-mounted device 400 are coupled together via a bus system 440. It is understood that the bus system 440 is used to achieve connection and communication between these components. In addition to the data bus, the bus system 440 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, the bus system 440 is not described in detail. Figure 2 Various buses are labeled as bus system 440 .

[0045] Processor 410 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., where the general-purpose processor can be a microprocessor or any conventional processor, etc.

[0046] The user interface 430 includes one or more output devices 431 that enable presentation of media content, including one or more speakers and / or one or more visual display screens. The user interface 430 also includes one or more input devices 432, including user interface components that facilitate user input, such as a touch screen display, a camera, other input buttons and controls.

[0047] The memory 450 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state memory, hard disk drives, optical disk drives, etc. The memory 450 may optionally include one or more storage devices that are physically remote from the processor 410.

[0048] The memory 450 includes a volatile memory or a non-volatile memory, and may also include both volatile and non-volatile memories. The non-volatile memory may be a read-only memory (ROM), and the volatile memory may be a random access memory (RAM). The memory 450 described in the embodiments of the present application is intended to include any suitable type of memory.

[0049] In some embodiments, memory 450 can store data to support various operations, examples of which include programs, modules, and data structures, or a subset or superset thereof, as exemplarily described below.

[0050] Operating system 451, including system programs for processing various basic system services and performing hardware-related tasks, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks;

[0051] A network communication module 452, used to reach other electronic devices via one or more (wired or wireless) network interfaces 420, exemplary network interfaces 420 include: Bluetooth, Wireless Compatibility Certification (WiFi), and Universal Serial Bus (USB), etc.;

[0052] a presentation module 453 for enabling presentation of information via one or more output devices 431 (e.g., display screen, speaker, etc.) associated with the user interface 430 (e.g., a user interface for operating peripherals and displaying content and information);

[0053] The input processing module 454 is used to detect one or more user inputs or interactions from one of the one or more input devices 432 and translate the detected inputs or interactions.

[0054] In some embodiments, the radar-based obstacle detection device provided in the embodiments of the present application can be implemented in a software manner. Figure 2 The radar-based obstacle detection device 455 stored in the memory 450 is shown, which can be software in the form of a program and a plug-in, etc., including the following software modules: an environment scene determination module 4551, a distance interval determination module 4552, a threshold determination module 4553 and a signal analysis module 4554. These modules are logical, so they can be arbitrarily combined or further split according to the functions implemented. The functions of each module will be explained below.

[0055] The radar-based obstacle detection method provided in the embodiment of the present application will be described in conjunction with the exemplary application and implementation of the electronic device provided in the embodiment of the present application.

[0056] See also Figure 3A , Figure 3A is a flow chart of a radar-based obstacle detection method provided in an embodiment of the present application, which will be combined with Figure 3A The steps shown are explained.

[0057] In step 101, a target environment scene where a radar is located is determined from a plurality of environment scenes; wherein the plurality of environment scenes respectively contain different noise levels.

[0058] Here, multiple environmental scenes can be pre-divided, and each of the multiple environmental scenes contains different noise levels. For example, the environmental scenes include a single target scene in an open environment and a large-area single material (such as a wall, iron plate, fence, etc.) scene. For a single target (target is an obstacle) scene in an open environment, the proportion of objects that can reflect signals in the scene is small, so the scene contains a small degree of noise; for a large-area single material scene, the proportion of objects that can reflect signals in the scene is large, so the scene contains a large degree of noise.

[0059] On the basis of having divided multiple environmental scenes, the target environmental scene where the radar is located is determined from the multiple environmental scenes, that is, the target environmental scene is one of the multiple environmental scenes. For example, the radar can be used to perform scene recognition processing to obtain the target environmental scene where the radar is located, that is, the radar transmitter transmits a detection signal, the radar receiver receives an echo signal, and the target environmental scene where the radar is located is determined based on the echo signal; for another example, the target environmental scene where the radar is located can be determined by other sensors, such as if the radar and the camera are deployed on the same vehicle, then the camera can be used to perform scene recognition processing (that is, the camera takes an image and recognizes the environmental scene in the image) to obtain the target environmental scene where the camera is located, and the target environmental scene where the camera is located is the target environmental scene where the radar is located.

[0060] The embodiment of the present application does not limit the type of radar involved, for example, it may be a millimeter wave radar or an ultrasonic radar.

[0061] In step 102, a target distance interval corresponding to an echo signal received by the radar is determined in a target environment scene; wherein the echo signal is obtained by reflecting a detection signal emitted by the radar in the target distance interval; and the target distance interval includes at least part of a plurality of distance intervals.

[0062] After the radar transmitter transmits the detection signal, the radar receiver receives the echo signal, and the target distance interval corresponding to the echo signal is further analyzed, that is, the echo signal is obtained by reflecting the detection signal emitted by the radar in the target distance interval. It is worth noting that the "distance" involved in the embodiment of the present application refers to the distance from the radar; the target distance interval includes at least part of multiple distance intervals, where multiple distance intervals can be pre-divided according to actual conditions, and different distance intervals do not overlap with each other, such as Figure 4 As shown, three distance intervals can be divided, namely (0m, 1m], (1m, 2m], and (2m, 3m].

