Vehicle emergency braking method, electronic equipment and storage medium

Abstract

The invention discloses a vehicle emergency braking method, electronic equipment and a storage medium, and belongs to the technical field of vehicle control. The method comprises the following steps: acquiring various sensor data obtained by detecting the surrounding environment of a vehicle, wherein the various sensor data at least comprise video data; according to the credibility of the video data, the contribution degree of the various sensor data to a perception result of the surrounding environment of the vehicle is adjusted, the credibility is related to a driving scene of the vehicle, and the perception result is used for indicating the consistent explanation of the various sensor data to the surrounding environment of the vehicle; and determining an emergency braking strategy of the vehicle according to the sensing result. According to the method, the contribution degree of various sensor data to the sensing result of the surrounding environment of the vehicle can be adjusted according to the credibility of the video data, so that the emergency braking operation of the vehicle has higher accuracy and more flexible environmental adaptability.

Description

Technical Field

[0001] The present application relates to the field of vehicle control technology, and in particular to a vehicle emergency braking method, electronic equipment and storage medium. Background Art

[0002] The AEB (Automatic Emergency Braking) system is an important vehicle active safety technology that can automatically trigger braking in an emergency to avoid or reduce the severity of a collision.

[0003] In the AEB system, the camera is particularly important for the perception of the front of the vehicle. By real-time monitoring of the traffic conditions in front of the vehicle, it can help the vehicle identify potential collision risks. In order to enhance the camera's perception ability in environments such as night, fog, and rain, other sensor data such as laser radar and millimeter-wave radar are usually used in related technologies to correct the video data obtained by the camera to make up for the lack of camera perception in some environments.

[0004] However, when the vehicle is driving at night, in heavy fog, in rainy days and other environments, due to the low credibility of the video data obtained by the camera, the perception of the vehicle's surrounding environment obtained by repairing the video data through sensor data such as radar still has the problem of low credibility. Summary of the invention

[0005] The present application provides a vehicle emergency braking method, electronic device and storage medium to solve the technical problems existing in the related technologies. The technical solutions include the following:

[0006] In a first aspect, the present application provides a method for vehicle emergency braking, the method comprising: acquiring a variety of sensor data obtained by detecting the vehicle's surrounding environment, the multiple sensor data including at least video data; adjusting the contribution of the multiple sensor data to the perception result of the vehicle's surrounding environment according to the credibility of the video data, wherein the credibility is related to the driving scenario of the vehicle, and the perception result is used to indicate the consistency of the interpretation of the vehicle's surrounding environment by the multiple sensor data; and determining the vehicle's emergency braking strategy according to the perception result.

[0007] In some possible implementations, adjusting the contribution of the multiple sensor data to the perception result of the vehicle's surrounding environment according to the credibility of the video data includes: acquiring multiple perception information corresponding to the multiple sensor data, the multiple perception information being used to indicate different interpretations of the vehicle's surrounding environment by the multiple sensor data; weighting the multiple perception information according to the credibility of the video data; and fusing the multiple perception information after weighting to obtain the perception result.

[0008] In some possible implementations, the multiple perception information includes first perception information corresponding to the video data, the first perception information including first target attribute information for performing a first interpretation of a target obstacle in the vehicle's surrounding environment; the multiple sensor data also include millimeter-wave radar data, the multiple perception information also include second perception information corresponding to the millimeter-wave radar data, the second perception information including second target attribute information for performing a second interpretation of the target obstacle.

[0009] In some possible implementations, the perception result includes a first perception result, and the weighted processing of the multiple perception information according to the credibility of the video data includes: weighted processing of the first target attribute information and the second target attribute information according to the credibility of the video data; the fusing of the multiple perception information after weighted processing to obtain the perception result includes: fusing the first target attribute information and the second target attribute information after weighted processing to obtain the first perception result, and the first perception result is used to indicate the consistent interpretation of the target obstacle by the multiple sensor data.

