Conical barrel visualization method and device based on grid map

Abstract

The application relates to a cone-shaped barrel visualization method and device based on a grid map, wherein the method comprises the following steps: identifying target information of a target, and constructing lane information according to environment information of a current environment; expanding according to a global path of a vehicle and a local path generated by the target information and the environment information, generating a grid map based on a driving track obtained, filtering grids in a cone-shaped barrel obstacle occupation state determined based on the length and width of the vehicle, and screening out a grid area occupied by the cone-shaped barrel target; detecting a driving working condition of the vehicle, calculating a driving boundary according to the driving working condition, predicting a collision distance of the vehicle, determining a cone-shaped barrel target with a collision risk, and then generating visualization information. The application embodiment can detect the collision distance of the potential collision target in combination with the driving working condition of the vehicle, and display the cone-shaped barrel target with the collision risk, so that the visual aid is provided, and the driving safety of the vehicle is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving safety collision, in particular to a cone-shaped bucket visualization method and device based on a grid map. BACKGROUND

[0002] Converting environment map information into a grid map and planning a vehicle obstacle avoidance path according to the grid occupancy distribution is a mainstream method for analyzing obstacles of a vehicle to control the vehicle to avoid obstacles and perform automatic driving.

[0003] For an automatic driving vehicle, an algorithm in the related art is designed for a structured road, where the structured road refers to a city road or a highway, which is a road with clear boundaries and lane lines. The structured road itself is regarded as a drivable area, and the left and right boundaries are defined by lane boundaries. The recognized obstacles are mainly used to limit the drivable distance in front of the lane and adjust the left and right boundaries of the lane.

[0004] However, the related art is strongly dependent on the lane environment and is not suitable for a parking environment without a lane. The parking lot environment is complex, there is a risk of weak or even missing map signals, and there are large differences in light irradiation, many obstructions, poor visibility, small volume and low height of the cone-shaped bucket, which are not easy to identify through visual observation of the user and are easy to be in a driving blind area, thereby causing the vehicle to collide with the cone-shaped bucket when parking and further causing traffic accidents to occur, which needs to be improved. SUMMARY

[0005] The present application provides a cone-shaped bucket visualization method and device based on a grid map to solve the technical problem that the grid map in the related art is strongly dependent on the lane environment and is not suitable for a parking scenario with small obstacles such as a cone-shaped bucket.

[0006] The first aspect embodiment of the present application provides a cone-shaped bucket visualization method based on a grid map, including the following steps: identifying target information of a target and constructing lane information according to environment information of a current environment; expanding a global path of a vehicle and a local path generated from the target information and the environment information, generating a grid map based on a driving trajectory obtained, filtering a grid in a cone-shaped bucket obstacle occupancy state based on a length and a width of the vehicle, and screening a grid area occupied by the cone-shaped bucket target; detecting a driving condition of the vehicle, calculating a driving boundary according to the driving condition, predicting a collision distance of the vehicle, determining a cone-shaped bucket target with a collision risk, and obtaining visualization information according to the cone-shaped bucket target with the collision risk, the grid area occupied by the cone-shaped bucket target, and the lane information.

[0007] According to the technical means, the embodiment of the present application can combine the driving condition of the vehicle with the detection of the collision distance of the potential collision target, display the cone-shaped bucket target with the collision risk, provide the visual field assistance, reduce the influence of the environment on the grid map, and thus increase the safety of the driving of the vehicle.

[0008] Optionally, in an embodiment of the present application, the calculation of the driving boundary according to the driving condition comprises: calculating a first turning radius, a second turning radius and a minimum turning radius under the driving condition; and planning the driving boundary according to the first turning radius, the second turning radius and the minimum turning radius.

[0009] According to the technical means, the embodiment of the present application can calculate the boundary, predict the collision distance of the vehicle and the obstacle, and confirm the collision risk.

[0010] Optionally, in an embodiment of the present application, the prediction of the collision distance of the vehicle comprises: regarding the cone-shaped bucket target within the range of the driving boundary as the cone-shaped bucket obstacle with the collision risk, taking the instantaneous turning center of the vehicle as the center of a circle, taking the distance from the instantaneous turning center to the nearest grid center point in the cone-shaped bucket obstacle occupancy state as the radius of the circle, and taking the track arc length obtained by the intersection of the driving track and the driving boundary as the collision distance.

[0011] According to the technical means, the embodiment of the present application can calculate the collision distance of the cone-shaped bucket target within the range of the driving boundary, and thus facilitate the reminding of the cone-shaped bucket with the collision risk.

[0012] Optionally, in an embodiment of the present application, the obtaining of the visual information according to the cone-shaped bucket target with the collision risk, the grid area occupied by the cone-shaped bucket target and the lane information comprises: generating visual feedback information according to the cone-shaped bucket target with the collision risk, the grid area occupied by the cone-shaped bucket target and the lane information; and / or generating auditory feedback information according to the cone-shaped bucket target with the collision risk, the grid area occupied by the cone-shaped bucket target and the lane information; and / or generating tactile feedback information according to the cone-shaped bucket target with the collision risk, the grid area occupied by the cone-shaped bucket target and the lane information; and controlling the vehicle to perform a corresponding feedback action on the user based on the visual feedback information, the auditory feedback information and / or the tactile feedback information.

[0013] According to the technical means, the embodiment of the present application can provide the information feedback based on the visual feedback information, the auditory feedback information and / or the tactile feedback information, so as to ensure that the user can receive the feedback information.

[0014] Optionally, in an embodiment of the present application, the controlling the vehicle to perform a corresponding feedback action according to the visual feedback information, the audible feedback information and / or the tactile feedback information comprises: displaying the cone-shaped bucket target according to the collision risk, and dividing the target into regions according to the grid occupied by the cone-shaped bucket target, and displaying the regions on the center control screen; and / or, voice broadcasting whether there is the cone-shaped bucket target in front, the number of the cone-shaped bucket target and the collision distance; and / or, when the distance between the cone-shaped bucket and the vehicle is less than a preset distance, controlling the vehicle to vibrate at a preset frequency for reminding.

