A vehicle travel assistance warning method, device, vehicle, and storage medium

Abstract

The application provides a vehicle driving assistance warning method and device, a vehicle and a storage medium, and relates to the technical field of vehicles.The method comprises the following steps: in response to a manual driving assistance warning instruction, determining a target limit speed corresponding to a current lane of the vehicle according to road environment information of the current lane of the vehicle, current operating parameters of the vehicle and a preset road environment information-operating parameter-target limit speed mapping relationship; and in response to the real-time speed of the vehicle meeting a warning trigger condition about the target limit speed, generating warning information.The application quickly and accurately determines the target limit speed based on the road environment information of the lane, the operating parameters of the vehicle and the corresponding mapping relationship in response to the manual driving assistance warning instruction, compares the real-time speed with the target limit speed, generates warning information for reminding the driver to slow down or adjust the operation when the real-time speed meets the warning trigger condition about the target limit speed, and improves the safety of manual driving.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and more specifically, to a vehicle driving assistance and warning method, device, vehicle, and storage medium. Background Technology

[0002] With the continuous development of Advanced Driver Assistance Systems (ADAS), features such as Lane Keeping Assist (LKA) and Lane Departure Warning (LDW) have gradually become standard equipment on vehicles. These functions typically rely on onboard cameras to recognize road lane markings and, when they detect a vehicle deviating from its lane, automatically adjust the steering or provide a lane departure warning to prevent the vehicle from accidentally leaving the lane. However, these functions usually operate in autonomous driving or cruise control mode. When the driver is in manual driving mode, the ADAS often cannot continuously provide effective safety assistance.

[0003] Moreover, in real-world driving scenarios, especially on high-curvature sections such as mountain roads, highway ramps, or complex curves in urban roads, drivers often choose to take over the vehicle actively due to considerations of the responsiveness of intelligent driving assistance systems or comfort. In such cases, the driver's judgment of the curve's curvature relies heavily on experience and visual estimation. Due to factors such as obstructed vision, weather conditions, and unclear road markings, the driver is prone to situations such as excessive speed when cornering and failure to decelerate in time, increasing the risk of understeer, fishtailing, skidding, or even rollover, which seriously threatens driving safety. Summary of the Invention

[0004] The problem this invention addresses is: how to improve the safety of manually driven vehicles.

[0005] To address the aforementioned problems, this invention provides a vehicle driving assistance warning method, device, vehicle, and storage medium.

[0006] In a first aspect, the present invention provides a vehicle driving assistance warning method, comprising:

[0007] In response to a manual driving assistance warning command, the target speed limit for the vehicle in the lane is determined based on the road environment information of the lane in which the vehicle is currently driving, the vehicle's current operating parameters, and a preset mapping relationship between road environment information, operating parameters, and target speed limit.

[0008] In response to the vehicle's real-time speed meeting the warning triggering conditions regarding the target speed limit, a warning message is generated.

[0009] Optionally, the warning triggering conditions include:

[0010] The real-time vehicle speed is greater than or equal to the target speed limit.

[0011] And / or, the real-time vehicle speed is greater than or equal to the difference between the target speed limit and the preset threshold, and the real-time acceleration of the vehicle is greater than 0.

[0012] Optionally, the vehicle driving assistance warning method further includes:

[0013] The target speed limit of the vehicle is calibrated under different road environment information and different operating parameters, and a mapping relationship between road environment information, operating parameters and target speed limit is constructed; wherein, the road environment information includes at least one of lane curvature, lane surface type and road speed limit; the operating parameters include at least one of vehicle speed and real-time driving assistance mode.

[0014] Optionally, the step of responding to a manual driving assistance warning command and determining the target speed limit for the vehicle in the current lane based on road environment information of the vehicle's current lane, the vehicle's current operating parameters, and a preset road environment information-operating parameter-target speed limit mapping relationship includes:

[0015] In response to the manual driving assistance warning command, the real-time driving assistance mode of the vehicle is determined; wherein, the real-time driving assistance mode is a preset driving assistance mode executed by the vehicle according to the mode switching command, or the preset driving assistance mode automatically loaded by the vehicle in the default state;

[0016] Based on the road environment information and the operating parameters, and combined with the mapping relationship between the road environment information, operating parameters, and target speed limit, the maximum permissible speed and the highest tire adhesion speed of the vehicle in the current lane are determined.

[0017] The minimum value among the maximum permissible speed, the maximum tire adhesion speed, and the road speed limit of the lane is used as the target speed limit.

[0018] Optionally, the road environment information-operating parameters-target speed limit mapping relationship includes: lane curvature-lateral acceleration-lane road surface type-maximum permissible speed mapping relationship, and lane road surface type-lane curvature-maximum tire adhesion speed mapping relationship;

[0019] The step of determining the maximum permissible speed and the highest tire-weighted speed of the vehicle in the current lane based on the road environment information and the operating parameters, combined with the mapping relationship between the road environment information, operating parameters, and target speed limits, includes:

[0020] Based on the lane curvature, lane surface type, and preset target lateral acceleration corresponding to the real-time driving assistance mode, and in conjunction with the lane curvature-lateral acceleration-lane surface type-maximum permissible speed mapping relationship, the maximum permissible speed of the vehicle currently in the lane is determined; and based on the lane curvature and lane surface type, and in conjunction with the lane surface type-lane curvature-maximum tire adhesion speed mapping relationship, the maximum tire adhesion speed of the vehicle currently in the lane is determined.

[0021] Optionally, the road environment information includes lane curvature;

[0022] The vehicle driving assistance warning method also includes:

[0023] Based on the acquired image information about the lane, determine the lane edge line;

[0024] The lane curvature is determined based on the lane edge line;

[0025] The target speed limit is determined based on the lane curvature.

[0026] Optionally, determining the lane edge line of the lane based on the acquired image information about the lane includes:

[0027] Based on the image information, determine the coordinate position information of the lane edge line in the vehicle coordinate system;

[0028] Determining the lane curvature based on the lane edge line includes:

[0029] Based on the coordinate position information of multiple points on the lane edge line in the vehicle coordinate system, curve fitting is performed on the lane edge line to determine candidate curvature;

[0030] The validity of the candidate curvatures is verified;

[0031] If the candidate curvature verification passes, the lane curvature is determined based on the candidate curvature.

[0032] Optionally, the step of performing curve fitting on the lane edge line and determining candidate curvature based on the coordinate position information of multiple points on the lane edge line in the vehicle coordinate system includes:

[0033] Based on the coordinate position information of multiple points on the lane edge line in each frame of the image information in a consecutive preset number of frames, the curve fitting is performed to determine the candidate curvature corresponding to each frame of the image information;

[0034] The validity verification of the candidate curvature includes:

[0035] The validity verification is performed on each of the candidate curvatures.

[0036] If the candidate curvature verification passes, determining the lane curvature based on the candidate curvature includes:

[0037] The mean of all the candidate curvatures that pass the verification is determined as the lane curvature.

[0038] Optionally, the validity verification of the candidate curvature includes:

[0039] Determine whether the candidate curvature meets the preset fitting reliability and curvature credibility constraints; wherein, the preset fitting reliability and curvature credibility constraints include preset input point number constraints, preset matrix rank verification conditions, preset curvature range constraints, preset inter-frame smoothness verification conditions, and preset derivative slope boundary conditions;

[0040] If the candidate curvature simultaneously satisfies the preset input point count limit, the preset matrix rank verification condition, the preset curvature range limit, the preset inter-frame smoothness verification condition, and the preset derivative slope boundary condition, the candidate curvature is determined to have passed verification; if the candidate curvature does not satisfy any of the preset input point count limit, the preset matrix rank verification condition, the preset curvature range limit, the preset inter-frame smoothness verification condition, and the preset derivative slope boundary condition, the candidate curvature is determined to have failed verification.

[0041] In a second aspect, the present invention provides a vehicle driving assistance and warning device, comprising:

[0042] The calculation unit is used to respond to manual driving assistance warning commands and determine the target speed limit of the vehicle in the lane based on the road environment information of the current driving lane, the current operating parameters of the vehicle, and the preset road environment information-operating parameters-target speed limit mapping relationship.

[0043] The warning unit is used to generate warning information in response to the real-time vehicle speed of the vehicle meeting the warning triggering conditions related to the target speed limit.

