Method and device for determining travelable area, storage medium and vehicle

Abstract

The invention provides a drivable area determination method and device, a storage medium and a vehicle, the method is applied to the field of vehicles, and the method comprises the following steps: determining a measurement grid corresponding to an obstacle measurement point in a grid map based on the obstacle measurement point, obtained by a perception sensor, of an area where the vehicle is located, and fusing the current obstacle probability value of the obstacle of the sensing sensor for the measurement grid with the historical obstacle probability value of the measurement grid to obtain a target obstacle probability value of the measurement grid, and determining a drivable area of the area where the vehicle is located according to the target obstacle probability value. According to the method, the accuracy of generating the drivable area and the safety and reliability of the vehicle are improved.

Description

Technical Field

[0001] The present application relates to the field of vehicles, and more specifically, to a method, device, storage medium, and vehicle for determining a drivable area in the field of vehicles. Background Art

[0002] With the popularization of vehicles, more and more people choose to drive. However, when driving on some narrow and complex roads, there are blind spots in the field of vision, which makes the vehicle likely to be scratched, resulting in safety hazards during driving. Therefore, improving the vehicle's ability to judge the drivable area has become an urgent problem to be solved. Summary of the Invention

[0003] The present application provides a method, device, storage medium, and vehicle for determining a drivable area. The method can obtain target obstacle probability values ​​for obstacles included in a measurement grid by combining current data and historical data, and determine the vehicle's drivable area based on the target obstacle probability values, thereby improving the accuracy of generating the drivable area and the safety and reliability of the vehicle.

[0004] In a first aspect, a method for determining a drivable area is provided, which is applied to a vehicle and includes:

[0005] Obtaining obstacle measurement points in the area where the vehicle is located based on a perception sensor, and determining a measurement grid corresponding to the obstacle measurement point in a preset grid map;

[0006] Determining a current obstacle probability value of the perception sensor for the measurement grid based on a preset probability algorithm;

[0007] Determining a target obstacle probability value of the measurement grid based on the current obstacle probability value and a historical obstacle probability value of the perception sensor for the measurement grid; the historical obstacle probability value is an obstacle probability value determined by the perception sensor for the measurement grid within a historical detection period;

[0008] A drivable area of ​​the vehicle is determined in the area based on the target obstacle probability value.

[0009] Through the above technical solution, the current obstacle probability value of the obstacle can be determined by judging the measurement grid corresponding to the obstacle measurement point, and then the target obstacle probability value can be obtained by combining the historical obstacle probability values. Thus, by combining the current data and historical data, the target obstacle probability value of the measurement grid including the obstacle is obtained, and the vehicle's drivable area is determined based on the target obstacle probability value, thereby improving the accuracy of generating the drivable area, as well as the safety and reliability of the vehicle.

[0010] In conjunction with the first aspect, in some possible implementations, the perception sensor is an ultrasonic sensor, and determining the measurement grid corresponding to the obstacle measurement point in a preset grid map includes:

[0011] Determine, based on the first position corresponding to the obstacle measurement point, a second position corresponding to the perception sensor, where the grid where the first position is located is a first grid;

[0012] A connection line is established between the first position and the second position, a second grid that the connection line passes through within a first preset distance is determined, and the first grid and the second grid are determined as measurement grids.

[0013] Through the above technical solution, it is possible to determine the measurement grid by adopting corresponding judgment methods for different perception sensors, thereby improving the compatibility with different perception sensors and the accuracy of the determined measurement grid.

[0014] In combination with the first aspect and the above implementation manner, in some possible implementation manners, determining the current obstacle probability value of the perception sensor for the measurement grid based on a preset probability algorithm includes:

[0015] Determining a first obstacle probability value of the perception sensor for the first grid based on a preset probability algorithm;

[0016] A second obstacle probability value corresponding to the second grid is obtained based on a preset attenuation probability value, the first obstacle probability value, and a distance between the first grid and each of the second grids.

[0017] Through the above technical solution, for the measurement grid corresponding to the ultrasonic sensor, a corresponding calculation method is used to determine the current obstacle probability value corresponding to the measurement grid, so as to improve the compatibility with different perception sensors and the accuracy of the determined current obstacle probability value.

