Vehicle intelligent driving behavior decision-making method and system

Abstract

This application discloses a method and system for intelligent vehicle driving behavior decision-making. The method includes the following steps: obtaining the main vehicle's driving environment; obtaining the main vehicle's driving mode and the driving conditions of the adjacent vehicle; evaluating and obtaining the main vehicle's driving risk based on the main vehicle's driving environment, the main vehicle's driving mode, and the adjacent vehicle's driving conditions; and executing different main vehicle driving behavior decisions based on the obtained main vehicle's driving mode and the main vehicle's driving risk assessment results. This application comprehensively considers the adjacent vehicle environment, driving mode, and the main vehicle's driving risk assessment results, providing different vehicle driving behavior decisions and effectively and comprehensively ensuring vehicle driving safety.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and specifically to a method and system for vehicle intelligent driving behavior decision-making. Background Art

[0002] In intelligent driving technology, the behavioral decision-making system determines the vehicle's driving strategy. Correct and reasonable driving behavior contributes to vehicle compliance, efficiency, safety, and comfort. Given the complex and ever-changing real-world traffic environment, making accurate driving decisions to avoid accidents while improving road traffic efficiency is a pressing issue.

[0003] Methods for intelligent vehicle behavioral decision-making can be categorized into two types: utility-based and rule-based. Utility-based behavioral decision-making models are widely used, but they are challenging to process, require high real-time performance, and fail to consider modeling traffic regulations. Rule-based behavioral decision-making models use pre-defined rules and environmental conditions to determine driving behavior. They offer simple rule settings, strong readability, and rapid response. Finite state machine-based behavioral decision-making models divide vehicle behavior and environmental information into a finite number of states, defining transition rules between each state. When making behavioral decisions, different driving behaviors are determined based on environmental information and driving state transition rules.

[0004] A finite state machine-based intelligent vehicle driving behavior decision-making method and system first defines various driving behaviors based on experience. Then, the judgment conditions of the vehicle's current driving scenario are determined based on the vehicle's position, heading angle, driving speed, driving environment, etc. The mapping relationship between driving scenarios and driving behaviors is established through event set descriptions. Finally, the finite state machine is used to determine the vehicle's optimal driving behavior:

[0005] 1. The vehicle's driving path and the paths on both sides are determined by creating a grid map and setting a row of scattered points at a certain distance in front of the vehicle. The longitudinal judgment range is small and does not consider the processing logic for the simultaneous presence of multiple vehicles in the left, center, and right lanes.

[0006] 2. The definition of driving behavior is incomplete. The host vehicle's assessment of the presence of surrounding vehicles is limited to the front, without any analysis of the side and rear. However, in real-world scenarios, two vehicles driving side by side is a dangerous condition and should be avoided as much as possible. When a vehicle is approaching rapidly from behind, the host vehicle must also determine whether to actively accelerate or change lanes to avoid it based on its lane and surrounding environment.

[0007] 3. The impact of different weather conditions on driving behavior decisions is not considered. Rainy and snowy weather makes the road slippery, significantly affecting braking distance. Visibility is low in foggy weather, so the rationality of the behavior must also be considered when making driving decisions. Summary of the Invention

[0008] The purpose of this application is to overcome the shortcomings of the above-mentioned background technology and provide a vehicle intelligent driving behavior decision-making method and system.

[0009] In a first aspect, a method for intelligent driving behavior decision-making of a vehicle is provided, comprising the following steps:

[0010] Obtain the main vehicle driving environment;

[0011] Obtaining a driving mode of the host vehicle and a driving condition of a neighboring vehicle, wherein the driving mode includes a lane-changing motivation of the vehicle;

[0012] Assess and obtain the driving risk assessment results of the main vehicle based on the main vehicle's driving environment, main vehicle's driving mode, and the driving conditions of the adjacent vehicle;

[0013] Different driving behavior decisions of the main vehicle are executed according to the obtained driving mode of the main vehicle and the assessment results of the main vehicle driving risk.

[0014] According to the first aspect, in a first implementation of the first aspect, the step of obtaining the driving environment of the host vehicle specifically includes the following steps:

[0015] Obtain the road environment in which the main vehicle is driving;

[0016] Obtain the surrounding vehicle environment of the main vehicle;

[0017] Based on the acquired road environment and adjacent vehicle environment, the effective adjacent vehicles in the driving environment of the vehicle are calibrated and acquired;

[0018] The driving environment of the host vehicle is determined based on the displacement, speed, lateral position of the effective side vehicles and the status information of the host vehicle.

[0019] According to the first implementation of the first aspect, in the second implementation of the first aspect, the step of determining the driving environment of the host vehicle based on the displacement, speed, and lateral position of the effective side vehicle and the status information of the host vehicle specifically includes the following steps:

[0020] Divide the area around the main vehicle and obtain the divided area;

[0021] The driving environment of the main vehicle is determined based on the displacement, speed, lateral position of the effective side vehicles, the status information of the main vehicle, and the divided areas.

[0022] According to the first aspect, in a third implementation of the first aspect, the step of evaluating and obtaining an assessment result of the driving risk of the host vehicle based on the driving environment of the host vehicle, the driving mode of the host vehicle, and the driving condition of the adjacent vehicle specifically includes the following steps:

[0023] According to the driving mode of the main vehicle, obtain the standard driving conditions of the adjacent vehicle related to the current driving mode;

[0024] When any of the vehicles around the main vehicle is driving irregularly, the driving risk assessment result of the main vehicle is obtained based on the comparison between the actual longitudinal distance or the actual lateral distance and the corresponding safe distance;

[0025] When all adjacent vehicles related to the current driving mode are driving in a standardized manner and the vehicle intends to change lanes, the assessment result of the main vehicle's driving risk is obtained based on the presence or absence of vehicles in the front and rear of the target lane and the driving conditions of the front and rear vehicles.

[0026] According to the third implementation of the first aspect, in the fourth implementation of the first aspect, when any of the adjacent vehicles around the host vehicle is driving irregularly, the step of obtaining an assessment result of the host vehicle's driving risk based on a comparison result between the actual longitudinal vehicle distance or the actual lateral vehicle distance and the corresponding safety distance specifically includes the following steps:

[0027] When any of the vehicles around the main vehicle is driving irregularly and the vehicle is driving longitudinally, the assessment result of the main vehicle's driving risk is obtained based on the comparison of the actual longitudinal distance between the leading and trailing vehicles and the safe longitudinal distance;

[0028] When any of the vehicles around the main vehicle is driving irregularly and the vehicle is changing lanes, an assessment result of the main vehicle's driving risk is obtained based on the actual lateral distance and the safe lateral distance between the main vehicle and the vehicle, and / or based on the comparison between the actual longitudinal distance and the safe longitudinal distance between the main vehicle and the vehicle.

