Obstacle information processing method and device, vehicle and program product
By obtaining and updating the current frame speed and historical frame status of the obstacle, and judging and updating the obstacle information table, the problem of trajectory planning errors caused by inaccurate input obstacle profile information is solved, and the accuracy of the vehicle avoiding obstacles is improved. Driving experience.
Patent Information
- Application Number
- CN202410953468.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-16
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-07-16
AI Technical Summary
When a vehicle avoids obstacles under urban operating conditions, due to inaccurate obstacle profile information inputted upstream, the trajectory planning results are incorrect or discontinuous, which affects the driving experience.
By obtaining the current frame speed and historical frame status of the target obstacle, we judge whether the obstacle is in a static state, and update the obstacle information table according to the type and speed to ensure the accuracy of the obstacle position information and avoid planning jumps.
It improves the accuracy and continuity of trajectory planning, improves the user's driving experience, and reduces the situation of sudden brakes and violent steering.
Smart Images

Figure CN118941588A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of vehicle technology, and in particular to an obstacle information processing method, device, vehicle and program product. Background Art
[0002] When vehicles in urban conditions avoid obstacles, they often encounter problems such as erroneous or inaccurate planning results during trajectory planning due to inaccurate obstacle contour information input upstream, resulting in discontinuous path planning or large planning jumps, which affects 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 is a large jump 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 planning module to jump, resulting in sudden braking or slamming the steering wheel when avoiding the outline of the obstacle, which is a poor experience. Summary of the invention
[0004] The present 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 obstacle contour information input upstream, thereby causing discontinuous vehicle path planning or large planning jumps, and greatly improve the user's driving experience.
[0005] The first embodiment of the present application provides an obstacle information processing method, comprising the following steps:
[0006] Obtaining the current frame speed, multiple historical frame states and types of the target obstacle, and determining whether the multiple historical frame states are all static;
[0007] If the multiple historical frame states are all the static state, determining 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, and 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 the type and the current frame speed, and 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] 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;
[0011] The preset obstacle information table is generated according to 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 a preset obstacle information table based on the current frame contour points includes:
[0013] Determine whether the current frame contour point is within a preset confidence interval;
[0014] If the current frame contour point is within the preset confidence interval, the current frame contour point is used as the current frame position; otherwise, the average of the multiple historical frame contour points is determined and the average is used as the current frame position.
[0015] Optionally, in some embodiments, obtaining the current frame position of the target obstacle according to the type and the current frame speed includes:
[0016] If the type is the first preset type, obtaining the current frame orientation 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 orientation;
[0017] If the type is the second preset type, the current frame orientation angle of the target obstacle is obtained, and when the current frame speed 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 a preset kinematic model.
[0018] Optionally, in some embodiments, after taking the current frame contour point as the current frame position, the method further includes:
[0019] The mean values of the plurality of historical frame contour points are updated according to the current frame position.
[0020] A second aspect of the present application provides an obstacle information processing device, including:
[0021] An acquisition module, 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 static;
[0022] A judging module, configured to judge whether the current frame speed is a preset value when the states of the plurality of historical frames are all the static state;
[0023] a processing module, configured to, when the current frame speed is the preset value, determine that the target obstacle is a stationary obstacle, collect current frame contour points of the target obstacle, and update a preset obstacle information table based on the current frame contour points; otherwise, determine that the target obstacle is a non-stationary obstacle, 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.
[0024] Optionally, in some embodiments, before updating the preset obstacle information table based on the current frame contour points, the acquisition module is further used to:
[0025] 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;
[0026] The preset obstacle information table is generated according to 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 to:
[0028] Determine whether the current frame contour point is within a preset confidence interval;
[0029] When the current frame contour point is within the preset confidence interval, the current frame contour point is used as the current frame position; otherwise, the average of the multiple historical frame contour points is determined and the average is used as the current frame position.
[0030] Optionally, in some embodiments, the processing module is specifically used to:
[0031] When the type is the first preset type, obtaining the current frame orientation 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 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 speed 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 a preset kinematic model.
[0033] Optionally, in some embodiments, after taking the current frame contour point as the current frame position, the processing module is further configured to:
[0034] The mean values of the plurality of historical frame contour points are updated according to the current frame position.
[0035] A third aspect of the present application provides a vehicle, comprising: 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 embodiment.
[0036] A fourth aspect of the present application provides a computer program product on which a computer program is stored, and the program is executed to implement the obstacle information processing method as described in the above embodiment.
