CN117633133A - Method, device, equipment and storage medium for calculating passable area of vehicle - Google Patents

Abstract

The invention provides a vehicle passable area calculating method, a device, equipment and a storage medium, wherein the method comprises the steps of obtaining historical driving data and current initial data of a target vehicle, removing interference data in the current initial data to obtain candidate data, calculating a current driving angle and a current driving distance radius corresponding to each candidate data based on the candidate data, constructing a current vehicle coordinate system based on the current driving angle and the current driving distance radius, determining a historical driving position based on the historical driving data, converting the historical driving position into the current vehicle coordinate system to obtain a target parameter for determining a passable area, calculating the confidence coefficient of the target parameter, and determining the passable area of the target vehicle based on the target parameter when the confidence coefficient of the target parameter is greater than or equal to a preset confidence coefficient threshold; by accumulating the historical data and the current data, the accuracy of environment identification is improved, the advantages of each sensor are fully utilized, and the effectiveness of the passable area is improved.

Description

Method, device, equipment and storage medium for calculating passable area of vehicle

Technical Field

The present disclosure relates to the field of navigation technologies, and in particular, to a method, an apparatus, a device, and a storage medium for calculating a passable area of a vehicle.

Background

Along with the continuous development of artificial intelligence technology, intelligent driving technology is also advancing continuously, and at present, intelligent driving technology can realize multiple functions, such as automatic parking, automatic emergency braking, lane departure early warning and the like. In the intelligent driving process, the intelligent automobile detects and analyzes the surrounding environment in the traffic scene through multi-sensor sensing, so that various functions are realized. It can be seen that an accurate and reliable communication area is an important condition for intelligent driving, so how to detect the passable area to obtain more accurate and reliable passable area information becomes a particularly important part of intelligent automobiles.

The intelligent vehicle passable area detection comprises road boundary detection and obstacle detection, which are the results after environment sensing and fusion based on the vehicle-mounted sensor, and are the basis of track planning of the intelligent vehicle. The detection of the passable area of the intelligent vehicle is an important component of the automatic driving environment sensing technology, and can provide basis for real-time track planning of the intelligent vehicle. The current passable area calculation method mostly adopts a mode of combining road edge characteristic information and automobile radar information to calculate the passable area of the space where the vehicle is located, and has the conditions of low identification accuracy and poor credibility of the passable area under a complex indoor environment or other environments with less road edge characteristic information.

Disclosure of Invention

In view of the above drawbacks of the prior art, the present invention provides a method, an apparatus, a device, and a storage medium for calculating a passable area of a vehicle, so as to solve the technical problem that the reliability of the passable area is poor due to low recognition accuracy in the complex indoor environment or other environments with less road edge feature information.

The invention provides a vehicle passable area calculating method, which comprises the following steps: acquiring historical driving data and current initial data of a target vehicle, wherein the target vehicle is a vehicle of a passable area to be calculated, and the current initial data is sensor parameters of the target vehicle in a preset environment; removing interference data in the current initial data to obtain processed candidate data, and calculating a current driving angle and a current driving distance radius corresponding to each candidate data based on the candidate data; constructing a current vehicle coordinate system based on the current driving angle and the current driving distance radius, determining a historical driving position based on the historical driving data, and converting the historical driving position into the current vehicle coordinate system; fusing the historical driving position, the current driving angle and the current driving distance radius in the current vehicle coordinate system to obtain target parameters for determining a passable area; and calculating the confidence coefficient of the target parameter, and if the confidence coefficient of the target parameter is greater than or equal to a preset confidence coefficient threshold value, determining a passable area of the target vehicle based on the target parameter.

In an embodiment of the present invention, rejecting the interference data in the current initial data to obtain processed candidate data includes: acquiring a data category of the current initial data, wherein the data category comprises vision sensor data and radar sensor data; when the current initial data is the vision sensor data, taking any two continuous data as data to be detected, and calculating an angle difference value of the data to be detected; if the angle difference value is smaller than a preset angle threshold value, carrying out interpolation sampling on the data to be detected based on a preset data acquisition rule, and determining parameters obtained based on the interpolation sampling as the candidate data; and comparing the current initial data with a preset radar threshold value when the current initial data is radar sensor data, and determining the current initial data as the candidate data if the current initial data is within the preset radar threshold value range.

In an embodiment of the present invention, determining a historical driving location based on the historical driving data includes: acquiring self-vehicle driving data of the target vehicle, determining current time, steering wheel rotation angle and vehicle gear information based on the self-vehicle driving data, determining data acquisition time of the historical driving data based on the historical driving data, and determining the self-vehicle driving data based on the current initial data; obtaining a running time difference based on the current time and the historical acquisition time, and calculating displacement and rotation angle of the target vehicle from the data acquisition time to the current time based on the running time difference, the steering wheel rotation angle and the vehicle gear information; constructing a translational rotation matrix of the target vehicle under the current time difference based on the displacement and the rotation angle; and calculating the historical driving position of the current vehicle according to the current position of the target vehicle and the translational rotation matrix.