[0029] According to the third implementation of the first aspect, in the fifth implementation of the first aspect, when the adjacent vehicles related to the current driving mode are all driving in a normal manner and the vehicle has a lane change intention, the step of obtaining an assessment result of the driving risk of the host vehicle based on the presence or absence of front and rear vehicles in the target lane of the host vehicle and the driving conditions of the front and rear vehicles specifically includes the following steps:

[0030] According to the acquired vehicle driving location environment, the existence conditions of the vehicles in front and behind the target lane of the main vehicle are obtained;

[0031] When there is a leading vehicle in the target lane of the main vehicle and the vehicle has the intention to change lanes, the collision time is obtained based on the longitudinal displacement and longitudinal vehicle speed of the leading and following vehicles. The driving risk assessment result of the main vehicle is obtained based on the comparison result between the collision time and the collision risk time threshold;

[0032] When there is a rear vehicle in the target lane of the main vehicle and the vehicle has the intention to change lanes, the rear vehicle's rear-end collision safety distance is obtained based on the longitudinal distance between the main vehicle and the rear vehicle, the main vehicle's speed and the main vehicle's acceleration. The main vehicle's driving risk assessment result is obtained based on the rear-end collision safety distance and the longitudinal distance between the main vehicle and the rear vehicle.

[0033] According to the first aspect, in a sixth implementation of the first aspect, executing different driving behavior decision steps for the host vehicle based on the acquired driving mode of the host vehicle and the evaluation result of the driving risk of the host vehicle further includes the following steps:

[0034] Get weather forecast information;

[0035] Execute different vehicle driving behavior decisions based on the acquired driving mode, the assessment results of the main vehicle's driving risk, and weather forecast information

[0036] In a second aspect, the present application provides a vehicle intelligent driving behavior decision system, a driving environment acquisition module, which acquires the driving environment of the main vehicle;

[0037] A driving mode acquisition module is used to acquire the driving mode of the host vehicle and the driving conditions of the adjacent vehicle, wherein the driving mode includes the vehicle lane change motivation;

[0038] The risk assessment module is used to evaluate the driving risk of the main vehicle based on the main vehicle's driving environment, the main vehicle's driving mode, and the driving conditions of the adjacent vehicle;

[0039] A behavior decision acquisition module is in communication with the driving environment acquisition module, the driving mode acquisition module, and the risk assessment module, and is used to execute different driving behavior decisions of the host vehicle based on the acquired driving mode of the host vehicle and the assessment results of the host vehicle driving risk.

[0040] According to the second aspect, in a first implementation of the second aspect, the driving environment acquisition module includes:

[0041] The road environment acquisition submodule is used to obtain the road environment in which the main vehicle is driving;

[0042] The adjacent vehicle environment acquisition module is used to obtain the adjacent vehicle environment in which the main vehicle is driving;

[0043] an effective adjacent vehicle calibration module, communicatively connected to the road environment acquisition submodule and the adjacent vehicle environment acquisition submodule, for calibrating and acquiring effective adjacent vehicles in the driving environment of the host vehicle based on the acquired road environment and adjacent vehicle environment;

[0044] The driving environment acquisition submodule is in communication with the effective side vehicle calibration module and is used to determine the driving environment of the host vehicle based on the displacement, speed, lateral position of the effective side vehicles and the status information of the host vehicle.

[0045] According to the first implementation of the second aspect, in the second implementation of the second aspect, the driving environment acquisition submodule includes:

[0046] An area division unit is used to divide the area around the main vehicle and obtain the divided area;

[0047] The driving environment acquisition unit is in communication with the area division unit and is used to determine the driving environment of the host vehicle based on the displacement, speed, lateral position of the effective side vehicles, the status information of the host vehicle and the divided areas.

[0048] Compared with the prior art, the advantages of this application are as follows:

[0049] The vehicle intelligent driving behavior decision-making method provided in this application comprehensively considers the vehicle driving environment, driving mode and the assessment results of the main vehicle driving risk, provides different vehicle driving behavior decisions, and effectively and comprehensively guarantees vehicle driving safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A flowchart of a method for intelligent vehicle driving behavior decision-making provided in an embodiment of the present application;

[0051] Figure 2 A schematic diagram of a lane determination scenario for adjacent vehicles provided in an embodiment of the present application;

[0052] Figure 3 A schematic diagram of a vehicle location marking scenario provided by an embodiment of the present application;

[0053] Figure 4 A schematic diagram of a lane-changing scenario when the preceding vehicle is in the target lane provided in an embodiment of the present application;

[0054] Figure 5 A schematic diagram of a lane-changing scenario when a following vehicle is in the target lane provided in an embodiment of the present application;

[0055] Figure 6 Schematic diagram of the minimum safe longitudinal distance provided by the embodiment of the present application;

[0056] Figure 7 Schematic diagram of the minimum safe lateral distance provided in the embodiment of the present application;

[0057] Figure 8 The state transition logic diagram of the driving mode provided in the embodiment of the present application. DETAILED DESCRIPTION

[0058] Reference will now be made in detail to specific embodiments of the present application, examples of which are illustrated in the accompanying drawings. Although the present application will be described in conjunction with specific embodiments, it will be understood that the present application is not intended to be limited to the described embodiments. On the contrary, it is intended to cover variations, modifications, and equivalents within the spirit and scope of the present application as defined by the appended claims. It should be noted that the method steps described herein can be implemented by any functional block or functional arrangement, and any functional block or functional arrangement can be implemented as a physical entity or a logical entity, or a combination of the two.

[0059] In order to enable those skilled in the art to better understand the present application, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0060] Note: The following example is only a specific example and is not intended to limit the embodiments of this application to the following specific steps, values, conditions, data, sequence, etc. Those skilled in the art can apply the concepts of this application to construct more embodiments not described in this specification by reading this specification.

[0061] The present application provides an intelligent vehicle driving behavior decision-making method and system based on a hierarchical serial finite state machine. It addresses the defects in the existing technology and solves the technical problems of limited judgment scope of vehicle-passable roads, incomplete definition of driving behavior, few considerations of driving scenarios, and failure to consider the impact of weather on driving behavior decision-making results.

[0062] See also Figure 1 As shown, the embodiment of the present application provides a vehicle intelligent driving behavior decision-making method, comprising the following steps:

[0063] Step S1, obtaining the driving environment of the main vehicle;

[0064] Step S2: obtaining a driving mode of the host vehicle and a driving condition of the adjacent vehicle set by the cosine, wherein the driving mode includes a lane change motivation of the vehicle, specifically, the driving mode includes cruising, following, start-stop, emergency collision avoidance, left lane change, and right lane change;

[0065] Step S3: Evaluate and obtain the driving risk assessment result of the main vehicle based on the main vehicle driving environment, the main vehicle driving mode, and the driving conditions of the adjacent vehicle;

[0066] Step S4: Execute different driving behavior decisions for the main vehicle according to the acquired driving mode of the main vehicle and the evaluation results of the driving risk of the main vehicle.

[0067] This application comprehensively considers the vehicle environment, driving mode and the assessment results of the main vehicle driving risk, and provides different vehicle driving behavior decisions to effectively and comprehensively ensure vehicle driving safety.

