Driving assistance system, system and method for extending operational design domain boundary

Abstract

The invention provides a driving assistance system, a system and a method for extending an operational design domain (ODD) boundary. The system (10) includes an ODD module (12) configured to: receive a visibility parameter representing an actual visibility level of the sensor to the autonomous driving environment; and determining an ODD boundary based on a comparison result between an actual visibility level represented by the visibility parameter and a predetermined visibility level. The system further comprises an extension module (13) configured to: monitor the actual visibility level represented by the visibility parameter and the predetermined visibility level; and expanding at least a portion of the ODD boundary in the event that it is monitored that the actual visibility level increases to be greater than or equal to the predetermined visibility level and / or that the predetermined visibility level is configured lower such that the actual visibility level is greater than or equal to the configured predetermined visibility level.

Description

Technical Field

[0001] The present invention relates to a system and method for extending the boundaries of an operational design domain. The present invention also relates to an operational design domain including the system. 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 the exit of the lane keeping function when it rains, that is, the rainy environment will be outside the ODD. However, the existing ODD does not specifically limit the amount of rain 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.

[0004] In this regard, for L2 level autonomous driving functions, the vehicle still relies on the driver's control, and if the system chooses to exit the autonomous driving function, it may not have much impact on the user experience. However, for autonomous driving functions above L3, most of them allow users to take their hands, feet and eyes off the car. If the system frequently chooses to exit the autonomous driving function, it will cause a negative user experience. Summary of the invention

[0005] In this context, one aspect of the present invention provides a system for extending the boundary of an operational design domain (ODD). The system includes an ODD module configured to: receive a visibility parameter representing an actual visibility level of a sensor to an autonomous driving environment; and determine the ODD boundary based on a comparison result between the actual visibility level represented by the visibility parameter and a predetermined visibility level, wherein the predetermined visibility level is configurable. The system also includes an extension module configured to: monitor the actual visibility level represented by the visibility parameter and the predetermined visibility level; and extend at least a portion of the ODD boundary when it is monitored that the actual visibility level increases to be greater than or equal to the predetermined visibility level and / or the predetermined visibility level is configured lower so that the actual visibility level is greater than or equal to the configured predetermined visibility level.

[0006] In one embodiment, the extended ODD boundary is used to improve the availability of at least one autonomous driving function.

[0007] In one embodiment, improving the availability of the at least one autonomous driving function includes: reducing the exit frequency of the at least one autonomous driving function, and / or extending the availability time of the at least one autonomous driving function, and / or increasing the scenarios in which the at least one autonomous driving function is activated.

[0008] In one embodiment, the predetermined visibility level refers to a minimum level of visibility required by the at least one driving function for the sensor.

[0009] In one embodiment, the actual visibility level is increased by one or more of the following methods:

[0010] -Hardware upgrade of sensors;

[0011] -Adding multi-view or multi-modal sensors; and

[0012] -Algorithm optimization for sensor data processing.

[0013] In one embodiment, the predetermined visibility level is reduced by one or more of the following methods:

[0014] - operation by the vehicle driver or manipulation by the autonomous driving controller causes the predetermined visibility level to be configured lower; and

[0015] - Reducing the minimum level of sensor visibility required by at least one autonomous driving function by sacrificing part of the performance of at least one driving function.

[0016] In one embodiment, the expansion module is further configured to determine whether the current autonomous driving condition is inside or outside the extended ODD boundary based on the extended ODD boundary, thereby determining whether to activate, continue to maintain, exit, deactivate or expand the at least one autonomous driving function.

[0017] In one embodiment, the system further comprises a visibility module configured to generate the visibility parameters based on the sensor data from the sensor, wherein the visibility parameters comprise one or more parameters that quantitatively describe the autonomous driving environment in one or more ways.

[0018] In one embodiment, the ODD module is coupled to the visibility module and receives visibility parameters from the visibility module; and the ODD module and a perception module associated with at least one autonomous driving function or an autonomous driving environment truth system for the perception module are decoupled.

[0019] According to another aspect of the present invention, a driving assistance system for a vehicle is provided, comprising an availability determination module for obtaining an ODD boundary and determining the availability of at least one autonomous driving function according to the obtained ODD boundary. The ODD boundary is an extended ODD boundary determined by the system (10) for extending the boundary of an operational design domain as described above.

[0020] In one embodiment, the ODD boundary corresponds to the at least one autonomous driving function.

[0021] In one embodiment, the driving assistance system further includes: an automatic driving function module, used to implement the at least one automatic driving function.

[0022] In one embodiment, the availability determination module is arranged in the ODD module, or in the autonomous driving function module, or in a module that is independent of the ODD module and the autonomous driving function module and can communicate with both.

