Vehicle collision risk monitoring method, computing device, vehicle and storage medium

Abstract

The invention relates to a vehicle collision risk monitoring method, computing equipment, a vehicle and a storage medium, and the method comprises the steps: determining a limit steering track of the vehicle in a set time window at a current sampling moment of collision risk monitoring; wherein the set time window takes the current sampling moment as a starting moment, and the limit steering track is a track formed by the vehicle in limit steering based on steering constraint; predicting a motion track of a target object in the set time window based on detection information of the vehicle for the target object; and comparing the limit steering track with the motion track to obtain a collision risk index value of steering avoidance, wherein the collision risk index value of steering avoidance represents the risk intensity of the vehicle for avoiding the target object through steering operation in the set time window.

Description

Technical Field

[0001] This disclosure relates to the field of driver assistance technology, and more specifically, to a vehicle collision risk monitoring method, computing device, vehicle, and computer-readable storage medium. Background Technology

[0002] Collision risk monitoring is a prerequisite for the effective operation of active safety functions in a Driving Automation System (DAS). Its core task is to dynamically identify potential collision risks of a vehicle, providing key information for the active safety system to make active safety decisions. Therefore, the accuracy and completeness of collision risk monitoring directly determine the effectiveness of triggering active safety functions and the user experience. Incomplete collision risk monitoring can easily lead to malfunctions or premature intervention of active safety functions, thereby damaging the smoothness of the driving experience and weakening the overall effectiveness of active safety due to unnecessary and frequent intervention. Summary of the Invention

[0003] In view of this, the present disclosure proposes a new technical solution for collision risk monitoring, which provides a collision risk index value for active safety decision-making from the perspective of whether the vehicle can avoid a collision by steering.

[0004] According to a first aspect of this disclosure, a vehicle collision risk monitoring method is provided, the method comprising: At the current sampling time of collision risk monitoring, the extreme steering trajectory of the vehicle within a set time window is determined; wherein, the set time window starts at the current sampling time, and the extreme steering trajectory is the trajectory formed by the vehicle performing extreme steering based on steering constraints. Based on the vehicle's detection information of the target object, the motion trajectory of the target object within the set time window is predicted; By comparing the extreme steering trajectory and the motion trajectory, a collision risk index value for steering avoidance is obtained; wherein, the collision risk index value for steering avoidance represents the risk intensity of the vehicle avoiding the target object through steering operation within the set time window.

[0005] Optionally, the steering constraint includes a first constraint representing the maximum steering wheel angle of the vehicle, and a second constraint representing the maximum steering wheel angle rate of the vehicle.

[0006] Optionally, at least some of the conditions of the steering constraints are determined based on the vehicle's dynamic steering constraints and the driver's steering operation characteristics constraints.

[0007] Optionally, the dynamic steering constraint is determined based on the vehicle's lateral motion constraints and the vehicle's dynamic model.

[0008] Optionally, determining the vehicle's extreme steering trajectory within a set time window includes: A steering wheel angle change model for the vehicle within a set time window is determined; wherein, the steering wheel angle change model represents the mapping relationship between the vehicle's steering wheel angle and time, and the steering wheel angle change model is set such that the steering wheel angle reaches a maximum value determined based on the steering constraint after a set time period, the set time period being determined based on the maximum steering wheel angle and the maximum steering wheel angle rate limited by the steering constraint, and the length of the set time window being greater than or equal to the set time period; Based on the steering wheel angle change model and the vehicle's dynamics model, a yaw rate change model of the vehicle within the set time window is generated; wherein, the yaw rate change model represents the mapping relationship between the vehicle's yaw rate and time. Based on the yaw rate variation model, multiple vehicle trajectory points representing the extreme steering trajectory are generated; wherein, the vehicle trajectory points include timestamp information, orientation angle information, and position information.

[0009] Optionally, comparing the extreme steering trajectory and the motion trajectory to obtain a collision risk index value representing the vehicle's ability to avoid the target object through steering maneuvers within the set time window includes: Based on the vehicle trajectory points representing the extreme steering trajectory, determine the corner position coordinates of the four corner points of the vehicle at the corresponding timestamps; Based on the target trajectory points representing the motion trajectory, the coordinates of the four corner points of the target object at the corresponding timestamps are determined; wherein, the multiple vehicle trajectory points of the extreme turning trajectory and the multiple target trajectory points of the motion trajectory are established in a correspondence based on timestamps; For each timestamp, the collision risk index value of the vehicle at the corresponding timestamp is obtained based on the relative positional relationship between the four corner points of the vehicle and the four corner points of the target object at the corresponding timestamp.

[0010] Optionally, after obtaining the collision risk index value for steering avoidance, the method further includes: An active safety strategy is determined based on the collision risk index value corresponding to the current sampling time; wherein, the collision risk index value corresponding to the current sampling time includes the collision risk index value for steering and avoidance.

