Method, system, device and medium for assisted driving based on road surface environment information

Abstract

The application discloses an auxiliary driving method and system based on road surface environment information, equipment and medium, and belongs to the technical field of general control or regulation systems. The method comprises the following steps: acquiring road surface environment information; acquiring vehicle use time length information, and determining a road situation grade based on the road surface environment information, the vehicle use time length information and a pre-trained road situation evaluation model; acquiring historical risk situation information and determining a risk occurrence probability based on the road situation grade and the historical risk situation information; acquiring vehicle state information and determining a target auxiliary driving strategy based on target object identification information, road surface state information, the road situation grade, the risk occurrence probability and the vehicle state information; and performing auxiliary driving control of the vehicle based on the target auxiliary driving strategy. According to the technical scheme, the environmental information, the road surface state information and the road state information are deeply integrated, the auxiliary driving strategy suitable for different road surface characteristics is output, and the safety, stability and adaptability are improved.

Description

Technical Field

[0001] This application belongs to the field of control or regulation system technology, specifically relating to assisted driving methods, systems, devices and media based on road environment information. Background Technology

[0002] Advanced driver assistance systems (ADAS) are a class of key technologies that proactively intervene in vehicle control to ensure safety when potential driving risks are detected. These technologies aim to compensate for driver reaction delays or improper operation through real-time risk assessment and automated intervention, effectively preventing dangerous accidents such as collisions and skidding. They are a core means of improving vehicle active safety performance.

[0003] However, the risk assessment logic of current driver assistance systems has significant limitations. Most rely on sensors such as cameras and radar to capture dynamic information about surrounding vehicles and pedestrians to determine risk and trigger braking or evasive maneuvers. This approach over-depends on "visible" moving obstacles, severely neglecting the inherent and constantly changing hazards of road infrastructure itself. In fact, even on roads without other road users, the slipperiness, iciness, potholes, or abnormal wear of the road surface constitute potential and frequent sources of driving hazards. Current driver assistance systems lack the fine-grained perception and assessment of this crucial risk dimension of road conditions, thus failing to accurately predict dangerous situations for the vehicle and consequently failing to provide safer driver assistance control, requiring improvement. Summary of the Invention

[0004] This application provides an assisted driving method, system, device, and medium based on road environment information. By deeply integrating environmental information, road surface condition information, and road condition information, it outputs assisted driving strategies adapted to different road surface characteristics, thereby improving the safety, stability, and adaptability of assisted driving control in complex road surface scenarios.

[0005] In a first aspect, embodiments of this application provide an assisted driving method based on road environment information, the method comprising: Acquire road surface environment information; wherein, the road surface environment information includes target object identification information, road surface condition information, and road condition information, and the road surface condition information includes the road surface friction coefficient and road surface humidity; The vehicle usage time information is obtained, and the road condition level is determined based on the road environment information, the vehicle usage time information, and the pre-trained road condition assessment model. Obtain historical risk information and determine the probability of risk occurrence based on the road condition level and the historical risk information; Obtain vehicle status information, and determine a target assisted driving strategy based on the target object identification information, the road surface status information, the road situation level, the risk occurrence probability, and the vehicle status information; The vehicle's assisted driving control is performed based on the aforementioned target assisted driving strategy.

[0006] Optionally, determining the assisted driving strategy based on the target object identification information, the road surface condition information, the road situation level, the risk occurrence probability, and the vehicle status information includes: The target object identification information, the road surface condition information, the road situation level, the risk occurrence probability, and the vehicle status information are matched with a preset assisted driving rule base to obtain an initial assisted driving strategy. Predict future vehicle status information based on the initial assisted driving strategy; Based on the initial driver assistance strategy and the future vehicle state information, a target driver assistance strategy is determined.

[0007] Optionally, the number of initial driver assistance strategies is at least two; Accordingly, determining the target assisted driving strategy based on the initial assisted driving strategy and the future vehicle state information includes: Based on each of the initial driver assistance strategies, the future vehicle state information corresponding to each of the initial driver assistance strategies, and the pre-constructed comprehensive cost function, the comprehensive cost score of each of the initial driver assistance strategies is determined; wherein, the dynamic adjustment weights in the comprehensive cost function include safety cost weights, comfort cost weights, and traffic efficiency cost weights. The initial driver assistance strategy with the lowest overall cost score is determined as the target driver assistance strategy.

[0008] Optionally, before determining the comprehensive cost score of each initial driver assistance strategy based on each initial driver assistance strategy, the future vehicle state information corresponding to each initial driver assistance strategy, and a pre-constructed comprehensive cost function, the method further includes: The safety cost weight is determined based on the road condition level and the probability of risk occurrence. Acquire historical user operation data and determine the comfort cost weight based on the historical user operation data; The traffic efficiency cost weight is determined based on the road condition information.

[0009] Optionally, the historical risk information includes historical road risk information and historical vehicle risk information; Accordingly, determining the probability of risk occurrence based on the road condition level and the historical risk information includes: The probability of the first risk occurring is determined based on the road condition level and the historical road risk information. Obtain vehicle status information, and determine the probability of the second risk occurring based on the vehicle status information and the historical vehicle risk information; The frequency of historical vehicle risk events is calculated based on the historical vehicle risk information, and the risk probability weight is determined based on the frequency of historical vehicle risk events. The probability of occurrence of the first risk and the probability of occurrence of the second risk are weighted and summed based on the risk probability weights to obtain the probability of occurrence of the risk.

[0010] Optionally, determining the road condition level based on the road surface environment information, the vehicle usage time information, and a pre-trained road condition assessment model includes: The road surface environment information is input into a pre-trained road condition assessment model to obtain the basic road condition level output by the road condition assessment model. Obtain vehicle tire material information, and determine the vehicle stability coefficient based on the vehicle tire material information and the vehicle usage time information; Obtain vehicle braking type information, and determine the vehicle braking attenuation coefficient based on the vehicle braking type information and the vehicle usage time information; The basic road condition level is corrected based on the vehicle stability coefficient, the vehicle brake fade coefficient, and the road surface condition information to obtain the road condition level.

[0011] Optionally, the road surface condition information may also include road surface slope information; Accordingly, the step of correcting the basic road condition level based on the vehicle stability coefficient, the vehicle brake fade coefficient, and the road surface condition information to obtain the road condition level includes: The vehicle grip risk coefficient is determined based on the vehicle stability coefficient and the road surface condition information. The comprehensive performance risk coefficient is determined based on the vehicle grip risk coefficient and the vehicle brake fade coefficient. The target level correction strategy is determined based on the comprehensive performance risk coefficient and the pre-constructed mapping relationship between the comprehensive performance risk coefficient and the level correction strategy. The target level correction strategy is applied to the basic road condition level to obtain the road condition level.

[0012] Secondly, embodiments of this application provide an assisted driving system based on road environment information, the system comprising: A road surface environment acquisition module is used to acquire road surface environment information; wherein, the road surface environment information includes target object identification information, road surface condition information, and road condition information, and the road surface condition information includes the road surface friction coefficient and road surface humidity; The situation level determination module is used to acquire vehicle usage time information and determine the road situation level based on the road environment information, the vehicle usage time information and the pre-trained road situation assessment model. The risk probability determination module is used to acquire historical risk information and determine the probability of risk occurrence based on the road condition level and the historical risk information. The auxiliary strategy determination module is used to acquire vehicle status information and determine the target assisted driving strategy based on the target object identification information, the road surface status information, the road situation level, the risk occurrence probability, and the vehicle status information. The assisted driving control module is used to perform assisted driving control of the vehicle based on the target assisted driving strategy.