[0023] According to another aspect of the present invention, a method for extending the boundary of an operational design domain (ODD) is provided, which is performed by the system as described above, and the method includes: receiving a visibility parameter, which represents an actual visibility level of a sensor to an autonomous driving environment; determining the ODD boundary based on a comparison result between the actual visibility level represented by the visibility parameter and a predetermined visibility level, wherein the predetermined visibility level is configurable; monitoring the actual visibility level represented by the visibility parameter and the predetermined visibility level; and extending at least a portion of the ODD boundary in the event that it is monitored that the actual visibility level increases to be greater than or equal to the predetermined visibility level and / or the predetermined visibility level is configured to be lower so that the actual visibility level is greater than or equal to the configured predetermined visibility level.

[0024] According to 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 caused to perform the method as described above.

[0025] 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

[0026] 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.

[0027] Figure 1 is a schematic block diagram of a system for extending an ODD boundary according to an embodiment of the present invention.

[0028] Figure 2 is a schematic diagram of ODD boundary extension according to an embodiment of the present invention.

[0029] Figure 3 is a flow chart of a method for extending an ODD boundary according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The inventors found that the prior art has the problem of unclear description of the ODD boundary. Moreover, it often happens that a certain autonomous driving condition (use case) directly causes the autonomous driving function to exit, that is, the availability of the autonomous driving function is greatly limited simply because a certain autonomous driving condition falls outside the ODD boundary.

[0031] In this regard, embodiments of the present invention relate to a method and system for extending an ODD boundary, and an ODD having an extended boundary.

[0032] The system according to an embodiment of the present invention includes: a visibility module, an ODD module and an extension module. The visibility module provides visibility information (e.g., visibility parameters including quantitative indicators). The visibility information is used as an input of the ODD module to determine the ODD boundary. Furthermore, the extension module extends at least part of the determined ODD boundary so that the availability of the autonomous driving function monitored by the ODD is improved.

[0033] The ODD product according to the embodiment of the present invention can bring users a better autonomous driving experience, because the user will feel the ODD monitoring after the expansion boundary, that is, the user will feel the autonomous driving function with improved usability.

[0034] According to the embodiment of the present invention, a strategy different from the perception judgment based on the truth value system usually adopted in the prior art is adopted, that is, the embodiment of the present invention adopts the visibility-based automatic driving function availability monitoring. Therefore, the embodiment of the present invention does not need to rely on the expensive truth value system, does not need to know the specific accuracy of the perception, and only needs to determine whether the current automatic driving condition reaches the "pass" through the predetermined visibility level (visibility parameter threshold) to realize the automatic driving function availability monitoring.

[0035] It should be noted 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.

[0036] The specific implementation of the present invention is described below in conjunction with the accompanying drawings.

[0037] Figure 1 A system 10 for extending the ODD boundary according to an embodiment of the present invention (hereinafter referred to as system 10) is shown, which includes: a visibility module 11, an ODD module 12, and an extension module 13. Figure 1 Also shown is a sensor 20 for capturing the autonomous driving environment. Figure 1 Also shown are modules related to autonomous driving, which include a perception module 30 and an autonomous driving function module 40 (hereinafter referred to as AD function module 40).

[0038] 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, sensor data refers to sensor data containing autonomous driving environment information output by the sensor 20 when sensing the autonomous driving environment, for example, a video stream. It is worth noting that both the perception module 30 and the visibility module 11 receive sensor data, but the perception module 20 and the visibility module 11 are decoupled.

[0039] The perception module 30 understands the autonomous driving environment based on the sensor data, thereby obtaining environmental perception results such as obstacle information or road information.

[0040] The AD function module 40 performs the autonomous driving function based on the environmental perception result from the perception module 30. The AD function module 40 may include multiple submodules for implementing the autonomous driving function. The multiple submodules include, for example, a planning module, a decision module, and an execution module. It is understandable that different autonomous driving functions may include different submodules.

[0041] 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 parameters based on sensor data. The visibility parameters are used to quantitatively represent the visibility of the autonomous driving environment by the sensor 20. The output end of the visibility module 11 is coupled to the input end of the ODD module 12 so that the visibility module 11 outputs the generated visibility parameters to the ODD module 12.

[0042] The ODD module 12 determines the ODD boundary based on the visibility parameter and the visibility parameter threshold received from the visibility module 11 (see Figure 2 B1 is shown by the thick black solid line in the figure). Based 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 corresponding autonomous driving function is not available, for example, the autonomous driving function is not activated or exited.