[0011] According to a second aspect of this disclosure, a computing device is provided, the computing device comprising: processor; Memory used to store computer programs that can be executed by the processor; The processor is configured to implement the method according to the first aspect of this disclosure when executing a computer program stored in the memory. According to a third aspect of this disclosure, a vehicle is provided that includes a computing device as described in a second aspect of this disclosure; or, the vehicle includes: processor; Memory used to store computer programs that can be executed by the processor; The processor is configured to implement the method according to the first aspect of this disclosure when executing a computer program stored in the memory. According to a fourth aspect of this disclosure, a non-volatile computer-readable storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements the method described in the first aspect of this disclosure.

[0012] According to an embodiment of this disclosure, at the current sampling time of collision risk monitoring, the extreme turning trajectory of the vehicle within a set time window starting from the current sampling time is determined. The extreme turning trajectory is then compared with the predicted trajectory of the target object within the set time window to obtain a collision risk index value for steering avoidance. This collision risk index value reflects whether the vehicle can avoid a collision by performing extreme turning maneuvers within the set time window. Thus, from the perspective of whether the vehicle can avoid a collision through steering, it provides a basis for the active safety system to make active safety decisions, which helps to avoid the malfunction or premature intervention of active safety functions and improves the user experience.

[0013] Other features and advantages of this disclosure will become clear from the following detailed description of exemplary embodiments of the invention with reference to the accompanying drawings. Attached Figure Description

[0014] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments of the invention and, together with their description, serve to explain the principles of the invention.

[0015] Figure 1 This is a schematic diagram of the structure of a vehicle networking system to which the methods provided in the embodiments of this disclosure can be applied; Figure 2 yes Figure 1 A schematic diagram of the component structure of a vehicle; Figure 3 This is a flowchart illustrating a collision risk monitoring method according to some embodiments; Figure 4 This is a flowchart illustrating a collision risk monitoring method according to other embodiments; Figure 5 This is a flowchart illustrating a collision risk monitoring method according to some other embodiments; Figure 6 This is a schematic diagram of the hardware structure of a computing device according to some embodiments; Figure 7 This is a schematic diagram of the hardware structure of a vehicle according to some embodiments. Detailed Implementation

[0016] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of the invention.

[0017] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the invention or its application or use.

[0018] Techniques, methods, and apparatus known to those skilled in the art in the relevant field may not be discussed in detail, but where appropriate, such techniques, methods, and apparatus should be considered part of the specification.

[0019] In all the examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0020] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0021] It should be noted that all actions involving the collection, storage, use, processing, transmission, provision, disclosure, and deletion of data in this disclosure are carried out in accordance with the relevant data protection laws and regulations of the country or region where the data is located, and with the full authorization of the relevant data owner.

[0022] This disclosure relates to a scheme for collision risk monitoring in a vehicle's driving automation system. During operation, the driving automation system performs environmental perception based on sensor data and performs path planning and decision control based on the environmental perception results. This includes activating active safety functions appropriate to the traffic scenario when a collision risk is detected, preventing the vehicle from colliding with pedestrians, other vehicles, or other traffic elements in the scene, thereby ensuring driving safety. The active safety methods supported by the driving automation system include Automatic Emergency Braking (AEB) and Automatic Emergency Steering (AES).

[0023] Currently, the industry generally uses time-to-collision (TTC) models or braking distance models to provide corresponding collision risk index values. However, these models monitor collision risk based on the current direction of motion, ignoring the possibility of the vehicle avoiding collisions in other directions of motion. This can easily lead to malfunctions or premature intervention of active safety functions. Such incomplete risk assessment can impair the smoothness of the driving experience due to unnecessary and frequent interventions, ultimately weakening the overall effectiveness of active safety.

[0024] Therefore, this disclosure proposes a method for collision risk monitoring from the steering dimension to improve the accuracy and completeness of collision risk monitoring.

[0025] The method described in this disclosure can be applied to, for example... Figure 1 The vehicle-to-everything (V2X) system shown is described. This V2X system 100 may include: a vehicle 101, a server 102, and a user terminal 103.

[0026] The vehicle 101 disclosed herein is equipped with a driving automation system. The driving automation system includes various systems capable of using sensors, communication devices, decision-making devices, and execution mechanisms installed on the vehicle to monitor the driver, the vehicle, and their driving environment in real time, and to partially or fully intervene in driving tasks through information and / or motion control, or to actively avoid / mitigate collision hazards. This driving automation system can be an Advanced Driver Assistance System (ADAS) or an Autonomous Driving System (ADS). Referring to the vehicle classification standards established by the Society of Automotive Engineers (SAE), in this embodiment of the disclosure, the driving automation system can be any level from L1 to L5, where L1 is driver assistance, L2 is partial automation, L3 is conditional automation, L4 is highly automated, and L5 is fully automated.

