Vehicle steering obstacle avoidance method, device and storage medium

Abstract

The embodiment of the present invention discloses a vehicle steering obstacle avoidance method, device and storage medium, including: when it is determined that there is a collision risk between the target vehicle and the first obstacle and the steering obstacle avoidance condition is met, obtaining a steering obstacle avoidance trajectory for the target vehicle; obtaining the lateral speed of the target vehicle, constructing an improved constant turn rate and speed model according to the lateral speed, estimating the improved constant turn rate and speed model to obtain final state information; and performing steering obstacle avoidance control on the target vehicle according to the steering obstacle avoidance trajectory and the final state information. By introducing the lateral speed of the target vehicle to construct an improved lateral rate and speed model, and obtaining the final state information through the model, the obtained final state information is made more accurate, and steering obstacle avoidance control is performed along the pre-acquired steering obstacle avoidance trajectory according to the final state information, so that when there is a collision risk, precise control of vehicle steering is achieved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of unmanned driving technology, and in particular to a vehicle steering obstacle avoidance method, device and storage medium. Background Art

[0002] With the development of autonomous driving perception algorithms and hardware computing power, more and more cars are equipped with ADAS (Advanced Driving Assistance System), among which FCW (Forward Collision Warning) and AEB (Autonomous Emergency Breaking) are the most representative.

[0003] However, both FCW and AEB focus on the longitudinal direction of the vehicle. When a collision is about to occur, the human-machine interface reminds the driver to brake or the vehicle automatically brakes to slow down the vehicle to avoid it. However, when an obstacle suddenly appears in front and the vehicle's speed is too high, FCW and AEB can only achieve partial deceleration but not real obstacle avoidance, which still poses a high risk of injury to vehicles or pedestrians. Summary of the invention

[0004] The embodiments of the present invention provide a vehicle steering obstacle avoidance method, device and storage medium to achieve steering obstacle avoidance control of a vehicle.

[0005] In a first aspect, an embodiment of the present invention provides a vehicle steering obstacle avoidance method, comprising: when it is determined that there is a collision risk between a target vehicle and a first obstacle and a steering obstacle avoidance condition is met, obtaining a steering obstacle avoidance trajectory for the target vehicle;

[0006] Acquire the lateral speed of the target vehicle, construct an improved constant turn rate and speed model according to the lateral speed, and estimate the improved constant turn rate and speed model to obtain final state information, wherein the final state information includes the vehicle position and yaw angle;

[0007] The target vehicle is controlled to avoid obstacles by steering according to the steering obstacle avoidance trajectory and the final state information.

[0008] In a second aspect, an embodiment of the present invention provides an electronic device, the electronic device comprising:

[0009] one or more processors;

[0010] a storage device for storing one or more programs,

[0011] When one or more programs are executed by one or more processors, the one or more processors implement the above method.

[0012] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the program implements the method described above when executed by a processor.

[0013] The technical solution of the embodiment of the present invention constructs an improved lateral rate and speed model by introducing the lateral speed of the target vehicle, and obtains final state information through the model, so that the obtained final state information is more accurate, and performs steering obstacle avoidance control along a pre-acquired steering obstacle avoidance trajectory according to the final state information, so as to achieve precise control of vehicle steering when a collision risk occurs. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0015] Figure 1 is a flow chart of a vehicle steering obstacle avoidance method provided by an embodiment of the present invention;

[0016] Figure 2 is a flow chart of a method for obtaining a vehicle lateral speed provided by an embodiment of the present invention;

[0017] Figure 3 is a flow chart of another vehicle steering obstacle avoidance method provided by an embodiment of the present invention;

[0018] Figure 4 is a schematic structural diagram of a vehicle steering obstacle avoidance device provided by an embodiment of the present invention;

[0019] Figure 5 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention.

[0021] It should also be noted that, for ease of description, only the part related to the present invention but not all the content is shown in the accompanying drawings. It should be mentioned before discussing the exemplary embodiments in more detail that some exemplary embodiments are described as the processing or method described as a flow chart. Although the flow chart describes each operation (or step) as a sequential process, many operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of each operation can be rearranged. When its operation is completed, the process can be terminated, but it can also have additional steps not included in the accompanying drawings. The process can correspond to a method, software implementation, hardware implementation, etc.

[0022] Figure 1 1 is a flow chart of a vehicle steering obstacle avoidance method provided by an embodiment of the present invention. This embodiment is applicable to the case of steering obstacle avoidance control of a vehicle. The method can be executed by a vehicle steering obstacle avoidance device in an embodiment of the present invention, and the device can be implemented in software and / or hardware. Figure 1 As shown, the method specifically includes the following operations:

[0023] Step S101, when it is determined that there is a collision risk between the target vehicle and the first obstacle and the steering obstacle avoidance condition is met, a steering obstacle avoidance trajectory for the target vehicle is obtained.