[0037] Therefore, by obtaining the current frame speed, multiple historical frame states and types of the target obstacle, and judging whether the multiple historical frame states are all static, if the multiple historical frame states are all static, judging whether the current frame speed is a preset value, if the current frame speed is a preset value, judging that the target obstacle is a static obstacle, and collecting the current frame contour points of the target obstacle, updating the preset obstacle information table based on the current frame contour points, otherwise, judging that the target obstacle is a non-static obstacle, and obtaining the current frame position of the target obstacle according to the type and current frame speed, clearing the information of the target obstacle in the preset obstacle information table. Therefore, the problem of incorrect or inaccurate planning results during trajectory planning due to inaccurate upstream input obstacle contour information is solved, which leads to discontinuous path planning or large planning jumps of the self-vehicle, and greatly improves the user's driving experience.
[0038] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0039] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:
[0040] Figure 1 A flowchart of an obstacle information processing method provided according to an embodiment of the present application;
[0041] Figure 2 is a schematic diagram of a common pedestrian model according to a specific embodiment of the present application;
[0042] Figure 3 is a schematic diagram of a kinematic model of a two-wheeled vehicle according to a specific embodiment of the present application;
[0043] Figure 4 is a schematic diagram of obstacle position point projection according to a specific embodiment of the present application;
[0044] Figure 5 A schematic diagram of obstacle position validity determination according to a specific embodiment of the present application;
[0045] Figure 6 A schematic diagram of a processing data flow of an obstacle information processing method according to a specific embodiment of the present application;
[0046] Figure 7 is a flowchart of an obstacle information processing method according to a specific embodiment of the present application;
[0047] Figure 8 A block diagram of an obstacle information processing device provided according to an embodiment of the present application;
[0048] Fig. 9 It is a block diagram of a vehicle provided according to an embodiment of the present application. DETAILED DESCRIPTION
[0049] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.
[0050] The obstacle information processing method, device, vehicle and program product of the embodiment of the present application are described below with reference to the accompanying drawings. In view of the problem mentioned in the above background technology that due to inaccurate upstream input obstacle contour information, the planning result is wrong or inaccurate when performing trajectory planning, thereby causing discontinuous path planning or large planning jumps of the self-vehicle, the present application provides an obstacle information processing method, in which 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 static; if the multiple historical frame states are all static, it is determined whether the current frame speed is a preset value; if the current frame speed is a preset value, it is determined that the target obstacle is a static obstacle, and the current frame contour points of the target obstacle are collected, and the preset obstacle information table is updated based on the current frame contour points, otherwise, the target obstacle is determined to be a non-static obstacle, and the current frame position of the target obstacle is obtained according to the type and current frame speed, and the information of the target obstacle in the preset obstacle information table is cleared. This solves the problem of incorrect or inaccurate planning results during trajectory planning due to inaccurate obstacle contour information input upstream, which leads to discontinuous vehicle path planning or large planning jumps, greatly improving the user's driving experience.
[0051] Specifically, Figure 1 A flowchart of the obstacle information processing method provided in an embodiment of the present 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 static.
[0054] Among them, the target obstacle of the embodiment of the present application refers to the obstacle currently monitored during the process of autonomous driving and robot navigation. The embodiment of the present application needs to process the detected current obstacle, that is, the target obstacle. It is understandable that in the process of trajectory planning, the embodiment of the present application uses the outline or position information of the static obstacle as a reference to solve the decision-making jump problem. The static obstacle refers to an obstacle that remains stationary for a long time.
[0055] It is understandable that the embodiment of the present application confirms the kinematic state based on the N frames of information collected by the obstacle. The current frame speed of the embodiment of the present application refers to the speed of the target obstacle in the frame being analyzed or processed. The state of the target obstacle in the embodiment of the present application is a stationary state and a non-stationary state, and the multiple historical frame states of the target obstacle are the historical states of the target obstacle.
[0056] It should be noted that the current frame in the embodiment of the present application is the N+1 frame, and the historical frame is the previous N frames.
[0057] Furthermore, the types of target obstacles in the embodiment of the present application 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 a pedestrian obstacle, a small animal obstacle, etc. Figure 2 A common pedestrian model is shown; the second preset type is defined as objects that are larger in size, faster in speed, or may pose a greater threat to the system, such as vehicle obstacles, etc. Therefore, this application makes the processing process more efficient and effectively reduces potential safety risks by classifying obstacles.
