Obstacle information processing method, device, vehicle and program product

Abstract

The application relates to the technical field of vehicles, in particular to an obstacle information processing method and device, a vehicle and a program product, wherein the method comprises the following steps: obtaining a current frame speed, a plurality of historical frame states and types of a target obstacle, determining that the target obstacle is a stationary obstacle when the plurality of historical frame states are all stationary states and the current frame speed is a preset value, collecting a current frame contour point of the target obstacle, updating a preset obstacle information table based on the current frame contour point, otherwise, determining that the target obstacle is a non-stationary obstacle, obtaining a current frame position of the target obstacle according to the type and the current frame speed, and emptying the information of the target obstacle in the preset obstacle information table. Therefore, the problem that the planning result is incorrect or inaccurate when trajectory planning is performed due to inaccurate upstream input obstacle contour information is solved, the problems that the path planning of the ego vehicle is discontinuous or the planning jump is large are solved, and the driving experience of a user is greatly improved.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to an obstacle information processing method, device, vehicle, and program product. Background Technology

[0002] In urban driving conditions, when vehicles attempt to avoid obstacles, inaccurate obstacle contour information input from upstream often leads to errors or inaccuracies in trajectory planning. This results in discontinuous or abrupt changes in the vehicle's path planning, affecting the driving experience.

[0003] In related technologies, the planning and decision-making module mainly relies on the input of the upstream perception or prediction module for single-frame planning. However, if there are significant jumps in the upstream obstacle information, such as outputting position information that does not conform to the kinematic constraints of the object model, it will cause the decision-making and planning module to make sudden changes in its decisions. This can lead to problems such as sudden braking or sharp steering wheel movements when avoiding obstacles based on their outlines, resulting in a poor user experience. Summary of the Invention

[0004] This application provides an obstacle information processing method, device, vehicle, and program product to solve the problems of incorrect or inaccurate planning results during trajectory planning due to inaccurate upstream obstacle contour information, which leads to discontinuous or large jumps in the planning of the vehicle path, thereby greatly improving the user's driving experience.

[0005] The first aspect of this application provides an obstacle information processing method, including the following steps:

[0006] Obtain the current frame speed, multiple historical frame states and types of the target obstacle, and determine whether all of the multiple historical frame states are in a stationary state;

[0007] If all of the historical frame states are in the static state, then determine whether the current frame speed is a preset value;

[0008] If the current frame speed is the preset value, the target obstacle is determined to be a stationary obstacle, and the current frame contour points of the target obstacle are collected. The preset obstacle information table is updated based on the current frame contour points. Otherwise, the target obstacle is determined to be a non-stationary obstacle, and the current frame position of the target obstacle is obtained according to the type and the current frame speed. The information of the target obstacle in the preset obstacle information table is cleared.

[0009] Optionally, in some embodiments, before updating the preset obstacle information table based on the current frame contour points, the method further includes:

[0010] Obtain multiple historical frame types, multiple historical frame velocities, multiple historical frame positions, and multiple historical frame contour points of a preset obstacle, wherein the multiple historical frame contour points conform to a preset distribution;

[0011] The preset obstacle information table is generated based on the multiple historical frame types, the multiple historical frame speeds, the multiple historical frame positions, and the multiple historical frame contour points.

[0012] Optionally, in some embodiments, updating the preset obstacle information table based on the current frame contour points includes:

[0013] Determine whether the current frame contour points are within a preset information interval;

[0014] If the current frame contour point is within the preset information interval, then the current frame contour point is taken as the current frame position; otherwise, the average value of the multiple historical frame contour points is determined, and the average value is taken as the current frame position.

[0015] Optionally, in some embodiments, obtaining the current frame position of the target obstacle based on the type and the current frame rate includes:

[0016] If the type is a first preset type, then the current frame orientation of the target obstacle is obtained, and when the current frame speed is less than or equal to a first preset threshold, the current frame position is calculated based on the current frame speed and the current frame orientation;

[0017] If the type is the second preset type, then the current frame orientation angle of the target obstacle is obtained, and when the current frame velocity is less than or equal to the second preset threshold and the current frame orientation angle is less than or equal to the third preset threshold, the current frame position is calculated according to the preset kinematic model.