[0015] According to the above technical means, the embodiments of the present application can realize distance reminding of the cone-shaped bucket through visual, audible and / or tactile methods.

[0016] The second aspect of the present application provides a cone-shaped bucket visualization device based on a grid map, comprising: a construction module configured to identify target information of a target, and construct lane information according to environmental information of a current environment; a generation module configured to extend a global path of a vehicle and a local path generated from the target information and the environmental information, generate a grid map based on a driving track obtained, and filter grids in a cone-shaped bucket obstacle occupancy state based on a length and a width of the vehicle, and screen a grid region occupied by a cone-shaped bucket target; and a visualization module configured to detect a driving condition of the vehicle, calculate a driving boundary according to the driving condition, predict a collision distance of the vehicle, determine a cone-shaped bucket target with a collision risk, and obtain visualization information according to the cone-shaped bucket target with the collision risk, the grid region occupied by the cone-shaped bucket target and the lane information.

[0017] Optionally, in an embodiment of the present application, the visualization module comprises: a calculation unit configured to calculate a first turning radius, a second turning radius and a minimum turning radius in the driving condition; and a planning unit configured to plan the driving boundary according to the first turning radius, the second turning radius and the minimum turning radius.

[0018] Optionally, in an embodiment of the present application, the visualization module comprises: a prediction unit configured to regard a cone-shaped bucket target within the range of the driving boundary as a cone-shaped bucket obstacle with a collision risk, take an instantaneous turning center of the vehicle as a center, take a distance from the instantaneous turning center to a nearest grid center point in a cone-shaped bucket obstacle occupancy state as a radius, and take a track arc length obtained by intersecting the driving track and the driving boundary as the collision distance.

[0019] Optionally, in an embodiment of the present application, the visualization module comprises: a first generation unit configured to generate visual feedback information according to the cone-shaped bucket target with collision risk, the grid area occupied by the cone-shaped bucket target and the lane information; and / or a second generation unit configured to generate audible feedback information according to the cone-shaped bucket target with collision risk, the grid area occupied by the cone-shaped bucket target and the lane information; and / or a third generation unit configured to generate tactile feedback information according to the cone-shaped bucket target with collision risk, the grid area occupied by the cone-shaped bucket target and the lane information; and a control unit configured to control the vehicle to perform corresponding feedback actions on the user based on the visual feedback information, the audible feedback information and / or the tactile feedback information.

[0020] Optionally, in an embodiment of the present application, the control unit comprises: a display subunit configured to display the cone-shaped bucket target according to collision risk, divide the target into areas according to the grid area occupied by the cone-shaped bucket target, and display the target on a center control screen; and / or a first reminding subunit configured to voice broadcast whether the cone-shaped bucket target exists in front of the vehicle, the number of the cone-shaped bucket target and the collision distance; and / or a second reminding subunit configured to control the vehicle to perform a shaking reminder at a preset frequency when the distance between the cone-shaped bucket and the vehicle is less than a preset distance.

[0021] The third aspect of the embodiments 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 cone-shaped bucket visualization method based on a grid map as described in the above embodiments.

[0022] The fourth aspect of the embodiments of the present application provides a computer readable storage medium, which stores a computer program executable by a processor to implement the cone-shaped bucket visualization method based on a grid map as described above.

[0023] The beneficial effects of the embodiments of the present application are as follows:

[0024] (1) The embodiments of the present application can combine the driving conditions of the vehicle and detect the collision distance of the potential collision target, and provide visual field assistance by displaying the cone-shaped bucket target with collision risk, reduce the influence of the environment on the grid map, and thus increase the safety of the vehicle driving.

[0025] (2) The embodiments of the present application can realize the prompt warning of the distance, collision risk, etc. of the cone-shaped bucket based on visual, audible and / or tactile methods, so as to ensure that the user can accurately obtain the obstacle information.

[0026] Additional aspects and advantages of the application will be set forth in part in the description which follows, and in part will become apparent to those skilled in the art upon examination of the following and the attached drawings. BRIEF DESCRIPTION OF DRAWINGS

[0027] The above and / or additional aspects and advantages of the application will become apparent and be well understood from a review of the description of an embodiment, taken in conjunction with the drawings.

[0028] Figure 1 A flow chart of a method for cone visualization based on a grid map according to an embodiment of the application;

[0029] Figure 2 A driving boundary diagram of a driving condition of a front right side of a vehicle for a method for cone visualization based on a grid map according to an embodiment of the application;

[0030] Figure 3 A model diagram of a vehicle for a method for cone visualization based on a grid map according to an embodiment of the application;

[0031] Figure 4 A principle diagram of a method for cone visualization based on a grid map according to an embodiment of the application;

[0032] Figure 5 A structure diagram of a device for cone visualization based on a grid map according to an embodiment of the application;

[0033] Figure 6 A structure diagram of a vehicle according to an embodiment of the application.

[0034] Wherein, 10 - a device for cone visualization based on a grid map; 100 - a constructing module, 200 - a generating module, 300 - a visualizing module. DETAILED DESCRIPTION

[0035] Embodiments of the application are described in detail below with reference to the attached drawing figures, wherein the same or like elements in the figures are denoted with the same or like reference numerals, and the implementation can be implemented as a hardware, software, firmware, or combination thereof. The embodiments of the application described below are exemplary and are intended to provide an example of the application, and are not to be understood as limiting the application.

[0036] A cone visualization method and device based on a grid map are described below with reference to the accompanying drawings. In view of the technical problems in the related art that the grid map is strongly dependent on the lane environment and is not suitable for parking scenarios with small obstacles such as cones, the present application provides a cone visualization method based on a grid map. In the method, lane information can be constructed according to environmental information of the current environment, and a grid map can be generated by extending a global path of a vehicle and a local path generated from target information and environmental information. The grid regions occupied by the cone targets are filtered out, and the driving boundary is calculated according to the driving conditions. The collision distance of the vehicle is predicted, and the cone targets with collision risks are determined. The visualization information is obtained according to the cone targets with collision risks, the grid regions occupied by the cone targets, and the lane information. The collision distance of the potential collision targets is detected in combination with the driving conditions of the vehicle. The cone targets with collision risks are displayed to provide visual assistance and reduce the impact of the environment on the grid map, thereby ensuring the driving safety of the vehicle. Thus, the technical problem in the related art that the grid map is strongly dependent on the lane environment and is not suitable for parking scenarios with small obstacles such as cones is solved.