[0010] In some possible implementations, the multiple perception information includes first perception information corresponding to the video data, and obtaining the multiple perception information corresponding to the multiple sensor data includes: processing the video data according to an attention mechanism to obtain first perception information, the first perception information includes key area information, and the key area information is used to indicate key areas with collision risks in the vehicle's surrounding environment.

[0011] In some possible implementations, before acquiring the multiple types of perception information respectively corresponding to the multiple types of sensor data, the method includes: preprocessing the multiple types of sensor data, wherein the preprocessing includes spatial alignment and / or temporal registration.

[0012] In some possible implementations, determining the emergency braking strategy of the vehicle based on the perception results includes: predicting the movement trajectory of the vehicle and other traffic participants in the surrounding environment of the vehicle based on the perception results; determining whether there is a risk of collision between the vehicle and the other traffic participants based on the movement trajectory; if there is a risk of collision between the vehicle and the other traffic participants, performing an emergency braking operation of the vehicle based on the movement trajectory.

[0013] In some possible implementations, the method further includes: if there is a risk of collision between the vehicle and the other traffic participants, determining and prompting the latest braking timing and braking force based on the action trajectory to prompt the driver of the vehicle to perform an emergency braking operation.

[0014] In a second aspect, the present application provides a control device for vehicle emergency braking, comprising: an acquisition module, used to acquire a variety of sensor data obtained by detecting the vehicle's surrounding environment, and the multiple sensor data include at least video data; an adjustment module, used to adjust the contribution of the multiple sensor data to the perception result of the vehicle's surrounding environment according to the credibility of the video data, wherein the credibility is related to the driving scenario of the vehicle, and the perception result is used to indicate the consistency of the interpretation of the vehicle's surrounding environment by the multiple sensor data; a determination module, used to determine the vehicle's emergency braking strategy according to the perception result.

[0015] In some possible implementations, the adjustment module is also used to obtain multiple perception information corresponding to the multiple sensor data, and the multiple perception information is used to indicate different interpretations of the vehicle surrounding environment by the multiple sensor data; weighted processing is performed on the multiple perception information according to the credibility of the video data; and the multiple perception information after weighted processing is fused to obtain the perception result.

[0016] In some possible implementations, the multiple perception information includes first perception information corresponding to the video data, the first perception information including first target attribute information for performing a first interpretation of a target obstacle in the vehicle's surrounding environment; the multiple sensor data also include millimeter-wave radar data, the multiple perception information also include second perception information corresponding to the millimeter-wave radar data, the second perception information including second target attribute information for performing a second interpretation of the target obstacle.

[0017] In some possible embodiments, the perception result includes a first perception result, and the adjustment module is further used to perform weighted processing on the first target attribute information and the second target attribute information according to the credibility of the video data; the weighted first target attribute information and the second target attribute information are fused to obtain the first perception result, and the first perception result is used to indicate the consistent interpretation of the target obstacle by the multiple sensor data.

[0018] In some possible implementations, the multiple perception information includes first perception information corresponding to the video data, and the adjustment module is further used to process the video data according to an attention mechanism to obtain first perception information, wherein the first perception information includes key area information, and the key area information is used to indicate key areas with collision risks in the vehicle's surrounding environment.

[0019] In some possible implementations, the adjustment module is further used to preprocess the multiple sensor data, where the preprocessing includes spatial alignment and / or temporal registration.

[0020] In some possible implementations, the determination module is also used to predict the movement trajectory of the vehicle and other traffic participants in the surrounding environment of the vehicle based on the perception results; determine whether there is a risk of collision between the vehicle and the other traffic participants based on the movement trajectory; if there is a risk of collision between the vehicle and the other traffic participants, perform emergency braking operation of the vehicle according to the movement trajectory.

[0021] In some possible implementations, the determination module is also used to determine and prompt the latest braking timing and braking force based on the action trajectory if there is a risk of collision between the vehicle and the other traffic participants, so as to prompt the driver of the vehicle to perform an emergency braking operation.

