Emergency collision avoidance method and device based on target trajectory prediction, equipment and medium

Abstract

The invention discloses an emergency collision avoidance method, device and equipment based on target trajectory prediction and a medium, and the method comprises the steps: determining a forward collision avoidance region and a lateral collision avoidance region of a vehicle, and predicting the motion trajectory of a target vehicle around the vehicle after a period of time in the future; whether the movement track makes contact with or overlaps with a forward collision avoiding area and a lateral collision avoiding area of the vehicle or not is judged; if yes, it is judged that collision risks exist between the vehicle and the target vehicle, and different collision avoidance strategies are adopted according to different collision risks. According to the method, the target motion track can be predicted, the collision risk of the target in the complex motion state can be effectively judged, different collision avoidance strategies are adopted for different risk scenes, the reliability of an emergency collision avoidance system is effectively guaranteed, and the driving comfort and safety are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle collision avoidance, and in particular to an emergency collision avoidance method, device, equipment and medium based on target trajectory prediction. Background Art

[0002] Current smart vehicles are usually equipped with active collision avoidance safety systems, which can effectively reduce the risk of traffic accidents and minimize casualties.

[0003] Typical active safety systems include Autonomous Emergency Braking (AEB), Emergency Lane Keeping (ELK), and Emergency Steering Assist (ESA): The AEB system will automatically initiate braking to avoid or reduce collision when there is a risk of collision between the vehicle and the target ahead; the ELK system will correct the driving trajectory and return the vehicle to its lane when the driver inadvertently deviates from the lane or the vehicle is at risk of collision while deviating from the lane; the ESA system will actively help the driver avoid or reduce collision by steering avoidance when there is a risk of collision between the vehicle and the target ahead.

[0004] The existing active safety systems have certain limitations. Both AEB and ESA act on the target in the longitudinal direction of the front of the ego vehicle in the same lane, while ELK acts on the target in the adjacent lane when the ego vehicle deviates from the lane or in the process of deviating from the lane. It is impossible to avoid collision with targets with complex motion states. For targets with complex motion states, the ego vehicle may collide with them because the trigger conditions of AEB, ELK, and ESA are not met.

[0005] Therefore, how to avoid collision with targets with complex motion states is a technical problem that urgently needs to be solved. Summary of the invention

[0006] The main purpose of the present invention is to provide an emergency collision avoidance method, device, equipment and medium based on target trajectory prediction, which can predict the target motion trajectory, effectively judge the collision risk of targets in complex motion states, and adopt different collision avoidance strategies for different risk scenarios, effectively ensuring the reliability of the emergency collision avoidance system and improving driving comfort and safety.

[0007] In a first aspect, the present application provides an emergency collision avoidance method based on target trajectory prediction, wherein the method comprises the steps of:

[0008] Determine the forward collision avoidance area and the side collision avoidance area of ​​the ego vehicle, and predict the movement trajectory of the target vehicles around the ego vehicle after a period of time in the future;

[0009] Determining whether the motion trajectory contacts or overlaps with a forward collision avoidance area and a side collision avoidance area of ​​the vehicle;

[0010] If so, it is determined that there is a collision risk between the ego vehicle and the target vehicle, and different collision avoidance strategies are adopted according to different collision risks.

[0011] In combination with the first aspect, as an optional implementation method, if it is determined that the movement trajectory of the target vehicle after a period of time in the future contacts or overlaps with the side collision avoidance zone of the own vehicle, it is determined that the own vehicle and the target vehicle are at risk of side collision;

[0012] If it is determined that the target vehicle's motion trajectory after a period of time in the future will touch or overlap with the self-vehicle's forward collision avoidance zone, it is determined that the self-vehicle and the target vehicle are in a forward collision risk scenario;

[0013] When it is determined that there is a risk of lateral collision between the ego vehicle and the target vehicle, and it is detected that the ego vehicle has a turning avoidance path, the ego vehicle triggers lateral avoidance to determine the set distance to the left or right according to the target motion trajectory and surrounding environment information;

[0014] If it is determined that there is a risk of forward collision between the ego vehicle and the target vehicle, the ego vehicle triggers emergency braking.

