Automatic driving control method and vehicle

Abstract

The invention provides an automatic driving control method and a vehicle, and relates to the technical field of automatic driving. The method comprises the steps of firstly determining whether a vehicle is in a congested road condition, determining a target driving strategy according to a driving habit of a user under the condition that the vehicle is determined to be in the congested road condition, and then controlling the vehicle to run under the congested road condition based on the target driving strategy. Therefore, the driving habit of the user under the congested road condition is learned, and the driving strategy is flexibly selected according to the learned driving habit of the user under the congested road condition, so that the performance of the automatic driving control system of the vehicle under the congested road condition is improved, automatic driving is more humanized, the riding comfort of the user is improved, and the driving experience of the user is improved. And the road passing efficiency can be improved.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to an autonomous driving control method and vehicle. Background Art

[0002] With the widespread application of artificial intelligence in various fields, intelligent driving has gradually been applied to daily life. Intelligent driving refers to the technology of machines helping people to drive, and completely replacing human driving in special circumstances. For example, the urban navigation assisted driving system (Navigate On Autopilot, NOA) has been popular in the field of intelligent driving in recent years. NOA combines autonomous driving technology with navigation systems, allowing vehicles to complete driving tasks between the starting point and the end point of driving in complex urban road environments such as vehicle-to-vehicle interaction and human-vehicle interaction. The purpose is to enable vehicles to achieve autonomous navigation and unmanned driving in urban road environments.

[0003] In the scenario of autonomous driving, the driving scenario of congested roads is an important part that should be considered. In congested roads, the vehicle speed is not high but the dynamic interaction between vehicles is more frequent. The situation of lane change and jamming often occurs, which brings certain difficulties to the automatic control of the vehicle. The current NOA technology cannot flexibly adjust the driving strategy when facing the complex traffic conditions on congested roads, resulting in low traffic efficiency and poor user experience. Summary of the invention

[0004] The present application provides an automatic driving control method and a vehicle, which can enhance the user's riding experience and improve traffic efficiency.

[0005] A first aspect of an embodiment of the present application provides an automatic driving control method, the method comprising: Determine whether the vehicle is in congested traffic; When it is determined that the vehicle is in a congested road condition, a target driving strategy is determined according to the user's driving habits; wherein the driving habits include aggressive driving habits and conservative driving habits, and the target driving strategy includes an efficient driving strategy corresponding to the aggressive driving habits and a prudent driving strategy corresponding to the conservative driving habits, and the efficient driving strategy and the prudent driving strategy make different decisions when facing a target scenario; Based on the target driving strategy, the vehicle is controlled to travel in the target scenario.

[0006] Optionally, determining whether the vehicle is in a congested traffic condition includes: Detect the road image and obtain the number of vehicles and lane lines; Based on the number of vehicles, the number of lane lines and the average speed of surrounding vehicles, determine whether the vehicle is in a congested road condition.

[0007] Optionally, determining whether the vehicle is in a congested road condition based on the number of vehicles, the number of lane lines, and an average speed of surrounding vehicles includes: Determining a road congestion score based on the number of vehicles, the number of lane lines and the average vehicle speed; the road congestion score represents the degree of congestion on the road; When the road congestion score is greater than or equal to the congestion score threshold, it is determined that the vehicle is in a congested road condition.

[0008] Optionally, when the target driving strategy is the efficiency driving strategy, controlling the vehicle to drive in the target scenario based on the target driving strategy includes: When the target scenario is that the congestion level of the lane is lower than that of the adjacent lane and the adjacent vehicle intends to change lanes, controlling the vehicle to closely follow the preceding vehicle; In the case where the target scenario is that the congestion level of the lane is higher than that of the adjacent lane, the vehicle is controlled to change lanes in a timely manner.

[0009] Optionally, when the target driving strategy is the safe driving strategy, controlling the vehicle to drive in the target scenario based on the target driving strategy includes: When the target scenario is that the congestion level of the lane is lower than that of the adjacent lane and the adjacent vehicle intends to change lanes, the vehicle is controlled to slow down and give way to the adjacent vehicle; When the target scenario is that the congestion level of the lane is higher than that of the adjacent lane, the vehicle is controlled to continue following the vehicle.

[0010] Optionally, the method further comprises: Counting a first cumulative number of times the user has aggressive driving behavior and a second cumulative number of times the user has conservative driving behavior; In a case where the first accumulated number reaches the number threshold before the second accumulated number reaches the number threshold, determining that the driving habit is the aggressive driving habit; When the second accumulated number reaches the number threshold before the first accumulated number, it is determined that the driving habit is the conservative driving habit.

[0011] Optionally, the congested road condition includes a lightly congested road condition, a moderately congested road condition, and a severely congested road condition, and the method further includes: If the congested road condition is a light congested road condition and the user changes lanes or steps on the accelerator, or if the congested road condition is a moderate congested road condition and the user steps on the accelerator while cutting in, or if the congested road condition is a severe congested road condition and the user steps on the accelerator or turns on the lights of a meeting vehicle, the first accumulated number is increased by one; When the congested road condition is a light congested road condition and the user does not change lanes or step on the accelerator pedal, or when the congested road condition is a moderate congested road condition and the user does not step on the accelerator pedal while cutting in, or when the congested road condition is a severe congested road condition and the user does not step on the accelerator pedal or turn on the meeting lights, the second accumulated number is increased by one.