[0027] In some examples, server 102 can be a single server or a distributed server cluster consisting of multiple servers, and its deployment can include local servers and / or cloud servers. Server 102 can communicate with vehicle 101 and / or user terminal 103 via a communication network, providing various services to vehicle 101 and / or user terminal 103. For example, server 102 can receive perception data sent by vehicle 101 and provide services such as data analysis and decision planning for vehicle 101. Alternatively, server 102 can receive query commands or control commands sent by user terminal 103 and provide corresponding services to the user.

[0028] In some examples, the user terminal 103 can be any form of electronic device that provides services to the user, such as a personal computer, laptop, smart tablet, smartphone, smart wearable device, etc. The user can interact with the vehicle 101 or server 102 through the human-machine interface terminal configured in the vehicle 101, or through the user terminal 103. For example, the user terminal 103 can be used to query the status and / or parameters of the vehicle 101, or to control the vehicle 101 to perform set tasks and / or modify configuration parameters, etc. The user terminal 103 runs an application based on the vehicle network system to achieve interaction with the vehicle 101 or server 102. This application can be a local application, a web application, or a mini-program, etc., and is not limited here.

[0029] In some examples, the aforementioned application running on user terminal 103 can provide authentication or authorization services to users. Users who are successfully authenticated and granted the corresponding permissions can query and / or control the vehicle within the scope of the granted permissions.

[0030] Vehicle 101, server 102, and user terminal 103 can communicate via a communication link provided by communication network 104. This communication network 104 can include one or more networks of any type, such as the Internet, Local Area Network (LAN), Wide Area Network (WAN), Virtual Private Network (VPN), Public Switched Telephone Network (PSTN), satellite communication network, Wi-Fi, 2G, 3G, 4G, 5G, 6G, NB-IoT, eMTC, infrared, Bluetooth, NFC, or a combination of these networks. The communication networks between vehicle 101 and server 102, between user terminal 103 and server 102, and between user terminal 103 and vehicle 101 can be the same or different.

[0031] It should be noted that, Figure 1 The structure of the vehicle-to-everything (V2X) system 100 shown is merely illustrative. V2X systems applicable to the methods described in this disclosure are not limited to the above structure and may include more or fewer devices as needed, or the devices may be combined or separated. For example, this V2X system may not include... Figure 1 User terminal 103 and / or server 102.

[0032] Figure 2 It is based on Figure 1 The illustrated embodiment provides a schematic diagram of a vehicle 101. (As shown) Figure 2As shown, the vehicle 101 may include a sensing component 1011, a computing platform 1012, an execution component 1013, etc. The sensing component 1011, the computing platform 1012, and the execution component 1013 may be connected via a bus or other means.

[0033] In some examples, the perception component 1011 can be used to collect information about the vehicle itself or its external environment. The perception component 1011 may include at least one of a visual sensing unit, radar, a positioning and navigation unit, and an inertial measurement unit (IMU). The visual sensor unit may include one or more cameras, the radar may include at least one of lidar, millimeter-wave radar, ultrasonic radar, or other radars, and the positioning and navigation unit may include at least one of a GPS system, a BeiDou system, or other global positioning systems.

[0034] In some examples, the computing platform 1012 may include a computing-capable device for processing the perception information collected by the perception component 1011 to obtain control information, and sending corresponding control commands to the execution component 1013 to cause the execution component 1013 to perform corresponding actions, thereby achieving control of the vehicle 101. For example, the computing platform 1012 can perform Simultaneous Localization and Mapping (SLAM), path planning, and behavior decision-making on the vehicle 101, thereby achieving autonomous control of the vehicle. The computing platform 1012 may include at least one processor and at least one memory, whereby each processor can individually or jointly execute instructions stored in the memory to implement the methods provided in the embodiments of this disclosure. The processor in the embodiments of this disclosure may include at least one of a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a Field Programmable Gate Array (FPGA), a System on Chip (SOC), an Application Specific Integrated Circuit (ASIC), a Micro Controller Unit (MCU), or other processors. Memory can be implemented using any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. In addition to storing instructions, memory can also store data, such as sequences of trajectory points of observed objects, or correlation data between lanes and traffic lights. The data stored in memory can be accessed and used by the processor.

[0035] In some examples, the computing platform of vehicle 101 can perform computing tasks independently or communicate with server 102 to complete computing tasks. For example, the computing platform of vehicle 101 can cooperate with server 102 to complete the corresponding computing tasks.