[0037] Specifically, Figure 1 A flowchart of a cone visualization method based on a grid map provided by the present application is shown in the figure.

[0038] As Figure 1 shown, the cone visualization method based on a grid map includes the following steps:

[0039] In step S101, the target information of the target is identified, and the lane information is constructed according to the environmental information of the current environment.

[0040] In actual execution, the present application can fuse and preprocess the collection information of collection devices such as radars and cameras based on sensors, identify the target information such as the type, motion state, and relative position of the target, and identify and filter the environmental information such as lane lines and road boundaries (walls, guardrails, etc.), thereby constructing the lane information.

[0041] The target type information in the target information can be fused and processed based on devices such as corner radars, ultrasonic radars, forward-looking cameras, surround-view cameras, and omnidirectional cameras, and each target obtained by perception fusion is assigned a unique target ID (Identity document, identity number). Thus, the identified target type is classified as a pedestrian target, a vehicle target, a cone target, and other obstacle targets, and the index of the cone target closest to the vehicle position is output.

[0042] The motion state information in the target information can be used by the embodiments of the present application to determine whether a target is a moving target or a stationary target according to the position change of the target in a plurality of continuous signal periods, and the cone-shaped barrel target and other obstacle targets are defined as stationary targets.

[0043] The relative position information in the target information can be processed by the embodiments of the present application as a coordinate in a vehicle coordinate system, and the target relative position obtained through fusion processing is output.

[0044] Specifically, the embodiments of the present application can perform Kalman filtering on the received sensing signals to obtain a lane line equation, wherein the lane line equation is a cubic equation, the characteristic coefficients are [A0-A3], and the coordinate system is a vehicle coordinate system. The embodiments of the present application can define the left and right lane lines as a left lane line and a right lane line according to the characteristic coefficients [A0-A3] of the lane line equation, determine and output the effective marks of the lane lines.

[0045] The embodiments of the present application can fill in the missing lane lines:

[0046] 1) When the left lane line is effective and the right lane line is invalid, a half lane width is extended from the left lane line to the right to obtain a right lane line equation;

[0047] 2) When the left lane line is invalid and the right lane line is effective, a half lane width is extended from the right lane line to the left to obtain a left lane line equation;

[0048] 3) When the left lane line is invalid and the right lane line is invalid, a half lane width is extended to the left and right respectively with the “vehicle expected driving path” as the center line to obtain a left and right lane line equation.

[0049] The embodiments of the present application can define the lane line ID according to the position relationship, wherein the lane line ID increases from left to right, and the minimum value is 0. The area between two lane lines with adjacent lane line numbers is defined as a lane, and the lane where the vehicle is located is defined as a vehicle lane, and the left lane and the right lane are defined in the same way.

[0050] In step S102, the global path of the vehicle and the local path generated from the target information and the environment information are expanded, a grid map is generated based on the obtained driving trajectory, and the grids in the cone-shaped barrel obstacle state are determined based on the length and width of the vehicle, and the grid area occupied by the cone-shaped barrel target is screened out.

[0051] As a possible implementation manner, the embodiment of the application can expand the M*N grid map to left and right on the basis of the global path of the vehicle and the local path generated by the target information and the environment information, cover a certain length and width range in front and back of the center of the rear axle of the vehicle, and perform ranging by, for example, an ultrasonic radar sensor, filter the grid in the state of being occupied by the cone-shaped barrel obstacle according to the length and width of the target, and screen the grid area occupied by the cone-shaped barrel target according to the information collected by the camera.

[0052] It should be noted that the certain length and width range in front and back of the center of the rear axle of the vehicle can be set by a person skilled in the art according to actual conditions, and is not specifically limited here.

[0053] Specifically, the embodiment of the application can expand the M*N grid map to left and right on the basis of the global path of the vehicle, cover a certain length and width range in front and back of the center of the rear axle of the vehicle, and calculate the xy coordinates of the grid frame point [m][n] (0≤n≤N, 0≤m≤M).

[0054] The embodiment of the application can filter the grid map based on the radar signal and the ultrasonic signal, for example, Freespace filter the moving target, mark the grid points in the area outside the Freespace frame point as occupied; according to the end point information of the two ends of the ultrasonic cluster signal, perform cluster filtering on the static target, and mark the grid points [m][n] of the grid occupied by the cluster as occupied.

[0055] The embodiment of the application can determine the grid area occupied by the cone-shaped barrel target according to the coordinates of the occupied grid points and the relative position of the target.

[0056] In step S103, the driving condition of the vehicle is detected, the driving boundary is calculated according to the driving condition, the collision distance of the vehicle is predicted, the cone-shaped barrel target with collision risk is determined, and the visualization information is obtained according to the cone-shaped barrel target with collision risk, the grid area occupied by the cone-shaped barrel target, and the lane information.

[0057] In some embodiments, the embodiment of the application can obtain the parameters of the vehicle such as gear, wheelbase, steering wheel angle, etc. based on the vehicle controller, calculate and plan the driving boundary according to the driving condition such as straight driving, reversing, front left turning, front right turning, etc., and take the cone-shaped barrel target within the planned driving boundary as the cone-shaped barrel target with collision risk, so as to perform visualization processing on the cone-shaped barrel target according to the cone-shaped barrel target with collision risk, the grid area occupied by the cone-shaped barrel target, and the lane information.

[0058] The determination of the driving condition can be as follows:

[0059] When the vehicle gear is D, the steering wheel angle is greater than a certain positive angle / less than a certain negative angle, and the working condition is front right turn / front left turn working condition;

[0060] When the vehicle gear is D, the steering wheel angle is greater than a certain negative angle and less than a certain positive angle, and the working condition is straight ahead working condition;

[0061] When the vehicle gear is R, the steering wheel angle is greater than a certain positive angle / less than a certain negative angle, and the working condition is rear right turn / rear left turn working condition;

[0062] When the vehicle gear is R, the steering wheel angle is greater than a certain negative angle and less than a certain positive angle, and the working condition is reverse working condition.

