Driving assistance system and information transmission method therefor

Abstract

The invention provides a driving assistance system and an information transmission method therefor. The driving assistance system includes a visibility module configured to generate visibility information based on sensor data including automatic driving environment information of a vehicle received from a sensor, the visibility information comprises a qualitative measurement result obtained by performing qualitative measurement on the automatic driving environment and / or a quantitative measurement result obtained by performing quantitative measurement on the automatic driving environment; and an ODD module configured to receive the visibility information from the visibility module in a wired and / or wireless communication manner, determine an ODD boundary based on the visibility information, and assist in performing at least one automatic driving function of the vehicle according to the determined ODD boundary.

Description

Technical Field

[0001] The present invention relates to a driver assistance solution based on an operational design domain. Background Art

[0002] The term Operational Design Domain (ODD) comes from the standard SAE J3016. ODD is described in the standard as the operating conditions for which a specific driving automation system or its functions are specifically designed, including but not limited to environmental, geographical and time constraints, and the presence or absence of certain traffic or road features. In other words, ODD is used to define the conditions under which the autonomous driving function is available, and out of these conditions, the autonomous driving function cannot be guaranteed to work.

[0003] However, it is difficult to accurately describe the ODD under the existing framework, both in academia and in practice. That is, there is a problem that the description of ODD is always vague. For example, the existing ODD may define exiting the lane keeping function when it rains, that is, the rainy environment will be outside the ODD. However, the existing ODD does not clearly define how heavy the rain is when the lane keeping function is exited. In this way, once rain is detected, the system determines that the current autonomous driving scene is outside the ODD, and the system chooses to exit the lane keeping function. As a result, the low availability of the lane keeping function is caused. Summary of the invention

[0004] In this context, according to one aspect of the present invention, a driving assistance system is provided. The driving assistance system includes: a visibility module, configured to generate visibility information based on sensor data containing autonomous driving environment information of a vehicle received from a sensor, wherein the visibility information includes qualitative measurement results obtained by qualitatively measuring the autonomous driving environment and / or quantitative measurement results obtained by quantitatively measuring the autonomous driving environment. The driving assistance system also includes an ODD module, configured to receive the visibility information from the visibility module in a wired and / or wireless communication manner, determine an ODD boundary based on the visibility information, and the ODD boundary is used to assist in executing at least one autonomous driving function of the vehicle.

[0005] In one embodiment, the qualitative measurement result includes a label for qualitatively describing weather conditions under at least one weather type.

[0006] In one embodiment, the labels are output from a machine learning model trained with fine-grained label data that contains a more detailed description of the weather condition than the weather type.

[0007] In one embodiment, the qualitative measurement result includes information that can reflect the non-uniformity of the sensor's visibility to different areas within its field of view.

[0008] In one embodiment, the quantitative measurement result includes: a value of visibility of each sub-area of ​​a plurality of sub-areas within the field of view of the sensor.

[0009] In one embodiment, the quantitative measurement result includes: a farthest visible curve for describing the farthest visible distance of the sensor in its field of view; and the farthest visible curve is composed of multiple farthest visible distances of the sensor in the direction of rays at different angles in its field of view.

[0010] In one embodiment, the visibility information is included in vehicle-to-everything (V2X) information, and the visibility information includes one or more of the following:

[0011] - descriptors for describing weather types and labels for qualitatively describing weather conditions under that weather type;

[0012] - Information that can reflect the non-uniformity of the sensor's visibility to different areas within its field of view;

[0013] - a value of the sensor's visibility for each of a plurality of sub-areas within its field of view; and

[0014] - The maximum visible distance curve used to describe the maximum visible distance of the sensor within its field of view.

[0015] In one embodiment, the ODD module is also used to assist in executing at least one autonomous driving function of the vehicle according to the determined ODD boundary, including: the ODD module determines whether the current autonomous driving condition is inside or outside the ODD boundary based on the determined ODD boundary, thereby determining to activate, continue to maintain, exit, deactivate or expand the at least one autonomous driving function.

[0016] In one embodiment, the driving assistance system also includes a communication interface, wherein the communication interface is a hardware communication interface for implementing wired communication between the visibility module and the ODD module, or the communication interface is an air interface for implementing wireless communication between the visibility module and the ODD module.