[0063] In step 103, an obstacle detection threshold corresponding to the target environment scene and the target distance interval is determined; wherein the obstacle detection threshold is negatively correlated with the noise level in the environment scene, and the obstacle detection threshold is positively correlated with the distance interval.

[0064] Here, the obstacle detection threshold is used to constrain the echo parameters determined according to the echo signal. The echo parameters are positively correlated with the probability of the existence of obstacles, wherein the specific content of the echo parameters is not limited. The principle of signal analysis can be summarized as follows: when the echo parameters are greater than the obstacle detection threshold, it is determined that an obstacle is detected; when the echo parameters are less than or equal to the obstacle detection threshold, it is determined that no obstacle is detected.

[0065] On the one hand, the obstacle detection threshold is negatively correlated with the noise level in the environmental scene. The reason is that the greater the noise level in the environmental scene, the greater the impact of the noise on the echo parameters (for example, the greater the proportion of the echo signal as noise), which will cause the echo parameters to be smaller, so the obstacle detection threshold needs to be adjusted accordingly; on the other hand, the obstacle detection threshold is positively correlated with the distance interval. The reason is that the smaller the distance interval (that is, the closer to the radar), the greater the impact of the noise in the distance interval on the echo parameters (for example, the greater the echo intensity of the echo signal as noise), which will cause the echo parameters to be smaller, so the obstacle detection threshold needs to be adjusted accordingly.

[0066] In the embodiment of the present application, since the target environment scene and the target distance interval have been determined, the obstacle detection threshold corresponding to the target environment scene and the target distance interval can be determined.

[0067] In step 104, the echo signal is analyzed according to the determined obstacle detection threshold to obtain an obstacle detection result.

[0068] Here, the echo parameter is determined according to the echo signal, and the obstacle detection result is obtained according to the magnitude relationship between the obstacle detection threshold and the echo parameter. The obstacle detection result is used to indicate whether an obstacle is detected in the target distance interval of the target environment scene. For example, when the echo parameter is greater than the obstacle detection threshold corresponding to the target environment scene and the target distance interval, the obstacle detection result is determined to be a detected obstacle; when the echo parameter is less than or equal to the obstacle detection threshold corresponding to the target environment scene and the target distance interval, the obstacle detection result is determined to be a non-detected obstacle.

[0069] It is worth noting that the target distance interval may include only one distance interval or multiple distance intervals. For the latter case, obstacle detection needs to be performed separately for each distance interval in the target distance interval. For example, distance interval 1, distance interval 2 and distance interval 3 are pre-set, and the target distance interval includes distance interval 1 and distance interval 2. Then, for distance interval 1, the obstacle detection threshold corresponding to the target environment scene and distance interval 1 is determined, and the echo signal reflected in distance interval 1 is analyzed according to the obstacle detection threshold to obtain the obstacle detection result corresponding to distance interval 1. The obstacle detection result corresponding to distance interval 1 is used to characterize whether an obstacle is detected in distance interval 1 of the target environment scene. Similarly, the obstacle detection result corresponding to distance interval 2 can be obtained.

[0070] It is worth noting that the above steps 101 to 104 describe a one-frame (or one-time) obstacle detection process, and obtain a one-frame obstacle detection result, which is used to characterize whether an obstacle is detected in the target distance interval of the target environment scene at the corresponding moment. In some embodiments, the above steps 101 to 104 can be performed periodically to obtain multiple frames of obstacle detection results, and then the multiple frames of obstacle detection results are analyzed to obtain the final obstacle detection result, that is, a multi-frame obstacle detection algorithm is used. This method can reduce the misjudgment caused by noise in a single frame of data and improve the accuracy of the final obstacle detection result.

[0071] In some embodiments, in addition to indicating whether an obstacle is detected, the obstacle detection result may also include obstacle information of the detected obstacle, such as the distance between the obstacle and the radar.

[0072] like Figure 3A As shown, the embodiment of the present application, on the one hand, determines the target environment scene where the radar is located from a variety of environment scenes, wherein the multiple environment scenes respectively contain different noise levels, and the obstacle detection threshold is negatively correlated with the noise level in the environment scene; on the other hand, determines the target distance interval corresponding to the echo signal received by the radar in the target environment scene, wherein the target distance interval includes at least part of a plurality of distance intervals, and the obstacle detection threshold is positively correlated with the distance interval. Then, the obstacle detection threshold corresponding to the target environment scene and the target distance interval is determined, and the echo signal is analyzed according to the determined obstacle detection threshold to obtain an obstacle detection result. The embodiment of the present application adjusts the obstacle detection threshold by comprehensively considering the environment scene and the distance interval, which can improve the degree of compliance of the obstacle detection threshold with the current situation, thereby improving the accuracy of obstacle detection.

[0073] In some embodiments, see Figure 3B , Figure 3B is a flow chart of a radar-based obstacle detection method provided in an embodiment of the present application. Figure 3A The illustrated step 104 can be implemented through steps 201 to 205 , which will be described in conjunction with each step.

[0074] In step 201, the field of view angle of the radar is divided into multiple sub-field of view angles.

[0075] The field of view (FOV) refers to the maximum angle range that the radar beam can reach through the scanning device, and is an important indicator for measuring the radar's sensing range. Here, the radar's field of view is divided and processed to obtain multiple sub-fields of view, wherein the division method is not limited, for example, it can be equally divided into N sub-fields of view, and the specific value of N can be set according to actual conditions.