[0018] Optionally, in some embodiments, after using the current frame contour point as the current frame position, the method further includes:

[0019] The mean of the contour points of the multiple historical frames is updated based on the current frame position.

[0020] A second aspect of this application provides an obstacle information processing device, comprising:

[0021] The acquisition module is used to acquire the current frame speed, multiple historical frame states and types of the target obstacle, and to determine whether the multiple historical frame states are all in a stationary state.

[0022] The judgment module is used to determine whether the current frame speed is a preset value when the states of the multiple historical frames are all in the static state.

[0023] The processing module is configured to determine that the target obstacle is a stationary obstacle when the current frame speed is the preset value, and to collect the current frame contour points of the target obstacle, and update a preset obstacle information table based on the current frame contour points; otherwise, it determines that the target obstacle is a non-stationary obstacle, and obtains the current frame position of the target obstacle according to the type and the current frame speed, and clears the information of the target obstacle in the preset obstacle information table.

[0024] Optionally, in some embodiments, before updating the preset obstacle information table based on the current frame contour points, the acquisition module is further configured to:

[0025] Obtain multiple historical frame types, multiple historical frame velocities, multiple historical frame positions, and multiple historical frame contour points of a preset obstacle, wherein the multiple historical frame contour points conform to a preset distribution;

[0026] The preset obstacle information table is generated based on the multiple historical frame types, the multiple historical frame speeds, the multiple historical frame positions, and the multiple historical frame contour points.

[0027] Optionally, in some embodiments, the processing module is specifically used for:

[0028] Determine whether the current frame contour points are within a preset information interval;

[0029] If the current frame contour point is within the preset information interval, the current frame contour point is taken as the current frame position; otherwise, the average value of the multiple historical frame contour points is determined and the average value is taken as the current frame position.

[0030] Optionally, in some embodiments, the processing module is specifically used for:

[0031] When the type is a first preset type, the current frame orientation of the target obstacle is obtained, and when the current frame speed is less than or equal to a first preset threshold, the current frame position is calculated based on the current frame speed and the current frame orientation;

[0032] When the type is the second preset type, the current frame orientation angle of the target obstacle is obtained, and when the current frame velocity is less than or equal to the second preset threshold and the current frame orientation angle is less than or equal to the third preset threshold, the current frame position is calculated according to the preset kinematic model.

[0033] Optionally, in some embodiments, after using the current frame contour point as the current frame position, the processing module is further configured to:

[0034] The mean of the contour points of the multiple historical frames is updated based on the current frame position.

[0035] A third aspect of this application provides a vehicle, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the obstacle information processing method as described in the above embodiments.

[0036] A fourth aspect of this application provides a computer program product having a computer program stored thereon, which is executed to implement the obstacle information processing method as described in the above embodiments.

[0037] Therefore, by acquiring the current frame speed, multiple historical frame states, and types of the target obstacle, and determining whether all historical frame states are stationary, if all historical frame states are stationary, the system checks if the current frame speed is a preset value. If the current frame speed is a preset value, the target obstacle is determined to be a stationary obstacle, and the current frame contour points of the target obstacle are collected. Based on these current frame contour points, the preset obstacle information table is updated. Otherwise, the target obstacle is determined to be a non-stationary obstacle, and the current frame position of the target obstacle is obtained based on its type and current frame speed. The information of the target obstacle in the preset obstacle information table is then cleared. This solves the problem of inaccurate or non-accurate planning results caused by inaccurate upstream obstacle contour information, leading to discontinuous or large jumps in the vehicle's path planning, thus greatly improving the user's driving experience.