[0044] Thirdly, the present invention provides a vehicle including a memory and a processor;

[0045] The memory is used to store computer programs;

[0046] The processor is configured to implement the vehicle driving assistance warning method as described in the first aspect when executing the computer program.

[0047] Fourthly, the present invention provides a computer-readable storage medium storing a computer program, which, when read and executed by a processor, implements the vehicle driving assistance warning method as described in the first aspect.

[0048] The beneficial effects of the vehicle driving assistance warning method, device, vehicle, and storage medium of the present invention are as follows: The present invention is applicable to road driving safety assistance when the vehicle is in manual driving mode. Specifically, upon receiving a manual driving assistance warning command, based on the road environment information of the vehicle's current driving lane and the vehicle's current operating parameters, combined with a preset road environment information-operating parameter-target speed limit mapping relationship, the maximum speed that can ensure stable and safe driving of the vehicle or ensure the driver's controllable operation in the current lane is quickly determined as the target speed limit for subsequent risk assessment. On this basis, the actual vehicle speed is compared with the target speed limit. When it is detected that the actual vehicle speed meets the warning triggering conditions such as the actual vehicle speed exceeding the target speed limit, or a continuous acceleration trend when approaching the target speed limit, it is determined that there is a driving safety risk, and the corresponding warning information is generated in a timely manner to remind the driver, ensuring that the driver can perceive the risk at the first time and take measures to slow down or adjust driving operations, avoiding dangerous situations such as understeering, fishtailing, skidding, or even rollover caused by excessive speed. This invention enables the driver to quickly determine the target speed limit by combining real-time road environment information and vehicle operating parameters when the driver is in manual driving mode. It achieves differentiated and dynamic safety assistance based on the actual driving environment, and realizes forward prediction and dynamic response to driving risks. Compared with related technologies that rely on driver experience or fixed speed limits, it significantly improves the matching degree between vehicle speed control and road environment, can detect potential risks earlier and issue intuitive and clear prompts, effectively make up for the lack of road driving safety assistance in manual driving scenarios, thereby improving the overall driving safety and driving comfort of the vehicle. It is particularly suitable for high-risk driving scenarios such as mountain roads, highway ramps or complex urban curves. Attached Figure Description

[0049] Figure 1 This is a schematic flowchart of a vehicle driving assistance warning method in an embodiment of the present invention;

[0050] Figure 2 This is a schematic diagram of a vehicle traveling in a lane according to an embodiment of the present invention;

[0051] Figure 3 This is a schematic diagram of a sub-process of step 100 in an embodiment of the present invention;

[0052] Figure 4This is a schematic diagram illustrating the mapping relationship between lane curvature, lateral acceleration, lane surface type, and maximum permissible vehicle speed in an embodiment of the present invention.

[0053] Figure 5 This is a schematic diagram of the warning information output status in an embodiment of the present invention;

[0054] Figure 6 This is a structural block diagram of the vehicle driving assistance and warning device in an embodiment of the present invention;

[0055] Figure 7 This is a schematic diagram of the communication connection between the vehicle's memory and processor in an embodiment of the present invention. Detailed Implementation

[0056] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0057] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in sequences other than those illustrated or described herein.

[0058] Combination Figure 1 , Figure 2 As shown, an embodiment of the present invention provides a vehicle driving assistance warning method, including:

[0059] Step 100: In response to the manual driving assistance warning command, determine the target speed limit for the vehicle in the current lane based on the road environment information of the current driving lane, the current operating parameters of the vehicle, and the preset road environment information-operating parameters-target speed limit mapping relationship.

[0060] This embodiment of the method is applicable to road driving safety assistance when the vehicle is in manual driving mode. It aims to determine the target speed limit of the vehicle's current driving lane by sensing the road environment information of the vehicle's current driving lane and the vehicle's current operating parameters, combined with a preset mapping relationship model. Based on the vehicle's real-time speed and the set warning trigger conditions for the target speed limit, when the speed meets the warning trigger conditions, relevant warning information is actively generated to remind the driver to intervene in a timely manner, thereby ensuring the safety of manual driving.

[0061] In step 100, when the vehicle receives a manual driving assistance warning command (referred to as a manual driving assistance warning command) while in manual driving mode (i.e., the vehicle is in a driving mode / state directly controlled by the driver, such as steering, acceleration, braking, etc., which are actively executed by the driver rather than taken over by the intelligent driving assistance system), the driving assistance warning function (or curvature assist function) is activated to assist the driver in driving the vehicle safely in the current lane. For example, road environment information of the vehicle's current driving lane can be obtained through onboard environmental perception devices (such as cameras / image sensors, radar, etc.) (which can be obtained directly or further processed based on directly obtained information), such as lane curvature, road surface type (such as dry / slippery / gravel, etc.), road speed limit (which can be determined by recognizing the speed limit value shown on the roadside speed limit sign, or provided by high-precision map data), etc.; and the vehicle's current operating parameters, such as real-time vehicle speed and real-time driving assistance mode, can be obtained through the onboard controller. Based on the acquired road environment information of the vehicle's current driving lane and the vehicle's current operating parameters, the target speed limit of the vehicle in the current lane can be determined by combining the preset (pre-built) mapping relationship between road environment information, operating parameters and target speed limit. This target speed limit is the maximum speed at which the vehicle can maintain stable and safe driving or ensure the driver's safe and stable control of the vehicle in the current driving lane (denoted as the target speed limit). It can be used to determine whether to trigger a warning in the future so as to promptly alert the driver and improve the safety of manual driving.

[0062] The mapping relationship between road environment information, operating parameters, and target speed limit can be a pre-calibrated model based on a large amount of vehicle measurement data and vehicle dynamics models. This model characterizes the maximum permissible speed for stable, controllable, and safe driving under various road environment conditions and vehicle operating parameter constraints. By employing this mapping relationship, the processing efficiency and response speed of the method in this embodiment can be effectively improved through pre-calibration, table lookup, index optimization, and caching mechanisms. This approach is particularly suitable for resource-constrained onboard computing environments and manual driving assistance warning scenarios with strict response latency requirements.

[0063] Thus, the method in this embodiment improves the matching degree between vehicle speed control and the actual road environment, and can provide drivers with timely and effective dynamic speed limit references, which facilitates timely warnings in corresponding risk scenarios and reduces the risk of understeering, fishtailing, skidding or even rollover caused by excessive speed.

[0064] Step 200: In response to the vehicle's real-time speed meeting the warning triggering conditions for the target speed limit, generate a warning message.

[0065] In step 200, based on the acquired real-time vehicle speed, it is determined whether the warning trigger conditions for the target speed limit are met. Warning trigger conditions may include situations where the vehicle's real-time speed exceeds the limit (i.e., the real-time speed is greater than or equal to the target speed limit) or is accelerating even when approaching the threshold (i.e., the real-time speed is approaching the target speed limit and the vehicle is still accelerating), indicating a potential driving safety risk. When the vehicle's real-time speed meets the warning trigger conditions for the target speed limit, it indicates a current driving safety risk, requiring timely reminders to the driver. Corresponding warning information is then generated to remind the driver to pay attention to speed control, slow down, etc. This ensures that the driver receives a clear and intuitive risk warning immediately, allowing them to take timely measures to slow down or adjust their driving operation, avoiding dangerous situations such as understeering, skidding, fishtailing, or even rollover caused by excessive speed. This significantly improves the vehicle's driving safety and comfort in manual driving scenarios. The warning information can be presented through a human-machine interface (HMI) in the form of sound and light, such as displaying the prompts as text or icons on the vehicle's display screen or instrument panel, and / or providing voice reminders through voice broadcast, to ensure that the driver can perceive the warning information in a timely manner and improve the safety of manual driving.