[0022] In a third aspect, the present application provides an electronic device for vehicle emergency braking, comprising: a memory storing at least one program instruction for vehicle emergency braking; and a processor, wherein when the program instruction is executed by the processor, the vehicle implements the method in the first aspect of the present application or any possible implementation of the first aspect.

[0023] In a fourth aspect, the present application provides a computer program (product), which includes a computer program / instructions, and the computer program / instructions are executed by a processor to enable a vehicle to implement the method in the first aspect of the present application or any possible implementation scheme of the first aspect.

[0024] In a fifth aspect, the present application provides a computer-readable storage medium having stored thereon program instructions for vehicle emergency braking. When the program instructions are executed by one or more processors, the vehicle implements the method in the first aspect of the present application or any possible implementation scheme of the first aspect.

[0025] The beneficial effects of the technical solution provided by this application include at least:

[0026] When generating the perception results of the vehicle's surrounding environment based on the acquired multiple sensor data, the present application can adjust the contribution of multiple sensor data to the perception results of the vehicle's surrounding environment through the credibility of the video data related to the vehicle's driving scene. For example, when the credibility of the video data is low, the contribution of other sensor data to the perception results can be enhanced; when the credibility of the video data is high, the contribution of the video data to the perception results can be enhanced, so that the perception results of the vehicle's surrounding environment can be dynamically adjusted according to the changes in the vehicle's driving scene, greatly improving the reliability of the vehicle's emergency braking operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] 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 ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0028] Figure 1 It is a schematic diagram of an implementation scenario provided by an embodiment of the present application;

[0029] Figure 2 is a flow chart of a vehicle emergency braking method provided by an embodiment of the present application;

[0030] Figure 3 is a schematic diagram of the structure of a vehicle emergency braking control device provided in an embodiment of the present application;

[0031] Figure 4 It is a schematic diagram of the structure of an electronic device for vehicle emergency braking provided in an embodiment of the present application. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0033] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0034] In the AEB system, the accuracy of the vehicle's ability to perceive the surrounding environment is particularly important and directly affects the reliability of the AEB system. The vehicle's ability to perceive the surrounding environment mainly refers to the ability to detect the vehicle's surrounding environment through various sensors, and to perceive other targets in the surrounding environment based on the fusion results of multiple sensor data. Among them, since the video data obtained by the camera includes scene-level semantic information of the vehicle's surrounding environment, it can help the vehicle identify and detect target obstacles in the vehicle's surrounding environment (target obstacles can be obstacles in the vehicle's surrounding environment that may affect the vehicle's driving, such as other vehicles, pedestrians, fences, etc.), so the fusion method of multiple sensor data usually uses video data as the main body of fusion, and uses other sensor data to correct the video data.

[0035] However, due to the influence of factors such as weather, lighting, and occlusion, the credibility of the video data obtained through the camera has certain fluctuations, which makes the fusion method based on video data relatively unreliable in perceiving the vehicle's surrounding environment, which in turn affects the reliability of the AEB system.

[0036] In view of this, the present application discloses a method for vehicle emergency braking, which can adjust the contribution of multiple sensor data to the perception results according to video data related to the vehicle's driving scene, so that the vehicle's emergency braking operation has a certain adaptability to the vehicle's driving scene, thereby ensuring the flexibility and reliability of the vehicle's emergency braking operation.

[0037] Figure 1 is a schematic diagram of an implementation scenario provided by an embodiment of the present application. Figure 1 The implementation scenario provided in the embodiment of the present application may include a vehicle 11 and a control unit 12.

[0038] The vehicle 11 is provided with a variety of sensors for detecting the environment around the vehicle, and the various sensors can establish communication connections with the control unit 12 in a wired or wireless manner, so that the control unit 12 can sense the environment around the vehicle 11 through the various sensors to determine the emergency braking strategy of the vehicle 11. Among them, the various sensors include at least a camera.

[0039] Optionally, the control unit 12 may be a server or a server cluster composed of multiple servers. The multiple sensors may also include any sensor that can detect the surrounding environment of the vehicle, such as a laser radar and a millimeter wave radar, and the present application does not impose any limitation in this regard.