[0068] In one embodiment, the step S1, obtaining the driving environment of the host vehicle, specifically includes the following steps:

[0069] Step S11: Acquire the road environment in which the host vehicle is driving, wherein the road environment includes a single-lane environment and a multi-lane environment;

[0070] Step S12: Obtain the surrounding vehicle environment of the main vehicle. The surrounding vehicle environment in this application specifically refers to the lane where the main vehicle is located and the surrounding vehicle environments of the two lanes to the left and right of the main vehicle lane. The lane diagram is as follows: Figure 2 As shown in the figure, when the ego vehicle is driving in the middle lane, assuming the lateral coordinate of the road centerline is 0, the road width is 3.75m, and the left side of the ego vehicle is defined as the positive direction, the coordinates of the lane boundary lines of the middle lane and the adjacent lanes are 5.625, 1.875, -1.875, and -5.625, respectively, which are lines A, B, C, and D in the figure. If the perceived lateral distance between the adjacent vehicle and the ego vehicle is within the range of (-1.875, 1.875), it indicates that the adjacent vehicle is in the same lane as the ego vehicle; if the lateral distance between the adjacent vehicle and the ego vehicle is within the range of (1.875, 5.625), it indicates that the adjacent vehicle is in the lane to the left of the ego vehicle; if the lateral distance between the adjacent vehicle and the ego vehicle is within the range of (-5.625, -1.875), it indicates that the adjacent vehicle is in the lane to the right of the ego vehicle; if the lateral distance between the adjacent vehicle and the ego vehicle is within the range of (-∞, -5.625) or (5.625, +∞), the adjacent vehicle is considered to be absent.

[0071] Step S13: Based on the acquired road environment and the adjacent vehicle environment, valid adjacent vehicles in the driving environment of the vehicle are calibrated. Specifically, when the vehicle is traveling on a single-lane road such as a ramp, adjacent vehicles outside the lane width are first found based on the lateral position information, and their corresponding information is filtered out. Then, information analysis is performed on the remaining perceived adjacent vehicles as valid adjacent vehicles. When the vehicle is traveling on a multi-lane road, the vehicle first determines whether there is an adjacent vehicle in the lane where the vehicle is located based on the lateral distance of the perceived obstacle from the lane centerline. Then, the position of the adjacent vehicle relative to the vehicle is determined based on the distance and speed detected by the sensor. If there are multiple adjacent vehicles, the adjacent vehicle closest to the vehicle is selected as the valid adjacent vehicle for information output. Similarly, the left and right lanes are determined separately based on the lateral position. If there are multiple adjacent vehicles in the lanes on both sides, the adjacent vehicle closest to the vehicle is selected as the valid adjacent vehicle for information output.

[0072] Step S14: Determine the driving environment of the host vehicle based on the displacement, speed, and lateral position of the effective adjacent vehicles and the status information of the host vehicle, thereby making a vehicle driving behavior decision in the adjacent vehicle environment taking into account the single lane or multi-lane situation in which the host vehicle is located.

[0073] In one embodiment, step S14, determining the driving environment of the host vehicle based on the displacement, speed, and lateral position of the effective adjacent vehicle and the host vehicle's status information, specifically includes the following steps:

[0074] Step S141, divide the area around the main vehicle, obtain the divided areas, and calibrate the position information of the adjacent vehicles according to the divided areas. Specifically, based on the scenarios encountered in real driving, the positions of the adjacent vehicles are divided into the following eight parts: with the main vehicle as the center, the adjacent vehicles in the front, left front, right front, left, right, left rear, and right rear are analyzed. Correspondingly, the area around the main vehicle is divided into the front, left front, right front, left, right, left rear, and right rear areas. According to the eight divided areas, the front vehicle in the lane where the main vehicle is located is recorded as "adjacent vehicle No. 1", the front vehicle in the left lane is recorded as "adjacent vehicle No. 2", the front vehicle in the right lane is recorded as "adjacent vehicle No. 3", the vehicle driving side by side in the left lane is recorded as "adjacent vehicle No. 4", the vehicle driving side by side in the right lane is recorded as "adjacent vehicle No. 5", the vehicle behind the left lane is recorded as "adjacent vehicle No. 6", the vehicle behind the right lane is recorded as "adjacent vehicle No. 7", and the vehicle directly behind is recorded as "adjacent vehicle No. 8". Figure 3 As shown;

[0075] Step S142: Determine the driving environment of the host vehicle based on the displacement, speed, and lateral position of the valid side vehicles, the host vehicle's status information, and the divided areas. Specifically, after completing the calibration of the side vehicle position information around the host vehicle, a series of rules must be established to enable the intelligent vehicle to recognize the position of side vehicles in real time during driving. When establishing these rules, the order in which the side vehicle positions are determined must be considered. This order must conform to the driving habits of human drivers. In actual driving, for the safety of the host vehicle and other vehicles, braking and throttle control take precedence over steering control. Therefore, the host vehicle's immediate front vehicle (side vehicle 1) is first determined. If there is no vehicle in front, other side vehicles are not considered (here, it is assumed that all side vehicles are driving in a standardized manner; irregular driving of side vehicles will be discussed later). If there is a vehicle in front, the driving conditions of the vehicles on both sides and in front (side vehicles 2, 3, 4, and 5) are considered. Finally, the driving conditions of the rear vehicles (side vehicles 6, 7, and 8) are considered. In addition, when the main vehicle changes its relative position to surrounding vehicles due to acceleration, deceleration, or lane change, the position information of the surrounding vehicles in the state machine must also be updated in a timely manner, thereby achieving dynamic recognition of the relative position of the surrounding vehicles;

[0076] On the basis of obtaining the displacement, speed and lateral position of the effective side car, it is also necessary to combine the status information of the main car: first, determine the side car in the same lane based on the lateral position. For the side car in the same lane, it is only necessary to judge the relationship between the displacement of the car and the displacement of the main car. If the displacement of the car is greater than the displacement of the main car, this car is considered to be side car No. 1, otherwise it is considered to be side car No. 8 directly behind; under the premise of confirming the existence of side car No. 1, select the side car with a displacement greater than the displacement of the main car but a lateral position within the width of the lanes on both sides as side car No. 2 and side car No. 3; for side car No. 4 and side car No. 5, first determine the side car whose front and rear positions are close to the main car or overlap with it through longitudinal displacement, and then determine the left and right positions through lateral position; the judgment of side cars No. 6 and 7 is also to first determine whether they are behind the main car through longitudinal position, and then rely on the relative lateral position to determine the left and right situation.

[0077] In one embodiment, in order to ensure driving safety and avoid collisions with other vehicles during lane changes, when the behavior decision system believes that there is a motivation to change lanes, it is necessary to confirm the situation of the adjacent vehicles in the target lane before executing the lane change, and fully consider the feasibility of the lane change action. In addition to the lateral movement of the vehicle in different lanes, the lane change process also involves the longitudinal displacement of the vehicle. When there is a vehicle in front of the adjacent lane, it is necessary to avoid collisions with the vehicle in front after changing lanes; when there is a vehicle behind the adjacent lane, the situation of the vehicle behind must also be considered to avoid rear-end collisions. The collision risks considered in this solution are divided into two categories: lane change risk and emergency collision avoidance risk. The lane change risk includes two situations: the front vehicle is in the target lane and the rear vehicle is in the target lane. Step S3, the step of evaluating and obtaining the evaluation result of the driving risk of the main vehicle based on the driving environment of the main vehicle, the driving mode of the main vehicle and the driving conditions of the adjacent vehicle, specifically includes the following steps:

[0078] When all adjacent vehicles are driving in a normal manner on the road, the lane-changing risk of the vehicle is assessed in two scenarios: A and B.