[0066] In summary, the method of this embodiment is applicable to road driving safety assistance when the vehicle is in manual driving mode. Specifically, upon receiving a manual driving assistance warning command, based on the road environment information of the vehicle's current driving lane and the vehicle's current operating parameters, combined with a preset mapping relationship between road environment information, operating parameters, and target speed limit, the maximum speed that can ensure stable and safe driving or ensure driver controllability in the current lane is quickly determined as the target speed limit for subsequent risk assessment. On this basis, the vehicle's actual speed is compared with the target speed limit. When the actual speed is detected to meet warning triggering conditions such as exceeding the target speed limit or exhibiting a continuous acceleration trend while approaching the target speed limit, a driving safety risk is determined to exist, and corresponding warning information is promptly generated to remind the driver. This ensures that the driver can perceive the risk immediately and take measures to slow down or adjust driving operations, avoiding dangerous situations such as understeering, fishtailing, skidding, or even rollover caused by excessive speed. The method in this embodiment can quickly determine the target speed limit by combining real-time road environment information and vehicle operating parameters when the driver is in manual driving mode. It realizes differentiated and dynamic safety assistance based on the actual driving environment, and achieves forward-looking prediction and dynamic response to driving risks. Compared with the methods of relying on driver experience or fixed speed limits in related technologies, it significantly improves the matching degree between vehicle speed control and road environment, can detect potential risks earlier and issue intuitive and clear prompts, effectively make up for the lack of road driving safety assistance in manual driving scenarios, thereby improving the overall driving safety and driving comfort of the vehicle. It is particularly suitable for high-risk driving scenarios such as mountain roads, highway ramps or complex urban curves.

[0067] Optionally, the warning triggering conditions include:

[0068] The real-time vehicle speed is greater than or equal to the target speed limit.

[0069] And / or, the real-time vehicle speed is greater than or equal to the difference between the target speed limit and the preset threshold, and the real-time acceleration of the vehicle is greater than 0.

[0070] Specifically, the setting of warning trigger conditions needs to consider both real-time performance and reasonableness in determining driving safety risks. Based on this, the method in this embodiment comprehensively considers factors such as the vehicle's current real-time speed, the target speed limit, and the vehicle's real-time acceleration when setting warning trigger conditions. For example, when the vehicle's real-time speed is greater than or equal to the target speed limit, it is directly determined as a speeding risk and a warning is triggered; and / or, to provide early warning when the vehicle speed approaches a critical value, a preset threshold is introduced. When the vehicle's real-time speed is greater than or equal to the difference between the target speed limit and the preset threshold, the real-time speed is considered to be approaching the target speed limit. Simultaneously, if the vehicle's real-time acceleration is greater than 0 (i.e., the vehicle is still accelerating), it is determined as a potential risk and a warning is triggered. The preset threshold can be a fixed value or dynamically adjusted based on driving mode, road type, and road surface conditions to improve the flexibility of risk assessment.

[0071] Thus, by setting warning trigger conditions, the method in this embodiment can generate warning information as soon as a driving safety risk or potential driving safety risk occurs, ensuring the timeliness and accuracy of the warning, effectively improving the driver's trust in the warning prompts, and ensuring that the driver can receive clear and intuitive prompts before danger occurs, thereby significantly improving the driving safety of the vehicle in manual driving scenarios.

[0072] Optionally, vehicle driving assistance warning methods also include:

[0073] The target speed limit of the vehicle is calibrated under different road environment information and different operating parameters, and a mapping relationship between road environment information, operating parameters and target speed limit is constructed. The road environment information includes at least one of lane curvature, lane surface type and road speed limit; the operating parameters include at least one of vehicle speed and real-time driving assistance mode.

[0074] Specifically, during the vehicle development or testing phase, a systematic analysis of the safe operating boundaries under various typical road scenarios and vehicle operating states can be conducted by combining real-vehicle testing, simulation, and historical operating data. Based on the vehicle dynamics model, the maximum controllable speed under various road environment and vehicle operating parameter combinations can be calculated and used as the target speed limit for calibration. Subsequently, based on the above calibration, a multi-dimensional mapping relationship between road environment information, operating parameters, and target speed limit can be constructed and stored for later retrieval. This mapping relationship can be implemented using a lookup table approach, such as constructing a multi-dimensional index table to support real-time queries; alternatively, a fitting model or machine learning algorithm (such as decision trees, neural networks, etc.) can be used to construct a non-linear mapping relationship with generalization capabilities to adapt to diverse road conditions and vehicle states. Through this mapping relationship, the corresponding target speed limit can be quickly and with low latency found or calculated based on the currently perceived road environment information and vehicle operating parameters during vehicle operation, adapting to real-world scenarios with limited onboard computing resources and high requirements for response timeliness. Thus, the method in this embodiment not only improves the accuracy and robustness of the target speed limit calculation, but also significantly enhances the practicality and reliability of manual driving assistance. It is especially suitable for dynamic speed limit management and proactive risk warning in high-risk areas such as mountain roads, ramps, and slippery curves, thereby effectively improving the safety and driving comfort of the whole vehicle in manual driving mode.

[0075] The road environment information includes at least one of lane curvature, lane surface type, and road speed limit. Lane curvature reflects the degree of road curvature and is an important parameter for assessing whether a vehicle can safely pass through a curve; a smaller curvature radius usually means a lower safe passing speed. Lane surface type, such as dry, wet, snowy, icy, or gravelly, directly affects the adhesion between the vehicle's tires and the ground, thus affecting the maximum controllable speed. The road speed limit, as the upper limit stipulated by traffic management, is usually used as the upper boundary or reference benchmark for target speed limits. The above road environment information can be collected in real time by perception systems such as cameras, millimeter-wave radar, lidar, and in-vehicle map modules, or provided by high-precision maps. Operating parameters include at least one of vehicle speed and real-time driving assistance mode. Vehicle speed is a fundamental dynamic parameter reflecting the current operating status of a vehicle and a key variable for determining the risk of speeding. Driving assistance mode represents the vehicle's control state. It can be linked to the manual driving assistance warning function switch. For example, when the driver activates the manual driving assistance warning function (corresponding to the generation of a manual driving assistance warning command), the default preset driving assistance mode is automatically loaded as the current real-time driving assistance mode. Alternatively, the vehicle can automatically load the default preset driving assistance mode in its default state (i.e., when the driver has not manually set the driving assistance mode). Or, the driver can set the driving assistance mode through the vehicle's infotainment system, physical buttons, or voice commands, generating corresponding mode switching commands to manually select the desired preset driving assistance mode as the current real-time driving assistance mode. The default preset driving assistance mode can be a fixed preset driving assistance mode or the real-time driving assistance mode executed before the vehicle was last powered off. By introducing the aforementioned road environment information and operating parameters as input variables, we can not only describe the current driving environment and vehicle status more precisely, but also provide high-dimensional, multi-factor data support for the reasonable setting of subsequent target speed limits. This enables driving safety assessment and decision-making that better meets the actual dynamic needs of the vehicle, and improves the vehicle's risk identification capabilities and response accuracy in complex and changing scenarios.

[0076] Optionally, combined Figure 1 , Figure 3 As shown, in response to a manual driving assistance warning command, based on the road environment information of the vehicle's current lane and the vehicle's current operating parameters, as well as the preset road environment information-operating parameter-target speed limit mapping relationship, the target speed limit for the vehicle in its current lane is determined, including:

[0077] Step 110: In response to the manual driving assistance warning command, determine the vehicle's real-time driving assistance mode; wherein, the real-time driving assistance mode is a preset driving assistance mode executed by the vehicle according to the mode switching command, or a preset driving assistance mode automatically loaded by the vehicle in the default state.

[0078] Step 120: Based on road environment information and operating parameters, and combining the mapping relationship between road environment information, operating parameters, and target speed limit, determine the maximum permissible speed and the highest tire adhesion speed of the vehicle in the current lane.

[0079] Step 130: Use the minimum of the maximum permissible speed, the maximum speed with tire adhesion, and the road speed limit of the lane as the target speed limit.

[0080] Determining the target speed limit for a vehicle in its current lane involves a combination of factors, such as road geometry (lane curvature, gradient), road surface type (dry, wet, icy, gravel), and current vehicle operating parameters (real-time speed, current driving assistance mode or ideal lateral acceleration, vehicle acceleration, yaw rate, etc.). Multiple driving assistance modes are preset to adapt to different driving needs, each corresponding to a preset target lateral acceleration. The real-time driving assistance mode is the currently used preset driving assistance mode. The preset target lateral acceleration is the ideal lateral acceleration corresponding to different driving assistance modes (denoted as preset target lateral acceleration; it is the maximum lateral acceleration preset for ideal safety or comfort in different driving assistance modes; lateral acceleration refers to the centripetal acceleration generated by the vehicle's speed and turning radius when turning).