[0013] Optionally, the auxiliary strategy determination module is specifically used for: The target object identification information, the road surface condition information, the road situation level, the risk occurrence probability, and the vehicle status information are matched with a preset assisted driving rule base to obtain an initial assisted driving strategy. Predict future vehicle status information based on the initial assisted driving strategy; Based on the initial driver assistance strategy and the future vehicle state information, a target driver assistance strategy is determined.

[0014] Optionally, the number of initial driver assistance strategies is at least two; Accordingly, the auxiliary strategy determination module is further configured to: Based on each of the initial driver assistance strategies, the future vehicle state information corresponding to each of the initial driver assistance strategies, and the pre-constructed comprehensive cost function, the comprehensive cost score of each of the initial driver assistance strategies is determined; wherein, the dynamic adjustment weights in the comprehensive cost function include safety cost weights, comfort cost weights, and traffic efficiency cost weights. The initial driver assistance strategy with the lowest overall cost score is determined as the target driver assistance strategy.

[0015] Optionally, the auxiliary strategy determination module is further configured to: The safety cost weight is determined based on the road condition level and the probability of risk occurrence. Acquire historical user operation data and determine the comfort cost weight based on the historical user operation data; The traffic efficiency cost weight is determined based on the road condition information.

[0016] Optionally, the historical risk information includes historical road risk information and historical vehicle risk information; Accordingly, the risk probability determination module is specifically used for: The probability of the first risk occurring is determined based on the road condition level and the historical road risk information. Obtain vehicle status information, and determine the probability of the second risk occurring based on the vehicle status information and the historical vehicle risk information; The frequency of historical vehicle risk events is calculated based on the historical vehicle risk information, and the risk probability weight is determined based on the frequency of historical vehicle risk events. The probability of occurrence of the first risk and the probability of occurrence of the second risk are weighted and summed based on the risk probability weights to obtain the probability of occurrence of the risk.

[0017] Optionally, the situation level determination module is specifically used for: The road surface environment information is input into a pre-trained road condition assessment model to obtain the basic road condition level output by the road condition assessment model. Obtain vehicle tire material information, and determine the vehicle stability coefficient based on the vehicle tire material information and the vehicle usage time information; Obtain vehicle braking type information, and determine the vehicle braking attenuation coefficient based on the vehicle braking type information and the vehicle usage time information; The basic road condition level is corrected based on the vehicle stability coefficient, the vehicle brake fade coefficient, and the road surface condition information to obtain the road condition level.

[0018] Optionally, the road surface condition information may also include road surface slope information; Accordingly, the situation level determination module is also used for: The vehicle grip risk coefficient is determined based on the vehicle stability coefficient and the road surface condition information. The comprehensive performance risk coefficient is determined based on the vehicle grip risk coefficient and the vehicle brake fade coefficient. The target level correction strategy is determined based on the comprehensive performance risk coefficient and the pre-constructed mapping relationship between the comprehensive performance risk coefficient and the level correction strategy. The target level correction strategy is applied to the basic road condition level to obtain the road condition level.

[0019] Thirdly, embodiments of this application provide an electronic device including a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the method described in the first aspect.

[0020] Fourthly, embodiments of this application provide a readable storage medium on which a program or instructions are stored, which, when executed by a processor, implement the method described in the first aspect.

[0021] In this embodiment, road environment information is acquired, including target object identification information, road surface condition information, and road condition information, wherein the road surface condition information includes the road surface friction coefficient and road surface humidity; vehicle usage time information is acquired, and a road condition level is determined based on the road environment information, the vehicle usage time information, and a pre-trained road condition assessment model; historical risk information is acquired, and the probability of risk occurrence is determined based on the road condition level and the historical risk information; vehicle condition information is acquired, and a target assisted driving strategy is determined based on the target object identification information, the road surface condition information, the road condition level, the probability of risk occurrence, and the vehicle condition information; and assisted driving control of the vehicle is performed based on the target assisted driving strategy. The above-described assisted driving method based on road environment information, by deeply integrating environmental information, road surface condition information, and road condition information, outputs assisted driving strategies adapted to different road surface characteristics, improving the safety, stability, and adaptability of assisted driving control in complex road surface scenarios. Attached Figure Description

[0022] Figure 1 This is a flowchart illustrating an assisted driving method based on road environment information provided in an embodiment of this application; Figure 2 This is a schematic diagram illustrating the interaction between the situation level determination module and the risk probability determination module provided in the embodiments of this application; Figure 3 This is an example diagram of a system architecture for vehicle assisted driving control based on the target assisted driving strategy provided in this application embodiment; Figure 4 This is a schematic flowchart of another assisted driving method based on road environment information provided in an embodiment of this application; Figure 5 This is a flowchart illustrating another assisted driving method based on road environment information provided in this application embodiment; Figure 6 This is a schematic diagram of the structure of an assisted driving system based on road environment information provided in an embodiment of this application; Figure 7This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of this application clearer, specific embodiments of this application will be described in further detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely for explaining this application and not for limiting it. It should also be noted that, for ease of description, only the parts relevant to this application are shown in the drawings, not all of them. Before discussing exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe operations (or steps) as sequential processes, many of these operations can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but may also have additional steps not included in the drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0024] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0025] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0026] The following description, in conjunction with the accompanying drawings, details the assisted driving method, system, device, and medium based on road environment information provided in this application through specific embodiments and application scenarios.

[0027] First, this application applies to dynamic assisted driving scenarios for autonomous and semi-autonomous vehicles in multiple driving scenarios, especially in driving scenarios with complex weather, large fluctuations in traffic flow, and varied road conditions. Based on the above application scenarios, it can be understood that the implementing entity of this application can be the vehicle's central processing unit.

[0028] Figure 1 This is a flowchart illustrating an assisted driving method based on road environment information provided in an embodiment of this application. Figure 1 As shown, the specific steps include the following: S101, acquire road surface environment information; wherein, the road surface environment information includes target object identification information, road surface condition information and road condition information, and the road surface condition information includes road surface friction coefficient and road surface humidity.

[0029] Among them, road surface environment information can be a set of data that can comprehensively reflect the characteristics of the roads and environment around the vehicle, and can include target object identification information, road surface condition information, and road condition information.

[0030] The target object identification information can be obtained by identifying, locating, and analyzing the motion state of various static and dynamic objects within the vehicle's driving path. The target objects can be various objects that affect vehicle driving safety, such as pedestrians, vehicles, and lane markings.

[0031] In one embodiment, the method for obtaining target identification information can be as follows: acquiring radar data through a radar sensor, acquiring image data through a high-definition camera, performing temporal and spatial alignment on the radar data and image data, and then performing multimodal fusion on the aligned data to obtain target identification information. The radar sensor can simultaneously include at least two of millimeter-wave radar sensors, lidar sensors, and ultrasonic radar sensors. The radar data acquired from each radar sensor is used to complement each other to obtain the final radar data. The method for multimodal fusion of the aligned data can be as follows: inputting the aligned data into a pre-trained multimodal fusion target tracking and detection model to obtain target identification information output by the target tracking and detection model.

