Control method and control system for preventing unexpected activation of high-speed piloting auxiliary function

By verifying multi-dimensional conditions in the autonomous driving system, the problem of highway navigation assist function being activated under unexpected conditions was solved, improving the safety and reliability of the system and ensuring the safe activation of the HNP function.

CN121133747APending Publication Date: 2025-12-16ZHIJI AUTOMOTIVE TECH CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202511501468.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-10-21
Publication Date
2025-12-16

AI Technical Summary

Technical Problem

In existing autonomous driving systems, the highway navigation assist function can be activated under unexpected conditions, leading to safety hazards, mainly due to misjudgments by the perception system and inconsistencies in map data.

Method used

By verifying lane information, current vehicle positioning results, scene understanding results, and external environment results in the autonomous driving assistance map, a multi-dimensional ODD judgment logic is introduced to suppress the activation of the HNP function.

Benefits of technology

It improves the safety and reliability of autonomous driving systems, reduces the safety risks caused by unintended activation, and ensures that HNP functions are activated only within safe and reliable operational design domains.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121133747A_ABST
    Figure CN121133747A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of automatic driving control, in particular to a control method and a control system for preventing unexpected activation of a high-speed navigation auxiliary function, and the method comprises the steps: verifying factors which affect an HNP function activation condition; the verification at least comprises the step of verifying lane information in the automatic driving assistance map; verifying a current vehicle positioning result; verifying a scene understanding result in the current environment; and / or verifying an external environment result; and when any one of the factors does not meet the HNP activation condition, inhibiting the activation of the HNP function. According to the method, the unexpected activation of the HNP function can be effectively inhibited, and the safety and reliability of the automatic driving system are remarkably improved.
Need to check novelty before this filing date? Find Prior Art

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving control, and particularly relates to a control method and a control system for preventing unexpected activation of a high-speed navigation assistance function. BACKGROUND

[0002] With the continuous progress of automobile technology and the rapid development of artificial intelligence, automatic driving technology has become an important development direction of the automobile industry. In recent years, automatic driving functions have gradually evolved from simple auxiliary driving to higher-level automatic driving. Among them, the HNP (Highway Navigation Pilot, highway navigation assistance driving) function, as an important application of automatic driving, has been widely used in highway and elevated road scenes. The HNP function can realize automatic driving of vehicles on highways, including adaptive cruise control, lane keeping, automatic lane changing and other functions, greatly improving the convenience and comfort of driving. However, with the widespread use of HNP functions, their safety issues have also been increasingly concerned.

[0003] The activation of the HNP function needs to be strictly limited within a specific Operational Design Domain (ODD) to ensure the safety and reliability of the system. ODD refers to the operating conditions defined by the automatic driving system during design, including road types, environmental conditions, traffic conditions, etc. For example, the HNP function is usually only applicable to highways or elevated roads, and requires roads to have clear lane lines and clear road signs. In addition, environmental conditions such as weather conditions, light intensity, etc. will also affect the activation of the HNP function. Within the ODD range, the automatic driving system can obtain accurate road information and environmental data through the automatic driving assistance map and perception system, so as to realize safe and reliable automatic driving. Once the ODD range is exceeded, the reliability and safety of the system cannot be guaranteed.

[0004] Currently, the automatic driving system mainly relies on the automatic driving assistance map and the perception system to independently judge whether to activate the HNP function. The automatic driving assistance map provides detailed road geometry information and traffic rules, while the perception system obtains real-time environmental information around the vehicle through cameras, radars and other sensors.

[0005] However, the prior art has certain limitations. On the one hand, the perception system may misjudge due to complex environmental conditions (such as bad weather, insufficient light, or road construction); on the other hand, the map data may not be updated in time or have insufficient accuracy, leading to inconsistencies between the map information and the actual road conditions. These factors can all cause the HNP function to be unexpectedly activated outside the ODD, thereby causing safety hazards. For example, in the scenario of up-and-down parallel roads where the high-speed road is on the bridge and the urban road is under the bridge, it is difficult for the general navigation map and positioning to distinguish whether the vehicle is on the bridge or under the bridge. If the HNP function is mistakenly activated in a non-high-speed road scenario, it may cause the vehicle to fail to correctly recognize road signs or handle traffic conditions, thereby endangering driving safety.