[0038] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0039] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0040] Figure 1 This is a flowchart of an obstacle information processing method provided according to an embodiment of this application;

[0041] Figure 2 This is a schematic diagram of a common pedestrian model according to a specific embodiment of this application;

[0042] Figure 3 This is a schematic diagram of a kinematic model of a two-wheeled vehicle according to a specific embodiment of this application;

[0043] Figure 4 This is a schematic diagram of the projection of an obstacle location point according to a specific embodiment of this application;

[0044] Figure 5 This is a schematic diagram illustrating the determination of the validity of an obstacle position according to a specific embodiment of this application;

[0045] Figure 6 This is a schematic diagram of the data flow of an obstacle information processing method according to a specific embodiment of this application;

[0046] Figure 7 This is a flowchart of an obstacle information processing method according to a specific embodiment of this application;

[0047] Figure 8 This is a block diagram of an obstacle information processing device provided according to an embodiment of this application;

[0048] Figure 9 This is a block diagram of a vehicle provided according to an embodiment of this application. Detailed Implementation

[0049] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0050] The obstacle information processing method, apparatus, vehicle, and program product of this application are described below with reference to the accompanying drawings. Addressing the problem mentioned in the background art where inaccurate upstream obstacle contour information leads to errors or inaccuracies in trajectory planning, resulting in discontinuous or large jumps in vehicle path planning, this application provides an obstacle information processing method. In this method, the current frame speed, multiple historical frame states, and type of the target obstacle are obtained, and it is determined whether all historical frame states are stationary. If all historical frame states are stationary, the current frame speed is determined to be a preset value. If the current frame speed is a preset value, the target obstacle is determined to be a stationary obstacle, and the current frame contour points of the target obstacle are collected. A preset obstacle information table is updated based on the current frame contour points. Otherwise, the target obstacle is determined to be a non-stationary obstacle, and the current frame position of the target obstacle is obtained according to its type and current frame speed. The information of the target obstacle in the preset obstacle information table is then cleared. This solves the problem of inaccurate or incorrect trajectory planning results caused by inaccurate obstacle contour information input from upstream, which leads to discontinuous or large jumps in the planning of the vehicle's path, and greatly improves the user's driving experience.

[0051] Specifically, Figure 1 This is a flowchart illustrating the obstacle information processing method provided in an embodiment of this application.

[0052] like Figure 1 As shown, the obstacle information processing method includes the following steps:

[0053] In step S101, the current frame speed, multiple historical frame states and types of the target obstacle are obtained, and it is determined whether the multiple historical frame states are all in a stationary state.

[0054] In this application embodiment, the target obstacle refers to the obstacle currently detected during autonomous driving and robot navigation. This application embodiment requires processing the detected current obstacle, i.e., the target obstacle. It is understood that during trajectory planning, this application embodiment uses the outline or position information of static obstacles as a reference to solve the decision-making jump problem. The static obstacle refers to an obstacle that has been stationary for a long time.

[0055] It is understood that the kinematic state of this application embodiment is confirmed based on N frames of information collected about the obstacle. The current frame velocity in this application embodiment refers to the velocity of the target obstacle in the frame being analyzed or processed. The state of the target obstacle in this application embodiment can be a stationary state or a non-stationary state, and the multiple historical frame states of the target obstacle are collected from the historical states of the target obstacle.

[0056] It should be noted that in this embodiment of the application, the current frame is frame N+1, and the historical frame is the previous N frames.

[0057] Furthermore, the types of target obstacles in this application embodiment include: a first preset type and a second preset type, wherein the first preset type is defined as a small or highly mobile object that poses a direct threat to a moving vehicle or requires special attention, such as pedestrian obstacles, small animal obstacles, etc. Figure 2 The first type showcases common pedestrian models; the second predefined type is defined as objects that are larger, faster, or may pose a greater threat to the system, such as vehicle obstacles. Therefore, this application, through the classification of obstacles, makes the processing more efficient and effectively reduces potential safety risks.

[0058] Optionally, embodiments of this application may use various sensors and positioning systems to obtain the current frame rate of the target obstacle; and use devices such as radar, lidar, or cameras to obtain multiple historical frame states and types of the target obstacle.

[0059] It should be noted that the obstacle information processing method in this application embodiment updates the obstacle information based on the obstacle type, kinematic information, position of the current frame (N+1 frames), and trajectory information. In the following description of the embodiments, this application uses a two-wheeled vehicle kinematic model, such as... Figure 3 As shown, Figure 3This is a schematic diagram of a two-wheeled vehicle kinematic model according to a specific embodiment of this application. This model can handle traffic participants such as two-wheeled vehicles and four-wheeled vehicles, and performs simplified calculations on obstacle models. Here, the obstacle's center of mass is approximated as the geometric center of the obstacle. Since this embodiment assumes the vehicle is front-wheel drive, the steering wheel angle is considered equal to the front wheel angle. Therefore, this application can confirm the kinematic state based on historical frame (first N frames) information collected from obstacles.