[0040] Those skilled in the art should understand that the above-mentioned vehicle 11 and control unit 12 are only examples, and other existing or future vehicles or control units that are applicable to the present application should also be included in the scope of protection of the present application and are included here by reference.

[0041] Figure 2 is a flow chart of a vehicle emergency braking method provided by an embodiment of the present application. The method can be executed by a control system installed in a vehicle, and the present application does not impose any limitation in this regard. Figure 2 The vehicle emergency braking method provided in the embodiment of the present application may include the following steps:

[0042] Step S210, acquiring a variety of sensor data obtained by detecting the surrounding environment of the vehicle, wherein the various sensor data at least include video data.

[0043] Illustratively, the acquisition method of multiple sensor data may include, for example, detecting the environment around the vehicle through multiple sensors disposed on the vehicle to obtain multiple sensor data. The sampling frequencies of the multiple sensor data may be the same or different, and the present application does not impose any limitation in this regard.

[0044] As mentioned above, video data includes scene-level semantic information of the vehicle's surroundings, which can be used to identify and detect other targets in the vehicle's surroundings. In view of this, the multiple sensor data can at least include video data, so that the embodiments of the present application can better understand the scene in which the vehicle is currently located, and identify and detect target obstacles in the vehicle's surroundings based on the scene.

[0045] Step S220: adjusting the contribution of various sensor data to the perception result of the vehicle's surrounding environment according to the credibility of the video data.

[0046] Among them, the credibility is related to the driving scene of the vehicle, and the perception result can be used to indicate the consistency of the interpretation of the vehicle's surrounding environment by multiple sensor data. Optionally, the driving scene can be used for example, but not limited to, to indicate the weather, lighting conditions, occlusion conditions, etc. during the driving process of the vehicle. As mentioned above, the credibility of video data may be affected by weather, lighting conditions, and occlusion conditions, that is, the credibility of video data in different driving scenes will also be different. The embodiment of the present application adjusts the contribution of multiple sensor data to the perception results according to the credibility of the video data, so that the vehicle's perception results of the surrounding environment have a certain adaptability to changes in driving scenes, and can be dynamically adjusted according to different driving scenes, thereby greatly improving the reliability of the perception results of the vehicle's surrounding environment.

[0047] In some embodiments, the driving scene of the vehicle may include, for example, a first driving scene in foggy weather and a second driving scene in clear weather; the credibility of the video data related to the driving scene of the vehicle may include a first credibility corresponding to the first driving scene and a second credibility corresponding to the second driving scene. When the driving scene of the vehicle changes from the first driving scene to the second driving scene, the contribution of multiple sensor data to the perception result may be adjusted according to the second credibility of the video data, so that the contribution of multiple sensor data to the perception result is adapted to the second driving scene. When the driving scene of the vehicle changes from the second driving scene to the first driving scene, the contribution of multiple sensor data to the perception result may be adjusted according to the first credibility of the video data, so that the contribution of multiple sensor data to the perception result is adapted to the first driving scene. It should be noted that the first driving scene and the second driving scene, as well as the first credibility of the video data corresponding to the first scene and the second credibility of the video data corresponding to the second driving scene are all illustrative and non-restrictive, and those skilled in the art may make adjustments according to actual application conditions, and the present application does not impose any restrictions in this regard.

[0048] As mentioned above, the perception results of the vehicle's surroundings can be used to indicate the consistency of the interpretation of the vehicle's surroundings by multiple sensor data. Since different sensors may detect the vehicle's surroundings in different ways, the interpretation methods or emphases of the interpretation of the vehicle's surroundings based on different sensor data may also be different. In view of this, multiple sensor data can be integrated and processed, and the contribution of multiple sensor data in the integration and processing process can be adjusted through the credibility of video data to obtain the perception results of the vehicle's surroundings, forming a complete, unified, and accurate consistent interpretation of the vehicle's surroundings.

