Vehicle driving control method, vehicle control device and vehicle

Abstract

The invention relates to a vehicle driving control method, a vehicle control device and a vehicle, and belongs to the technical field of automatic driving. Predicting whether an accident occurrence trend exists or not based on the surrounding environment information; if the accident occurrence trend exists, determining the damage degree of each accident influence factor when the accident occurs based on the surrounding environment information; based on the damage degree of each accident influence factor when the accident occurs, carrying out weight adjustment on each accident influence factor in a decision model; and outputting a vehicle avoidance driving strategy based on the decision model after weight adjustment. According to the method, the weight of each accident influence factor in the decision model is adjusted according to the damage degree of each accident influence factor when an accident occurs; and on the basis of the decision model after weight adjustment, a vehicle avoidance driving strategy is output, so that the vehicle tends to drive towards the lightest damage direction, and the driving safety of the vehicle is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, and in particular to a vehicle driving control method, a vehicle control device and a vehicle. BACKGROUND

[0002] With the development of society, there are more and more vehicles. Especially under the condition of heavy traffic, there are often close following distance, frequent lane changing and other bad driving behaviors. When facing an emergency, due to overreaction or delay, an incorrect decision is made, resulting in an accident. Therefore, it is necessary to improve the safety of vehicle driving. Especially with the increase of automatic driving, it is urgent to improve the safety of automatic driving. SUMMARY

[0003] In view of the above-mentioned shortcomings and deficiencies of the prior art, the present application provides a vehicle driving control method, a vehicle and a storage medium, which solve the technical problem of how to improve the safety of automatic driving.

[0004] In order to achieve the above-mentioned purpose, the main technical solutions adopted by the present application include:

[0005] The present application provides a vehicle driving control method.

[0006] The vehicle driving control method provided by the present application includes:

[0007] Obtaining surrounding environment information during vehicle driving;

[0008] Based on the surrounding environment information, it is predicted whether there is a trend of accident occurrence;

[0009] If there is a trend of accident occurrence, based on the surrounding environment information, the injury degree of each accident influencing factor when the accident occurs is determined; wherein the surrounding environment information at least includes one of the following: vehicle speed, front vehicle speed, rear vehicle speed and opposite vehicle speed;

[0010] Based on the injury degree of each accident influencing factor when the accident occurs, the weight adjustment of each accident influencing factor in the decision model is carried out; wherein the decision model is constructed based on the injury evaluation of each accident influencing factor to the vehicle;

[0011] Based on the weight-adjusted decision model, the vehicle avoidance driving strategy is output.

[0012] In some examples,

[0013] The determination of the injury degree of each accident influencing factor when the accident occurs based on the surrounding environment information includes:

[0014] analyzing a moving state of each vehicle at the time of the accident based on the self-vehicle speed, the front-vehicle speed, the rear-vehicle speed, and the oncoming-vehicle speed;

[0015] determining a damage degree of each accident influencing factor at the time of the accident based on the moving state of each vehicle at the time of the accident.

[0016] In some examples, the determining the damage degree of each accident influencing factor at the time of the accident based on the moving state of each vehicle at the time of the accident includes:

[0017] if the front vehicle and the oncoming vehicle have the accident, and the oncoming-vehicle speed is greater than a first threshold value and the front-vehicle speed and the rear-vehicle speed are less than a second threshold value, determining that the front vehicle has a greater damage degree than the rear vehicle at the time of the accident;

[0018] if the front vehicle and the oncoming vehicle have the accident, and the oncoming-vehicle speed and the front-vehicle speed are less than the second threshold value and the rear-vehicle speed is greater than the first threshold value, determining that the rear vehicle has a greater damage degree than the front vehicle at the time of the accident;

[0019] if the front vehicle and the oncoming vehicle have the accident, and the oncoming-vehicle speed is less than the second threshold value and the front-vehicle speed and the rear-vehicle speed are greater than the first threshold value, determining that the rear vehicle has a greater damage degree than the front vehicle at the time of the accident;

[0020] if the front vehicle and the oncoming vehicle have the accident, and the oncoming-vehicle speed and the front-vehicle speed are greater than the first threshold value and the rear-vehicle speed is less than the second threshold value, determining that the front vehicle has a greater damage degree than the rear vehicle at the time of the accident;

[0021] if the front vehicle and the oncoming vehicle do not have the accident, and the self-vehicle speed is greater than the first threshold value and the rear-vehicle speed is less than the second threshold value, determining that the oncoming vehicle has a greater damage degree than the rear vehicle at the time of the accident;

[0022] if the front vehicle and the oncoming vehicle do not have the accident, and the self-vehicle speed is less than the second threshold value and the rear-vehicle speed is greater than the first threshold value, determining that the rear vehicle has a greater damage degree than the oncoming vehicle at the time of the accident; wherein the first threshold value is greater than the second threshold value.

[0023] In some examples, the determining the damage degree of each accident influencing factor at the time of the accident based on the moving state of each vehicle at the time of the accident includes:

[0024] sorting the damage degree of each accident influencing factor at the time of the accident in descending order of the damage degree;

[0025] Based on the ranking of the degree of harm of each accident influencing factor at the time of the accident, the weights of each accident influencing factor in the decision-making model are adjusted.

[0026] In some instances, the decision model is:

[0027] U 策略 =W 自 V 自 +W 前 V 前 +W 后 V 后 +W 对 V 对 +W 周1 V 周1 +W 周2 V 周2 +……W 周n V 周n +B 偏置 ; wherein, the V 自 For vehicle speed, W 自 For vehicle weight, V 前 For the speed of the vehicle in front, W 前 Weight of the preceding vehicle, V 后 For the speed of the following vehicle, W 后 Weighting of following vehicles, V 对 For oncoming vehicle speed, W 对 Weighting of oncoming vehicles, V 周1 V 周2 and V 周n All are the speeds of surrounding vehicles, W 周1 W 周2 and W 周n All are weighted by surrounding vehicles, B 偏置 The impact of external environmental factors on the vehicle;

[0028] The adjustment of the weights of each accident influencing factor in the decision-making model based on the degree of harm of each accident influencing factor at the time of the accident includes:

[0029] If it is determined that the damage caused by the vehicle in front is greater than that caused by the vehicle behind at the time of the accident, then the weight of the vehicle in front will be increased and the weight of the vehicle behind will be decreased.

[0030] If it is determined that the degree of damage to the rear vehicle is greater than that to the front vehicle at the time of the accident, then the weight of the front vehicle is reduced and the weight of the rear vehicle is increased.