[0081] Therefore, the method in this embodiment does not rely solely on a single parameter in determining the target speed limit. Specifically, in step 110, upon receiving a manual driving assistance warning command, the vehicle's current real-time driving assistance mode is determined. In step 120, based on the acquired road environment information and operating parameters, intermediate parameters corresponding to these parameters in the road environment information-operating parameters-target speed limit mapping relationship are determined, such as the vehicle's current maximum permissible speed in the lane and the maximum tire adhesion speed. Based on this, in step 130, the acquired road speed limit parameter of the current lane is introduced, and the maximum permissible speed, the maximum tire adhesion speed, and the lane's road speed limit are comprehensively compared, selecting the minimum value as the final target speed limit. This ensures that the obtained target speed limit conforms to vehicle dynamics constraints (to avoid understeer, skidding, or rollover), reflects the actual road driving environment, and meets regulatory speed limits, thereby significantly improving the scientific rigor, rationality, and safety of speed determination and avoiding risks caused by insufficient consideration of a single factor.

[0082] The maximum permissible speed reflects the highest speed that a vehicle can withstand while smoothly passing through its current lane position, such as the highest speed that can withstand under current turning conditions and meet the requirements for safe cornering (i.e., lateral acceleration does not exceed the safety threshold); while the maximum tire adhesion speed reflects the highest feasible speed that a vehicle can avoid slipping due to insufficient lateral adhesion under different adhesion conditions (such as wet, icy, gravelly, etc.).

[0083] For example, upon receiving a manual driving assistance warning command, the vehicle's current real-time driving assistance mode is determined. This driving assistance mode can be linked to the manual driving assistance warning function switch. For instance, when the driver activates the manual driving assistance warning function (corresponding to the generation of a manual driving assistance warning command), the default preset driving assistance mode is automatically loaded as the current real-time driving assistance mode. Similarly, in the default state (i.e., when the driver has not manually set the driving assistance mode), the default preset driving assistance mode is automatically loaded. Alternatively, the driver can set the driving assistance mode through the vehicle's infotainment system, physical buttons, or voice commands, generating a corresponding mode switching command to manually select the desired preset driving assistance mode as the current real-time driving assistance mode. The default preset driving assistance mode can be a fixed preset driving assistance mode or the real-time driving assistance mode executed before the vehicle was last powered off.

[0084] Optionally, the mapping relationship between road environment information, operating parameters, and target speed limit includes: the mapping relationship between lane curvature, lateral acceleration, lane surface type, and maximum permissible speed; and the mapping relationship between lane surface type, lane curvature, and maximum tire adhesion speed.

[0085] Based on road environment information and operational parameters, and combining the mapping relationship between road environment information, operational parameters, and target speed limits, the maximum permissible speed and the maximum tire adhesion speed of the vehicle in its current lane are determined, including:

[0086] Based on the lane curvature, lane surface type, and preset target lateral acceleration corresponding to the real-time driving assistance mode, and combined with the mapping relationship between lane curvature-lateral acceleration-lane surface type-maximum permissible speed, the maximum permissible speed of the vehicle in the current lane is determined; and based on the lane curvature and lane surface type, and combined with the mapping relationship between lane surface type-lane curvature-maximum tire adhesion speed, the maximum tire adhesion speed of the vehicle in the current lane is determined.

[0087] Specifically, to improve the efficiency of determining the maximum permissible speed and the maximum tire adhesion speed of a vehicle currently in its lane, the mapping relationship between road environment information, operating parameters, and target speed limits can be pre-constructed into two sub-mapping relationships: a lane curvature-lateral acceleration-lane surface type-maximum permissible speed mapping relationship, and a lane surface type-lane curvature-maximum tire adhesion speed mapping relationship. These relationships are used to describe the stable and controllable safe speed range that a vehicle can achieve under different degrees of turning (i.e., lane curvature) and different road surface adhesion conditions, respectively. During actual vehicle operation, the corresponding maximum permissible speed and maximum tire adhesion speed can be quickly determined by looking up a table or calling a pre-defined mapping relationship model.

[0088] The mapping relationship between lane curvature, lateral acceleration, lane surface type, and maximum permissible speed can be constructed based on the vehicle dynamics model. For example, by considering the lateral acceleration constraints when the vehicle is turning, combined with the preset target lateral acceleration corresponding to the real-time driving assistance mode, and the maximum speed and lateral acceleration boundaries allowed by the current lane surface type, the maximum permissible speed under this combination condition can be further derived, thereby calibrating (constructing) the mapping relationship between lane curvature, lateral acceleration, lane surface type, and maximum permissible speed for the vehicle. The mapping relationship between lane surface type, lane curvature, and maximum tire adhesion speed can be established based on the corresponding relationship between the tire adhesion coefficient and the path curvature under different road surface conditions. For example, on gravel, wet, or icy roads, considering the influence of the change in the friction coefficient between the tire and the road surface on the adhesion limit, combined with the curvature of the vehicle's current path, the safe speed under the tire adhesion limit (i.e., the maximum tire adhesion speed) can also be derived, thereby calibrating (constructing) the mapping relationship between lane surface type, lane curvature, and maximum tire adhesion speed for the vehicle. Thus, based on the mapping relationship between lane curvature, lateral acceleration, lane surface type, and maximum permissible speed, the maximum permissible speed of the vehicle in the lane can be quickly and accurately determined according to the lane curvature, lane surface type, and preset target lateral acceleration corresponding to the real-time driving assistance mode; and based on the mapping relationship between lane surface type, lane curvature, and maximum tire adhesion speed, the maximum tire adhesion speed of the vehicle in the lane can be quickly and accurately determined according to the lane curvature and lane surface type.

[0089] The lane curvature can be obtained by curve fitting after identifying the lane edge lines using an environmental perception device. The lane surface type can be determined by considering lane image features acquired by the environmental perception device, tire slippage detected by the vehicle wheel speed sensor, yaw characteristics detected by the vehicle acceleration sensor, or by combining this with meteorological information detected by external environmental sensors. This allows for the determination of different road surface types for vehicles, such as dry, wet, icy, or gravelly. In determining the target speed limit, the lane surface type can be reflected in the corresponding road adhesion coefficient (which can be determined by both the lane surface type and vehicle tire parameters). The current preset target lateral acceleration is determined based on the driving assistance mode corresponding to the manual driving assistance warning command. For example, based on the driving assistance mode currently in operation when the manual driving assistance warning command is received (denoted as the real-time driving assistance mode), the preset target lateral acceleration corresponding to the real-time driving assistance mode is determined to determine the target speed limit. For instance, each driving assistance mode corresponds to a specific preset target lateral acceleration. In other words, different driving assistance modes correspond to different preset target lateral accelerations. For example, driving assistance modes include standard mode, safety mode, and custom mode. The preset target lateral acceleration for standard mode is... The preset target lateral acceleration corresponding to the safety mode The preset target lateral acceleration corresponding to the custom mode. Among them, the preset target lateral acceleration (parameter value) for different driving assistance modes, such as , , The system can be pre-calibrated for different vehicle models to take into account actual vehicle conditions. For example, during vehicle development or testing, through real vehicle tests and simulation tests, the extreme lateral acceleration values ​​of different vehicle models under different working conditions (such as dry road surface, wet and slippery road surface, and gravel road surface) can be obtained. Combined with the driver's comfort needs and safety redundancy coefficient, the target lateral acceleration calibration value (as the preset target lateral acceleration) for each vehicle model in each driving assistance mode can be determined. In some embodiments, the driver can manually set the preset target lateral acceleration corresponding to the custom mode.