[0036] The computing platform 1012 can be installed in the vehicle 101. Some or all of the computing platform 1012 can also be installed in the server 102 corresponding to the vehicle 101. For example, some functions of the computing platform 1012 with high real-time requirements are installed in the vehicle 101, while other functions with lower real-time requirements are installed in the server 102 corresponding to the vehicle 101.

[0037] In some examples, the execution component 1013 is used to perform corresponding actions based on the control of the computing platform 1012, enabling the vehicle 101 to complete the movement task. The execution component 1013 may include, for example, a power component, a braking component, a transmission component, a steering component, etc.

[0038] It should be noted that, Figure 2 The structure of vehicle 101 shown is merely illustrative. The vehicle in this embodiment is not limited to the above structure and may include more or fewer components as needed. The devices may also be combined or separated. For example, the vehicle may not include the aforementioned computing platform. Furthermore, the vehicle may also include communication components, interface components, multimedia components, input components, output components, etc.

[0039] The following is combined with Figure 1 The systems shown illustrate various embodiments of this disclosure.

[0040] <First Embodiment> Figure 3 A flowchart illustrating a vehicle collision risk monitoring method according to some embodiments is shown. This method can be... Figure 1 Vehicle 101 in the middle can also be implemented by Figure 1 The implementation can be carried out by server 102, or it can be implemented jointly by vehicle 101 and server 102. For example... Figure 3 As shown, the method of this embodiment may include the following steps S310 to S330.

[0041] Step S310: At the current sampling time of collision risk monitoring, determine the vehicle's extreme steering trajectory within a set time window starting from the current sampling time.

[0042] In this embodiment, collision risk monitoring can be triggered by a set event. The set event can be the arrival of the sampling time based on a set sampling frequency, the receipt of a set input from the driver, or the occurrence of a set condition in the environmental perception results, etc.

[0043] The driving automation system can execute steps S310 to S330 at each sampling time of collision risk monitoring to obtain the collision risk index value corresponding to the current sampling time, so as to determine the active safety decision corresponding to the current sampling time based at least on the collision risk index value. The active safety decision includes the timing of the activation of active safety functions, as well as the active safety mode that needs to be activated.

[0044] In this embodiment, the extreme steering trajectory is the trajectory formed by the vehicle performing extreme steering based on steering constraints starting from the current state. In other words, the extreme steering trajectory is the trajectory formed by the vehicle performing extreme steering based on the steering constraints starting from the current state. The current state of the vehicle is the state of the vehicle at the current sampling time.

[0045] In some examples, steering constraints may include a first constraint representing the maximum steering wheel angle and a second constraint representing the rate of maximum steering wheel angle. The first constraint may be the maximum steering wheel angle itself, or other parameters that are mapped to the maximum steering wheel angle, such as maximum lateral acceleration or maximum front wheel angle. The second constraint may be the maximum steering wheel angle rate itself, or other parameters that are mapped to the maximum steering wheel angle rate, such as maximum rate of change of lateral acceleration or maximum front wheel angle rate.

[0046] In this example, the maximum steering wheel angle represents the maximum angular position the steering wheel can rotate to, limiting the vehicle's minimum turning radius. The maximum steering wheel angular velocity represents the maximum angular velocity of the steering wheel, limiting the time required for the steering wheel to reach its maximum angle. The maximum steering wheel angle and maximum steering wheel angular velocity define the limits of steering operation from the spatial dimension of geometric boundaries and the temporal dimension of dynamic response, respectively. Together, they define a functional model of the steering wheel angle changing over time, i.e., the steering wheel angle variation model, to generate the vehicle's extreme steering trajectory. Here, since the maximum steering wheel angle and maximum steering wheel angular velocity directly correspond to motion control commands and are the most direct manifestation of human driver steering operations, using these two parameters as steering constraint benchmarks makes model construction simple and direct, and also makes it easier to incorporate the driver's steering operation characteristics into the steering constraints.

[0047] In some examples, steering constraints can be determined based on the vehicle's dynamic steering constraints to ensure that the vehicle does not experience dangers such as sideslip or rollover when steering at its limit steering trajectory. The vehicle's dynamic steering constraints reflect its own performance and are primarily determined by the vehicle's design parameters. Furthermore, when determining dynamic steering constraints, road surface condition parameters reflecting road conditions can also be incorporated. For example, road surface condition parameters can be converted into adjustment coefficients, and these coefficients can be applied to the vehicle's design parameters to obtain the dynamic steering constraints at the current sampling time.

[0048] In other examples, at least some conditions of the steering constraints, such as the maximum steering wheel angle rate and / or the maximum steering wheel angle, can be determined based on both the vehicle's dynamic steering constraints and the driver's steering operation characteristics constraints. The driver's steering operation characteristics constraints reflect the steering ability achievable by the driver in actual operation and are used to ensure that the extreme steering trajectory is feasible for the driver. In this example, determining at least some conditions of the steering constraints based on the vehicle's dynamic steering constraints and the driver's steering operation characteristics constraints ensures that the extreme steering trajectory is within the range of vehicle dynamics and human driving ability, avoiding vehicle instability or impractical maneuvering.