[0049] In some embodiments, the method of adjusting the contribution of multiple sensor data to the perception results of the vehicle's surrounding environment according to the credibility of the video data may include, for example: obtaining multiple perception information corresponding to the multiple sensor data; weighting the multiple perception information according to the credibility of the video data; fusing the multiple perception information after weighting to obtain the perception result. Among them, the multiple perception information is used to indicate the different interpretations of the vehicle's surrounding environment by multiple sensor data. Through the above method, the embodiment of the present application can fuse different perception information by weighted processing to obtain the perception results of the vehicle's surrounding environment, and obtain the perception information corresponding to the multiple sensor data before fusion, which reduces the redundancy and complexity of the original sensor data and improves the efficiency of sensor data integration and processing.

[0050] Since the data characteristics of sensor data obtained by different sensors may be different, in some embodiments, a variety of different sensor data may be processed separately to obtain a variety of perception information corresponding to the various sensors.

[0051] Considering that in the emergency braking scenario of the vehicle, the need to perceive the target obstacle in the vehicle's surrounding environment may be the main need for the vehicle to perceive the surrounding environment. For example, the need to perceive the relative position, relative speed, relative angle, etc. between the vehicle and the target obstacle. In view of this, when integrating and processing multiple sensor data, multiple interpretations of the target obstacle in the vehicle's surrounding environment by multiple sensor data can be obtained respectively according to the multiple sensor data, and then the multiple interpretations of the target obstacle by the multiple sensor data can be integrated and processed.

[0052] As mentioned above, different sensor data may interpret the vehicle's surroundings in different ways or with different focuses. In view of this, when obtaining multiple interpretations of target obstacles in the vehicle's surroundings from multiple sensor data, appropriate sensor data may be selected based on the main perception requirements of the vehicle's surroundings and sensor characteristics to meet the vehicle's main perception requirements of the vehicle's surroundings in emergency braking scenarios (e.g., the perception requirements of the relative position, relative speed, relative angle, etc. between the vehicle and the target obstacle).

[0053] In some embodiments, in order to meet the perception requirements of the relative position, relative speed, relative angle, etc. between the vehicle and the target obstacle, the environment around the vehicle can be perceived through video data and millimeter wave radar data. The multiple perception information may include, for example, first perception information corresponding to the video data, and the first perception information may include, for example, first target attribute information for performing a first interpretation of the target obstacle in the environment around the vehicle; the multiple sensor data may also include millimeter wave radar data, and the multiple perception information may also include second perception information corresponding to the millimeter wave radar data, and the second perception information may include, for example, second target attribute information for performing a second interpretation of the target obstacle.

[0054] In some embodiments, a plurality of perception information is weighted according to the credibility of the video data, for example, it may include: weighting the first target attribute information and the second target attribute information according to the credibility of the video data. The plurality of perception information after weighting is fused to obtain a perception result of the vehicle's surrounding environment, for example, it may include: fusing the first target attribute information and the second target attribute information after weighting to obtain a first perception result. The first perception result is used to indicate the consistency of the interpretation of the target obstacle in the vehicle's surrounding environment by the plurality of sensor data.

[0055] It is also considered that there may be some critical areas with higher collision risks in the vehicle's surroundings, such as areas corresponding to other moving vehicles and pedestrians, etc.; there may also be some non-critical areas with lower collision risks, such as areas corresponding to stationary guardrails and the sky, etc. In view of this, the target obstacles in the vehicle's surroundings can be detected and identified based on the video data, and the critical areas with possible collision risks can be determined based on the characteristics of the target obstacles.

[0056] In some embodiments, the multiple perception information may include, for example, first perception information corresponding to the video data. Obtaining the multiple perception information corresponding to the multiple sensor data may include, for example: processing the video data according to the attention mechanism to obtain the first perception information, the first perception information including key area information. Among them, the key area information is used to indicate the key areas in the vehicle's surrounding environment where there is a risk of collision. Through the above method, the embodiment of the present application can process multiple frames of continuous images in the video data through the attention mechanism, and determine the key areas where collision may occur based on the correlation between different areas in the multiple frames of continuous images in the time series, thereby improving data processing efficiency.