[0012] Optionally, controlling the vehicle to closely follow the preceding vehicle comprises: Controlling the distance between the vehicle and the preceding vehicle to reach a preset following distance, and after reaching the preset following distance, controlling the vehicle to follow the preceding vehicle at the same speed as the preceding vehicle; When the leading vehicle decelerates, the vehicle is controlled to perform adaptive deceleration based on a preset minimum safety distance.

[0013] Optionally, the method further comprises: When the target driving strategy is the safe driving strategy, determining an expansion boundary of the vehicle; the expansion boundary is a region including the vehicle; Based on the expansion boundary, a driving path of the vehicle is planned.

[0014] Based on the same inventive concept, a second aspect of an embodiment of the present application provides an automatic driving control device, the device comprising: A road condition judgment module is used to determine whether the vehicle is in a congested road condition; A strategy selection module, for determining a target driving strategy according to the user's driving habits when it is determined that the vehicle is in a congested road condition; wherein the driving habits include aggressive driving habits and conservative driving habits, and the target driving strategy includes an efficiency driving strategy corresponding to the aggressive driving habits and a prudent driving strategy corresponding to the conservative driving habits, and the efficiency driving strategy and the prudent driving strategy make different decisions when facing a target scenario; A control module is used to control the vehicle to travel in the target scenario based on the target driving strategy.

[0015] Based on the same inventive concept, the third aspect of an embodiment of the present application provides a storage medium, which stores machine executable instructions. When the machine executable instructions are executed by a processor, the automatic driving control method proposed in the first aspect of the present application is implemented.

[0016] Based on the same inventive concept, the fourth aspect of an embodiment of the present application provides a vehicle, including a processor and a memory; the memory stores machine executable instructions that can be executed by the processor, and the processor is used to execute the machine executable instructions to implement the automatic driving control method proposed in the first aspect of the present application.

[0017] Compared with the prior art, this application has the following advantages: An automatic driving control method provided in an embodiment of the present application first determines whether the vehicle is in a congested road condition, and when it is determined that the vehicle is in a congested road condition, determines a target driving strategy according to the user's driving habits, and then controls the vehicle to drive in the congested road condition based on the target driving strategy. Thus, by learning the user's driving habits in congested road conditions, and flexibly selecting a driving strategy according to the learned user's driving habits when facing congested road conditions, the performance of the vehicle's automatic driving control system in congested road conditions is improved, making automatic driving more humane, thereby improving the user's riding comfort, and facilitating the improvement of road traffic efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0019] Figure 1 is a flow chart of an automatic driving control method in one embodiment of the present application; Figure 2 is a logical schematic diagram of road image detection in an embodiment of the present application; Figure 3 is a schematic diagram of an expansion boundary of a vehicle determined in an embodiment of the present application; Figure 4 This is a schematic diagram of the functional modules of an automatic driving control device in one embodiment of the present application; Figure 5 It is a structural schematic diagram of a vehicle in one embodiment of the present application. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0021] In the scenario of autonomous driving, the driving scenario of congested roads is an important part that should be considered. In congested roads, the vehicle speed is not high but the dynamic interaction between vehicles is more frequent. The situation of lane change and jamming often occurs, which brings certain difficulties to the automatic control of the vehicle. The current NOA technology cannot flexibly adjust the driving strategy, and the following problems often occur in congested roads: On congested roads, the car starts slowly after the car in front starts, resulting in a large distance between the car in front and the car in front, which makes it easy for the car next to it to cut in, and affects the starting of the car behind, resulting in reduced traffic efficiency; After the front vehicle starts, if your vehicle starts too fast and then brakes suddenly to slow down after approaching the front vehicle, it will affect the user's riding experience and may cause the rear vehicle to rear-end, posing a safety hazard.

[0022] In view of this, the present application proposes an automatic driving control method, which learns the user's driving habits in congested road conditions, and flexibly selects driving strategies according to the learned user driving habits when facing congested road conditions, so as to match the most appropriate vehicle control strategy according to the current road conditions and user habits, improve the performance of the vehicle's automatic driving control system in congested road conditions, reduce the phenomenon of cutting in, sudden braking and sudden stopping, make automatic driving more humane, thereby improving the user's riding comfort, and is conducive to improving road traffic efficiency.

[0023] Please refer to Figure 1 , Figure 1 : is a flow chart of an automatic driving control method proposed in one embodiment of the present application. Figure 1 As shown, the method comprises the following steps: S101: Determine whether the vehicle is in a congested traffic condition.

[0024] In this embodiment, considering that in a congested environment, the vehicle's driving speed is low and the traffic density on the road is high, the current traffic density can be obtained based on the distribution position and number of dynamic obstacles within a certain surrounding range fed back by the autonomous driving sensor system in the autonomous driving vehicle. When the traffic density is high and the current speed of the vehicle is low, the vehicle is considered to be in a congested road condition, such as driving on a congested section of a city main road or a highway.