[0018] In combination with the first aspect and the above implementation manner, in some possible implementation manners, determining the target obstacle probability value of the measurement grid based on the current obstacle probability value and the historical obstacle probability value of the perception sensor for the measurement grid includes:

[0019] Obtaining a first historical obstacle probability value corresponding to the first grid by the perception sensor, obtaining a first measured obstacle probability value based on the first historical obstacle probability value and the first obstacle probability value using a Bayesian formula, and obtaining a first target obstacle probability value for the first grid based on the first measured obstacle probability value using a logic function;

[0020] Obtain a second historical obstacle probability value corresponding to the second grid by the perception sensor, obtain a second measured obstacle probability value based on the second historical obstacle probability value and the second obstacle probability value using a Bayesian formula, and obtain a second target obstacle probability value for the second grid based on the second measured obstacle probability value using a logic function.

[0021] Through the above technical solution, the current obstacle probability value and the historical obstacle probability values ​​are combined to obtain the target obstacle probability value that the measurement grid includes obstacles. Therefore, by combining the detection data over a period of time, the target obstacle probability value of whether the measurement grid contains obstacles is obtained, thereby improving the accuracy of the obtained target obstacle probability value.

[0022] In combination with the first aspect and the above implementations, in some possible implementations, the perception sensor is a visual sensor, and determining the target obstacle probability value of the measurement grid based on the current obstacle probability value and the historical obstacle probability values ​​of the perception sensor for the measurement grid includes:

[0023] Obtaining a historical obstacle probability value corresponding to the measurement grid from the perception sensor, and obtaining a measured obstacle probability value corresponding to the measurement grid using a Bayesian formula based on the historical obstacle probability value and the current obstacle probability value;

[0024] A logic function is used to obtain a target obstacle probability value of the measurement grid based on the measured obstacle probability value.

[0025] In combination with the first aspect and the above implementation manner, in some possible implementation manners, the number of the perception sensors is multiple, and determining the target obstacle probability value of the measurement grid based on the current obstacle probability value and the historical obstacle probability values ​​of the perception sensors for the measurement grid includes:

[0026] determining a measured obstacle probability value of the perception sensor for the measurement grid based on the current obstacle probability value and a historical obstacle probability value of the perception sensor for the measurement grid;

[0027] The measured obstacle probability values ​​corresponding to each of the perception sensors are fused to obtain a target obstacle probability value corresponding to the measurement grid.

[0028] Through the above technical solution, the measured obstacle probability values ​​corresponding to multiple perception sensors are fused to obtain the target obstacle probability value of the measurement grid. Therefore, by combining the detection data of multiple perception sensors, the target obstacle probability value for the measurement grid is determined, thereby improving the accuracy of the obtained target obstacle probability value.

[0029] In combination with the first aspect and the above implementation, in some possible implementations, fusing the measured obstacle probability values ​​corresponding to the perception sensors to obtain the target obstacle probability value corresponding to the measurement grid includes:

[0030] Perform weighted averaging on the measured obstacle probability values ​​to obtain the target obstacle probability value of the measurement grid; or

[0031] A maximum value among the measured obstacle probability values ​​is determined, and the maximum value is determined as the target obstacle probability value of the measurement grid.

[0032] In combination with the first aspect and the above implementation manner, in some possible implementation manners, determining the drivable area of ​​the vehicle in the area based on the target obstacle probability value includes:

[0033] Determining a target grid in each of the measurement grids based on a preset probability threshold and the target obstacle probability value corresponding to each of the measurement grids;

[0034] Acquire target measurement points in the target grid, and generate obstacle areas based on each of the target measurement points;

[0035] A drivable area of ​​the vehicle is determined based on the obstacle area.

[0036] Through the above technical solution, the obstacle area is determined according to the target measurement points in the determined target grid, and the drivable area that meets the vehicle driving needs is determined based on the obstacle area, so that it is convenient for users to view the drivable area and drive the vehicle, providing users with more considerate services, thereby improving the user experience and vehicle reliability.

[0037] In combination with the first aspect and the above implementation manner, in some possible implementation manners, obtaining the target measurement points in the target grid and generating the obstacle area based on each of the target measurement points includes:

[0038] Target measurement points in the target grid are acquired, and a preset convex hull algorithm is used to perform convex hull processing on the target measurement points whose distance is less than a second preset distance to generate an obstacle area.