[0090] Optionally, in determining the maximum permissible speed and the maximum tire adhesion speed of a lane based on the lane curvature, lane surface type, and the preset target lateral acceleration corresponding to the real-time driving assistance mode, the maximum permissible speed and the maximum tire adhesion speed can be calculated in real time based on a vehicle dynamics model. Alternatively, a preset model (or target speed limit calculation model) can be used for calculation. The preset model can be pre-built during the training phase using machine learning algorithms (such as neural networks, support vector machines, or ensemble learning models). The inputs include parameters such as lane curvature, target lateral acceleration, and road surface adhesion coefficient, and the outputs are the corresponding maximum permissible speed and maximum tire adhesion speed. The training data can come from real-vehicle road test data and / or high-precision simulation data under different working conditions to cover various lane types, road surface conditions, and driving modes. This allows the model to quickly and accurately provide the target speed limit during the inference phase. By adopting this preset model, not only can the real-time performance and accuracy of speed calculation be improved, but the system's generalization ability and robustness in complex environments can also be enhanced. Alternatively, it can be determined by looking up a map (MAP) based on a pre-defined mapping relationship between lane curvature, lane surface type (or road surface adhesion coefficient), driving assistance mode (or target lateral acceleration), maximum permissible speed, and maximum tire adhesion speed; for example, based on... Figure 4 The diagram showing the mapping relationship between lane curvature, lateral acceleration, lane surface type, and maximum permissible speed is shown below. Figure 4 (a) represents the mapping relationship between lane curvature, lateral acceleration, and maximum permissible vehicle speed when the road surface adhesion coefficient is 1. Figure 4 (b) represents the mapping relationship between lane curvature, lateral acceleration, and maximum permissible vehicle speed when the road surface adhesion coefficient is 0.6. Figure 4 (c) represents the mapping relationship between lane curvature, lateral acceleration, and maximum permissible speed when the road surface adhesion coefficient is 0.2, to determine the maximum permissible speed corresponding to a specific lane curvature and lateral acceleration.

[0091] For example, the lane curvature is determined based on a preset lane curvature-lateral acceleration-lane surface type (or road surface adhesion coefficient)-maximum permissible speed mapping relationship (MAP; which can be calibrated based on real vehicle experiments). Road surface adhesion coefficient corresponding to lane road surface type μ Preset target lateral acceleration corresponding to the vehicle's real-time driving assistance mode The maximum permissible speed corresponding to the above mapping relationship ,Right now:

[0092] .

[0093] For example, for the maximum permissible vehicle speed Maximum speed with tire adhesion and the speed limit for the lanes The minimum value in the range is used as the target speed limit. Output;

[0094] Among them, the highest vehicle speed with tire adhesion The lane curvature can be determined based on a preset mapping relationship between lane surface type (or road surface adhesion coefficient), lane curvature, and maximum tire adhesion speed. Road surface adhesion coefficient corresponding to lane road surface type μ The corresponding maximum tire grip speed Alternatively, the following formula can be used to calculate the mapping relationship between lane surface type (or road surface adhesion coefficient), lane curvature, and maximum tire adhesion speed:

[0095] ,

[0096] In the formula: μ This represents the current road surface adhesion coefficient (e.g., 0.9 for dry asphalt pavement, 0.6 for wet and slippery pavement, and 0.3 for snow pavement). g This is the gravitational acceleration at the location of the lane.

[0097] For example, for the driving assistance mode corresponding to the manual driving assistance warning command, when the driver turns on the driving assistance warning function (corresponding to the manual driving assistance warning command), the driver can first enter the standard mode by default, and then the driver can further set (switch) the driving assistance mode.

[0098] Optionally, combined Figure 2 As shown, road environment information includes lane curvature; vehicle driving assistance warning methods also include:

[0099] Based on the acquired image information about the lane, determine the lane edge line.

[0100] Considering that lane curvature directly reflects road geometry and affects vehicle stability in lanes (such as curves), this embodiment uses lane curvature determination to assist in determining the target speed limit. Specifically, image information about the lane is acquired through environmental perception devices (such as cameras / image sensors) mounted on the vehicle. For example, images of the road ahead are captured in real time by a camera or image sensor positioned forward of the vehicle. The images are then processed based on corresponding lane line detection algorithms (such as edge detection, Hough transform, or deep learning models) to identify and extract the position coordinates of the left and right edges of the lane for subsequent curve fitting and curvature calculation.

[0101] The lane edge lines can be solid or dashed lines marked on both sides of the road (e.g., lane edge lines). Figure 2As shown in the diagram, lane edge lines can be white or yellow lane markings on highways or urban expressways, or physical boundaries that define lane boundaries, such as curbs, guardrails, or medians. They can also be boundaries formed by temporary construction markings or reflective cones, and so on. Thus, by identifying and extracting different types of lane edge lines, the method of this embodiment can adapt to various road environments and achieve accurate perception of the actual driving lane range of a vehicle. In some embodiments, the lane edge line of the vehicle's current driving lane is preferably the lane edge line closest to the vehicle on both sides of that lane, in order to accurately define the spatial range of the vehicle's actual driving passage and avoid misidentifying the edge lines of adjacent or distant lanes as the boundary of this lane, thereby improving the accuracy of lane edge line extraction and the reliability of subsequent curvature calculation. If multiple lane edge lines are identified simultaneously, the two edge lines that best match the vehicle's current lane can be automatically selected as the boundary lines of this lane by combining the vehicle's current position, lateral offset, and navigation information.

[0102] Determine the lane curvature based on the lane edge lines.

[0103] Specifically, based on the determined lane edge lines, such as the determined left and right lane edge lines (in the vehicle coordinate system), curve fitting can be performed on them. For example, the least squares method can be used to perform second-order polynomial fitting on the edge line position coordinates to obtain the fitting function of the lane edge lines. Based on the derivative relationship of the fitting function, the curvature value of the current lane (i.e., lane curvature) can be calculated, which can be used for subsequent vehicle dynamics analysis and determination of the target speed limit.

[0104] The method in this embodiment can determine lane curvature in real time without relying on high-precision maps, based solely on the vehicle's environmental perception device (such as a monocular or binocular camera), and dynamically calculate the maximum safe driving speed (i.e., the target speed limit) of the vehicle in the current lane. This can significantly improve the applicability and safety of the vehicle in high-risk scenarios such as curves, thereby enhancing the fault tolerance of the method in this embodiment and the vehicle using this method in complex road conditions such as lane changes and occlusions. It effectively improves the real-time performance, accuracy, and robustness of lane curvature recognition, providing reliable input for subsequent warning triggering logic.

[0105] Optionally, based on the acquired image information about the lane, the lane edge line is determined by including:

[0106] Based on the image information, determine the coordinate position information of the lane edge line in the vehicle coordinate system.

[0107] Specifically, to facilitate accurate determination of lane curvature, the lane edge line pixels identified by the environmental perception device can be transformed from the image coordinate system to the vehicle coordinate system (such as a coordinate system built based on the vehicle, or a coordinate system built based on corresponding components on the vehicle, such as a coordinate system built based on the environmental perception device). This can be achieved by performing an inverse perspective transformation or a bird's-eye view (BEV) transformation on the identified lane edge lines based on the calibration parameters (such as intrinsic and extrinsic parameter matrices) of the environmental perception device. This maps the pixels on the two-dimensional image plane to their actual spatial coordinates in the vehicle coordinate system. Through this coordinate transformation, the positional relationship of the lane edge lines can be kept consistent with the actual driving direction of the vehicle, eliminating errors caused by factors such as camera installation angle and imaging distortion. In this way, in dynamic driving scenarios, curve fitting and curvature calculation of the lane edge lines can be performed based on a unified vehicle coordinate system. This makes the curvature calculation results more closely match the vehicle's kinematic characteristics and driving state, ensuring the accuracy and comparability of curvature estimation, and providing a stable and reliable data foundation for subsequent target speed limit calculations and risk warnings.

[0108] Determining lane curvature based on lane edge lines includes:

[0109] Based on the coordinate position information of multiple points on the lane edge line in the vehicle coordinate system, curve fitting is performed on the lane edge line to determine candidate curvature.

[0110] Specifically, based on the coordinate position information of multiple points on the lane edge line in the vehicle coordinate system, curve fitting is performed on the lane edge line. For example, the least squares method is used to perform second-order polynomial fitting to obtain the fitting function of the lane edge line. Based on the relationship between the first and second derivatives of the fitting function, the curvature of the current lane (denoted as candidate curvature) is calculated.

[0111] The validity of the candidate curvatures is verified.

[0112] Specifically, in order to ensure the reliability of the fitting and the credibility of the curvature results, and to avoid curvature distortion caused by identification noise or insufficient input points, the candidate curvature is validated to verify whether the currently obtained candidate curvature is accurate and effective.

[0113] If the candidate curvature verification passes, the lane curvature is determined based on the candidate curvature.