[0024] Optionally, when it is determined that there is a collision risk between the target vehicle and the first obstacle and the steering obstacle avoidance condition is met, a steering obstacle avoidance trajectory for the target vehicle is obtained, including: obtaining operating parameters of the target vehicle, and calculating the collision time based on the operating parameters and first associated information, wherein the operating parameters include longitudinal speed and longitudinal acceleration; when the collision time is less than a preset time, it is determined that there is an obstacle avoidance risk between the target vehicle and the first obstacle, and the minimum braking obstacle avoidance distance and the minimum steering obstacle avoidance distance of the target vehicle are obtained; second associated information of a second obstacle whose distance to the target vehicle is within a preset range is obtained; when it is determined that the steering obstacle avoidance condition is met based on the minimum braking obstacle avoidance distance, the minimum steering obstacle avoidance distance and the second associated information, a steering obstacle avoidance trajectory for the target vehicle is obtained.

[0025] Optionally, when it is determined that the steering obstacle avoidance condition is met based on the minimum braking obstacle avoidance distance, the minimum steering obstacle avoidance distance and the second associated information, a steering obstacle avoidance trajectory for the target vehicle is obtained, including: determining that there is a steering obstacle avoidance space based on the second associated information; when it is determined that the minimum steering obstacle avoidance distance is less than the minimum braking obstacle avoidance distance, obtaining the steering obstacle avoidance trajectory of the target vehicle based on the steering obstacle avoidance space.

[0026] Specifically, the present embodiment will obtain the operating parameters of the target vehicle and the first associated information of the first obstacle, wherein the operating parameters specifically include the longitudinal speed and the longitudinal acceleration, and the first associated information specifically includes the obstacle type, the lateral distance of the obstacle, the longitudinal distance of the obstacle, the lateral acceleration of the obstacle, the longitudinal acceleration of the obstacle and the width of the obstacle, and the longitudinal direction in the present embodiment refers to the tangent along the turning obstacle avoidance trajectory and points to the direction of the vehicle's travel, while the lateral direction refers to the direction perpendicular to the longitudinal direction and points to the direction of the center of the turning obstacle avoidance trajectory. Thus, the collision time between the two can be calculated based on the longitudinal speed and longitudinal acceleration of the target vehicle, and the longitudinal distance of the obstacle and the longitudinal acceleration of the first obstacle and other related information. In the present embodiment, a preset time is pre-set, so when it is determined that the collision time is less than the preset time, it is considered that the target vehicle and the first obstacle have a collision risk; if the collision time is greater than or equal to the preset time, the automatic emergency steering obstacle avoidance (AES) process is exited, that is, the target vehicle is not automatically controlled by AES.

[0027] It should be noted that when it is determined that there is an obstacle avoidance risk, in order to avoid the target vehicle from colliding with the first obstacle, it is necessary to intervene in the target vehicle in advance at an appropriate time. Therefore, other obstacles within a preset range of distance from the target vehicle will be obtained, and the obstacle is marked as a second obstacle. The second associated information may specifically include information such as the obstacle type, obstacle lateral distance, obstacle longitudinal distance, obstacle lateral acceleration, obstacle longitudinal acceleration and obstacle width of the second obstacle. In addition, the minimum braking obstacle avoidance distance D1 and the minimum turning obstacle avoidance distance D2 of the target vehicle will also be obtained. Therefore, the turning obstacle avoidance trajectory for the target vehicle will be obtained only when it is determined that the turning obstacle avoidance conditions are met based on the minimum braking obstacle avoidance distance, the minimum turning obstacle avoidance distance and the second associated information.

[0028] Among them, in this embodiment, the latest turning time of the target vehicle is determined based on the obstacle width, obstacle lateral distance, obstacle lateral speed and other related information of the first obstacle, and the minimum turning obstacle avoidance distance D2 of the target vehicle is determined based on the longitudinal speed of the target vehicle, the longitudinal speed of the first obstacle, the latest turning time and the preset system response time. In addition, the minimum braking distance D1 corresponding to the automatic emergency braking AEB decision of the target vehicle is also obtained, and D1 can be set in advance by the AEB decision. The specific setting method of the minimum braking distance D1 is not limited in this embodiment.