[0063] Optionally, in an embodiment of the present application, the driving boundary is calculated according to the driving working condition, comprising: calculating a first turning radius, a second turning radius and a minimum turning radius in the driving working condition; and planning the driving boundary according to the first turning radius, the second turning radius and the minimum turning radius.

[0064] For example, as shown in FIG. 1, when the driving working condition of the vehicle is determined to be front right turn, the driving boundary of the embodiment of the present application can be the area delimited by the first turning radius and the minimum turning radius (or the area expanded on the basis of the first turning radius and the minimum turning radius); Figure 2 When the driving working condition of the vehicle is determined to be rear right turn, the driving boundary is the area delimited by the second turning radius and the minimum turning radius (or the area expanded on the basis of the second turning radius and the minimum turning radius);

[0065] The boundary processing logic of the unillustrated front left turn working condition is the same as that of the front right turn working condition, and the boundary processing logic of the rear left turn working condition is the same as that of the rear right turn working condition

[0066] When the determined driving working condition of the vehicle is straight ahead / reverse, the first, second and minimum turning radii can be regarded as infinite.

[0067] Optionally, in an embodiment of the present application, the collision distance of the vehicle is predicted, comprising: regarding the cone-shaped bucket target within the range of the driving boundary as a cone-shaped bucket obstacle with collision risk, taking the instantaneous turning center of the vehicle as the center of a circle, taking the distance from the instantaneous turning center to the nearest grid center point in the cone-shaped bucket obstacle occupancy state as the radius, and taking the track arc length obtained by the intersection of the driving track and the driving boundary as the collision distance.

[0068]

[0069] ​In actual implementation, the application embodiment can take the grid region occupied by the cone-shaped bucket target in the driving boundary corresponding to the current working condition of the vehicle as the center, take the distance from the instantaneous steering center of the vehicle to the nearest grid point as the radius, and take the arc length of the trajectory obtained by intersecting the drawn trajectory with the collision boundary as the predicted collision distance.

[0070] In the application embodiment, the collision boundary corresponding to the driving condition of the vehicle can be determined based on the driving condition of the vehicle, for example, as shown in the following table. Figure 3 As shown in the table, the vehicle model can be abstracted as an 8-side closed figure (or other polygon approximating the vehicle contour boundary), and the specific parameters of the figure can be calibrated according to the parameters of the ego vehicle.

[0071] When the determined driving condition of the vehicle is straight driving, the collision boundary can be composed of line segment 34, line segment 45, and line segment 56.

[0072] When the determined driving condition of the vehicle is front-right turning, the collision boundary can be composed of line segment 34, line segment 45, line segment 56, and line segment 23.

[0073] Similarly, similar processing is performed on other mentioned conditions.

[0074] When the determined driving condition of the vehicle is front-left turning, the collision boundary can be composed of line segment 34, line segment 45, line segment 56, and line segment 67.

[0075] When the determined driving condition of the vehicle is reverse driving, the collision boundary can be composed of line segment 78, line segment 81, and line segment 12.

[0076] When the determined driving condition of the vehicle is rear-right turning, the collision boundary can be composed of line segment 78, line segment 81, line segment 12, and line segment 23.

[0077] When the determined driving condition of the vehicle is rear-left turning, the collision boundary can be composed of line segment 78, line segment 81, line segment 12, and line segment 67.

[0078] Optionally, in an embodiment of the application, the visual information obtained according to the cone-shaped bucket target with a collision risk, the grid region occupied by the cone-shaped bucket target, and the lane information includes: generating visual feedback information according to the cone-shaped bucket target with a collision risk, the grid region occupied by the cone-shaped bucket target, and the lane information; and / or generating auditory feedback information according to the cone-shaped bucket target with a collision risk, the grid region occupied by the cone-shaped bucket target, and the lane information; and / or generating tactile feedback information according to the cone-shaped bucket target with a collision risk, the grid region occupied by the cone-shaped bucket target, and the lane information; and controlling the vehicle to perform a corresponding feedback action on the user based on the visual feedback information, the auditory feedback information, and / or the tactile feedback information.

[0079] As a possible implementation manner, the embodiment of the present application can perform visual processing on the cone-shaped barrel target according to the cone-shaped barrel target with collision risk, the grid occupied by the cone-shaped barrel target and the lane information, and feed back the cone-shaped barrel information through three feedback channels of vision, hearing and / or touch.

[0080] Optionally, in an embodiment of the present application, the vehicle is controlled to perform corresponding feedback actions on the user based on the visual feedback information, the hearing feedback information and / or the touch feedback information, including: displaying the cone-shaped barrel target according to the collision risk, and regionally dividing the target according to the grid occupied by the cone-shaped barrel target, and correspondingly displaying on the center control screen; and / or, voice broadcasting whether there is a cone-shaped barrel target in front, the number of cone-shaped barrel targets and the collision distance; and / or, when the distance between the vehicle and the cone-shaped barrel is less than a preset distance, controlling the vehicle to vibrate at a preset frequency for reminding.

[0081] For example, for the visual feedback information, the embodiment of the present application can display the cone-shaped barrel target according to whether there is a collision risk, such as high-light and gray display, and regionally divide the target according to the grid occupied by the cone-shaped barrel target, and correspondingly display on the center control screen;

[0082] For the hearing feedback information, the embodiment of the present application can prompt the user through voice broadcasting whether there is a cone-shaped barrel target in front, the number of cone-shaped barrel targets, the collision distance;

[0083] For the touch feedback information, the embodiment of the present application can make the steering wheel and the seat vibrate at a certain frequency when the cone-shaped barrel distance approaches the set limit collision distance, to strongly remind the user, wherein the set limit collision distance can be set by the person skilled in the art according to the actual situation, which is not limited here.