[0076] In step 202, the echo signal is divided and processed according to a plurality of sub-viewing angles to obtain an echo signal corresponding to each sub-viewing angle.

[0077] The number of echo signals received by the radar usually includes multiple. In the case where multiple sub-viewing angles have been divided, the echo signals are divided and processed according to the multiple sub-viewing angles to obtain the echo signals corresponding to each sub-viewing angle. The echo signal corresponding to a sub-viewing angle essentially refers to the echo signal received by the radar after transmitting the detection signal according to the sub-viewing angle.

[0078] In step 203, the echo parameters corresponding to each sub-viewing angle are determined according to the echo signals corresponding to each sub-viewing angle.

[0079] Here, the echo signal corresponding to each sub-viewing angle is calculated to obtain the echo parameter corresponding to each sub-viewing angle. The echo parameter corresponding to a certain sub-viewing angle can measure the probability of the obstacle existing in the sub-viewing angle.

[0080] In some embodiments, the above-mentioned determination of the echo parameters corresponding to each sub-field of view angle based on the echo signals corresponding to each sub-field of view angle can be achieved in the following manner: determining the intensity of the echo signals corresponding to each sub-field of view angle; comparing the intensity of the echo signal corresponding to any sub-field of view angle with the average of the intensities of the echo signals corresponding to other sub-field of view angles, to obtain the echo parameters corresponding to any sub-field of view angle.

[0081] For example, the radar's field of view is divided into sub-field of view 1, sub-field of view 2, and sub-field of view 3. Based on the known echo signal corresponding to each sub-field of view, the intensity of the echo signal corresponding to each sub-field of view can be determined. Then, if it is necessary to calculate the echo parameters corresponding to sub-field of view 1, first calculate the average of the intensity of the echo signal corresponding to sub-field of view 2 and the intensity of the echo signal corresponding to sub-field of view 3, and then compare the intensity of the echo signal corresponding to sub-field of view 1 with the above average (divide it) to obtain the echo parameters corresponding to sub-field of view 1. Similarly, the echo parameters corresponding to sub-field of view 2 and the echo parameters corresponding to sub-field of view 3 can be calculated.

[0082] It is understandable that if there is an obstacle at a certain sub-viewing angle, the obstacle will reflect the detection signal to form an echo signal, so the intensity of the echo signal corresponding to the sub-viewing angle will be greater, and the echo parameter corresponding to the sub-viewing angle will also be greater; if there is no obstacle at a certain sub-viewing angle, the intensity of the echo signal corresponding to the sub-viewing angle will be smaller, and the echo parameter corresponding to the sub-viewing angle will also be smaller. In summary, the probability of the existence of obstacles can be accurately measured through echo parameters, and the echo parameters corresponding to a sub-viewing angle are obtained by comparing the sub-viewing angle with other view angles in terms of echo intensity, which can comprehensively consider the overall situation and further improve accuracy.

[0083] In step 204, when the echo parameter corresponding to any sub-viewing angle is greater than the determined obstacle detection threshold, the obstacle detection result is determined to be a detected obstacle.

[0084] Here, when the echo parameter corresponding to any sub-viewing angle is greater than the obstacle detection threshold corresponding to the target environment scene and the target distance interval, the obstacle detection result is determined to be a detected obstacle.

[0085] In step 205, when the echo parameters corresponding to the plurality of sub-viewing angles are all less than or equal to the determined obstacle detection threshold, the obstacle detection result is determined to be no obstacle detected.

[0086] Here, when the echo parameters corresponding to all sub-viewing angles are less than or equal to the obstacle detection threshold corresponding to the target environment scene and the target distance interval, it is proved that no obstacle is detected in all sub-viewing angles, and therefore the obstacle detection result is determined to be no obstacle detected.

[0087] like Figure 3B As shown, the embodiment of the present application divides multiple sub-viewing angles, determines the echo parameters corresponding to each sub-viewing angle according to the echo signal corresponding to each sub-viewing angle, and determines the obstacle detection result according to the size relationship between the echo parameters corresponding to the sub-viewing angle and the obstacle detection threshold. By dividing the multiple sub-viewing angles, the meticulousness of the signal analysis can be improved, and the calculated echo parameters can more accurately measure the probability of the existence of obstacles in the corresponding sub-viewing angles, thereby further improving the obstacle detection accuracy.

[0088] In some embodiments, see Figure 5 , Figure 5 is a flow chart of a radar-based obstacle detection method provided in an embodiment of the present application, which will be combined with Figure 5 The steps shown are explained.

[0089] In step 301, in response to a door opening operation for a vehicle, it is determined whether a current obstacle detection result satisfies a door opening condition.

[0090] Here, the radar is deployed on the vehicle (such as an electric vehicle), and the obstacle detection result obtained by the radar can be used for door opening and obstacle avoidance, which will be described in detail below. Among them, the deployment position of the radar is not limited, for example, it can be deployed on the door and / or the roof.

[0091] Under the premise that the vehicle door is closed, when the vehicle door opening operation is received, the obstacle detection is triggered, such as executing Figure 3A Steps 101 to 104 are shown to obtain the current obstacle detection result. Then, it is determined whether the current obstacle detection result meets the door opening condition. The door opening condition can be set according to the actual situation, such as no obstacle is detected, or the distance between the detected obstacle and the radar is greater than the distance threshold (in this case, the obstacle will not collide with the opened door).