[0060] In step S102, if multiple historical frame states are all in a static state, then it is determined whether the current frame speed is a preset value.

[0061] In this embodiment, the preset value is 0.

[0062] It is understandable that before handling obstacles, this application embodiment needs to determine whether the obstacle is a stationary obstacle. The determination condition needs to meet two requirements at the same time, namely, whether the states of multiple historical frames are all stationary, and whether the current frame speed is 0.

[0063] In other words, if the target obstacle is stationary for the previous N frames and its velocity in the current frame (N+1 frame) is 0, the target obstacle is determined to be a stationary obstacle.

[0064] In some cases, the target obstacle is stationary for the first N frames, but suddenly starts to move, i.e., the speed of the current frame (N+1 frame) is not 0. In such cases, the target obstacle is determined to be a potential dynamic obstacle or a non-stationary obstacle.

[0065] Optionally, in some embodiments, before updating the preset obstacle information table based on the current frame contour points, the method further includes: obtaining multiple historical frame types, multiple historical frame speeds, multiple historical frame positions, and multiple historical frame contour points of the preset obstacle, wherein the multiple historical frame contour points conform to a preset distribution; and generating a preset obstacle information table based on the multiple historical frame types, multiple historical frame speeds, multiple historical frame positions, and multiple historical frame contour points.

[0066] It is understood that, before processing obstacles, this application embodiment needs to collect data on obstacles (with decision labels) associated with the vehicle's decision-making, that is, to continuously collect data on obstacles with decision labels in order to determine information arrays such as the type, speed, position and outline of the obstacles.

[0067] Optionally, the obstacle information statistics array in this embodiment can be represented as I N speed v i heading i Position x i y iIn the form of}, the projection of the obstacle's location point can be as follows: Figure 4 As shown. This application embodiment can use a queue data structure to manage the previous N frames (historical frames) of obstacle information, thereby ensuring that the collected obstacle information is updated in a rolling manner, thus ensuring the real-time nature of obstacle processing.

[0068] Optionally, the contour points of multiple historical frames in this application embodiment conform to a normal distribution, and the mean μ and standard deviation σ of the historical frame contour points can be calculated in this application embodiment.

[0069] Specifically, in this embodiment, a preset obstacle information table is generated based on multiple historical frame types, multiple historical frame velocities, multiple historical frame positions, and multiple historical frame contour points, i.e., the obstacle information statistics array in the above embodiments. This embodiment updates the preset obstacle information table by processing and analyzing the target obstacles.

[0070] In step S103, if the current frame speed is a preset value, the target obstacle is determined to be a stationary obstacle, and the current frame contour points of the target obstacle are collected. The preset obstacle information table is updated based on the current frame contour points. Otherwise, the target obstacle is determined to be a non-stationary obstacle, and the current frame position of the target obstacle is obtained according to the type and the current frame speed. The information of the target obstacle in the preset obstacle information table is cleared.

[0071] In some cases, if the target obstacle is stationary, its position and outline information need to be processed and updated. In other cases, if the target obstacle suddenly becomes moving, its speed and orientation information need to be updated, and the current statistical array based on the target obstacle needs to be cleared, that is, the information of the target obstacle in the preset obstacle information table needs to be cleared.

[0072] The following examples will provide a detailed description of the methods and principles for processing obstacle data in this application.

[0073] Optionally, in some embodiments, updating a preset obstacle information table based on the current frame contour point includes: determining whether the current frame contour point is within a preset information interval; if the current frame contour point is within the preset information interval, then the current frame contour point is used as the current frame position; otherwise, the average of multiple historical frame contour points is determined and the average is used as the current frame position.