[0057] It is also considered that the sampling frequencies of the various sensor data, as described above, may be the same or different. At the same time, when the various sensor data are obtained through various different sensors, the positions of the various different sensors in the vehicle may be the same or different. In view of this, in some embodiments, before obtaining the various sensor information corresponding to the various sensor data, the method for emergency braking of the vehicle disclosed in the embodiment of the present application may include, for example: preprocessing the various sensor data, and the preprocessing may include, for example, spatial alignment and / or temporal registration. For example, when the sampling frequencies of the various sensor data are different and the various sensor positions for obtaining the various sensor data are the same, the various sensor data may be temporally registered; or, when the sampling frequencies of the various sensor data are the same and the various sensor positions for obtaining the various sensor data are different, the various sensor data may be spatially aligned; or, when the sampling frequencies of the various sensor data are different and the various sensor positions for obtaining the various sensor data are different, the various sensor data may be spatially aligned and temporally registered. Through the above method, the embodiment of the present application can transform the various sensor data to the same spatial coordinate system and / or synchronize the data to facilitate subsequent data integration and processing.

[0058] Step S230, determining the emergency braking strategy of the vehicle according to the sensing result.

[0059] Illustratively, the emergency braking strategy of a vehicle can be used, for example, to indicate whether the vehicle has a collision risk within a given time threshold and to indicate countermeasures for the collision risk. The value of the time threshold can be adjusted according to actual application conditions, and this application does not impose any restrictions in this regard.

[0060] In some embodiments, emergency braking of the vehicle is performed based on the perception results of the vehicle's surroundings, which may include, for example: predicting the movement trajectory of the vehicle and other traffic participants in the vehicle's surroundings based on the perception results of the vehicle's surroundings; determining whether there is a risk of collision between the vehicle and other traffic participants based on the movement trajectory of the vehicle and other traffic participants in the vehicle's surroundings; if there is a risk of collision between the vehicle and other traffic participants, performing emergency braking of the vehicle based on the movement trajectory. Among them, other traffic participants in the vehicle's surroundings are used to indicate all entities that are in the same driving scene as the vehicle and participate in traffic behaviors, which may include, for example, other vehicles, pedestrians, etc. Through the above method, the embodiments of the present application can predict the movement trajectory of the vehicle and other traffic participants based on the perception results, thereby discovering the risk of collision in advance and reducing the possibility of collision.

[0061] In some embodiments, the vehicle emergency braking method disclosed in the embodiments of the present application may also include: if there is a risk of collision between a vehicle and other traffic participants, determining and prompting the latest braking time and braking force according to the movement trajectory of the vehicle and other traffic participants, so as to prompt the driver of the vehicle to perform an emergency braking operation. Through the above method, the present application can timely warn the driver of the vehicle to ensure the safety of the vehicle in the emergency braking scenario.

[0062] When generating the perception results of the vehicle's surrounding environment based on the acquired multiple sensor data, the present application can adjust the contribution of multiple sensor data to the perception results of the vehicle's surrounding environment through the credibility of the video data related to the vehicle's driving scene. For example, when the credibility of the video data is low, the contribution of other sensor data to the perception results can be enhanced; when the credibility of the video data is high, the contribution of the video data to the perception results can be enhanced, so that the perception results of the vehicle's surrounding environment can be dynamically adjusted according to the changes in the vehicle's driving scene, greatly improving the reliability of the vehicle's emergency braking operation.

[0063] In some possible implementations, the present application also provides a vehicle emergency braking control device. Figure 3 is a schematic diagram of the structure of the vehicle emergency brake control device provided in the embodiment of the present application, see Figure 3 The vehicle emergency braking control device provided in the embodiment of the present application includes:

[0064] The acquisition module 310 is used to acquire a variety of sensor data obtained by detecting the surrounding environment of the vehicle, and the various sensor data at least include video data.