[0039] In combination with the first aspect and the above implementation manner, in some possible implementation manners, determining the drivable area of ​​the vehicle based on the obstacle area includes:

[0040] Mapping the obstacle area to a real-world map of the vehicle to obtain the vehicle size of the vehicle;

[0041] Based on the obstacle area and the vehicle size, a drivable area of ​​the vehicle is determined in the real-world map.

[0042] Through the above technical solution, judgment is made based on the obstacle area, the real-life map, and the size of the vehicle, and the drivable area that meets the vehicle's driving needs is determined in the real-life map, thereby making it easier for users to view the drivable area and drive the vehicle, providing users with more considerate services, thereby improving the user experience and vehicle reliability.

[0043] In a second aspect, a device for determining a drivable area is provided, which is applied to a vehicle, and includes:

[0044] a grid determination unit, configured to obtain obstacle measurement points in the area where the vehicle is located based on a perception sensor, and determine a measurement grid corresponding to the obstacle measurement point in a preset grid map;

[0045] a current probability value determining unit, configured to determine a current obstacle probability value of the perception sensor for the measurement grid based on a preset probability algorithm;

[0046] a target probability value determining unit, configured to determine a target obstacle probability value for the measurement grid based on the current obstacle probability value and a historical obstacle probability value of the perception sensor for the measurement grid; the historical obstacle probability value being an obstacle probability value determined by the perception sensor for the measurement grid within a historical detection period;

[0047] An area determination unit is configured to determine a drivable area of ​​the vehicle in the area based on the target obstacle probability value.

[0048] In a third aspect, a vehicle is provided, comprising a memory for storing executable program code;

[0049] A processor is used to call and run the executable program code from the memory, so that the vehicle executes the method in the first aspect or any possible implementation of the first aspect.

[0050] In a fourth aspect, a computer program product is provided, comprising: a computer program code, which, when executed on a computer, enables the computer to execute the method in the first aspect or any possible implementation of the first aspect.

[0051] In a fifth aspect, a computer-readable storage medium is provided, which stores a computer program code. When the computer program code runs on a computer, the computer executes the method in the above-mentioned first aspect or any possible implementation of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1This is a system architecture diagram of a method for determining a drivable area provided in an embodiment of the present application;

[0053] Figure 2 This is a flow chart of a method for determining a drivable area provided in an embodiment of the present application;

[0054] Figure 3 This is a flow chart of a method for determining a drivable area provided in an embodiment of the present application;

[0055] Figure 4 This is a schematic diagram of an example of determining a measurement grid provided in an embodiment of the present application;

[0056] Figure 5 This is a schematic diagram of an example of determining a target grid provided in an embodiment of the present application;

[0057] Figure 6 This is an example schematic diagram of determining an obstacle area provided by an embodiment of the present application;

[0058] Figure 7 This is an example schematic diagram of determining a drivable area provided in an embodiment of the present application;

[0059] Figure 8 Schematic diagram of a device for determining a drivable area provided in an embodiment of the present application;

[0060] Figure 9 It is a structural schematic diagram of a vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0061] The following will clearly and thoroughly describe the technical solutions in this application in conjunction with the accompanying drawings. In the description of the embodiments of this application, unless otherwise specified, " / " means or, for example, A / B can mean A or B: "and / or" in the text is only a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of this application, "multiple" means two or more than two.

[0062] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to imply or suggest relative importance or implicitly indicate the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features.

[0063] Figure 1 This is a system architecture diagram of a method for determining a drivable area provided in an embodiment of the present application. Figure 1As shown, the method for determining a drivable area provided in the embodiment of the present application can be applied to a vehicle to implement the process of determining a drivable area. The system architecture provided in the embodiment of this specification mainly includes a vehicle 10, a perception sensor 11 in the vehicle 10, and a drivable area 20. The vehicle 10 can be a motor vehicle, such as a fuel vehicle, a hybrid vehicle, or an electric vehicle. The perception sensor 11 can be a sensor that uses a wireless method to measure the distance or position between objects and is used to detect environmental features included in the area where the vehicle is located. For example, it can be a visual sensor, an ultrasonic sensor, etc. The drivable area 20 can be an area in the area where the vehicle is located that meets driving requirements.