In an embodiment of the present invention, after fusing the historical driving position, the current driving angle, and the current driving distance radius, the method further includes: obtaining fusion results, and converting the fusion results based on the translation rotation matrix to obtain grid positions of each fusion result; if a plurality of fusion results exist at the same target grid position, determining the smallest fusion result in the plurality of fusion results as a target fusion result of the target grid.

In one embodiment of the present invention, obtaining target parameters for determining a passable area includes: traversing each target sensor effective point number, and calculating a current coordinate value of the effective point in the current vehicle coordinate system; obtaining a current radius value and an accumulated radius value based on the current coordinate value, and calculating a radius difference value between the current radius value and the accumulated radius value; when the radius difference value is smaller than a preset radius threshold value, determining the current coordinate value as an effective coordinate value, obtaining data weight based on the association relation between the accumulated radius value and the target sensor, obtaining a new driving distance radius and a new driving angle based on the data weight and the current coordinate value, and determining the new driving distance radius and the new driving angle as the target parameter; when the radius difference value is larger than or equal to the preset radius threshold value, determining that the current coordinate value is an invalid coordinate value, comparing the accumulated radius value with the data weight, traversing next input data if the accumulated radius value is smaller than or equal to the data weight, and accumulating the data weight to obtain new data weight if the accumulated radius value is larger than the data weight.

In an embodiment of the present invention, before determining the passable area of the target vehicle based on the target parameter, the method includes: determining whether an obstacle exists in the environment to be detected or not based on a laser radar, if so, acquiring current parameters of each sensor, and detecting the data state of the current parameters of each sensor based on a preset sensor sequence; if any current parameter is larger than a preset parameter threshold, determining the current parameter as an overrun parameter, and determining a grid corresponding to the overrun parameter as a stable grid.

In an embodiment of the present invention, determining a passable area of the target vehicle based on the target parameter includes: grid parameters of all stable grids are obtained, wherein the grid parameters comprise vehicle relative angles and vehicle relative position distances in the grids; and generating an updated coordinate system based on the vehicle relative angle and the vehicle relative position distance, calculating the position validity of each grid parameter based on the updated coordinate system, and determining a set of all legal positions as a passable area of the target vehicle.

There is provided in itself a vehicle passable zone computing device, the device comprising: the data acquisition module is used for acquiring historical driving data and current initial data of a target vehicle, wherein the target vehicle is a vehicle of a passable area to be calculated, and the current initial data is sensor parameters of the target vehicle in a preset environment; the data preprocessing module is used for eliminating interference data in the current initial data to obtain processed candidate data, and calculating a current driving angle and a current driving distance radius corresponding to each candidate data based on the candidate data; the data synchronization module is used for constructing a current vehicle coordinate system based on the current driving angle and the current driving distance radius, generating a historical driving track based on the historical driving data, and converting the historical driving track into the current vehicle coordinate system; the grid accumulation module is used for fusing the historical driving track, the current driving angle and the current driving distance radius in the current vehicle coordinate system to obtain target parameters for determining a passable area; the confidence analysis and region calculation module is used for calculating the confidence coefficient of the target parameter, and if the confidence coefficient of the target parameter is larger than or equal to a preset confidence coefficient threshold value, the passable region of the target vehicle is determined based on the target parameter.

Itself provides an electronic device comprising: one or more processors; and a storage means for storing one or more programs which, when executed by the one or more processors, cause the electronic device to implement the vehicle-passable region calculation method as described above.

The present application provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor of a computer, causes the computer to perform the vehicle-passable region calculation method as described above.

The invention has the beneficial effects that: the method comprises the steps of obtaining historical driving data and current initial data of a target vehicle, removing interference data in the current initial data to obtain candidate data, calculating a current driving angle and a current driving distance radius corresponding to each candidate data based on the candidate data, constructing a current vehicle coordinate system based on the current driving angle and the current driving distance radius, determining a historical driving position based on the historical driving data, converting the historical driving position into the current vehicle coordinate system to obtain a target parameter for determining a passable area, calculating the confidence coefficient of the target parameter, and determining the passable area of the target vehicle based on the target parameter when the confidence coefficient of the target parameter is greater than or equal to a preset confidence coefficient threshold; by accumulating the historical data and the current data, the accuracy of environment identification is improved, the advantages of each sensor are fully utilized, and the effectiveness of the passable area is improved.