[0029] It is worth mentioning that in this embodiment, when it is determined that there is a turning obstacle avoidance space according to the second associated information, and when it is determined that the minimum turning obstacle avoidance distance D2 is less than the minimum braking obstacle avoidance distance D1, it will also be determined whether the driver has taken over the target vehicle. If the driver's operation instruction is not received, it is determined that the driver has not taken over the target vehicle. At this time, the turning obstacle avoidance direction will be determined according to the turning obstacle avoidance space, and the turning obstacle avoidance trajectory will be determined based on the turning obstacle avoidance direction and the preset acceleration. The present invention performs turning obstacle avoidance based on the situation where there is no driver taking over. When a driver takes over, the automatic driving system will exit automatic control and the driver will operate the automatic driving vehicle. Among them, the turning obstacle avoidance direction includes left or right, specifically referring to the target vehicle avoiding the first obstacle by turning left or changing lanes to the left; or the target vehicle avoiding the first obstacle by turning right or changing lanes to the right. If it is determined that there is a turning obstacle avoidance space only on the left side of the target vehicle, the turning obstacle avoidance direction is to the left; if it is determined that there is a turning obstacle avoidance space only on the right side of the target vehicle, the turning obstacle avoidance direction is to the right; if it is determined that there is a turning obstacle avoidance space on both the left and right sides of the target vehicle, the turning obstacle avoidance direction is determined according to the relative lateral distance between the target vehicle and the first obstacle. In addition, the preset lateral acceleration is the lateral acceleration of the target vehicle when turning, which is an acceleration set with the coordinate system of the target vehicle as a reference. By adding the constraint of the preset lateral acceleration to the turning obstacle avoidance edge trajectory, the stability of the target vehicle during emergency turning can be fundamentally guaranteed, thereby achieving the purpose of improving vehicle safety. In the embodiment disclosed herein, a quintic polynomial is selected as the trajectory equation of AES, that is, the trajectory equation of AES is the equation shown in the following expression (1):

[0030]

[0031] Among them, x represents the longitudinal distance, y represents the lateral distance, and y e represents the lateral displacement of the target vehicle to complete the turning and lane changing process (i.e., the lateral offset distance required for obstacle avoidance), x e Indicates the longitudinal displacement of the target vehicle when completing the turning and lane changing process.

[0032] In the process of the target vehicle turning to avoid the first obstacle, it is assumed that the longitudinal speed of the target vehicle remains unchanged, so the longitudinal distance x and the longitudinal displacement xe can be converted into time quantities t and te. Specifically, x=Vx*t and xe=Vx*te, where Vx represents the longitudinal speed of the target vehicle and te represents the time required for the target vehicle to complete the turning to avoid the obstacle. Based on expression (1), the set trajectory equation shown in expression (2) can be obtained as follows:

[0033]

[0034] Among them, t is the first variable, which represents time; te is the first coefficient, which represents the time required for the target vehicle to complete the steering obstacle avoidance; ye is the second coefficient, which represents the lateral offset distance required for obstacle avoidance.

[0035] By taking the second-order derivative of the above expression (2), we can obtain the relationship between the lateral acceleration of the target vehicle and time during the entire steering obstacle avoidance process, that is, the second-order derivative formula is as shown in the following expression (3):

[0036]

[0037] Among them, a y (t) represents the lateral acceleration, and the solution formula for the maximum value of the lateral acceleration is determined based on the second-order derivative formula; the preset lateral acceleration is determined as the maximum value of the lateral acceleration, so as to determine the first coefficient in the solution formula according to the preset lateral acceleration. The value of the determined first coefficient is substituted into the set trajectory equation to obtain the steering obstacle avoidance trajectory L.

[0038] Step S102, obtaining the lateral speed of the target vehicle, constructing an improved constant turn rate and speed model according to the lateral speed, and estimating the improved constant turn rate and speed model to obtain final state information.

[0039] The final state information includes the vehicle position and yaw angle.

[0040] Optionally, an improved constant turn rate and speed model is constructed according to the lateral speed, and the improved constant turn rate and speed model is estimated to obtain final state information, including: updating the lateral position according to the lateral speed, and determining second historical state information according to the updated lateral position, wherein the second historical state information includes the lateral position, longitudinal position, yaw angle, longitudinal speed and yaw angular velocity; constructing an improved constant turn rate and speed model according to the second historical state information, and estimating the improved constant turn rate and speed model to obtain second initial state information; and correcting the second initial state information according to the measured longitudinal speed and yaw angular velocity to obtain the final state information.

[0041] Specifically, in this embodiment, after obtaining the lateral velocity v at time T y After that, the lateral position will be updated according to the lateral velocity And determine the second historical state information based on the updated lateral position, wherein the second historical state information includes the lateral position, longitudinal position, yaw angle, longitudinal speed and yaw angular velocity, and the second historical state information can specifically be the time T adjacent to the current time T+1, and construct an improved constant turn rate and speed model based on the second historical state information.

[0042] For example, Figure 2As shown, obtaining the lateral speed of the target vehicle is specifically described, and the method steps specifically include the following operations:

[0043] Step S201, obtaining first historical status information.

[0044] The first historical state information includes the lateral velocity and the yaw angular velocity, and in this embodiment, the first historical state information may be specifically acquired at time T-1.

[0045] Step S202: constructing a vehicle dynamics model according to the first historical state information, and estimating the vehicle dynamics model to obtain first initial state information.

