Intelligent networked vehicle obstacle avoidance method

Abstract

The invention relates to the technical field of vehicle data processing, in particular to an intelligent network connection vehicle obstacle avoidance method and device, and the method comprises the steps: obtaining vehicle information of a target vehicle, and a first position and a moving posture of an obstacle, the vehicle information comprising a second position and a vehicle speed; predicting a moving track of the obstacle within a preset time length according to the moving pose; acquiring an obstacle category of the obstacle; according to the obstacle category, the first position, the second position and the moving track, the collision probability of the obstacle and the target vehicle is determined; and generating an obstacle avoidance strategy based on the vehicle speed and the collision probability, and controlling the target vehicle according to the obstacle avoidance strategy. According to the invention, the accuracy of vehicle obstacle avoidance is effectively improved.

Description

Technical Field

[0001] The present application relates to the technical field of image data processing, and in particular to an obstacle avoidance method for intelligent networked vehicles. Background Art

[0002] With the advancement and development of science and technology, the automotive industry is also constantly moving towards intelligence and digitalization. At the same time, autonomous driving and assisted driving technologies have been increasingly widely used. During the driving process, autonomous driving technology and assisted driving technology can help the car avoid obstacles in time, and timely obstacle avoidance can effectively improve the safety of car driving.

[0003] In the related technology, the road surface image and vehicle position are acquired in real time, and the current obstacle position of the obstacle on the road surface is determined based on the road surface image, and the collision probability is determined based on the current obstacle position and the vehicle position. However, in the actual driving process, obstacles move suddenly, and different obstacles have different controllability. Therefore, it can be seen that the accuracy of the related technology that only considers the current obstacle position to determine the collision probability is poor. Summary of the invention

[0004] In order to improve the accuracy of vehicle obstacle avoidance, the present invention provides an intelligent connected vehicle obstacle avoidance method.

[0005] In a first aspect, the present application provides an intelligent connected vehicle obstacle avoidance method, which adopts the following technical solution: An intelligent connected vehicle obstacle avoidance method, comprising: Acquire vehicle information of the target vehicle, a first position and a moving posture of the obstacle, wherein the vehicle information includes a second position and a vehicle speed; Predicting the movement trajectory of the obstacle within a preset time period according to the movement posture; Obtaining the obstacle category of the obstacle; Determining a collision probability between the obstacle and the target vehicle according to the obstacle category, the first position, the second position, and the moving trajectory; An obstacle avoidance strategy is generated based on the vehicle speed and the collision probability, and the target vehicle is controlled according to the obstacle avoidance strategy.

[0006] In a preferred embodiment of the present application, the method may further be configured such that the method determines the collision probability between the obstacle and the target vehicle according to the obstacle category, the first position, the second position and the moving trajectory, including: Determining a third position of the target vehicle based on the vehicle speed, the preset time duration, and the second position; Determine whether the obstacle arrival point is within a preset safety range of the third position, the obstacle arrival point being the end point of the moving trajectory, which is determined by the first position and the moving trajectory; If not, obtaining driver information, and determining a collision probability between the obstacle and the target vehicle according to the driver information, the first position, the second position, and the obstacle category; If so, the collision probability is determined to be the first preset collision probability.

[0007] In a preferred embodiment of the present application, the driver information may be further configured as follows: the driving time and age of the driver, The determining, according to the driver information, the first position, the second position and the obstacle category, the collision probability between the obstacle and the target vehicle comprises: Determining the driver's reaction time based on the driver's age and the driving time; Determining a fourth position of the target vehicle based on the vehicle speed, the reaction time, and the second position; Determining a fifth position of the obstacle based on the moving speed of the obstacle, the reaction time, and the first position; determining a first collision probability according to the fourth position and the fifth position; Determining a second collision probability based on a first corresponding relationship and the obstacle category, wherein the first corresponding relationship is a corresponding relationship between the obstacle category and the collision probability; The collision probability between the obstacle and the target vehicle is determined according to the first collision probability and the second collision probability.