[0031] If it is determined that the oncoming vehicle causes more damage than the following vehicle at the time of the accident, then the weight of the oncoming vehicle will be increased and the weight of the following vehicle will be decreased.

[0032] If it is determined that the rear vehicle has a greater degree of injury than the oncoming vehicle when the accident occurs, the weight of the oncoming vehicle is reduced and the weight of the rear vehicle is increased.

[0033] In some examples, the decision model based on the weight adjustment outputs a vehicle avoidance driving strategy, including:

[0034] U 策略 =W 自 V 自 +W 前 V 前 +W 后 V 后 +W 对 V 对 +W 周1 V 周1 +W 周2 V 周2 +……W 周n V 周n +B 偏置 , divided into:

[0035] U X策略 =W 自 V 自 COSθ+W 前 V 前 COSθ+W 后 V 后 COSθ + W 对 V 对 COSθ+W 周1 V 周1 COSθ+W 周2 V 周2 COSθ+……W 周 n V 周n COSθ+B 偏置 ; wherein U X策略 is a vehicle lateral control strategy, V 自 is a vehicle speed, V 自 is a vehicle speed, W 自 is a vehicle weight, V 前 is a front vehicle speed, W 前 is a front vehicle weight, V 后 is a rear vehicle speed, W 后 is a rear vehicle weight, V 对 is an oncoming vehicle speed, W 对 is an oncoming vehicle weight, V 周1 , V 周2 , and V 周n are surrounding vehicle speeds, W 周1 , W 周2 , and W 周nare all peripheral vehicle weights, B 偏置 is an environmental factor outside the vehicle affecting the ego vehicle, COSθ represents the influence degree of the motion direction of the traffic participant on the lateral position of the ego vehicle;

[0036] U y策略 = W 自 V 自 SINθ + W 前 V 前 SINθ + W 后 V 后 SINθ + W 对 V 对 SINθ + W 周1 V 周1 SINθ + W 周2 V 周2 SINθ + …… W 周 n V 周n SINθ + B 偏置 ; wherein, U y策略 is a vehicle longitudinal control strategy, and SINθ represents the influence degree of the motion direction of the traffic participant on the longitudinal position of the ego vehicle.

[0037] In some examples, the decision model adjusted based on the weight outputs a vehicle avoidance driving strategy, including:

[0038] The decision model adjusted based on the weight outputs one of the following strategies:

[0039] an ego vehicle left turn strategy, an ego vehicle right turn strategy, an ego vehicle acceleration strategy, an ego vehicle deceleration strategy, and a stationary strategy.

[0040] In some examples, the surrounding environment information further includes:

[0041] an overhead view of the surrounding environment;

[0042] The prediction of whether there is a trend of accident occurrence based on the surrounding environment information includes:

[0043] obtaining relative position relationships of the ego vehicle, a front vehicle, a rear vehicle, and an oncoming vehicle through the overhead view;

[0044] predicting whether there is a trend of accident occurrence based on the relative position relationships of the ego vehicle, the front vehicle, the rear vehicle, and the oncoming vehicle, ego vehicle speed, front vehicle speed, rear vehicle speed, and oncoming vehicle speed.

[0045] The second aspect of the embodiment of the application provides a vehicle control device for executing the vehicle driving control method described in the first aspect, and the vehicle control device includes:

[0046] a perception module for obtaining surrounding environment information during vehicle driving.

[0047] an identification module configured to identify a person, a vehicle, a lane line, a traffic sign and a traffic light based on the surrounding environment information;

[0048] a distance judgment module configured to judge distances between the ego vehicle and a front vehicle, a rear vehicle and an oncoming vehicle based on the surrounding environment information;

[0049] a speed judgment module configured to judge speeds of the ego vehicle, the front vehicle, the rear vehicle and the oncoming vehicle based on the surrounding environment information;

[0050] a collision analysis module configured to predict whether there is a trend of an accident based on the surrounding environment information;

[0051] a subsequent collision probability and impact consequence analysis module configured to, if there is the trend of the accident, determine injury degrees of each accident influencing factor when the accident occurs based on the surrounding environment information;

[0052] a decision module configured to adjust weights of each accident influencing factor in a decision model based on the injury degrees of each accident influencing factor when the accident occurs, and output a vehicle avoidance driving strategy based on the decision model after the weight adjustment.

[0053] A third aspect of the embodiment of the present application provides a vehicle comprising the vehicle control device of the second aspect.

[0054] The vehicle driving control method of the present application comprises: obtaining surrounding environment information in a vehicle driving process; predicting whether there is a trend of an accident based on the surrounding environment information; if there is the trend of the accident, determining injury degrees of each accident influencing factor when the accident occurs based on the surrounding environment information; adjusting weights of each accident influencing factor in a decision model based on the injury degrees of each accident influencing factor when the accident occurs; and outputting a vehicle avoidance driving strategy based on the decision model after the weight adjustment. In the present application, the weights of each accident influencing factor in the decision model are adjusted based on the injury degrees of each accident influencing factor when the accident occurs, and the vehicle avoidance driving strategy is outputted based on the decision model after the weight adjustment, which is conducive to making the vehicle tend to drive in a direction of the lightest injury, thereby improving the vehicle driving safety. BRIEF DESCRIPTION OF DRAWINGS

[0055] Figure 1 A vehicle driving control method flow chart is provided for the embodiment of the present application;

[0056] Figure 2 A vehicle driving accident trend schematic diagram is provided for the embodiment of the present application;

[0057] Figure 3A vehicle control device structure schematic diagram provided by the embodiment of the present application. DETAILED DESCRIPTION

[0058] In order to better explain the present application, in order to facilitate understanding, the following will be combined with the drawings, through the specific embodiments, the present application is described in detail.

[0059] The vehicle driving control method provided by the embodiment of the present application is used to solve the problem of how to improve the safety of automatic driving, the weight adjustment of each accident influencing factor in the decision model is carried out through the injury degree of each accident influencing factor when the accident occurs, and the vehicle avoidance driving strategy is output based on the decision model after the weight adjustment, which is conducive to making the vehicle tend to drive in the direction of the lightest injury, thereby improving the driving safety of the vehicle.

[0060] In order to better understand the above technical solutions, the exemplary embodiments of the present application will be described in more detail below with reference to the drawings. Although the exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a clearer, more thorough understanding of the present application and to enable the scope of the present application to be fully conveyed to those skilled in the art.