[0114] Specifically, based on the validity verification results, candidate curvatures are only used to determine the final lane curvature when they pass the validity verification. For example, if the lane curvature is determined only based on a single frame of image information, then the candidate curvature corresponding to that frame of image information is output as the lane curvature when it passes the validity verification. However, if the lane curvature is determined based on multiple consecutive frames of image information, then the lane curvature is determined based on the candidate curvatures corresponding to all frames of image information that have passed the verification. For example, the average value of all verified candidate curvatures is taken as the lane curvature to improve the stability and anti-interference ability of the results. In this way, it is ensured that the final output lane curvature can truly reflect the geometric characteristics of the vehicle's current driving lane, avoiding curvature distortion caused by insufficient input points, fitting degradation, sudden noise, or recognition anomalies, thereby providing accurate and reliable data support for subsequent target speed limit calculation and risk warning logic.

[0115] Optionally, based on the coordinate position information of multiple points on the lane edge line in the vehicle coordinate system, curve fitting is performed on the lane edge line to determine candidate curvatures, including:

[0116] Based on the coordinate position information of multiple points on the lane edge line in each frame of image information in a continuously preset number of frames, curve fitting is performed to determine the candidate curvature corresponding to each frame of image information.

[0117] Validating the candidate curvatures includes:

[0118] Validate the effectiveness of each candidate curvature;

[0119] If the candidate curvature verification passes, the lane curvature is determined based on the candidate curvature, including:

[0120] The mean of all validated candidate curvatures is determined as the lane curvature.

[0121] Specifically, considering the potential uncertainties in determining frame image information based on single-frame image information—for example, when the lane edge line in the frame image is blurred, partially missing, obscured by the preceding vehicle or guardrail, or when noise increases due to changes in lighting or rain / snow—the candidate curvature obtained from single-frame fitting may fluctuate or become distorted, thus affecting the final curvature calculation result. Therefore, a method can be used to determine the candidate curvature corresponding to each frame image information by combining image information from a continuously preset number of frames. For instance, based on the coordinate position information of multiple points on the lane edge line in each continuously preset number of frames image information, curve fitting can be performed to determine the candidate curvature corresponding to each frame image information. The validity of the candidate curvature corresponding to each frame image information is then verified. The mean (e.g., average or weighted average) of all verified candidate curvatures is calculated. This mean is used as the lane curvature corresponding to the vehicle's current position in the driving lane (or the lane curvature corresponding to the corresponding position ahead of the vehicle in the current driving lane) to reduce the impact of instantaneous anomalies on the curvature output and ensure the stability and robustness of the curvature estimation. In some embodiments, the lane curvature can also be obtained by smoothing or statistically fusing (such as averaging, weighted averaging, or filtering) all the verified candidate curvatures.

[0122] Thus, even in complex or dynamically changing road environments, the method of this embodiment can still output more accurate and continuous lane curvature, providing reliable support for determining target speed limits and providing driving safety warnings.

[0123] Optionally, validating the candidate curvature includes:

[0124] Determine whether the candidate curvature meets the preset fitting reliability and curvature credibility constraints; wherein the preset fitting reliability and curvature credibility constraints include preset input point number constraints, preset matrix rank verification conditions, preset curvature range constraints, preset inter-frame smoothness verification conditions, and preset derivative slope boundary conditions.

[0125] If a candidate curvature simultaneously meets the preset input point limit, preset matrix rank verification condition, preset curvature range limit, preset inter-frame smoothness verification condition, and preset derivative slope boundary condition, the candidate curvature is deemed to have passed verification; if a candidate curvature does not meet any of the preset input point limit, preset matrix rank verification condition, preset curvature range limit, preset inter-frame smoothness verification condition, and preset derivative slope boundary condition, the candidate curvature is deemed to have failed verification.

[0126] Specifically, in the process of validating the candidate curvature, based on the preset judgment conditions (i.e. preset fitting reliability and curvature credibility constraints), it is determined whether the obtained candidate curvature meets the preset fitting reliability and curvature credibility constraints. If it meets the constraints, the candidate curvature is considered to have passed the verification; otherwise, the verification fails.

[0127] For example, the preset constraints on fit reliability and curvature confidence include the following conditions:

[0128] The preset input point limit condition means that the number of points on the lane edge line used for curve fitting must be greater than or equal to the preset point threshold to avoid unstable fitting results due to too few points.

[0129] A preset matrix rank verification condition is set, meaning that the matrix in the fitting process must satisfy the full rank condition to ensure that the fitting process does not degenerate and to guarantee the mathematical validity of the output curvature.

[0130] The preset curvature range limit condition means that the candidate curvature value must be within a reasonable physical range, such as excluding abnormally large or negative values ​​caused by noise or recognition errors;

[0131] The preset inter-frame smoothness verification condition is that the rate of change of candidate curvature in multiple consecutive frames must be less than a preset threshold in order to avoid abrupt changes that do not conform to the road geometry.

[0132] The boundary condition of the derivative slope is preset, that is, the slope of the edge line calculated based on the derivative of the fitted function must be within a reasonable range, so as to further ensure the reliability of the curvature value;

[0133] When a candidate curvature simultaneously meets all the above conditions, it is considered to satisfy the preset fitting reliability and curvature credibility constraints, and the verification is passed. Conversely, if a candidate curvature does not satisfy any of the above conditions, it is considered not to satisfy the preset fitting reliability and curvature credibility constraints, and the verification fails. Thus, through the joint determination of the above constraints, multi-level anomaly detection is achieved, enabling the method of this embodiment to effectively filter out erroneous curvature values ​​caused by lane recognition anomalies, lighting interference, partial occlusion, or noise. This achieves stable restoration and dynamic tracking of changes in the curvature of the road ahead, thereby improving the reliability and robustness of the final lane curvature output and providing stable data support for subsequent target speed limit calculations and risk warning logic.

[0134] For example, to determine the lane curvature, the edge coordinates of the lane edges are first acquired. This can be done by acquiring real-time images of the road ahead using a monocular or binocular camera mounted at the front of the vehicle. Based on visual recognition algorithms (such as edge detection, deep learning models, etc.), the pixel coordinates of the left and right lane edges are extracted and transformed into a sequence of two-dimensional coordinate points in a vehicle coordinate system with the rear axle center as the origin through projection transformation. The identified lane edge coordinate data is then sent at a fixed period (the time interval between acquiring adjacent frames of image information, such as 100ms). For example, the coordinates of the left lane edge are represented as: The coordinates of the right edge of the lane are represented as follows: ;in, N This represents the number of sampling points along the edge of each lane; a typical value can be taken as... N =50; The lateral coordinates of the corresponding point in the vehicle coordinate system are, i.e. Let be the lateral coordinates of the corresponding point on the left edge of the lane in the vehicle coordinate system. This represents the lateral coordinates of the corresponding point on the right edge of the lane in the vehicle coordinate system. The longitudinal coordinate of the corresponding point in the vehicle coordinate system is, i.e. This represents the longitudinal coordinates of the corresponding point on the left edge of the lane in the vehicle coordinate system. This represents the longitudinal coordinates of the corresponding point on the right edge of the lane in the vehicle coordinate system. Subsequently, based on the lane edge coordinates, curve fitting is performed using the least squares method to model the lane edge as a function of longitudinal distance. Quadratic polynomial function: ,in, 、 、 These are the coefficients of the quadratic term, the coefficients of the linear term, and the constant term, representing the curvature, tilt trend, and overall offset of the lane edge line; the fitting matrix and solution are constructed as follows:

[0135] Input vector:

[0136] ,

[0137] Construct the corresponding Vandermonde matrix:

[0138] ,

[0139] Horizontal coordinate vector:

[0140] ,

[0141] The least squares fitting coefficients are:

[0142] ,

[0143] After successful fitting, the road curvature is calculated using the derivative formula. For example,... The curve represented in the formal way, its curvature for:

[0144] ,

[0145] in,

[0146] ,

[0147] ,

[0148] Evaluation points are usually selected. To obtain the current candidate curvature The unit is :

[0149] .

[0150] Subsequently, the validity of the candidate curvatures is verified. To ensure the reliability of the fitting and the credibility of the curvature results, the following constraints and verification mechanisms are introduced:

[0151] 1) Points validity check: If the input points are valid... ( If the preset number of points is a threshold (e.g., 50), or all points are invalid or empty, it is considered abnormal and an invalid status (i.e., verification failed) is output.