[0084] In summary, the embodiment of the present application can plan a grid map based on target information and lane information, and detect the collision distance of the potential collision target combined with the driving conditions of the vehicle, so as to determine whether there is a collision cone-shaped barrel target in the path, which can improve the accuracy and efficiency of small-volume obstacle analysis on the path, and display the cone-shaped barrel target with collision risk in real time, and improve the accuracy of the driver's obstacle avoidance operation on small-volume obstacles in the limited space of the road environment.

[0085] In combination Figures 2 to 4 In an embodiment, the working principle of the cone-shaped barrel visualization method based on the grid map of the embodiment of the present application is described in detail.

[0086] For example Figure 4As shown, the embodiments of the present application can include an environmental signal processing module, a grid map planning module, a collision prediction module, and an HMI (Human Machine Interface) module display module.

[0087] The environmental signal processing module can identify the type, motion state, and relative position of a target after target fusion preprocessing of radar and camera signals by the sensor signal input module, and identify and filter process environmental information such as lane lines and road boundaries (walls, guardrails, etc.), and construct lane information.

[0088] The grid map planning module, the vehicle expected driving trajectory includes a global path planned by the intelligent driving system and a local path planned based on the surrounding environment and target information, and the embodiments of the present application can expand the grid map by MxN to the left and right on the basis of the vehicle expected driving trajectory, cover a certain length and width range in front and behind the center of the rear axle of the vehicle, filter the grid occupied by the cone-shaped barrel obstacle according to the length and width of the target through ultrasonic and radar sensing ranging, and screen out the grid area occupied by the cone-shaped barrel target according to the camera sensing signal.

[0089] The collision prediction module can calculate the first, second, and minimum steering radii under the corresponding driving conditions (straight driving, reversing, front left turning, front right turning, etc.) according to the vehicle parameters (gear, wheelbase, steering wheel angle, etc.) to plan the driving boundary, receive the signal from the environmental signal processing module, and regard the cone-shaped barrel target within the planned driving boundary range as a cone-shaped barrel target with a collision risk, take the instantaneous steering center of the vehicle as the center and the distance from the instantaneous steering center of the vehicle to the nearest grid center point in the cone-shaped barrel obstacle occupation state as the radius, and take the arc length of the trajectory obtained by the intersection of the drawn trajectory and the vehicle boundary as the predicted collision distance.

[0090] The HMI module display module can receive signals from the environmental signal processing module, the grid map planning module, and the collision prediction module, and process the cone-shaped barrel target visually according to the cone-shaped barrel target with a collision risk, the cone-shaped barrel target occupied grid, and the lane line signal, and feed back the cone-shaped barrel information through three feedback channels of vision, hearing, and touch.

[0091] The visual feedback channel can display the cone-shaped barrel target in highlight and grayscale according to whether there is a collision risk, divide the target into regions according to the grid occupied by the cone-shaped barrel target, and display on the center control screen.

[0092] The auditory feedback channel can prompt the user through voice whether there is a cone-shaped barrel target in front, the number of cone-shaped barrel targets, and the collision distance.

[0093] The haptic feedback channel can make the steering wheel and the chair shake at a certain frequency when the cone barrel distance approaches the set limit collision distance, thereby strongly reminding the user.

[0094] In actual implementation, the embodiment of the present application can include the following steps:

[0095] S1: The embodiment of the present application can fuse and preprocess the collection information of collection devices such as radars and cameras based on sensors, identify target information such as the type, motion state, and relative position of the target, and identify and filter the environmental information such as lane lines and road boundaries (walls, guardrails, etc.), thereby constructing lane information.

[0096] Specifically, the embodiment of the present application can perform Kalman filtering on the received sensing signals to obtain a lane line equation, wherein the lane line equation is a cubic equation, the characteristic coefficients are [A0-A3], and the coordinate system is a vehicle coordinate system. The embodiment of the present application can define the lane lines on the left and right sides as left and right lane lines according to the characteristic coefficients [A0-A3] of the lane line equation, judge and output the effective marks of the lane lines.

[0097] The embodiment of the present application can fill in the missing lane lines:

[0098] 1) When the left lane line is valid and the right lane line is invalid, a right lane line equation is obtained by extending half a lane width from the left lane line to the right;

[0099] 2) When the left lane line is invalid and the right lane line is valid, a left lane line equation is obtained by extending half a lane width from the right lane line to the left;

[0100] 3) When the left lane line is invalid and the right lane line is invalid, left and right lane line equations are obtained by extending half a lane width to the left and right respectively with the "vehicle expected driving path" as the center line.

[0101] The embodiment of the present application can define lane line IDs according to the position relationship, wherein the lane line IDs increase from left to right, the minimum value is 0, and the area between two lane lines with adjacent lane line numbers is defined as a lane. The lane in which the vehicle is located is defined as the vehicle lane, and the left and right lanes are defined in the same way.

[0102] S2: The embodiment of the present application can identify the type, motion state, relative position, size, etc. of the target after the target fusion preprocessing of the radar and camera signals by the sensor signal input module based on the target processing module.

[0103] The target type information in the target information can be based on target information fusion processing of devices such as corner radar, ultrasonic radar, forward-looking, surround-view, and surround-view cameras, and a unique target ID (Identity document) is assigned to each target obtained by perception fusion, so as to classify the recognized target type as a pedestrian target, a vehicle target, a cone-shaped bucket target, and other obstacle targets, and output the index of the cone-shaped bucket target closest to the vehicle position.

[0104] The motion state information in the target information can be determined by the embodiments of the present application for pedestrian targets and vehicle targets according to the position changes of the targets in a plurality of continuous signal periods, and the cone-shaped bucket target and the other obstacle target are defined as a stationary target.

[0105] The relative position information in the target information can be processed by the embodiments of the present application as coordinates in the vehicle coordinate system, and the relative position of the target obtained by fusion processing is output.

[0106] S3: Specifically, the embodiments of the present application can expand the grid map by MxN to the left and right on the basis of the expected driving trajectory of the vehicle, cover a certain length and width in front and behind the center of the rear axle of the vehicle, and calculate the xy coordinates of the grid border points [m][n] (0≤n≤N, 0≤m≤M).