[0006] In view of the limitations of the prior art, it is of great significance to develop a method and system that can effectively suppress the unexpected activation of the HNP function. SUMMARY

[0007] In view of the above-mentioned shortcomings of the prior art, the purpose of the present application is to provide a control method and control system for preventing the unexpected activation of the high-speed pilot assistance function, and to solve the passenger comfort during driving.

[0008] The first aspect of the present application provides a control method for preventing the unexpected activation of the high-speed pilot assistance function, comprising: verifying factors affecting the activation conditions of the HNP function, including at least verifying the lane information in the automatic driving assistance map, verifying the current vehicle positioning result, verifying the scene understanding result under the current environment, and / or verifying the external environment result; when any of the factors does not meet the HNP activation condition, suppressing the activation of the HNP function.

[0009] As an optional implementation, the verification of factors affecting the activation conditions of the HNP function further includes: verifying whether the current vehicle has passed a road segment that cannot be activated by the HNP.

[0010] As an optional implementation, the verification of the lane information in the automatic driving assistance map includes: matching and verifying the number of perceived lanes with the number of lanes in the map; matching and verifying the vehicle boundary with the road boundary in the map; matching and verifying the vehicle boundary with the lane boundary in the map.

[0011] As an optional implementation, the matching and verifying of the number of perceived lanes with the number of lanes in the map includes: identifying the number of perceived lanes of the road where the current vehicle is located by the perception system; acquire a number of map lanes of the current vehicle in the automatic driving assistance map through the positioning module; Compare the perceived lane number and the map lane number, and determine a verification result based on consistency of the number comparison; if the numbers are consistent, the verification is successful, and if the numbers are inconsistent, the verification fails.

[0012] As an optional implementation, the matching verification of the map road boundary by the perceived vehicle boundary comprises: acquire a leftmost perceived lane edge line and a rightmost perceived lane edge line of the vehicle through the perception system; If the perception system does not identify the lane edge line, the verification fails; If the perception system identifies the perceived edge line, all the identified edge lines are verified, wherein the verification method comprises comparing the edge line distance of the perceived vehicle edge line and the corresponding map vehicle edge line, and determining the verification result based on the relationship between the edge line distance and a preset edge line distance.

[0013] As an optional implementation, the matching verification of the map road boundary by the perceived vehicle boundary comprises: The perceived lane edge line result and the matching map lane edge line are divided into different distance intervals along the driving direction of the ego vehicle according to a preset driving distance, and the distance error of the perceived lane edge line and the map lane edge line in each segmented interval is calculated respectively; In a single segmented interval, the perceived-map matching lane line sampling points are obtained by interval sampling in a near-to-far manner for the single-side matching perceived lane line and the map lane line respectively; The straight line distance of each pair of lane line sampling points is calculated, and the average value of the distances of the multiple sampling points is taken as the lateral error of the perceived-map matching lane line in the segmented interval; The lane direction inconsistency level is calculated according to the lateral error in the segmented interval; The verification result is determined based on the level, wherein the level requirement is higher in the front segmented interval and lower in the rear segmented interval.

[0014] The second aspect of the present application provides a control system for preventing unintended activation of high-speed piloting assistance function, comprising: an automatic driving state machine, a map module, a perception module, a planning module, a positioning module and a vehicle-related component, wherein: the automatic driving system state machine is specifically an HNP state machine; the HNP state machine determines whether all factors meet the requirements by receiving data from the map module, the perception module, the positioning module, the planning module and the vehicle-related component. Before activation, if any of the HNP operating conditions is detected to be not met, the HNP activation is inhibited; during activation, if any of the HNP operating conditions is detected to be not met, the user is reminded in time and the function is downgraded.

[0015] A third aspect of the present invention provides a control system for preventing unintended activation of a high-speed navigation assist function, comprising: The verification unit is used to verify at least the factors affecting the activation conditions of the HNP function, including verifying unexpected activation, verifying lane information in the autonomous driving assistance map, verifying the current vehicle positioning result, verifying the scene understanding result in the current environment, and verifying the external environment result. The inhibition unit is used to inhibit the activation of HNP function when at least one of the factors does not meet the HNP activation condition.