[0032] The road surface condition information can be a set of parameters reflecting the physical characteristics of the road surface on which vehicles travel, including the road surface friction coefficient and road surface moisture content. The road surface friction coefficient is a quantitative parameter characterizing the road surface's frictional capacity, with a value ranging from 0 to 1 (a higher value indicates stronger frictional capacity); road surface moisture content is a quantitative indicator of the road surface's water content.

[0033] In one embodiment, road surface condition information can be acquired using a MEMS (Micro-Electro-Mechanical Systems) road surface condition sensor. The MEMS road surface condition sensor is a miniaturized, high-precision sensor based on micro-nano manufacturing technology, and its core function is to detect the physical state of the road surface in real time.

[0034] Among them, road condition information can be a set of information reflecting the traffic operation characteristics of the current road, which may include traffic flow or congestion index, etc.

[0035] In one embodiment, road status information can be obtained by using specialized sensors installed at intersections or by extracting it directly from network information.

[0036] S102, acquire vehicle usage time information, and determine the road condition level based on the road environment information, the vehicle usage time information, and the pre-trained road condition assessment model.

[0037] Among them, the vehicle usage time information can be the cumulative driving time from the first start of the vehicle to the current moment.

[0038] In one embodiment, vehicle usage time information can be obtained by analyzing the recorded information from the vehicle's onboard clock module and driving status recording module.

[0039] Among them, the road condition level can be a graded indicator based on the risk level of road surface environmental information, which is used to quantify the safety level of the current driving scenario. Figure 2 This is a schematic diagram illustrating the interaction between the situation level determination module and the risk probability determination module provided in an embodiment of this application. For example... Figure 2 As shown, road condition levels can include safety level, warning level, and danger level.

[0040] Among them, the road condition assessment model can be a multi-dimensional fusion assessment model based on deep learning.

[0041] In one embodiment, the road condition assessment model takes road surface environment information and vehicle usage time information as inputs and road condition level as output. It extracts road surface environment features through a convolutional neural network, analyzes time series features by combining a long short-term memory network, outputs the probability distribution of road condition level through a fully connected layer, and finally selects the road condition level with the highest probability for output.

[0042] S103, obtain historical risk information, and determine the probability of risk occurrence based on the road condition level and the historical risk information.

[0043] Historical risk information can include data related to risk events that occurred to the vehicle before the current moment. This data can include the type of risk event (such as collision risk, skid risk, rear-end collision risk), the time of occurrence, the road condition level at the time, vehicle status information, and the severity of the risk event (minor, moderate, severe).

[0044] In one embodiment, historical risk information can be obtained by reading risk event data recorded in real time during driving by the vehicle's dashcam or autonomous driving domain controller.

[0045] The probability of risk occurrence can be a quantitative value of the likelihood of a risk event occurring within a preset time period (e.g., 3-5 seconds) under the current driving scenario, with a value range of 0-100%.

[0046] In one embodiment, determining the probability of risk occurrence based on road condition level and historical risk information can be achieved by matching the road condition level with the road condition levels in the historical risk information, and then weighting the probability of risk occurrence by combining the severity of each successfully matched road condition level. For example, if the current road condition level is dangerous, and 10 risk events occurred under the dangerous level in the historical risk information (5 severe, 3 moderate, and 2 minor), the severity of severe, moderate, and minor events are assigned weights of 1.5, 1.0, and 0.5, respectively. The total number of risk events after weighting (11.5) is calculated, and then the total number of risk events (11.5) is divided by the maximum weighted value under this level (1.5 x 10 = 15) to obtain the probability of risk occurrence (77%).

[0047] Optionally, the historical risk information includes historical road risk information and historical vehicle risk information; Accordingly, determining the probability of risk occurrence based on the road condition level and the historical risk information includes: The probability of the first risk occurring is determined based on the road condition level and the historical road risk information. Obtain vehicle status information, and determine the probability of the second risk occurring based on the vehicle status information and the historical vehicle risk information; The frequency of historical vehicle risk events is calculated based on the historical vehicle risk information, and the risk probability weight is determined based on the frequency of historical vehicle risk events. The probability of occurrence of the first risk and the probability of occurrence of the second risk are weighted and summed based on the risk probability weights to obtain the probability of occurrence of the risk.

[0048] Historical road risk information can be data related to risk events that occurred on the current road and similar road sections before the current moment, including the time of occurrence of the risk event, the road condition level at that time, road surface environment information, and degree of danger. These risk events are unrelated to specific vehicles and reflect the inherent risk characteristics of the road itself. Historical vehicle risk information can be data related to risk events that occurred to the current vehicle before the current moment, including vehicle status information at the time of the risk event, the road condition level and severity at that time, reflecting the individual risk characteristics of the vehicle in different scenarios.

[0049] Among them, the probability of the first risk can be a quantitative value of the likelihood of a risk event occurring within a preset time in the current driving scenario when only considering road-level risk factors. The value ranges from 0 to 100%, representing the objective risk brought by the external road environment.

[0050] In one embodiment, the probability of the first risk occurring can be determined based on the road condition level and historical road risk information by filtering historical risk events that are consistent with the current road condition level, and then weighting the probability of the first risk occurring by combining the degree of danger corresponding to these historical risk events.

[0051] Among them, vehicle status information can be a set of parameters reflecting the current driving status of the vehicle and the working status of the hardware equipment, which may include vehicle speed, acceleration, and steering angle.

[0052] In one embodiment, vehicle status information can be obtained in real time through onboard sensors.

[0053] Among them, the probability of the second risk can be a quantitative value of the likelihood of a risk event occurring within a preset time in the current driving scenario, considering only the risk factors of the vehicle's own state. The value ranges from 0 to 100%, representing the subjective risk brought about by the vehicle's own state.

[0054] In one embodiment, the probability of the second risk occurring can be determined based on vehicle status information and historical vehicle risk information by filtering historical risk events that are consistent with the current vehicle status information from historical road risk information, and then weighting the probability of the second risk occurring by combining the degree of danger corresponding to these historical risk events.

[0055] Among them, the frequency of historical vehicle risk situations can be the density of risk events occurring during the vehicle's historical driving process, that is, the number of risk events occurring per unit driving time.

[0056] In one embodiment, the method for calculating the frequency of historical vehicle risk events based on historical vehicle risk information can be to extract the total number of all risk events in the historical vehicle risk information and divide the total number by the vehicle usage duration information to obtain the frequency of historical vehicle risk events.

[0057] Among them, the risk probability weight can be a coefficient used to balance the influence of the probability of occurrence of the first risk and the probability of occurrence of the second risk in the final result, including the first risk probability weight and the second risk probability weight.

[0058] In one embodiment, the method of determining the risk probability weight based on the frequency of historical vehicle risk events can be achieved by using a preset mapping database to determine the risk probability weight corresponding to the current frequency of historical vehicle risk events. For example, if the frequency of historical vehicle risk events is less than 0.1 times / hour, the risk probability weights are 0.7 and 0.3, respectively; if the frequency of historical vehicle risk events is between 0.1 and 0.3 times / hour, the risk probability weights are 0.5 and 0.5, respectively; and if the frequency of historical vehicle risk events is greater than 0.3 times / hour, the risk probability weights are 0.3 and 0.7, respectively.

[0059] In one embodiment, the probability of occurrence of a risk can be obtained by weighted summation of the probability of occurrence of the first risk and the probability of occurrence of the second risk based on the risk probability weight. This can be achieved by multiplying the probability of occurrence of the first risk by the first risk probability weight to obtain the first sub-risk probability, multiplying the probability of occurrence of the second risk by the second risk probability weight to obtain the second sub-risk probability, and summing the first sub-risk probability and the second sub-risk probability to obtain the probability of occurrence of the risk.