[0015] In combination with the first aspect, as an optional implementation method, when it is determined that there is a risk of a forward collision between the ego vehicle and the surrounding target vehicles, and it is detected that the ego vehicle cannot avoid the collision, but there is a turning collision avoidance path, the ego vehicle triggers lateral avoidance;

[0016] If the collision probability of the target vehicle crossing in front of the ego vehicle is greater than the set threshold, the ego vehicle is controlled to slow down or deviate to the left or right.

[0017] In combination with the first aspect, as an optional implementation manner, collision detection is performed on the ego vehicle based on an axis-aligned bounding box detection method to determine a forward collision avoidance area and a lateral collision avoidance area of ​​the ego vehicle.

[0018] In combination with the first aspect, as an optional implementation method, a rectangular coordinate system is established with the rear axle center of the vehicle as the origin, and motion information of targets around the vehicle is obtained through sensors, where the motion information includes position, velocity and acceleration;

[0019] Establishing a target kinematics model, and inputting the motion information into the target kinematics model to output a predicted state vector and an observation vector of the target trajectory;

[0020] The predicted state vector and the observation vector are input as inputs to the Kalman filter, so as to output the predicted motion trajectory of the target vehicle after a period of time in the future through the time update equation and the state update equation in the Kalman filter.

[0021] In combination with the first aspect mentioned above, as an optional implementation method, based on the motion state of the own vehicle after a period of time in the future and the motion trajectory of the target vehicle after a period of time in the future, it is determined whether the motion trajectory of the target vehicle after a period of time in the future contacts or overlaps with the forward collision avoidance area and the side collision avoidance area of ​​the own vehicle.

[0022] In combination with the first aspect above, as an optional implementation method, when it is determined that there is a risk of collision between the vehicle and the target vehicle, the driver is reminded according to multiple customized reminder methods, wherein the multiple reminder methods include: sound, instrument, text pop-up window on the central control screen, animation, pop-up picture, steering wheel vibration and seat belt tightening vibration.

[0023] In a second aspect, the present application provides an emergency collision avoidance device based on target trajectory prediction, wherein the device comprises:

[0024] A processing module, which is used to determine the forward collision avoidance area and the side collision avoidance area of ​​the ego vehicle, and predict the movement trajectory of the target vehicles around the ego vehicle after a period of time in the future;

[0025] A judgment module, which is used to judge whether the motion trajectory contacts or overlaps with the forward collision avoidance area and the side collision avoidance area of ​​the vehicle;

[0026] The collision avoidance module is used to determine if there is a collision risk between the vehicle and the target vehicle, and adopt different collision avoidance strategies according to different collision risks.

[0027] In a third aspect, the present application further provides an electronic device, comprising: a processor; a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the method described in any one of the first aspects is implemented.

[0028] In a fourth aspect, the present application further provides a computer-readable storage medium storing computer program instructions, which, when executed by a computer, enables the computer to execute any of the methods described in the first aspect.

[0029] The present application provides an emergency collision avoidance method, device, equipment and medium based on target trajectory prediction, wherein the method includes the steps of: determining the forward collision avoidance area and the lateral collision avoidance area of ​​the own vehicle, and predicting the movement trajectory of the target vehicles around the own vehicle after a period of time in the future; judging whether the movement trajectory contacts or overlaps with the forward collision avoidance area and the lateral collision avoidance area of ​​the own vehicle; if so, judging that there is a collision risk between the own vehicle and the target vehicle, and adopting different collision avoidance strategies according to different collision risks. The present application can predict the target movement trajectory, realize the effective judgment of the collision risk of the target in complex motion state, and adopt different collision avoidance strategies for different risk scenarios, effectively ensuring the reliability of the emergency collision avoidance system and improving driving comfort and safety.

[0030] It is to be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0032] Figure 1 A flow chart of an emergency collision avoidance method based on target trajectory prediction provided in an embodiment of the present application;

[0033] Figure 2 A schematic diagram of an emergency collision avoidance device based on target trajectory prediction provided in an embodiment of the present application;

[0034] Figure 3 A schematic diagram of a collision risk determination scenario provided in an embodiment of the present application;

[0035] Figure 4 A flowchart for determining collision risk provided in an embodiment of the present application;

[0036] Figure 5 A schematic diagram of an electronic device provided in an embodiment of the present application;

[0037] Figure 6 A schematic diagram of a computer-readable program medium provided in an embodiment of the present application. DETAILED DESCRIPTION

[0038] Here, exemplary embodiments will be described in detail, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0039] Furthermore, the drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. Some of the blocks shown in the drawings are functional entities and do not necessarily correspond to physically or logically separate entities.