[0061] Figure 1 A vehicle driving control method flow chart provided by the embodiment of the present application. As shown in Figure 1 The vehicle driving control method provided by the embodiment of the present application comprises:

[0062] Step 100, acquiring surrounding environment information in the vehicle driving process;

[0063] Step 110, predicting whether there is a trend of accident occurrence based on the surrounding environment information;

[0064] Step 120, if there is a trend of accident occurrence, determining the injury degree of each accident influencing factor when the accident occurs based on the surrounding environment information; wherein the surrounding environment information at least includes one of the following: vehicle speed, front vehicle speed, rear vehicle speed and opposite vehicle speed;

[0065] Step 130, based on the injury degree of each accident influencing factor when the accident occurs, the weight adjustment of each accident influencing factor in the decision model is carried out; wherein the decision model is constructed based on the injury evaluation of each accident influencing factor to the vehicle;

[0066] Step 140, outputting the vehicle avoidance driving strategy based on the decision model after the weight adjustment.

[0067] In the embodiment, the chain reaction after the vehicle collision causes greater subsequent injury, how to avoid the subsequent injury is crucial, and the scene needs to be processed through the vehicle and the road side information and situation, and the vehicle itself also needs to be improved to avoid greater injury and cause serious traffic accident consequences.

[0068] For example, the road surface and surrounding traffic sign situation are analyzed by bird's eye view, the motion trajectory of the vehicle and the human body within 30 meters is tracked in real time, and then comprehensive judgment is performed,

[0069] If the behavior should be performed according to the traffic rules, the abnormal behavior of the related vehicle and human body in operation is observed. For example, in the most complex traffic section at the intersection, the abnormal behavior of the human body and the three-wheeled vehicle and the two-wheeled vehicle must be observed at all times, such as running a red light;

[0070] Then if the related abnormality occurs, several coping strategies are triggered in time, first, the safety of the vehicle itself is ensured, second, the safety of the opposite vehicle and the pedestrian is ensured, then the safety of the nearby traffic participants is observed, and the most reasonable coping strategy is determined. For example, the above embodiment may need to first ensure the safety of the vehicle itself, the object and other traffic participants.

[0071] In the embodiment, the surrounding environment information can include vehicle, personnel, lane line, traffic sign and traffic light information. The surrounding environment information can be obtained through various sensors such as cameras, laser radars and millimeter wave radars.

[0072] In the application, the vehicle driving control method is applied to an automatic driving system. Through the automatic driving system, data collection and judgment are autonomously performed. The weight of each accident influencing factor in the decision model is adjusted based on the injury degree of each accident influencing factor when an accident occurs. Based on the decision model after the weight adjustment, a vehicle avoidance driving strategy is output, which is conducive to making the vehicle tend to drive in the direction of the lightest injury, thereby improving the vehicle driving safety.

[0073] In some examples, the determination of the injury degree of each accident influencing factor when an accident occurs based on the surrounding environment information includes:

[0074] Based on the speed of the ego vehicle, the speed of the front vehicle, the speed of the rear vehicle and the speed of the oncoming vehicle, the moving state of each vehicle when an accident occurs is analyzed;

[0075] Based on the moving state of each vehicle when an accident occurs, the injury degree of each accident influencing factor when an accident occurs is determined.

[0076] In the embodiment, Figure 2 A vehicle driving accident occurrence trend diagram is provided for the embodiment of the application. As shown in Figure 2As shown, the more important information in the surrounding environment information includes the vehicle speed of the ego vehicle, the vehicle speed of the front vehicle, the vehicle speed of the rear vehicle, and the vehicle speed of the oncoming vehicle. Among them, the faster the vehicle speed, the greater the damage assessment to the ego vehicle. Therefore, by evaluating the vehicle speed, the damage assessment of each accident influencing factor to the ego vehicle is performed, and then a decision model is constructed.

[0077] In some examples, the determination of the damage degree of each accident influencing factor at the time of the accident based on the movement state of each vehicle at the time of the accident includes:

[0078] If the front vehicle and the oncoming vehicle have an accident, and the speed of the oncoming vehicle is greater than a first threshold value, and the speeds of the front vehicle and the rear vehicle are less than a second threshold value, it is determined that the damage degree of the front vehicle at the time of the accident is greater than the damage degree of the rear vehicle at the time of the accident.

[0079] If the front vehicle and the oncoming vehicle have an accident, and the speed of the oncoming vehicle and the speed of the front vehicle are less than a second threshold value, and the speed of the rear vehicle is greater than a first threshold value, it is determined that the damage degree of the rear vehicle at the time of the accident is greater than the damage degree of the front vehicle at the time of the accident.

[0080] If the front vehicle and the oncoming vehicle have an accident, and the speed of the oncoming vehicle is less than a second threshold value, and the speeds of the front vehicle and the rear vehicle are greater than a first threshold value, it is determined that the damage degree of the rear vehicle at the time of the accident is greater than the damage degree of the front vehicle at the time of the accident.

[0081] If the front vehicle and the oncoming vehicle have an accident, and the speed of the oncoming vehicle and the speed of the front vehicle are greater than a first threshold value, and the speed of the rear vehicle is less than a second threshold value, it is determined that the damage degree of the front vehicle at the time of the accident is greater than the damage degree of the rear vehicle at the time of the accident.

[0082] If the front vehicle and the oncoming vehicle do not have an accident, and the speed of the ego vehicle is greater than a first threshold value, and the speed of the rear vehicle is less than a second threshold value, it is determined that the damage degree of the oncoming vehicle at the time of the accident is greater than the damage degree of the rear vehicle at the time of the accident.

[0083] If the front vehicle and the oncoming vehicle do not have an accident, and the speed of the ego vehicle is less than a second threshold value, and the speed of the rear vehicle is greater than a first threshold value, it is determined that the damage degree of the rear vehicle at the time of the accident is greater than the damage degree of the oncoming vehicle at the time of the accident. The first threshold value is greater than the second threshold value.

[0084] In the embodiment, as shown in Figure 2As shown, if an accident occurs between the vehicle in front and the oncoming vehicle, and the oncoming vehicle's speed is greater than a first threshold while both the speeds of the vehicles in front and behind are less than a second threshold, it indicates that the impact of the oncoming vehicle on the vehicle in front is relatively large. Therefore, the assessed damage to the vehicle from the impact of the oncoming vehicle on the vehicle in front is greater. Since the vehicle behind is traveling slower, the assessed damage from the oncoming vehicle on the vehicle in front is greater than that from the vehicle behind. Therefore, the weight of the vehicle in front can be increased while the weight of the vehicle behind can be decreased. The vehicle in front can then avoid the collision by slowing down.