[0017] In one embodiment, the visibility module and the ODD module are arranged in the same roadside device or both are arranged in the vehicle; or one of the visibility module and the ODD module is arranged in the vehicle and the other is arranged in a roadside unit or a cloud server.

[0018] In one embodiment, the driving assistance system further includes an autonomous driving function module for implementing the at least one autonomous driving function, and the autonomous driving function module is disposed on the vehicle.

[0019] According to another aspect of the present invention, there is provided an information transmission method for the driving assistance system as described above, comprising: including the visibility information in vehicle-to-everything (V2X) information and transmitting the visibility information from the visibility module to the ODD module.

[0020] In one embodiment, the visibility information is included in a predetermined field or a predetermined data frame of the V2X message and includes the following data elements: an environment type element, a visibility grid element, and a visibility description element. The environment type element includes: fine-grained label data that describes the weather conditions more finely than the weather type. The visibility grid element includes one or more of the following: grid position, grid resolution, and visibility on the grid. The visibility description element includes: the farthest visible distance of the sensor in each direction within its field of view.

[0021] According to yet another aspect of the present invention, a machine-readable storage medium is provided, which stores executable instructions. When the instructions are executed, a processor is enabled to perform the method described above.

[0022] A summary of the main aspects of the present invention is provided above so that these aspects can be basically understood. This summary is not intended to limit the scope of any or all aspects of the present invention. The purpose of this summary is to provide some implementations of these aspects in a simplified form as a preface to the detailed description that will be provided later. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The technical solution of the present invention will become clearer from the following detailed description in conjunction with the accompanying drawings. It is understood that these drawings are only used for exemplary description and are not intended to limit the scope of protection of the present invention.

[0024] Figure 1 is a schematic block diagram of a driving assistance system according to an embodiment of the present invention.

[0025] Figure 2 The ODD boundary according to an embodiment of the present invention is schematically shown.

[0026] Figure 3A and Figure 3B Shows Figure 1 Some embodiments of the architecture of the driver assistance system in FIG.

[0027] Figure 4 is a flow chart of an information transmission method for a driving assistance system according to an embodiment of the present invention.

[0028] Figure 5 The visibility information according to the embodiment of the present invention is schematically shown. DETAILED DESCRIPTION

[0029] Embodiments of the present invention relate to a driving assistance system and an information transmission method implemented in the driving assistance system. The driving assistance system according to an embodiment of the present invention includes a visibility module and an ODD module. The visibility module outputs the generated visibility information to the ODD module. That is, the output of the visibility module is the input of the ODD module. The ODD module determines the boundary of the ODD based on the received visibility information, and makes decisions related to autonomous driving accordingly.

[0030] The inventors realize that the ODD monitoring in the prior art mainly relies on rough environmental perception, and determining the ODD boundary in this way will lead to low availability of the autonomous driving function. For example, some use cases (autonomous driving conditions) may directly cause the current autonomous driving condition to be outside the ODD boundary, thereby causing the autonomous driving function to exit. In this regard, according to an embodiment of the present invention, the visibility information includes qualitative measurement results and / or quantitative measurement results, thereby obtaining a more accurate or extended ODD boundary, thereby improving the availability of the autonomous driving function and improving the user's experience of the vehicle's autonomous driving.

[0031] According to an embodiment of the present invention, the visibility module and the ODD module can be set in the same device (for example, both are set in a vehicle), and the two exchange information in a wired communication manner via a hardware communication interface. The visibility module and the ODD module can also be set in different devices (for example, the visibility module is set in a cloud server or an edge server, and the ODD module is set in a vehicle), and the two exchange information in a wireless communication manner via an air interface. In this case, the information exchanged between the two can be included in the vehicle-to-everything (V2X) information, which can save precious air interface resources, so that more meaningful information can be transmitted on limited bandwidth.

[0032] It is understood that in the embodiments of the present invention, autonomous driving includes assisted driving and autonomous driving. According to the definition of the Society of Automotive Engineers, L1-L5 are different levels of autonomous driving, among which low levels of autonomous driving are often referred to as assisted driving. Accordingly, in the embodiments of the present invention, the autonomous driving function includes various autonomous driving functions for achieving different levels of autonomous driving.