In addition, the technical scheme provided by the application not only realizes the distinction of the obstacle and the miscellaneous point, realizes the filtration of the miscellaneous point, improves the accuracy of the drivable area, but also avoids the accumulated time consumption, and ensures the real-time performance by a frame-by-frame updating method; in addition, the content of a single frame FreePace is enriched, the boundary contour detection of barriers such as walls, cones and the like is more accurate, and the accuracy and the integrity of an output passable area are improved; and corresponding confidence coefficient threshold and analysis method are provided for each different sensor characteristic, the advantages of each sensor are fully utilized, the effectiveness of the output passable area is ensured, and the output can be effectively performed in an indoor environment.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application. It is apparent that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art. In the drawings:

FIG. 1 is a schematic diagram illustrating an implementation environment of a vehicle-passable region calculation method according to an exemplary embodiment of the present application;

FIG. 2 is a flow chart of a vehicle-passable region calculation method shown in an exemplary embodiment of the present application;

FIG. 3 is a schematic diagram of a vehicle-passable region calculation method data acquisition and processing flow shown in an exemplary embodiment of the present application;

FIG. 4 is a flow chart of a fusion grid confidence analysis algorithm shown in an exemplary embodiment of the present application;

FIG. 5 is a block diagram of a vehicle-passable zone computing device shown in an exemplary embodiment of the present application;

fig. 6 shows a schematic diagram of a computer system suitable for use in implementing the electronic device of the embodiments of the present application.

Detailed Description

Further advantages and effects of the present invention will become readily apparent to those skilled in the art from the disclosure herein, by referring to the accompanying drawings and the preferred embodiments. The invention may be practiced or carried out in other embodiments that depart from the specific details, and the details of the present description may be modified or varied from the spirit and scope of the present invention. It should be understood that the preferred embodiments are presented by way of illustration only and not by way of limitation.

It should be noted that the illustrations provided in the following embodiments merely illustrate the basic concept of the present invention by way of illustration, and only the components related to the present invention are shown in the drawings and are not drawn according to the number, shape and size of the components in actual implementation, and the form, number and proportion of the components in actual implementation may be arbitrarily changed, and the layout of the components may be more complicated.

In the following description, numerous details are set forth in order to provide a more thorough explanation of embodiments of the present invention, it will be apparent, however, to one skilled in the art that embodiments of the present invention may be practiced without these specific details, in other embodiments, well-known structures and devices are shown in block diagram form, rather than in detail, in order to avoid obscuring the embodiments of the present invention.

It should be noted that, the Freespace data is data related to the perception and positioning of the robot, and is mainly used for the perception task of the robot, including but not limited to 3D perception, SLAM, 3D reconstruction, and the like. Typically including point cloud data, image data, and other sensor data, where point cloud data is one of the most common data types. Point cloud data is a data format describing the geometry of the surface of an object, acquired by sensors such as lidar, depth cameras, and the like.

Freepace refers to the area of travel of an unmanned vehicle, as well as the space in the point cloud data that is used to describe the robotic perception and localization tasks.

the transform_matrix is a transformation matrix for implementing a translation operation, and the rotation_matrix is also a rotation matrix, which has the effect of changing the direction of a vector but not the size when multiplying by a vector and maintains chirality.

A polar Grid (Radial Grid) is a Grid under a cylindrical coordinate system, and is commonly used in reservoir simulation, mainly considering anisotropy and heterogeneity of a reservoir. In a polar coordinate system, the radial grid is arranged mainly around the center point, thus providing finer resolution for the region near the center.

lidar (Light Detection And Ranging) is a system integrating three technologies of laser, global Positioning System (GPS) and Inertial Navigation System (INS) for obtaining point cloud data and generating an accurate digitized three-dimensional model.

The sensor is a detection device, can sense the measured information, and can convert the information sensed by detection into an electric signal or other information in a required form according to a certain rule so as to meet the requirements of information transmission, processing, storage, display, recording, control and the like.

Fig. 1 is a schematic view showing an implementation environment of a vehicle passable region calculation method according to an exemplary embodiment of the present application. As shown in fig. 1, the environment for implementing the vehicle passable area calculation method includes a data acquisition device 101 and a computer device 102, where the data acquisition device 101 is used for acquiring running parameters of a vehicle and surrounding environment information of a space where the vehicle is located, and sending the acquired data information to the computer device 102, and the surrounding environment information acquisition devices include, but are not limited to, a visual data acquisition device and a spatial data acquisition device, where the visual data acquisition device may be any device that may be used for acquiring image data, such as an infrared camera, and the spatial data acquisition device may be any device that may be used for ranging or determining any other spatial information, such as a radar device, and the application does not limit the type, number and installation position of the device. The computer device 102 is configured to receive the vehicle running parameter acquired by the data acquisition device 101 and surrounding environmental information of a space where the vehicle is located, and perform comprehensive processing on the information, so as to calculate a drivable area of the vehicle in the environmental space. The computer device 102 may be at least one of a desktop graphics processor (Graphic Processing Unit, GPU) computer, a GPU computing cluster, a neural network computer, etc., or may be an intelligent processor integrated on the current vehicle, which is not limited in this application.

FIG. 2 is a flow chart of a vehicle passable region calculation method, as shown in an exemplary embodiment of the present application.

As shown in fig. 2, in an exemplary embodiment, the road condition refreshing method at least includes steps S210 to S250, which are described in detail as follows:

step S210, acquiring historical driving data and current initial data of a target vehicle, wherein the target vehicle is a vehicle in a passable area to be calculated, and the current initial data is a sensor parameter of the target vehicle in a preset environment.