[0065] The adjustment module 320 is used to adjust the contribution of various sensor data to the perception results of the vehicle's surrounding environment according to the credibility of the video data, wherein the credibility is related to the vehicle's driving scene, and the perception results are used to indicate the consistency of the interpretation of the vehicle's surrounding environment by various sensor data.

[0066] The determination module 330 is used to determine the emergency braking strategy of the vehicle according to the sensing result.

[0067] In some embodiments, the adjustment module 320 is also used to obtain multiple perception information corresponding to multiple sensor data, where the multiple perception information is used to indicate different interpretations of the vehicle's surrounding environment by the multiple sensor data; weight the multiple perception information according to the credibility of the video data; and fuse the weighted perception information to obtain a perception result.

[0068] In some embodiments, the multiple perception information includes first perception information corresponding to the video data, the first perception information includes first target attribute information for a first interpretation of a target obstacle in the vehicle's surrounding environment; the multiple sensor data also include millimeter-wave radar data, the multiple perception information also includes second perception information corresponding to the millimeter-wave radar data, the second perception information includes second target attribute information for a second interpretation of the target obstacle.

[0069] In some embodiments, the perception result includes a first perception result, and the adjustment module 320 is further used to perform weighted processing on the first target attribute information and the second target attribute information according to the credibility of the video data; the weighted first target attribute information and the second target attribute information are fused to obtain a first perception result, and the first perception result is used to indicate the consistent interpretation of the target obstacle by multiple sensor data.

[0070] In some embodiments, the multiple perception information includes first perception information corresponding to the video data. The adjustment module 320 is also used to process the video data according to the attention mechanism to obtain the first perception information. The first perception information includes key area information. The key area information is used to indicate key areas with collision risks in the vehicle's surrounding environment.

[0071] In some embodiments, the adjustment module 320 is further used to pre-process the various sensor data, where the pre-processing includes spatial alignment and / or temporal registration.

[0072] In some embodiments, the determination module 330 is also used to predict the movement trajectory of the vehicle and other traffic participants in the vehicle's surrounding environment based on the perception results; determine whether there is a risk of collision between the vehicle and other traffic participants based on the movement trajectory; if there is a risk of collision between the vehicle and other traffic participants, perform emergency braking operations on the vehicle based on the movement trajectory.

[0073] In some embodiments, the determination module 330 is also used to determine and prompt the latest braking time and braking force according to the movement trajectory if there is a risk of collision between the vehicle and other traffic participants, so as to prompt the driver of the vehicle to perform emergency braking operations.

[0074] The vehicle emergency braking control device and the vehicle emergency braking method embodiment provided in the above embodiment belong to the same concept, and the specific implementation process thereof is detailed in the vehicle emergency braking method embodiment.

[0075] In some other possible implementations, the present application also provides an electronic device for vehicle emergency braking. Figure 4 is a schematic diagram of the structure of an electronic device for vehicle emergency braking provided in an embodiment of the present application, see Figure 4 The electronic device for vehicle emergency braking provided in the embodiment of the present application includes:

[0076] The memory 410 stores at least one program instruction for vehicle emergency braking.

[0077] Processor 420, when the above program instructions are executed by processor 420, the vehicle realizes the above combination Figure 2 The described method and steps of multiple embodiments thereof. Depending on the implementation, the processor 420 may be a CPU (central processing unit), a GPU (graphics processing unit), or one or more types of processors in other general and / or special processors, including but not limited to a DSP (digital signal processor), an ASIC (application specific integrated circuit), an FPGA (field-programmable gate array), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., and the number thereof may be determined according to actual needs.

[0078] In some other possible implementations, the present application further provides a computer program (product), the computer program (product) comprising a computer program / instruction, the computer program / instruction being executed by a processor to enable the vehicle to implement the above combination Figure 2 The method and steps of its various embodiments are described.

[0079] In some other possible implementations, the present application further provides a computer-readable storage medium on which program instructions for vehicle emergency braking are stored. When the program instructions are executed by one or more processors, the vehicle implements the above combination. Figure 2 The described method and steps of multiple embodiments thereof. The computer readable storage medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0080] In the embodiments of the present application, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance. The term "plurality" refers to two or more, unless otherwise clearly defined.