[0074] Based on the above embodiments, the position distribution of the target obstacle in the first N frames of this application embodiment conforms to a normal distribution with a mean of μ and a standard deviation of σ. The preset confidence interval of this application embodiment is μ ± 2σ.

[0075] It is understandable that if the target obstacle is stationary in all previous N frames and its velocity is 0 in the current frame (N+1 frame), then the target obstacle is determined to be a stationary obstacle. This embodiment compares and analyzes the information from the previous N frames with the contour points of the current frame. Furthermore, the positional distribution of the target obstacle in the previous N frames conforms to a normal distribution, allowing for comparison with the generated contour points of the current frame. If the current frame contour points fall within a distribution of μ±2σ, then the data of those current frame contour points is considered reliable, and they can be used as the current frame position of the target obstacle. Otherwise, the mean μ is used as the current frame position of the target obstacle.

[0076] Specifically, embodiments of this application can utilize technologies such as radar or lidar to detect the contour point P of a target obstacle in frame N+1 (the current frame). n+1 , will P n+1 Compare with the statistics of the previous N frames, if P n+ 1 falls within a confidence interval centered at μ and with a width of 2σ (i.e., satisfying μ - 2σ ≤ P). n+1 If ≤μ+2σ), then P is considered to be... n+1 It is credible.

[0077] Furthermore, if P n+1 If it is trustworthy, then use P. n+1 This serves as the location information of the obstacle in frame N+1; if P n+1 If the obstacle is not in the distribution of μ±2σ, it is assumed that there may be false detection or other interference, and the mean μ of the first N frames is used as the obstacle position information for the N+1 frame.

[0078] Optionally, in some embodiments, after using the current frame contour point as the current frame position, the method further includes: updating the average value of multiple historical frame contour points based on the current frame position.

[0079] Specifically, if P is used n+1 As a new location, it can be added to a preset obstacle information table, and the mean μ and standard deviation σ can be recalculated for subsequent obstacle information processing, effectively improving the real-time performance of information management.

[0080] Optionally, in some embodiments, obtaining the current frame position of the target obstacle based on the type and the current frame velocity includes: if the type is a first preset type, obtaining the current frame orientation of the target obstacle, and calculating the current frame position based on the current frame velocity and the current frame orientation when the current frame velocity is less than or equal to a first preset threshold; if the type is a second preset type, obtaining the current frame orientation angle of the target obstacle, and calculating the current frame position based on a preset kinematic model when the current frame velocity is less than or equal to a second preset threshold and the current frame orientation angle is less than or equal to a third preset threshold.

[0081] It is understandable that if the target obstacle is stationary for k frames (k ≤ N), and its velocity in the current frame (frame k+1) is v0, but no predicted trajectory is output, then the target obstacle's position will be updated. In this case, since the target obstacle suddenly starts moving, its kinematic model parameters may need to be reinitialized. In this embodiment, the velocity v0 can be used as the initial velocity of the target obstacle.

[0082] In some cases, when the target obstacle is of a first preset type, such as a pedestrian obstacle or a small animal obstacle, this application embodiment sets a maximum speed constraint for the first preset type, namely, the first preset threshold of this application embodiment. This maximum speed constraint v pmax ≤5m / s, when the current frame rate is less than or equal to the maximum speed constraint v pmax In this case, the current frame rate and the current frame orientation heading can be used. n+1 Determine the location information of the target obstacle (X) n+t Y n+t ), and clear the stationary queue to which the target obstacle belongs.

[0083] In some cases, when the target obstacle is of the second preset type, such as a vehicle obstacle, the embodiments of this application set a speed constraint v for the second preset type. cmax That is, the second preset threshold in this application embodiment, and the orientation angle constraint θ is set for the second preset type in this application embodiment. max That is, the third preset threshold in this application embodiment, when the orientation angle θ0 of the target obstacle in the current frame is less than or equal to the orientation angle constraint θ max And the current frame velocity (which can be used as the initial velocity at this time) is less than or equal to the velocity constraint v. cmax In this case, the position of the vehicle obstacle must be less than or equal to the position calculated by the following constraints:

[0084] X K+1 =X n +v0*cos(θ n+1 );

[0085] Y K+1 =Y n +v0*sin(θ n+1 );

[0086] Among them, X K+1 Y is the current frame x-coordinate of the target obstacle. K+1 X is the current frame ordinate of the target obstacle. n Y represents the x-coordinate of the target obstacle in historical frames. n v0 is the historical frame ordinate of the target obstacle, v0 is the current frame velocity of the target obstacle, and θ is the vertical coordinate of the target obstacle. n+1The current frame orientation angle of the target obstacle.