[0043] 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 vehicles around the vehicle. Static elements include, for example, road-related features such as 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.

[0044] The expansion module 13 is coupled to the ODD module 12 and the AD function module 40 respectively. The expansion module 13 is used to expand at least a portion of the determined ODD boundary (for example, see Figure 2 The autonomous driving function module 40 is based on the gray thin solid line in the figure, which shows the extended ODD boundary, and interacts with the autonomous driving function module 40 based on the extended boundary. For example, it is determined whether the current autonomous driving condition is within the ODD boundary or outside the ODD boundary based on the extended ODD boundary. In this way, the availability of the autonomous driving function (for example, the available range of the autonomous driving function) can be improved. For example, the autonomous driving condition that originally fell into the area between the black thick solid line and the gray thin solid line will be considered to be outside the ODD when the black thick line is used as the boundary, and will be considered to be within the ODD boundary when the expanded thin line is used as the boundary. In this way, some use cases that were originally close to and outside the ODD boundary are changed to be within the ODD boundary, thereby improving the availability of the autonomous driving function.

[0045] It should be understood that the naming of the ODD module 12 and the expansion module 13 is functional (logical) and is not intended to limit their specific implementation methods or physical locations. They can be arranged in the same circuit or chip, or in different circuits or chips. In addition, the ODD module 12 and the expansion module 13 can be combined into one module, or they can be divided into multiple sub-modules.

[0046] In one embodiment, the ODD module 12 and the extension module 13 are both disposed on the vehicle, and the autonomous driving function module 40 is also disposed on the vehicle. In this way, the ODD boundary extended by the extension module 13 acts on the autonomous driving function module 40, thereby improving the availability of the autonomous driving function on the vehicle side.

[0047] Figure 3 A method 300 for extending an ODD boundary according to an embodiment of the present invention is shown. The method 300 can be implemented by means of the above system 10, so the above description of the system 10 is also applicable here.

[0048] In box 302, the visibility module 11 generates a visibility parameter based on the sensor data. The visibility parameter is used to quantitatively represent the visibility of the sensor 20 to the autonomous driving environment, that is, the actual visibility level of the sensor. The visibility parameter can be understood as a quantitative indicator that describes the autonomous driving environment from the perspective of visibility. The visibility module 11 can analyze and process the sensor data and obtain the visibility parameter. The present invention does not limit the specific implementation method of the visibility module 11 obtaining the visibility parameter based on the sensor data.

[0049] The visibility parameter may include one or more visibility parameters, which are used to quantitatively express visibility from one or more aspects, that is, to quantitatively describe the autonomous driving environment from one or more aspects. For example, the visual distance of the sensor is described from the rainfall, light intensity, and fog concentration respectively; or the visual distance of the sensor is described from the combination of rainfall and occlusion; or the visual distance is described from the combination of rainfall and the estimated duration of the rainfall.

[0050] At block 304 , the ODD module 12 receives the visibility parameter from the visibility module 11 and determines the ODD boundary based on a comparison result between the actual visibility level represented by the visibility parameter and the predetermined visibility level represented by the visibility parameter threshold.

[0051] The visibility parameter threshold represents a predetermined visibility level of the sensor 20. The predetermined visibility level can be understood as: achieving the minimum level required by the autonomous driving function for the visibility level of the sensor 20.

[0052] Specifically, when the visibility of the sensor 20 is very good, the sensor can "see" the autonomous driving environment very clearly. If the visibility parameter threshold is set according to the visibility level in such a situation, a large number of autonomous driving conditions will fall outside the ODD, resulting in frequent exit of the autonomous driving function. When the visibility of the sensor 20 is very poor, the sensor "sees" the autonomous driving environment very unclearly. If the visibility parameter threshold is set according to the visibility level in such a situation, 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 parameter threshold is predetermined to be a value between the above two situations, that is, the value when the sensor can "vaguely" see the autonomous driving environment, and the "vague" visibility level is the above-mentioned predetermined visibility level, that is, the minimum level required by the autonomous driving function for the visibility level of the sensor.

[0053] It should be noted that for visibility parameters that describe visibility in different quantitative ways, the specific expressions of visibility parameter thresholds are different. For example, the visibility parameter is expressed as a visible distance, for example, the visible distance is 50 meters. In this case, the visibility parameter threshold should be a specific value for the visible distance, for example, the visible distance threshold is 45 meters.