[0033] It can be understood that ODD monitoring is aimed at the autonomous driving function. In this regard, ODD monitoring is embodied in that the ODD according to an embodiment of the present invention interacts with at least one autonomous driving function module. In addition, according to the concept of the invention, it can also be extended to other modules, such as a perception module. In this case, means such as qualified behavior monitoring (NPM: nominal performance monitoring) can be adopted accordingly to achieve this.

[0034] The specific implementation of the present invention is described below in conjunction with the accompanying drawings.

[0035] Figure 1 FIG. 1 shows a driving assistance system 10 according to an embodiment of the present invention, which includes: a visibility module 11, an ODD module 12, and a communication interface 13. Figure 1 Also shown is a sensor 20 for capturing the autonomous driving environment. Figure 1 Also shown is an automatic driving function module 30 (hereinafter referred to as AD function module 30).

[0036] The sensor 20 may include an on-board sensor and / or a roadside sensor. The sensor may include, for example, one or more of a camera, an ultrasonic radar, a millimeter-wave radar, and a laser radar. According to an embodiment of the present invention, the sensor data refers to the sensor data containing the autonomous driving environment information output by the sensor 20 sensing the autonomous driving environment, for example, a video stream.

[0037] The visibility module 11 is used to describe the autonomous driving environment from the dimension of visibility. For example, the visibility module 11 generates visibility information based on sensor data. The visibility information includes qualitative measurement results and / or quantitative measurement results. Thus, the visibility information may include fine-grained visibility information. For example, the visibility information may include measurement results that quantitatively describe the autonomous driving environment in one or more aspects.

[0038] The visibility information generated by the visibility module 11 is transmitted to the ODD module 12 via the communication interface 13 in a wired and / or wireless communication manner. The communication interface 13 may include a hardware communication interface for implementing wired communication and / or an air interface for implementing wireless communication. It is understood that the communication interface 13 can be implemented to adapt to the communication mode (e.g., wired communication mode or wireless communication mode) and communication protocol (e.g., V2X communication protocol) between the visibility module 11 and the ODD module 12.

[0039] The ODD module 12 determines the ODD boundary based on the received visibility information (see Figure 2Based on the boundary, it is possible to determine whether the current autonomous driving condition is within the ODD boundary (i.e., IN ODD) or outside the ODD boundary (i.e., OUT ODD). When it is determined that the current autonomous driving condition is within the ODD boundary, the autonomous driving function is available, for example, the autonomous driving function is activated or maintained. When it is determined that the current autonomous driving condition is outside the ODD boundary, the autonomous driving function is not available, for example, the autonomous driving function is not activated or exited.

[0040] According to an embodiment of the present invention, the automatic driving condition includes external elements and internal elements. The external elements may include dynamic elements and static elements. Dynamic elements include, for example, object-related features such as the speed and direction of movement of other objects around the vehicle. Static elements include, for example, road-related features such as road topology, roadside guardrails, and road friction coefficient; weather-related features such as temperature, rainfall, and illumination; and traffic-related features such as traffic signs and traffic regulations.

[0041] The AD function module 30 is controlled within the limits of the ODD boundary determined by the ODD module 12 , for example, activated, kept running, deactivated or exited.

[0042] Figure 3A and Figure 3B Some examples of deployment of the above ODD are shown.

[0043] In one embodiment, see Figure 3A , the visibility module 11 and the ODD module 12 are both arranged on the vehicle, and the visibility module 11 and the ODD module 12 can exchange information in a wired communication manner. In this embodiment, the communication interface 13 can be implemented as a hardware communication interface, for example, a CAN interface coupled to a vehicle bus. In this embodiment, the sensor 20 can be implemented as a vehicle-mounted sensor. In addition, in this embodiment, the AD function module 30 can be included in the driving assistance system 10. And, in this embodiment, the driving assistance system can be implemented as a vehicle-mounted system.

[0044] Figure 3A A variation of the embodiment (not shown) is that the visibility module 11 and the ODD module 12 are both arranged on the roadside unit, and the visibility module 11 and the ODD module 12 can exchange information in a wired communication manner. In this embodiment, the communication interface 13 can be implemented as a hardware communication interface, for example, a cable interface for implementing wired communication between the visibility module 11 and the ODD module 12. In this variation, the sensor 20 can be implemented as a vehicle-mounted sensor.