[0064] In related technologies, when judging the vehicle's drivable area, the method adopted is to obtain detection areas based on images or echo signals detected by radar, and fuse the detection areas to obtain the vehicle's drivable area. However, due to different detection methods, there are problems such as glitches and jumps when fusing the detection areas, resulting in insufficient accuracy of the obtained drivable area and the inability to effectively reduce the risk of vehicle accidents.

[0065] In an embodiment of the present application, obstacle measurement points of the area where the vehicle 10 is located are obtained based on the perception sensor 11, a measurement grid corresponding to the obstacle measurement point is determined in a preset grid map, a current obstacle probability value of the perception sensor 11 for the measurement grid is determined based on a preset probability algorithm, a target obstacle probability value of the measurement grid is determined based on the current obstacle probability value and the historical obstacle probability value of the perception sensor 11 for the measurement grid, and a drivable area 20 of the vehicle 10 is determined in the area based on the target obstacle probability value. Thus, by combining current data and historical data, a target obstacle probability value of the measurement grid including obstacles is obtained, and the drivable area of ​​the vehicle is determined based on the target obstacle probability value, thereby improving the accuracy of generating the drivable area, as well as the safety and reliability of the vehicle.

[0066] based on Figure 1 The system architecture shown below will be combined with Figure 2-Figure 7 , a detailed introduction is given to the method for determining the drivable area provided in the embodiment of the present application.

[0067] See Figure 2 , provides a flow chart of a method for determining a drivable area according to an embodiment of the present application. Figure 2 As shown, the method of the embodiment of the present application may include the following steps S101 to S104.

[0068] S101, obtaining obstacle measurement points in the area where the vehicle is located based on a perception sensor, and determining measurement grids corresponding to the obstacle measurement points in a preset grid map;

[0069] In one embodiment, based on the perception sensors installed in the vehicle, the surrounding environment of the area where the vehicle is located is detected, and the obstacle measurement points detected by the perception sensors are obtained. The perception sensors can be sensors that use wireless methods to measure the distance or position between objects, and are used to detect the environmental characteristics of the area where the vehicle is located. The type of perception sensor can be set according to actual conditions, for example, it can be a visual sensor, an ultrasonic sensor, etc. The obstacle measurement point can be the point position of the obstacle detected by the perception sensor. The obstacle measurement point is mapped to a preset grid map, and the measurement grid corresponding to the measurement point is determined in the grid map. The grid map can be a pre-established map composed of grids of the same size, and each grid in the pre-established grid map can be a blank grid. The measurement grid can be the grid where the mapping point corresponding to the obstacle measurement point is located when the obstacle measurement point is mapped to the grid map.

[0070] The grid map can be a map generated by radiating the vehicle's location around the vehicle. Since the grid cells in the grid map are all the same size, the coordinate system of the grid map can be defined based on the vehicle coordinate system, thereby locating each grid cell in the grid map. It is understood that the coordinate system of the grid map can also be defined based on the world coordinate system, and the specific setting can be based on actual conditions.

[0071] S102, determining a current obstacle probability value of the perception sensor for the measurement grid based on a preset probability algorithm;

[0072] In one embodiment, a current obstacle probability value is determined by a sensor calculation for the measurement grid based on a preset probability algorithm. The preset probability algorithm may be an algorithm for calculating the probability that the measurement grid includes an obstacle, and the specific algorithm used may be set based on actual circumstances. The current obstacle probability value may be a numerical value representing the probability that the measurement grid includes an obstacle, determined based on currently detected data. The larger the current obstacle probability value, the greater the likelihood that the measurement grid includes an obstacle.

[0073] S103, determining a target obstacle probability value of the measurement grid based on the current obstacle probability value and the historical obstacle probability values ​​of the perception sensor for the measurement grid;

[0074] In one embodiment, a sensor obtains historical obstacle probability values ​​for the measurement grid. The historical obstacle probability values ​​may be obstacle probability values ​​determined by the sensor for the measurement grid during a historical detection period. The historical detection period may be the duration over which the indicated probability values ​​are accumulated. A target obstacle probability value for the measurement grid is obtained by performing a fusion calculation based on the current obstacle probability value and the historical obstacle probability values. The target obstacle probability value may be a value obtained by integrating historical data with current data and is used to indicate the probability that the measurement grid contains an obstacle.