[0040] The embodiments of the present application are further described in detail below in conjunction with the accompanying drawings.

[0041] Reference Figure 1 , Figure 1 FIG. 1 is a flow chart of an emergency collision avoidance method based on target trajectory prediction provided by the present invention, as shown in FIG. Figure 1 As shown, the method comprises the steps of:

[0042] Step S101: Determine the forward collision avoidance area and the lateral collision avoidance area of ​​the vehicle, and predict the movement trajectory of the target vehicles around the vehicle after a period of time in the future.

[0043] Specifically, the vehicle is subjected to collision detection based on the axis-aligned bounding box detection method to determine the forward collision avoidance area and the lateral collision avoidance area of ​​the vehicle. Figure 3 For example, AABB (axis-aligned bounding box) is used for collision detection, A1 and A2 are risk areas based on the expansion of the axis-aligned bounding box, where A1 is the forward collision avoidance area and A2 is the lateral collision avoidance area.

[0044] Predict the motion trajectory of target vehicles around the ego vehicle in the future, specifically: establish a rectangular coordinate system with the center of the rear axle of the ego vehicle as the origin, and obtain the motion information of the targets around the ego vehicle through sensors, the motion information including position, speed and acceleration;

[0045] Establishing a target kinematics model, and inputting the motion information into the target kinematics model to output a predicted state vector and an observation vector of the target trajectory;

[0046] The predicted state vector and the observation vector are input as inputs to the Kalman filter, so as to output the predicted motion trajectory of the target vehicle after a period of time in the future through the time update equation and the state update equation in the Kalman filter.

[0047] For ease of understanding, an example is given. A rectangular coordinate system is established with the center of the rear axle of the vehicle as the origin, and the motion information of the target vehicles around the vehicle is obtained through sensors, the motion information including position, target speed and acceleration; based on the motion information, a target kinematic model is established, and the kinematic model is used to obtain the target trajectory prediction state equation and observation equation; the target trajectory prediction state equation is substituted into the time update equation and the state update equation to optimally estimate the current state of the target and predict the motion trajectory at the next moment.

[0048] Among them, the kinematic model is established, which is:

[0049]

[0050] v ij =v ij-1 +a ij-1 Δt;

[0051] Among them, p ij is the position of the i-th target at time j, v ij is the speed of the i-th target at time j, a ij is the acceleration of the ith target at time j, p i(j-1) is the position of the i-th target at time j-1, v i(j-1) is the speed of the i-th target at time j-1, a i(j-1) is the acceleration of the i-th target at time j-1;

[0052] The target trajectory prediction state equation is established as follows:

[0053]

[0054] Among them, ω k is process noise, indicating external interference

[0055] The observation equation is:

[0056]

[0057] v k To represent the measurement noise, H is the observation matrix;

[0058] The time update equation is:

[0059]

[0060] The state update equation is:

[0061]

[0062] in, and They represent the posterior state estimates at time k-1 and time k respectively, represents the prior state estimate at time k, P k-1 and P k They represent the posterior estimated covariance at time k-1 and time k respectively, is the prior estimated covariance at time k, H is the transformation matrix from state variables to observations, k kis the Kalman filter gain matrix, A is the state transfer matrix, Q and R are the covariances of the system process and measurement noise, B is the matrix that converts input to state, is the residual between the actual observation and the predicted observation.

[0063] For ease of understanding, let's take an example. In Kalman filtering, the state transfer equation is usually expressed as:

[0064] xk=Fxk-1+Buk+wk

[0065] Among them, xk is the state vector at the current moment; xk-1 is the state vector at the previous moment; F is the state transfer matrix, which describes how the system state is transferred from the previous moment to the current moment; B is the control input matrix, which describes how the external control input uk affects the change of the system state; uk is the control input vector, which represents the control effect on the system at time k; wk is the system noise vector, which represents the uncertainty or random disturbance in the system model, which is usually assumed to be zero-mean Gaussian white noise, and its covariance matrix is ​​Qk.