[0092] It is worth noting that the embodiment of the present application does not limit the triggering method of the door opening operation. For example, it can be triggered by the vehicle system, it can be triggered by the door opening hardware button inside the vehicle, or it can be triggered by the vehicle remote control key (at this time the user can be outside the vehicle).

[0093] In step 302, when the current obstacle detection result meets the door opening condition, the vehicle door is controlled to open.

[0094] When the current obstacle detection result meets the door opening condition, it proves that the door will not hit an obstacle during the opening process, so the vehicle door is controlled to open.

[0095] In some embodiments, in response to the door opening operation for the vehicle, after determining whether the current obstacle detection result meets the door opening condition, the radar-based obstacle detection method further includes: when the current obstacle detection result does not meet the door opening condition, outputting an alarm prompt. When the current obstacle detection result does not meet the door opening condition, the door may hit an obstacle during the opening process, so the vehicle door is not controlled to open, but an alarm prompt is output, thereby prompting the user to clear the obstacles around the vehicle or manually open the door to ensure safety. Among them, there is no limitation on the output method of the alarm prompt, for example, it can be output by the vehicle system in the form of sound or pop-up window.

[0096] In some embodiments, the radar-based obstacle detection method also includes: during the process of opening the vehicle door, determining whether the current obstacle detection result meets the door opening condition; when the current obstacle detection result meets the door opening condition, continuing to control the vehicle door opening; when the current obstacle detection result does not meet the door opening condition, stopping controlling the vehicle door opening.

[0097] Here, during the process of opening the vehicle door, obstacle detection can also be performed periodically to obtain obstacle detection results. When the current obstacle detection result (referring to the latest obstacle detection result) meets the door opening condition, it proves that the door is not expected to hit an obstacle, so the vehicle door continues to be controlled to open; when the current obstacle detection result does not meet the door opening condition, it proves that the door may hit an obstacle, so the vehicle door is stopped from opening, and an alarm can be output to prompt the user. The above method periodically performs obstacle detection during the process of opening the vehicle door, and determines whether to continue to control the vehicle door opening based on the current obstacle detection result. It is suitable for situations where the radar has a blind spot when the door is closed, or an obstacle suddenly appears during the door opening process, which can further improve safety.

[0098] In some embodiments, the radar includes a door radar and a roof radar; the above-mentioned response to the door opening operation of the vehicle to determine whether the current obstacle detection result meets the door opening condition can be achieved in the following manner: in response to the door opening operation of the vehicle, determine whether the current obstacle detection result obtained by the door radar and the obstacle detection result obtained by the roof radar meet the door opening condition; the above-mentioned during the opening process of the vehicle door to determine whether the current obstacle detection result meets the door opening condition can be achieved in the following manner: during the opening process of the vehicle door, determine whether the current obstacle detection result obtained by the door radar meets the door opening condition.

[0099] Here, the vehicle is deployed with a door radar and a roof radar. In this case, in response to the door opening operation for the vehicle, it is determined whether the obstacle detection results currently obtained by the door radar and the obstacle detection results obtained by the roof radar meet the door opening conditions. When the obstacle detection results currently obtained by the door radar and the obstacle detection results obtained by the roof radar both meet the door opening conditions, the vehicle's door is controlled to open; when the obstacle detection results currently obtained by the door radar or the obstacle detection results obtained by the roof radar do not meet the door opening conditions, the vehicle's door is not controlled to open, but an alarm prompt is output. In this way, the door radar and the roof radar are combined to achieve double insurance, strengthen the field of vision coverage of the vehicle's surroundings, and improve the safety of door opening. It is worth noting that the above-mentioned door radar may refer to the radar deployed for the door to be opened by the door opening operation, which can improve the pertinence of obstacle detection and avoid unnecessary resource consumption.

[0100] Then, during the process of opening the vehicle door, it is determined whether the obstacle detection result currently obtained by the door radar meets the door opening condition. When the obstacle detection result currently obtained by the door radar meets the door opening condition, the vehicle door opening is continued to be controlled; when the obstacle detection result currently obtained by the door radar does not meet the door opening condition, the vehicle door opening is stopped and an alarm is output at the same time. It is worth noting that the obstacle detection result obtained by the roof radar is not considered during the process of opening the vehicle door. The reason is that the area that can be detected by the roof radar usually does not change, and the door may be mistaken for an obstacle by the roof radar, which affects the door opening.

[0101] In some embodiments, when the vehicle door is opened, an opening completion prompt may be output to prompt the user.

[0102] like Figure 5 As shown, the embodiment of the present application responds to the door opening operation of the vehicle, determines whether the current obstacle detection result meets the door opening condition, and controls the vehicle door to open when the current obstacle detection result meets the door opening condition, thereby avoiding accidental bumps of the door and improving safety during the door opening process.

[0103] The following will describe an exemplary application of the embodiment of the present application in a practical application scenario. Taking the application scenario of door opening obstacle avoidance as an example, the embodiment of the present application mainly includes the following three parts: improving the detection performance of millimeter wave radar for stationary obstacles, determining the number and deployment location of radars, obstacle detection and door opening obstacle avoidance. The following will describe them separately.

[0104] 1) Improve the detection performance of millimeter-wave radar for stationary obstacles.