In one embodiment of the application, a plurality of data parameters are acquired based on a vehicle-mounted sensor, the data acquired at present are used as the initial parameters at present, and historical storage data of a vehicle terminal are called to obtain historical driving data. It should be noted that the vehicle-mounted sensor includes various visual sensors and radar sensors, and the application does not limit the types, the number and the installation positions of the sensors.

Step S220, eliminating interference data in the current initial data to obtain processed candidate data, and calculating the current driving angle and the current driving distance radius corresponding to each candidate data based on the candidate data.

In one embodiment of the present application, rejecting interference data in current initial data to obtain processed candidate data includes: acquiring a data category of current initial data, wherein the data category comprises vision sensor data and radar sensor data; if the current initial data is the vision sensor data, taking any two continuous data as the data to be detected, and calculating the angle difference value of the data to be detected; if the angle difference value is smaller than a preset angle threshold value, carrying out interpolation sampling on the data to be detected based on a preset data acquisition rule, and determining parameters obtained based on the interpolation sampling as candidate data; if the current initial data is radar sensor data, comparing the current initial data with a preset radar threshold value, and if the current initial data is within the preset radar threshold value range, determining the current initial data as candidate data.

Step S230, a current vehicle coordinate system is constructed based on the current driving angle and the current driving distance radius, the historical driving position is determined based on the historical driving data, and the historical driving position is converted into the current vehicle coordinate system.

In one embodiment of the present application, determining a historical driving location based on historical driving data includes: acquiring self-vehicle driving data of a target vehicle, determining current time, steering wheel rotation angle and vehicle gear information based on the self-vehicle driving data, determining data acquisition time of historical driving data based on the historical driving data, and determining the self-vehicle driving data based on the current initial data; obtaining a running time difference based on the current time and the historical acquisition time, and calculating displacement and rotation angle of the target vehicle between the data acquisition time and the current time based on the running time difference, the steering wheel rotation angle and the vehicle gear information; constructing a translational rotation matrix of the target vehicle under the current time difference based on the displacement and the rotation angle; and calculating according to the current position of the target vehicle and the translational rotation matrix to obtain the historical driving position of the current vehicle.

Step S240, merging the historical driving position, the current driving angle and the current driving distance radius in the current vehicle coordinate system to obtain the target parameters for determining the passable area.

In one embodiment of the present application, after fusing the historical driving position, the current driving angle, and the current driving distance radius, the method further includes: obtaining fusion results, and converting the fusion results based on the translation rotation matrix to obtain grid positions of each fusion result; if a plurality of fusion results exist at the same target grid position, determining the smallest fusion result in the plurality of fusion results as the target fusion result of the target grid.

In one embodiment of the present application, obtaining target parameters for determining a passable area includes: traversing the effective points of each target sensor, and calculating the current coordinate values of the effective points in the current vehicle coordinate system; obtaining a current radius value and an accumulated radius value based on the current coordinate value, and calculating the current radius value and the accumulated radius value to obtain a radius difference value; when the radius difference value is smaller than a preset radius threshold value, determining the current coordinate value as an effective coordinate value, obtaining a data weight based on the association relation between the accumulated radius value and the target sensor, obtaining a new driving distance radius and a new driving angle based on the data weight and the current coordinate value, and determining the new driving distance radius and the new driving angle as target parameters; when the radius difference value is larger than or equal to a preset radius threshold value, determining that the current coordinate value is an invalid coordinate value, comparing the accumulated radius value with the data weight, traversing the next input data if the accumulated radius value is smaller than or equal to the data weight, and accumulating the data weight if the accumulated radius value is larger than the data weight to obtain a new data weight.

In step S250, the confidence level of the target parameter is calculated, and if the confidence level of the target parameter is greater than or equal to the preset confidence threshold, the passable area of the target vehicle is determined based on the target parameter.

In one embodiment of the present application, before determining the passable area of the target vehicle based on the target parameter, it includes: determining whether an obstacle exists in the environment to be detected based on the laser radar, if so, acquiring current parameters of each sensor, and detecting the data state of the current parameters of each sensor based on a preset sensor sequence; if any current parameter is larger than a preset parameter threshold, determining the current parameter as an overrun parameter, and determining a grid corresponding to the overrun parameter as a stable grid.

In one embodiment of the present application, determining a passable area of a target vehicle based on a target parameter includes: grid parameters of all stable grids are obtained, wherein the grid parameters comprise vehicle relative angles and vehicle relative position distances in the grids; an updated coordinate system is generated based on the vehicle relative angle and the vehicle relative position distance, the position validity of each grid parameter is calculated based on the updated coordinate system, and the set of all legal positions is determined as a passable area of the target vehicle.

FIG. 3 is a schematic diagram of a data acquisition and processing flow of a vehicle-passable region calculation method according to an exemplary embodiment of the present application.