[0075] Among them, based on the current obstacle probability value and the historical obstacle probability value, the method of determining the target obstacle probability value can be processed according to the Bayesian formula, logical function, or combined according to other complicated methods. The specific setting can be made according to the actual situation.

[0076] It is understandable that the possibility of misidentification based on only a single frame of data is greater than the functionality of misidentification based on multiple frames of data. Therefore, combining historical data with current data for comprehensive judgment can improve the accuracy of the judgment results. If the historical detection time is too long, the judgment result may be incorrect due to excessive historical data and too small a proportion of current data. Therefore, the specific value of the historical detection time can be set according to the actual situation, for example, it can be 3 frames or 5 frames.

[0077] S104, determining a drivable area of ​​the vehicle in the area based on the target obstacle probability value;

[0078] In one embodiment, based on the target obstacle probability value, a drivable area of ​​the vehicle is determined in the area the vehicle is located in. The drivable area may be an area that represents a region that meets the vehicle's drivability requirements, such as a road, a parking space, etc.

[0079] The method for determining the drivable area of ​​the vehicle based on the target obstacle probability value may be: determining an obstacle area including obstacles in the area where the vehicle is located based on the target obstacle probability value, and then obtaining the drivable area of ​​the vehicle based on the obstacle area.

[0080] In an embodiment of the present application, the current obstacle probability value of the obstacle is obtained by judging the measurement grid corresponding to the obstacle measurement point, and then the target obstacle probability value is obtained by combining the historical obstacle probability values. Thus, by combining the current data and the historical data, the target obstacle probability value of the measurement grid including the obstacle is obtained, and the drivable area of ​​the vehicle is determined based on the target obstacle probability value, thereby improving the accuracy of generating the drivable area, as well as the safety and reliability of the vehicle.

[0081] The following will be combined Figure 3A specific example of a method for determining a drivable area provided in an embodiment of the present application is described in detail. Figure 3 As shown, the method of the embodiment of the present application may include the following steps S201 to S206.

[0082] S201, obtaining obstacle measurement points in the area where the vehicle is located based on a perception sensor, and determining measurement grids corresponding to the obstacle measurement points in a preset grid map;

[0083] In one embodiment, a perception sensor installed in a vehicle detects the surrounding environment of the vehicle's area and obtains obstacle measurement points detected by the perception sensor. The perception sensor can be a sensor that wirelessly measures the distance or position between objects and is used to detect environmental characteristics of the vehicle's area. The type of perception sensor can be set according to actual circumstances, such as a visual sensor, an ultrasonic sensor, etc. The obstacle measurement point can be the location of an obstacle detected by the perception sensor. The obstacle measurement point is mapped to a preset grid map, and the measurement grid corresponding to the measurement point is determined in the grid map. The grid map can be a pre-established map composed of grids of equal size. Each grid in the pre-established grid map can be a blank grid. The grid size can be set according to actual circumstances, such as a 10 cm x 10 cm rectangle. The measurement grid can be the grid where the mapping point corresponding to the obstacle measurement point is located when the obstacle measurement point is mapped to the grid map.

[0084] If the perception sensor is a visual sensor, the grid where the mapping point corresponding to the obstacle measurement point is located is determined as the measurement grid. If the perception sensor is an ultrasonic sensor, in addition to determining the grid where the mapping point corresponding to the obstacle measurement point is located as the measurement grid, the grids adjacent to the mapping point can also be determined as the measurement grid.

[0085] Exemplarily, the method for determining the measurement grid may be: based on the first position corresponding to the obstacle measurement point, determine the second position corresponding to the perception sensor, and the grid where the first position is located is the first grid. Establish a connection line between the first position and the second position, determine the second grid that the connection line passes through within a first preset distance, and determine the first grid and the second grid as the measurement grid. The first position may be the position of the mapping point corresponding to the obstacle measurement point after mapping the obstacle measurement point to the measurement grid. Since the perception sensor is an ultrasonic sensor, the second position where the perception sensor is located can be calculated based on the first position by direct echo or indirect echo. The first preset distance can be used to determine the length of the second grid. The value of the first preset distance can be set according to the physical distance, for example, it can be 15 centimeters, or it can be set according to the size or number of the grids, for example, it can be one grid, 1.5 grids, etc., and can be set according to actual conditions. It should be noted that since a connecting line is established between the first position and the second position, the grids passed from the second position to the first preset distance and the grids passed from the first position to the first preset distance can be determined on the connecting line, and all the second grids passed and the grid at the second position are determined as measurement grids.