[0087] It should be noted that the obstacle information processing method in this application embodiment can filter out obstacles such as... Figure 5 The error location input is shown, such as Figure 5 As shown, the dashed line represents the updated position of the upstream input in frame N+1 (the current frame), and the solid line represents the positions of obstacles in the previous N frames (historical frames). Due to angle constraints, the position information of this dashed line is invalid. Similarly, the position of pedestrian obstacles can also be determined as valid using velocity based on the time interval between two frames.

[0088] To enable those skilled in the art to further understand the obstacle information processing method of the embodiments of this application, the following examples illustrate the processing flow of the obstacle information processing method.

[0089] Specifically, Figure 6 This is a schematic diagram of the data flow processing of an obstacle information processing method according to a specific embodiment of this application, as shown below. Figure 6 As shown, in this embodiment of the application, obstacle type, speed, trajectory, and contour information of N+1 frames (current frame) are obtained; based on the obstacle kinematic constraint processor, the obstacle information of N+1 frames is processed according to the obstacle type, speed, trajectory, and contour information of the previous N frames (historical frames); and the obstacle type, speed, trajectory, and contour information of N+1 frames after processing are obtained.

[0090] In some embodiments, Figure 7 This is a flowchart of an obstacle information processing method according to a specific embodiment of this application, such as... Figure 7 As shown, the obstacle information processing method of this application embodiment includes the following steps:

[0091] Step S701: Obtain the obstacle information array of the current frame, which is the shape, speed, trajectory and contour information of the target obstacle;

[0092] Step S702: Determine whether the obstacle is stationary in the current frame. If the obstacle is stationary in the current frame, proceed to step S703; otherwise, proceed to step S706.

[0093] Step S703: Determine the validity of the location based on the type of obstacle and the statistical values ​​of the previous N frames (historical frames);

[0094] Step S704: Determine whether the location information is valid. If the location information is valid, proceed to step S705; otherwise, proceed to step S708.

[0095] Step S705: Add the obstacle to the static obstacle information and count the set (N frames);

[0096] Step S706: Based on the type of obstacle and the velocity sequence of the previous frame, determine the validity of the current frame position sequence;

[0097] Step S707: Do not perform statistics on obstacle information, and clear the queue storing obstacles;

[0098] Step S708: Update obstacle information based on the mean μ of the current statistical values, and then proceed to step S705.

[0099] Therefore, this application embodiment performs kinematic modeling on stationary obstacles, and filters and updates the obstacle information input in the N+1 frame (current input frame) based on the type of obstacle by storing and statistically analyzing the collected obstacle information from the previous N frames (historical frames).

[0100] According to the obstacle information processing method proposed in this application, the current frame speed, multiple historical frame states, and type of the target obstacle are obtained. If all historical frame states are static and the current frame speed is a preset value, the target obstacle is determined to be a stationary obstacle. The current frame contour points of the target obstacle are then collected, and a preset obstacle information table is updated based on these points. Otherwise, the target obstacle is determined to be a non-stationary obstacle, and its current frame position is obtained based on its type and current frame speed. The information of the target obstacle in the preset obstacle information table is then cleared. This solves the problem of inaccurate obstacle contour information input from upstream, which leads to incorrect or inaccurate planning results during trajectory planning, resulting in discontinuous or large jumps in the vehicle's path planning. This significantly improves the user's driving experience.

[0101] Next, the obstacle information processing apparatus according to the embodiments of this application is described with reference to the accompanying drawings.

[0102] Figure 8 This is a block diagram of an obstacle information processing device according to an embodiment of this application.

[0103] like Figure 8 As shown, the obstacle information processing device 10 includes: an acquisition module 100, a judgment module 200, and a processing module 300.