[0049] Taking steering constraints, including maximum steering wheel angle and maximum steering wheel angle rate, as an example, the maximum steering wheel angle... It can be the first maximum steering wheel angle based on dynamic steering constraints. and the second maximum steering wheel angle constrained by the driver's steering operation characteristics minimum value Maximum steering wheel turning rate It can be the first maximum steering wheel angle rate based on dynamic steering constraints. and the second maximum steering wheel angle rate constrained by the driver's steering operation characteristics minimum value .

[0050] In some examples, driver steering characteristics are constrained, such as the second maximum steering wheel angle. Second maximum steering wheel angular rate This can be obtained based on the driver's historical operation data. In other words, a driving operation profile of the driver can be generated based on this historical data, and corresponding steering operation characteristic constraints can be determined based on this profile. These steering operation characteristic constraints may include, for example, the maximum steering wheel angle achievable by the driver, and / or the maximum steering wheel angle rate achievable by the driver.

[0051] In other examples, driver steering characteristics constraints can also be obtained through user settings. During the user settings process, the vehicle can guide the user to perform extreme steering maneuvers within their capabilities via the onboard terminal to collect the driver's steering characteristics.

[0052] In some examples, dynamic steering constraints can be determined based on the vehicle's lateral motion constraints. For example, the first maximum steering wheel angle. First maximum steering wheel angular rate It can be based on the vehicle's maximum lateral acceleration. and the maximum lateral acceleration change rate of the vehicle. Confirmed. The lateral motion constraint can be derived from the vehicle's original design parameters, or the road surface state parameters at the current sampling moment can be converted into adjustment coefficients and applied to the original design parameters to obtain the final lateral motion constraint.

[0053] In some examples, the dynamic steering constraint is a constraint about the steering wheel angle. In this example, the dynamic steering constraint can be determined based on the vehicle's front wheel steering constraint, which can be further determined based on the vehicle's lateral motion constraint and the vehicle's dynamic model. A first mapping relationship based on the dynamic model exists between the front wheel steering constraint and the lateral motion constraint, and a relationship based on the steering ratio exists between the dynamic steering constraint and the front wheel steering constraint. The established second mapping relationship, the turning ratio This refers to the transmission ratio from the steering wheel angle to the wheel angle.

[0054] For example, dynamic steering constraints include a first maximum steering wheel angle. First maximum steering wheel angular rate Front wheel steering constraints include the maximum front wheel steering angle. Maximum front wheel steering angle change rate The second mapping relationship can be expressed as: ; .

[0055] Furthermore, taking a two-degree-of-freedom dynamic model as an example, the first mapping relationship can be expressed as: ; ; , ; Where L represents the wheelbase in meters (m); M represents the vehicle mass in kilograms (kg); c represents the distance from the rear axle to the center of gravity in meters (m); b represents the distance from the front axle to the center of gravity in meters (m); and v represents the vehicle speed in m / s, where v can be the speed of the vehicle at the current sampling time. This is the front wheel lateral stiffness, expressed in Newtons per radian (N / rad). This represents the rear wheel lateral stiffness, expressed in N / rad.

[0056] In some examples, determining the vehicle's extreme steering trajectory within a set time window starting from the current adoption time in step S310 may include the following steps S311 to S313: Step S311: Determine the steering wheel angle change model of the vehicle within a set time window.

[0057] This steering wheel angle variation model represents the mapping relationship between the vehicle's steering wheel angle and time. This mapping relationship can be represented as a continuous function or as a discrete sequence.

[0058] The steering wheel angle variation model is set so that the steering wheel angle reaches the maximum value limited by the steering constraint after a set time. The set time is determined based on the maximum steering wheel angle and the maximum steering wheel angle rate limited by the steering constraint. The length of the set time window is greater than or equal to the set time. In other words, the length of the set time window should be such that the steering wheel angle can reach the maximum value.

[0059] The steering wheel angle variation model can be constructed based on any smooth model, such as a trigonometric function model, as long as the steering wheel angle is based on the maximum steering wheel angle. and maximum steering wheel angle rate A predetermined time is set to reach the turning constraint. That's all.

[0060] For example, the steering wheel angle change model can be represented as: ,

[0061] The starting time of the time window is set to t=0, at which point the steering wheel angle is... =0, set time At this time, the steering wheel angle Here, the time window is set to start at relative time 0, therefore, the set time has the same meaning as the set duration mentioned above.