[0086] For example, Figure 4 As shown, Figure 4 After establishing a line between the first position and the second position, the grid at the first position is determined as the first grid, and the grids on the line between the second position and the first position, starting from the second position, close to the first position by a first preset distance (one grid) and away from the first position by the first preset distance, and the grid at the second position are determined as the second grid.

[0087] S202, determining a current obstacle probability value of the perception sensor for the measurement grid based on a preset probability algorithm;

[0088] In one embodiment, a current obstacle probability value is determined by a sensor calculation for the measurement grid based on a preset probability algorithm. The preset probability algorithm may be an algorithm for calculating the probability that the measurement grid includes an obstacle, and the specific algorithm used may be set based on actual circumstances. The current obstacle probability value may be a numerical value representing the probability that the measurement grid includes an obstacle, determined based on currently detected data. The larger the current obstacle probability value, the greater the likelihood that the measurement grid includes an obstacle.

[0089] Furthermore, if the perception sensor is an ultrasonic sensor, the current obstacle probability value may be obtained by determining, for the first grid in the measurement grid, a first obstacle probability value of the perception sensor for the first grid based on a preset probability algorithm, and obtaining, for the second grid, a second obstacle probability value corresponding to the second grid based on a preset attenuation probability value, the first obstacle probability value, and the distance between the first grid and each second grid. The preset attenuation probability value may be a preset value for the attenuation probability value per unit grid, for example, a value that attenuates by 0.1 for each grid closer to or farther from the first position, starting from the second position. The specific value of the preset attenuation probability value may be set based on actual circumstances.

[0090] For example, if Figure 4 The second obstacle probability value of the second grid at the second position is 0.5, the preset attenuation probability value is 0.1, and the other two second obstacle probability values ​​are 0.4.

[0091] It should be noted that if a measurement grid includes mapping points corresponding to multiple obstacle measurement points, the perception sensor processes each mapping point separately to obtain a second grid corresponding to each mapping point.

[0092] Furthermore, after determining the current obstacle probability value of the perception sensor for the measurement grid, the current obstacle probability value is stored according to the measurement grid, so that the obstacle probability value corresponding to the measurement grid can be obtained later according to the spatial index of the measurement grid.

[0093] S203, determining a target obstacle probability value of the measurement grid based on the current obstacle probability value and the historical obstacle probability values ​​of the perception sensor for the measurement grid;

[0094] In one embodiment, historical obstacle probability values ​​corresponding to the measurement grid are obtained from the perception sensor. A Bayesian formula is used based on the historical and current obstacle probability values ​​to determine the corresponding obstacle probability values ​​for each measurement. A logical function is then used to determine the target obstacle probability value for the measurement grid based on the measured obstacle probability values. The historical obstacle probability values ​​may be obstacle probability values ​​determined by the perception sensor for the measurement grid during a historical detection period. The target obstacle probability value may be a combination of historical and current data, representing the probability that the measurement grid contains an obstacle.

[0095] It is understandable that the possibility of misidentification based on only a single frame of data is greater than the functionality of misidentification based on multiple frames of data. Therefore, combining historical data with current data for comprehensive judgment can improve the accuracy of the judgment results. If the historical detection time is too long, the judgment result may be incorrect due to excessive historical data and too small a proportion of current data. Therefore, the specific value of the historical detection time can be set according to the actual situation, for example, it can be 3 frames or 5 frames.

[0096] Specifically, the method for obtaining the historical obstacle probability value may be: obtaining at least one obstacle detection probability value determined by the perception sensor for the measurement grid within the historical detection time, and fusing the obstacle detection probability values. The fusion method may be weighted average, etc., which may be set specifically according to the actual situation. The obstacle detection probability value may be the target obstacle detection probability value determined by the perception sensor for the measurement grid at each time unit of the historical detection time. For example, if the historical detection time is three frames, the target obstacle probability value corresponding to the measurement grid of each frame of the perception sensor is determined as the obstacle detection probability value, and the historical obstacle probability value is obtained by fusing the three obstacle detection probability values. It is understandable that if the perception sensor includes a mapping point corresponding to an obstacle measurement point for the measurement grid in a certain frame, then the obstacle detection probability value of the perception sensor for the measurement grid in the frame is 0.