[0058] Optionally, the embodiment of the present application can obtain the current frame speed of the target obstacle through various sensors and positioning systems; and obtain multiple historical frame states and types of the target obstacle through devices such as radar, lidar, or camera.
[0059] It should be noted that the obstacle information processing method of the embodiment of the present application is updated according to the type of obstacle, kinematic information, the position of the current frame (N+1 frame), and the trajectory information. In the following embodiments, the present application adopts 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 of a specific embodiment of the present application. This model can handle traffic participants such as two-wheeled vehicles and four-wheeled vehicles, and simplify the calculation of the obstacle model. Here, the center of mass of the obstacle is approximately calculated as the geometric center of the obstacle. At the same time, since the embodiment of the present application assumes that the vehicle is front-wheel driven, the embodiment of the present application considers that the steering wheel angle is equal to the front wheel angle. Therefore, the present application can confirm the kinematic state based on the historical frame (first N frames) information collected by the obstacle.
[0060] In step S102, if the states of the plurality of historical frames are all static states, it is determined whether the current frame speed is a preset value.
[0061] Among them, the preset value of the embodiment of the present application is 0.
[0062] It is understandable that before obstacle processing, the embodiment of the present application needs to determine whether the obstacle is a stationary obstacle. The judgment condition needs to meet two requirements at the same time, namely, whether multiple historical frame states are all stationary and whether the current frame speed is 0.
[0063] That is, when the first N frames of the target obstacle are all in a stationary state and the speed of 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 in the first N frames, but the target obstacle suddenly starts to move, that is, when the speed of the current frame (N+1 frame) is not 0, 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, it also includes: obtaining multiple historical frame types, multiple historical frame speeds, multiple historical frame positions and multiple historical frame contour points of the preset obstacles, wherein the multiple historical frame contour points conform to a preset distribution; generating a preset obstacle information table according to the multiple historical frame types, multiple historical frame speeds, multiple historical frame positions and multiple historical frame contour points.
[0066] It is understandable that before processing obstacles, the embodiment of the present application needs to collect data on obstacles associated with the vehicle's decision (with decision tags), that is, to continuously collect data on obstacles with decision tags to determine the type, speed, position, contour and other information arrays of the obstacles.
[0067] Optionally, the information statistics array of the obstacle in the embodiment of the present application can be expressed as I N {Speed v i , heading angle i , position x i ,y i}, where the projection of the obstacle position point can be as follows Figure 4 The embodiment of the present application can use the data structure of the queue to manage the previous N frames (historical frames) of the obstacle information, thereby ensuring that the collected obstacle information is updated in a rolling manner, thereby ensuring the real-time nature of obstacle processing.
[0068] Optionally, a plurality of historical frame contour points in the embodiment of the present application conform to a normal distribution, and the embodiment of the present application can obtain a mean μ and a standard deviation σ of the historical frame contour points by calculation.
[0069] Specifically, the embodiment of the present application generates a preset obstacle information table, i.e., the obstacle information statistical array in the above embodiment, according to multiple historical frame types, multiple historical frame speeds, multiple historical frame positions, and multiple historical frame contour points. The embodiment of the present application updates the preset obstacle information table by processing and analyzing the target obstacle.
[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, and 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, and the information of the target obstacle in the preset obstacle information table is cleared.
[0071] In some cases, if the target obstacle is a stationary obstacle, it is necessary to process and update the position and contour information of the target obstacle; in other cases, if the target obstacle suddenly moves, it is necessary to update the speed and direction information of the target obstacle and clear the current statistical array based on the target obstacle, that is, clear the information of the target obstacle in the preset obstacle information table.
[0072] The following examples will be given to specifically introduce the method and principle of processing obstacle data in this application.
[0073] Optionally, in some embodiments, a preset obstacle information table is updated based on the current frame contour point, including: 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, using the current frame contour point as the current frame position, otherwise, determining the average of multiple historical frame contour points, and using the average as the current frame position.
[0074] Among them, based on the above embodiments, the position distribution of the target obstacle in the first N frames of the embodiment of the present application conforms to the normal distribution, with a mean of μ and a standard deviation of σ. The preset confidence interval of the embodiment of the present application is μ±2σ.