[0079] A. The vehicle ahead is in the target lane

[0080] When there is a vehicle ahead in the target lane of a lane change, a collision may occur when the rear vehicle accelerates to overtake but the front vehicle decelerates or is driving at a slower speed. To better study this scenario, assume that the front vehicle in the target lane is driving along the centerline of the road and the lateral displacement of the vehicle is 0. Then the critical position of the rear vehicle and the front vehicle when changing lanes is as follows: Figure 4 shown.

[0081] Because the leading vehicle has no lateral displacement and the trailing vehicle is always completely behind it at the start of the lane change, there will be no longitudinal overlap between the two vehicles. Therefore, the lane change risk under this condition is related to the longitudinal distance between the leading and trailing vehicles and their longitudinal speeds. To quantitatively analyze the lane change collision scenario when the leading vehicle is in the target lane, the Time to Collision (TTC) metric is introduced. This TTC is the ratio of the distance between the leading and trailing vehicles to their relative speeds, calculated as follows:

[0082]

[0083] Where s1 and s0 represent the longitudinal displacements of the leading and trailing vehicles, respectively; v1 and v0 represent the longitudinal velocities of the leading and trailing vehicles, respectively.

[0084] According to the above formula, when the speed difference between the two vehicles is large, even if they are not very close, the TTC value will still be relatively low, and the system will trigger an alarm if it falls below a certain threshold. However, if the two vehicles are close but their speeds are equal, the TTC value will be large, and the system will deem it safe. Therefore, TTC is mainly applicable when the two vehicles are close and have a large speed difference, targeting "dangerous and urgent" situations. Therefore, this solution uses collision time to assess the lane change risk when there is a neighboring vehicle in front of the target lane. Considering that when calculating the collision time in the behavioral decision system, the speeds of the two vehicles may be equal. In this case, the TTC will become +∞ or -∞, which is not conducive to the state machine's state transition judgment. Furthermore, because the displacements of the host vehicle and the neighboring vehicle may not be exactly equal, TTC-1 is used as a parameter in the lane change risk assessment.

[0085] B. The following vehicle is in the target lane

[0086] When there is a following vehicle in the target lane of the lane change, regardless of the situation where the lane-changing vehicle intentionally decelerates after entering the target lane, the possible collision is often caused by the following vehicle not maintaining a sufficient safe distance. To better describe this scenario, similar to the analysis process of the leading vehicle in the target lane, it is assumed that the lateral displacement of the following vehicle is 0 during the process of the main vehicle changing lanes to the target lane, and it maintains longitudinal movement along the lane line. The critical position of the collision between the two vehicles is as follows: Figure 5 shown.

[0087] The longitudinal distance sx between the rear end of the main vehicle and the head of the following vehicle can be expressed as:

[0088] s x =s0-s1-R0cos(θ)

[0089] Where s0 and s1 represent the longitudinal distances traveled by the main vehicle and the following vehicle, respectively; R0 represents the distance from the center of mass of the main vehicle to the rear of the vehicle.

[0090] To avoid collision with the following vehicle when changing lanes, sx>0 is required. Since cos(θ)<1, in order to ensure the safety of lane changing, a certain redundant distance is added, so:

[0091] s0-s1-R0>0

[0092] The relationship between the longitudinal distance traveled by the vehicle and its own speed and acceleration can be expressed as follows:

[0093]

[0094] Where a represents the longitudinal acceleration and v represents the longitudinal velocity.

[0095] Therefore, the safe distance to avoid rear-end collision in this scenario can be expressed as:

[0096]

[0097] C. Emergency conditions

[0098] During actual driving, the main vehicle will face many challenges from the vehicles beside it. For example, during normal driving, the vehicle beside it suddenly changes lanes and squeezes into the lane where the main vehicle is located, or the vehicle beside it becomes fatigued and drives close to the lane boundary line. In order to deal with such dangerous problems promptly and accurately, the risk of collision caused by the irregular driving of the vehicle beside it must be considered. This solution uses the Responsibility Sensitive Safety (RSS) model to judge the safe distance under emergency conditions. The safe distance refers to the distance that can still avoid collision in the worst case scenario. For two vehicles traveling longitudinally, one in front and one behind, the worst case scenario here means that when the front vehicle starts braking at the maximum braking acceleration, the rear vehicle has a certain amount of reaction time after discovering it. During this reaction time, the rear vehicle still moves forward at the maximum acceleration, and then brakes at the minimum braking acceleration until the danger is eliminated. The minimum longitudinal safety distance is as follows: Figure 6 shown.

[0099] When two vehicles are traveling longitudinally in the same lane, the minimum longitudinal safety distance between them is calculated as follows:

[0100]

[0101] Where, v r is the speed of the following vehicle; ρ is the reaction time of the following vehicle from the braking of the leading vehicle to the braking action, which is 0.5s according to the driver's reaction time under normal circumstances; a max,accel is the maximum acceleration of the following vehicle; a min,brake is the minimum braking deceleration of the following vehicle; v f is the speed of the preceding vehicle; a max,brakeis the maximum braking deceleration of the vehicle in front.

[0102] Since a car not only moves longitudinally when driving, but also performs lateral maneuvers such as changing lanes, and it is difficult to ensure that it drives completely along the center line of the road, the car's lateral fluctuations are always present. Therefore, in addition to considering the longitudinal safety distance, the lateral safety distance must also be considered. For two cars driving side by side, the lateral safety distance refers to the distance between the two cars that can avoid hitting the lane line if both cars approach each other laterally at maximum acceleration, after a certain reaction time, and then brake at minimum lateral deceleration. Figure 7 shown.

[0103] When two vehicles are traveling parallel in adjacent lanes, assuming that both vehicles approach each other at maximum lateral acceleration, and after a period of reaction time, both vehicles brake at minimum lateral deceleration until the lateral speed reaches 0, the minimum lateral safety distance between them is calculated as follows:

[0104]

[0105]

[0106]

[0107] Where μ is the final lateral distance between the two vehicles after they stop, which is 0.15m based on the standard lane width; v1 and v2 are the lateral speeds of the two vehicles respectively; ρ is the reaction time, which is also 0.5s based on the normal driver's reaction time. is the minimum lateral braking deceleration; is the maximum lateral acceleration.

[0108] In the behavioral decision-making model, when the actual lateral or longitudinal distance between the main vehicle and the nearest neighboring vehicle is greater than the minimum safe distance, it is judged that there is no emergency condition and the main vehicle's driving mode is not affected; when the actual distance is less than the minimum safe distance, regardless of the main vehicle's driving mode, it will switch to emergency collision avoidance mode and brake in time to ensure driving safety.

[0109] In one embodiment, step S3, the step of evaluating and obtaining the driving risk assessment result of the host vehicle based on the host vehicle driving environment, the host vehicle driving mode, and the adjacent vehicle driving conditions, specifically includes the following steps:

[0110] Step S31: Based on the host vehicle's driving mode, obtain standard operating conditions for adjacent vehicles associated with the current driving mode. This takes into account the various challenges that the host vehicle may face from adjacent vehicles during actual driving, such as the impact on safe driving of the vehicle caused by an adjacent vehicle suddenly changing lanes and cutting into the host vehicle's lane during normal driving, or the impact on safe driving of the vehicle caused by an adjacent vehicle driving close to a lane boundary due to driver fatigue.