[0107] The embodiments of the present application can filter the grid map based on radar signals and ultrasonic signals, for example, Freespace filtering is performed on the moving target, and the grid points in the area outside the Freespace border points are marked as occupied; according to the end point information of the ultrasonic cluster signal, the cluster filtering is performed on the static target, and the grid points [m][n] of the grid occupied by the cluster are marked as occupied.

[0108] The embodiments of the present application can determine the grid area occupied by the cone-shaped bucket target according to the occupied grid point coordinates and the target relative position.

[0109] S4: The determination of the driving condition can be as follows:

[0110] When the gear of the vehicle is D, the steering wheel angle is greater than a certain positive angle / less than a certain negative angle, and the condition is a front right turn / front left turn condition;

[0111] When the gear of the vehicle is D, the steering wheel angle is greater than a certain negative angle and less than a certain positive angle, and the condition is a straight driving condition;

[0112] When the gear of the vehicle is R, the steering wheel angle is greater than a certain positive angle / less than a certain negative angle, and the condition is a rear right turn / rear left turn condition;

[0113] When the vehicle gear is R, the steering wheel angle is greater than a certain negative angle and less than a certain positive angle, and the working condition is a reversing working condition.

[0114] The embodiment of the present application can plan the first, second, and minimum steering radii according to the vehicle wheelbase, axle width, steering wheel angle, steering transmission ratio, and the like, in combination with the current vehicle driving working condition, as shown in the following table. Figure 2 As shown in the table, when the driving working condition of the vehicle is determined to be front right turning, the driving boundary of the embodiment of the present application can be the area delineated by the first steering radius and the minimum steering radius (or the area expanded on the basis of the first steering radius and the minimum steering radius);

[0115] When the driving working condition of the vehicle is determined to be rear right turning, the driving boundary is the area delineated by the second steering radius and the minimum steering radius (or the area expanded on the basis of the second steering radius and the minimum steering radius);

[0116] The boundary processing logic of the unlisted front left turning working condition is the same as that of the front right turning working condition, and the boundary processing logic of the rear left turning working condition is the same as that of the rear right turning working condition.

[0117] When the determined driving working condition of the vehicle is straight driving / reversing, the first, second, and minimum steering radii can be considered to be infinite.

[0118] The embodiment of the present application can determine the collision boundary under the corresponding driving working condition on the basis of the driving working condition of the vehicle, as shown in the following table. Figure 3 As shown in the table, the vehicle model can be abstracted as an 8-side closed figure (or other polygons, approximating the vehicle contour boundary), and the specific parameters of the figure can be calibrated according to the parameters of the ego vehicle.

[0119] When the determined driving working condition of the vehicle is straight driving, the collision boundary can be composed of line segment 34, line segment 45, and line segment 56.

[0120] When the determined driving working condition of the vehicle is front right turning, the collision boundary can be composed of line segment 34, line segment 45, line segment 56, and line segment 23.

[0121] Similarly, other mentioned working conditions are processed in a similar manner.

[0122] When the determined driving working condition of the vehicle is front left turning, the collision boundary can be composed of line segment 34, line segment 45, line segment 56, and line segment 67.

[0123] When the determined driving working condition of the vehicle is reversing, the collision boundary can be composed of line segment 78, line segment 81, and line segment 12.

[0124] When the determined driving working condition of the vehicle is rear right turning, the collision boundary can be composed of line segment 78, line segment 81, line segment 12, and line segment 23.

[0125] When the determined driving condition of the vehicle is left rear turning, the collision boundary can be composed of line segment 78, line segment 81, line segment 12 and line segment 67.

[0126] In actual implementation, the application can take the grid region occupied by the cone-shaped bucket target in the driving boundary corresponding to the current condition of the vehicle as the center, take the distance from the instantaneous steering center of the vehicle to the nearest grid point as the radius, and take the arc length of the trajectory obtained by intersecting the drawn trajectory with the collision boundary as the predicted collision distance.

[0127] S5: visual feedback channel, the application can display the cone-shaped bucket target in different light effects such as highlighting and graying according to whether there is a collision risk, and divide the target into regions according to the grid region occupied by the cone-shaped bucket target, and display the regions on the central control screen accordingly.

[0128] Auditory feedback channel, the application can prompt the user through voice broadcast whether there is a cone-shaped bucket target in front, the number of cone-shaped bucket targets, and the collision distance.

[0129] Tactile feedback channel, the application can make the steering wheel and the table and chair vibrate at a certain frequency when the cone-shaped bucket distance approaches the set limit collision distance, thereby strongly reminding the user, wherein the set limit collision distance can be set by a person skilled in the art according to the actual situation, and is not limited specifically herein.

[0130] The cone-shaped bucket visualization method based on the grid map according to the application can construct lane information according to environmental information of the current environment, and expand the global path of the vehicle and the local path generated by the target information and the environmental information to generate a grid map, screen out the grid region occupied by the cone-shaped bucket target, calculate the driving boundary according to the driving condition, predict the collision distance of the vehicle, determine the cone-shaped bucket target with collision risk, and obtain the visualization information according to the cone-shaped bucket target with collision risk, the grid region occupied by the cone-shaped bucket target, and the lane information, realize the combination of the driving condition of the vehicle and the collision distance detection of the potential collision target, and provide visual aid by displaying the cone-shaped bucket target with collision risk, reduce the influence of the environment on the grid map, and thus ensure the driving safety of the vehicle. Thus, the technical problem that the grid map in the related art has strong dependence on the lane environment and is not suitable for parking scenes with small obstacles such as cone-shaped buckets is solved.

[0131] Secondly, the cone-shaped bucket visualization device based on the grid map according to the application is described with reference to the accompanying drawings.

[0132] Figure 5 is a block schematic diagram of the cone-shaped bucket visualization device based on the grid map according to the application.

[0133] As Figure 5 shown, the cone bucket visualization device 10 based on the grid map includes a construction module 100, a generation module 200 and a visualization module 300.