[0075] It can be understood that if the historical frames (previous N frames) of the target obstacle are all in a stationary state, and the speed of the current frame (N+1 frame) is 0, the target obstacle is determined to be a stationary obstacle. The embodiment of the present application compares and analyzes the information of the previous N frames and the contour points of the current frame. In addition, the position distribution of the target obstacle in the previous N frames of the embodiment of the present application conforms to the normal distribution, and the contour points of the current frame generated can be compared. If the contour point of the current frame is in the distribution of μ±2σ, the data of the contour point of the current frame is considered to be credible, and then the contour point of the current frame 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, the embodiment of the present application can use radar or laser radar technology to detect the contour point P of the target obstacle in the N+1 frame (current frame) n+1 , P n+1 Compare with the statistics of the previous N frames. If P n+ 1 falls within the confidence interval centered on μ and 2σ wide (i.e., μ-2σ≤P n+1 ≤μ+2σ), then P n+1 It is credible.
[0077] Furthermore, if P n+1 is credible, then use P n+1 As the position information of the obstacle in frame N+1; if P n+1 If it is not in the distribution of μ±2σ, it is considered that there may be false detection or other interference, and the mean μ of the previous N frames is used as the obstacle position information of the N+1 frame.
[0078] Optionally, in some embodiments, after taking the current frame contour point as the current frame position, the method further includes: updating the average of multiple historical frame contour points according to the current frame position.
[0079] Specifically, if P is used n+1 As a new position, it can be added to the 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, the current frame position of the target obstacle is obtained according to the type and the current frame speed, including: if 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 according to the current frame speed and the current frame orientation; if the type is a second preset type, the current frame orientation angle of the target obstacle is obtained, and when the current frame speed is less than or equal to the second preset threshold and the current frame orientation angle is less than or equal to a third preset threshold, the current frame position is calculated according to a preset kinematic model.
[0081] It is understandable that if the target obstacle k (k is less than or equal to N) frames are in a stationary state, and the speed of the current frame (k+1 frame) is v0, but there is no predicted trajectory output, then the position of the target obstacle is updated at this time. In this case, since the target obstacle suddenly starts to move, its kinematic model parameters may need to be reinitialized. In the embodiment of the present application, the speed v0 can be used as the initial speed of the target obstacle.
[0082] In some cases, when the target obstacle is of the first preset type, i.e., a pedestrian obstacle, a small animal obstacle, etc., the embodiment of the present application sets a maximum speed constraint for the first preset type, i.e., the first preset threshold of the embodiment of the present application. The maximum speed constraint v pmax ≤5m / s, when the current frame speed is less than or equal to the maximum speed constraint v pmax In this case, the current frame speed and the current frame heading can be used n+1 To 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, that is, a vehicle obstacle, etc., the embodiment of the present application sets a speed constraint v for the second preset type. cmax , i.e., the second preset threshold of the embodiment of the present application. The embodiment of the present application sets the orientation angle constraint θ for the second preset type. max , i.e., the third preset threshold of the embodiment of the present application, when the current frame orientation angle θ0 of the target obstacle is less than or equal to the orientation angle constraint θ max , and the current frame speed (which can be used as the initial speed at this time) is less than or equal to the speed constraint v cmax In the case of , the position of the vehicle obstacle needs to 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 is the current frame horizontal coordinate of the target obstacle, Y K+1 is the current frame ordinate of the target obstacle, X n is the historical frame horizontal coordinate of the target obstacle, Y n is the historical frame ordinate of the target obstacle, v0 is the current frame speed of the target obstacle, θ n+1is the current frame orientation angle of the target obstacle.
[0087] It should be noted that the obstacle information processing method of the embodiment of the present application can filter Figure 5 The wrong position input shown, such as Figure 5 As shown in the figure, the dotted line is the updated position of the upstream input in the N+1 frame (current frame), and the solid line is the statistical position of the obstacle in the previous N frames (historical frames). Due to the angle constraint, the dotted line position information is invalid information. Similarly, the position of pedestrian obstacles can also be judged based on the speed and the time interval between two frames.
[0088] In order to enable those skilled in the art to further understand the obstacle information processing method of the embodiment of the present application, the following examples are listed to schematically illustrate the processing flow of the obstacle information processing method.
[0089] Specifically, Figure 6 This is a schematic diagram of a processing data flow of an obstacle information processing method according to a specific embodiment of the present application, such as Figure 6 As shown, the embodiment of the present application obtains the obstacle type, speed, trajectory and contour information of the N+1 frame (current frame); based on the obstacle kinematic constraint processor, the obstacle information of the N+1 frame 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 the N+1 frame obstacle after processing is obtained.