[0025] In another feasible implementation, it is also possible to determine whether the vehicle is currently in a traffic jam based on the average speed and braking frequency of the vehicle. For example, within a 30s time window, if the average speed of the vehicle is less than or equal to 10km / h and the braking frequency is greater than or equal to 0.2 times / s, the vehicle is considered to be in a traffic jam.

[0026] In addition, the vehicle can also be directly determined based on the information about the road conditions fed back by the map software to determine whether the vehicle is in a congested road condition. For example, a green section in the map software indicates that the road is unobstructed, while a red section indicates that the road is congested.

[0027] S102: When it is determined that the vehicle is in a congested road condition, a target driving strategy is determined according to the user's driving habits.

[0028] When the road is unobstructed, the autonomous driving system can determine the driving speed of the autonomous driving vehicle in the current lane based on the distance between the current position and the destination position, the speed limit and traffic restrictions of the current lane, etc., and control the vehicle to travel at this speed to prevent violations of traffic regulations, etc. However, in the case of road congestion, dynamic interactions between vehicles are more frequent. If the vehicle operation is still controlled by a fixed driving strategy under unobstructed roads, the congestion situation may be aggravated and the user experience may be affected. Therefore, in congested road conditions, the autonomous driving system should adopt a more effective control strategy to control the operation of the vehicle.

[0029] In this embodiment, it is considered that when interacting with other vehicles on congested roads, experienced drivers will make corresponding driving decisions based on different situations, combined with the vehicle status and the surrounding environment. Therefore, this embodiment pre-sets different driving strategies in the automatic driving system and makes corresponding selections based on the user's driving habits, that is, different user driving habits correspond to different target driving strategies, so as to flexibly adjust the driving strategy according to different road conditions, thereby taking into account factors such as the vehicle's driving status and the interaction distance of the adjacent vehicle, and without violating traffic rules, generating intelligent decisions similar to those of the driver, making the control strategy of the automatic driving more humane and better applicable to various congested road conditions.

[0030] Furthermore, driving habits include aggressive driving habits and conservative driving habits, and the target driving strategy includes an efficient driving strategy corresponding to the aggressive driving habits and a prudent driving strategy corresponding to the conservative driving habits. The efficient driving strategy and the prudent driving strategy make different decisions when facing the target scenario.

[0031] In this embodiment, the driver's driving logic habits in the NOA mode can be learned by detecting the driver's intervention behavior in the vehicle path planning during the NOA navigation process. If the user's driving habits are aggressive driving habits, it means that the user is more inclined to intervene in the automatic driving system under congested road conditions, such as intervening the accelerator pedal, brake, turn signal, etc. At this time, an efficiency driving strategy is adopted to ensure the traffic efficiency of the vehicle. That is, the efficiency driving strategy targets the traffic efficiency of the vehicle. If the user's driving habits are conservative driving habits, it means that the user rarely intervenes in the automatic driving system under congested road conditions. At this time, a safe driving strategy is adopted. The safe driving strategy targets the safety of the vehicle and is the default strategy of the automatic driving system to ensure the safety of the vehicle and prevent accidents.

[0032] It is easy to understand that the decision-making of efficient driving strategy and safe driving strategy is different when facing the same target scenario. For example, in a congested road, if the efficient driving strategy is adopted, the nearby car will be avoided to ensure the traffic efficiency of the lane. If the safe driving strategy is adopted, the nearby car will be courteous to ensure the safety of the vehicle and avoid collision with the nearby car.

[0033] Furthermore, the congested road conditions can be classified into, for example, mild congested road conditions, moderate congested road conditions and severe congested road conditions, and then the user's driving logic habits can be learned for each degree of congested road conditions, and finally the user's driving strategy corresponding to different degrees of congested road conditions can be formed and applied to actual driving scenarios. Thus, based on different degrees of congested road conditions, the driving strategy can be set and applied more comprehensively, further improving the user's riding experience.

[0034] S103: Based on the target driving strategy, control the vehicle to drive in the target scenario.

[0035] In this embodiment, when it is determined that the vehicle is in a congested road condition, after determining the target driving strategy according to the user's driving habits, the vehicle operation is controlled according to the target driving strategy, so that the vehicle can make adaptive behaviors in different target scenarios to improve the user experience. It is easy to understand that the specific actions made by the same target driving strategy in different target scenarios are different. Specifically: When the target driving strategy is the efficiency driving strategy, the vehicle control process includes: when the target scenario is that the congestion level of the lane is lower than that of the adjacent lane and the adjacent vehicle intends to change lanes, the vehicle is controlled to follow the front vehicle closely; when the target scenario is that the congestion level of the lane is higher than that of the adjacent lane, the vehicle is controlled to change lanes in a timely manner.

[0036] Among them, in congested road conditions, when it is detected that the congestion level of the lane is lower than that of the adjacent lane and the adjacent vehicle changes lanes to the lane in front of the vehicle, that is, in the scenario of adjacent vehicles cutting in, the efficiency driving strategy will be adopted to control the acceleration of the vehicle, shorten the distance with the vehicle in front, and avoid adjacent vehicles cutting in, so as to ensure the traffic efficiency of the lane. When it is detected that the lane is seriously congested and the traffic efficiency is low, while the adjacent lane is less congested and has a higher traffic efficiency, the efficiency driving strategy will be adopted to control the vehicle to change lanes, enter the adjacent lane and follow the preceding vehicle closely, so as to improve the traffic efficiency of the vehicle.