[0008] In a preferred embodiment, the present application may be further configured as follows: determining the driver's reaction time based on the driver's age and the driving time includes: Determining a reaction time corresponding to the driver's age based on the driver's age and a second corresponding relationship, wherein the second corresponding relationship is a corresponding relationship between the driver's age and the reaction time; Determining a correction factor for correcting reaction time according to the driving time; The reaction time corresponding to the driver's age is corrected using the correction coefficient to obtain the driver's reaction time.

[0009] In a preferred embodiment of the present application, the method may further be configured such that the determining of the first collision probability based on the fourth position and the fifth position includes: Determining a danger range corresponding to the fifth position of the obstacle, and judging whether the fourth position of the target vehicle is within the danger range; If the vehicle is within the danger range, the preset second collision probability is determined as the first collision probability; If the vehicle is not located within the danger range, a preset third collision probability is determined as the first collision probability.

[0010] In a preferred embodiment, the present application may be further configured as follows: generating an obstacle avoidance strategy based on the vehicle speed and the collision probability includes: Determining whether the collision probability is greater than a preset collision probability threshold; If yes, controlling the vehicle speed to change to a first safe speed, and generating the obstacle avoidance strategy based on the first safe speed; If not, obtaining a sixth position of the vehicle in the adjacent lane, and determining the cross-lane distance of the target vehicle based on the sixth position and the second position; A second safe speed is obtained, and an obstacle avoidance strategy is generated according to the cross-road distance and the second safe speed.

[0011] In summary, this application includes the following beneficial technical effects: Obtain vehicle information of the target vehicle, the first position and moving posture of the obstacle; during the actual driving process, the target vehicle is in a dynamic environment, and avoiding obstacles according to dynamic changes can effectively improve the accuracy of the obstacle avoidance probability, so it is necessary to predict the moving trajectory according to the moving posture, so as to combine the main dynamic change factors to avoid obstacles; then obtain the obstacle category of the obstacle, different categories of obstacles have different controllability during driving, so it is necessary to obtain the obstacle category; and when the distance between the target vehicle and the obstacle is closer, the collision probability is higher, so according to the obstacle category, the first position, the second position and the moving trajectory, a more accurate collision probability can be obtained, and then according to the accurate collision probability and vehicle speed, a more reasonable obstacle avoidance strategy can be generated, and the target vehicle is controlled according to the obstacle avoidance strategy; compared with the related art, the present application analyzes obstacles in different dimensions to determine the collision probability, which solves the problem of poor accuracy of the collision probability in the related art. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A flowchart of an intelligent connected vehicle obstacle avoidance method provided in an embodiment of the present application; Figure 2 A schematic structural diagram of an intelligent connected vehicle obstacle avoidance device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0013] The following is combined with Figure 1 To Attachment Figure 2 This application is described in further detail.

[0014] After reading this specification, those skilled in the art may make non-creative modifications to this embodiment as needed, but such modifications are protected by patent law as long as they are within the scope of the claims of this application.

[0015] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings 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.

[0016] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0017] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0018] The embodiment of the present application provides an intelligent networked vehicle obstacle avoidance method, which is executed by an on-board electronic device, and the on-board electronic device is a terminal device. The terminal device can be connected indirectly or directly through wired or wireless communication, and the embodiment of the present application is not limited here. Figure 1 The figure is a flow chart of a method for avoiding obstacles of an intelligent networked vehicle provided in an embodiment of the present application, the method comprising step S1, step S2, step S3, step S4 and step S5, wherein: Step S1: Obtain vehicle information of the target vehicle, a first position and a moving posture of the obstacle, and the vehicle information includes a second position and a vehicle speed.

[0019] Specifically, when the on-board electronic device detects that the target vehicle is started, the vehicle information of the target vehicle, the first position of the obstacle and the moving posture of the obstacle are obtained; the target vehicle is equipped with an image acquisition device, which can acquire the moving posture of the obstacle and upload it to the on-board electronic device, and the second position and vehicle speed can be detected by the position sensor and the vehicle speed sensor respectively and uploaded to the on-board electronic device. In the embodiment of the present application, the moving posture can be the direction of the obstacle.

[0020] Step S2: predict the movement trajectory of the obstacle within a preset time period according to the movement posture.