[0060] The advantage of this scheme is that it fully considers the objective risks of the road environment, accurately considers the subjective risks of the vehicle itself, and dynamically adjusts the weights by using the historical vehicle risk frequency, so that the risk assessment results are more in line with the individual characteristics of the vehicle.

[0061] like Figure 2 As shown, after the situation level determination module determines the road situation level (one of safety level, warning level, and danger level), it interacts and collaborates with the risk probability determination module. The risk probability determination module combines the road situation level transmitted by the situation level determination module with its own historical risk information to calculate and output the probability of risk occurrence (value range 0-100%).

[0062] S104, acquire vehicle status information, and determine a target assisted driving strategy based on the target object identification information, the road surface status information, the road situation level, the risk occurrence probability, and the vehicle status information.

[0063] Among these, the assisted driving strategy can be a vehicle control scheme formulated for different driving scenarios to ensure vehicle driving safety. Correspondingly, the target assisted driving strategy is the vehicle control scheme formulated for the current driving scenario to ensure vehicle driving safety.

[0064] In one embodiment, the method of determining the target assisted driving strategy based on target object identification information, road surface condition information, road situation level, risk occurrence probability, and vehicle status information can be achieved by constructing an assisted driving strategy decision tree with road situation level as the root node, risk occurrence probability as the first-level branch, target object type as the second-level branch, and road surface friction coefficient as the third-level branch. Based on the vehicle status information, the decision tree is traversed to initially screen candidate assisted driving strategies. Fuzzy logic reasoning is introduced (using parameters such as risk occurrence probability, road surface friction coefficient, and vehicle speed as fuzzy inputs, and defining safety priority and control strength as fuzzy outputs). The candidate assisted driving strategies are optimized and adjusted through a fuzzy rule base to finally determine the target assisted driving strategy.

[0065] S105, Perform vehicle assisted driving control based on the target assisted driving strategy.

[0066] In one embodiment, the method of vehicle assisted driving control based on the target assisted driving strategy can be achieved by a central processing unit parsing the target assisted driving strategy into specific control commands (such as speed control commands, steering control commands, gear shift control commands, and warning control commands), and then sending the control commands to the corresponding execution units for execution via a data transmission bus.

[0067] Figure 3 This is an example diagram of a system architecture for vehicle assisted driving control based on the target assisted driving strategy provided in this application embodiment. For example... Figure 3 As shown, the control commands obtained after parsing the target assisted driving strategy are distributed to the speed control system, steering control system, shift control system, and user and feedback system via a data transmission bus. Within the speed control system, the throttle system is responsible for adjusting the throttle mechanism to control the engine power output, and the braking system is responsible for operating the braking mechanism to achieve vehicle deceleration or braking. The steering control system is responsible for driving the steering mechanism to adjust the vehicle's driving direction. The shift control system is responsible for operating the shift mechanism to change the vehicle's gear. The central control display screen in the user interaction and feedback system will display assisted driving related information in real time, and in special circumstances, the driver can take over control of the vehicle and intervene in or take over the assisted driving process.

[0068] In this embodiment, road environment information is acquired, including target object identification information, road surface condition information, and road condition information, wherein the road surface condition information includes the road surface friction coefficient and road surface humidity; vehicle usage time information is acquired, and a road condition level is determined based on the road environment information, the vehicle usage time information, and a pre-trained road condition assessment model; historical risk information is acquired, and the probability of risk occurrence is determined based on the road condition level and the historical risk information; vehicle condition information is acquired, and a target assisted driving strategy is determined based on the target object identification information, the road surface condition information, the road condition level, the probability of risk occurrence, and the vehicle condition information; and assisted driving control of the vehicle is performed based on the target assisted driving strategy. The above-described assisted driving method based on road environment information, by deeply integrating environmental information, road surface condition information, and road condition information, outputs assisted driving strategies adapted to different road surface characteristics, improving the safety, stability, and adaptability of assisted driving control in complex road surface scenarios.

[0069] Figure 4 This is a flowchart illustrating another assisted driving method based on road environment information provided in an embodiment of this application. Figure 4 As shown, the specific steps include the following: S401, acquire road surface environment information; wherein, the road surface environment information includes target object identification information, road surface condition information and road condition information, and the road surface condition information includes road surface friction coefficient and road surface humidity.

[0070] S402, acquire vehicle usage time information, and determine the road condition level based on the road environment information, the vehicle usage time information, and the pre-trained road condition assessment model.

[0071] S403, obtain historical risk information, and determine the probability of risk occurrence based on the road condition level and the historical risk information.

[0072] S404, obtain vehicle status information.

[0073] S405, the target object identification information, the road surface condition information, the road situation level, the risk occurrence probability, and the vehicle status information are matched with a preset assisted driving rule base to obtain an initial assisted driving strategy.

[0074] The preset assisted driving rule base can be a structured set of rules built on historical risk information, various road environment information, traffic accident cases and driving safety regulations. It includes the mapping relationship between multi-dimensional input parameters (object recognition information, road condition information, road situation level, risk occurrence probability) and assisted driving strategies.

[0075] The initial assisted driving strategy can be a assisted driving strategy that fits the current driving scenario by matching the current multi-dimensional input information with each rule entry in the preset assisted driving rule library.

[0076] In one embodiment, the initial assisted driving strategy is obtained by matching target identification information, road surface condition information, road situation level, risk occurrence probability, and vehicle status information with a preset assisted driving rule base. This can be achieved by first using the road situation level as the primary matching condition to filter out the candidate assisted driving strategy set corresponding to the level in the rule base; then using the risk occurrence probability range and the road surface friction coefficient range as secondary matching conditions to further narrow down the candidate assisted driving strategy set; next, using the target type in the target identification information and its distance from the vehicle, as well as the current vehicle speed in the vehicle status information, as tertiary matching conditions to traverse the candidate assisted driving strategy set for further filtering; and finally, each assisted driving strategy in the selected candidate assisted driving strategy set is the initial assisted driving strategy.

[0077] S406, predict future vehicle state information based on the initial assisted driving strategy.

[0078] Among them, future vehicle status information can refer to the vehicle's driving status information within a preset time period in the future, under the premise of executing the initial assisted driving strategy. This includes predicted vehicle speed, predicted acceleration, predicted steering angle, predicted distance to target objects, etc., which are used to assess the vehicle's safety status and its impact on the surrounding environment after the initial strategy is executed.

[0079] In one embodiment, the method of predicting future vehicle state information based on an initial assisted driving strategy can be achieved by using the control commands converted from the initial assisted driving strategy, the current vehicle state information, and the road surface state information as inputs to a vehicle dynamics model to obtain basic information about the future vehicle state. Then, the control commands converted from the initial assisted driving strategy, historical risk information, and the current vehicle state information are used as inputs to a temporal prediction model of a long short-term memory network to obtain temporal prediction information about the vehicle state. Finally, the basic information about the future vehicle state and the temporal prediction information about the vehicle state are weighted and fused to obtain the future vehicle state information corresponding to the initial assisted driving strategy.

[0080] S407, Based on the initial driver assistance strategy and the future vehicle state information, determine the target driver assistance strategy.