[0037] When the target driving strategy is a safe driving strategy, the vehicle control process includes: when the target scenario is that the congestion level of the lane is lower than that of the adjacent lane and the adjacent vehicle intends to change lanes, the vehicle is controlled to slow down and give way to the adjacent vehicle; when the target scenario is that the congestion level of the lane is higher than that of the adjacent lane, the vehicle is controlled to continue following the vehicle.

[0038] In congested traffic, when facing a situation where a car cuts in, the prudent driving strategy will control the car to slow down, increase the distance from the car in front, and leave enough space for the car to change lanes, so as to ensure the safety of the car and avoid collision with the car. When it is detected that the lane is seriously congested and the traffic efficiency is low, while the congestion in the lane next to it is less severe and the traffic efficiency is higher, the prudent driving strategy will control the car to keep driving slowly in the lane to avoid safety problems caused by lane changes.

[0039] This embodiment learns the user's driving habits in congested road conditions, and flexibly selects driving strategies based on the learned user driving habits when facing congested road conditions, so as to match the most appropriate vehicle control strategy according to the current road scene and user habits, thereby improving the performance of the vehicle's automatic driving control system in congested road conditions, reducing phenomena such as cutting in, sudden braking and sudden stopping, making automatic driving more humane, thereby improving the user's riding comfort, and facilitating the improvement of road traffic efficiency.

[0040] Optionally, determining whether the vehicle is in a congested traffic condition includes: S201: Detect the road image to obtain the number of vehicles and lane lines.

[0041] In this embodiment, considering that the map navigation software has a certain delay in judging road congestion, this embodiment uses a driving recorder to monitor the road congestion in real time. Specifically, the driving recorder can record the surrounding vehicles, pedestrians, road markings and other information captured by the camera, so the captured road image can be subjected to target detection through the target detection method, and the surrounding environment information of the congested road section can be accurately identified, including the number of vehicles and the number of lane lines, etc., to provide data support for the judgment of congested road conditions.

[0042] In a feasible implementation, a YOLOv7 network may be used for road image detection. YOLOv7 uses a deep convolutional neural network (CNN) as the main architecture, which can effectively extract features from images, thereby improving the accuracy of image recognition and classification.

[0043] Specifically, the process of using the YOLOv7 network for road image detection is as follows: Figure 2 As shown, including: First, collect road images in various scenarios, including road images under different lighting conditions such as daytime and nighttime, road images under different roads such as urban roads and highways, and road images under different traffic conditions such as congested and non-congested periods. Then use the labelimg tool to label the actual number of vehicles and the actual number of lane lines in the road image, and store the image format as YOLO to obtain multiple sample images.

[0044] Next, the initial YOLOv7 network is trained using multiple sample images. The initial YOLOv7 network detects vehicles and lane lines on multiple sample images, and the predicted number of vehicles and lane lines corresponding to each sample image are obtained. Based on the difference between the predicted number of vehicles and the actual number of vehicles, and the difference between the predicted number of lane lines and the actual number of lane lines, the initial YOLOv7 network is reversely updated with gradients to optimize the model parameters. This update and iteration is repeated until the preset number of iterations is reached, and the training is finally obtained. The optimized YOLOv7 network is obtained.

[0045] Afterwards, the trained YOLOv7 network is used to detect road images to obtain the number of vehicles and lane lines in the surrounding environment, providing a basis for subsequent judgment of congested road conditions.

[0046] S202: Determine whether the vehicle is in a congested road condition based on the number of vehicles, the number of lane lines, and the average speed of surrounding vehicles.

[0047] In this implementation, the number of vehicles, the number of lane lines, and the average speed of surrounding vehicles can all intuitively reflect the current traffic situation. The more vehicles detected, the greater the traffic volume on the current road, and the greater the possibility of road congestion; the more lane lines detected, the wider the vehicle's field of vision (there are fewer vehicles on the current road, so more lane lines will be detected), and the less likely the road will be congested; the higher the average speed of surrounding vehicles, the faster the vehicles on the current road are moving, and the less likely the road will be congested. Therefore, the number of vehicles, the number of lane lines, and the average speed of surrounding vehicles can be comprehensively considered to more accurately determine whether the vehicle is currently in a congested road condition.

[0048] Specifically, the judgment process mainly includes: S202-1: Determine a road congestion score based on the number of vehicles, the number of lane lines, and the average vehicle speed.

[0049] In this embodiment, the road congestion score represents the degree of road congestion. For example, the number of vehicles, the number of lanes and the average speed can be assigned corresponding weights according to their respective importance to the judgment of congested road conditions, and the weighted sum can be performed to obtain the road congestion score. Specifically, the calculation method is as follows:

[0050] in, represents the road congestion score, Indicates the number of vehicles, represents the average vehicle speed, Indicates the number of lane lines.

[0051] Calculating road congestion scores When the number of vehicles is given With a positive weight of 2, assign the average speed Assign the number of lane lines with a negative weight of -0.5 With a negative weight of -0.5. Thus, the calculated road congestion score is The larger the value, the higher the current road congestion level.

[0052] S202-2: When the road congestion score is greater than or equal to the congestion score threshold, determine that the vehicle is in a congested road condition.