[0062] Step S312: Based on the steering wheel angle change model and the vehicle's dynamics model, generate a yaw rate change model for the vehicle within the set time window. This yaw rate change model represents the vehicle's yaw rate. The mapping relationship between time and time.

[0063] Since the vehicle position is related to the yaw rate, in this example, the corresponding yaw rate change model can be generated based on the steering wheel angle change model and the vehicle's dynamics model.

[0064] Taking a two-degree-of-freedom dynamic model as an example, the yaw rate It can be represented as: ,

[0065] Step S313: Based on the yaw rate change model, generate multiple trajectory points representing the extreme turning trajectory.

[0066] In this example, the trajectory points can include timestamp information, orientation angle information, and location information. The location information could be the vehicle's center of mass at the current sampling time. The corresponding position coordinates in the vehicle coordinate system.

[0067] Let the current sampling time be... The 0th trajectory point is represented as... That is, position coordinates Orientation angle Then, within the set time window... At time i, the i-th trajectory point can be represented as : Orientation Angle ; Position coordinates in the x direction ; Position coordinates in the y direction

[0068] in, , Where i is an integer greater than or equal to 1, x is the longitudinal direction of the vehicle, and y is the lateral direction of the vehicle. The time interval between two adjacent trajectory points is also called the time step. , This represents the displacement component of the vehicle in its own coordinate system along the corresponding direction.

[0069] In another example, steering constraints can also be represented by yaw rate, and a yaw rate variation model can be directly established. Based on the yaw rate variation model, multiple trajectory points representing the extreme steering trajectory can be generated.

[0070] Step S320: Based on the vehicle's detection information of the target object, predict the motion trajectory of the target object within a set time window.

[0071] In this embodiment, the detection information of the target object can come from various sensors mounted on the vehicle, including but not limited to cameras, millimeter-wave radar, and lidar. Based on the analysis of the target object's motion state, which includes the motion state at the current sampling moment and historical motion states prior to the current sampling moment, the motion trajectory within a set future time window is predicted using a motion model. Here, the motion model can be a constant velocity model (CV) or a constant acceleration model (CA), or a combination of both models can be used to complete the prediction.

[0072] Step S330: Compare the extreme steering trajectory with the motion trajectory of the target object to obtain the collision risk index value for steering avoidance.

[0073] In this embodiment, the collision risk index value of the steering avoidance indicates the risk intensity of the vehicle avoiding the target object through steering operation within a set time window.

[0074] In some examples, the collision risk index value for steering avoidance can be determined by the distance between the vehicle and the target object. The minimum distance at any given time can also be represented by a risk level based on the minimum distance mapping.

[0075] In some examples, to make accurate comparisons and improve the accuracy and reliability of the determined collision risk index value for steering avoidance, step S330 may further include steps S331 to S333: Step S331: Based on the vehicle trajectory points representing the extreme steering trajectory, determine the corner position coordinates of the four corner points of the vehicle at the corresponding timestamps.

[0076] In step S331, the vehicle shape can be represented as a rectangle. At each vehicle trajectory point, the coordinates of the four corner points of the vehicle can be converted based on the vehicle length, width, and the distance from the vehicle's centroid to its geometric center. The coordinates of the four corner points can be represented as follows: , , , .

[0077] Step S332: Based on the target trajectory points representing the motion trajectory, determine the corner coordinates of the four corner points of the target object at the corresponding timestamps.

[0078] Multiple vehicle trajectory points of the extreme steering trajectory and multiple target trajectory points of the target object's motion trajectory are established based on timestamps. For example, multiple vehicle trajectory points correspond one-to-one with multiple target trajectory points, and the corresponding vehicle trajectory points and target trajectory points have the same timestamp.

[0079] The i-th target trajectory point can be represented as The target trajectory point. In predicting the motion trajectory, during the prediction... It can be the geometric center of the target object at the current sampling time. The corresponding position coordinates in the vehicle coordinate system.

[0080] Accordingly, at each target trajectory point, the target object's length and width can be converted into the coordinates of its four corner points. The coordinates of the four corner points can be represented as follows: , , , .

[0081] Step S333: For each timestamp, based on the relative positional relationship between the four corners of the vehicle and the four corners of the target object at the corresponding timestamp, obtain the collision risk index value of the vehicle at the corresponding timestamp.

[0082] In some examples, the relative positional relationship between the vehicle and the target object can be represented by the minimum distance from the corner points of the vehicle to each side of the target object, or by the minimum distance from the corner points of the target object to each side of the vehicle, or by a combination of both. The four sides of the target object are obtained by connecting its two adjacent corner points. Similarly, the four sides of the vehicle are obtained by connecting its two adjacent corner points.