[0105] In the application scenario of door opening and obstacle avoidance, it is usually necessary to detect whether there are stationary (or low-speed) obstacles around the vehicle, and ultrasonic radar is usually used in traditional solutions. However, ultrasonic radar is easily interfered by high-frequency environmental noise, cannot detect irregular small objects, cannot detect right-angled sharp objects, etc., and has many limitations in obstacle detection functions. In addition, it is necessary to open holes in the car body when installing the ultrasonic radar, and it is very difficult to achieve waterproofness and reliability, especially when the ultrasonic radar is installed on the roof. In comparison, millimeter-wave radar has more performance advantages, so the embodiment of the present application can use millimeter-wave radar to achieve door opening and obstacle avoidance. As an example, the embodiment of the present application provides a performance comparison table as shown in Table 1.

[0106] Table 1 Performance comparison table

[0107]

[0108] In traditional solutions, although millimeter-wave radar can detect stationary objects, it requires the reflection cross-section of the stationary object to be large enough, such as a continuous metal guardrail, and a certain back-end fitting algorithm to achieve detection. Therefore, millimeter-wave radar has a weak ability to detect single stationary objects, especially small objects.

[0109] The embodiment of the present application is based on the traditional medium and long-range millimeter-wave radar, and optimizes the overall system solution, mainly including adjusting the transmission bandwidth of the millimeter-wave radar radio frequency and adjusting the obstacle detection algorithm.

[0110] First, according to the rule that the distance resolution is inversely proportional to the signal bandwidth, the transmission bandwidth of the millimeter wave radar is greatly improved, which is about 8-9 times that of the medium and long-range millimeter wave radar, in order to obtain a smaller detection resolution and accuracy, so that small stationary objects are easier to detect. The ultra-short-range millimeter wave radar obtained in this way can be better applied to the application scenario of door opening and obstacle avoidance. As an example, the embodiment of the present application provides a performance comparison table of three millimeter wave radars as shown in Table 2.

[0111] Table 2 Performance comparison of three millimeter wave radars

[0112]

[0113] Secondly, adjust the obstacle detection threshold X used by the obstacle detection algorithm ij .X ij The i in the code represents the environment scene, such as X 1j represents a single target scene in an open environment, X 2j Indicates a large area of ​​a single material scene, X 3j Indicates a large area of ​​a single material superimposed on a single other obstacle scene; X ij The j in the equation represents the distance interval. In different distance intervals, the obstacle detection threshold is different. For example, 11 , X 12 , X 13 , X 14 Indicates the obstacle detection thresholds corresponding to different distance intervals of a single target scene in an open environment.

[0114] Based on the test data of a large number of experiments, the obstacle detection threshold corresponding to each environmental scene and each distance interval can be obtained by comprehensive analysis of the impact of the installation of decorative panels, and an obstacle detection threshold matrix can be constructed so that when actually performing obstacle detection, the appropriate obstacle detection threshold can be selected from the obstacle detection threshold matrix. The obstacle detection threshold matrix is ​​as follows:

[0115]

[0116] Through the above method, stationary objects within a close distance can be accurately detected, which well meets the obstacle detection requirements of the application scenario of door opening and obstacle avoidance.

[0117] 2) Determine the number and deployment locations of radars.

[0118] Here, there are two factors that affect the deployment position of the radar. First, the shape and movement trajectory of the electric door. For example, the movement trajectory of the electric swing door is to open to both sides of the vehicle, so the radar is suitable for deployment on the doors on both sides; if the movement trajectory of the gull-wing door or scissor door is not only to open to both sides of the vehicle, but also to open upwards, the radar needs to be deployed not only on the doors on both sides, but also on the roof to detect obstacles on the roof. Second, the size of the detected area and the radar's field of view. Try to require the radar's field of view to cover the detected area as much as possible. If the radar's field of view is small, it is necessary to increase the number of radars. By deploying multiple radars, the reliability of the system can be increased through fusion perception.

[0119] The number of radars depends on the field of view angle and the detected area. Usually, the field of view angle of the radar is 60° to 100°. The radar deployment positions and quantities shown in Table 3 can be adopted. However, this does not constitute a limitation on the embodiments of the present application. In specific projects, it can be decided according to cost and performance requirements.

[0120] Table 3 Radar deployment locations and numbers

[0121]

[0122] As an example, for a vehicle with two electric swing doors at the front and two electric gullwing doors at the rear, the present application embodiment provides a combination of 10 ultrasonic radars and 2 ultra-short-range millimeter-wave radars to balance the cost and performance level to the greatest extent. Figure 6 The radar deployment diagram shown in the figure shows that two ultrasonic radars are installed on each front door. Figure 6 The rear doors are equipped with two ultrasonic radars within 3-15cm of the bottom of the door and more than 40cm from the empty ground line, and one ultrasonic radar is installed within 3-15cm of the rear edge of the door. Figure 6In the serial number ⑤-⑩, the ultrasonic radar can be installed on plastic parts to facilitate hole opening and installation positioning. If radars ⑦ and ⑩ cannot be installed on plastic parts, they can also be installed on the door sheet metal. After proper installation, positioning and waterproofing, two ultra-short-range millimeter-wave radars are installed between the two European-wing door beams on the roof. The two ultra-short-range millimeter-wave radars are 5-10cm away from the center axis of the beams. The two ultra-short-range millimeter-wave radars are 30-40cm away from the front and rear axles of the vehicle body. The two ultra-short-range millimeter-wave radars are installed below the plastic trim. The plastic trim does not contain any metallic paint or coating. Figure 6 In addition, the present application also provides the following examples: Figure 7 The radar deployment diagram shown is illustrated in a top view. It is worth noting that Figure 6 The digital sequence number in Figure 7 The numbers in the table may not have the same meaning. All ultrasonic radar signals can be connected to the ultrasonic radar control box, such as Figure 7 As shown in C in the figure, the ultrasonic radar control box can uniformly drive, control and resolve the ultrasonic radar signals to improve the system perception performance.