[0053] In this implementation, the congestion score threshold can be set with reference to the actual urban road congestion situation, for example, it can be set to 4, so that when the road congestion score When the traffic congestion score reaches or exceeds 4, the vehicle is determined to be in a congested traffic condition. When it is less than 4, it is determined that the vehicle is currently in a non-congested road condition.

[0054] Furthermore, the congested road conditions can be further subdivided based on the road congestion score. For example, when the road congestion score is between 4 and 6, it is determined as a lightly congested road condition; when it is between 6 and 8, it is determined as a moderately congested road condition; and when it is between 8 and 10, it is determined as a severely congested road condition. Thus, for different congested road conditions, corresponding driving strategies are adopted to control the operation of the vehicle, improve the performance of the vehicle's automatic driving control system under various congested road conditions, and enhance the riding comfort of users.

[0055] Optionally, the driving habits include aggressive driving habits and conservative driving habits; according to the user's driving habits, a target driving strategy is determined, including: S301: When the driving habit is an aggressive driving habit, determining the target driving strategy to be an efficient driving strategy.

[0056] In this embodiment, considering that vehicles cutting in from the side often occur in congested roads, affecting traffic efficiency, and in this case, the most efficient way to travel is to drive in separate lanes, an efficiency driving strategy can be adopted. Under the efficiency driving strategy, the vehicle is controlled to gradually accelerate to a distance of only one vehicle body from the vehicle in front after starting, and then drive at the same speed as the vehicle in front to avoid vehicles cutting in from the side and affecting traffic efficiency.

[0057] The efficient driving strategy corresponds to the user's aggressive driving habits. Specifically, the aggressive driving habits are determined as follows: a first cumulative number of times the user has aggressive driving behaviors and a second cumulative number of times the user has conservative driving behaviors are counted; if the first cumulative number reaches a number threshold before the second cumulative number, the driving habit is determined to be an aggressive driving habit.

[0058] Aggressive driving behavior refers to the user's intervention in the vehicle during NOA navigation under congested road conditions, including stepping on the accelerator pedal, turning on the lights, changing lanes, etc. It is easy to understand that when a user engages in aggressive driving behavior under congested road conditions, the purpose is often to avoid being squeezed in by other cars and to maintain the speed of the vehicle. If the user does not intervene in the vehicle during NOA navigation, it is considered that the user has conservative driving behavior.

[0059] In the process of learning the user's driving habits, by counting the first cumulative number of times the user exhibits aggressive driving behavior and the second cumulative number of times the user exhibits conservative driving behavior, and comparing the first cumulative number with the second cumulative number, it is determined whether the user is more inclined to aggressive driving or conservative driving.

[0060] Specifically, if the first cumulative number reaches the number threshold before the second cumulative number, the user's driving habit is determined to be an aggressive driving habit. For example, if the first cumulative number reaches 50 times first, it means that the user frequently intervenes in the vehicle during the NOA navigation process and the user pays great attention to traffic efficiency, so it is considered that the user's driving habit is more inclined to aggressive driving habits.

[0061] S302: When the driving habit is a conservative driving habit, determining the target driving strategy to be a safe driving strategy.

[0062] In this implementation, the safe driving strategy is the default strategy of the automatic driving system. The safe driving strategy pays more attention to driving safety. Efficiency will be considered only when driving safety is guaranteed. Therefore, the traffic efficiency under the safe driving strategy may be lower than that under the efficient driving strategy. For example, in a congested road condition, when a car cuts in, the safe driving strategy may slow down appropriately to allow the car to enter the lane to ensure vehicle safety, so as to avoid collision during the car cutting in.

[0063] The prudent driving strategy corresponds to the user's conservative driving habits. Specifically, the conservative driving habits are determined as follows: a first cumulative number of times the user has aggressive driving behaviors and a second cumulative number of times the user has conservative driving behaviors are counted; if the second cumulative number reaches a threshold before the first cumulative number, the driving habit is determined to be a conservative driving habit.

[0064] In the process of learning the user's driving habits, if the second cumulative number reaches the number threshold before the first cumulative number, the user's driving habits are determined to be conservative. For example, if the second cumulative number reaches 50 times first, it means that the user rarely intervenes in the vehicle during the NOA navigation process, and the user may pay more attention to traffic safety, so it is considered that the user's driving habits tend to be more conservative.

[0065] Furthermore, the congested road condition includes a light congested road condition, a moderate congested road condition and a severe congested road condition. The statistical process of the above-mentioned aggressive driving behavior and conservative driving behavior includes: When the congested road condition is mild and the user changes lanes or steps on the accelerator, or when the congested road condition is moderate and the user steps on the accelerator while cutting in, or when the congested road condition is severe and the user steps on the accelerator or turns on the lights of oncoming vehicles, the first cumulative number is increased by one; when the congested road condition is mild and the user does not change lanes or step on the accelerator, or when the congested road condition is moderate and the user does not step on the accelerator while cutting in, or when the congested road condition is severe and the user does not step on the accelerator or turns on the lights of oncoming vehicles, the second cumulative number is increased by one.