[0083] For example, at each timestamp, the minimum distance from each corner of the vehicle to each side of the target object is calculated, and the minimum value among all the minimum distances corresponding to all corners is used as the basis for the calculation. To determine the collision risk indicators for that timestamp.

[0084] For example, at each timestamp, the minimum distance from each corner of the target object to each side of the vehicle is calculated, and the minimum value among all the minimum distances corresponding to all corner points is used as the basis for the calculation. To determine the collision risk indicators for that timestamp.

[0085] For example, at each timestamp, calculate the minimum distance from each corner point of the vehicle to each side of the target object, and the minimum distance from each corner point of the target object to each side of the vehicle, and based on... and The minimum value in the time stamp determines the collision risk index for that time stamp.

[0086] In some examples, at each timestamp, the relative positions of the four corners of the vehicle and the four corners of the target object at that timestamp can be used to determine whether a collision will occur. If the vehicle region formed by the four corners of the vehicle overlaps with the target region formed by the four corners of the target object, a collision is likely, with a minimum distance of 0 and the highest risk level. If the vehicle region and the target region do not overlap, no collision is likely, and the minimum distance is calculated. and / or In order to obtain collision risk indicators.

[0087] When determining whether the vehicle area overlaps with the target area, the maximum and minimum corner coordinates of the vehicle in the x and y directions can be determined: ; , ; In addition, determine the maximum and minimum corner coordinates of the target object in the x and y directions: ; .

[0088] like( )or( )or( )or( If the condition is true, then the vehicle area and the target area do not overlap, and the vehicle and the target object do not collide. Otherwise, the vehicle area and the target area overlap, and the vehicle and the target object collide. In this case, the minimum distance between the two is 0.

[0089] In another example, the collision risk index value for steering avoidance can also be determined based on the distance between the vehicle's trajectory point and the target trajectory point at the same timestamp. For example, the collision risk index value for steering avoidance can be determined based on the distance difference between the two and a set distance threshold.

[0090] According to steps S310 to S330, the collision risk index value for steering avoidance in this embodiment reflects whether the vehicle can avoid the target object through extreme turning operations within a set time window to avoid a collision. Thus, from the perspective of whether the vehicle can avoid a collision through steering, it can provide an important basis for the active safety system to make active safety decisions, which is conducive to avoiding the malfunction or premature intervention of active safety functions and improving the user experience.

[0091] <Second Embodiment> In this embodiment, the driving automation system can make active safety decisions based on collision risk index values ​​related to steering and avoidance, to determine when to activate active safety functions and the active safety methods that need to be activated. For example... Figure 4 As shown, the method of this embodiment may include the following steps S410 to S440: Step S410: At the current sampling time of collision risk monitoring, determine the vehicle's extreme steering trajectory within a set time window starting from the current sampling time.

[0092] Step S420: Based on the vehicle's detection information of the target object, predict the motion trajectory of the target object within a set time window.

[0093] Step S430: Compare the extreme steering trajectory with the motion trajectory of the target object to obtain the collision risk index value for steering avoidance.

[0094] Step S440: Determine the active safety strategy based on the collision risk index value corresponding to the current sampling time.

[0095] The collision risk index value corresponding to the current sampling time includes at least the collision risk index value for steering and avoidance.

[0096] For example, when the collision risk index value is lower than the safety threshold, active safety functions are not triggered at the current sampling time; when the collision risk index value indicates that the vehicle will collide with the target object at a certain moment, automatic emergency braking (AEB) is triggered before that moment.

[0097] In this embodiment, as Figure 5 As shown, when conducting collision risk monitoring, not only can the collision risk index value of steering avoidance be evaluated, but at least one of the collision time interval (TTC) and braking distance can also be evaluated simultaneously to combine multiple index values ​​and determine active safety strategies.

[0098] The method according to the embodiments of this disclosure provides a more comprehensive basis for decision-making for active safety systems by evaluating the vehicle's avoidance ability under extreme steering conditions. This effectively avoids the problem of false triggering caused by ignoring the possibility of steering avoidance in traditional methods, and improves the accuracy of the system and user experience.

[0099] <Third Embodiment> This embodiment provides a computing device, such as Figure 6 As shown, the computing device 600 includes a memory 602 and a processor 601. The memory 602 is used to store a computer program executed by the processor 601. The processor 601 is configured to implement the method according to any embodiment of the present disclosure when executing the computer program stored in the memory 602.

[0100] The computing device 600 can be independent of the vehicle, or at least partially located in the vehicle. For example, the computing device 600 can be a chip, controller, etc. located in the vehicle, or it can be a server. No limitation is made here.

[0101] <Fourth Embodiment> This embodiment provides a vehicle that may include a computing device 600 according to a third embodiment.