[0104] Specifically, the acquisition module 100 is used to acquire the current frame speed, multiple historical frame states and types of the target obstacle, and determine whether the multiple historical frame states are all stationary; the judgment module 200 is used to determine whether the current frame speed is a preset value when the multiple historical frame states are all stationary; the processing module 300 is used to determine that the target obstacle is a stationary obstacle when the current frame speed is a preset value, and to collect the current frame contour points of the target obstacle, and update the preset obstacle information table based on the current frame contour points; otherwise, it determines that the target obstacle is a non-stationary obstacle, and obtains the current frame position of the target obstacle according to the type and the current frame speed, and clears the information of the target obstacle in the preset obstacle information table.

[0105] Optionally, in some embodiments, before updating the preset obstacle information table based on the current frame contour points, the acquisition module 100 is further configured to: acquire multiple historical frame types, multiple historical frame speeds, multiple historical frame positions, and multiple historical frame contour points of the preset obstacle, wherein the multiple historical frame contour points conform to a preset distribution; and generate a preset obstacle information table based on the multiple historical frame types, multiple historical frame speeds, multiple historical frame positions, and multiple historical frame contour points.

[0106] Optionally, in some embodiments, the processing module 300 is specifically used to: determine whether the current frame contour point is within a preset information interval; if the current frame contour point is within the preset information interval, use the current frame contour point as the current frame position; otherwise, determine the average of multiple historical frame contour points and use the average as the current frame position.

[0107] Optionally, in some embodiments, the processing module 300 is specifically used to: when the type is a first preset type, obtain the current frame orientation of the target obstacle, and when the current frame speed is less than or equal to a first preset threshold, calculate the current frame position based on the current frame speed and the current frame orientation; when the type is a second preset type, obtain the current frame orientation angle of the target obstacle, and when the current frame speed is less than or equal to a second preset threshold and the current frame orientation angle is less than or equal to a third preset threshold, calculate the current frame position based on a preset kinematic model.

[0108] Optionally, in some embodiments, after taking the current frame contour point as the current frame position, the processing module 300 is further configured to: update the average value of multiple historical frame contour points according to the current frame position.

[0109] It should be noted that the foregoing explanation of the obstacle information processing method embodiment also applies to the obstacle information processing device of this embodiment, and will not be repeated here.

[0110] The obstacle information processing device proposed in this application obtains the current frame speed, multiple historical frame states, and type of the target obstacle. When multiple historical frame states are all stationary and the current frame speed is a preset value, the target obstacle is determined to be a stationary obstacle. The device then collects the current frame contour points of the target obstacle and updates a preset obstacle information table based on these points. Otherwise, the target obstacle is determined to be a non-stationary obstacle, and its current frame position is obtained based on its type and current frame speed. Finally, the information of the target obstacle in the preset obstacle information table is cleared. This solves the problem of inaccurate obstacle contour information input from upstream, which leads to incorrect or inaccurate planning results during trajectory planning, resulting in discontinuous or large jumps in the vehicle's path planning. This significantly improves the user's driving experience.

[0111] Figure 9 A schematic diagram of the structure of a vehicle provided in an embodiment of this application. The vehicle may include:

[0112] The memory 901, the processor 902, and the computer program stored on the memory 901 and capable of running on the processor 902.

[0113] When the processor 902 executes the program, it implements the obstacle information processing method provided in the above embodiments.

[0114] Furthermore, the vehicle also includes:

[0115] Communication interface 903 is used for communication between memory 901 and processor 902.

[0116] The memory 901 is used to store computer programs that can run on the processor 902.

[0117] The memory 901 may include high-speed RAM (Random Access Memory) memory, and may also include non-volatile memory, such as at least one disk storage.

[0118] If the memory 901, processor 902, and communication interface 903 are implemented independently, then the communication interface 903, memory 901, and processor 902 can be interconnected via a bus to complete communication between them. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 9 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0119] Optionally, in a specific implementation, if the memory 901, processor 902, and communication interface 903 are integrated on a single chip, then the memory 901, processor 902, and communication interface 903 can communicate with each other through an internal interface.

[0120] The processor 902 may be a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of this application.