[0066] In this implementation, the congested road conditions can be subdivided into light congested road conditions, moderate congested road conditions and severe congested road conditions through the above step S202. Under different congestion levels, the situations faced by users and the behaviors they take may be different. For example: In lightly congested road conditions, the average vehicle speed is generally 39-70km / h, and there are still many vehicles on the road. During the NOA system navigation process, the system will combine the map road information to detect whether the vehicle speed exceeds the speed limit, and detect whether the user frequently intervenes in changing lanes or stepping on the accelerator pedal. If so, it will be accumulated as an "aggressive driving behavior" and the first cumulative number will increase by one. If the user does not intervene during the NOA system navigation process, it will be accumulated as a "conservative driving behavior" and the second cumulative number will increase by one.

[0067] In moderately congested road conditions, the average vehicle speed is generally 33-39km / h, and cutting in may occur under such road conditions. When the NOA system detects through the laser radar that the adjacent vehicle has changed lanes to the lane in front of the vehicle, it defines this situation as cutting in. At this time, the NOA system will detect whether the user has any human intervention behavior. If the user steps on the accelerator pedal to reduce the distance to the vehicle in front during the cutting in process, it will be accumulated as "aggressive driving behavior" and the first accumulated number will increase by one. If the user steps on the brakes or does not intervene in any way during the cutting in process, it will be accumulated as "conservative driving behavior" and the second accumulated number will increase by one.

[0068] In severely congested road conditions, the average vehicle speed is generally 0-33km / h. Under such road conditions, vehicles can basically only drive slowly in sequence, but different users keep different distances from the vehicle in front when following. During the NOA system's slow following process, if it is detected that the user has stepped on the accelerator pedal or used the "meeting lights", it means that the driver has the intention to accelerate, and then one "aggressive driving behavior" is accumulated, and the first cumulative number is increased by one. If the user does not intervene in the entire NOA system navigation process of slow following, one "conservative driving behavior" is accumulated, and the second cumulative number is increased by one.

[0069] Therefore, by detecting the corresponding behaviors that may occur in users under different congestion levels, the number of aggressive driving behaviors and conservative driving behaviors is counted to provide a basis for determining the user's driving habits.

[0070] Optionally, when the target driving strategy is the efficiency driving strategy, controlling the vehicle to closely follow the preceding vehicle includes: S401: Control the distance between the vehicle and the preceding vehicle to reach a preset following distance, and after reaching the preset following distance, control the vehicle to follow the preceding vehicle at the same speed as the preceding vehicle.

[0071] In this embodiment, when the target driving strategy is determined to be the efficiency driving strategy, the automatic driving system will control the vehicle to gradually accelerate to a preset following distance from the vehicle in front after starting, and then maintain the same speed as the vehicle in front to follow the vehicle. The preset following distance can be set to the distance of one vehicle body, which can ensure a safe distance from the vehicle in front in congested and slow-moving conditions, avoid rear-end collisions with the vehicle in front, and avoid other vehicles cutting in, thereby improving the overall traffic efficiency of the current road.

[0072] S402: When the vehicle ahead decelerates, the vehicle is controlled to perform adaptive deceleration based on a preset minimum safety distance.

[0073] In this embodiment, when slowly following a vehicle in congested road conditions, the vehicle can identify the relative position of the vehicle in front and the state of the brake lights through the laser radar and the camera. If it is detected that the vehicle in front starts to slow down, the vehicle also starts to slow down gradually. In congested road conditions, the reserved preset following distance itself can meet the needs of safe braking of the vehicle, but in order to improve the comfort of the braking process and avoid sudden braking, this embodiment allows the vehicle to get closer to the vehicle in front during the deceleration and braking process under the efficiency driving strategy to achieve the purpose of comfortable braking, but the final distance from the vehicle in front cannot be less than the preset minimum safety distance. Among them, the minimum safety distance is less than the preset following distance, for example, the minimum safety distance can be set to half the distance of the vehicle body.

[0074] In this embodiment, the efficient driving strategy under congested road conditions can control the vehicle's starting, stable driving, and braking processes accordingly. While ensuring driving safety, it can avoid other vehicles from cutting in and improve the comfort of the braking process, thereby improving the user's riding experience.

[0075] Optionally, the method further includes: when the target driving strategy is a safe driving strategy, determining an expansion boundary of the vehicle; the expansion boundary is a region range including the vehicle; and planning a driving path of the vehicle based on the expansion boundary.

[0076] In this embodiment, when the target driving strategy is determined to be a safe driving strategy, the automatic driving system will first detect the expansion boundary of the vehicle to determine the safety range of the vehicle, and then plan the driving path of the vehicle based on the expansion boundary and combined with the surrounding environmental information (the speed and relative position of surrounding vehicles), road speed limit information, etc., to ensure driving safety and avoid collisions with surrounding vehicles.

[0077] The expansion boundary is the area that includes the vehicle. Figure 3 As shown, Figure 3The boundary after the three circles C1, C2 and C3 are superimposed is the expansion boundary of the vehicle. Circle C2 is formed with the midpoint of the central axis of the vehicle as the center and the distance from the midpoint to the front headlight as the radius. Circle C1 is formed with the rear wheel axis of the vehicle as the center and the radius is the same as that of circle C2. Circle C3 is formed with the front wheel axis of the vehicle as the center and the radius is the same as that of circle C2.