[0046] Specifically, in this embodiment, a vehicle dynamics model is constructed according to the first historical state information. The following formula (4) is an example of the constructed vehicle dynamics model:

[0047]

[0048] The state variables in the vehicle dynamics model are Y = [v y ω] T , where the measured quantity is the yaw angular velocity ω and the predicted quantity is the lateral velocity v y According to the above vehicle dynamics model, the Kalman filter algorithm is used to estimate and obtain the first initial state information Wherein, A represents the first parameter of the vehicle dynamics model, and B represents the second parameter of the vehicle dynamics model. The Kalman filter algorithm can be used to estimate the state quantity at the next moment using the state quantity at the previous moment. Therefore, when the first historical state information is at moment T-1, the first historical state information can be used to estimate the first initial state information at moment T.

[0049] Step S203, correcting the first initial state information according to the measured yaw angular velocity to obtain the corrected first initial state information, wherein the corrected first initial state information includes the lateral velocity.

[0050] Optionally, the first initial state information is corrected according to the measured yaw angular velocity to obtain the corrected first initial state information, including: obtaining a first covariance matrix corresponding to the first initial state information, and a first measurement matrix and a first noise matrix corresponding to the measured yaw angular velocity; calculating a first Kalman gain according to the first covariance matrix, the first measurement matrix and the first noise matrix; and correcting the first initial state information according to the measured yaw angular velocity, the first Kalman gain and the first measurement matrix to obtain the corrected first initial state information.

[0051] Specifically, in this implementation, the following formula (5) is used to obtain the covariance matrix corresponding to the first initial state information:

[0052] M k+1 =A*M k *A T +F (5)

[0053] Among them, M k+1 represents the first covariance matrix corresponding to the first initial state information, M k represents the covariance matrix corresponding to the historical state information, A represents the first parameter of the vehicle dynamics model, and F represents the covariance matrix of the predicted noise, which is a 2*2 specified matrix.

[0054] It should be noted that, since the measured quantity in this embodiment is the yaw angular velocity ω, the first measurement matrix S=[0 1] corresponding to the measured yaw angular velocity is the first noise matrix W=set_noise_w^2, and according to the first covariance matrix M k+1 , the first measurement matrix S and the first noise matrix W, the first Kalman gain is calculated using the following formula (6):

[0055] K k1 =M k+1 S T (SM k+1 S T +W) -1 (6)

[0056] The state quantity measured by the sensor is as follows: k+1 =[w], then according to the measured state quantity, the first Kalman gain and the first measurement matrix, the first initial state information is corrected according to the following formula (7) to obtain the corrected first initial state information:

[0057] Y′ K+1 =Y K+1 +K k1 (n k+1 -SY K+1 ) (7)

[0058] Among them, Y′ K+1 represents the first initial state information obtained after correction, Y K+1 Represents the first initial state information, K k1 represents the first Kalman gain, n k+1 represents the measured yaw rate, S represents the first measurement matrix, where Y′ K+1 Including lateral velocity, which can be And the first initial state information at this time may specifically be the last moment, that is, moment T.

[0059] Wherein, on the basis of obtaining the lateral velocity, an improved constant turn rate and speed model can be constructed according to the lateral velocity. The following formula (8) is an example of the improved constant turn rate and speed model:

[0060]

[0061] Improved constant rotation rate and speed model state variables are Among them, the measured quantity is the longitudinal velocity v x and yaw rate ω, the predicted quantities are longitudinal position x, lateral position y, and yaw angle The improved constant rotation rate and speed model is estimated using a Kalman filter algorithm to obtain the second initial state information X(k+1).

[0062] Optionally, the second initial state information is corrected according to the measured longitudinal velocity and yaw angular velocity to obtain the final state information, including: obtaining a second covariance matrix corresponding to the second initial state information, and a second measurement matrix and a second noise matrix corresponding to the measured longitudinal velocity and yaw angular velocity; calculating the second Kalman gain according to the second covariance matrix, the second measurement matrix and the second noise matrix; correcting the second initial state information according to the measured longitudinal velocity and yaw angular velocity, the second Kalman gain and the second measurement matrix to obtain the final state information.

[0063] Specifically, for each term in formula (8) The partial derivatives of each state variable are calculated to form the following Jacobian matrix J:

[0064]

[0065]

[0066]

[0067]

[0068]

[0069]

[0070]

[0071] Specifically, in this embodiment, the obtained Jacobian matrix J is used to obtain the second covariance matrix corresponding to the second initial state information using the following formula (10):

[0072] P k+1 =J*P k *J T+Q (10)

[0073] Among them, P k+1 represents the second covariance matrix corresponding to the second initial state information, J represents the Jacobian matrix, Q is the covariance matrix of the predicted noise, P k Represents the covariance matrix corresponding to the second historical state information.

[0074] It should be noted that the noise introduced in the improved constant rotation rate and speed model mainly comes from two sources: linear acceleration u a and yaw acceleration Noise. The influence of these two acceleration measures on the state variables is expressed as follows:

[0075]

[0076] Assume that the linear acceleration u a and yaw acceleration The mean of the noise is 0 and the variance is These two quantities are set in the model.