[0085] If an accident occurs between the vehicle in front and the oncoming vehicle, and both the speeds of the oncoming vehicle and the vehicle in front are less than the second threshold, while the speed of the vehicle behind is greater than the first threshold, it indicates that the impact of the oncoming vehicle on the vehicle in front is relatively small, while the impact of the vehicle behind on the vehicle is relatively large. Therefore, in this case, the weight of the vehicle in front can be reduced and the weight of the vehicle behind can be increased. The vehicle can then avoid the accident by steering. Other situations are similar to the above. By analyzing the damage assessment caused by the vehicles to the vehicle, the vehicle weight values ​​are adjusted to generate a control strategy for vehicle driving control.

[0086] In some instances, the decision model is:

[0087] U 策略 =W 自 V 自 +W 前 V 前 +W 后 V 后 +W 对 V 对 +W 周1 V 周1 +W 周2 V 周2 +……W 周n V 周n +B 偏置 ; wherein, the V 自 For vehicle speed, W 自 For vehicle weight, V 前 For the speed of the vehicle in front, W 前 Weight of the preceding vehicle, V 后 For the speed of the following vehicle, W 后 Weighting of following vehicles, V 对 For oncoming vehicle speed, W 对 Weighting of oncoming vehicles, V 周1 V 周2 and V 周n All are the speeds of surrounding vehicles, W 周1 W 周2 and W 周n All are weighted by surrounding vehicles, B 偏置 The impact of external environmental factors on the vehicle;

[0088] The weight adjustment of each accident influence factor in the decision model is based on the injury degree of each accident influence factor when the accident occurs, and includes:

[0089] If it is determined that the injury degree of the front vehicle is greater than that of the rear vehicle when the accident occurs, the weight of the front vehicle is increased and the weight of the rear vehicle is decreased;

[0090] If it is determined that the injury degree of the rear vehicle is greater than that of the front vehicle when the accident occurs, the weight of the front vehicle is decreased and the weight of the rear vehicle is increased;

[0091] If it is determined that the injury degree of the oncoming vehicle is greater than that of the rear vehicle when the accident occurs, the weight of the oncoming vehicle is increased and the weight of the rear vehicle is decreased;

[0092] If it is determined that the injury degree of the rear vehicle is greater than that of the oncoming vehicle when the accident occurs, the weight of the oncoming vehicle is decreased and the weight of the rear vehicle is increased.

[0093] In the embodiment, the output U of the vehicle control strategy in the decision model is related to the weight of each accident influence factor. 策略 By adjusting the weight of each accident influence factor, different vehicle control strategies are output. For example, if the weight of the front vehicle is increased, the ego vehicle can output a control strategy to avoid the front vehicle. If the weight of the rear vehicle is increased, the ego vehicle can output a control strategy to avoid the rear vehicle. In this way, the driving safety of the ego vehicle when encountering an accident can be improved.

[0094] In some examples, the weight adjustment of each accident influence factor in the decision model is based on the injury degree of each accident influence factor when the accident occurs, and includes:

[0095] The injury degree of each accident influence factor when the accident occurs is sorted from large to small according to the injury degree;

[0096] The weight adjustment of each accident influence factor in the decision model is based on the sorting of the injury degree of each accident influence factor when the accident occurs.

[0097] In the embodiment, the decision model is used to output the control strategy of the ego vehicle (i.e., the vehicle avoidance driving strategy), and the injury degree of each accident influence factor is considered to preferentially avoid the vehicle with the greatest injury degree, thereby improving the driving safety of the vehicle. Based on the weight-adjusted decision model, the vehicle avoidance driving strategy includes:

[0098] In necessary cases, secondary injury or continuous collision can be considered to output a comprehensive avoidance strategy. The comprehensive avoidance strategy can include a first vehicle avoidance driving strategy and a second vehicle avoidance driving strategy.

[0099] In some examples, the decision model based on the weight adjustment outputs a vehicle avoidance driving strategy, including:

[0100] U 策略 =W 自 V 自 +W 前 V 前 +W 后 V 后 +W 对 V 对 +W 周1 V 周1 +W 周2 V 周2 +……W 周n V 周n +B 偏置 , divided into:

[0101] U X策略 =W 自 V 自 COSθ+W 前 V 前 COSθ+W 后 V 后 COSθ + W 对 V 对 COSθ+W 周1 V 周1 COSθ+W 周2 V 周2 COSθ+……W 周 n V 周n COSθ+B 偏置 ; wherein, the V 自 is the vehicle speed, W 自 is the vehicle weight, V 前 is the front vehicle speed, W 前 is the front vehicle weight, V 后 is the rear vehicle speed, W 后 is the rear vehicle weight, V 对 is the opposite vehicle speed, W 对 is the opposite vehicle weight, V 周1 , V 周2 and V 周n are all surrounding vehicle speeds, W 周1 , W 周2 and W 周n are all surrounding vehicle weights, B 偏置 is the influence of the environment outside the vehicle on the vehicle, and COSθ represents the influence degree of the motion direction of the traffic participant on the lateral position of the vehicle.

[0102] Uy策略 =W 自 V 自 SINθ+W 前 V 前 SINθ+W 后 V 后 SINθ +W 对 V 对 SINθ+W 周1 V 周1 SINθ+W 周2 V 周2 SINθ+……W 周 n V 周n SINθ +B 偏置 SINθ represents the degree to which the direction of motion of a traffic participant affects the longitudinal position of the vehicle.

[0103] In this exemplary embodiment, the vehicle control strategy U 策略 Lateral and longitudinal decomposition is possible. COSθ represents the influence of the traffic participants' movement direction on the vehicle's lateral position, while SINθ represents the influence of the traffic participants' movement direction on the vehicle's longitudinal position. When COSθ=1, the influence of the traffic participants' movement direction on the vehicle's left-side collision damage is greatest; when COSθ=-1, the influence of the traffic participants' movement direction on the vehicle's right-side collision damage is greatest. In these cases, when generating the vehicle's control strategy, avoidance maneuvers to prevent left-side or right-side collisions can be implemented, such as lateral steering avoidance maneuvers. X策略 .

[0104] When SINθ=1, the direction of movement of traffic participants has the greatest impact on the longitudinal position of the vehicle in a frontal collision, while when SINθ=-1, the direction of movement of traffic participants has the greatest impact on the longitudinal position of the vehicle in a rearal collision. In these cases, when generating the vehicle control strategy, avoidance maneuvers to prevent frontal or rearal collisions can be implemented, such as longitudinal acceleration or deceleration avoidance maneuvers. y策略 Therefore, by comprehensively considering U X策略 and U y策略， This determines the final vehicle control strategy.