[0066] The observation equation is used to describe the relationship between the observed value of the system state and the state. It is usually expressed as:

[0067] zk=Hxk+vk

[0068] Where zk is the observation vector at time k, which contains the system state information obtained by sensors and other measurement methods. H is the observation matrix, which describes the linear relationship between the observation vector zk and the state vector xk. vk is the observation noise vector, which represents the uncertainty or random disturbance in the observation model. It is usually assumed that vk is a zero-mean Gaussian white noise, whose covariance matrix is ​​Rk.

[0069] In the target trajectory prediction based on Kalman filtering, the control input is ignored and it is assumed that the system noise and the measurement noise are independent of each other. Then the time update equation is expressed as:

[0070]

[0071] The state update equation is:

[0072]

[0073] in, and They represent the posterior state estimates at time k-1 and time k respectively, which are one of the results of filtering, that is, the updated result, also called the optimal estimate. It represents the prior state estimate at time k, which is the intermediate calculation result of filtering, that is, the result of time k predicted based on the optimal estimate at the previous time (time k-1), which is the result of the prediction equation, Pk-1 and P k They represent the posterior estimated covariance at time k-1 and time k respectively, is the prior estimated covariance at time k, H is the transformation matrix from state variables to observations, which represents the relationship connecting the state and observations. In Kalman filtering, it is a linear relationship. It is responsible for converting the m-dimensional measurement value to the n-dimensional one to conform to the mathematical form of the state variable. It is one of the prerequisites for filtering. k is the Kalman filter gain matrix, which is the intermediate calculation result of the filter. A is the state transfer matrix. In the trajectory prediction of the target, the state transfer matrix is ​​used to model the motion of the target. Q and R are the covariances of the system process and measurement noise. B is the matrix that converts the input into the state. is the residual between the actual observation and the predicted observation.

[0074] Therefore, by substituting the state of the target at the previous moment into the time update equation, we can get the prior estimate of the current state, and use the Kalman gain to get the posterior optimal estimate of the current state. Then, we substitute the optimal estimate at the current moment into the time update equation to calculate the prior estimate at the next moment in the future, and then we can predict the trajectory of the target.

[0075] Step S102: Determine whether the motion trajectory contacts or overlaps with the forward collision avoidance area and the side collision avoidance area of ​​the vehicle.

[0076] Specifically, according to the motion state of the ego vehicle in the future and the motion trajectory of the target vehicle in the future, it is determined whether the motion trajectory of the target vehicle in the future contacts or overlaps with the forward collision avoidance area and the side collision avoidance area of ​​the ego vehicle.

[0077] It is understandable that the calculation of the vehicle in Δ t The position after time, and whether a collision will occur is determined based on whether the target's bounding box and the risk area extended by the axis-aligned bounding box of the vehicle are in contact or overlapped (see Figure 3 illustrate).

[0078] In one embodiment, based on the axis-aligned bounding box collision detection, a forward collision avoidance area and a lateral collision avoidance area of ​​the ego vehicle are determined; a motion state of the ego vehicle after a set time is calculated; and it is determined whether the motion trajectory of a target around the ego vehicle within the set time appears in the collision avoidance area corresponding to the ego vehicle moving after the set time.

[0079] If the collision does not occur within the collision avoidance zone, it is determined that there is no collision risk;

[0080] If it appears in the collision avoidance area, it is determined that there is a collision risk (for details on the collision risk, refer to Figure 3illustrate).

[0081] Step S103: If yes, it is determined that there is a collision risk between the vehicle and the target vehicle, and different collision avoidance strategies are adopted according to different collision risks.

[0082] Specifically, if it is determined that the target vehicle's motion trajectory after a period of time in the future will contact or overlap with the ego vehicle's side collision avoidance zone, it is determined that the ego vehicle and the target vehicle are at risk of side collision;

[0083] If it is determined that the target vehicle's motion trajectory after a period of time in the future will touch or overlap with the self-vehicle's forward collision avoidance zone, it is determined that the self-vehicle and the target vehicle are in a forward collision risk scenario;

[0084] When it is determined that there is a risk of lateral collision between the ego vehicle and the target vehicle, and it is detected that the ego vehicle has a turning avoidance path, the ego vehicle triggers lateral avoidance to determine the set distance to the left or right according to the target motion trajectory and surrounding environment information;

[0085] If it is determined that there is a risk of forward collision between the ego vehicle and the target vehicle, the ego vehicle triggers emergency braking.