[0077]

[0078] Therefore, the covariance matrix Q of the prediction noise can be expressed by the following formula (13):

[0079] Q=E[(XE(X)·(XE(X) T )]=E[Guu T G T ]=G·E[uu T ]·G T (13)

[0080] Improved longitudinal velocity v of target vehicle in constant turn rate and velocity model x , yaw angular velocity ω, so the second measurement matrix corresponding to the measured longitudinal velocity and yaw angular velocity The measurement noise mainly comes from the velocity measurement error and the yaw rate measurement error. set_noise_v = 0.02; set_noise_w = 0.01, so the second noise matrix And according to the second covariance matrix P k+1 , the second measurement matrix H and the second noise matrix R, the second Kalman gain is calculated using the following formula (14):

[0081] K k2 =P k+1 H T (HP k+1 H T +R) -1 (14)

[0082] The state quantities measured by the sensor are as follows: k+1 =[v x w], then according to the measured state quantity, the second Kalman gain and the second measurement matrix, the second initial state information is corrected according to the following formula (15) to obtain the final state information:

[0083] X′ K+1 =X K+1 +K k2 (z k+1 -HX K+1 ) (15)

[0084] Among them, X′ K+1 represents the final state information obtained after correction, X K+1 Represents the second initial state information, K k represents the second Kalman gain, z k+1 represents the measured longitudinal velocity and yaw angular velocity, and H represents the second measurement matrix.

[0085] Step S103, performing steering obstacle avoidance control on the target vehicle according to the steering obstacle avoidance trajectory and the final state information.

[0086] Optionally, the target vehicle is controlled to steer for obstacle avoidance based on the steering obstacle avoidance trajectory and the final state information, including: determining the target point position on the steering obstacle avoidance trajectory that is closest to the target vehicle position; determining the lateral deviation based on the target point position and the current vehicle position, and determining the heading deviation based on the current yaw angle; and performing steering obstacle avoidance control on the target vehicle based on the lateral deviation and the heading deviation.

[0087] Specifically, since the final state information contains the vehicle position (x, y) and yaw angle Therefore, the target vehicle is estimated by improving the constant turn rate and speed model, and the final state information of the real-time estimation is obtained. After turning to the obstacle avoidance trajectory L, the target vehicle will be controlled to turn to avoid obstacles. The vehicle steering obstacle avoidance control algorithms include: Stanley algorithm Stanley, linear quadratic optimal control algorithm LQR, model predictive control algorithm MPC and pure tracking PurePursuit, etc. The specific type of vehicle steering obstacle avoidance control algorithm is not limited in this implementation.

[0088] In a specific implementation, when the Stanley algorithm Stanley is used, the target point position closest to the target vehicle position is determined from the steering obstacle avoidance trajectory according to the target vehicle position, and the target point position and the current target vehicle position are calculated to determine the lateral deviation e, and the heading deviation θ is calculated according to the target vehicle yaw angle, so that the Stanley algorithm is used to perform turning angle control according to the lateral deviation e and the heading deviation θ, thereby realizing steering obstacle avoidance control of the target vehicle.

[0089] The technical solution of the embodiment of the present invention constructs an improved lateral rate and speed model by introducing the lateral speed of the target vehicle, and obtains final state information through the model, so that the obtained final state information is more accurate, and performs steering obstacle avoidance control in real time along a pre-acquired steering obstacle avoidance trajectory according to the final state information including the vehicle position and yaw angle, so as to achieve precise control of the vehicle steering when a collision risk occurs.

[0090] Figure 3 : is a flow chart of another vehicle steering obstacle avoidance method provided by an embodiment of the present invention. This embodiment is based on the above embodiment and specifically describes how to obtain the first obstacle. The method steps specifically include the following operations:

[0091] Step S301: Determine whether there is a candidate obstacle within the perception range through the fusion perception module.

[0092] Specifically, in this embodiment, the fusion perception module can be used to determine whether there are candidate obstacles within the perception range, wherein the candidate obstacles are, for example, pedestrians, vehicles, trees, large animals, and objects that suddenly fall from high altitudes, which may affect the safety of the target vehicle. In this embodiment, based on but not limited to sensors such as vehicle-mounted millimeter-wave radars or camera radars set on the target vehicle, multiple candidate obstacles are obtained through a fusion perception algorithm.

[0093] Step S302: If it is determined that a candidate obstacle exists, first associated information of the candidate obstacle is obtained.

[0094] Specifically, when it is determined that there are candidate obstacles based on the information from the sensor, first associated information of each candidate obstacle will be obtained. The first associated information includes obstacle type, obstacle lateral distance, obstacle longitudinal distance, obstacle lateral acceleration, obstacle longitudinal acceleration and obstacle width. The specific content of the first associated information is not limited in this embodiment.

[0095] Step S303: Screening the candidate obstacles according to the first association information to obtain the obstacle with the highest collision risk, and taking the obstacle with the highest collision risk as the first obstacle.