[0021] Specifically, the preset time is pre-set by the technician based on work experience, and may be 1 second, 1.5 seconds or 3 seconds, etc.; the preset time is the maximum reaction time of drivers of different age groups and driving time after seeing an obstacle in actual scenarios, that is, after seeing the obstacle, the driver will make an obstacle avoidance reaction within this preset time no matter what; wherein, the moving trajectory of the obstacle can be predicted by the time series neural network model and the current moving speed of the obstacle, and the embodiment of the present application does not limit the specific process of predicting the moving trajectory of the obstacle.

[0022] Step S3: Obtain the obstacle category of the obstacle.

[0023] Specifically, obstacle categories include: first category, second category and third category, where the first category can be a stationary object, such as a vehicle or a sign stationary on the road. When it is the first category, the movement trajectory corresponding to the obstacle is 0, that is, there is no movement trajectory; the second category can be a moving child (a human under the age of six or a person under 130 cm in height), an animal and a non-motor vehicle, and the third category is a moving motor vehicle and a non-child. The on-board electronic device identifies the received obstacle image to determine the obstacle category, and the embodiment of the present application does not limit the specific process of identification.

[0024] Step S4: Determine the collision probability between the obstacle and the target vehicle according to the obstacle category, the first position, the second position and the moving trajectory.

[0025] Specifically, according to the obstacle category, the first position, the second position and the moving trajectory, the specific process of determining the collision probability can refer to the following embodiments. It can be understood that different obstacle categories have different collision probabilities with the target vehicle, such as a stationary marker and a moving child. The stationary marker will not move during the driving process of the target vehicle, so the target vehicle only needs to adjust the vehicle position in time to avoid collision; in comparison, the moving child has greater uncertainty during the driving process, and the collision probability between the obstacle and the target vehicle will be greatly increased at this time, and when the moving trajectory of the moving child coincides with the forward route of the target vehicle, the collision probability will further increase; and when the distance between the target vehicle and the obstacle is closer, the collision probability will also increase accordingly. When the distance between the obstacle and the target vehicle is closer, the overlap rate of the moving trajectory of the obstacle and the target vehicle is higher, and the collision probability will also increase accordingly. Therefore, a more accurate collision probability can be obtained according to the obstacle category, the first position, the second position and the moving trajectory.

[0026] Further, determining the collision probability between the obstacle and the target vehicle according to the obstacle category, the first position, the second position and the moving trajectory includes: Determining a third position of the target vehicle based on the vehicle speed, the preset time duration, and the second position; Determine whether the obstacle arrival point is within a preset safety range of the third position, the obstacle arrival point being the end point of the moving trajectory, which is determined by the first position and the moving trajectory; If not, obtaining the driver information, and determining the collision probability between the obstacle and the target vehicle based on the driver information, the first position, the second position, and the obstacle category; If so, the collision probability is determined to be the first preset collision probability.

[0027] Specifically, the first forward distance of the target vehicle is obtained according to the vehicle speed and the preset time, and then the third position, that is, the position of the target vehicle after moving, is obtained according to the first forward distance and the second position. The preset safety range of the third position is pre-set. When the obstacle arrival point is within the preset safety range, it indicates that the obstacle is within the safety range of the third position. At this time, the vehicle will not collide with the obstacle, that is, the first preset collision probability is 0 (in other words, assuming that a driver reacts within the maximum reaction time, there is still a safety range between the position of the vehicle and the obstacle, then the vehicle and the obstacle are almost impossible to collide); otherwise, it indicates that a collision with the obstacle may occur. At this time, it is necessary to predict the reaction time for this determined driver based on the driver information, and re-determine the position that the obstacle and the target vehicle may reach within this reaction time based on the reaction time, and then determine an accurate collision probability in combination with the obstacle category.

[0028] Based on the above embodiment, when the moving speed of the obstacle and the speed of the vehicle are faster and the distance between the two is closer, the collision time from the collision to the collision is shorter, and as the collision time decreases, the collision probability also increases. Therefore, it is necessary to determine the third position of the target vehicle and judge whether the obstacle arrival point is within the preset safety range of the third position. When the obstacle arrival point is within the preset safety range, it indicates that the collision probability between the target vehicle and the obstacle is extremely small, so it is directly determined as the first preset collision probability; if the obstacle arrival point is not within the preset safety range, it indicates that there is a greater collision probability, so it is necessary to combine the driver information, the first position, the second position and the obstacle category to obtain a more accurate collision probability.