[0016] As an optional implementation, the verification unit includes a sensing verification unit, which is at least used for: The number of lanes in the map is matched and verified by sensing the number of lanes. The map road boundaries are matched and verified by sensing vehicle boundaries; The map lane boundaries are matched and verified by sensing vehicle boundaries.

[0017] A fourth aspect of the present invention provides an electronic device, comprising: at least one processor; and at least one memory communicatively connected to the processor, wherein: the memory stores program instructions executable by the processor, and the processor, by invoking the program instructions, can perform the steps of the method described in the first aspect of the present invention.

[0018] A fifth aspect of the present invention provides a readable storage medium storing a computer program that is executed by a processor as described in the first aspect of the present invention. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating a control method for preventing unintended activation of the high-speed navigation assist function according to a specific embodiment of the present invention.

[0021] Figure 2 This is a schematic diagram of the process for verifying lane information in an autonomous driving assistance map in a specific embodiment of the present invention.

[0022] Figure 3 This is a schematic diagram illustrating the operational principle of verifying the lane boundaries of a map in a specific embodiment of the present invention.

[0023] Figure 4This is a block diagram of a control system for preventing unintended activation of the high-speed navigation assist function according to a specific embodiment of the present invention.

[0024] Figure 5 This is an architectural diagram illustrating a specific embodiment of the present invention for a control system that prevents unintended activation of the high-speed navigation assist function.

[0025] Figure 6 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0026] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application. Furthermore, it should be understood that the specific embodiments described herein are only for illustration and explanation of this application and are not intended to limit this application.

[0027] It should be noted that the order of description of the following embodiments is not intended to limit the preferred order of the embodiments of this application. Furthermore, the descriptions of each embodiment in the following embodiments have their own emphasis; for parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0028] Autonomous driving systems primarily rely on automated driving assistance maps and perception systems to independently determine whether to activate the HNP (Hardware-Navigate-Programmable) function. The automated driving assistance map provides detailed road geometry information and traffic rules, while the perception system acquires real-time environmental information about the vehicle's surroundings through sensors such as cameras and radar.

[0029] However, existing technologies have certain limitations. On the one hand, perception systems may misjudge situations due to complex environmental conditions (such as severe weather, insufficient lighting, or road construction); on the other hand, the data in autonomous driving assistance maps may be outdated or lack accuracy, leading to inconsistencies between map information and actual road conditions. These factors can all cause the HNP function to be unexpectedly activated outside the ODD, thereby posing safety hazards.

[0030] For example, in scenarios where the bridge is a highway and the road below is an urban road, navigation maps and positioning systems generally have difficulty distinguishing whether a vehicle is on or below the bridge. If the HNP function is accidentally activated in a non-highway scenario, the vehicle may be unable to correctly recognize road signs or handle traffic conditions, thereby endangering driving safety.

[0031] In view of this, such as Figure 1As shown, the first aspect of the present invention provides a control method for preventing the unintended activation of a high-speed navigation assist function, comprising the following steps.

[0032] Step S100: Verify the factors affecting the activation conditions of the HNP function, including at least verifying the lane information in the autonomous driving assistance map; verifying the current vehicle positioning result; verifying the scene understanding result in the current environment; and / or verifying the external environment result.

[0033] Specifically, such as Figure 2 As shown, the method for verifying lane information in the autonomous driving assistance map is based on the assistance of the perception system; the lane information includes at least the number of lanes, road width, and lane direction, which expresses the lane-level road geometry and topology attributes.

[0034] The specific verification of lane quantity includes comparing the perceived lane quantity with the map lane quantity. If the perceived lane quantity is inconsistent with the map lane quantity, or if lane quantity information is missing, the verification will fail.

[0035] The specific verification of road width includes determining whether the distance error between the perceived road boundary and the map road boundary is less than a threshold. If it is less than the threshold, the verification will fail.

[0036] Lane direction, also known as lane travel direction, includes specific verification content such as segmented calculation of the distance error between the perceived lane boundary and the map lane boundary, and defining the lane direction inconsistency level based on the error statistics. If the error is higher than a certain level, the verification will fail.

[0037] Specifically, the verification of the current vehicle location result is based on the positioning assistance of the perception system. If the perception positioning verification fails, HNP cannot be activated.