[0081] The term "and / or" in the embodiments of the present application is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent three situations: A exists alone, A and B exist at the same time, and B exists alone.

[0082] The above description is only for the purpose of facilitating the technical solution of the present application to be understood by those skilled in the art, and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for emergency braking of a vehicle, characterized in that: The method comprises: Acquire a variety of sensor data obtained by detecting the surrounding environment of the vehicle, wherein the variety of sensor data at least includes video data; Adjusting the contribution of the multiple sensor data to the perception result of the vehicle surrounding environment according to the credibility of the video data, wherein the credibility is related to the driving scene of the vehicle, and the perception result is used to indicate the consistency of the interpretation of the vehicle surrounding environment by the multiple sensor data; An emergency braking strategy for the vehicle is determined according to the sensing result.

2. The method according to claim 1, characterized in that The step of adjusting the contribution of the multiple sensor data to the perception result of the vehicle surrounding environment according to the credibility of the video data includes: Acquire a plurality of perception information corresponding to the plurality of sensor data, respectively, the plurality of perception information being used to indicate different interpretations of the plurality of sensor data on the vehicle surrounding environment; Performing weighted processing on the multiple types of perception information according to the credibility of the video data; The weighted multiple perception information are fused to obtain the perception result.

3. The method according to claim 2, characterized in that The plurality of perception information includes first perception information corresponding to the video data, the first perception information including first target attribute information for performing a first interpretation of a target obstacle in the environment surrounding the vehicle; The multiple sensor data also include millimeter wave radar data, and the multiple perception information also include second perception information corresponding to the millimeter wave radar data, and the second perception information includes second target attribute information used for a second interpretation of the target obstacle.

4. The method according to claim 3, characterized in that The perception result includes a first perception result, and the weighted processing of the multiple perception information according to the credibility of the video data includes: Performing weighted processing on the first target attribute information and the second target attribute information according to the credibility of the video data; The fusing the weighted multiple perception information to obtain the perception result includes: The first target attribute information and the second target attribute information after weighted processing are fused to obtain the first perception result, where the first perception result is used to indicate a consistent interpretation of the target obstacle by the multiple sensor data.

5. The method according to claim 2, characterized in that: The multiple types of perception information include first perception information corresponding to the video data, and the acquiring of the multiple types of perception information corresponding to the multiple types of sensor data respectively includes: The video data is processed according to an attention mechanism to obtain first perception information, where the first perception information includes key area information, and the key area information is used to indicate a key area with a collision risk in the environment around the vehicle.

6. The method according to claim 2, characterized in that Before acquiring the plurality of perception information respectively corresponding to the plurality of sensor data, the method includes: The multiple sensor data are pre-processed, wherein the pre-processing includes spatial alignment and / or temporal registration.

7. The method according to claim 1, characterized in that Determining the emergency braking strategy of the vehicle according to the sensing result includes: Predicting the movement trajectory of the vehicle and other traffic participants in the surrounding environment of the vehicle according to the perception result; Determining whether there is a collision risk between the vehicle and the other traffic participants according to the movement trajectory; If there is a risk of collision between the vehicle and the other traffic participants, an emergency braking operation of the vehicle is performed according to the action trajectory.

8. The method according to claim 7, characterized in that The method further comprises: If there is a risk of collision between the vehicle and the other traffic participants, the latest braking timing and braking force are determined and prompted according to the action trajectory to prompt the driver of the vehicle to perform an emergency braking operation.

9. An electronic device, characterized in that: include: A memory having stored therein program instructions for emergency braking of the vehicle; as well as The processor, when the program instructions are executed by the processor, enables the vehicle to implement the method described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that: Program instructions for vehicle emergency braking are stored thereon, and when the program instructions are executed by one or more processors, the vehicle implements the method described in any one of claims 1-8.

Images