[0078] It is easy to understand that the expansion boundary is the expansion of the risk boundary of the vehicle. The risk boundary of the vehicle is a rectangular boundary formed by the length and width of the vehicle, such as Figure 3 A rectangular boundary with a width of m1 and a length of m2. Therefore, under the safe driving strategy, the expansion boundary of the vehicle is delineated by using the determination method of the vehicle's "three-circle" safety zone, and in the process of vehicle trajectory planning, the expansion boundary is used as a constraint condition, and the dynamic programming algorithm is used to solve the most stable driving path of the vehicle, so that the collision risk of the vehicle appears outside the expansion boundary to ensure the safety of vehicle driving.

[0079] Please refer to Figure 4 Based on the same inventive concept, the second aspect of the embodiment of the present application provides an automatic driving control device, the automatic driving control device 400 includes: A road condition determination module 401 is used to determine whether the vehicle is in a congested road condition; The strategy selection module 402 is used to determine a target driving strategy according to the user's driving habits when it is determined that the vehicle is in a congested road condition; wherein the driving habits include aggressive driving habits and conservative driving habits, and the target driving strategy includes an efficient driving strategy corresponding to the aggressive driving habits and a prudent driving strategy corresponding to the conservative driving habits, and the efficient driving strategy and the prudent driving strategy make different decisions when facing the target scenario; The control module 403 is used to control the vehicle to travel in a target scenario based on the target driving strategy.

[0080] Optionally, the road condition determination module 401 includes: The image detection submodule is used to detect the road image and obtain the number of vehicles and lane lines; The road condition detection submodule is used to determine whether the vehicle is in a congested road condition based on the number of vehicles, the number of lane lines and the average speed of surrounding vehicles.

[0081] Optionally, the road condition detection submodule includes: A congestion score calculation unit, used to determine a road congestion score based on the number of vehicles, the number of lane lines and the average vehicle speed; the road congestion score represents the degree of congestion of the road; The congestion judgment unit is used to determine that the vehicle is in a congested road condition when the road congestion score is greater than or equal to the congestion score threshold.

[0082] Optionally, when the target driving strategy is an efficiency driving strategy, the strategy selection module 402 includes: The first control submodule is used to control the vehicle to follow the preceding vehicle closely when the target scenario is that the congestion level of the lane is lower than that of the adjacent lane and the adjacent vehicle intends to change lanes; The second control submodule is used to control the vehicle to change lanes in a timely manner when the target scenario is that the congestion level of the lane is higher than that of the adjacent lane.

[0083] Optionally, when the target driving strategy is a safe driving strategy, the strategy selection module 402 includes: The first control submodule is used to control the vehicle to slow down and give way to the adjacent vehicle when the target scenario is that the congestion level of the lane is lower than that of the adjacent lane and the adjacent vehicle intends to change lanes; The second control submodule is used to control the vehicle to continue to follow the vehicle when the target scenario is that the congestion level of the lane is higher than that of the adjacent lane.

[0084] Optionally, the above device further includes: A behavior frequency statistics module, used to count the first cumulative number of times the user has aggressive driving behavior and the second cumulative number of times the user has conservative driving behavior; an aggressive driving habit determination module, configured to determine that the driving habit is an aggressive driving habit when the first cumulative number reaches a number threshold before the second cumulative number reaches a number threshold; The conservative driving habit determination module is used to determine that the driving habit is a conservative driving habit when the second cumulative number of times reaches the number threshold before the first cumulative number of times.

[0085] Optionally, the congested road condition includes a light congested road condition, a moderate congested road condition and a severe congested road condition; and the above device further includes: A first statistical module is used for, when the congested road condition is a light congested road condition and the user changes lanes or steps on the accelerator, or when the congested road condition is a moderate congested road condition and the user steps on the accelerator while cutting in, or when the congested road condition is a severe congested road condition and the user steps on the accelerator or turns on the lights of a meeting vehicle, to increase the first cumulative number by one; The second statistical module is used to add one to the second cumulative number of times when the congested road condition is light and the user does not change lanes or step on the accelerator pedal, or when the congested road condition is moderate and the user does not step on the accelerator pedal when cutting in, or when the congested road condition is severe and the user does not step on the accelerator pedal or turn on the meeting lights.

[0086] Optionally, the control module 403 further includes: The following vehicle submodule is used to control the distance between the vehicle and the preceding vehicle to reach a preset following distance, and after reaching the preset following distance, control the vehicle to follow the preceding vehicle at the same speed; The deceleration submodule is used to control the vehicle to perform adaptive deceleration based on a preset minimum safety distance when the vehicle ahead decelerates.

[0087] Optionally, the control module 403 further includes: The expansion boundary determination submodule is used to determine the expansion boundary of the vehicle when the target driving strategy is a safe driving strategy; the expansion boundary is the area range including the vehicle; The path planning submodule is used to plan the driving path of the vehicle based on the expansion boundary.

[0088] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0089] On the third aspect, based on the same inventive concept, an embodiment of the present application provides a storage medium, which stores machine executable instructions. When the machine executable instructions are executed by a processor, the automatic driving control method proposed in the first aspect of the present application is implemented.