[0045] In another embodiment, see Figure 3B, the visibility module 11 is set in the cloud server, the ODD module 12 is set on the vehicle, and the visibility module 11 and the ODD module 12 exchange information in a wireless communication manner via the air interface 13. In this embodiment, the sensor 20 can be implemented as a roadside sensor, and the sensor data output by the sensor 20 is uploaded to the visibility module 11 located on the cloud server in a wireless communication manner.

[0046] Figure 3B A modified example (not shown) of the embodiment is that the visibility module 11 is arranged in the roadside unit, the ODD module 12 is arranged on the vehicle V, and the visibility module 11 and the ODD module 12 exchange information in a wireless communication manner via the air interface 13. In this embodiment, the sensor 20 can be implemented as a roadside sensor, and the sensor data output by the sensor 20 is transmitted to the visibility module 11 located in the roadside unit in a wired communication manner.

[0047] When the visibility module 11 is set on the roadside or in the cloud, the calculation of visibility information is performed on the roadside or in the cloud, thereby saving computing resources on the vehicle side and avoiding increasing the computing power demand on the vehicle side.

[0048] According to an embodiment of the present invention, the communication interface 13 may be a hardware interface or an air interface. The hardware interface, for example, is adapted to the physical connection form between the visibility module 11 and the ODD module 12 and the specification of the transmitted electrical signal. The air interface, for example, is matched to the communication protocol between the visibility module 11 and the ODD module 12 and the format of the transmitted data. The air interface, for example, may be one or more of Bluetooth, Wi-Fi, V2X (e.g., V2I), and NFC.

[0049] Figure 4 The figure shows an information transmission method 400 for a driving assistance system according to an embodiment of the present invention. The method 400 can be implemented in the driving assistance system 10, so the above description of the driving assistance system 10 is also applicable to this.

[0050] See also Figure 4 At block 402, the visibility module 11 generates visibility information based on sensor data from the sensor 20. The visibility information includes qualitative measurements and / or quantitative measurements.

[0051] In one embodiment, referring to block 4021, the visibility module 11 qualitatively measures the autonomous driving environment based on the sensor data to obtain a qualitative measurement result. The qualitative measurement result may include one or more items for qualitatively describing the autonomous driving environment from one or more aspects. Some examples of qualitative measurement results are described below.

[0052] An example of a qualitative measurement result is a fine-grained weather measurement result, which contains a descriptor for describing the weather type and a corresponding label, which is used to qualitatively describe the weather condition. For example, the weather type is fog, and the corresponding label is dense fog. For another example, the weather type is rain, and the corresponding label is light rain. It can be seen that the weather measurement result not only contains the weather type, but also contains a more fine-grained description than the weather type, that is, the above-mentioned label for qualitatively describing the weather condition. Here, "fine-grained" can be understood as a more detailed description of the weather condition than the weather type (for example, compared to the next level description of the weather type). That is, on the basis of the weather type, the condition of this type of weather is further described.

[0053] In one embodiment, fine-grained weather measurement results can be obtained by training a machine learning model. For example, the machine learning model is trained using data containing fine-grained labels as training data, so that the trained machine learning model has the ability to output fine-grained weather measurement results based on input (e.g., the above-mentioned sensor data).

[0054] Another example of a qualitative measurement result is one that includes information that can reflect the non-uniformity of the visibility of different areas within the field of view of the sensor 20. For example, in the case of street lighting, the qualitative measurement result includes information that the illumination is strong within a distance range of 0-10 meters from the camera, the illumination is medium within a distance range of 10-50 meters from the camera, and the illumination is weak when the distance from the camera is greater than 50 meters.

[0055] In one embodiment, referring to block 4022, the visibility module 11 quantitatively measures the autonomous driving environment based on the sensor data to obtain a quantitative environmental measurement result. The quantitative measurement may include one or more items for quantitatively describing the autonomous driving environment from one or more aspects. Some examples of quantitative measurement results are described below.