[0102] In some embodiments, such as Figure 7 As shown, the vehicle 700 may also include a memory 702 and a processor 701. The memory 702 is used to store a computer program that runs on the processor 701. The processor 701 is configured to implement the method according to any embodiment of the present disclosure when executing the computer program stored in the memory 702.

[0103] This invention can be a system, method, and / or computer program product. A computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of the invention.

[0104] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example, but not limited to, electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination thereof. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0105] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0106] The computer program instructions used to perform the operations of this invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing state information from the computer-readable program instructions. This electronic circuitry can execute the computer-readable program instructions to implement various aspects of the invention.

[0107] Various aspects of the present invention are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0108] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0109] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0110] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions. It is well known to those skilled in the art that implementation in hardware, implementation in software, and implementation using a combination of software and hardware are equivalent.

[0111] The various embodiments of the present invention have been described above. These descriptions are exemplary and not exhaustive, and are not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or technical improvements to the embodiments in the market, or to enable others skilled in the art to understand the embodiments disclosed herein. The scope of the invention is defined by the appended claims.

Claims

1. A method for monitoring vehicle collision risk, characterized in that, include: At the current sampling time of collision risk monitoring, the extreme steering trajectory of the vehicle within a set time window is determined; wherein, the set time window starts at the current sampling time, and the extreme steering trajectory is the trajectory formed by the vehicle performing extreme steering based on steering constraints. Based on the vehicle's detection information of the target object, the motion trajectory of the target object within the set time window is predicted; By comparing the extreme steering trajectory and the motion trajectory, a collision risk index value for steering avoidance is obtained; wherein, the collision risk index value for steering avoidance represents the risk intensity of the vehicle avoiding the target object through steering operation within the set time window.

2. The method according to claim 1, characterized in that, The steering constraints include a first constraint representing the maximum steering wheel angle of the vehicle, and a second constraint representing the maximum steering wheel angle rate of the vehicle.

3. The method according to claim 1, characterized in that, At least some of the conditions of the steering constraints are determined based on the vehicle's dynamic steering constraints and the driver's steering operation characteristics constraints.

4. The method according to claim 3, characterized in that, The dynamic steering constraint is determined based on the vehicle's lateral motion constraint and the vehicle's dynamic model.

5. The method according to claim 1, characterized in that, Determining the vehicle's extreme steering trajectory within a set time window includes: A steering wheel angle change model for the vehicle within a set time window is determined; wherein, the steering wheel angle change model represents the mapping relationship between the vehicle's steering wheel angle and time, and the steering wheel angle change model is set such that the steering wheel angle reaches a maximum value determined based on the steering constraint after a set time period, the set time period being determined based on the maximum steering wheel angle and the maximum steering wheel angle rate limited by the steering constraint, and the length of the set time window being greater than or equal to the set time period; Based on the steering wheel angle change model and the vehicle's dynamics model, a yaw rate change model of the vehicle within the set time window is generated; wherein, the yaw rate change model represents the mapping relationship between the vehicle's yaw rate and time. Based on the yaw rate variation model, multiple vehicle trajectory points representing the extreme steering trajectory are generated; wherein, the vehicle trajectory points include timestamp information, orientation angle information, and position information.

6. The method according to any one of claims 1 to 5, characterized in that, The comparison of the extreme steering trajectory and the motion trajectory to obtain a collision risk index value representing the vehicle's ability to avoid the target object through steering operations within the set time window includes: Based on the vehicle trajectory points representing the extreme steering trajectory, determine the corner position coordinates of the four corner points of the vehicle at the corresponding timestamps; Based on the target trajectory points representing the motion trajectory, the coordinates of the four corner points of the target object at the corresponding timestamps are determined; wherein, the multiple vehicle trajectory points of the extreme turning trajectory and the multiple target trajectory points of the motion trajectory are established in a correspondence based on timestamps; For each timestamp, the collision risk index value of the vehicle at the corresponding timestamp is obtained based on the relative positional relationship between the four corner points of the vehicle and the four corner points of the target object at the corresponding timestamp.

7. The method according to any one of claims 1 to 5, characterized in that, After obtaining the collision risk index value for steering avoidance, the method further includes: An active safety strategy is determined based on the collision risk index value corresponding to the current sampling time; wherein, the collision risk index value corresponding to the current sampling time includes the collision risk index value for steering and avoidance.

8. A computing device, characterized in that, include: processor; Memory used to store computer programs that can be executed by the processor; The processor is configured to implement the method of any one of claims 1 to 7 when executing a computer program stored in the memory.

9. A vehicle, characterized in that, Includes the computing device of claim 8; or includes: processor; Memory used to store computer programs that can be executed by the processor; The processor is configured to implement the method of any one of claims 1 to 7 when executing a computer program stored in the memory.

10. A non-volatile computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method described in any one of claims 1 to 7.

Images