[0038] Specifically, the verification of the scene understanding results is based on the assistance of the perception system. The scene understanding results are a specific scene representation of the current vehicle's environment, such as highway main roads, highway ramps, highway underpasses, tunnels, auxiliary roads, other urban roads, toll stations, parking lots, gas stations, and other unstructured roads (service areas). Those skilled in the art can design or customize the verification based on the actual verification scenario, which will not be elaborated here.

[0039] If the current vehicle is on a main highway, the verification fails and HNP activation is not allowed.

[0040] Specifically, the external environment result is an external environment result obtained through vehicle sensors or vehicle-related components. If there is a negative external environment result, it means that the verification has failed. For example, if the external environment result is a low ground adhesion coefficient, the windshield wipers are on high, the ambient temperature is too low, or the light intensity is too dim, HNP is not allowed to be activated.

[0041] Step S200: When any of the factors does not meet the HNP activation conditions, suppress the activation of HNP function.

[0042] Specifically, when any situation that does not meet the HNP activation conditions is detected, the activation of the HNP function can be suppressed through a state machine jump arbitration mechanism.

[0043] This invention improves upon the traditional method of independently judging and activating the HNP function by the perception system and the autonomous driving assistance map. It introduces a more accurate matching and verification mechanism between the perception system and the autonomous driving assistance map, as well as multi-dimensional ODD judgment logic, such as the current vehicle location, scene understanding results, and external environment results. This significantly improves the safety and reliability of the autonomous driving system and reduces the safety hazards of vehicle driving.

[0044] In one embodiment of the present invention, the verification of factors affecting the activation conditions of the HNP function further includes: verifying whether the current vehicle passes through a road segment where HNP cannot be activated.

[0045] Specifically, in the map provider's data, when calculating routes in the cloud, road sections where HNP cannot be activated, such as toll booths, are marked as ODDClose. If there is an ODDClose area within a certain range of kilometers ahead, such as 2 kilometers, then HNP activation is not allowed.

[0046] This approach further ensures the security of HNP activation. By using perception and autonomous driving assistance map matching verification, as well as a multi-dimensional ODD judgment mechanism, it suppresses the unexpected activation of HNP outside the ODD, thereby improving the safety and reliability of the autonomous driving system.

[0047] In one embodiment of the present invention, the verification of lane information in the autonomous driving assistance map includes: The number of lanes in the map is matched and verified by sensing the number of lanes. The map road boundaries are matched and verified by sensing vehicle boundaries; The map lane boundaries are matched and verified by sensing vehicle boundaries.

[0048] In one embodiment of the present invention, the step of matching and verifying the number of lanes on the map by sensing the number of lanes includes: The number of sensing lanes on the road where the vehicle is currently located is identified through the sensing system; The number of map lanes in the autonomous driving assistance map is obtained through the positioning module; The number of perceived lanes is compared with the number of lanes on the map. The verification result is determined based on the consistency of the number comparison. If the numbers are the same, the verification is successful; if the numbers are different, the verification fails.

[0049] For details, please continue reading. Figure 2 The perception system uses cameras to identify the number of lanes on the road where the vehicle is currently located, and uses the vehicle positioning module to capture the road, thereby obtaining the map link of the current vehicle in the autonomous driving assistance system and the number of lanes in that link.

[0050] Specifically, the number of lanes output by the sensor is compared with the number of lanes obtained from the map link. If the number of lanes is inconsistent or the information on the number of perceived lanes is missing, the output verification fails and the activation of the HNP function is suppressed.

[0051] In one embodiment of the present invention, the step of matching and verifying the map road boundary by sensing the vehicle boundary includes: The leftmost and rightmost lane edge lines of the vehicle are obtained through the perception system. If the perception system fails to recognize the lane edge line, the verification fails. If the perception system identifies a perceived edge line, it verifies all identified edge lines. The verification method includes comparing the edge line distances of the perceived vehicle edge line and the corresponding map vehicle edge line, and determining the verification result based on the relationship between the edge line distance and the preset edge line distance.

[0052] For details, please continue reading. Figure 2 ,exist Figure 2 The edge line of the middle lane is indicated by LB.