[0111] Step S32: When any of the adjacent vehicles around the host vehicle is driving irregularly, an assessment result of the host vehicle's driving risk is obtained based on a comparison result between the actual longitudinal distance or the actual lateral distance and the corresponding safe distance;

[0112] Step S33: When all adjacent vehicles related to the current driving mode are driving in a normal manner and the vehicle intends to change lanes, an assessment result of the driving risk of the host vehicle is obtained based on the presence or absence of vehicles in the front and rear lanes of the host vehicle and the driving conditions of the front and rear vehicles in order to assess the driving risk of the vehicle under the lane-changing condition.

[0113] In one embodiment, step S32, when any of the adjacent vehicles around the host vehicle is driving irregularly, obtaining an assessment result of the host vehicle's driving risk based on a comparison result between the actual longitudinal distance or the actual lateral distance and the corresponding safety distance, specifically includes the following steps:

[0114] Step S321: When any of the vehicles around the host vehicle is driving irregularly and the vehicle is driving longitudinally, an assessment result of the host vehicle's driving risk is obtained based on a comparison of the actual longitudinal distance between the leading and trailing vehicles and the safe longitudinal distance;

[0115] Step S322: When any of the adjacent vehicles around the host vehicle is driving irregularly and the vehicle is changing lanes, an assessment result of the host vehicle's driving risk is obtained based on a comparison between the actual lateral distance and the safe lateral distance between the host vehicle and the adjacent vehicle, and / or based on a comparison between the actual longitudinal distance and the safe longitudinal distance between the host vehicle and the adjacent vehicle.

[0116] In a more specific embodiment, in the step of obtaining the assessment result of the driving risk of the main vehicle in S322, when any of the side vehicles around the main vehicle is driving irregularly and the vehicle is changing lanes, based on the actual lateral distance and the safe lateral distance between the main vehicle and the side vehicle, and / or based on the comparison between the actual longitudinal distance and the safe longitudinal distance between the main vehicle and the side vehicle, the Responsibility Sensitive Safety (RSS) model is referenced to judge the safe distance under emergency conditions. The safe distance refers to the distance that can still avoid collision in the worst case scenario. For two vehicles traveling straight ahead, one in front and the other behind, the worst case scenario here refers to when the front vehicle starts braking with the maximum braking acceleration, and the rear vehicle has a certain reaction time after discovering it. During this reaction time, the rear vehicle still moves forward with the maximum acceleration, and then brakes with the minimum braking acceleration until the danger is eliminated. The minimum safe longitudinal distance is as follows: Figure 6 As shown, the front vehicle and the rear vehicle here are applicable to the longitudinal driving conditions of the main vehicle and the rear vehicle as well as the front vehicle and the main vehicle, and the longitudinal driving condition specifically refers to the vehicle driving straight.

[0117] 1) When two vehicles are traveling straight ahead in the same lane, the minimum safe longitudinal distance between them is calculated as follows:

[0118]

[0119] Where, v r is the speed of the following vehicle; ρ is the reaction time of the following vehicle from the braking of the leading vehicle to the braking action, which is 0.5s according to the driver's reaction time under normal circumstances; a max,accel is the maximum acceleration of the following vehicle; a min,brake is the minimum braking deceleration of the following vehicle; v f is the speed of the preceding vehicle; a max,brake is the maximum braking deceleration of the front vehicle, Figure 6 The main vehicle in the middle is the rear vehicle;

[0120] 2) Since a car not only moves longitudinally but also makes lateral movements such as lane changing during driving, and it is difficult to ensure that it moves completely along the center line of the road, the car's lateral fluctuations are always present. Therefore, in addition to considering the safe longitudinal distance, the safe lateral distance must also be considered. For two cars driving side by side, the safe lateral distance refers to the distance between the two cars that can avoid hitting the lane line if both cars approach each other laterally at maximum acceleration, after a certain reaction time, and then brake at minimum lateral deceleration. Figure 7 shown.

[0121] When two vehicles are traveling parallel in adjacent lanes, assuming that both vehicles approach each other at maximum lateral acceleration, and after a period of reaction time, both vehicles brake at minimum lateral deceleration until the lateral speed reaches 0, the minimum safe lateral distance between them is calculated as follows:

[0122]

[0123]

[0124]

[0125] Where μ is the final lateral distance between the two vehicles after they stop, which is 0.15m based on the standard lane width; v1 and v2 are the lateral speeds of the two vehicles respectively; ρ is the reaction time, which is also 0.5s based on the normal driver's reaction time. is the minimum lateral braking deceleration; is the maximum lateral acceleration, Figure 7 In the diagram, the main vehicle is the left vehicle or the right vehicle.

[0126] In the behavioral decision-making model, when any of the vehicles around the main vehicle has irregular driving behavior and the actual lateral and longitudinal distances between the main vehicle and the nearest neighboring vehicle are both greater than the minimum safety distance, it is judged that there is no emergency condition and the driving mode of the main vehicle is not affected; when any of the vehicles around the main vehicle has irregular driving behavior and the actual lateral or longitudinal distances between the main vehicle and the nearest neighboring vehicle are both greater than the minimum safety distance, regardless of the driving mode of the main vehicle, it will switch to emergency collision avoidance mode and brake in time to ensure driving safety. Preferably, when the main vehicle is traveling straight ahead and any of the adjacent vehicles related to the main vehicle traveling straight ahead has irregular driving behavior, and the longitudinal distance between the main vehicle and the adjacent vehicles related to the main vehicle traveling straight ahead is greater than the minimum safe distance, it is determined that there is no emergency condition and the driving mode of the main vehicle is not affected; when the main vehicle is traveling straight ahead and any of the adjacent vehicles related to the main vehicle traveling straight ahead has irregular driving behavior, and the longitudinal distance between the main vehicle and the adjacent vehicles related to the main vehicle traveling straight ahead is not greater than the minimum safe distance, it is determined that there is an emergency condition and the main vehicle switches to the emergency collision avoidance mode and brakes in time; when the main vehicle changes lanes, the main vehicle When any of the adjacent vehicles involved in lane changing has irregular driving behavior, and the longitudinal distance and lateral distance between the main vehicle and the adjacent vehicles involved in lane changing are both greater than the minimum safety distance (including the safe lateral distance and the safe longitudinal distance), it is judged that there is no emergency condition and the driving mode of the main vehicle is not affected; when the main vehicle is changing lanes, if any of the adjacent vehicles involved in lane changing has irregular driving behavior, and the longitudinal distance or lateral distance between the main vehicle and the adjacent vehicles involved in lane changing is not greater than the minimum safety distance, it is judged that there is an emergency condition, the main vehicle switches to the emergency collision avoidance mode and brakes in time.

[0127] In one embodiment, a logical determination method for determining whether a vehicle intends to change lanes is implemented as follows:

[0128] Time Headway (TH) represents the time difference between the front ends of two vehicles passing the same location. This refers to the maximum reaction time a driver of a following vehicle has when the leading vehicle brakes. In real-world driving scenarios, TH primarily triggers an alarm when two vehicles are close together, helping the driver of the following vehicle develop the habit of maintaining proper distance. This situation falls under "dangerous but not urgent" conditions and is suitable for measuring the necessity of lane changes for smart cars.