[0086] Optionally, when it is determined that there is a risk of a forward collision between the ego vehicle and the surrounding target vehicles, and it is detected that the ego vehicle cannot avoid the collision, but there is a turning collision avoidance path, the ego vehicle triggers lateral avoidance;

[0087] If the collision probability of the target vehicle crossing in front of the ego vehicle is greater than the set threshold, the ego vehicle is controlled to slow down or deviate to the left or right.

[0088] In one embodiment, when it is determined that there is a risk of collision between the vehicle and the target vehicle, the driver is reminded according to multiple customized reminder methods, wherein the multiple reminder methods include: sound, instrument, text pop-up window on the central control screen, animation, pop-up picture, steering wheel vibration and seat belt tightening vibration.

[0089] It is understandable that when the emergency collision avoidance function is activated, the system reminds the driver of the activation of the emergency collision avoidance function and the risk of collision through sounds, text pop-ups, pictures, animations on the instrument and central control screen, ARHUD text pop-ups, pictures, animations, steering wheel vibrations, seat belt tightening vibrations, etc.

[0090] In addition, when the system determines that there is a collision risk, but cannot trigger active collision avoidance due to a malfunction or failure to meet the automatic emergency braking or automatic emergency steering trigger conditions, the system reminds the driver of the collision risk through sound, instrument and central control screen text pop-ups, pop-ups, animations, ARHUD text pop-ups, pop-ups, animations, steering wheel vibrations, seat belt tightening vibrations, etc.

[0091] In summary, this application uses the Kalman filter algorithm to predict the trajectory of the target after T seconds (preset value) in the current state, and calculates the motion state (position, speed, acceleration) of the vehicle after T seconds. Afterwards, different control strategies are adopted according to the vehicle and motion state and the predicted trajectory of the target, which can well achieve collision avoidance for targets with complex motion states.

[0092] It can be understood that the present application realizes effective judgment of the collision risk of targets in complex motion states by predicting the target motion trajectory; different collision avoidance strategies are adopted for different risk scenarios, which effectively ensures the reliability of the emergency collision avoidance system and improves driving comfort and safety.

[0093] Reference Figure 2 , Figure 2 FIG. 1 is a schematic diagram of an emergency collision avoidance device based on target trajectory prediction provided by the present invention, such as Figure 2 As shown, the device comprises:

[0094] Processing module 201 is used to determine the front collision avoidance area and the side collision avoidance area of ​​the vehicle, and predict the movement trajectory of the target vehicles around the vehicle after a period of time in the future.

[0095] The judgment module 202 is used to judge whether the motion trajectory contacts or overlaps with the forward collision avoidance area and the side collision avoidance area of ​​the vehicle.

[0096] Collision avoidance module 203: If yes, it determines that there is a collision risk between the vehicle and the target vehicle, and adopts different collision avoidance strategies according to different collision risks.

[0097] Furthermore, in a possible implementation manner, the collision avoidance module is further configured to determine that the ego vehicle and the target vehicle are at risk of side collision if it is determined that the motion trajectory of the target vehicle after a period of time in the future contacts or overlaps with the ego vehicle's side collision avoidance zone;

[0098] If it is determined that the target vehicle's motion trajectory after a period of time in the future will touch or overlap with the self-vehicle's forward collision avoidance zone, it is determined that the self-vehicle and the target vehicle are in a forward collision risk scenario;

[0099] When it is determined that there is a risk of lateral collision between the ego vehicle and the target vehicle, and it is detected that the ego vehicle has a turning avoidance path, the ego vehicle triggers lateral avoidance to determine the set distance to the left or right according to the target motion trajectory and surrounding environment information;

[0100] If it is determined that there is a risk of forward collision between the ego vehicle and the target vehicle, the ego vehicle triggers emergency braking.