[0053] Specifically, the leftmost and rightmost lane edge lines are obtained through the perception system. If the perception system does not identify either lane edge line, the verification fails. If only one side detects a lane edge line, only that side is checked. If both sides detect lane edge lines, both sides are checked.

[0054] Obtain the map lane edge lines that match the leftmost and rightmost perceived lane edge lines. The leftmost perceived lane edge line will only match the leftmost map edge line; the rightmost perceived lane edge line will only match the rightmost map lane edge line.

[0055] If the distance between the edge line of the perceived lane on one side and the edge line of the lane on the map on one side is greater than the preset edge line distance, such as 50cm, then the road structure matching on one side is considered abnormal, the output verification fails, and the activation of the HNP function is suppressed. If the difference between the distance between the edge lines of the perceived lane on the left and right sides and the distance between the edge lines of the lane on the map on the left and right sides is greater than the total preset edge line distance, such as 1m, then the road width matching is considered abnormal, the output verification fails, and the activation of the HNP function is suppressed.

[0056] In one embodiment of the present invention, the step of matching and verifying the map lane boundaries by sensing vehicle boundaries includes: The perceived lane edge line and the matching map lane edge line are divided into different distance intervals along the vehicle's driving direction according to a preset driving distance, and the distance error between the perceived lane edge line and the map lane edge line in each segment interval is calculated. Within a single segmented interval, multiple lane line sampling points for perception-map matching are obtained by sampling at intervals from near to far for both the perceived lane lines and the map lane lines matched on one side. Calculate the straight-line distance between each pair of lane line sampling points, and use the average of the distances of multiple sampling points as the lateral error of lane line matching in the perception map of that segment interval; The lane direction inconsistency level is calculated based on the lateral error within the segmented intervals; The verification result is determined based on the level, where the level requirement is higher for the earlier segment intervals and lower for the later segment intervals.

[0057] Specifically, lane boundary verification mainly involves verifying lane direction. First, the map lane edge line that matches the perceived lane edge line is obtained. The perceived lane edge line result and the matching map lane edge line are processed. Along the vehicle's driving direction, a preset driving distance, such as 20m, is used as a preset driving distance, which is divided into different distance intervals. The distance error between the perceived lane edge line and the map lane edge line in each segment interval is calculated.

[0058] In one application scenario of this invention, the method for calculating the distance error between the perceived lane edge line and the map lane edge line within a segmented interval includes: Within a single segmented interval, for both the perceived lane line edge line and the map lane line edge line matched on one side, sampling is performed every 1m from near to far, resulting in a total of 20 pairs of perceived-map matched lane line edge line sampling points. The sampling time, number of sampling pairs, etc., can be adjusted according to the actual needs of those skilled in the art. The straight-line distance of each pair of lane line sampling points is calculated, and the average distance of the 20 pairs of sampling points is taken as the lateral error of the perceived-map lane line matching in that segmented interval. The lane direction inconsistency level is calculated based on the lateral error within the segmented intervals.

[0059] Horizontal error level calculation as follows Figure 3 As shown in Table 1: Table 1 .

[0060] For intervals 1-3, if the lateral error level of any interval is not low, the verification fails and the activation of the HNP function is suppressed; for intervals 4-6, if the lateral error level of any two intervals is not low, the verification fails and the activation of the HNP function is suppressed.

[0061] Here, the present invention comprehensively determines whether the HNP activation conditions are met by combining cloud-based road marking ODD Close (toll stations and other HNP-inactive road sections), map data, perception scene understanding, and vehicle sensor / related component information.

[0062] like Figure 4 and Figure 5 As shown, a second aspect of the present invention provides a control system for preventing unintended activation of a high-speed navigation assist function, comprising: an autonomous driving state machine, a map module, a perception module, a planning module, a positioning module, and a vehicle association component, wherein: The state machine of the autonomous driving system is specifically an HNP state machine. The HNP state machine receives data from the map module, perception module, positioning module, planning module, and vehicle-related components to determine whether all factors are satisfied. Before activation, if any HNP operating conditions are not met, HNP activation is suppressed. During activation, if any HNP operating conditions are not met, the user is promptly alerted and functionality is downgraded.