[0081] In one embodiment, the method for determining the target assisted driving strategy based on the initial assisted driving strategy and future vehicle state information can be as follows: Set safety assessment indicators (including whether the predicted vehicle speed is within the current road safety speed range, whether the predicted distance to the target object is greater than a safe distance threshold, and whether the predicted steering angle will cause the vehicle to deviate from its lane, etc.), substitute the future vehicle state information into the safety assessment indicators for verification, and if all safety assessment indicators meet the safety requirements, then the initial assisted driving strategy is directly determined as the target assisted driving strategy; if any safety assessment indicator does not meet the safety requirements, then based on the deviation between the future vehicle state information and the safety requirements, the control parameters of the initial assisted driving strategy are optimized and adjusted until the safety requirements are met, ultimately obtaining the target assisted driving strategy.

[0082] Optionally, the number of initial driver assistance strategies is at least two; Accordingly, determining the target assisted driving strategy based on the initial assisted driving strategy and the future vehicle state information includes: Based on each of the initial driver assistance strategies, the future vehicle state information corresponding to each of the initial driver assistance strategies, and the pre-constructed comprehensive cost function, the comprehensive cost score of each of the initial driver assistance strategies is determined; wherein, the dynamic adjustment weights in the comprehensive cost function include safety cost weights, comfort cost weights, and traffic efficiency cost weights. The initial driver assistance strategy with the lowest overall cost score is determined as the target driver assistance strategy.

[0083] The comprehensive cost function can be a quantitative evaluation function that integrates the costs of safety, comfort, and traffic efficiency. It is used to evaluate the multi-objective trade-offs of different initial assisted driving strategies, and its formula is as follows:

[0084] .

[0085] The dynamic adjustment weights in the comprehensive cost function can be coefficients dynamically allocated based on the priority requirements of the current driving scenario. These can include safety cost weights, comfort cost weights, and traffic efficiency cost weights. Specifically, the safety cost weight can be a coefficient reflecting the importance of safety in the current driving scenario; the comfort cost weight can be a coefficient reflecting the importance of ride comfort; and the traffic efficiency cost weight can be a coefficient reflecting the importance of traffic efficiency.

[0086] Among them, the comprehensive cost score can be used to quantify the overall performance of the initial assisted driving strategy in the current driving scenario. The lower the value, the better the initial assisted driving strategy.

[0087] In one embodiment, the comprehensive cost score of an initial assisted driving strategy is determined based on an initial assisted driving strategy, the future vehicle state information corresponding to the initial assisted driving strategy, and a pre-constructed comprehensive cost function. This can be achieved by comparing the future vehicle state information with a safety threshold to obtain a safety cost, determining a comfort cost based on parameters such as the rate of change of acceleration and the rate of change of steering angle in the future vehicle state information, comparing the average vehicle speed in the future vehicle state information with the current free-flow speed (ideal speed when there is no congestion) to calculate the speed loss ratio as a traffic efficiency cost, and finally multiplying the safety cost, comfort cost, and traffic efficiency cost by their respective dynamic adjustment weights and summing them to obtain the comprehensive cost score of the initial assisted driving strategy.

[0088] The initial driver assistance strategy with the lowest overall cost score indicates that it achieves the optimal balance between safety, comfort, and traffic efficiency in the current driving scenario. It is a driver assistance strategy that better meets actual driving needs and can therefore be identified as the target driver assistance strategy.

[0089] Optionally, before determining the comprehensive cost score of each initial driver assistance strategy based on each initial driver assistance strategy, the future vehicle state information corresponding to each initial driver assistance strategy, and a pre-constructed comprehensive cost function, the method further includes: The safety cost weight is determined based on the road condition level and the probability of risk occurrence. Acquire historical user operation data and determine the comfort cost weight based on the historical user operation data; The traffic efficiency cost weight is determined based on the road condition information.

[0090] In one embodiment, the method of determining the safety cost weight based on the road condition level and the probability of risk occurrence can be achieved by pre-setting the correspondence between the road condition level and the basic safety weight (for example, the basic safety weight corresponding to the safe level is 0.3, the basic safety weight corresponding to the warning level is 0.5, and the basic safety weight corresponding to the danger level is 0.7), and simultaneously pre-setting the correspondence between the probability of risk occurrence range and the weight adjustment coefficient (for example, the weight adjustment coefficient corresponding to 0-30% is 0.8, the weight adjustment coefficient corresponding to 30-70% is 1.0, and the weight adjustment coefficient corresponding to 70-100% is 1.2). The safety cost weight is obtained by multiplying the basic safety weight corresponding to the current road condition level with the weight adjustment coefficient corresponding to the probability of risk occurrence.

[0091] Historical user operation data can be a record of the driving operation behavior of the user of this vehicle up to the current moment, which is used to reflect the user's preference characteristics for driving operation.

[0092] In one embodiment, historical user operation data can be obtained by using a vehicle driving behavior acquisition module (which integrates an accelerator pedal sensor, a brake pedal sensor, and a steering angle sensor, etc.) to record user operation data in real time as historical user operation data.

[0093] In one embodiment, the method of determining the comfort cost weight based on historical user operation data can be achieved by extracting features from historical user operation data, calculating the average rate of change of accelerator pedal amplitude as acceleration operation smoothness, calculating the average rate of change of brake pedal force as braking operation smoothness, calculating the average rate of change of steering angle as steering operation smoothness, weighting and summing the acceleration operation smoothness, braking operation smoothness, and steering operation smoothness, and determining the comfort cost weight corresponding to the current weighted summation result based on a preset mapping relationship between the weighted summation result and the comfort cost weight (for example, a comfort cost weight of 0.15 corresponds to a weighted summation result less than 0.6, a comfort cost weight of 0.35 corresponds to a weighted summation result between 0.6 and 0.8, and a comfort cost weight of 0.55 corresponds to a weighted summation result greater than 0.8).

[0094] In one embodiment, the method for determining the traffic efficiency cost weight based on road condition information can be as follows: calculate the road condition assessment level (which may include smooth traffic, slow traffic, and congestion levels) corresponding to the road condition information according to preset rules, and determine the traffic efficiency cost weight corresponding to the current road condition assessment level based on the preset correspondence between the road condition assessment level and the traffic efficiency cost weight (for example, the traffic efficiency cost weight corresponding to the smooth traffic level is 0.15, the traffic efficiency cost weight corresponding to the slow traffic level is 0.35, and the traffic efficiency cost weight corresponding to the congestion level is 0.55).

[0095] The advantages of this scheme are as follows: By dynamically adjusting the safety cost weights based on road condition levels and the probability of risk occurrence, the weights can accurately match the safety risk level of the current scenario, ensuring that safety is prioritized in high-risk scenarios; determining the comfort cost weights based on historical user operation data achieves personalized adaptation between the weights and user driving preferences, improving user acceptance of the assisted driving system; and determining the traffic efficiency cost weights based on road condition information ensures that the weights are aligned with actual road conditions, avoiding excessive pursuit of comfort at the expense of traffic efficiency in congested scenarios.

[0096] The advantage of this scheme is that when multiple initial assisted driving strategies exist, a comprehensive cost function can be used to quantitatively evaluate and select strategies from multiple dimensions such as safety, comfort, and traffic efficiency, thus avoiding the limitations of single-dimensional decision-making.

[0097] S408, Perform vehicle assisted driving control based on the target assisted driving strategy.