[0101] Furthermore, in a possible implementation manner, the collision avoidance module is further configured to trigger lateral avoidance of the ego vehicle when it is determined that there is a risk of a forward collision between the ego vehicle and surrounding target vehicles, and when it is detected that the ego vehicle cannot avoid the collision but there is a turning collision avoidance path;

[0102] If the collision probability of the target vehicle crossing in front of the ego vehicle is greater than the set threshold, the ego vehicle is controlled to slow down or deviate to the left or right.

[0103] Furthermore, in a possible implementation manner, the processing module is further configured to perform collision detection on the ego vehicle based on an axis-aligned bounding box detection method to determine a forward collision avoidance area and a lateral collision avoidance area of ​​the ego vehicle.

[0104] Furthermore, in a possible implementation manner, the processing module is further used to establish a rectangular coordinate system with the center of the rear axle of the vehicle as the origin, and obtain motion information of targets around the vehicle through sensors, wherein the motion information includes position, speed and acceleration;

[0105] Establishing a target kinematics model, and inputting the motion information into the target kinematics model to output a predicted state vector and an observation vector of the target trajectory;

[0106] The predicted state vector and the observation vector are input as inputs to the Kalman filter, so as to output the predicted motion trajectory of the target vehicle after a period of time in the future through the time update equation and the state update equation in the Kalman filter.

[0107] Furthermore, in a possible implementation, the judgment module is also used to judge whether the motion trajectory of the target vehicle after a period of time in the future will contact or overlap with the forward collision avoidance area and the side collision avoidance area of ​​the own vehicle based on the motion state of the own vehicle after a period of time in the future and the motion trajectory of the target vehicle after a period of time in the future.

[0108] Furthermore, in a possible implementation, the processing module is also used to remind the driver according to multiple customized reminder methods when it is determined that there is a risk of collision between the vehicle and the target vehicle, wherein the multiple reminder methods include: sound, instrument, text pop-up window on the central control screen, animation, pop-up picture, steering wheel vibration and seat belt tightening vibration.

[0109] Reference Figure 3 , Figure 3 FIG. 1 is a schematic diagram of a collision risk determination scenario provided by the present invention. Figure 3 As shown:

[0110] As shown in the figure, AABB (axis-aligned bounding box) is used for collision detection. A1 and A2 are risk areas based on the expansion of the axis-aligned bounding box, where A1 is the forward collision avoidance area and A2 is the side collision avoidance area.t The position after time is determined, and whether a collision will occur is determined based on whether the target's bounding box and the risk area extended by the axis-aligned bounding box of the vehicle are in contact or overlapped. The details are as follows:

[0111] like Figure 3 As shown, 7 situations of the predicted motion trajectory of the target are listed.

[0112] For trajectory P1, there is no risk of collision between the target and the ego vehicle during the movement trajectory within T seconds, so the emergency collision avoidance system is not triggered.

[0113] For trajectory P2, the system determines that there is a collision risk and a steering avoidance path, triggering lateral avoidance. The system will automatically send a torque request to the electronic power steering system (EPS) to avoid to the right. The lateral avoidance distance is d, where d is obtained by calibration. In one possible way, the avoidance distance of the ego vehicle will not cause the ego vehicle to cross the lane, or the ego vehicle can cross the lane to avoid.

[0114] For trajectories P3, P4, and P5, the system determines that there is a collision risk and will trigger automatic emergency braking. If the AEB calculation finds that the collision cannot be avoided or the AEB triggering conditions are not met but there is a steering collision avoidance path, the system will automatically send a torque request to the electronic power steering system (EPS) to avoid to the left or right (determine whether to avoid to the left or right based on the target motion trajectory and surrounding environment information).

[0115] For trajectory P6, the system determines that there is a collision risk and a steering avoidance path. The lateral avoidance system is triggered to automatically send a torque request to the electronic power steering system (EPS) to avoid to the left. The lateral avoidance distance is d, which is obtained by calibration. One possible way is that the avoidance distance of the ego vehicle will not cause the ego vehicle to cross the lane, or the ego vehicle can cross the lane to avoid.

[0116] For trajectory P7, the target's movement trajectory within T seconds has no collision risk with the ego vehicle, but the target crosses in front of the ego vehicle (that is, the collision probability when the target vehicle crosses in front of the ego vehicle is greater than the set threshold, and it is judged that there is a potential collision risk). Therefore, the system controls the ego vehicle to slow down or slightly offset to the left or right to avoid (the offset distance will not cause the ego vehicle to cross the lane, and the slight offset can be customized to set the offset distance).