[0134] Specifically, the construction module 100 is configured to identify target information of a target, and construct lane information according to environment information of a current environment.

[0135] The generation module 200 is configured to extend a global path of a vehicle and a local path generated according to the target information and the environment information, generate a grid map based on a driving track obtained, filter grids in a cone bucket obstacle occupancy state based on a length and a width of the vehicle, and screen a grid area occupied by a cone bucket target.

[0136] The visualization module 300 is configured to detect a driving condition of the vehicle, calculate a driving boundary according to the driving condition, predict a collision distance of the vehicle, determine a cone bucket target with a collision risk, and obtain visualization information according to the cone bucket target with the collision risk, the grid area occupied by the cone bucket target and the lane information.

[0137] Optionally, in an embodiment of the present application, the visualization module 300 includes a calculation unit and a planning unit.

[0138] The calculation unit is configured to calculate a first turning radius, a second turning radius and a minimum turning radius in the driving condition.

[0139] The planning unit is configured to plan the driving boundary according to the first turning radius, the second turning radius and the minimum turning radius.

[0140] Optionally, in an embodiment of the present application, the visualization module 300 includes a prediction unit.

[0141] The prediction unit is configured to regard a cone bucket target within a range of the driving boundary as a cone bucket obstacle with the collision risk, take an instantaneous turning center of the vehicle as a center of a circle, take a distance from the instantaneous turning center to a nearest grid center point in the cone bucket obstacle occupancy state as a radius of the circle, and take a track arc length obtained by intersecting the driving track with the driving boundary as the collision distance.

[0142] Optionally, in an embodiment of the present application, the visualization module includes a first generation unit and / or a second generation unit and / or a third generation unit and a control unit.

[0143] The first generation unit is configured to generate visual feedback information according to the cone bucket target with the collision risk, the grid area occupied by the cone bucket target and the lane information.

[0144] The second generating unit is configured to generate auditory feedback information according to the cone-shaped bucket target with the collision risk, the grid area occupied by the cone-shaped bucket target, and the lane information.

[0145] The third generating unit is configured to generate tactile feedback information according to the cone-shaped bucket target with the collision risk, the grid area occupied by the cone-shaped bucket target, and the lane information.

[0146] The control unit is configured to control the vehicle to perform a corresponding feedback action on the user based on the visual feedback information, the auditory feedback information, and / or the tactile feedback information.

[0147] Optionally, in an embodiment of the present application, the control unit comprises a display subunit and / or a first reminding subunit and / or a second reminding subunit.

[0148] The display subunit is configured to display the cone-shaped bucket target according to the collision risk, divide the target into areas according to the grid area occupied by the cone-shaped bucket target, and display the areas on the center control screen.

[0149] The first reminding subunit is configured to voice broadcast whether there is a cone-shaped bucket target in front, the number of the cone-shaped bucket target, and the collision distance.

[0150] The second reminding subunit is configured to control the vehicle to perform a shaking reminder at a preset frequency when the distance between the vehicle and the cone-shaped bucket is less than a preset distance.

[0151] It should be noted that the foregoing explanation and description of the embodiment of the cone-shaped bucket visualization method based on the grid map also applies to the embodiment of the cone-shaped bucket visualization device based on the grid map, which will not be described herein again.

[0152] The cone-shaped bucket visualization device based on the grid map according to the embodiment of the present application can construct lane information according to environmental information of a current environment, expand a global path of the vehicle and a local path generated by target information and environmental information, generate a grid map, screen out a grid area occupied by a cone-shaped bucket target, calculate a driving boundary according to a driving condition, predict a collision distance of the vehicle, determine a cone-shaped bucket target with a collision risk, and obtain visualization information according to the cone-shaped bucket target with the collision risk, the grid area occupied by the cone-shaped bucket target, and the lane information, realize collision distance detection of a potential collision target in combination with a driving condition of the vehicle, provide a visual aid by displaying the cone-shaped bucket target with the collision risk, reduce the influence of the environment on the grid map, and thus guarantee driving safety of the vehicle. Therefore, the technical problem in the related art that the grid map has strong dependence on a lane environment and is not suitable for a parking scene with small obstacles such as a cone-shaped bucket is solved.

[0153] Figure 6A structural schematic diagram of a vehicle is provided for an embodiment of the present application. The vehicle can include

[0154] The memory 601, the processor 602 and the computer program stored in the memory 601 and executable on the processor 602.

[0155] The processor 602 implements the cone visualization method based on the grid map provided in the above embodiments when executing the program.

[0156] Further, the vehicle further includes

[0157] The communication interface 603 is used for communication between the memory 601 and the processor 602.

[0158] The memory 601 is used to store the computer program executable on the processor 602.

[0159] The memory 601 can include a high-speed RAM memory, and can also include a non-volatile memory, for example, at least one disk memory.

[0160] If the memory 601, the processor 602 and the communication interface 603 are independently implemented, the communication interface 603, the memory 601 and the processor 602 can be connected to each other through a bus and complete communication between each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one thick line is used in the figure, but it does not mean that there is only one bus or only one type of bus.

[0161] Optionally, in a specific implementation, if the memory 601, the processor 602 and the communication interface 603 are integrated on a chip, the memory 601, the processor 602 and the communication interface 603 can complete communication between each other through an internal interface.

[0162] The processor 602 can be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0163] The embodiment also provides a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the above-mentioned cone-shaped bucket visualization method based on a grid map.

[0164] In the description of the specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or N embodiments or examples. In addition, the person skilled in the art can combine and combine the different embodiments or examples described in the specification and the features of the different embodiments or examples, without contradiction.

[0165] In addition, the terms "first", "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "N" is at least two, for example, two, three, etc., unless otherwise specifically limited.

[0166] Any process or method descriptions in flow charts or otherwise described herein can be understood as representing code modules, segments, or portions of code that include one or more executable instructions for performing a step of a process, and that the scope of preferred embodiments of the present application encompasses alterations, modifications, and variations of these codes modules, segments, or portions of code that can be performed in an order different than that which is shown or discussed. The order in which steps are described is not necessarily the order in which the steps are performed.