As shown in fig. 3, initial data is obtained through a data acquisition device, then data preprocessing and data synchronization are performed on the initial data, grid accumulation and confidence analysis are performed on the synchronized data, and finally, a freepace generation is fused, and the generated result is used as a data basis for subsequent processing. The device for acquiring the initial data comprises a front view camera, a round view camera, a peripheral view camera, an angle radar, a front radar and a laser radar, and in addition, the self-vehicle running data can be acquired based on a vehicle-mounted center.

In one embodiment of the present application, taking autopilot parking as an example, the following is specific:

firstly, based on a detection range required by a parking scene system, acquiring initial data through a front-view camera, a round-view camera, a peripheral-view camera, an angular radar, a front radar, a laser radar and other related data acquisition devices, taking the initial data as input parameters, screening and removing the input parameters, and reserving the initial parameters in the range for subsequent processing.

In a specific embodiment of the present application, different standard data ranges are determined based on different data acquisition devices, and the acquired initial data is compared with the corresponding standard data range after being classified based on the data acquisition devices, if the initial data is within the corresponding standard data range, the data is reserved, otherwise the data is removed, for example, if the front-view camera a is taken as an example, the corresponding standard data range is a, if the initial data X is front-view camera data and is greater than or equal to the minimum value of a and less than the maximum value of a, namely, the value of the data X is within the range of a, the data X is reserved; otherwise, the data Y is also a parameter acquired by the front-view camera, and the value of the data Y exceeds the range of a, and the data Y is removed.

In addition, for the freepace data of the vision sensor, if the deviation of the front freepace point and the rear freepace point is smaller than a specific threshold, interpolation up-sampling is carried out on the freepace point and the rear freepace point based on the angular resolution, and the up-sampling result is stored in the preprocessing freepace for subsequent processing.

Then, based on the processed candidate data, the Euclidean distance between the vehicle and the FreePace point is calculated for each sensor data input value as coordinates (x, y) of the parallel vehicle running direction and the perpendicular vehicle running direction The angle is->If the angle α is smaller than 0, α=α+2pi. For the obtained alpha value, coordinates are calculatedWhere Angle Res represents the polar grid resolution. The polar coordinates id, angle α, euclidean distance radius ρ are saved in the structure and the total number of valid points per sensor FreeSpace is recorded for subsequent processing.

And then, the data after being processed by the data preprocessing module mainly comprises the currently received data frame after invalid information is filtered and the data frame stored in history as inputs, so that the data is spatially synchronized. Firstly, traversing a data frame stored by history for stored historical frame data, calculating the driving distance of a vehicle in a time difference range through vehicle driving data and the time difference, and calculating the displacement delta x, delta y and the rotation angle delta angle of the vehicle in the x and y directions through steering wheel rotation angle and gear information shift position; secondly, through displacement deltax, deltay and rotation delta angle of the vehicle in the x and y directions, a translation rotation matrix transformation_matrix and a rotation matrix corresponding to the current time difference can be formed, and then the historically stored data frame is calculated under a vehicle coordinate system corresponding to the current time according to the translation rotation matrix transformation_matrix and the rotation matrix.

Furthermore, dead reckoning is then also required for the fusion result track and the multi-frame accumulated accumu data for each sensor: after converting the fusion result track according to the translation rotation matrix translation_matrix and the rotation_matrix, selecting a track with a smaller radius as a storage if a plurality of tracks are positioned in the same polar coordinate grid; for the sensor multi-frame accumulated accumu, firstly judging whether coordinate conversion is needed according to the confidence coefficient, and after coordinate conversion is carried out on the accumu meeting the conditions, if a plurality of accumu are positioned in the same polar coordinate grid, the accumu with larger confidence coefficient is visually selected, the millimeter wave radar is selected from the accumu with smaller radius, and the lidar is selected from the accumu with smaller radius and confidence coefficient exceeding the threshold.

And then, after the data synchronization module, matching and fusion updating are carried out on the accumulated value accumu data based on the dead reckoning completed by the grid accumulation module and the received latest frame data. The method comprises traversing the valid point number of each latest frame sensor for each sensor, and carrying out association matching and fusion operation on each corresponding grid by combining the coordinate id values obtained in the preprocessing. For each grid, calculating a difference Eradius between a radius value rho sensor of the new input sensor and an accumulation value rho accum, comparing the obtained difference with a threshold, if the difference is smaller than the threshold, the association is successful, otherwise, the association is unsuccessful.

In a specific embodiment of the present application, the association threshold may be set to γ×min (ρaccum, ρsensor), γ is a scaling factor, where the scaling factor of the look-around, and look-ahead sensor is set to 0.1, and the scaling factor of the angular radar, the front radar, and the lidar is set to 0.2.

In addition, for the associated sensor and accumu, the radius and angle can be updated according to the confidence of the two as weights [ wassum, wsensor ], which is specifically as follows:

ρaccum＝waccum*ρaccum+wsensor*ρsensor

αaccum＝waccum*αaccum+wsensor*αsensor

the confidence is updated with lossframes set to 0 and freepace type set to sensor input freepace type.