[0063] Specifically, the perception module mainly outputs image information and detected lane line information to the planning and positioning modules. The planning module, based on the vehicle's location information, navigation route information, and simultaneously combining the perceived image information, performs scene understanding and identification to determine whether it is a tunnel, on or under a bridge, in an urban area or on a highway, and whether the vehicle has taken the wrong route or deviated from its course. The positioning module verifies the perceived lane line information against the lane line information on the map to determine whether the number, width, and direction of lanes are consistent, preventing the positioning module from mistakenly activating functions due to its inability to distinguish between on and under bridge scenarios. For example, if the navigation indicates that the vehicle is on a bridge, but the vehicle is under a bridge, this is something that the positioning module alone cannot identify.

[0064] like Figure 5As shown, in one application scenario of the present invention, the system activates the HNP autonomous driving function through a switch button, acquires perception information such as road lane lines and surrounding environment through radar and cameras, acquires vehicle location information through the positioning module, and acquires current vehicle and road information ahead of the vehicle by combining the autonomous driving (assisted) map. The system controls the ODD judgment and suppression mechanism through the state machine of the autonomous driving system, and displays the ODD judgment result and suppression status through the vehicle instrument panel.

[0065] A third aspect of the present invention provides a control system for preventing unintended activation of a high-speed navigation assist function, comprising: The verification unit is used to verify at least the factors affecting the activation conditions of the HNP function, including verifying unexpected activation, verifying lane information in the autonomous driving assistance map, verifying the current vehicle positioning result, verifying the scene understanding result in the current environment, and verifying the external environment result. The inhibition unit is used to inhibit the activation of HNP function when at least one of the factors does not meet the HNP activation condition.

[0066] In one embodiment of the present invention, the verification unit includes a sensing verification unit, which is at least used for: The number of lanes in the map is matched and verified by sensing the number of lanes. The map road boundaries are matched and verified by sensing vehicle boundaries; The map lane boundaries are matched and verified by sensing vehicle boundaries.

[0067] This invention significantly improves the safety and reliability of autonomous driving systems by introducing a more accurate perception and autonomous driving assistance map matching and verification mechanism, as well as multi-dimensional ODD judgment logic. It ensures that the HNP function is activated only within a safe and reliable operation design domain, thereby providing stronger technical support for the widespread application of autonomous driving technology and improving the user's driving safety and experience.

[0068] like Figure 6 As shown, a fourth aspect of the present invention provides an electronic device, comprising: at least one processor; and at least one memory communicatively connected to the processor, wherein: the memory stores program instructions executable by the processor, and the processor invokes the program instructions to perform the steps of the method as described in any of the above embodiments.

[0069] The fifth aspect of the present invention discloses a readable storage medium storing a computer program, which is executed by a processor as described in any of the above embodiments.

[0070] Computer-readable storage media can include: any entity or device capable of carrying computer programs, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (RON), random access memory (RAN), and software distribution media, etc. Computer programs include computer program code. Computer program code can be in the form of source code, object code, executable files, or certain intermediate forms, etc. Computer-readable storage media can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (RON), random access memory (RAN), and software distribution media, etc.

[0071] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0072] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus or device (such as a computer-based system, a system including a processing module or other system that can fetch and execute instructions from, an instruction execution system, apparatus or device).

[0073] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A control method for preventing unintended activation of high-speed navigation assist function, characterized in that, include: Verify the factors that affect the activation conditions of the HNP function, including at least verifying the lane information in the autonomous driving assistance map; Verify the current vehicle location result; Verify the scene understanding results in the current environment; and / or verify the results in the external environment; When any of these factors does not meet the HNP activation condition, the activation of HNP function is inhibited.

2. The control method for preventing unintended activation of high-speed navigation assist function according to claim 1, characterized in that, The factors affecting the activation conditions of the HNP function, as mentioned in the verification, also include: Verify whether the current vehicle has passed through a road segment that HNP cannot activate.

3. The control method for preventing unintended activation of high-speed navigation assist function according to claim 1, characterized in that, The verification of lane information in the autonomous driving assistance map includes: The number of lanes in the map is matched and verified by sensing the number of lanes. The map road boundaries are matched and verified by sensing vehicle boundaries; The map lane boundaries are matched and verified by sensing vehicle boundaries.