[0121] This application also provides a computer program product on which a computer program is stored, which, when executed, implements the obstacle information processing method described above.

[0122] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0123] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0124] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0125] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or more of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (FPGAs), field-programmable gate arrays (FPGAs), etc.

[0126] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware, and the program can be stored in a computer-readable storage medium. When executed, the program includes one or a combination of the steps of the method embodiments.

[0127] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. An obstacle information processing method characterized by comprising: The method comprises the following steps: obtaining a current frame speed, a plurality of historical frame states and a type of a target obstacle, and determining whether the plurality of historical frame states are all static states; if the plurality of historical frame states are all the static states, determining whether the current frame speed is a preset value; if the current frame speed is the preset value, determining that the target obstacle is a static obstacle, collecting a current frame contour point of the target obstacle, updating a preset obstacle information table based on the current frame contour point, otherwise, determining that the target obstacle is a non-static obstacle, and obtaining a current frame position of the target obstacle according to the type and the current frame speed, and clearing information of the target obstacle in the preset obstacle information table; before updating the preset obstacle information table based on the current frame contour point, the method further comprises: obtaining a plurality of historical frame types, a plurality of historical frame speeds, a plurality of historical frame positions and a plurality of historical frame contour points of a preset obstacle, wherein the plurality of historical frame contour points conform to a preset distribution; and generating the preset obstacle information table according to the plurality of historical frame types, the plurality of historical frame speeds, the plurality of historical frame positions and the plurality of historical frame contour points; the updating of the preset obstacle information table based on the current frame contour point comprises: determining whether the current frame contour point is within a preset confidence interval; if the current frame contour point is within the preset confidence interval, taking the current frame contour point as the current frame position, otherwise, determining a mean value of the plurality of historical frame contour points, and taking the mean value as the current frame position.

2. The method of claim 1, wherein, the obtaining of the current frame position of the target obstacle according to the type and the current frame speed comprises: if the type is a first preset type, obtaining a current frame direction of the target obstacle, and when the current frame speed is less than or equal to a first preset threshold, calculating the current frame position according to the current frame speed and the current frame direction; if the type is a second preset type, obtaining a current frame direction angle of the target obstacle, and when the current frame speed is less than or equal to a second preset threshold and the current frame direction angle is less than or equal to a third preset threshold, calculating the current frame position according to a preset kinematic model.

3. The method of claim 1, wherein, after taking the current frame contour point as the current frame position, the method further comprises: updating the mean value of the plurality of historical frame contour points according to the current frame position.

4. An obstacle information processing device characterized by comprising: The method comprises the following steps: obtaining a current frame speed, a plurality of historical frame states and a type of a target obstacle, and determining whether the plurality of historical frame states are all static states; if the plurality of historical frame states are all the static states, determining whether the current frame speed is a preset value; The processing module is configured to determine that the target obstacle is a static obstacle when the current frame speed is the preset value, collect a current frame contour point of the target obstacle, update a preset obstacle information table based on the current frame contour point, and otherwise determine that the target obstacle is a non-static obstacle, and obtain a current frame position of the target obstacle according to the type and the current frame speed, and clear information of the target obstacle in the preset obstacle information table. Before the preset obstacle information table is updated based on the current frame contour point, the acquisition module is further configured to acquire a plurality of historical frame types, a plurality of historical frame speeds, a plurality of historical frame positions and a plurality of historical frame contour points of a preset obstacle, wherein the plurality of historical frame contour points conform to a preset distribution, and generate the preset obstacle information table according to the plurality of historical frame types, the plurality of historical frame speeds, the plurality of historical frame positions and the plurality of historical frame contour points. The processing module is specifically configured to determine whether the current frame contour point is within a preset signal interval, take the current frame contour point as the current frame position when the current frame contour point is within the preset signal interval, and otherwise determine a mean value of the plurality of historical frame contour points and take the mean value as the current frame position.

5. A vehicle characterized by comprising: The computer program is executed to implement the obstacle information processing method according to any one of claims 1-3. The computer program is executed to implement the obstacle information processing method according to any one of claims 1-3.

6. A computer program product comprising a computer program, characterized in that, ​

Images