[0098] The advantage of this solution is that the pre-set assisted driving rule base ensures rapid matching and basic safety of the initial assisted driving strategy, and the future vehicle state prediction and strategy optimization stages can avoid potential risks that the initial assisted driving strategy may cause in advance, making the target assisted driving strategy more in line with the vehicle's dynamic driving scenario, especially suitable for complex and ever-changing urban roads and severe weather scenarios.

[0099] Figure 5 This is a flowchart illustrating another assisted driving method based on road environment information provided in an embodiment of this application. Figure 5 As shown, the specific steps include the following: S501, acquire road surface environment information; wherein, the road surface environment information includes target object identification information, road surface condition information and road condition information, and the road surface condition information includes road surface friction coefficient and road surface humidity.

[0100] S502, obtain vehicle usage time information.

[0101] S503, input the road surface environment information into the pre-trained road condition assessment model to obtain the basic road condition level output by the road condition assessment model.

[0102] Among them, the road situation assessment model can be a multi-feature fusion classification model based on deep learning. It extracts spatial features such as target density, friction coefficient, and traffic flow from road surface environment information through convolutional neural networks, and uses attention mechanism to strengthen the weight of high-risk features (such as close pedestrians and low friction coefficient road surfaces). The output layer uses the softmax function to achieve multi-level classification. The training data covers massive road scene data with different weather, traffic flow, and road surface conditions.

[0103] Among them, the basic road condition level can be a road condition level obtained solely based on road surface environmental information assessment, without considering the impact of vehicle characteristics on driving safety.

[0104] In one embodiment, the method of inputting road surface environment information into a pre-trained road condition assessment model to obtain the basic road condition level output by the road condition assessment model can be achieved by calling the road condition assessment model function with the road surface environment information as the input parameter and receiving the return data of the road condition assessment model function, i.e., the basic road condition level.

[0105] S504, obtain vehicle tire material information, and determine the vehicle stability coefficient based on the vehicle tire material information and the vehicle usage time information.

[0106] Among them, the vehicle tire material information can be the type of rubber material used in the vehicle tires.

[0107] In one embodiment, the method for obtaining vehicle tire material information can be by reading the tire manufacturing information (including vehicle tire material information) pre-stored in the vehicle database.

[0108] Among them, the vehicle stability coefficient can be a parameter that quantifies the contribution of vehicle tires to driving stability under current usage conditions.

[0109] In one embodiment, the method for determining the vehicle stability coefficient based on vehicle tire material information and vehicle usage time information can be as follows: a base stability coefficient is determined based on the vehicle tire material information (for example, the base stability coefficient for natural rubber is 0.9, the base stability coefficient for synthetic rubber is 0.8, and the base stability coefficient for mixed rubber is 0.85). Then, the tire aging degradation coefficient is calculated based on the vehicle usage time information and the preset aging degradation rate of different vehicle tire materials. Finally, the base stability coefficient and the tire aging degradation coefficient are multiplied together to obtain the vehicle stability coefficient.

[0110] S505, obtain vehicle braking type information, and determine the vehicle braking attenuation coefficient based on the vehicle braking type information and the vehicle usage time information.

[0111] Among them, vehicle braking type information can be the type of vehicle braking system, which may include disc brakes, drum brakes, electronic parking brakes, etc.

[0112] In one embodiment, the vehicle braking type information can be obtained by reading the factory configuration information (including vehicle braking type information) pre-stored in the vehicle database.

[0113] Among them, the vehicle brake attenuation coefficient can be a parameter that quantifies the degree of brake performance degradation of the vehicle braking system under current use conditions.

[0114] In one embodiment, the method for determining the vehicle brake attenuation coefficient based on vehicle brake type information and vehicle usage time information can be as follows: determine the base attenuation rate based on the vehicle brake type information (the monthly attenuation rate is 0.5% for disc brakes, 1% for drum brakes, and 0.3% for electronic parking brakes), and then multiply the vehicle usage time information by the base attenuation rate to obtain the vehicle brake attenuation coefficient.

[0115] S506, Based on the vehicle stability coefficient, the vehicle braking attenuation coefficient, and the road surface condition information, the basic road condition level is corrected to obtain the road condition level.

[0116] In one embodiment, the road condition level is obtained by correcting the basic road condition level based on the vehicle stability coefficient, the vehicle braking attenuation coefficient, and the road surface condition information. This can be achieved by weighting and summing the vehicle stability coefficient, the vehicle braking attenuation coefficient, and the road surface friction coefficient and road surface humidity from the road surface condition information to obtain a correction coefficient. Based on the mapping relationship between the preset correction coefficient and the correction strategy, the target correction strategy corresponding to the current correction coefficient is determined. The target correction strategy is then applied to the basic road condition level to obtain the road condition level.

[0117] Optionally, the road surface condition information may also include road surface slope information; Accordingly, the step of correcting the basic road condition level based on the vehicle stability coefficient, the vehicle brake fade coefficient, and the road surface condition information to obtain the road condition level includes: The vehicle grip risk coefficient is determined based on the vehicle stability coefficient and the road surface condition information. The comprehensive performance risk coefficient is determined based on the vehicle grip risk coefficient and the vehicle brake fade coefficient. The target level correction strategy is determined based on the comprehensive performance risk coefficient and the pre-constructed mapping relationship between the comprehensive performance risk coefficient and the level correction strategy. The target level correction strategy is applied to the basic road condition level to obtain the road condition level.

[0118] Among them, road slope information can be a quantitative parameter that represents the degree of inclination of the road surface under current driving conditions, including slope value and slope direction.

[0119] Among them, the vehicle grip risk coefficient can be a parameter that quantifies the risk of skidding, rolling away, etc. due to insufficient tire grip under the current road conditions and its own stability characteristics.

[0120] In one embodiment, the method for determining the vehicle grip risk coefficient based on the vehicle stability coefficient and road condition information can be achieved by normalizing and weighting the parameters in the vehicle stability coefficient and road condition information to obtain the vehicle grip risk coefficient.

[0121] Among them, the comprehensive performance risk coefficient can be a comprehensive quantitative indicator that integrates vehicle grip risk and braking fade risk.

[0122] In one embodiment, the method for determining the comprehensive performance risk coefficient based on the vehicle grip risk coefficient and the vehicle brake attenuation coefficient can be to use the arithmetic mean of the vehicle grip risk coefficient and the vehicle brake attenuation coefficient as the base value. If the slope direction in the road slope information is downhill, the base value is increased by 10%; if the slope direction in the road slope information is uphill, the base value is increased by 5%; if it is a flat road, the base value remains unchanged, and the comprehensive performance risk coefficient is finally obtained.

[0123] The grade correction strategy can be a set of specific rules formulated based on the comprehensive performance risk coefficient to adjust the basic road situation grade, including grade maintenance, grade increase by 1 level, and grade increase by 2 levels. The target grade correction strategy is the grade correction strategy that is matched from the grade correction strategy set based on the currently calculated comprehensive performance risk coefficient and is applicable to the current scenario.

[0124] The mapping relationship between the comprehensive performance risk coefficient and the level adjustment strategy can be a one-to-one correspondence rule established based on the comprehensive performance risk coefficient and the road condition level adjustment requirements. For example, when the comprehensive performance risk coefficient is less than 0.3, the corresponding level remains unchanged; when the comprehensive performance risk coefficient is between 0.3 and 0.6, the corresponding level is increased by 1 level; and when the comprehensive performance risk coefficient is greater than 0.6, the corresponding level is increased by 2 levels.