[0054] Below, taking rainfall and visible distance as examples, an example of the ODD module 12 determining the ODD boundary based on the comparison result between the visibility parameter and the visibility parameter threshold is introduced. In one embodiment, the visibility parameter is expressed as the visible distance of the sensor for a rainfall, and the corresponding visibility parameter threshold is the visibility distance threshold. The ODD module 12 determines that: if the visible distance under the current autonomous driving condition is greater than or equal to the visibility distance threshold, the current autonomous driving condition is within the ODD boundary; conversely, if the visible distance under the current autonomous driving condition is less than the visibility distance threshold, the current autonomous driving condition is outside the ODD boundary. Thus, the ODD module 12 determines the ODD boundary. For example, in an autonomous driving condition: the visibility parameter is expressed as the visible distance of the sensor is 50 meters in weather with a rainfall of 10 mm / hour, and the corresponding visibility parameter threshold is 40 meters. The visible distance of 50 meters under this weather condition is greater than the visibility distance threshold of 40 meters. Therefore, the autonomous driving condition is within the ODD boundary.

[0055] In block 306, the expansion module 13 monitors the actual visibility level and the predetermined visibility level indicated by the visibility parameter. When it is monitored that the actual visibility level increases to be greater than or equal to the predetermined visibility level and / or the predetermined visibility level decreases to be less than or equal to the actual visibility level, at least a portion of the ODD boundary is expanded; and the availability of at least one autonomous driving function is improved by means of the expanded ODD boundary.

[0056] Expanding the ODD boundary can make the autonomous driving conditions that were originally close to the ODD boundary but outside the ODD boundary fall within the expanded ODD boundary, thereby improving the availability of the autonomous driving function. For example, the autonomous driving function can run longer, and / or the autonomous driving function can be activated in more scenarios, and / or the scenarios in which the autonomous driving function is activated are increased.

[0057] In general, the actual visibility level is made to reach the predetermined visibility level by increasing the actual visibility level and / or configuring the predetermined visibility level to be lower.

[0058] In one embodiment, the expansion module 13 monitors the actual visibility level represented by the visibility parameter and the predetermined visibility level. In this embodiment, the actual visibility level is increased to be greater than or equal to the predetermined visibility level. The ways in which the actual visibility level can be increased include one or more of the following: 1) hardware upgrade of the sensor (for example, replacing the hardware of the sensor with hardware with higher performance relative to the original hardware. For another example, replacing the sensor with a sensor with a larger field of view or a higher resolution); 2) adding multi-view or multi-modal sensors (for example, adding sensors that collect autonomous driving environment information from multiple angles or adding multiple types of sensors to make up for the shortcomings of a certain type of sensor in a specific environment); 3) algorithm optimization of sensor data processing (for example, obtaining visibility parameters with higher visibility levels through improved sensor data fusion algorithms or using retrained machine learning models).

[0059] In another embodiment, the expansion module 13 monitors the actual visibility level indicated by the visibility parameter and the predetermined visibility level. In this embodiment, the predetermined visibility level is configured to be lower so that the actual visibility level is greater than or equal to the reconfigured predetermined visibility level. Situations in which the predetermined visibility level can be configured lower include one or more of the following: 1) the operation of the vehicle driver or the manipulation of the automatic driving controller enables the predetermined visibility level to be configured lower (for example, when the rainfall exceeds 10 mm / hour, the visible distance as the visibility parameter threshold is 100 meters, that is, the automatic driving function can be activated only when the visible distance is greater than or equal to 100 meters. But if the driver actively reduces the vehicle speed or the automatic driving controller issues an instruction to reduce the vehicle speed at this time, the visible distance as the visibility parameter threshold will be reduced from 100 meters to 80 meters. That is, the automatic driving function can be operated when the visible distance is greater than or equal to 80 meters); 2) by sacrificing part of the performance of the automatic driving function to reduce the minimum level of the visibility level of the sensor required by the automatic driving function (for example, the effective distance of lane line recognition is reduced from the original 100 meters to 80 meters, then the requirement for the sensor's visible distance will also be reduced accordingly. For another example, the detection area of ​​the forward collision warning function is reduced, then the requirement for the sensor's visible range will also be reduced accordingly).

[0060] In block 308, the expansion module 13 uses the expanded ODD boundary to determine whether the current autonomous driving condition is within or outside the expanded ODD boundary, thereby determining whether to activate, continue to maintain, exit, deactivate, or expand the autonomous driving function. An example of expanding the autonomous driving function is to add a lane keeping function to the applicable scenario.