If the confidence is not related, the accumulated data and the confidence of the input sensor are compared, if conf_accum is larger, the next input data is continuously traversed, if conf_sensor is smaller, the lossframes is set to 0, the accumulated confidence, the type, the angle and the radius are all set to be the values of the input sensor. According to the logic, after all inputs are traversed, confidence degree attenuation processing is carried out on accumulated data with lossframes larger than 0, attenuation coefficient is 0.1 for all-round looking and all-round looking forward looking data, and attenuation coefficient is 0.05 for angle radar, front radar and laser radar.

FIG. 4 is a flow chart of a fusion grid confidence analysis algorithm, as shown in an exemplary embodiment of the present application.

Then, for the updated grid accumulation result, confidence analysis needs to be carried out on the updated grid accumulation result, the grid meeting the confidence requirement is marked as stable, corresponding sensor sources are recorded, and the main algorithm idea of the confidence analysis is shown in fig. 4:

firstly, whether the obstacle is a candidate is primarily judged according to the confidence coefficient of the round-looking, millimeter wave radar and laser radar, and if the obstacle is not a candidate, the next grid is directly traversed. For candidate obstacles, the judgment steps are as follows:

1) Firstly judging whether the ultrasonic component in the looking around exceeds a threshold, if so, recording the state as stable, and recording the input source as ultrasonic.

2) Judging whether the laser radar exceeds a threshold, if so, recording the state as stable, and recording the input source as the laser radar.

3) Judging whether the confidence coefficient of the millimeter wave radar exceeds a threshold, if so, selecting a front angle radar and a rear angle radar, wherein a sensor with the maximum confidence coefficient in the front radar is used as an input source, and the following steps are as follows:

a) Judging whether the front radar exceeds a threshold, if so, recording as stable;

b) If the laser radar and the front radar exceed the combination threshold and the distance between the laser radar and the front radar is smaller, recording as stable;

c) If the looking-around radar and the front radar exceed the combination threshold and the distance between the looking-around radar and the front radar is smaller, recording the distance as stable;

d) If the confidence level of the looking around, the angle radar, the periscope, the foresight, the laser and the foresight exceeds the combination threshold, the distance is smaller, and the record is stable;

4) If the vision threshold exceeds the threshold, selecting the sensor with the largest front view, peripheral view and ring view confidence as an input source, and the following steps are as follows:

a) If the looking-around confidence coefficient exceeds the threshold, recording as stable;

b) If the weekly confidence exceeds the threshold, recording as stable;

c) If the forward looking confidence exceeds the threshold, recording as stable;

d) If the confidence level of the looking-around and laser radar exceeds the combination threshold and the distance is smaller, recording as stable;

e) If the confidence coefficient of the forward looking radar and the laser radar exceeds the combination threshold and the distance is smaller, recording as stable;

f) If the linearity of the periscope and the laser radar exceeds the combination threshold and the distance is smaller, recording as stable;

5) If the confidence coefficient of the angle radar exceeds a threshold and the grid is not marked as stable, setting a data source as the angle radar, setting an angle searching range, counting the confidence coefficient of the angle radar, front radar, peripheral vision, round-the-road vision, front vision and laser radar, which are close to the angle in the grid, and if the counted result exceeds a combined threshold, recording as stable.

6) For a grid in stable state, based on the sensor data source, the angles, radii and freepace types within the grid are recorded.

7) And outputting a confidence analysis result.

And finally, outputting the final FreePace structure by the function internal grid structure. The output freepace will first be time-set based on the current timestamp. The input fused Objects are then circumscribed by a rectangle calculation and saved as refPtsPos. And according to the states of the tracks in each grid, if the track states are stable, the angles alpha and the radii rho of the tracks are converted into x and y under a Cartesian coordinate system, the x and the y are stored in an output structure element Fs_point, whether the Fs_point is in a rectangular group of refPtsPos is judged, the internal Fs_point is marked as dynamic FreeStace, and the rest is static. After traversing all grids, the set FreePace_opt of all Fs_points is output as a function for the next stage. The internal structures accum and track are stored in global variables for use in the next fusion cycle.

Fig. 5 is a block diagram of a road condition refreshing apparatus according to an exemplary embodiment of the present application. The device may be applied to the implementation environment shown in fig. 1. The apparatus may also be adapted to other exemplary implementation environments and may be specifically configured in other devices, and the present embodiment is not limited to the implementation environments to which the apparatus is adapted.

As shown in fig. 5, the exemplary road condition refreshing apparatus includes: a data acquisition module 510, a data preprocessing module 520, a data synchronization module 530, a grid accumulation module 540, and a confidence analysis and region calculation module 550.

The data acquisition module 510 is configured to acquire historical driving data and current initial data of a target vehicle, where the target vehicle is a vehicle in a passable area to be calculated, and the current initial data is a sensor parameter of the target vehicle in a preset environment; the data preprocessing module 520 is configured to reject the interference data in the current initial data to obtain processed candidate data, and calculate a current driving angle and a current driving distance radius corresponding to each candidate data based on the candidate data; the data synchronization module 530 is configured to construct a current vehicle coordinate system based on the current driving angle and the current driving distance radius, generate a historical driving track based on the historical driving data, and convert the historical driving track into the current vehicle coordinate system; the grid accumulation module 540 is configured to fuse the historical driving track, the current driving angle and the current driving distance radius in the current vehicle coordinate system to obtain a target parameter for determining the passable area; the confidence analysis and region calculation module 550 is configured to calculate a confidence level of the target parameter, and determine a passable region of the target vehicle based on the target parameter if the confidence level of the target parameter is greater than or equal to a preset confidence threshold.