[0125] In one embodiment, the method of determining the target level correction strategy based on the comprehensive performance risk coefficient and the pre-built mapping relationship between the comprehensive performance risk coefficient and the level correction strategy can be to determine the comprehensive performance risk coefficient range in which the current comprehensive performance risk coefficient is located, and then determine the level correction strategy corresponding to the comprehensive performance risk coefficient range as the target level correction strategy.

[0126] In one embodiment, the method for obtaining the road situation level by applying a target level correction strategy to the basic road situation level can be as follows: if the target correction strategy is to maintain the level, then the basic level is directly used as the road situation level; if the target correction strategy is to increase the level by 1 level, then the adjustment is made according to the rule of "safe level → warning level, warning level → danger level, danger level → danger level (remains unchanged)"; if the target correction strategy is to increase the level by 2 levels, then the adjustment is made according to the rule of "safe level → danger level, warning level → danger level, danger level → danger level (remains unchanged)".

[0127] The advantage of this scheme is that road surface gradient (especially uphill and downhill) directly changes the vehicle's grip requirements and braking load. Through hierarchical reasoning logic based on grip risk coefficient, comprehensive performance risk coefficient, and grade correction strategy, a deep coupling assessment of the vehicle's own performance and the road environment (including gradient) is achieved.

[0128] S507, Obtain historical risk information, and determine the probability of risk occurrence based on the road condition level and the historical risk information.

[0129] S508, acquire vehicle status information, and determine a target assisted driving strategy based on the target object identification information, the road surface status information, the road situation level, the risk occurrence probability, and the vehicle status information.

[0130] S509, Perform vehicle assisted driving control based on the target assisted driving strategy.

[0131] The advantage of this approach is that it breaks through the limitations of traditional road condition assessment based solely on road surface conditions, and innovatively incorporates the vehicle's core characteristics (tire stability, brake fade status), achieving a two-dimensional condition assessment of both the external environment and the internal vehicle condition.

[0132] Figure 6 This is a schematic diagram of the structure of an assisted driving system based on road environment information provided in an embodiment of this application. Figure 6 As shown, the system includes: The road surface environment acquisition module 610 is used to acquire road surface environment information; wherein, the road surface environment information includes target object identification information, road surface condition information and road condition information, and the road surface condition information includes road surface friction coefficient and road surface humidity; The situation level determination module 620 is used to acquire vehicle usage time information and determine the road situation level based on the road environment information, the vehicle usage time information and the pre-trained road situation assessment model. The risk probability determination module 630 is used to acquire historical risk information and determine the probability of risk occurrence based on the road condition level and the historical risk information. The auxiliary strategy determination module 640 is used to acquire vehicle status information and determine a target assisted driving strategy based on the target object identification information, the road surface status information, the road situation level, the risk occurrence probability, and the vehicle status information. The assisted driving control module 650 is used to perform assisted driving control of the vehicle based on the target assisted driving strategy.

[0133] Optionally, the auxiliary strategy determination module 640 is specifically used for: The target object identification information, the road surface condition information, the road situation level, the risk occurrence probability, and the vehicle status information are matched with a preset assisted driving rule base to obtain an initial assisted driving strategy. Predict future vehicle status information based on the initial assisted driving strategy; Based on the initial driver assistance strategy and the future vehicle state information, a target driver assistance strategy is determined.

[0134] Optionally, the number of initial driver assistance strategies is at least two; Accordingly, the auxiliary strategy determination module 640 is further configured to: Based on each of the initial driver assistance strategies, the future vehicle state information corresponding to each of the initial driver assistance strategies, and the pre-constructed comprehensive cost function, the comprehensive cost score of each of the initial driver assistance strategies is determined; wherein, the dynamic adjustment weights in the comprehensive cost function include safety cost weights, comfort cost weights, and traffic efficiency cost weights. The initial driver assistance strategy with the lowest overall cost score is determined as the target driver assistance strategy.

[0135] Optionally, the auxiliary strategy determination module 640 is further configured to: The safety cost weight is determined based on the road condition level and the probability of risk occurrence. Acquire historical user operation data and determine the comfort cost weight based on the historical user operation data; The traffic efficiency cost weight is determined based on the road condition information.

[0136] Optionally, the historical risk information includes historical road risk information and historical vehicle risk information; Accordingly, the risk probability determination module 630 is specifically used for: The probability of the first risk occurring is determined based on the road condition level and the historical road risk information. Obtain vehicle status information, and determine the probability of the second risk occurring based on the vehicle status information and the historical vehicle risk information; The frequency of historical vehicle risk events is calculated based on the historical vehicle risk information, and the risk probability weight is determined based on the frequency of historical vehicle risk events. The probability of occurrence of the first risk and the probability of occurrence of the second risk are weighted and summed based on the risk probability weights to obtain the probability of occurrence of the risk.

[0137] Optionally, the situation level determination module 620 is specifically used for: The road surface environment information is input into a pre-trained road condition assessment model to obtain the basic road condition level output by the road condition assessment model. Obtain vehicle tire material information, and determine the vehicle stability coefficient based on the vehicle tire material information and the vehicle usage time information; Obtain vehicle braking type information, and determine the vehicle braking attenuation coefficient based on the vehicle braking type information and the vehicle usage time information; The basic road condition level is corrected based on the vehicle stability coefficient, the vehicle brake fade coefficient, and the road surface condition information to obtain the road condition level.

[0138] Optionally, the road surface condition information may also include road surface slope information; Accordingly, the situation level determination module 620 is also used for: The vehicle grip risk coefficient is determined based on the vehicle stability coefficient and the road surface condition information. The comprehensive performance risk coefficient is determined based on the vehicle grip risk coefficient and the vehicle brake fade coefficient. The target level correction strategy is determined based on the comprehensive performance risk coefficient and the pre-constructed mapping relationship between the comprehensive performance risk coefficient and the level correction strategy. The target level correction strategy is applied to the basic road condition level to obtain the road condition level.

[0139] In this embodiment, a road environment acquisition module is used to acquire road environment information, including target object identification information, road surface state information, and road state information, wherein the road surface state information includes the road surface friction coefficient and road surface humidity; a situation level determination module is used to acquire vehicle usage time information and determine the road situation level based on the road environment information, the vehicle usage time information, and a pre-trained road situation assessment model; a risk probability determination module is used to acquire historical risk information and determine the probability of risk occurrence based on the road situation level and the historical risk information; an assistance strategy determination module is used to acquire vehicle state information and determine a target assisted driving strategy based on the target object identification information, the road surface state information, the road situation level, the probability of risk occurrence, and the vehicle state information; and an assisted driving control module is used to perform assisted driving control of the vehicle based on the target assisted driving strategy. The above-mentioned assisted driving system based on road environment information, by deeply integrating environmental information, road surface state information, and road state information, outputs assisted driving strategies adapted to different road surface characteristics, improving the safety, stability, and adaptability of assisted driving control in complex road surface scenarios.

[0140] The assisted driving system based on road environment information in this application embodiment can be a system with an operating system. This operating system can be Android, iOS, or other possible operating systems; this application embodiment does not specifically limit it.

[0141] The assisted driving system based on road environment information provided in this application can realize the various processes implemented in the above embodiments. To avoid repetition, it will not be described again here.

[0142] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. For example... Figure 7 As shown, this application embodiment also provides an electronic device 700, including a processor 701, a memory 702, and a program or instructions stored in the memory 702 and executable on the processor 701. When the program or instructions are executed by the processor 701, they implement the various processes of the above-described assisted driving method embodiment based on road environment information and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0143] It should be noted that the electronic devices in the embodiments of this application include the mobile electronic devices and non-mobile electronic devices described above.