[0090] It should be noted that the specific implementation of the storage medium of the embodiment of the present application refers to the specific implementation of the automatic driving control method proposed in the first aspect of the embodiment of the present application, and will not be repeated here.

[0091] In the fourth aspect, based on the same inventive concept, refer to Figure 5 An embodiment of the present application provides a vehicle 500, including a processor 501 and a memory 502; the memory 502 stores machine executable instructions that can be executed by the processor 501, and the processor 501 is used to execute the machine executable instructions to implement the automatic driving control method proposed in the first aspect of the present application.

[0092] It should be noted that the specific implementation of the vehicle 500 in the embodiment of the present application refers to the specific implementation of the automatic driving control method proposed in the first aspect of the embodiment of the present application, and will not be repeated here.

[0093] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0094] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, devices, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0095] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), 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 terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal 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.

[0096] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0097] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable terminal device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0098] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present application.

[0099] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0100] The above is a detailed introduction to an automatic driving control method and vehicle provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. An automatic driving control method, characterized in that: The method comprises: Determine whether the vehicle is in congested traffic; When it is determined that the vehicle is in a congested road condition, a target driving strategy is determined according to the user's driving habits; wherein the driving habits include aggressive driving habits and conservative driving habits, and the target driving strategy includes an efficient driving strategy corresponding to the aggressive driving habits and a prudent driving strategy corresponding to the conservative driving habits, and the efficient driving strategy and the prudent driving strategy make different decisions when facing a target scenario; Based on the target driving strategy, the vehicle is controlled to travel in the target scenario.

2. The method according to claim 1, characterized in that Determine if the vehicle is in congested traffic, including: Detect the road image and obtain the number of vehicles and lane lines; Based on the number of vehicles, the number of lane lines and the average speed of surrounding vehicles, determine whether the vehicle is in a congested road condition.

3. The method according to claim 2, characterized in that Determining whether the vehicle is in a congested road condition based on the number of vehicles, the number of lane lines, and the average speed of surrounding vehicles includes: Determining a road congestion score based on the number of vehicles, the number of lane lines and the average vehicle speed; the road congestion score represents the degree of congestion on the road; When the road congestion score is greater than or equal to the congestion score threshold, it is determined that the vehicle is in a congested road condition.

4. The method according to claim 1, characterized in that When the target driving strategy is the efficiency driving strategy, controlling the vehicle to drive in the target scenario based on the target driving strategy includes: When the target scenario is that the congestion level of the lane is lower than that of the adjacent lane and the adjacent vehicle intends to change lanes, controlling the vehicle to closely follow the preceding vehicle; In the case where the target scenario is that the congestion level of the lane is higher than that of the adjacent lane, the vehicle is controlled to change lanes in a timely manner.

5. The method according to claim 1, characterized in that When the target driving strategy is the safe driving strategy, controlling the vehicle to drive in the target scenario based on the target driving strategy includes: When the target scenario is that the congestion level of the lane is lower than that of the adjacent lane and the adjacent vehicle intends to change lanes, the vehicle is controlled to slow down and give way to the adjacent vehicle; When the target scenario is that the congestion level of the lane is higher than that of the adjacent lane, the vehicle is controlled to continue following the vehicle.

6. The method according to claim 1, characterized in that The method further comprises: Counting a first cumulative number of times the user has aggressive driving behavior and a second cumulative number of times the user has conservative driving behavior; In a case where the first accumulated number reaches the number threshold before the second accumulated number reaches the number threshold, determining that the driving habit is the aggressive driving habit; When the second accumulated number reaches the number threshold before the first accumulated number, it is determined that the driving habit is the conservative driving habit.

7. The method according to claim 6, characterized in that The congested road conditions include light congested road conditions, moderate congested road conditions and severe congested road conditions, and the method further includes: If the congested road condition is a light congested road condition and the user changes lanes or steps on the accelerator, or if the congested road condition is a moderate congested road condition and the user steps on the accelerator while cutting in, or if the congested road condition is a severe congested road condition and the user steps on the accelerator or turns on the lights of a meeting vehicle, the first accumulated number is increased by one; When the congested road condition is a light congested road condition and the user does not change lanes or step on the accelerator pedal, or when the congested road condition is a moderate congested road condition and the user does not step on the accelerator pedal while cutting in, or when the congested road condition is a severe congested road condition and the user does not step on the accelerator pedal or turn on the meeting lights, the second accumulated number is increased by one.

8. The method according to claim 4, characterized in that Controlling the vehicle to closely follow the preceding vehicle comprises: Controlling the distance between the vehicle and the preceding vehicle to reach a preset following distance, and after reaching the preset following distance, controlling the vehicle to follow the preceding vehicle at the same speed as the preceding vehicle; When the leading vehicle decelerates, the vehicle is controlled to perform adaptive deceleration based on a preset minimum safety distance.

9. The method according to claim 1, characterized in that: The method further comprises: When the target driving strategy is the safe driving strategy, determining an expansion boundary of the vehicle; the expansion boundary is a region including the vehicle; Based on the expansion boundary, a driving path of the vehicle is planned.

10. A vehicle, characterized in that: It includes a processor and a memory; the memory stores machine executable instructions that can be executed by the processor, and the processor is used to execute the machine executable instructions to implement the automatic driving control method as described in any one of claims 1 to 9.

Images