[0167] The logic and / or steps represented in the flowcharts and / or described herein, for example, can be considered as a sequence of executable instructions stored in a computer readable medium, which can be executed by an instruction execution system, apparatus or device, such as a computer-based system, a processor-based system, or other system that can fetch the instructions from the instruction execution system, apparatus or device and execute the instructions, or a combination of them. For the purposes of this specification, a "computer readable medium" can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus or device. The computer readable medium can be a computer readable storage medium or a computer readable signal medium. The computer readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a propagation medium. The computer readable signal medium can include, but is not limited to, a computer readable medium that facilitates transfer of the program from one place to another. A specific example of a computer readable medium is a non-transitory computer-readable storage medium. A specific example of a computer readable signal medium is a source or destination of the computer readable medium. Another specific example of a computer readable signal medium is a computer readable signal travelling through space. Thus, a computer readable medium can take many forms of hardware to carry out the program for use by or in connection with the instruction execution system, apparatus or device.

[0168] It should be understood that aspects of the application can be implemented in hardware, software, firmware or combinations thereof. In the above embodiments, the N steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As such, if implemented in hardware, and in another embodiment, any of the following technologies, known in the art, or their combinations can be used: discrete logic circuitry having logic gates for implementing logic functions on data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), and the like.

[0169] Those skilled in the art can understand that all or part of the steps carried out by the above-mentioned embodiment methods can be completed by programs instructing related hardware, and the programs can be stored in a computer readable storage medium. When the programs are executed, one or a combination of the steps of the method embodiments is included.

[0170] In addition, each of the functional units in the various embodiments of the present application can be integrated in one processing module, or each of the units can be physically present separately, or two or more units can be integrated in one module. The integrated module can be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer readable storage medium.

[0171] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above embodiments within the scope of the present application.

Claims

1. A method for cone visualization based on a raster map, characterized in that, The method comprises the following steps: identifying target information of a target and constructing lane information according to environment information of a current environment; extending a global path of a vehicle and a local path generated by the target information and the environment information, generating a grid map based on a driving track obtained, filtering grids in a cone barrel obstacle state based on a length and a width of the vehicle, and screening a grid area occupied by a cone barrel target; and detecting a driving condition of the vehicle, calculating a driving boundary according to the driving condition, predicting a collision distance of the vehicle, determining a cone barrel target with a collision risk, and obtaining visual information according to the cone barrel target with the collision risk, the grid area occupied by the cone barrel target, and the lane information; wherein the calculation of the driving boundary according to the driving condition comprises: calculating a first turning radius, a second turning radius, and a minimum turning radius under the driving condition; and planning the driving boundary according to the first turning radius, the second turning radius, and the minimum turning radius; wherein the prediction of the collision distance of the vehicle comprises: regarding a cone barrel target within the range of the driving boundary as a cone barrel obstacle with a collision risk, taking an instantaneous turning center of the vehicle as the center of a circle, taking the distance from the instantaneous turning center to the center of the nearest grid in the cone barrel obstacle state as the radius of the circle, and taking the track arc length obtained by the intersection of the driving track and the driving boundary as the collision distance.

2. The method of claim 1, wherein, The obtaining of the visual information according to the cone barrel target with the collision risk, the grid area occupied by the cone barrel target, and the lane information comprises: generating visual feedback information according to the cone barrel target with the collision risk, the grid area occupied by the cone barrel target, and the lane information; and / or, generating auditory feedback information according to the cone barrel target with the collision risk, the grid area occupied by the cone barrel target, and the lane information; and / or, generating tactile feedback information according to the cone barrel target with the collision risk, the grid area occupied by the cone barrel target, and the lane information; controlling the vehicle to perform corresponding feedback actions on the user based on the visual feedback information, the auditory feedback information, and / or the tactile feedback information.

3. The method of claim 2, wherein, The control of the vehicle to perform corresponding feedback actions on the user based on the visual feedback information, the auditory feedback information, and / or the tactile feedback information comprises: displaying the cone barrel target according to the collision risk, dividing the target into areas according to the grid area occupied by the cone barrel target, and displaying the target on a center control screen accordingly; and / or, voice broadcasting whether the cone barrel target exists in front, the number of the cone barrel targets, and the collision distance; and / or, controlling the vehicle to perform a shaking reminder at a preset frequency when the distance between the vehicle and the cone barrel target is less than a preset distance.

4. A device for cone visualization based on a raster map, characterized by The method comprises: a construction module configured to identify target information of a target and construct lane information according to environment information of a current environment; The generating module is configured to extend a global path of the vehicle and a local path generated based on the target information and the environment information, generate a grid map based on a resulting driving trajectory, filter grids in a cone bucket obstacle state based on a length and a width of the vehicle, and screen a grid area occupied by the cone bucket target. and The visualization module is configured to detect a driving condition of the vehicle, calculate a driving boundary based on the driving condition, predict a collision distance of the vehicle, determine a cone bucket target with a collision risk, and obtain visualization information based on the cone bucket target with the collision risk, the grid area occupied by the cone bucket target, and the lane information. The visualization module includes a calculation unit configured to calculate a first turning radius, a second turning radius, and a minimum turning radius in the driving condition, and a planning unit configured to plan the driving boundary based on the first turning radius, the second turning radius, and the minimum turning radius. The visualization module includes a prediction unit configured to regard a cone bucket target within a range of the driving boundary as a cone bucket obstacle with the collision risk, take an instantaneous turning center of the vehicle as a center of a circle, take a distance from the instantaneous turning center to a nearest grid center point in the cone bucket obstacle state as a radius of the circle, and take a trajectory arc length obtained by intersecting the driving trajectory and the driving boundary as the collision distance.

5. A vehicle characterized by comprising: The computer program is stored in the memory and executable on the processor, and the processor executes the program to implement the cone bucket visualization method based on the grid map according to any one of claims 1-3. The program is executed by the processor to implement the cone bucket visualization method based on the grid map according to any one of claims 1-3.

6. A computer-readable storage medium having stored thereon a computer program, characterized in that, ​

Images