[0117] Reference Figure 4 , Figure 4 The flowchart of the collision risk determination provided by the present invention is shown as follows: Figure 4 As shown:

[0118] A rectangular coordinate system is established with the rear axle center of the vehicle as the origin. The position of the target relative to the vehicle (including the target lateral distance and the target longitudinal distance), target speed (including the target relative lateral speed and the target relative longitudinal speed) and acceleration (including lateral acceleration and longitudinal acceleration) are obtained through sensors such as forward millimeter-wave radar, corner radar, front-view camera, side-view camera, and lidar. This information is stored in the data set Pa i In Chinese, that is:

[0119] Pa i ={(p i1 ,v i1 ,a i1 ),…,(p in ,v in ,a in )}

[0120] Among them, p in is the position of the i-th target at time n, v in is the speed of the ith target at time n, a in is the acceleration of the ith target at time n.

[0121] Build a kinematic model of the target:

[0122]

[0123] v ij =v ij-1 +a ij-1 Δt

[0124] Then the target trajectory prediction state equation is obtained:

[0125]

[0126] The observation equation is:

[0127]

[0128] Substituting the state equation and observation equation into the time update equation and state update equation, the optimal estimation of the current state of the target and the trajectory prediction of the next moment can be completed. t The trajectory prediction for a period of time in the future can be achieved.

[0129] Use AABB (axis-aligned bounding box) for collision detection, obtain the forward collision avoidance area and the side collision avoidance area of ​​the ego vehicle, and calculate the ego vehicle in Δ tThe position after a certain time is combined with the predicted movement trajectory of the target vehicles around the ego vehicle in the future, and it is determined whether the movement trajectory of the target vehicle in the future will contact or overlap with the forward collision avoidance area and the side collision avoidance area of ​​the ego vehicle. If so, it is determined that there is a risk of collision between the ego vehicle and the target vehicle, and whether there is a forward collision risk or a side collision risk. If it is a forward collision risk, emergency braking is initiated to avoid the collision. If it is a side collision risk, emergency steering is triggered to avoid the collision. In addition, if it is determined that there is no collision risk, the vehicle is not controlled to avoid. If it is determined that the vehicle has a potential collision risk (that is, the collision probability is determined to be greater than the set threshold, and it is confirmed that there is a potential collision risk), the vehicle is controlled to slow down or deviate to the left or right to avoid it.

[0130] Refer to the following Figure 5 The electronic device 500 according to this embodiment of the present invention is described. Figure 5 The electronic device 500 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0131] like Figure 5 As shown, the electronic device 500 is in the form of a general computing device. The components of the electronic device 500 may include but are not limited to: at least one processing unit 510, at least one storage unit 520, and a bus 530 connecting different system components (including the storage unit 520 and the processing unit 510).

[0132] The storage unit stores program codes, which can be executed by the processing unit 510, so that the processing unit 510 executes the steps according to various exemplary embodiments of the present invention described in the above “Embodiment Method” section of this specification.

[0133] The storage unit 520 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 521 and / or a cache memory unit 522 , and may further include a read-only memory unit (ROM) 523 .

[0134] The storage unit 520 may also include a program / utility 524 having a set (at least one) of program modules 525, such program modules 525 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0135] Bus 530 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0136] The electronic device 500 may also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 500, and / or may communicate with any device that enables the electronic device 500 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 550. Furthermore, the electronic device 500 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 560. As shown, the network adapter 560 communicates with other modules of the electronic device 500 via a bus 530. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 500, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0137] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0138] According to the solution of the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible implementations, various aspects of the present invention can also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary implementations of the present invention described in the above "Exemplary Method" section of the present specification.

[0139] refer to Figure 6 As shown, a program product 600 for implementing the above method according to an embodiment of the present invention is described, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0140] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable 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 above.

[0141] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0142] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0143] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0144] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to an exemplary embodiment of the present invention, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0145] The above description is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest range consistent with the principles and novel features applied for herein.