[0152] 2) Fitting matrix rank detection: If the Vandermonde matrix Insufficient full rank, such as the Vandermonde matrix rank This indicates that the point set is degenerate or collinear, the fitting has failed, and an invalid state is output (i.e., the validation has not passed).

[0153] 3) Curvature range limitation: If the calculated candidate curvature Not satisfied This indicates that the candidate curvature is unreliable, and an invalid state is output (i.e., verification failed); in some embodiments, this indicates that the candidate curvature is unreliable. A value of 0.0015 is acceptable. 0.03 is acceptable;

[0154] 4) Continuous frame smoothness check: Perform first-order difference on the curvature changes of multiple consecutive frames to prevent jumps. If the output is invalid (i.e., verification failed), then the output will be an invalid status.

[0155] 5) Derivative slope boundary check: If the absolute value of the fitted derivative is... Greater than the threshold ,Right now If the slope is abnormal, an invalid status will be output (i.e., the verification failed).

[0156] Finally, if the candidate curvature If the verification passes, the curvature state is... It outputs the candidate curvatures that have passed the verification. If candidate curvature If the verification fails, then Candidate curvature If invalid, you can choose to discard the image information of the corresponding frame.

[0157] For example, when determining the lane curvature based on all verified candidate curvatures, a moving average filter can be introduced to enhance the stability of curvature estimation across consecutive frames, applying the filter to a preset number of consecutive frames (e.g., a preset number of frames). M The candidate curvature corresponding to the image information that passed the frame verification (i.e.) Smooth the image, such as the (previous) image. M The candidate curvatures corresponding to the image information that passed frame verification are smoothed using the following moving average formula:

[0158] ,

[0159] in, The average curvature of the k-th frame (the lane curvature obtained after smoothing). M The size of the sliding window (i.e., how many frames of verified image information are used to average the candidate curvature). express M The first frame corresponds to the image information that passed the candidate curvature verification. Candidate curvature of frame image information; the moving average formula represents the curvature of the frame image information. M The average value of the candidate curvatures corresponding to the image information that passed frame verification is used to obtain the lane curvature of the current lane. It should be noted that the superscripts and subscripts in the formula use... to rather than simply 1 to M This is to reflect the dynamic characteristics of the sliding window, that is, at any given moment... Each frame takes the candidate curvature corresponding to the image information that has passed verification in the current frame and its preceding continuous curve. M The candidate curvatures corresponding to the image information that passed the verification of -1 frame are averaged to ensure that the output results can reflect the smoothness of the curvature and track the dynamic changes of road curvature in real time.

[0160] Optionally, the lane curvature can be calculated based on the left and right edge lines of the lane respectively, and then the two can be weighted and fused to obtain the comprehensive curvature of the lane center as the final lane curvature, which is used as the basis for calculating the target speed limit. For example, an arithmetic mean, weighted average, or a weighted fusion method based on the confidence of edge line recognition can be used to improve the accuracy and stability of curvature determination. Alternatively, considering that the curvature values ​​of the left and right edge lines of the lane are usually approximately the same in most cases, the curvature corresponding to either the left or right edge line can be directly selected as the lane curvature to simplify calculation and reduce the real-time processing burden. In some implementations, if both left and right lane edge lines can be stably recognized, a weighted fusion method is preferred to enhance robustness; while when one edge line is occluded, has insufficient recognition confidence, or is missing, the calculation can be performed based only on the curvature of the other edge line. In this way, while ensuring real-time performance and reliability, adaptability to different road environments can be taken into account.

[0161] Optionally, generating early warning information includes:

[0162] Early warning information is generated periodically within a preset time period.

[0163] Specifically, a warning message is generated when the vehicle's real-time speed meets the warning trigger conditions related to the target speed limit. During the warning message generation process, it is preferable to continuously output the warning message according to a preset periodic rule within a preset duration. For example, combined with... Figure 5 The diagram showing the output status of the warning information indicates that if the warning trigger condition for limiting the vehicle speed is met at time t1, then within the subsequent preset duration T, a warning information lasting for a duration of T1 will be generated (and output) every T2 intervals, with a duration of T2 as the interval. Figure 5 The generation of warning information (corresponding to state 1) occurs from time t1 to t2, t3 to t4, t5 to t6, and t7 to t8. Warning information generation is paused (corresponding to state 0) from time t2 to t3, t4 to t5, and t6 to t7. This periodic output method avoids driver auditory or visual fatigue caused by continuous output and effectively prevents drivers from ignoring single warning prompts. It ensures that drivers continuously receive intuitive and clear risk reminders throughout the entire risk period, further improving the effectiveness and reliability of warning prompts.

[0164] For example, when generating a warning message, the corresponding prompt can be periodically displayed on the vehicle's infotainment system or instrument panel in text or icon form within a preset time period, such as "Please slow down on curves." Simultaneously, the message can also be periodically broadcast via voice. In some embodiments, the driver can choose to enable or disable the corresponding prompt method as needed. Enabling or disabling prompt methods such as the vehicle's infotainment system, instrument panel, and voice broadcast enriches the personalized selection of warning message prompt methods.

[0165] Optionally, in response to the vehicle's real-time speed meeting the warning triggering conditions regarding the target speed limit, the warning information generated includes:

[0166] A warning message is generated in response to the vehicle's real-time speed meeting the warning trigger conditions for the target speed limit and the real-time speed being greater than the preset minimum warning speed limit.

[0167] Specifically, considering that vehicles traveling at lower speeds (e.g., speeds less than or equal to the preset minimum warning speed limit) are less likely to experience excessive speeds while cornering or insufficient deceleration, thus posing no risk to driving safety, if the target speed limit is lower than the preset minimum warning speed limit, and the vehicle speed is between the target speed limit and the preset minimum warning speed limit, the generated warning information is meaningless. Therefore, in this case, it is advisable not to generate warning information to avoid frequent output of invalid or redundant prompts during low-speed vehicle operation, which could cause driver interference or information fatigue. The minimum warning speed limit can be set according to actual needs, such as 30 km / h. km / h .

[0168] Accordingly, when the vehicle's real-time speed meets the warning triggering conditions for the target speed limit and the real-time speed is greater than the preset minimum warning speed limit, a warning message is generated. This ensures that the warning prompts are more focused on high-speed or critical operating conditions where there is a real risk, thereby improving the rationality and effectiveness of the warning strategy and enhancing the driver's trust and acceptance of the vehicle driving assistance warning.

[0169] Optionally, when a manual driving assistance warning exit instruction is received, if the driver actively turns off the manual driving assistance warning function switch, such as by issuing an exit instruction through the vehicle interface, physical buttons, voice commands, etc., the vehicle will automatically turn off the corresponding warning function and stop the generation and output of subsequent warning information.

[0170] Combination Figure 6 As shown, another embodiment of the present invention provides a vehicle driving assistance warning device, comprising:

[0171] The calculation unit is used to respond to manual driving assistance warning commands and determine the target speed limit of the lane based on the road environment information of the lane in which the vehicle is currently driving;

[0172] The warning unit is used to generate warning information in response to the vehicle's real-time speed meeting the warning triggering conditions related to the target speed limit.

[0173] The vehicle driving assistance warning device of this embodiment is used to implement the above-mentioned vehicle driving assistance warning method. Its advantages over the prior art are the same as the advantages of the above-mentioned vehicle driving assistance warning method over the prior art, and will not be repeated here.

[0174] Combination Figure 7 As shown, another embodiment of the present invention provides a vehicle, including a memory 701 and a processor 702;

[0175] Memory 701 is used to store computer programs;

[0176] The processor 702 is used to implement the vehicle driving assistance warning method described above when executing a computer program.

[0177] Alternatively, a vehicle includes a memory 701 and a processor 702 coupled to the memory 701; the memory 701 is configured to store a computer program; the processor 702 is configured to perform the following operations when the computer program is executed:

[0178] In response to manual driving assistance warning commands, the target speed limit for the lane is determined based on road environment information of the current lane in which the vehicle is driving;

[0179] A warning message is generated in response to the vehicle's real-time speed meeting the warning trigger conditions for the target speed limit.