[0123] As mentioned above, although the overall detection performance of ultrasonic radar is not as good as that of ultra-short-range millimeter-wave radar, it is better in terms of mature technology and low price. By increasing the number of ultrasonic radars to achieve perception fusion, it can cope with most door obstacle avoidance needs and scenarios, and accurately detect obstacles such as walls, water barriers, bushes, wire mesh, pedestrians, and vehicles. Because the roof has a small installation space and waterproof requirements, a non-perforated ultra-short-range millimeter-wave radar is used, that is, 1-3 ultra-short-range millimeter-wave radars are used to cover the top detection area. In this way, performance and robustness are guaranteed, and cost optimization is achieved, and accurate detection of obstacles such as top walls, mechanical parking spaces, lamps, sprinkler heads, and road signs is achieved.

[0124] 3) Obstacle detection and door opening to avoid obstacles.

[0125] The logic of obstacle detection and door opening and obstacle avoidance functions of the door radar and the roof radar is slightly different. This is because the door radar moves with the door and needs to detect obstacles at all times when the door is opening. The roof radar is fixed on the roof, so after the vehicle stops, the area that the roof radar can detect usually does not change. In addition, the door may be mistaken for an obstacle by the roof radar, affecting the door opening.

[0126] As an example, the present application embodiment provides the following Figure 8 A flowchart of a radar-based obstacle detection method is shown in FIG. Figure 8 The logic of the door radar and roof radar in realizing obstacle detection and door opening and obstacle avoidance functions is explained respectively.

[0127] The logic of the door radar to realize obstacle detection and door opening and obstacle avoidance functions is as follows:

[0128] ① After the vehicle stops, the door control module or domain controller module responds to the door opening operation triggered by the user (for example, the user clicks the door opening button) and sends a radar enable signal POD_ObstDetcn to the door radar to start the obstacle detection function.

[0129] ② When the door radar receives the radar enable signal POD_ObstDetcn, it performs obstacle detection, obtains the obstacle detection result, and sends the obstacle detection result to the door control module or the domain controller module.

[0130] ③ The door control module or the domain controller module determines whether the obstacle detection results obtained by the door radar and the obstacle detection results obtained by the roof radar (if any) meet the door opening conditions.

[0131] ④ If the obstacle detection results obtained by the door radar and the obstacle detection results obtained by the roof radar both meet the door opening conditions, the door control module or the domain controller module controls the vehicle door to open; if the obstacle detection results obtained by the door radar or the obstacle detection results obtained by the roof radar do not meet the door opening conditions, the door control module or the domain controller module outputs an alarm prompt in the form of sound or pop-up window to prompt the user.

[0132] ⑤ During the door opening process, the door radar will periodically (continuously) detect obstacles. If an obstacle is detected, it will send a signal SensorC_EmergencyStopFL to request to stop opening the door.

[0133] ⑥ When the door control module or the domain controller module receives the signal SensorC_EmergencyStopFL, it immediately stops opening the door and outputs an alarm prompt in the form of sound or pop-up window to prompt the user.

[0134] The logic of the roof radar to achieve obstacle detection and door opening and obstacle avoidance functions is as follows:

[0135] ① After the vehicle stops, the door control module or domain controller module responds to the door opening operation triggered by the user (for example, the user clicks the door opening button) and sends a radar enable signal POD_ObstDetcn to the roof radar to start the obstacle detection function.

[0136] ② When the roof radar receives the radar enable signal POD_ObstDetcn, it performs obstacle detection, obtains the obstacle detection result, and sends the obstacle detection result to the door control module or domain controller module in the form of a signal.

[0137] ③ The door control module or the domain controller module determines whether the obstacle detection results obtained by the roof radar and the obstacle detection results obtained by the door radar (if any) meet the door opening conditions.

[0138] ④ If the obstacle detection results obtained by the roof radar and the obstacle detection results obtained by the door radar both meet the door opening conditions, the door control module or the domain controller module controls the vehicle door to open; if the obstacle detection results obtained by the roof radar or the obstacle detection results obtained by the door radar do not meet the door opening conditions, the door control module or the domain controller module outputs an alarm prompt in the form of sound or pop-up window to prompt the user.

[0139] ⑤ During the door opening process, the roof radar stops outputting signals or sets the signal status bit to invalid, that is, the door control module or domain controller module no longer monitors the signal output by the roof radar during this door opening process.

[0140] In some embodiments, to increase the reliability and stability of obstacle detection, the obstacle detection function of the radar can be turned on all the time, or turned on when the vehicle speed is lower than a threshold, so as to continuously monitor obstacles in the surrounding environment and achieve multi-frame obstacle detection. During this period, the signal status bit of the radar is always set to invalid until the radar enable signal is triggered, in which case the signal status bit of the radar is set to valid, so as to output the obstacle detection result. The advantage of the above strategy is that it can improve the accuracy of obstacle detection and avoid misjudgment due to single-frame data.