[0105] For example, if the vehicle is stopped by braking, and the vehicle speed V > Vmax, considering that the vehicle and the oncoming vehicle will collide at high speed, the vehicle should not continue to accelerate and crash, as this will cause more serious injuries to the tricycle driver.

[0106] When the vehicle speed V < Vmax, and the vehicle deceleration, considering traffic rules, to prevent rear-end collision. The vehicle should be normal speed deceleration, to give the rear car enough space, to ensure that the vehicle as little as possible to be hit by the front and rear damage. Also to ensure the safety of the rear car and their own safety.

[0107] When the vehicle suddenly turn to the right to avoid the opposite car, so the vehicle may be directly facing the collision of the opposite car. If the vehicle speed V > Vmax, this should try to slow down. At the same time can not change line, to prevent and side collision. At the same time to consider the rear car, to avoid the right can also be slightly turn, to give the rear car space, to avoid the vehicle after the damage.

[0108] When the vehicle suddenly turn to the right to avoid the opposite car, so the vehicle may be directly facing the collision of the opposite car. If the vehicle speed V < Vmax, this should slow down and observe the surrounding, while considering the rear car, to avoid the right can also be slightly turn, to give the rear car space, to avoid the vehicle after the damage.

[0109] At the same time to consider the variance and the determination of the loss function, in the real strategy of the actual driving speed V and the ideal planning speed V has a deviation, need to be considered in the actual deviation. The difference between the two is as follows: 策略 The variance is as follows:

[0110] 策略 = W x自 (V x自实 -V x自理 ) 2 COSθ + W x前 (V x前实 -V x前自 ) 2 COSθ + W x后 (V x后实 -V x后理 ) 2 COSθ + W x对 (V x对实 -V x对理 ) 2 COSθ + W x周1 (V x周1实 -V x周1理 ) 2 COSθ + … W x周n (V x周n实 -V x周n理 ) 2 COSθ + B 偏置 ;

[0111] Where, W x自 is the weight of the vehicle in the lateral, W x前W is the weight of the front vehicle in the lateral direction x后 W is the weight of the rear vehicle in the lateral direction x对 W is the weight of the oncoming vehicle in the lateral direction x周1 ~W x周n W are the weights of the surrounding vehicles in the lateral direction; V x自实 V is the actual speed of the ego vehicle in the lateral direction x前实 V is the actual speed of the front vehicle in the lateral direction x后实 V is the actual speed of the rear vehicle in the lateral direction x对实 V is the actual speed of the oncoming vehicle in the lateral direction x周1实 ~ V x周n实 V are the actual speeds of the surrounding vehicles in the lateral direction; V x自理 V is the theoretical planning speed of the ego vehicle in the lateral direction x前理 V is the theoretical planning speed of the front vehicle in the lateral direction x后理 V is the theoretical planning speed of the rear vehicle in the lateral direction x对理 V is the theoretical planning speed of the oncoming vehicle in the lateral direction x周1理 ~ V x周n理 V are the theoretical planning speeds of the surrounding vehicles in the lateral direction, B 偏置 COS is the influence of the external environmental factors on the ego vehicle, COS represents the degree of influence of the motion direction of the traffic participant on the lateral position of the ego vehicle.

[0112] 策略 The variances are as follows:

[0113] 策略 =W y自 (V y自实 -V y自理 ) 2 SIN +W y前 (V y前实 -V y前自 ) 2 SIN +W y后 (V y后实 -V y后理 ) 2 SIN +W y对 (V y对实 -V y对理 ) 2 SIN +W y周1 (V y周1实 -V y周1理 ) 2 SIN +…W y周n (V y周n实 -V y周n理 ) 2 SIN +B 偏置 ; wherein W y自W is the weight of the ego vehicle in the longitudinal direction y前 W is the weight of the front vehicle in the longitudinal direction y后 W is the weight of the rear vehicle in the longitudinal direction y对 W is the weight of the oncoming vehicle in the longitudinal direction y周1 W y周n W are the weights of the surrounding vehicles in the longitudinal direction; V y自实 V is the actual speed of the ego vehicle in the longitudinal direction y前实 V is the actual speed of the front vehicle in the longitudinal direction y后实 V is the actual speed of the rear vehicle in the longitudinal direction y对实 V is the actual speed of the oncoming vehicle in the longitudinal direction y周1实 V y周n实 V are the actual speeds of the surrounding vehicles in the longitudinal direction; V y自理 V is the theoretical planning speed of the ego vehicle in the longitudinal direction y前理 V is the theoretical planning speed of the front vehicle in the longitudinal direction y后理 V is the theoretical planning speed of the rear vehicle in the longitudinal direction y对理 V is the theoretical planning speed of the oncoming vehicle in the longitudinal direction y周1理 V y周n理 SIN are the theoretical planning speeds of the surrounding vehicles in the lateral direction; SIN represents the degree of influence of the motion direction of the traffic participants on the longitudinal position of the ego vehicle

[0114] To reduce variance and improve the overall actual optimization of the execution strategy, it is necessary to reduce the loss in this process, which involves the loss function problem.

[0115] First, the deviation values in the X and Y directions are combined as follows:

[0116] = ( 策略 COS) 2 + 策略 2 ; wherein, is the comprehensive deviation of the vehicle control strategy in the X and Y directions.

[0117] The comprehensive deviation can be optimized to be minimum by gradient descent method.

[0118] At the same time, when executing the ego vehicle control strategy, the lateral speed deviation and the longitudinal speed deviation can be considered by combining 策略 and 策略 .

[0119] U X策略 = W自 V 自 COSθ+W 前 V 前 COSθ+W 后 V 后 COSθ +W 对 V 对 COSθ+W 周1 V 周1 COSθ+W 周2 V 周2 COSθ+……W 周 n V 周n COSθ+B 偏置 + 策略 ;

[0120] U y策略 =W 自 V 自 SINθ+W 前 V 前 SINθ+W 后 V 后 SINθ +W 对 V 对 SINθ+W 周1 V 周1 SINθ+W 周2 V 周2 SINθ+……W 周 n V 周n SINθ+B 偏置 + 策略 。

[0121] In some examples, the decision model based on the weight adjustment outputs a vehicle avoidance driving strategy, including:

[0122] The decision model based on the weight adjustment outputs one of the following strategies:

[0123] A left turn strategy of the ego vehicle, a right turn strategy of the ego vehicle, an acceleration strategy of the ego vehicle, a deceleration strategy of the ego vehicle, and a stationary strategy.