[0090] In some embodiments, Figure 7 This is a flowchart of an obstacle information processing method according to a specific embodiment of the present application. Figure 7 As shown, the obstacle information processing method of the embodiment of the present application includes the following steps:
[0091] Step S701, obtaining the obstacle information array of the current frame, that is, the type, speed, trajectory and contour information of the target obstacle;
[0092] Step S702, determining whether the obstacle is stationary in the current frame, if the obstacle is stationary in the current frame, executing step S703, otherwise, executing step S706;
[0093] Step S703, judging the position validity based on the type of obstacle and the statistical values of the previous N frames (historical frames);
[0094] Step S704, determining whether the location information is valid, if the location information is valid, executing step S705, otherwise, executing step S708;
[0095] Step S705, adding the obstacle to the static obstacle information and performing statistical collection (N frames);
[0096] Step S706, judging the validity of the current frame position sequence based on the type of obstacle and the previous frame speed sequence;
[0097] Step S707: No obstacle information is counted, and the queue storing obstacles is cleared;
[0098] Step S708, updating the obstacle information based on the mean μ of the current statistical value, and executing step S705.
[0099] Therefore, the embodiment of the present application performs kinematic modeling on the stationary obstacle, and based on the storage and statistics of the collected information of the previous N frames (historical frames) of the obstacle, filters and updates the obstacle information input by the N+1 frame (current input frame) based on the type of obstacle by kinematic model calculation.
[0100] According to the obstacle information processing method proposed in the embodiment of the present application, by obtaining the current frame speed, multiple historical frame states and types of the target obstacle, and when multiple historical frame states are all static and the current frame speed is a preset value, the target obstacle is determined to be a static obstacle, and the current frame contour points of the target obstacle are collected, and the preset obstacle information table is updated based on the current frame contour points. Otherwise, the target obstacle is determined to be a non-static obstacle, and the current frame position of the target obstacle is obtained according to the type and current frame speed, and the information of the target obstacle in the preset obstacle information table is cleared. Thus, the problem of incorrect or inaccurate planning results during trajectory planning due to inaccurate upstream input obstacle contour information is solved, which leads to discontinuous self-vehicle path planning or large planning jumps, and greatly improves the user's driving experience.
[0101] Next, the obstacle information processing device proposed according to the embodiment of the present application is described with reference to the accompanying drawings.
[0102] Figure 8 It is a block diagram of an obstacle information processing device according to an embodiment of the present 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 static states; 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 static states; the processing module 300 is used to determine that the target obstacle is a static obstacle when the current frame speed is a preset value, and 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, determine that the target obstacle is a non-static obstacle, and obtain the current frame position of the target obstacle according to the type and the current frame speed, and clear 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 used to: acquire multiple historical frame types, multiple historical frame speeds, multiple historical frame positions and multiple historical frame contour points of the preset obstacles, wherein the multiple historical frame contour points conform to a preset distribution; and generate a preset obstacle information table according to 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 confidence interval; if the current frame contour point is within the preset confidence 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 according to 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 the second preset threshold and the current frame orientation angle is less than or equal to a third preset threshold, calculate the current frame position according to 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 mean value of multiple historical frame contour points according to the current frame position.
[0109] It should be noted that the above explanations of the obstacle information processing method embodiment are also applicable to the obstacle information processing device of this embodiment, and will not be repeated here.
[0110] According to the obstacle information processing device proposed in the embodiment of the present application, by obtaining the current frame speed, multiple historical frame states and types of the target obstacle, and when the multiple historical frame states are all static and the current frame speed is a preset value, the target obstacle is determined to be a static obstacle, and the current frame contour points of the target obstacle are collected, and the preset obstacle information table is updated based on the current frame contour points. Otherwise, the target obstacle is determined to be a non-static obstacle, and the current frame position of the target obstacle is obtained according to the type and current frame speed, and the information of the target obstacle in the preset obstacle information table is cleared. In this way, the problem of incorrect or inaccurate planning results during trajectory planning due to inaccurate upstream input obstacle contour information is solved, which leads to discontinuous path planning or large planning jumps of the self-vehicle, and greatly improves the user's driving experience.
[0111] Fig. 9 A schematic diagram of the structure of a vehicle provided in an embodiment of the present application. The vehicle may include:
[0112] A memory 901 , a processor 902 , and a computer program stored in the memory 901 and executable on the processor 902 .
[0113] When the processor 902 executes the program, the obstacle information processing method provided in the above embodiment is implemented.