It should be noted that, the vehicle-passable area calculating device provided in the foregoing embodiment and the vehicle-passable area calculating method provided in the foregoing embodiment belong to the same concept, and the specific manner in which each module and unit perform the operation has been described in detail in the method embodiment, which is not repeated herein. In practical application, the vehicle-accessible area computing device provided in the above embodiment may be configured to distribute the functions as required by different functional modules, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above, which is not limited herein.

The embodiment of the application also provides electronic equipment, which comprises: one or more processors; and a storage means for storing one or more programs that, when executed by the one or more processors, cause the electronic device to implement the vehicle-passable region calculation method provided in the respective embodiments described above.

Fig. 6 shows a schematic diagram of a computer system suitable for use in implementing the electronic device of the embodiments of the present application. It should be noted that, the computer system 600 of the electronic device shown in fig. 6 is only an example, and should not impose any limitation on the functions and the application scope of the embodiments of the present application.

As shown in fig. 6, the computer system 600 includes a central processing unit (Central Processing Unit, CPU) 601, which can perform various appropriate actions and processes according to a program stored in a Read-only memory (ROM) 602 or a program loaded from a storage section 608 into a random access memory (Random Access Memory, RAM) 603, for example, performing the method described in the above embodiment. In the RAM 603, various programs and data required for system operation are also stored. The CPU 601, ROM 602, and RAM 603 are connected to each other through a bus 604. An Input/Output (I/O) interface 605 is also connected to bus 604.

The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, mouse, etc.; an output portion 607 including a Cathode Ray Tube (CRT), a liquid crystal display (Liquid Crystal Display, LCD), and a speaker, etc.; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN (Local AreaNetwork ) card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The drive 610 is also connected to the I/O interface 605 as needed. Removable media 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is installed as needed on drive 610 so that a computer program read therefrom is installed as needed into storage section 608.

In particular, according to embodiments of the present application, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising a computer program for performing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication portion 609, and/or installed from the removable medium 611. When executed by a Central Processing Unit (CPU) 601, performs the various functions defined in the system of the present application.

It should be noted that, the computer readable medium shown in the embodiments of the present application may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium may be, for example, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-Only Memory (ROM), an erasable programmable read-Only Memory (Erasable Programmable Read Only Memory, EPROM), flash Memory, an optical fiber, a portable compact disc read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with a computer-readable computer program embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. A computer program embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. Where each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units involved in the embodiments of the present application may be implemented by means of software, or may be implemented by means of hardware, and the described units may also be provided in a processor. Wherein the names of the units do not constitute a limitation of the units themselves in some cases.

Another aspect of the present application also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor of a computer, causes the computer to perform the vehicle-passable region calculation method as described above. The computer-readable storage medium may be included in the electronic device described in the above embodiment or may exist alone without being incorporated in the electronic device.

Another aspect of the present application also provides a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions so that the computer device performs the vehicle-passable region calculating method provided in the above-described respective embodiments.

The above embodiments are merely illustrative of the principles of the present invention and its effectiveness, and are not intended to limit the invention. Modifications and variations may be made to the above-described embodiments by those skilled in the art without departing from the spirit and scope of the invention. It is therefore intended that all equivalent modifications and changes made by those skilled in the art without departing from the spirit and technical spirit of the present invention shall be covered by the appended claims.

Claims (10)

1. A vehicle passable area calculation method, the method comprising:

acquiring historical driving data and current initial data of a target vehicle, wherein the target vehicle is a vehicle of a passable area to be calculated, and the current initial data is sensor parameters of the target vehicle in a preset environment;

removing interference data in the current initial data to obtain processed candidate data, and calculating a current driving angle and a current driving distance radius corresponding to each candidate data based on the candidate data;

constructing a current vehicle coordinate system based on the current driving angle and the current driving distance radius, determining a historical driving position based on the historical driving data, and converting the historical driving position into the current vehicle coordinate system;

fusing the historical driving position, the current driving angle and the current driving distance radius in the current vehicle coordinate system to obtain target parameters for determining a passable area;

and calculating the confidence coefficient of the target parameter, and if the confidence coefficient of the target parameter is greater than or equal to a preset confidence coefficient threshold value, determining a passable area of the target vehicle based on the target parameter.