[0029] Further, determining the collision probability between the obstacle and the target vehicle according to the driver information, the first position, the second position and the obstacle category includes: Determine the driver's reaction time based on the driver's age and driving time; determining a fourth position of the target vehicle based on the vehicle speed, the reaction time, and the second position; Determine a fifth position of the obstacle based on the movement speed, the reaction time, and the first position of the obstacle; determining a first collision probability according to the fourth position and the fifth position; Determining a second collision probability based on the first corresponding relationship and the obstacle category, where the first corresponding relationship is a corresponding relationship between the obstacle category and the collision probability; The collision probability between the obstacle and the target vehicle is determined according to the first collision probability and the second collision probability.

[0030] Specifically, as the driver's age increases, the driver's reaction time will increase accordingly, and as the driving time increases, the driver becomes more tired and the driver's reaction time also increases accordingly; as the reaction time increases, the driver's ability to deal with emergencies becomes worse and dangerous accidents are more likely to occur, that is, the probability of collision increases accordingly, so the driver's reaction time needs to be determined based on the driver's age and driving time. The specific process of determining the reaction time includes: determining the reaction time corresponding to the driver's age according to the driver's age and a second corresponding relationship, the second corresponding relationship is the corresponding relationship between the driver's age and the reaction time, and the second corresponding relationship is established by the technical personnel. The specific process includes: obtaining multiple first reference driver information, the first reference driver information includes the number of first reference drivers and the corresponding test reaction time of each driver; calculating the sum of the test reaction times according to all test reaction times, and then determining the average reaction time according to the sum of the test reaction times and the number of drivers, and determining the average reaction time as the reaction time corresponding to the driver's age; and then determining the correction coefficient corresponding to the above driving time according to the corresponding relationship between the driving time and the correction coefficient. It can be understood that the increase in driving time will increase the driver's fatigue and the reaction time will increase. Therefore, the reaction time needs to be corrected. The longer the driving time, the larger the correction coefficient; reaction time = reaction time corresponding to the driver's age * correction coefficient. Determining a second forward distance of the vehicle according to the vehicle speed and the reaction time, and then obtaining a fourth position according to the second forward distance and the second position; determining a third forward distance of the obstacle according to the moving speed and the reaction time of the obstacle, and then obtaining a fifth position according to the third forward distance and the first position; and then determining a first collision probability according to the fourth position and the fifth position includes: determining a danger range corresponding to a fifth position of the obstacle, and determining whether a fourth position of the target vehicle is within the danger range; If it is within the danger range, the preset second collision probability is determined as the first collision probability; If the vehicle is not within the danger range, the preset third collision probability is determined as the first collision probability.

[0031] A circle can be established with the fifth position of the obstacle as the center and a preset distance (pre-set by the technician) as the radius, and the range covered by the circle is determined as the danger range; it is understandable that in actual driving, the obstacle may slide due to loss of control or falling, so considering the occurrence of sliding, it is necessary to determine the danger range of the obstacle. If the fourth position of the target vehicle is within the danger range, the preset second collision probability is determined as the first collision probability, such as 80% or 70%, etc.; if it is not within the danger range, it is determined as the preset third collision probability, such as 10% or 15%, etc.; the embodiment of the present application does not limit the specific numerical value, and the preset second collision probability is greater than the preset third collision probability.

[0032] Furthermore, the second collision probability is determined by the first corresponding relationship (the corresponding relationship between the obstacle category and the collision probability), and the corresponding relationship between the obstacle category and the collision probability is set by the technician based on multiple historical data and pre-entered into the on-board electronic device, thereby determining the second collision probability. In an embodiment of the present application, the second collision probability of the first category < the second collision probability of the third category < the second collision probability of the second category. The sum of the collision probabilities of the first collision probability and the second collision probability is calculated, and the sum of the collision probabilities is determined as the collision probability. It can be understood that when the driver's reaction time is long and the obstacle category is the second category or the third category, the collision probability will be greatly increased, so the sum of the collision probabilities is determined as the collision probability of the obstacle and the target vehicle, so as to effectively improve the accuracy of determining the collision probability.