[0124] In the embodiment, when there is a right-side collision injury, the decision model can output a left turn strategy of the ego vehicle. When there is a left-side collision injury, the decision model can output a right turn strategy of the ego vehicle. When there is a front collision injury, the decision model can output a deceleration strategy of the ego vehicle. When there is a rear collision injury, the decision model can output an acceleration strategy of the ego vehicle, and so on. In this way, the driving safety of the vehicle can be effectively improved.

[0125] The decision model based on the weight adjustment outputs a vehicle avoidance driving strategy, including:

[0126] minimizing the target optimization function is optimized as a condition, combined with a decision model, to output a vehicle avoidance driving strategy; wherein,

[0127] the decision model is:

[0128] U 策略 =W 自 exp(α 自 V 自 )+W 前 exp(α 前 V 前 )+W 后 exp(α 后 V 后 )+W 对 exp(α 对 V 对 )+W 周1 exp(α 周1 V 周1 )+W 周2 exp(α 周2 V 周2 )...+B 偏置 ;

[0129] W 自 is a self-vehicle weight, V 前 is a front-vehicle speed, W 前 is a front-vehicle weight, V 后 is a rear-vehicle speed, W 后 is a rear-vehicle weight, V 对 is a counter-vehicle speed, W 对 is a counter-vehicle weight, V 周1 , V 周2 , and V 周n are surrounding-vehicle speeds, W 周1 , W 周2 , and W 周n are surrounding-vehicle weights, and B 偏置 is an environmental factor outside the vehicle affecting the self-vehicle.

[0130] Here, α 自 , α 前 , α 后 , α 对 , α周1 , a 周2 are hyperparameters that control the sensitivity of speed to risk;

[0131] wherein the target optimization function is ;

[0132] wherein, ; is the risk target function; is the real-time adjustment weight of the traffic participant in the decision model; is the current speed of the traffic participant; is the predicted probability of a collision between the ego vehicle and the traffic participant, which is estimated based on the relative distance, relative speed, and motion direction (represented by factors such as COS0, SIN0, etc.) between the two. The traffic participant includes the front vehicle, rear vehicle, oncoming vehicle, surrounding vehicle, etc.

[0133] wherein the comfort target function is ;

[0134] ; is the longitudinal acceleration of the ego vehicle; is the longitudinal jerk (rapid acceleration) of the ego vehicle; is the lateral acceleration of the ego vehicle.

[0135] wherein the efficiency target function is ; ; is the predicted time for the ego vehicle to travel to the target point based on the current strategy.

[0136] wherein λ1, λ2, and λ3 are pre-set non-negative coefficients for adjusting the importance of risk, comfort, and efficiency in the overall optimization target, and satisfy λ1+λ2+λ3=1.

[0137] In the case of high accident risk prediction, the system will dynamically increase λ1 (safety weight) to prioritize safety.

[0138] The system solves the minimum value of the above multi-objective optimization function, selects the action that minimizes the target function value from the feasible action set (such as ego vehicle left turn, right turn, acceleration, deceleration, keep, etc.), and outputs the final vehicle avoidance driving strategy.

[0139] In some examples, the surrounding environment information further includes:

[0140] an overhead view of the surrounding environment;

[0141] The prediction of whether there is a trend of accident occurrence based on the surrounding environment information includes:

[0142] obtaining, by the bird's eye view, relative position relationships of the ego vehicle, the front vehicle, the rear vehicle and the oncoming vehicle;

[0143] predicting, based on the relative position relationships of the ego vehicle, the front vehicle, the rear vehicle, the oncoming vehicle, ego vehicle speed, front vehicle speed, rear vehicle speed and oncoming vehicle speed, whether there is a trend of an accident.

[0144] In the embodiment, the bird's eye view is used to analyze the road surface and the surrounding traffic sign situation, the motion trajectories of vehicles and human bodies within 30 meters are tracked in real time, and then a comprehensive judgment is made to analyze the relative position relationships of the ego vehicle, the front vehicle, the rear vehicle and the oncoming vehicle, etc.

[0145] In some examples, the vehicle control device 20 comprises:

[0146] After determining the vehicle avoidance driving strategy, the vehicle avoidance instruction is issued by the VCU or the MCU, the control electrical signal is sent to the steering module, the acceleration module or the deceleration and braking module by the linear control system, and the vehicle avoidance action is executed.

[0147] In the embodiment, for the aforementioned collision analysis, the optimal execution strategy and execution parameters are determined, the instruction is issued by the VCU or the MCU, the control electrical signal is sent to the steering, acceleration, deceleration and braking modules by the linear control system, the related action is executed, and whether the action is appropriate and whether the personnel safety and the minimized collision consequences are ensured are confirmed by the perception and recognition module.

[0148] In the embodiment, when the vehicle is at an intersection or a two-lane road and there are other vehicles on the left and right sides, the weight W 周1 , W 周2 , etc. of the surrounding vehicles can be comprehensively considered when the ego vehicle control strategy is specifically generated. In this way, the decision model generates the ego vehicle control strategy which is more reasonable and more conducive to improving the vehicle safety.

[0149] The embodiment of the present application provides a vehicle control device which executes the vehicle driving control method described in each of the above embodiments. Figure 3 The vehicle control device structure schematic diagram provided by the embodiment of the present application is shown in FIG. 2. As shown in FIG. 2, the vehicle control device 20 comprises: Figure 3

[0150] The perception sub-module 201 is configured to obtain the surrounding environment information in the vehicle driving process.

[0151] The recognition sub-module 202 is configured to recognize people, vehicles, lane lines, traffic signs and traffic lights based on the surrounding environment information. ​

[0152] The distance determination module 203 is configured to determine distances between the ego vehicle and the front vehicle, the rear vehicle, and the oncoming vehicle based on the surrounding environment information.

[0153] The speed determination module 204 is configured to determine speeds of the ego vehicle, the front vehicle, the rear vehicle, and the oncoming vehicle based on the surrounding environment information.

[0154] The collision analysis module 205 is configured to predict whether there is a trend of an accident based on the surrounding environment information.

[0155] The subsequent collision probability and impact consequence analysis module 206 is configured to determine degrees of injury of each accident influencing factor in the event of an accident based on the surrounding environment information if there is a trend of an accident.