[0141] The embodiments of the present application can at least achieve the following technical effects:

[0142] 1) For the electric door opening process, ultra-short-range millimeter-wave radar technology is integrated to realize the automatic obstacle avoidance function; the embodiment of the present application makes full use of the performance of ultra-short-range millimeter-wave radar in detecting obstacles to ensure the safe and accurate execution of the automatic opening mechanism of the electric door in different situations and prevent the occurrence of collision accidents.

[0143] 2) It can enhance the intelligence level of the vehicle and significantly improve the comfort and sense of security of passengers; it not only meets the basic requirements of automatic obstacle avoidance when the electric door is opened, but also effectively prevents damage caused by accidental collisions, reduces the user's economic burden and waiting time for vehicle maintenance, and helps to reduce the complaint rate.

[0144] 3) It can improve the detection capability of small objects such as thin poles to avoid accidental collisions of car doors. For example, when the vehicle is parked in a narrow, low parking space with irregular obstacles, it can effectively prevent the electric door from hitting obstacles such as vehicles, pedestrians, fences, fire hydrants, chains, parallel square columns on both sides during the opening process. In addition, it can effectively prevent the electric door from hitting obstacles such as the ceiling, water pipes, height limit poles, lamp poles, sprinklers, etc. during the opening process.

[0145] 4) It only needs to integrate the corresponding software logic and complete software development and testing before it can be applied in the actual vehicle. The implementation cost is low and there is no need to significantly change the vehicle's hardware architecture.

[0146] The following is a description of an exemplary structure of a radar-based obstacle detection device 455 provided in an embodiment of the present application implemented as a software module. In some embodiments, for example, Figure 2 As shown, the software modules in the radar-based obstacle detection device 455 stored in the memory 450 may include: an environmental scene determination module 4551, which is used to determine the target environmental scene where the radar is located from a plurality of environmental scenes; wherein the plurality of environmental scenes respectively contain different noise levels; a distance interval determination module 4552, which is used to determine the target distance interval corresponding to the echo signal received by the radar in the target environmental scene; wherein the echo signal is obtained by reflecting the detection signal emitted by the radar in the target distance interval; the target distance interval includes at least part of the plurality of distance intervals; a threshold determination module 4553, which is used to determine the obstacle detection threshold corresponding to the target environmental scene and the target distance interval; wherein the obstacle detection threshold is negatively correlated with the noise level in the environmental scene, and the obstacle detection threshold is positively correlated with the distance interval; a signal analysis module 4554, which is used to perform signal analysis on the echo signal according to the determined obstacle detection threshold to obtain an obstacle detection result.

[0147] In some embodiments, the signal analysis module 4554 is also used to: divide the radar's field of view angle to obtain multiple sub-field of view angles; divide the echo signal according to the multiple sub-field of view angles to obtain an echo signal corresponding to each sub-field of view angle; determine the echo parameters corresponding to each sub-field of view angle according to the echo signal corresponding to each sub-field of view angle; when the echo parameter corresponding to any sub-field of view angle is greater than the determined obstacle detection threshold, determine that the obstacle detection result is a detected obstacle; when the echo parameters corresponding to multiple sub-field of view angles are less than or equal to the determined obstacle detection threshold, determine that the obstacle detection result is an undetected obstacle.

[0148] In some embodiments, the signal analysis module 4554 is also used to: determine the intensity of the echo signal corresponding to each sub-field of view angle; compare the intensity of the echo signal corresponding to any sub-field of view angle with the average of the intensities of the echo signals corresponding to other sub-field of view angles to obtain the echo parameters corresponding to any sub-field of view angle.

[0149] In some embodiments, the radar is deployed on the vehicle; the radar-based obstacle detection device 455 also includes a door opening obstacle avoidance module, which is used to: respond to the door opening operation of the vehicle, determine whether the current obstacle detection result meets the door opening condition; when the current obstacle detection result meets the door opening condition, control the vehicle door to open.

[0150] In some embodiments, the door opening obstacle avoidance module is also used to: during the process of opening the vehicle door, determine whether the current obstacle detection result meets the door opening condition; when the current obstacle detection result meets the door opening condition, continue to control the vehicle door opening; when the current obstacle detection result does not meet the door opening condition, stop controlling the vehicle door opening.

[0151] In some embodiments, the radar includes a door radar and a roof radar; the door opening obstacle avoidance module is also used to: in response to a door opening operation for the vehicle, determine whether the obstacle detection results currently obtained by the door radar and the obstacle detection results obtained by the roof radar meet the door opening conditions; during the process of opening the vehicle door, determine whether the obstacle detection results currently obtained by the door radar meet the door opening conditions.

[0152] The embodiment of the present application provides a computer program product or a computer program, which includes executable instructions stored in a computer-readable storage medium. The processor of the electronic device reads the executable instructions from the computer-readable storage medium, and the processor executes the executable instructions, so that the electronic device implements the above-mentioned radar-based obstacle detection method in the embodiment of the present application.

[0153] An embodiment of the present application provides a computer-readable storage medium storing executable instructions, wherein executable instructions are stored. When the executable instructions are executed by a processor, the processor will be caused to implement the radar-based obstacle detection method provided by the embodiment of the present application.