[0129] The headway is obtained by the ratio of the distance between the front and rear vehicles to the speed of the rear vehicle. The calculation formula is as follows:

[0130]

[0131] Where d is the distance between the front and rear vehicles; vrear is the speed of the rear vehicle.

[0132] The larger the TH value, the more time the following vehicle has to react to the situation of the vehicle ahead. The behavioral decision-making system calculates the TH values ​​of the host vehicle and the preceding vehicle in real time. By setting a threshold for headway, the system switches between lane change motivation and lane keeping motivation. When there's no vehicle ahead, or when a vehicle ahead is detected but the TH value is greater than the threshold, the system assumes there's no lane change motivation and maintains lane keeping. When the TH value is less than the threshold, the decision-making system determines a lane change is necessary.

[0133] In one embodiment, step S33, when all adjacent vehicles related to the current driving mode are driving normally and the vehicle has a lane change intention, obtains an assessment result of the driving risk of the host vehicle based on the presence or absence of vehicles in the target lane and the driving conditions of the vehicles in the target lane, specifically includes the following steps:

[0134] Step S331: Obtain the presence of vehicles in front and behind the target lane of the host vehicle based on the acquired vehicle driving location environment;

[0135] Step S332: When there is a preceding vehicle in the target lane of the host vehicle and the vehicle has a lane change intention, a collision time is obtained based on the longitudinal displacement and longitudinal speed of the preceding and following vehicles, and a driving risk assessment result of the host vehicle is obtained based on a comparison result between the collision time and the collision risk time threshold.

[0136] More specifically, when there is a preceding vehicle in the target lane for lane change, a potential collision often occurs when the following vehicle accelerates to overtake but the preceding vehicle decelerates or is traveling at a slower speed. To better study this scenario, assume that the preceding vehicle in the target lane is traveling along the centerline of the road and the lateral displacement of the vehicle is zero. Then, the critical position of the following vehicle when colliding with the preceding vehicle during lane change is as follows: Figure 4 shown.

[0137] Because the leading vehicle has no lateral displacement and the trailing vehicle is always completely behind it at the start of the lane change, there will be no longitudinal overlap between the two vehicles. Therefore, the lane change risk under this condition is related to the longitudinal distance between the leading and trailing vehicles and their longitudinal speeds. To quantitatively analyze the lane change collision scenario when the leading vehicle is in the target lane, the Time to Collision (TTC) metric is introduced. This TTC is the ratio of the distance between the leading and trailing vehicles to their relative speeds, calculated as follows:

[0138]

[0139] Where s1 and s0 represent the longitudinal displacement of the leading and trailing vehicles respectively; v1 and v0 represent the longitudinal speed of the leading and trailing vehicles respectively. Figure 4 The main car in the middle is the rear car.

[0140] According to the above formula, when the speed difference between the two vehicles is large, even if the distance between them is not very close, the TTC value will still be relatively small. When it is below a certain threshold, the system will alarm; if the distance between the two vehicles is close, but the speed is equal, the TTC value will be large, and the system will consider it safe. Therefore, TTC is mainly applicable to situations where the distance between the two vehicles is close and there is a large speed difference. It is aimed at "dangerous and urgent" situations. Therefore, this application uses collision time to evaluate the lane change risk when there is a side vehicle in front of the target lane. Taking into account that when calculating the collision time in the behavioral decision-making system, the speed of the two vehicles may be equal. At this time, TTC will become +∞ or -∞, which is not conducive to the state machine's judgment of state switching. At the same time, since the displacement of the main vehicle and the side vehicle will not be completely equal, TTC-1 is used as a parameter for calculation when performing lane change risk assessment.

[0141] Step S333: When there is a following vehicle in the target lane of the host vehicle and the vehicle has a lane change intention, the rear-end collision safety distance is obtained based on the longitudinal distance between the host vehicle and the following vehicle, the host vehicle's speed, and the host vehicle's acceleration. Based on the rear-end collision safety distance and the longitudinal distance between the host vehicle and the following vehicle, an assessment result of the host vehicle's driving risk is obtained.

[0142] More specifically, when there is a following vehicle in the target lane of a lane change, regardless of the situation where the lane-changing vehicle intentionally decelerates after entering the target lane, a collision may occur because the following vehicle does not maintain a sufficient safe distance. To better describe this scenario, similar to the analysis process of the leading vehicle in the target lane, it is assumed that the lateral displacement of the following vehicle is 0 during the process of the main vehicle changing lanes to the target lane, and it keeps driving straight along the lane line. The critical position where the two vehicles collide is as follows: Figure 5 shown.

[0143] The longitudinal distance sx between the rear of the main vehicle and the head of the following vehicle can be expressed as:

[0144] sx=s0-s1-R0cos(θ)

[0145] Where s0 and s1 represent the longitudinal distances traveled by the main vehicle and the following vehicle, respectively; R0 represents the distance from the center of mass of the main vehicle to the rear of the main vehicle; and θ represents the angle between the length of the main vehicle and the length of the lane during the lane change process. Figure 5 The main car in the middle is the front car.

[0146] To avoid collision between the main vehicle and the following vehicle during lane change, sx>0 is required. Since cos(θ)<1, a certain redundant distance is added to ensure the safety of lane change, so:

[0147] s0-s1-R0>0;

[0148] Where s1 and s0 represent the longitudinal displacement of the leading and trailing vehicles respectively, R0 represents the distance from the center of mass of the main vehicle to the rear of the main vehicle, Figure 5 The main car in the middle is the front car.

[0149] The relationship between the longitudinal distance traveled by the vehicle and its own speed and acceleration can be expressed as follows:

[0150]

[0151] Where a(τ) represents the longitudinal acceleration at time τ; v represents the longitudinal velocity, t is the current time, and t0 is the initial time.

[0152] Therefore, the safe distance to avoid rear-end collision in this scenario can be expressed as:

[0153]

[0154] Among them, a0 is the initial acceleration, a1(τ) is the acceleration at time τ, v0 is the initial velocity, and v1 is the velocity at time τ.

[0155] In one embodiment, in addition to information about surrounding vehicles and roads, the impact of weather conditions on driving behavior decisions also needs to be considered. Different driving behavior decision steps for the host vehicle are executed based on the acquired driving mode of the host vehicle and the assessment results of the host vehicle's driving risk, and the following steps are also included:

[0156] Get weather forecast information;

[0157] Based on the acquired driving pattern, the driver's driving risk assessment, and weather forecast information, different vehicle driving behavior decisions are executed. This adds weather processing logic, using the weather forecast as a tangible algorithm input rather than simply informing the driver. Weather forecast information can be used as input to appropriately adjust driving strategies in different weather conditions. While ensuring safety, when weather conditions are favorable, the behavioral decision-making process can prioritize efficiency. In rainy or snowy weather, the road adhesion coefficient decreases, and the driving strategy prioritizes safety and compliance. The collision risk threshold needs to be increased, forcing the vehicle to adopt a relatively conservative driving strategy: maintaining a longer following distance and reducing the frequency of lane changes. The specific threshold can be determined through driver data collection and real-vehicle calibration. When the weather conditions are bad, the behavior decision system adopts a conservative driving strategy, ensuring the safety of passengers on slippery roads by keeping a longer following distance and reducing the frequency of lane changes, thus making up for the defect of the existing behavior decision process being insufficient. When the assessment result of the main vehicle's driving risk indicates that there is a risk of emergency conditions, the main vehicle's driving mode is switched to the emergency collision avoidance mode and brakes in time to ensure driving safety. When the weather forecast information shows that the weather conditions are bad and the assessment result of the main vehicle's driving risk is that there is no driving risk, different vehicle driving behavior decisions are executed according to the main vehicle's driving mode and the assessment result of the main vehicle's driving risk. Specifically, when the vehicle is driving normally, the state transition conditions of each driving mode are shown in Tables 1 and 2. Figure 8 shown.