[0056] An example of a quantitative measurement result is: the measurement result includes a visibility value for each sub-area in the different sub-areas within the field of view of the sensor 20. For example, on a grid map of an autonomous driving environment, the visible range of the sensor 20 is determined, and each grid within the range corresponds to a sub-area or multiple grids correspond to a sub-area. The visibility value of the sensor 20 for each sub-area is determined. The visibility value can quantitatively express the degree of visibility of the sensor 20 to each sub-area, that is, the degree to which the sensor 20 can "see" clearly. For example, the smaller the value, the more blurry the sensor 20 sees.

[0057] Another example of a quantitative measurement result is: the measurement result includes the farthest visible distance in the field of view of the sensor 20 and in the ray directions at different angles relative to the sensor 20. For example, the field of view of the sensor 20 has two sides, one side is the starting side, and the other side is the ending side. In the field of view and in the ray direction of 15° relative to the starting side, the farthest visible distance of the sensor 20 is 50 meters. In the field of view and in the ray direction of 55° relative to the starting side, the farthest visible distance of the sensor 20 is 250 meters.

[0058] It should be noted that there is such a situation: in a certain ray direction (for example, the above-mentioned 15° ray direction relative to the starting edge), the original maximum visible distance is 50. However, if a person wearing a reflective yellow vest (for example, a traffic safety suit) appears at a distance of 65 meters from the sensor 20 in the ray direction, then the distance is originally invisible because it exceeds the maximum visible distance. However, the reflective yellow vest causes the object at this distance to become visible. At this time, the farthest distance in the ray direction should be changed from 50 meters to 65 meters. Therefore, according to an embodiment of the present invention, the farthest visible distance should include the farthest visible distance when the autonomous driving environment changes.

[0059] Figure 5 An example of visual information including the above-mentioned qualitative and quantitative measurement results is shown. Figure 5 A grid map of an autonomous driving environment is shown in FIG. , and the grid map includes two quantitative measurement results and one qualitative measurement result. Figure 5 As shown, the curve circled by the box Q1 represents a quantitative measurement result. This curve is a farthest visible curve used to describe the farthest visible distance of the sensor 20 in its field of view. The farthest visible curve is composed of a plurality of farthest visible position points in the direction of rays at different angles in the sensor's field of view. The grid shown by the lead line Q2 contains the value of the visibility of the sensor 20 to the grid. In addition, the following qualitative measurement results can also be included in the grid map: dense fog.

[0060] Continue to see Figure 4 In block 404 , the visibility information generated by the visibility module 11 is transmitted to the ODD module 12 via the communication interface 13 .

[0061] In block 406 , the ODD module 12 uses the received visibility information to determine the ODD boundary and thereby decides on activation or exit of the autonomous driving function.

[0062] In one embodiment, the ODD module 12 determines the ODD boundary based on the qualitative and / or quantitative measurement results in the visibility information and the visibility threshold. For example, when the qualitative and / or quantitative measurement results meet the visibility threshold, the current autonomous driving condition is determined to be within the ODD boundary. On the contrary, when the qualitative and / or quantitative measurement results do not meet the visibility threshold, the current autonomous driving condition is determined to be outside the ODD boundary.

[0063] The visibility threshold refers to the value of the visibility parameter when the visibility level of the sensor 20 is just equal to the minimum requirement (i.e., the passing level) of the visibility level of the sensor for the autonomous driving function. Specifically, when the visibility performance of the sensor 20 is very good, the sensor can "see" the autonomous driving environment very clearly. If the value of the visibility parameter in such a situation is used as the visibility threshold, a large number of autonomous driving conditions will fall outside the ODD, resulting in frequent exit of the autonomous driving function. When the visibility performance of the sensor is very poor, the sensor "sees" the autonomous driving environment very unclearly. If the value of the visibility parameter in such a situation is used as the visibility threshold, a large number of autonomous driving conditions will fall into the ODD, resulting in the autonomous driving function not exiting even when it cannot be executed normally. According to an embodiment of the present invention, the visibility threshold is predetermined to be a value between the above two situations, that is, a value when the sensor can "vaguely" see the autonomous driving environment.