[0154] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface storage, optical disk, or CD-ROM; or it may be various devices including one or any combination of the above memories.

[0155] In some embodiments, executable instructions may be in the form of a program, software, software module, script or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine or other unit suitable for use in a computing environment.

[0156] As an example, executable instructions may, but need not, correspond to a file in a file system, may be stored as part of a file that stores other programs or data, such as in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files storing one or more modules, subroutines, or code portions).

[0157] As an example, the executable instructions may be deployed to be executed on one electronic device, or on multiple electronic devices located at one site, or on multiple electronic devices distributed at multiple sites and interconnected by a communication network.

[0158] The above are only embodiments of the present application and are not intended to limit the protection scope of the present application. Any modifications, equivalent substitutions and improvements made within the spirit and scope of the present application are included in the protection scope of the present application.

Claims

1. A radar-based obstacle detection method, characterized in that: include: Determining a target environment scene where the radar is located from a plurality of environment scenes; wherein the plurality of environment scenes respectively contain different noise levels; Determining a target distance interval corresponding to an echo signal received by the radar in the target environment scene; wherein the echo signal is obtained by reflecting a detection signal emitted by the radar in the target distance interval; and the target distance interval includes at least part of a plurality of distance intervals; Determining an obstacle detection threshold corresponding to the target environment scene and the target distance interval; wherein the obstacle detection threshold is negatively correlated with the noise level in the environment scene, and the obstacle detection threshold is positively correlated with the distance interval; The echo signal is analyzed according to the determined obstacle detection threshold to obtain an obstacle detection result.

2. The method according to claim 1, characterized in that The performing signal analysis on the echo signal according to the determined obstacle detection threshold to obtain an obstacle detection result includes: Dividing the field of view angle of the radar to obtain a plurality of sub-field of view angles; Dividing and processing the echo signal according to the multiple sub-viewing angles to obtain an echo signal corresponding to each sub-viewing angle; Determine the echo parameter corresponding to each sub-viewing angle according to the echo signal corresponding to each sub-viewing angle; When the echo parameter corresponding to any sub-viewing angle is greater than the determined obstacle detection threshold, the obstacle detection result is determined to be a detected obstacle; When the echo parameters respectively corresponding to the multiple sub-viewing angles are all less than or equal to the determined obstacle detection threshold, it is determined that the obstacle detection result is that no obstacle is detected.

3. The method according to claim 2, characterized in that The step of determining the echo parameters corresponding to each sub-viewing angle according to the echo signals corresponding to each sub-viewing angle comprises: Determine the intensity of the echo signal corresponding to each sub-viewing angle; The intensity of the echo signal corresponding to any sub-viewing angle is compared with the average of the intensities of the echo signals corresponding to other sub-viewing angles to obtain the echo parameters corresponding to the sub-viewing angle.

4. The method according to any one of claims 1 to 3, characterized in that: The radar is deployed on a vehicle; the method further comprises: In response to a door opening operation for the vehicle, determining whether a current obstacle detection result meets a door opening condition; When the current obstacle detection result meets the door opening condition, the door of the vehicle is controlled to open.

5. The method according to claim 4, characterized in that The method further comprises: During the opening process of the door of the vehicle, determining whether the current obstacle detection result meets the door opening condition; When the current obstacle detection result meets the door opening condition, continue to control the door of the vehicle to open; When the current obstacle detection result does not meet the door opening condition, the control of the vehicle door opening is stopped.

6. The method according to claim 5, characterized in that The radar includes a door radar and a roof radar; and in response to a door opening operation of the vehicle, determining whether a current obstacle detection result meets a door opening condition includes: In response to a door opening operation for the vehicle, determining whether an obstacle detection result currently obtained by the door radar and an obstacle detection result obtained by the roof radar meet the door opening condition; During the process of opening the door of the vehicle, determining whether the current obstacle detection result meets the door opening condition includes: During the opening process of the vehicle door, it is determined whether the obstacle detection result currently obtained by the door radar satisfies the door opening condition.

7. A radar-based obstacle detection device, characterized in that: include: An environmental scene determination module, used to determine the target environmental scene where the radar is located from a plurality of environmental scenes; wherein the plurality of environmental scenes respectively contain different noise levels; A distance interval determination module, used to determine a target distance interval corresponding to the echo signal received by the radar in the target environment scene; wherein the echo signal is obtained by reflecting the detection signal emitted by the radar in the target distance interval; and the target distance interval includes at least part of a plurality of distance intervals; A threshold determination module, used to determine an obstacle detection threshold corresponding to the target environment scene and the target distance interval; wherein the obstacle detection threshold is negatively correlated with the noise level in the environment scene, and the obstacle detection threshold is positively correlated with the distance interval; The signal analysis module is used to perform signal analysis on the echo signal according to the determined obstacle detection threshold to obtain an obstacle detection result.

8. An electronic device, characterized in that: include: A memory for storing executable instructions; A processor, configured to implement the method according to any one of claims 1 to 6 when executing the executable instructions stored in the memory.

9. A computer-readable storage medium, characterized in that: Executable instructions are stored, and when executed by a processor, the method described in any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that The method comprises executable instructions for implementing the method according to any one of claims 1 to 6 when executed by a processor.

Images