[0158] In one embodiment, based on the calibration of surrounding vehicle position information, combined with lane change motivations and risk assessment results, the intelligent vehicle can make timely and appropriate choices and switches between different driving modes based on its driving tasks and safe driving behavior guidelines. Combining the driver's actions during actual driving with the vehicle's driving behavior, this application defines the following six driving modes: cruising, following, start-stop, emergency collision avoidance, left lane change, and right lane change.

[0159] The behavioral decision system uses a finite state machine to select a driving mode suitable for the current driving conditions from these six driving modes and switches between states when necessary. It should be noted that the initial driving mode is cruise mode. Figure 8 The state transition relationships of the six driving modes are given. More specifically, the logic conversion method is set in the state machine. By inputting relevant information, the target transition state of the main vehicle is obtained, where "!" represents negative. The state transition conditions of each driving mode are shown in Table 1.

[0160] Table 1 State transition conditions of driving mode

[0161]

[0162] When making a decision to switch driving modes, the initial state is cruise mode. If there is no preceding vehicle or there is a preceding vehicle but the calculation determines there is no lane change motivation, the state transition conditions are not met and cruise mode remains. If there is a lane change motivation, the lane change risk is calculated for the left front and left rear, and right front and right rear directions (since the overtaking lane in my country is on the left, priority is given to changing to the left lane). If the lane change risk is met, the lane change is executed, entering Mode 5 or 6 (left / right lane change). After the lane change is completed, the state returns to Mode 1. If the calculated lane change risk parameters indicate unsafe conditions, the system enters lane keeping mode and further assesses the driving condition of the preceding vehicle. Depending on whether the preceding vehicle is stationary, the system enters Mode 3 (start-stop) or Mode 2 (following), respectively. If there is no lane change motivation, Mode 1 is restored. Furthermore, at any point in the decision-making process, if the system determines that a dangerous condition exists, the system directly switches from the current mode to Mode 4 for emergency collision avoidance. Once the danger is resolved, the system returns to the original state and outputs the decision results to the planning and control system.

[0163] This application considers the presence of vehicles in the vehicle's own lane and the lanes on both sides at the horizontal level. At the longitudinal level, the area around the main vehicle is divided into eight areas based on the distance between the front and rear vehicles and the vehicle itself, ensuring the comprehensiveness of the behavioral decision-making system in judging environmental information. For multiple vehicles in the same lane, the application effectively addresses the situation where multiple vehicles exist in the left, middle, and right lanes at the same time, which is not considered in the existing solution, through the longitudinal distance and the strategy of first considering the middle lane and then the lanes on both sides.

[0164] When defining the conversion logic of each driving behavior, this application fully considers dangerous conditions in actual scenarios such as two vehicles running parallel or approaching quickly from behind, and uses the RSS model to make decisions on the vehicle's behavior under dangerous conditions, solving the problem that existing solutions default to standard driving of the vehicle next to them and do not consider emergency scenarios.

[0165] This application adds weather processing logic, using weather forecasts as actual algorithm input rather than simply informing the driver. When the weather is relatively bad, the behavioral decision-making system adopts a conservative driving strategy, ensuring the safety of passengers on slippery roads by maintaining a longer following distance and reducing lane changes, thus making up for the shortcomings of the existing solution's insufficient behavioral decision-making process.

[0166] Based on the same inventive concept, the vehicle intelligent driving behavior decision system provided by the present application includes a driving environment acquisition module, a driving mode acquisition module, a risk assessment module and a behavior decision acquisition module. The driving environment acquisition module acquires the driving environment of the main vehicle; the driving mode acquisition module acquires the driving mode of the main vehicle and the driving condition of the adjacent vehicle, and the driving mode includes the vehicle lane changing motivation; the risk assessment module is used to evaluate and obtain the evaluation results of the main vehicle driving risk based on the main vehicle driving environment, the main vehicle driving mode and the driving condition of the adjacent vehicle; the behavior decision acquisition module is communicated with the driving environment acquisition module, the driving mode acquisition module and the risk assessment module, and is used to execute different main vehicle driving behavior decisions based on the acquired main vehicle driving mode and the evaluation results of the main vehicle driving risk.

[0167] In one embodiment, the driving environment acquisition module includes a road environment acquisition submodule, a side car environment acquisition module, an effective side car calibration module and a driving environment acquisition submodule. The road environment acquisition submodule is used to acquire the road environment in which the main vehicle is driving; the side car environment acquisition module is used to acquire the side car environment in which the main vehicle is driving; the effective side car calibration module is communicatively connected to the road environment acquisition submodule and the side car environment acquisition submodule, and is used to calibrate the effective side cars in the driving environment of the vehicle based on the acquired road environment and side car environment in which the main vehicle is driving; the driving environment acquisition submodule is communicatively connected to the effective side car calibration module, and is used to determine the driving environment of the main vehicle based on the displacement, speed, lateral position of the effective side cars and the status information of the main vehicle.

[0168] In one embodiment, the driving environment acquisition submodule includes an area division unit and a driving environment acquisition unit. The area division unit is used to divide the area around the main vehicle and obtain the divided area. The driving environment acquisition unit is communicatively connected to the area division unit and is used to determine the driving environment of the main vehicle based on the displacement, speed, lateral position of the effective side vehicle, the status information of the main vehicle, and the divided area.

[0169] Based on the same inventive concept, an embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, all or part of the method steps of the above method are implemented.

[0170] The present application implements all or part of the processes in the above-mentioned method, and can also be completed by instructing related hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, it can implement the steps of the above-mentioned various method embodiments. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0171] Based on the same inventive concept, an embodiment of the present application also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program running on the processor, and when the processor executes the computer program, all or part of the method steps in the above method are implemented.

[0172] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor. The processor is the control center of a computer device, connecting all parts of the entire computer device using various interfaces and lines.

[0173] The memory can be used to store computer programs and / or modules. The processor implements various functions of the computer device by running or executing the computer programs and / or modules stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system and at least one application required for a function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created based on the use of the mobile phone (such as audio data, video data, etc.). In addition, the memory can include a high-speed random access memory and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0174] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, servers, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage and optical storage, etc.) containing computer-usable program code.