[0146] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

Claims

1. An emergency collision avoidance method based on target trajectory prediction, characterized in that: include: Determine the forward collision avoidance area and the side collision avoidance area of ​​the ego vehicle, and predict the movement trajectory of the target vehicles around the ego vehicle after a period of time in the future; Determining whether the motion trajectory contacts or overlaps with a forward collision avoidance area and a side collision avoidance area of ​​the vehicle; If so, it is determined that there is a collision risk between the ego vehicle and the target vehicle, and different collision avoidance strategies are adopted according to different collision risks.

2. The method according to claim 1, characterized in that The determining whether there is a collision risk between the vehicle and the target vehicle and adopting different collision avoidance strategies according to different collision risks include: If it is determined that the target vehicle's motion trajectory after a period of time in the future contacts or overlaps with the lateral collision avoidance zone of the ego vehicle, it is determined that the ego vehicle and the target vehicle are at risk of lateral collision; If it is determined that the target vehicle's motion trajectory after a period of time in the future will touch or overlap with the self-vehicle's forward collision avoidance zone, it is determined that the self-vehicle and the target vehicle are in a forward collision risk scenario; When it is determined that there is a risk of lateral collision between the ego vehicle and the target vehicle, and it is detected that the ego vehicle has a turning avoidance path, the ego vehicle triggers lateral avoidance to determine the set distance to the left or right according to the target motion trajectory and surrounding environment information; If it is determined that there is a risk of forward collision between the ego vehicle and the target vehicle, the ego vehicle triggers emergency braking.

3. The method according to claim 2, characterized in that Also includes: When it is determined that there is a risk of a forward collision between the ego vehicle and the surrounding target vehicles, and it is detected that the ego vehicle cannot avoid the collision, but there is a turning collision avoidance path, the ego vehicle triggers lateral avoidance; If the collision probability of the target vehicle crossing in front of the ego vehicle is greater than the set threshold, the ego vehicle is controlled to slow down or deviate to the left or right.

4. The method according to claim 1, characterized in that The determining of the front collision avoidance area and the side collision avoidance area of ​​the vehicle includes: The vehicle is subjected to collision detection based on the axis-aligned bounding box detection method to determine the forward collision avoidance area and the lateral collision avoidance area of ​​the vehicle.

5. The method according to claim 1, characterized in that The prediction of the movement trajectory of the target vehicles around the vehicle after a period of time in the future includes: A rectangular coordinate system is established with the rear axle center of the vehicle as the origin, and motion information of targets around the vehicle is obtained through sensors, the motion information including position, velocity and acceleration; Establishing a target kinematics model, and inputting the motion information into the target kinematics model to output a predicted state vector and an observation vector of the target trajectory; The predicted state vector and the observation vector are input as inputs to the Kalman filter, so as to output the predicted motion trajectory of the target vehicle after a period of time in the future through the time update equation and the state update equation in the Kalman filter.

6. The method according to claim 1, characterized in that The determining whether the motion trajectory contacts or overlaps with the forward collision avoidance area and the side collision avoidance area of ​​the vehicle includes: According to the motion state of the ego vehicle after a period of time in the future and the motion trajectory of the target vehicle after a period of time in the future, it is determined whether the motion trajectory of the target vehicle after a period of time in the future contacts or overlaps with the forward collision avoidance area and the side collision avoidance area of ​​the ego vehicle.

7. The method according to claim 1, characterized in that Also includes: When it is determined that there is a risk of collision between the vehicle and the target vehicle, the driver is reminded according to multiple customized reminder methods, including: sound, instrument, text pop-up window on the central control screen, animation, pop-up picture, steering wheel vibration and seat belt tightening vibration.

8. An emergency collision avoidance device based on target trajectory prediction, characterized in that: include: A processing module, which is used to determine the forward collision avoidance area and the side collision avoidance area of ​​the ego vehicle, and predict the movement trajectory of the target vehicles around the ego vehicle after a period of time in the future; A judgment module, which is used to judge whether the motion trajectory contacts or overlaps with the forward collision avoidance area and the side collision avoidance area of ​​the vehicle; The collision avoidance module is used to determine if there is a collision risk between the vehicle and the target vehicle, and adopt different collision avoidance strategies according to different collision risks.

9. An electronic device, characterized in that: The electronic device comprises: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer program instructions are stored therein, and when the computer program instructions are executed by a computer, the computer is caused to execute the method according to any one of claims 1 to 7.

Images