[0156] The decision module 207 is configured to adjust weights of each accident influencing factor in a decision model based on the degrees of injury of each accident influencing factor in the event of an accident, and output a vehicle evasive driving strategy based on the decision model after the weight adjustment.

[0157] In the present embodiment, the chain reaction after the vehicle collision leads to greater subsequent injury, and it is crucial to avoid the subsequent injury. The scene is processed by means of vehicle and roadside information and conditions, and the vehicle itself is also improved to avoid greater injury and serious consequences of traffic accidents.

[0158] For example, the situation of the road surface and the surrounding traffic signs is analyzed by bird's eye view, the motion trajectories of vehicles and human bodies within 30 meters are tracked in real time, and then a comprehensive judgment is made.

[0159] If the behavior should be performed according to the traffic rules, the behaviors of the relevant vehicles and human bodies in operation are observed in real time. For example, in the most complex traffic section at the intersection, the abnormal behaviors of people and three-wheeled and two-wheeled vehicles, such as running a red light, must be observed at all times.

[0160] Then, if the relevant abnormal behaviors occur, several coping strategies are triggered in a timely manner. First, the safety of the ego vehicle is ensured, and then the safety of the opponent vehicle and the pedestrian is ensured. Then, the safety of the nearby traffic participants is observed, and the most reasonable coping strategy is determined. For example, in the above embodiment, the ego vehicle, the object, and other traffic participants may need to be ensured first.

[0161] In the present embodiment, the surrounding environment information can include vehicle, personnel, lane line, traffic sign, and traffic light information. The surrounding environment information can be obtained by various sensors such as cameras, laser radars, and millimeter wave radars.

[0162] In the present application, the weight of each accident influencing factor in the decision model is adjusted according to the injury degree of each accident influencing factor when the accident occurs; and the vehicle avoidance driving strategy is output based on the decision model after the weight adjustment, which is beneficial to make the vehicle tend to drive in the direction of the lightest injury, thereby improving the vehicle driving safety.

[0163] Since the system / device for implementing the method of the above-mentioned embodiments of the present application is described in the above-mentioned embodiments of the present application, the specific structure and modification of the system / device can be understood by those skilled in the art based on the method described in the above-mentioned embodiments of the present application, and thus will not be described here. Any system / device used in the method of the above-mentioned embodiments of the present application belongs to the scope of the present application.

[0164] The embodiment of the present application provides a vehicle comprising the vehicle control device described in the above-mentioned embodiments.

[0165] In the description of the present application, it should be understood that the terms "first", "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features limited by "first", "second" can be explicitly or implicitly included one or more features. In the description of the present application, the meaning of "multiple" is two or more, unless otherwise specifically limited.

[0166] In the present application, unless otherwise specifically defined and limited, the terms "mounting", "connection", "connection", "fixing" and the like should be understood in a broad sense, for example, it can be fixed connection, or detachable connection, or integrated; it can be mechanical connection, or electrical connection; it can be directly connected, or indirectly connected through intermediate medium; it can be the internal communication of two elements or the interaction relationship between two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0167] In the present application, unless otherwise specifically defined and limited, the first feature is "on" or "under" the second feature, which can be direct contact between the first and second features, or indirect contact between the first and second features through intermediate medium. Moreover, the first feature "above", "above" and "above" the second feature, can be directly above or obliquely above the first feature, or only indicate that the horizontal height of the first feature is higher than that of the second feature. The first feature "below", "below" and "below" the second feature, can be directly below or obliquely below the first feature, or only indicate that the horizontal height of the first feature is lower than that of the second feature.

[0168] In the description of the specification, the description of the terms "one embodiment", "some embodiments", "an embodiment", "example", "specific example" or "some examples" etc. means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are contained in at least one embodiment or example of the present application. In the specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. In addition, the person skilled in the art can combine and combine the different embodiments or examples described in the specification and the features of the different embodiments or examples without contradiction.

[0169] Although the embodiments of the present application have been shown and described above, it is understood that the above-described embodiments are exemplary and are not to be construed as limiting the present application, and the person skilled in the art can modify, modify, replace and modify the above-described embodiments within the scope of the present application.

Claims

1. A vehicle travel control method characterized by comprising: The method comprises: acquiring surrounding environment information during vehicle driving; based on the surrounding environment information, predicting whether there is a trend of accident occurrence; if there is a trend of accident occurrence, determining the injury degree of each accident influencing factor based on the surrounding environment information; wherein the surrounding environment information at least includes one of the following: the speed of the ego vehicle, the speed of the front vehicle, the speed of the rear vehicle and the speed of the oncoming vehicle; based on the injury degree of each accident influencing factor, adjusting the weight of each accident influencing factor in the decision model; wherein the decision model is constructed based on the injury evaluation of each accident influencing factor to the ego vehicle; based on the decision model after weight adjustment, outputting a vehicle avoidance driving strategy.

2. The vehicle driving control method of claim 1, wherein the determination of the injury degree of each accident influencing factor based on the surrounding environment information comprises: based on the speed of the ego vehicle, the speed of the front vehicle, the speed of the rear vehicle and the speed of the oncoming vehicle, analyzing the movement state of each vehicle in the accident; based on the movement state of each vehicle in the accident, determining the injury degree of each accident influencing factor.

3. The vehicle travel control method according to claim 2, characterized by the determination of the injury degree of each accident influencing factor based on the movement state of each vehicle in the accident comprises: if the front vehicle and the oncoming vehicle have an accident, and the speed of the oncoming vehicle is greater than a first threshold value, and the speed of the front vehicle and the speed of the rear vehicle are less than a second threshold value, it is determined that the injury degree of the front vehicle is greater than that of the rear vehicle in the accident; if the front vehicle and the oncoming vehicle have an accident, and the speed of the oncoming vehicle and the speed of the front vehicle are less than a second threshold value, and the speed of the rear vehicle is greater than a first threshold value, it is determined that the injury degree of the rear vehicle is greater than that of the front vehicle in the accident; if the front vehicle and the oncoming vehicle have an accident, and the speed of the oncoming vehicle is less than a second threshold value, and the speed of the front vehicle and the speed of the rear vehicle are greater than a first threshold value, it is determined that the injury degree of the rear vehicle is greater than that of the front vehicle in the accident; if the front vehicle and the oncoming vehicle have an accident, and the speed of the oncoming vehicle and the speed of the front vehicle are greater than a first threshold value, and the speed of the rear vehicle is less than a second threshold value, it is determined that the injury degree of the front vehicle is greater than that of the rear vehicle in the accident; if the front vehicle and the oncoming vehicle do not have an accident, and the speed of the ego vehicle is greater than a first threshold value, and the speed of the rear vehicle is less than a second threshold value, it is determined that the injury degree of the oncoming vehicle is greater than that of the rear vehicle in the accident; if the front vehicle and the oncoming vehicle do not have an accident, and the speed of the ego vehicle is less than a second threshold value, and the speed of the rear vehicle is greater than a first threshold value, it is determined that the injury degree of the rear vehicle is greater than that of the oncoming vehicle in the accident; wherein the first threshold value is greater than the second threshold value.