[0064] It is understandable that for visibility parameters that describe visibility in different quantitative ways, the specific expression of the visibility threshold is different. For example, for the visibility distance as a visibility parameter, the visibility threshold is a specific value for the visibility distance. For the rainfall as a visibility parameter, the visibility threshold is a specific value for the rainfall.

[0065] In addition, according to an embodiment of the present invention, visibility information may be included in vehicle-to-everything (V2X) information and sent to the ODD module. For example, the visibility information is included in a predetermined field or a predetermined data frame of a V2X message. The predetermined field may be a field newly added in a V2X (e.g., V2I) message and specifically used for visibility information. The predetermined field may also be implemented by means of a reserved bit in a field used for other information in a V2X message. The predetermined data frame may be an existing data frame in a V2X message or a newly added data frame.

[0066] The visibility information may include the following data elements: an environment type element, a visibility grid element, and a visibility description element. The environment type element, for example, includes: fine-grained label data that describes the weather conditions more finely than the weather type (e.g., heavy rain, moderate rain, light rain, heavy fog, moderate fog, light fog, heavy snow, moderate snow, light snow, foggy rain, dizziness, dimness, and darkness). The visibility grid element includes one or more of the following: grid position (e.g., using an offset position relative to a reference position to express the position of each grid); grid resolution (e.g., the x-axis resolution and y-axis resolution of a 2D grid; or the x-axis resolution, y-axis resolution, and z-axis resolution of a 3D grid) and the degree of visibility on the grid; the degree of visibility on the grid (e.g., the degree of visibility of each grid expressed in the form of a binary value or probability). The visibility description element includes: the farthest visible distance of the sensor in each direction within its field of view. The granularity of the direction may be defined in the visibility description element.

[0067] In one embodiment, the visibility information may be included as a data frame in vehicle-to-everything (V2X) information, such as a roadside safety message (RSM). The data frame may include predetermined data elements (DE). The data element may include one or more of the following: 1) a descriptor for describing the weather type and a label for qualitatively describing the weather type from the perspective of visibility; 2) information that can reflect the non-uniformity of the visibility of the sensor to different areas within its field of view; 3) the value of the visibility of the sensor to each of the multiple sub-areas within its field of view; 4) a farthest visibility curve for describing the farthest visible distance of the sensor within its field of view. The data frame may be an existing data frame or a newly added data frame in an RSM or other V2X message. The aforementioned data elements and transmission methods contained in the visibility information can greatly save resources of the air interface.

[0068] It should be understood that the ODD boundary corresponds to the autonomous driving function. In other words, the autonomous driving function corresponds to the ODD boundary judgment logic. Different autonomous driving functions may correspond to different ODD boundary judgment logics, for example, including different judgment indicators. For example, the ODD boundary judgment indicator of the lane keeping function is the accuracy of the sensor's lane detection, and the ODD boundary judgment indicator of the forward collision warning function is the accuracy of the sensor's recognition of the object in front.

[0069] According to an embodiment of the present invention, a machine-readable storage medium is further provided, which stores executable instructions. When the instructions are executed, one or more processors execute the above method 400.

[0070] It is to be understood that the processor can be implemented using electronic hardware, computer software or any combination thereof. Whether these processors are implemented as hardware or software will depend on specific application and the overall design constraints imposed on the system. As an example, the processor provided in the present invention, any part of the processor or any combination of the processor can be implemented as a microprocessor, a microcontroller, a digital signal processor (DSP), a field programmable gate array (FPGA), a programmable logic device (PLD), a state machine, a gate logic, a discrete hardware circuit and other suitable processing components configured to perform the various functions described in the present disclosure. The function of the processor provided in the present invention, any part of the processor or any combination of the processor can be implemented as software performed by a microprocessor, a microcontroller, a DSP or other suitable platforms.

[0071] It is to be understood that software should be broadly considered to represent instructions, instruction sets, codes, code segments, program codes, programs, subroutines, software modules, applications, software applications, software packages, routines, subroutines, objects, running threads, processes, functions, etc. Software can reside in a computer-readable medium. A computer-readable medium can include, for example, a memory, which can be, for example, a magnetic storage device (e.g., a hard disk, a floppy disk, a magnetic stripe), an optical disk, a smart card, a flash memory device, a random access memory (RAM), a read-only memory (ROM), a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), a register, or a removable disk. Although the memory is shown as being separated from the processor in the various aspects provided in the present disclosure, the memory can also be located inside the processor (e.g., a cache or a register).