4. The control method for preventing unintended activation of high-speed navigation assist function according to claim 3, characterized in that, The process of matching and verifying the number of lanes on the map by sensing the number of lanes includes: The number of sensing lanes on the road where the vehicle is currently located is identified through the sensing system; The number of map lanes in the autonomous driving assistance map is obtained through the positioning module; The number of perceived lanes is compared with the number of lanes on the map. The verification result is determined based on the consistency of the number comparison. If the numbers are the same, the verification is successful; if the numbers are different, the verification fails.

5. The control method for preventing unintended activation of high-speed navigation assist function according to claim 3, characterized in that, The process of matching and verifying map road boundaries by sensing vehicle boundaries includes: The leftmost and rightmost lane edge lines of the vehicle are obtained through the perception system. If the perception system fails to recognize the lane edge line, the verification fails. If the perception system identifies a perceived edge line, it verifies all identified edge lines. The verification method includes comparing the edge line distances of the perceived vehicle edge line and the corresponding map vehicle edge line, and determining the verification result based on the relationship between the edge line distance and the preset edge line distance.

6. The control method for preventing unintended activation of high-speed navigation assist function according to claim 5, characterized in that, The process of matching and verifying map lane boundaries by sensing vehicle boundaries includes: The perceived lane edge line and the matching map lane edge line are divided into different distance intervals along the vehicle's driving direction according to a preset driving distance, and the distance error between the perceived lane edge line and the map lane edge line in each segment interval is calculated. Within a single segmented interval, multiple lane line sampling points for perception-map matching are obtained by sampling at intervals from near to far for both the perceived lane lines and the map lane lines matched on one side. Calculate the straight-line distance between each pair of lane line sampling points, and use the average of the distances of multiple sampling points as the lateral error of lane line matching in the perception map of that segment interval; The lane direction inconsistency level is calculated based on the lateral error within the segmented intervals; The verification result is determined based on the level, where the level requirement is higher for the earlier segment intervals and lower for the later segment intervals.

7. A control system for preventing unintended activation of high-speed navigation assist function, characterized in that, include: The autonomous driving state machine, map module, perception module, planning module, positioning module, and vehicle-related components include: The state machine of the autonomous driving system is specifically an HNP state machine. The HNP state machine receives data from the map module, perception module, positioning module, planning module, and vehicle-related components to determine whether all factors are satisfied. Before activation, if any HNP operating conditions are not met, HNP activation is suppressed. During activation, if any HNP operating conditions are not met, the user is promptly alerted and the function is downgraded.

8. A control system for preventing unintended activation of high-speed navigation assist function, characterized in that, include: The verification unit is used to verify at least the factors that affect the activation conditions of the HNP function, including verifying unexpected activation and verifying lane information in the autonomous driving assistance map. Verify the current vehicle location result; verify the scene understanding result in the current environment; Verify the results of the external environment; The inhibition unit is used to inhibit the activation of HNP function when at least one of the factors does not meet the HNP activation condition.

9. The control system for preventing unintended activation of high-speed navigation assist function according to claim 8, characterized in that, The verification unit includes a sensing verification unit, which is at least used for: The number of lanes in the map is matched and verified by sensing the number of lanes. The map road boundaries are matched and verified by sensing vehicle boundaries; The map lane boundaries are matched and verified by sensing vehicle boundaries.

10. An electronic device, characterized in that, include: At least one processor; And at least one memory communicatively connected to the processor, wherein: the memory stores program instructions executable by the processor, and the processor invokes the program instructions to perform the steps of the control method for preventing unintended activation of the high-speed navigation assist function as described in any one of claims 1-6.

11. A readable storage medium storing a computer program, characterized in that, The computer program is executed by the processor using the steps of the control method for preventing unintended activation of the high-speed navigation assist function as described in any one of claims 1-6.

Citation Information

Patent Citations

  • Low-cost high-precision positioning method based on multi-sensor fusion

    CN114889606A

  • Vehicle high-speed self-adaptive function control method, device and equipment and storage medium

    CN118636892A

  • Method for automatically activating or deactivating a driving function of a vehicle, computer program, control unit and vehicle

    DE102021214787A1

  • Travel support method and travel support device

    JP2024013046A

  • Advanced driver-assistance systems feature activation control using digital map and on-board sensing to confirm safe vehicle operation

    US20230115240A1