[0033] Step S5: Generate an obstacle avoidance strategy based on the vehicle speed and collision probability, and control the target vehicle according to the obstacle avoidance strategy.

[0034] Specifically, the specific process of generating an obstacle avoidance strategy according to the vehicle speed and collision probability can be referred to as follows. Then, a corresponding control signal is generated according to the obstacle avoidance strategy, and the control signal is sent to the corresponding device to control the target vehicle, reduce the collision probability between the target vehicle and the obstacle, and minimize the loss.

[0035] Furthermore, an obstacle avoidance strategy is generated based on the vehicle speed and collision probability, including: Determine whether the collision probability is greater than a preset collision probability threshold; If yes, control the vehicle speed to change to a first safe speed, and generate an obstacle avoidance strategy based on the first safe speed; If not, obtaining a sixth position of the vehicle in the adjacent lane, and determining the cross-lane distance of the target vehicle based on the sixth position and the second position; The second safe speed is obtained, and an obstacle avoidance strategy is generated according to the cross-lane distance and the second safe speed.

[0036] Specifically, the preset collision probability threshold and the second safe speed are set by technicians based on work experience; the first safe speed is 0; when the collision probability is greater than the preset collision probability threshold, it indicates that the collision probability between the obstacle and the target vehicle is large, and there may be a serious collision with the obstacle. In order to minimize the damage to the obstacle, it is necessary to control the target vehicle to stop moving forward to avoid the obstacle. If not, it indicates that the collision probability between the obstacle and the target vehicle is small at this time, and obstacle avoidance can be achieved by deviating from the original driving road, that is, driving into the adjacent lane. Before the target vehicle enters the adjacent lane, it is also necessary to consider whether it collides with the vehicle in the adjacent lane to avoid the vehicle in the adjacent lane from bringing danger to the driver of the target vehicle. Therefore, it is necessary to obtain the sixth position of the vehicle in the adjacent lane. The method for obtaining the sixth position is the same as the method for obtaining the first position of the obstacle, and the embodiments of this application will not be repeated. The process of determining the cross-lane distance according to the sixth position and the second position includes: determining the distance difference based on the second position and the sixth position; and determining the cross-lane distance according to the distance difference and the corresponding relationship; the distance difference can be obtained according to the Euclidean distance calculation formula, and the above corresponding relationship is the corresponding relationship between the distance difference and the cross-lane distance is pre-set by the technician; it can be understood that as the distance difference increases, the cross-lane distance increases. The on-board electronic device sends the preset safe driving speed to the vehicle speed control system so that the vehicle speed of the target vehicle drops to the preset safe driving speed, and at the same time sends the cross-lane distance to the vehicle steering wheel control system so as to control the target vehicle to drive into the adjacent lane at the preset safe driving speed.

[0037] Based on the above embodiment, the collision probability and the preset collision probability threshold are judged. When the collision probability is greater than the preset collision probability threshold, it indicates that there is a great possibility of a serious collision between the obstacle and the target vehicle. At this time, the vehicle speed is directly controlled to be the first safe speed, and the vehicle is braked to avoid a collision between the target vehicle and the obstacle. When the collision probability is not greater than the preset collision probability threshold, it indicates that the probability of a head-on collision between the obstacle and the target vehicle is small. At this time, controlling the target vehicle to drive into other lanes can reduce the damage to the obstacle and the danger caused by braking the target vehicle. Therefore, it is necessary to obtain the fourth position in the adjacent lane to ensure the rationality of the cross-lane distance, and then generate an obstacle avoidance strategy based on the cross-lane distance and the second safe speed, so as to effectively improve the rationality of the obstacle avoidance strategy.

[0038] Based on the above embodiments, the vehicle information of the target vehicle, the first position and the moving posture of the obstacle are obtained; during the actual driving process, the target vehicle is in a dynamic environment, and avoiding obstacles according to dynamic changes can effectively improve the accuracy of the obstacle avoidance probability, so it is necessary to predict the moving trajectory according to the moving posture, so as to avoid obstacles in combination with the main dynamic change factors; then the obstacle category of the obstacle is obtained, and obstacles of different categories have different controllability during driving, so it is necessary to obtain the obstacle category; and when the distance between the target vehicle and the obstacle is closer, the collision probability is higher, so according to the obstacle category, the first position, the second position and the moving trajectory, a more accurate collision probability can be obtained, and then according to the accurate collision probability and vehicle speed, a more reasonable obstacle avoidance strategy can be generated, and the target vehicle is controlled according to the obstacle avoidance strategy; compared with the related art, the present application analyzes obstacles in different dimensions to determine the collision probability, which solves the problem of poor accuracy of the collision probability in the related art.