[0072] Although some embodiments have been described above, these embodiments are given by way of example only and are not intended to limit the scope of the invention. The appended claims and their equivalents are intended to cover all modifications, substitutions and changes made within the scope and spirit of the invention.

Claims

1. A driving assistance system, include: a visibility module configured to generate visibility information based on sensor data including autonomous driving environment information of the vehicle received from a sensor, wherein the visibility information includes qualitative measurement results obtained by qualitatively measuring the autonomous driving environment and / or quantitative measurement results obtained by quantitatively measuring the autonomous driving environment; as well as The ODD module is configured to receive the visibility information from the visibility module in a wired and / or wireless communication manner, and determine an ODD boundary based on the visibility information, wherein the ODD boundary is used to assist in executing at least one autonomous driving function of the vehicle.

2. The driving assistance system according to claim 1, in, The qualitative measurement results include labels for qualitatively describing weather conditions under at least one weather type.

3. The driving assistance system according to claim 2, in, The labels are output from a machine learning model trained with fine-grained labeled data that contains a more detailed description of the weather condition than the weather type.

4. The driving assistance system according to any one of claims 1 to 3, in, The qualitative measurements include information that can reflect the non-uniformity of the sensor's visibility into different areas within its field of view.

5. The driving assistance system according to any one of claims 1 to 4, in, The quantitative measurement result includes: a value of visibility of each sub-area in a plurality of sub-areas within the field of view of the sensor.

6. The driving assistance system according to any one of claims 1 to 5, in, The quantitative measurement results include: a farthest visible curve for describing the farthest visible distance of the sensor within its field of view; And wherein, the farthest visible curve is composed of a plurality of farthest visible distances of the sensor in the direction of rays at different angles within its field of view.

7. The driving assistance system according to claim 1, in, The visibility information is included in vehicle-to-everything (V2X) information, and the visibility information includes one or more of the following: - descriptors for describing weather types and labels for qualitatively describing weather conditions under that weather type; - Information that can reflect the non-uniformity of the sensor's visibility to different areas within its field of view; - a value of the sensor's visibility for each of a plurality of sub-areas within its field of view; - The maximum visible distance curve used to describe the maximum visible distance of the sensor within its field of view.

8. The driving assistance system according to claim 1, in, The ODD module is further configured to assist in executing at least one autonomous driving function of the vehicle according to the determined ODD boundary, including: The ODD module determines whether the current autonomous driving condition is within or outside the ODD boundary based on the determined ODD boundary, thereby determining to activate, continue to maintain, exit, deactivate or expand the at least one autonomous driving function.

9. The driving assistance system according to any one of claims 1 to 8, further comprising a communication interface, in, The communication interface is a hardware communication interface for realizing wired communication between the visibility module and the ODD module, or the communication interface is an air interface for realizing wireless communication between the visibility module and the ODD module.

10. The driving assistance system according to any one of claims 1 to 9, in, The visibility module and the ODD module are arranged in the same roadside equipment or both are arranged in the vehicle; or One of the visibility module and the ODD module is arranged in the vehicle, and the other is arranged in a roadside unit or a cloud server.

11. The driving assistance system according to claim 1, in, The driving assistance system also includes an automatic driving function module for implementing the at least one automatic driving function, and the automatic driving function module is arranged on the vehicle.

12. An information transmission method for a driving assistance system according to any one of claims 1 to 11, include: The visibility information is included in vehicle-to-everything (V2X) information and transmitted from the visibility module to the ODD module.

13. The information transmission method according to claim 12, in, The visibility information is contained in a predetermined field or a predetermined data frame of the V2X message and includes the following data elements: an environment type element, a visibility grid element, and a visibility description element, And wherein the environment type element includes: fine-grained label data that describes the weather condition in a more detailed manner than the weather type; The visibility grid element includes one or more of the following: grid position, grid resolution, and visibility on the grid; The visibility description element includes: the farthest visible distance of the sensor in each direction within its field of view.

14. A machine-readable storage medium storing executable instructions, which, when executed, cause a processor to perform the method according to claim 13.

Images