2. The vehicle-accessible region calculation method according to claim 1, wherein rejecting the interference data in the current initial data to obtain processed candidate data comprises:

acquiring a data category of the current initial data, wherein the data category comprises vision sensor data and radar sensor data;

when the current initial data is the vision sensor data, taking any two continuous data as data to be detected, and calculating an angle difference value of the data to be detected;

if the angle difference value is smaller than a preset angle threshold value, carrying out interpolation sampling on the data to be detected based on a preset data acquisition rule, and determining parameters obtained based on the interpolation sampling as the candidate data;

and comparing the current initial data with a preset radar threshold value when the current initial data is radar sensor data, and determining the current initial data as the candidate data if the current initial data is within the preset radar threshold value range.

3. The vehicle passable region calculation method of claim 1 wherein determining a historical driving location based on the historical driving data comprises:

Acquiring self-vehicle driving data of the target vehicle, determining current time, steering wheel rotation angle and vehicle gear information based on the self-vehicle driving data, determining data acquisition time of the historical driving data based on the historical driving data, and determining the self-vehicle driving data based on the current initial data;

obtaining a running time difference based on the current time and the historical acquisition time, and calculating displacement and rotation angle of the target vehicle from the data acquisition time to the current time based on the running time difference, the steering wheel rotation angle and the vehicle gear information;

constructing a translational rotation matrix of the target vehicle under the current time difference based on the displacement and the rotation angle;

and calculating the historical driving position of the current vehicle according to the current position of the target vehicle and the translational rotation matrix.

4. The vehicle passable region calculation method of claim 3 wherein after fusing the historical driving position, the current driving angle, and the current driving distance radius, further comprising:

obtaining fusion results, and converting the fusion results based on the translation rotation matrix to obtain grid positions of each fusion result;

If a plurality of fusion results exist at the same target grid position, determining the smallest fusion result in the plurality of fusion results as a target fusion result of the target grid.

5. The vehicle passable region calculation method of claim 4 wherein obtaining the target parameters for determining the passable region comprises:

traversing each target sensor effective point number, and calculating a current coordinate value of the effective point in the current vehicle coordinate system;

obtaining a current radius value and an accumulated radius value based on the current coordinate value, and calculating a radius difference value between the current radius value and the accumulated radius value;

when the radius difference value is smaller than a preset radius threshold value, determining the current coordinate value as an effective coordinate value, obtaining data weight based on the association relation between the accumulated radius value and the target sensor, obtaining a new driving distance radius and a new driving angle based on the data weight and the current coordinate value, and determining the new driving distance radius and the new driving angle as the target parameter;

when the radius difference value is larger than or equal to the preset radius threshold value, determining that the current coordinate value is an invalid coordinate value, comparing the accumulated radius value with the data weight, traversing next input data if the accumulated radius value is smaller than or equal to the data weight, and accumulating the data weight to obtain new data weight if the accumulated radius value is larger than the data weight.

6. The vehicle passable region calculation method according to any one of claims 1 to 5, characterized by comprising, before determining the passable region of the target vehicle based on the target parameter:

determining whether an obstacle exists in the environment to be detected or not based on a laser radar, if so, acquiring current parameters of each sensor, and detecting the data state of the current parameters of each sensor based on a preset sensor sequence;

if any current parameter is larger than a preset parameter threshold, determining the current parameter as an overrun parameter, and determining a grid corresponding to the overrun parameter as a stable grid.

7. The vehicle passable region calculation method of claim 6 wherein determining the passable region of the target vehicle based on the target parameter comprises:

grid parameters of all stable grids are obtained, wherein the grid parameters comprise vehicle relative angles and vehicle relative position distances in the grids;

and generating an updated coordinate system based on the vehicle relative angle and the vehicle relative position distance, calculating the position validity of each grid parameter based on the updated coordinate system, and determining a set of all legal positions as a passable area of the target vehicle.

8. A vehicle passable zone computing device, the device comprising:

the data acquisition module is used for acquiring historical driving data and current initial data of a target vehicle, wherein the target vehicle is a vehicle of a passable area to be calculated, and the current initial data is sensor parameters of the target vehicle in a preset environment;

the data preprocessing module is used for eliminating interference data in the current initial data to obtain processed candidate data, and calculating a current driving angle and a current driving distance radius corresponding to each candidate data based on the candidate data;

the data synchronization module is used for constructing a current vehicle coordinate system based on the current driving angle and the current driving distance radius, generating a historical driving track based on the historical driving data, and converting the historical driving track into the current vehicle coordinate system;

the grid accumulation module is used for fusing the historical driving track, the current driving angle and the current driving distance radius in the current vehicle coordinate system to obtain target parameters for determining a passable area;

the confidence analysis and region calculation module is used for calculating the confidence coefficient of the target parameter, and if the confidence coefficient of the target parameter is larger than or equal to a preset confidence coefficient threshold value, the passable region of the target vehicle is determined based on the target parameter.

9. An electronic device, the electronic device comprising:

one or more processors;

storage means for storing one or more programs which when executed by the one or more processors cause the electronic device to implement the vehicle-passable region calculation method of any one of claims 1 to 7.

10. A computer-readable storage medium, having stored thereon a computer program which, when executed by a processor of a computer, causes the computer to perform the vehicle-passable region calculation method of any one of claims 1 to 7.