4. The vehicle travel control method according to claim 3, characterized by the weight adjustment of each accident influencing factor in the decision model based on the injury degree of each accident influencing factor comprises: sorting the injury degree of each accident influencing factor in the accident from large to small according to the injury degree. The weight adjustment of each accident influencing factor in the decision model is based on the injury degree of each accident influencing factor when the accident occurs.

5. The vehicle travel control method according to claim 4, characterized in that, The decision model is: U 策略 =W 自 V 自 +W 前 V 前 +W 后 V 后 +W 对 V 对 +W 周1 V 周1 +W 周2 V 周2 +……W 周n V 周n +B 偏置 ; wherein, the V 自 For vehicle speed, W 自 For vehicle weight, V 前 The speed of the preceding vehicle, W 前 Weight of the preceding vehicle, V 后 The following vehicle speed, W 后 Weighting of following vehicles, V 对 The oncoming vehicle speed, W 对 Weighting of oncoming vehicles, V 周1 V 周2 and V 周n All are the speeds of surrounding vehicles, W 周1 W 周2 and W 周n All are weighted by surrounding vehicles, B 偏置 The impact of external environmental factors on the vehicle; The weight adjustment of each accident influencing factor in the decision model is based on the injury degree of each accident influencing factor when the accident occurs. If it is determined that the injury degree of the front vehicle is greater than that of the rear vehicle when the accident occurs, the weight of the front vehicle is increased and the weight of the rear vehicle is decreased; If it is determined that the injury degree of the rear vehicle is greater than that of the front vehicle when the accident occurs, the weight of the front vehicle is decreased and the weight of the rear vehicle is increased; If it is determined that the injury degree of the oncoming vehicle is greater than that of the rear vehicle when the accident occurs, the weight of the oncoming vehicle is increased and the weight of the rear vehicle is decreased; If it is determined that the injury degree of the rear vehicle is greater than that of the oncoming vehicle when the accident occurs, the weight of the oncoming vehicle is decreased and the weight of the rear vehicle is increased.

6. The vehicle travel control method according to claim 5, characterized in that, The vehicle avoidance driving strategy outputted based on the decision model after the weight adjustment includes: U 策略 = W 自 V 自 + W 前 V 前 + W 后 V 后 + W 对 V 对 + W 周1 V 周1 + W 周2 V 周2 + … W 周n V 周n + B 偏置 , divided into: U X策略 =W 自 V 自 COSθ+W 前 V 前 COSθ+W 后 V 后 COSθ + W 对 V 对 COSθ+W 周1 V 周1 COSθ+W 周2 V 周2 COSθ+……W 周n V 周n COSθ+B 偏置 Among them, U X策略 For vehicle lateral control strategy, the V 自 For vehicle speed, W 自 For vehicle weight, V 前 For the speed of the vehicle in front, W 前 Weight of the preceding vehicle, V 后 For the speed of the following vehicle, W 后 Weighting of following vehicles, V 对 For oncoming vehicle speed, W 对 Weighting of oncoming vehicles, V 周1 V 周2 and V 周n All are the speeds of surrounding vehicles, W 周1 W 周2 and W 周n All are weighted by surrounding vehicles, B 偏置 COSθ represents the influence of external environmental factors on the vehicle, and COSθ represents the degree of influence of the movement direction of traffic participants on the lateral position of the vehicle. U y策略 =W 自 V 自 SINθ+W 前 V 前 SINθ+W 后 V 后 SINθ +W 对 V 对 SINθ+W 周1 V 周1 SINθ+W 周2 V 周2 SINθ+……W 周n V 周 n SINθ+B 偏置 Among them, U y策略 SINθ represents the influence of the movement direction of traffic participants on the longitudinal position of the vehicle, which is the vehicle's longitudinal control strategy.

7. The vehicle travel control method according to claim 6, characterized by The vehicle avoidance driving strategy outputted based on the decision model after the weight adjustment includes: The strategy outputted based on the decision model after the weight adjustment includes one of: The left turn strategy of the ego vehicle, the right turn strategy of the ego vehicle, the acceleration strategy of the ego vehicle, the deceleration strategy of the ego vehicle and the stationary strategy of the ego vehicle.

8. The vehicle travel control method according to claim 2, characterized by The surrounding environment information further includes: The bird's eye view of the surrounding environment; The prediction of whether there is a trend of accident occurrence based on the surrounding environment information includes: The relative position relationship of the ego vehicle, the front vehicle, the rear vehicle and the oncoming vehicle is obtained through the bird's eye view; The prediction of whether there is a trend of accident occurrence is based on the relative position relationship of the ego vehicle, the front vehicle, the rear vehicle and the oncoming vehicle, the speed of the ego vehicle, the speed of the front vehicle, the speed of the rear vehicle and the speed of the oncoming vehicle.

9. A vehicle control device characterized by comprising: The vehicle control device for executing the vehicle driving control method of any one of claims 1-8 includes: A perception module for obtaining the surrounding environment information during vehicle driving; An identification module for identifying people, vehicles, lane lines, traffic signs and traffic lights based on the surrounding environment information; A distance judgment module for judging the distance between the ego vehicle and the front vehicle, the rear vehicle and the oncoming vehicle based on the surrounding environment information; A speed judgment module for judging the speed of the ego vehicle, the speed of the front vehicle, the speed of the rear vehicle and the speed of the oncoming vehicle based on the surrounding environment information; A collision analysis module for predicting whether there is a trend of accident occurrence based on the surrounding environment information; A subsequent collision probability and impact consequence analysis module for determining the injury degree of each accident influencing factor when the accident occurs based on the surrounding environment information if there is a trend of accident occurrence; A decision module for adjusting the weight of each accident influencing factor in the decision model based on the injury degree of each accident influencing factor when the accident occurs, and outputting a vehicle avoidance driving strategy based on the decision model after the weight adjustment.

10. A vehicle characterized by comprising: The vehicle control device of claim 9 is included.

Images