[0039] The above are only some implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. An obstacle avoidance method for an intelligent connected vehicle, characterized in that: include: Acquire vehicle information of the target vehicle, a first position and a moving posture of the obstacle, wherein the vehicle information includes a second position and a vehicle speed; Predicting the movement trajectory of the obstacle within a preset time period according to the movement posture; Obtaining the obstacle category of the obstacle; Determining a collision probability between the obstacle and the target vehicle according to the obstacle category, the first position, the second position, and the moving trajectory; An obstacle avoidance strategy is generated based on the vehicle speed and the collision probability, and the target vehicle is controlled according to the obstacle avoidance strategy.

2. The intelligent connected vehicle obstacle avoidance method according to claim 1, characterized in that: The determining, according to the obstacle category, the first position, the second position, and the moving trajectory, a collision probability between the obstacle and the target vehicle includes: Determining a third position of the target vehicle based on the vehicle speed, the preset time duration, and the second position; Determine whether the obstacle arrival point is within a preset safety range of the third position, the obstacle arrival point being the end point of the moving trajectory, which is determined by the first position and the moving trajectory; If not, obtaining driver information, and determining a collision probability between the obstacle and the target vehicle according to the driver information, the first position, the second position, and the obstacle category; If so, the collision probability is determined to be the first preset collision probability.

3. The intelligent connected vehicle obstacle avoidance method according to claim 2, characterized in that: The driver information includes: the driver's driving time and the driver's age, The determining, according to the driver information, the first position, the second position, and the obstacle category, a collision probability between the obstacle and the target vehicle includes: Determining the driver's reaction time based on the driver's age and the driving time; Determining a fourth position of the target vehicle based on the vehicle speed, the reaction time, and the second position; Determining a fifth position of the obstacle based on the moving speed of the obstacle, the reaction time, and the first position; determining a first collision probability according to the fourth position and the fifth position; Determining a second collision probability based on a first corresponding relationship and the obstacle category, wherein the first corresponding relationship is a corresponding relationship between the obstacle category and the collision probability; The collision probability between the obstacle and the target vehicle is determined according to the first collision probability and the second collision probability.

4. The intelligent connected vehicle obstacle avoidance method according to claim 3, characterized in that: The determining the driver's reaction time based on the driver's age and the driving time includes: Determining a reaction time corresponding to the driver's age based on the driver's age and a second corresponding relationship, wherein the second corresponding relationship is a corresponding relationship between the driver's age and the reaction time; Determining a correction factor for correcting reaction time according to the driving time; The reaction time corresponding to the driver's age is corrected using the correction coefficient to obtain the driver's reaction time.

5. The intelligent connected vehicle obstacle avoidance method according to claim 3, characterized in that: The determining a first collision probability based on the fourth position and the fifth position includes: Determining a danger range corresponding to the fifth position of the obstacle, and judging whether the fourth position of the target vehicle is within the danger range; If the vehicle is within the danger range, the preset second collision probability is determined as the first collision probability; If the vehicle is not located within the danger range, a preset third collision probability is determined as the first collision probability.

6. The intelligent connected vehicle obstacle avoidance method according to claim 1, characterized in that: The generating an obstacle avoidance strategy based on the vehicle speed and the collision probability comprises: Determining whether the collision probability is greater than a preset collision probability threshold; If yes, controlling the vehicle speed to change to a first safe speed, and generating the obstacle avoidance strategy based on the first safe speed; If not, obtaining a sixth position of the vehicle in the adjacent lane, and determining the cross-lane distance of the target vehicle based on the sixth position and the second position; A second safe speed is obtained, and an obstacle avoidance strategy is generated according to the cross-road distance and the second safe speed.

Images