[0096] Specifically, in this embodiment, the candidate obstacles are screened according to the first associated information of each candidate obstacle to obtain the risk factor of each candidate obstacle, and the risk factor is proportional to the collision risk, so that the obstacle with the highest collision risk is used as the first obstacle. Since the candidate obstacles in this embodiment include multiple types such as pedestrians or vehicles, different methods can be used to calculate the risk factor for pedestrians and vehicles, and the specific calculation method of the risk factor is not limited in this embodiment.

[0097] Step S304: when it is determined that there is a collision risk between the target vehicle and the first obstacle and the steering obstacle avoidance condition is met, a steering obstacle avoidance trajectory for the target vehicle is obtained.

[0098] Optionally, when it is determined that there is a collision risk between the target vehicle and the first obstacle and the steering obstacle avoidance condition is met, a steering obstacle avoidance trajectory for the target vehicle is obtained, including: obtaining operating parameters of the target vehicle, and calculating the collision time based on the operating parameters and first associated information, wherein the operating parameters include longitudinal speed and longitudinal acceleration; when the collision time is less than a preset time, it is determined that there is an obstacle avoidance risk between the target vehicle and the first obstacle; obtaining a minimum braking obstacle avoidance distance and a minimum steering obstacle avoidance distance of the target vehicle; obtaining second associated information of a second obstacle whose distance from the target vehicle is within a preset range; and when it is determined that the steering obstacle avoidance condition is met based on the minimum braking obstacle avoidance distance, the minimum steering obstacle avoidance distance and the second associated information, obtaining a steering obstacle avoidance trajectory for the target vehicle.

[0099] Step S305, obtaining the lateral speed of the target vehicle, constructing an improved constant turn rate and speed model according to the lateral speed, and estimating the improved constant turn rate and speed model to obtain final state information.

[0100] Optionally, obtaining the lateral velocity of the target vehicle includes: obtaining first historical state information, wherein the first historical state information includes lateral velocity and yaw angular velocity; constructing a vehicle dynamics model based on the first historical state information, estimating the vehicle dynamics model to obtain first initial state information; correcting the first initial state information based on the measured yaw angular velocity, and obtaining corrected first initial state information, wherein the corrected first initial state information includes the lateral velocity.

[0101] Optionally, an improved constant turn rate and speed model is constructed according to the lateral speed, and the improved constant turn rate and speed model is estimated to obtain final state information, including: updating the lateral position according to the lateral speed, and determining second historical state information according to the updated lateral position, wherein the second historical state information includes the lateral position, longitudinal position, yaw angle, longitudinal speed and yaw angular velocity; constructing an improved constant turn rate and speed model according to the second historical state information, and estimating the improved constant turn rate and speed model to obtain second initial state information; and correcting the second initial state information according to the measured longitudinal speed and yaw angular velocity to obtain the final state information.

[0102] Step S306: performing steering obstacle avoidance control on the target vehicle according to the steering obstacle avoidance trajectory and the final state information.

[0103] Optionally, the target vehicle is controlled to steer for obstacle avoidance based on the steering obstacle avoidance trajectory and the final state information, including: determining the position of the target point on the steering obstacle avoidance trajectory that is closest to the target vehicle; determining the lateral deviation based on the target point position and the target vehicle position, and determining the heading deviation based on the target vehicle yaw angle; and performing steering obstacle avoidance control on the target vehicle based on the lateral deviation and the heading deviation.

[0104] Figure 4 This is a schematic diagram of the structure of a vehicle steering obstacle avoidance device provided in an embodiment of the present invention. The device includes: a steering obstacle avoidance trajectory acquisition module 410, a final state information acquisition module 420 and a steering obstacle avoidance control module 430.

[0105] The turning obstacle avoidance trajectory acquisition module 410 is used to acquire the turning obstacle avoidance trajectory for the target vehicle when it is determined that there is a collision risk between the target vehicle and the first obstacle and the turning obstacle avoidance condition is met;

[0106] The final state information acquisition module 420 is used to acquire the lateral speed of the target vehicle, construct an improved constant turn rate and speed model according to the lateral speed, and estimate the improved constant turn rate and speed model to acquire the final state information, wherein the final state information includes the vehicle position and yaw angle;

[0107] The steering obstacle avoidance control module 430 is used to perform steering obstacle avoidance control on the target vehicle according to the steering obstacle avoidance trajectory and final state information.

[0108] Optionally, the final state information acquisition module includes a lateral speed acquisition submodule, which is used to acquire first historical state information, wherein the first historical state information includes lateral speed and yaw angular velocity;

[0109] Building a vehicle dynamics model according to the first historical state information, and estimating the vehicle dynamics model to obtain first initial state information;

[0110] The first initial state information is corrected according to the measured yaw angular velocity to obtain the corrected first initial state information, wherein the corrected first initial state information includes a lateral velocity.