[0180] The vehicle in this embodiment can be used to implement the above-described vehicle driving assistance warning method. Its advantages over the prior art are the same as those of the above-described vehicle driving assistance warning method over the prior art, and will not be repeated here.

[0181] Another embodiment of the present invention provides a computer-readable storage medium storing a computer program, which is read and executed by a processor to implement the vehicle driving assistance warning method described above.

[0182] Alternatively, a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the following operations:

[0183] In response to manual driving assistance warning commands, the target speed limit for the lane is determined based on road environment information of the current lane in which the vehicle is driving;

[0184] A warning message is generated in response to the vehicle's real-time speed meeting the warning trigger conditions for the target speed limit.

[0185] The technical solutions of the embodiments of the present invention, or the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods of the embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, external hard drives, ROM, RAM, magnetic disks, or optical disks.

[0186] The computer-readable storage medium of this embodiment can be used to implement the above-described vehicle driving assistance warning method. Its advantages over the prior art are the same as those of the above-described vehicle driving assistance warning method over the prior art, and will not be repeated here.

[0187] While the present invention has been disclosed above, its scope of protection is not limited thereto. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention, and all such changes and modifications will fall within the scope of protection of the present invention.

Claims

1. A vehicle travel assist warning method characterized by, The vehicle driving assistance warning method comprises the following steps: in response to a manual driving assistance warning instruction, determining a target limit speed of the vehicle in a current lane according to road environment information of the current lane and current running parameters of the vehicle, and a preset road environment information-running parameter-target limit speed mapping relationship; in response to a real-time vehicle speed of the vehicle satisfying a warning trigger condition related to the target limit speed, generating a warning information; The vehicle driving assistance warning method further comprises: calibrating the target limit speed of the vehicle under different road environment information and different running parameters, and constructing the road environment information-running parameter-target limit speed mapping relationship; wherein the road environment information comprises at least one of lane curvature, road surface type, and road speed limit; the running parameters comprise at least one of vehicle speed and real-time driving assistance mode; The response to the manual driving assistance warning instruction, according to the road environment information of the vehicle's current driving lane and the vehicle's current running parameters, and the preset road environment information-running parameter-target limit speed mapping relationship, determines the target limit speed of the vehicle in the current lane includes: in response to the manual driving assistance warning instruction, determining the real-time driving assistance mode of the vehicle; wherein the real-time driving assistance mode is a preset driving assistance mode executed by the vehicle according to a mode switching instruction, or is the preset driving assistance mode automatically loaded by the vehicle in a default state; According to the road environment information and the running parameters, combined with the road environment information-running parameter-target limit speed mapping relationship, determine the maximum allowable speed and the tire adhesion highest speed of the vehicle in the current lane; The minimum value of the maximum allowable speed, the tire adhesion highest speed and the road speed limit of the lane is taken as the target limit speed.

2. The vehicle travel assist warning method according to claim 1, characterized by, The warning trigger condition comprises: The real-time vehicle speed is greater than or equal to the target limit speed; And / or, the real-time vehicle speed is greater than or equal to the difference between the target limit speed and a preset threshold, and the real-time acceleration of the vehicle is greater than 0.

3. The vehicle travel assist warning method according to claim 1 or 2, characterized by, The road environment information-running parameter-target limit speed mapping relationship comprises: lane curvature-lateral acceleration-road surface type-maximum allowable speed mapping relationship, road surface type-lane curvature-tire adhesion highest speed mapping relationship; According to the road environment information and the running parameters, combined with the road environment information-running parameter-target limit speed mapping relationship, determine the maximum allowable speed and the tire adhesion highest speed of the vehicle in the current lane includes: determining the maximum allowable speed of the vehicle currently in the lane according to the lane curvature, the road surface type of the lane, and a preset target lateral acceleration corresponding to the real-time driving assistance mode, in combination with a lane curvature-lateral acceleration-road surface type-maximum allowable speed mapping relationship; and determining the highest tire adhesion speed of the vehicle currently in the lane according to the lane curvature and the road surface type of the lane, in combination with a road surface type-lane curvature-highest tire adhesion speed mapping relationship.

4. The vehicle travel assist warning method according to claim 1, characterized by, The road environment information comprises a lane curvature. The vehicle driving assistance and early warning method further comprises: determining a lane edge line of the lane according to the acquired image information about the lane; determining the lane curvature according to the lane edge line; determining the target limit speed according to the lane curvature.

5. The vehicle travel assist warning method according to claim 4, characterized by, The determining of the lane edge line of the lane according to the acquired image information about the lane comprises: determining coordinate position information of the lane edge line in a vehicle coordinate system according to the image information; The determining of the lane curvature according to the lane edge line comprises: performing curve fitting on the lane edge line based on the coordinate position information of a plurality of position points on the lane edge line in the vehicle coordinate system to determine a candidate curvature; validating the candidate curvature; if the candidate curvature passes the validation, determining the lane curvature according to the candidate curvature.

6. The vehicle travel assist warning method according to claim 5, characterized by The performing of the curve fitting on the lane edge line based on the coordinate position information of a plurality of position points on the lane edge line in the vehicle coordinate system to determine a candidate curvature comprises: performing the curve fitting based on the coordinate position information of a plurality of position points on the lane edge line in each of a plurality of continuous preset frames of the image information to determine the candidate curvature corresponding to each frame of the image information; The validating of the candidate curvature comprises: validating all the candidate curvatures respectively; The determining of the lane curvature according to the candidate curvature if the candidate curvature passes the validation comprises: determining the mean value of all the candidate curvatures that pass the validation as the lane curvature.

7. The vehicle travel assist warning method according to claim 5, characterized by, The validating of the candidate curvature comprises: judging whether the candidate curvature satisfies preset fitting reliability and curvature credibility limit conditions; wherein the preset fitting reliability and curvature credibility limit conditions comprise a preset input point number limit condition, a preset matrix rank check condition, a preset curvature range limit condition, a preset inter-frame smoothness check condition, and a preset derivative slope boundary condition. If the candidate curvature satisfies the preset input point number limit condition, the preset matrix rank check condition, the preset curvature range limit condition, the preset inter-frame smoothness check condition and the preset derivative slope boundary condition simultaneously, it is determined that the candidate curvature passes the verification; if the candidate curvature does not satisfy any one of the preset input point number limit condition, the preset matrix rank check condition, the preset curvature range limit condition, the preset inter-frame smoothness check condition and the preset derivative slope boundary condition, it is determined that the candidate curvature fails the verification.

8. A vehicle travel assist warning device characterized by comprising: Comprise: The computing unit is used for determining the target limit speed of the vehicle in the current lane according to the road environment information of the current lane and the current operating parameter of the vehicle, and a preset road environment information-operating parameter-target limit speed mapping relationship in response to a manual driving assistance warning instruction; The warning unit is used for generating a warning information in response to the real-time speed of the vehicle satisfying a warning trigger condition about the target limit speed; The vehicle driving assistance warning device is further used for: Calibrating the target limit speed of the vehicle under different road environment information and different operating parameters, and constructing the road environment information-operating parameter-target limit speed mapping relationship; wherein the road environment information comprises at least one of lane curvature, road surface type and road speed limit; the operating parameter comprises at least one of vehicle speed and real-time driving assistance mode; The response to the manual driving assistance warning instruction, the determination of the target limit speed of the vehicle in the current lane according to the road environment information of the current lane and the current operating parameter of the vehicle, and the preset road environment information-operating parameter-target limit speed mapping relationship comprises: In response to the manual driving assistance warning instruction, determining the real-time driving assistance mode of the vehicle; wherein the real-time driving assistance mode is a preset driving assistance mode executed by the vehicle according to a mode switching instruction, or is the preset driving assistance mode automatically loaded by the vehicle in a default state; According to the road environment information and the operating parameter, combining the road environment information-operating parameter-target limit speed mapping relationship, determining the maximum allowable speed of the vehicle in the current lane and the highest tire adhesion speed; Taking the minimum value of the maximum allowable speed, the highest tire adhesion speed and the road speed limit of the lane as the target limit speed.

9. A vehicle characterized by comprising: Comprise a memory and a processor; The memory is used for storing a computer program; The processor is used for implementing the vehicle driving assistance warning method of any one of claims 1-7 when executing the computer program.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is read and run by the processor to implement the vehicle driving assistance warning method of any one of claims 1-7.

Images