[0114] Furthermore, the vehicle also includes:
[0115] The communication interface 903 is used for communication between the memory 901 and the processor 902 .
[0116] The memory 901 is used to store computer programs that can be executed on the processor 902 .
[0117] The memory 901 may include a high-speed RAM (Random Access Memory) memory, and may also include a non-volatile memory, such as at least one disk memory.
[0118] If the memory 901, the processor 902 and the communication interface 903 are implemented independently, the communication interface 903, the memory 901 and the processor 902 can be connected to each other through a bus and communicate with each other. 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 an address bus, a data bus, a control bus, etc. For ease of representation, Fig. 9 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0119] Optionally, in a specific implementation, if the memory 901, the processor 902 and the communication interface 903 are integrated on a chip, the memory 901, the processor 902 and the communication interface 903 can communicate with each other through an internal interface.
[0120] The processor 902 may be a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.
[0121] The embodiment of the present application also provides a computer program product, on which a computer program is stored, and when the program is executed, the above obstacle information processing method is implemented.
[0122] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms are not necessarily directed to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.
[0123] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.
[0124] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.
[0125] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one or a combination of multiple of the following technologies known in the art: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array, a field programmable gate array, etc.
[0126] A person skilled in the art may understand that all or part of the steps in the above-mentioned embodiment method may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.
[0127] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.
Claims
1. An obstacle information processing method, characterized in that: The following steps are involved: Obtaining the current frame speed, multiple historical frame states and types of the target obstacle, and determining whether the multiple historical frame states are all static; If the multiple historical frame states are all the static state, determining whether the current frame speed is a preset value; 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, and 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 the type and the current frame speed, and the information of the target obstacle in the preset obstacle information table is cleared.
2. The method according to claim 1, characterized in that: Before updating the preset obstacle information table based on the current frame contour point, the method further includes: 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; The preset obstacle information table is generated according to the multiple historical frame types, the multiple historical frame speeds, the multiple historical frame positions and the multiple historical frame contour points.
3. The method according to claim 2, characterized in that The updating of the preset obstacle information table based on the current frame contour points includes: Determine whether the current frame contour point is within a preset confidence interval; If the current frame contour point is within the preset confidence interval, the current frame contour point is used as the current frame position; otherwise, the average of the multiple historical frame contour points is determined and the average is used as the current frame position.
4. The method according to claim 1, characterized in that: Obtaining the current frame position of the target obstacle according to the type and the current frame speed includes: If the type is the first preset type, obtaining the current frame orientation 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 orientation; If the type is the second preset type, the current frame orientation angle of the target obstacle is obtained, and when the current frame speed 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 a preset kinematic model.
5. The method according to claim 3, characterized in that: After taking the current frame contour point as the current frame position, the method further comprises: The mean values of the plurality of historical frame contour points are updated according to the current frame position.
6. An obstacle information processing device, characterized in that: include: An acquisition module, 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 static; A judging module, configured to judge whether the current frame speed is a preset value when the states of the plurality of historical frames are all the static state; a processing module, configured to, when the current frame speed is the preset value, determine that the target obstacle is a stationary obstacle, collect current frame contour points of the target obstacle, and update a preset obstacle information table based on the current frame contour points; otherwise, determine that the target obstacle is a non-stationary obstacle, 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.
7. The device according to claim 6, characterized in that Before updating the preset obstacle information table based on the current frame contour points, the acquisition module is further used 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; The preset obstacle information table is generated according to the multiple historical frame types, the multiple historical frame speeds, the multiple historical frame positions and the multiple historical frame contour points.
8. The device according to claim 7, characterized in that The processing module is specifically used for: Determine whether the current frame contour point is within a preset confidence interval; When the current frame contour point is within the preset confidence interval, the current frame contour point is used as the current frame position; otherwise, the average of the multiple historical frame contour points is determined and the average is used as the current frame position.
9. A vehicle, characterized in that: include: 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 according to any one of claims 1 to 5.
10. A computer program product, comprising a computer program, characterized in that The computer program is executed to implement the obstacle information processing method according to any one of claims 1 to 5.
Citation Information
Patent Citations
Determination method and device of barrier contour, vehicle, and storage medium
CN110514163A
Obstacle detection method and device
CN110691990A
Obstacle sensing method, storage medium and electronic equipment
CN112257542A
Obstacle speed fusion method and device based on multiple sensors
CN112285714A
Target tracking method and device, electronic equipment and storage medium
CN114170274A