[0111] Optionally, a lateral velocity acquisition submodule is used to acquire a first covariance matrix corresponding to the first initial state information, and a first measurement matrix and a first noise matrix corresponding to the measured yaw angular velocity;

[0112] Calculate a first Kalman gain according to the first covariance matrix, the first measurement matrix and the first noise matrix;

[0113] The first initial state information is corrected according to the measured yaw angular velocity, the first Kalman gain, and the first measurement matrix to obtain the corrected first initial state information.

[0114] Optionally, the final state information acquisition module includes a final state information acquisition submodule, which is used to update the lateral position according to the lateral speed, and determine the second historical state information according to the updated lateral position, wherein the second historical state information includes the lateral position, the longitudinal position, the yaw angle, the longitudinal speed and the yaw angular speed;

[0115] constructing an improved constant rotation rate and speed model according to the second historical state information, and estimating the improved constant rotation rate and speed model to obtain second initial state information;

[0116] The second initial state information is corrected according to the measured longitudinal velocity and yaw angular velocity to obtain final state information.

[0117] Optionally, a final state information acquisition submodule is used to acquire a second covariance matrix corresponding to the second initial state information, and a second measurement matrix and a second noise matrix corresponding to the measured longitudinal velocity and yaw angular velocity;

[0118] Calculate a second Kalman gain according to the second covariance matrix, the second measurement matrix and the second noise matrix;

[0119] The second initial state information is corrected according to the measured longitudinal velocity and yaw angular velocity, the second Kalman gain and the second measurement matrix to obtain the final state information.

[0120] Optionally, the device further includes a first obstacle acquisition submodule, which is used to determine whether there is a candidate obstacle within the perception range through the fusion perception module;

[0121] If it is determined that there is a candidate obstacle, first associated information of the candidate obstacle is obtained, wherein the first associated information includes obstacle type, obstacle lateral distance, obstacle longitudinal distance, obstacle lateral acceleration, obstacle longitudinal acceleration, and obstacle width;

[0122] Screening the candidate obstacles according to the first association information to obtain an obstacle with the highest collision risk;

[0123] The obstacle with the highest collision risk is selected as the first obstacle.

[0124] Optionally, a steering obstacle avoidance trajectory acquisition module is used to obtain operating parameters of the target vehicle and calculate the collision time according to the operating parameters and the first associated information, wherein the operating parameters include longitudinal speed and longitudinal acceleration;

[0125] When the collision time is less than the preset time, it is determined that there is an obstacle avoidance risk between the target vehicle and the first obstacle;

[0126] Obtaining the minimum braking obstacle avoidance distance and the minimum steering obstacle avoidance distance of the target vehicle;

[0127] Acquire second associated information of a second obstacle whose distance from the target vehicle is within a preset range;

[0128] When it is determined that a turning obstacle avoidance condition is met according to the minimum braking obstacle avoidance distance, the minimum turning obstacle avoidance distance, and the second associated information, a turning obstacle avoidance trajectory for the target vehicle is acquired.

[0129] Optionally, a turning obstacle avoidance trajectory acquisition module is used to determine the existence of a turning obstacle avoidance space according to the second association information;

[0130] When it is determined that the minimum steering obstacle avoidance distance is less than the minimum braking obstacle avoidance distance, a steering obstacle avoidance trajectory of the target vehicle is acquired based on the steering obstacle avoidance space.

[0131] Optionally, a steering obstacle avoidance control module is used to determine the position of a target point on the steering obstacle avoidance trajectory that is closest to the position of the target vehicle;

[0132] Determine the lateral deviation according to the position of the target point and the position of the target vehicle, and determine the heading deviation according to the yaw angle of the target vehicle;

[0133] The target vehicle is steered and controlled to avoid obstacles based on the lateral deviation and heading deviation.

[0134] The above device can execute the vehicle steering obstacle avoidance method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method. For technical details not described in detail in this embodiment, please refer to the method provided by any embodiment of the present invention.

[0135] Figure 5A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0136] like Figure 5 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0137] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0138] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the vehicle steering obstacle avoidance method.

[0139] In some embodiments, the vehicle steering obstacle avoidance method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the vehicle steering obstacle avoidance method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the vehicle steering obstacle avoidance method in any other appropriate manner (e.g., by means of firmware).