[0144] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described assisted driving method embodiments based on road environment information and achieve the same technical effects. To avoid repetition, they will not be described again here.

[0145] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0146] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element. Furthermore, it should be noted that the scope of the methods and systems in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0147] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0148] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

[0149] The above description is merely a preferred embodiment and the technical principles employed in this application. This application is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions that can be made by those skilled in the art will not depart from the scope of protection of this application. Therefore, although this application has been described in detail through the above embodiments, this application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of this application, the scope of which is determined by the scope of the claims.

Claims

1. A driving assistance method based on road environment information, characterized in that, The method includes: Acquire road surface environment information; wherein, the road surface environment information includes target object identification information, road surface condition information, and road condition information, and the road surface condition information includes road surface friction coefficient and road surface humidity; The vehicle usage time information is obtained, and the road condition level is determined based on the road environment information, the vehicle usage time information, and the pre-trained road condition assessment model. Obtain historical risk information and determine the probability of risk occurrence based on the road condition level and the historical risk information; Acquire vehicle status information, and determine a target assisted driving strategy based on the target object identification information, the road surface status information, the road situation level, the risk occurrence probability, and the vehicle status information; The vehicle's assisted driving control is performed based on the aforementioned target assisted driving strategy; The step of determining a target assisted driving strategy based on the target object identification information, the road surface condition information, the road situation level, the risk occurrence probability, and the vehicle status information includes: matching the target object identification information, the road surface condition information, the road situation level, the risk occurrence probability, and the vehicle status information with a preset assisted driving rule base to obtain an initial assisted driving strategy; predicting future vehicle status information based on the initial assisted driving strategy; and determining a target assisted driving strategy based on the initial assisted driving strategy and the future vehicle status information. The step of determining the target assisted driving strategy based on the initial assisted driving strategy and the future vehicle state information includes: the number of initial assisted driving strategies is at least two; a comprehensive cost score is determined for each initial assisted driving strategy based on each initial assisted driving strategy, the future vehicle state information corresponding to each initial assisted driving strategy, and a pre-constructed comprehensive cost function; wherein the dynamic adjustment weights in the comprehensive cost function include safety cost weights, comfort cost weights, and traffic efficiency cost weights; and the initial assisted driving strategy with the lowest comprehensive cost score is determined as the target assisted driving strategy. The step of determining the probability of risk occurrence based on the road condition level and the historical risk information includes: the historical risk information including historical road risk information and historical vehicle risk information; determining a first probability of risk occurrence based on the road condition level and the historical road risk information; acquiring vehicle status information, and determining a second probability of risk occurrence based on the vehicle status information and the historical vehicle risk information; calculating the frequency of historical vehicle risk situations based on the historical vehicle risk information, and determining a risk probability weight based on the frequency of historical vehicle risk situations; and performing a weighted summation of the first probability of risk occurrence and the second probability of risk occurrence based on the risk probability weight to obtain the probability of risk occurrence.

2. The assisted driving method based on road environment information according to claim 1, characterized in that, Before determining the comprehensive cost score of each initial driver assistance strategy based on each initial driver assistance strategy, the future vehicle state information corresponding to each initial driver assistance strategy, and a pre-constructed comprehensive cost function, the method further includes: The safety cost weight is determined based on the road condition level and the probability of risk occurrence. Acquire historical user operation data and determine the comfort cost weight based on the historical user operation data; The traffic efficiency cost weight is determined based on the road condition information.

3. The assisted driving method based on road environment information according to any one of claims 1-2, characterized in that, The determination of the road condition level based on the road surface environment information, the vehicle usage time information, and the pre-trained road condition assessment model includes: The road surface environment information is input into a pre-trained road condition assessment model to obtain the basic road condition level output by the road condition assessment model. Obtain vehicle tire material information, and determine the vehicle stability coefficient based on the vehicle tire material information and the vehicle usage time information; Obtain vehicle braking type information, and determine the vehicle braking attenuation coefficient based on the vehicle braking type information and the vehicle usage time information; The basic road condition level is corrected based on the vehicle stability coefficient, the vehicle brake fade coefficient, and the road surface condition information to obtain the road condition level.

4. The assisted driving method based on road environment information according to claim 3, characterized in that, The road surface condition information also includes road surface slope information; Accordingly, the step of correcting the basic road condition level based on the vehicle stability coefficient, the vehicle brake fade coefficient, and the road surface condition information to obtain the road condition level includes: The vehicle grip risk coefficient is determined based on the vehicle stability coefficient and the road surface condition information. The comprehensive performance risk coefficient is determined based on the vehicle grip risk coefficient and the vehicle brake fade coefficient. The target level correction strategy is determined based on the comprehensive performance risk coefficient and the pre-constructed mapping relationship between the comprehensive performance risk coefficient and the level correction strategy. The target level correction strategy is applied to the basic road condition level to obtain the road condition level.

5. A driver assistance system based on road environment information, characterized in that, The system includes: A road surface environment acquisition module is used to acquire road surface environment information; wherein, the road surface environment information includes target object identification information, road surface condition information, and road condition information, and the road surface condition information includes the road surface friction coefficient and road surface humidity; The situation level determination module is used to acquire vehicle usage time information and determine the road situation level based on the road environment information, the vehicle usage time information and the pre-trained road situation assessment model. The risk probability determination module is used to acquire historical risk information and determine the probability of risk occurrence based on the road condition level and the historical risk information. The auxiliary strategy determination module is used to acquire vehicle status information and determine the target assisted driving strategy based on the target object identification information, the road surface status information, the road situation level, the risk occurrence probability, and the vehicle status information. The assisted driving control module is used to perform assisted driving control of the vehicle based on the target assisted driving strategy; The auxiliary strategy determination module is specifically used for: matching the target object identification information, the road surface condition information, the road situation level, the risk occurrence probability, and the vehicle status information with a preset assisted driving rule base to obtain an initial assisted driving strategy; predicting future vehicle status information based on the initial assisted driving strategy; and determining a target assisted driving strategy based on the initial assisted driving strategy and the future vehicle status information. The auxiliary strategy determination module is specifically used for: having at least two initial assisted driving strategies; determining a comprehensive cost score for each initial assisted driving strategy based on each initial assisted driving strategy, the future vehicle state information corresponding to each initial assisted driving strategy, and a pre-constructed comprehensive cost function; wherein the dynamic adjustment weights in the comprehensive cost function include safety cost weights, comfort cost weights, and traffic efficiency cost weights; and determining the initial assisted driving strategy with the lowest comprehensive cost score as the target assisted driving strategy. The risk probability determination module is specifically used for: the historical risk information including historical road risk information and historical vehicle risk information; determining a first risk occurrence probability based on the road condition level and the historical road risk information; acquiring vehicle status information, and determining a second risk occurrence probability based on the vehicle status information and the historical vehicle risk information; calculating the historical vehicle risk frequency based on the historical vehicle risk information, and determining a risk probability weight based on the historical vehicle risk frequency; and performing a weighted summation of the first risk occurrence probability and the second risk occurrence probability based on the risk probability weight to obtain the risk occurrence probability.

6. An electronic device, characterized in that, It includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the assisted driving method based on road environment information as described in any one of claims 1-4.

7. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the assisted driving method based on road environment information as described in any one of claims 1-4.

Images