[0061] According to an embodiment of the present invention, there is also provided a driving assistance system for a vehicle, which includes an availability determination module for obtaining an ODD boundary and determining the availability of at least one autonomous driving function according to the obtained ODD boundary. The ODD boundary is an extended ODD boundary determined by a system for extending the boundary of an operational design domain according to an embodiment of the present invention. The availability determination module can be implemented with the aid of an ODD module, for example, by being set in the ODD module. The availability determination module can also be implemented with the aid of an autonomous driving function module, for example, by being set in the autonomous driving function module. The availability determination module can also be implemented as a module (not shown) that is independent of the ODD module and the autonomous driving function module and can communicate with both. In one embodiment, the driving assistance system includes an autonomous driving function module.

[0062] 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.

[0063] 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 300.

[0064] 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.

[0065] 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).

[0066] 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 system (10) for extending the boundaries of an operational design domain (ODD), include: The ODD module (12) is configured to: receive a visibility parameter representing an actual visibility level of the sensor to the autonomous driving environment; and determining an ODD boundary based on a comparison result between an actual visibility level represented by the visibility parameter and a predetermined visibility level, wherein the predetermined visibility level is configurable; as well as An expansion module (13) is configured to: monitor the actual visibility level represented by the visibility parameter and the predetermined visibility level; and expand at least a portion of the ODD boundary when it is monitored that the actual visibility level increases to be greater than or equal to the predetermined visibility level and / or the predetermined visibility level is configured to be lower so that the actual visibility level is greater than or equal to the configured predetermined visibility level.

2. The system (10) as claimed in claim 1, in, The extended ODD boundary is used to improve availability of at least one autonomous driving function.

3. The system (10) as claimed in claim 2, in, Improving the availability of the at least one autonomous driving function includes: reducing the exit frequency of the at least one autonomous driving function, and / or extending the available time of the at least one autonomous driving function, and / or increasing the scenarios in which the at least one autonomous driving function is activated.

4. The system (10) according to any one of claims 1 to 3, in, The predetermined visibility level refers to a minimum level of visibility of the sensor required by the at least one driving function.

5. The system (10) according to any one of claims 1 to 4, in, Improve the actual visibility level by one or more of the following: -Hardware upgrade of sensors; -Adding multi-view or multi-modal sensors; and -Algorithm optimization for sensor data processing.

6. The system (10) according to any one of claims 1 to 5, in, The predetermined visibility level is reduced by one or more of the following: - the predetermined visibility level is configured to be lower due to the operation of the vehicle driver or the manipulation of the automatic driving controller; and - Reducing the minimum level of sensor visibility required by at least one autonomous driving function by sacrificing part of the performance of at least one driving function.

7. The system (10) according to any one of claims 1 to 6, in, The expansion module is also configured to: Based on the extended ODD boundary, it is determined whether the current autonomous driving condition is within or outside the extended ODD boundary, so as to determine whether to activate, continue to maintain, exit, deactivate or expand the at least one autonomous driving function.

8. The system (10) as described in any one of claims 1-7 further includes a visibility module (11) configured to generate the visibility parameters based on the sensor data from the sensor, wherein the visibility parameters include one or more parameters that quantitatively describe the autonomous driving environment in one or more ways.

9. The system (10) as claimed in claim 8, in, The ODD module is coupled to the visibility module and receives visibility parameters from the visibility module; and The ODD module is decoupled from a perception module associated with the at least one autonomous driving function or an autonomous driving environment truth system for the perception module.

10. A driving assistance system for a vehicle, include: an availability determination module, configured to obtain an ODD boundary and determine availability of at least one autonomous driving function according to the obtained ODD boundary; The ODD boundary is an extended ODD boundary determined by the system (10) for extending the boundary of the operational design domain according to any one of claims 1 to 9.

11. The driving assistance system according to claim 10, in, The ODD boundary corresponds to the at least one autonomous driving function.

12. The driving assistance system according to claim 10, further comprising: include: An automatic driving function module (40) is used to implement the at least one automatic driving function.

13. The driving assistance system according to claim 12, in, The availability determination module is arranged in the ODD module, or in the autonomous driving function module (40), or is arranged as a module independent of the ODD module and the autonomous driving function module and capable of communicating with both.

14. A method for extending the boundary of an operational design domain (ODD), performed by the system according to any one of claims 1 to 9, the method include: receiving a visibility parameter representing an actual visibility level of the sensor to the autonomous driving environment; determining an ODD boundary based on a comparison result between an actual visibility level represented by the visibility parameter and a predetermined visibility level, wherein the predetermined visibility level is configurable; monitoring an actual visibility level represented by the visibility parameter and the predetermined visibility level; and In case that it is monitored that the actual visibility level increases to be greater than or equal to the predetermined visibility level and / or the predetermined visibility level is configured lower so that the actual visibility level is greater than or equal to the configured predetermined visibility level, at least a portion of the ODD boundary is extended.

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

Images