[0140] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0141] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0142] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0143] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0144] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0145] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0146] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0147] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A vehicle steering obstacle avoidance method, characterized in that: include: When it is determined that there is a collision risk between the target vehicle and the first obstacle and the steering obstacle avoidance condition is met, obtaining a steering obstacle avoidance trajectory for the target vehicle; Acquire the lateral speed of the target vehicle, construct an improved constant turn rate and speed model according to the lateral speed, and estimate the improved constant turn rate and speed model to obtain final state information, wherein the final state information includes the vehicle position and yaw angle; Performing steering obstacle avoidance control on the target vehicle according to the steering obstacle avoidance trajectory and the final state information; The method of obtaining a turning obstacle avoidance trajectory for the target vehicle when it is determined that there is a collision risk between the target vehicle and the first obstacle and that a turning obstacle avoidance condition is met includes: obtaining operating parameters of the target vehicle, and calculating a collision time based on the operating parameters and first associated information of candidate obstacles within a sensing range, wherein the operating parameters include longitudinal velocity and longitudinal acceleration; when the collision time is less than a preset time, determining that there is an obstacle avoidance risk between the target vehicle and the first obstacle; obtaining a minimum braking obstacle avoidance distance and a minimum turning obstacle avoidance distance of the target vehicle; obtaining second associated information of a second obstacle whose distance from the target vehicle is within a preset range; and obtaining a turning obstacle avoidance trajectory for the target vehicle when it is determined that the turning obstacle avoidance condition is met based on the minimum braking obstacle avoidance distance, the minimum turning obstacle avoidance distance, and the second associated information; The step of constructing an improved constant turn rate and speed model according to the lateral speed, and estimating the improved constant turn rate and speed model to obtain final state information includes: updating a lateral position according to the lateral speed, and determining second historical state information according to the updated lateral position, wherein the second historical state information includes a lateral position, a longitudinal position, a yaw angle, a longitudinal speed, and a yaw angular velocity; constructing the improved constant turn rate and speed model according to the second historical state information, and estimating the improved constant turn rate and speed model to obtain second initial state information; and correcting the second initial state information according to the measured longitudinal speed and yaw angular velocity to obtain the final state information.

2. The method according to claim 1, characterized in that The step of obtaining the lateral speed of the target vehicle comprises: Acquire first historical state information, wherein the first historical state information includes lateral velocity and yaw angular velocity; Building a vehicle dynamics model according to the first historical state information, and estimating the vehicle dynamics model to obtain first initial state information; The first initial state information is corrected according to the measured yaw angular velocity to obtain the corrected first initial state information, wherein the corrected first initial state information includes the lateral velocity.

3. The method according to claim 2, characterized in that The step of correcting the first initial state information according to the measured yaw angular velocity to obtain the corrected first initial state information includes: Acquire a first covariance matrix corresponding to the first initial state information, and a first measurement matrix and a first noise matrix corresponding to the measured yaw angular velocity; Calculate a first Kalman gain according to the first covariance matrix, the first measurement matrix and the first noise matrix; The first initial state information is corrected according to the measured yaw angular velocity, the first Kalman gain, and the first measurement matrix to obtain the corrected first initial state information.

4. The method according to claim 2, characterized in that: The correcting the second initial state information according to the measured longitudinal velocity and yaw angular velocity to obtain the final state information includes: Acquire a second covariance matrix corresponding to the second initial state information, and a second measurement matrix and a second noise matrix corresponding to the measured longitudinal velocity and yaw angular velocity; Calculate a second Kalman gain according to the second covariance matrix, the second measurement matrix and the second noise matrix; The second initial state information is corrected according to the measured longitudinal velocity and yaw angular velocity, the second Kalman gain and the second measurement matrix to obtain the final state information.

5. The method according to claim 1, characterized in that When it is determined that there is a collision risk between the target vehicle and the first obstacle and the steering obstacle avoidance condition is met, before obtaining the steering obstacle avoidance trajectory for the target vehicle, the method further includes: Determine whether there are candidate obstacles within the perception range through the fusion perception module; If it is determined that a candidate obstacle exists, first associated information of the candidate obstacle is obtained, wherein the first associated information includes obstacle type, obstacle lateral distance, obstacle longitudinal distance, obstacle lateral acceleration, obstacle longitudinal acceleration, and obstacle width; Screening the candidate obstacles according to the first association information to obtain an obstacle with the highest collision risk; The obstacle with the highest collision risk is used as the first obstacle.

6. The method according to claim 5, characterized in that When it is determined that the turning obstacle avoidance condition is met according to the minimum braking obstacle avoidance distance, the minimum turning obstacle avoidance distance and the second associated information, obtaining a turning obstacle avoidance trajectory for the target vehicle includes: determining, according to the second association information, that there is a turning obstacle avoidance space; When it is determined that the minimum steering obstacle avoidance distance is less than the minimum braking obstacle avoidance distance, a steering obstacle avoidance trajectory of the target vehicle is acquired based on the steering obstacle avoidance space.

7. The method according to claim 1, characterized in that The performing steering obstacle avoidance control on the target vehicle according to the steering obstacle avoidance trajectory and the final state information comprises: Determine the position of the target point on the steering obstacle avoidance trajectory that is closest to the target vehicle position; Determine a lateral deviation according to the target point position and the target vehicle position, and determine a heading deviation according to the target vehicle yaw angle; Steering and obstacle avoidance control is performed on the target vehicle according to the lateral deviation and the heading deviation.

8. An electronic device, characterized in that: The electronic device comprises: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images