[0175] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), servers and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0176] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0177] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0178] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. A vehicle intelligent driving behavior decision-making method, characterized in that: The steps include: Obtain the main vehicle driving environment; Obtain the driving mode of the main vehicle and the driving conditions of the adjacent vehicle; Assess and obtain the driving risk assessment results of the main vehicle based on the main vehicle's driving environment, main vehicle's driving mode, and the driving conditions of the adjacent vehicle; Execute different driving behavior decisions for the main vehicle based on the acquired driving mode of the main vehicle and the assessment results of the main vehicle's driving risk; The step of evaluating and obtaining the driving risk assessment result of the main vehicle according to the main vehicle driving environment, the main vehicle driving mode, and the driving condition of the adjacent vehicle specifically includes the following steps: According to the driving mode of the main vehicle, obtain the standard driving conditions of the adjacent vehicle related to the current driving mode; When any of the vehicles around the main vehicle is driving irregularly, the driving risk assessment result of the main vehicle is obtained based on the comparison between the actual longitudinal distance or the actual lateral distance and the corresponding safe distance; When all adjacent vehicles related to the current driving mode are driving in a standard manner and the vehicle intends to change lanes, the driver's driving risk assessment result is obtained based on the presence or absence of vehicles in the target lane and the driving conditions of the vehicles in the target lane. The step of obtaining an assessment result of the driving risk of the host vehicle based on the presence or absence of front and rear vehicles in the target lane of the host vehicle and the driving conditions of the front and rear vehicles when all adjacent vehicles related to the current driving mode are driving in a normal manner and the vehicle has an intention to change lanes specifically includes the following steps: According to the acquired vehicle driving location environment, the existence conditions of the vehicles in front and behind the target lane of the main vehicle are obtained; When there is a leading vehicle in the target lane of the host vehicle and the vehicle has the intention to change lanes, the collision time is calculated based on the longitudinal displacement and longitudinal speed of the leading and following vehicles. The driving risk assessment result of the host vehicle is obtained by comparing the collision time with the collision risk time threshold. The collision time is the ratio of the distance between the front and rear vehicles to the relative speed of the two vehicles. Its calculation formula is as follows: ； Where s1 and s0 represent the longitudinal displacement of the leading and trailing vehicles, respectively; v1 and v0 represent the longitudinal speed of the leading and trailing vehicles, respectively; Using TTC when conducting lane change risk assessments -1 Calculate as a parameter; When there is a rear vehicle in the target lane of the main vehicle and the vehicle has the intention to change lanes, the rear vehicle rear-end collision safety distance is obtained based on the longitudinal distance between the main vehicle and the rear vehicle, the main vehicle speed and the main vehicle acceleration. The driving risk assessment result of the main vehicle is obtained based on the rear vehicle rear-end collision safety distance and the longitudinal distance between the main vehicle and the rear vehicle; Longitudinal distance s between the main vehicle and the following vehicle x The calculation formula is: s x =s0-s1-R0cos(θ), where s0 and s1 represent the longitudinal distances traveled by the leading vehicle and the following vehicle, respectively, R0 represents the distance from the center of mass of the leading vehicle to the rear, s0-s1-R0>0, and θ is the angle between the length of the leading vehicle and the length of the lane during the lane change process; The relationship between the longitudinal distance traveled by the vehicle and its own speed and acceleration is expressed as: ； Where, a ( τ )for τ The longitudinal acceleration at the moment, v represents the longitudinal velocity, t is the current moment, and t0 is the initial moment.

2. The vehicle intelligent driving behavior decision-making method according to claim 1, characterized in that: The step of obtaining the driving environment of the host vehicle specifically includes the following steps: Obtain the road environment in which the main vehicle is driving; Obtain the surrounding vehicle environment of the main vehicle; Based on the acquired road environment and adjacent vehicle environment, the effective adjacent vehicles in the driving environment of the vehicle are calibrated and acquired; The driving environment of the host vehicle is determined based on the displacement, speed, lateral position of the effective side vehicles and the status information of the host vehicle.

3. The vehicle intelligent driving behavior decision-making method according to claim 2, characterized in that: The step of determining the driving environment of the host vehicle based on the displacement, speed, and lateral position of the effective side vehicle and the status information of the host vehicle specifically includes the following steps: Divide the area around the main vehicle and obtain the divided area; The driving environment of the main vehicle is determined based on the displacement, speed, lateral position of the effective side vehicles, the status information of the main vehicle, and the divided areas.

4. The vehicle intelligent driving behavior decision-making method according to claim 1, characterized in that: The step of obtaining an assessment result of the driving risk of the main vehicle based on a comparison result between the actual longitudinal vehicle distance or the actual lateral vehicle distance and the corresponding safe distance when any of the surrounding vehicles around the main vehicle are driving irregularly specifically includes the following steps: When any of the vehicles around the main vehicle is driving irregularly and the vehicle is driving longitudinally, the assessment result of the main vehicle's driving risk is obtained based on the comparison of the actual longitudinal distance between the leading and trailing vehicles and the safe longitudinal distance; When any of the vehicles around the main vehicle is driving irregularly and the vehicle is changing lanes, an assessment result of the main vehicle's driving risk is obtained based on the actual lateral distance and the safe lateral distance between the main vehicle and the vehicle, and / or based on the comparison between the actual longitudinal distance and the safe longitudinal distance between the main vehicle and the vehicle.

5. The vehicle intelligent driving behavior decision-making method according to claim 1, characterized in that: Based on the obtained driving mode of the main vehicle and the assessment results of the main vehicle driving risk, different driving behavior decision steps for the main vehicle are executed, which also includes the following steps: Get weather forecast information; Different vehicle driving behavior decisions are made based on the acquired driving pattern, the assessment results of the main vehicle's driving risk, and weather forecast information.

6. A vehicle intelligent driving behavior decision system using the vehicle intelligent driving behavior decision method according to claim 1, characterized in that: Driving environment acquisition module, which obtains the driving environment of the main vehicle; A driving mode acquisition module is used to acquire the driving mode of the host vehicle and the driving conditions of the adjacent vehicle, wherein the driving mode includes the vehicle lane change motivation; The risk assessment module is used to evaluate the driving risk of the main vehicle based on the main vehicle's driving environment, the main vehicle's driving mode, and the driving conditions of the adjacent vehicle; A behavior decision acquisition module is in communication with the driving environment acquisition module, the driving mode acquisition module, and the risk assessment module, and is used to execute different driving behavior decisions of the host vehicle based on the acquired driving mode of the host vehicle and the assessment results of the host vehicle driving risk.

7. The vehicle intelligent driving behavior decision system according to claim 6, characterized in that: The driving environment acquisition module includes: The road environment acquisition submodule is used to obtain the road environment in which the main vehicle is driving; The adjacent vehicle environment acquisition module is used to obtain the adjacent vehicle environment in which the main vehicle is driving; an effective adjacent vehicle calibration module, communicatively connected to the road environment acquisition submodule and the adjacent vehicle environment acquisition submodule, for calibrating and acquiring effective adjacent vehicles in the driving environment of the host vehicle based on the acquired road environment and adjacent vehicle environment; The driving environment acquisition submodule is in communication with the effective side vehicle calibration module and is used to determine the driving environment of the host vehicle based on the displacement, speed, lateral position of the effective side vehicles and the status information of the host vehicle.

8. The vehicle intelligent driving behavior decision system according to claim 7, characterized in that: The driving environment acquisition submodule includes: An area division unit is used to divide the area around the main vehicle and obtain the divided area; The driving environment acquisition unit is in communication with the area division unit and is used to determine the driving environment of the host vehicle based on the displacement, speed, lateral position of the effective side vehicles, the status information of the host vehicle and the divided areas.

Images