[0097] The Bayesian formula can be used to fuse historical obstacle probability values ​​and current obstacle probability values, so as to combine current data with historical data and improve the accuracy of the obtained obstacle probability values.

[0098] The logic function can be used to further process the measured obstacle probability value to improve the numerical stability of the obtained target obstacle probability value. The logic function can be specifically a logit function, and the expression of the logit function can be a formula shown in formula (1).

[0099]

[0100] Where p is the probability of measuring an obstacle. It should be noted that the logistic function converts the probability of measuring an obstacle calculated using the Bayesian formula from a ratio to a logarithmic form, simplifying the calculation logic and avoiding the vanishing gradient problem when dealing with binary classification problems.

[0101] Furthermore, if the perception sensor is an ultrasonic sensor, the target obstacle probability value may be determined by obtaining a first historical obstacle probability value corresponding to a first grid cell from the perception sensor, applying a Bayesian formula based on the first historical obstacle probability value and the first obstacle probability value to obtain a first measured obstacle probability value, and applying a logic function based on the first measured obstacle probability value to obtain a first target obstacle probability value for the first grid cell. Furthermore, obtaining a second historical obstacle probability value corresponding to a second grid cell from the perception sensor, applying a Bayesian formula based on the second historical obstacle probability value and the second obstacle probability value to obtain a second measured obstacle probability value, and applying a logic function based on the second measured obstacle probability value to obtain a second target obstacle probability value for the second grid cell.

[0102] Furthermore, if there are multiple perception sensors installed on the vehicle, the method for determining the target obstacle probability value of the measurement grid can be: based on the current obstacle probability value and the historical obstacle probability value of the perception sensor for the measurement grid, determine the measurement obstacle probability value of the perception sensor for the measurement grid, and fuse the measurement obstacle probability values ​​corresponding to each perception sensor to obtain the target obstacle probability value corresponding to the measurement grid.

[0103] Specifically, the obstacle probability values ​​measured by each sensor can be integrated by taking a weighted average of the values ​​to obtain the target obstacle probability value for the measurement grid. The weights of the obstacle probability values ​​can be determined based on the type of sensor, its location in the vehicle, and other factors, and can be adjusted based on actual circumstances.

[0104] For example, the vehicle includes a visual sensor and an ultrasonic sensor, the weight of the visual sensor is 0.6, the weight of the ultrasonic sensor is 0.4, the obstacle probability value measured by the visual sensor for the measurement grid is 0.6, and the obstacle probability value measured by the ultrasonic sensor for the measurement grid is 0.5, then the target obstacle probability value of the measurement grid is 0.6*0.6+0.4*0.5=0.56.

[0105] Optionally, the fusion method may also be: determining the maximum value among the measured obstacle probability values, and determining the maximum value as the target obstacle probability value of the measurement grid.

[0106] Exemplarily, the vehicle includes a visual sensor and an ultrasonic sensor. The visual sensor's obstacle probability value for the measurement grid is 0.6, and the ultrasonic sensor's obstacle probability value for the measurement grid is 0.5. The maximum value of 0.6 and 0.5, 0.6, is determined as the target obstacle probability value of the measurement grid.

[0107] It should be noted that after obtaining the target obstacle probability value of the measurement grid, the target obstacle probability value is stored according to the spatial index of the measurement grid so as to be used in the next frame to determine the historical obstacle probability value corresponding to the measurement grid.

[0108] S204, determining a target grid in each measurement grid based on a preset probability threshold and a target obstacle probability value corresponding to each measurement grid;

[0109] In one embodiment, each measurement grid is screened based on a comparison between a preset probability threshold and the target obstacle probability value corresponding to each measurement grid, and a target grid is determined. The preset probability threshold may be a probability value used to screen the measurement grids, and the specific value of the preset probability threshold may be set according to actual conditions.

[0110] For example, Figure 5 As shown, the preset probability threshold is 0.5, and the preset probability threshold is compared with the target obstacle probability value of each measurement network one by one. Figure 5 The measurement grid with a target obstacle probability value greater than or equal to the preset probability threshold of 0.5 is determined as the target grid.

[0111] S205, obtaining target measurement points in the target grid, and generating an obstacle area based on each target measurement point;

[0112] In one embodiment, a target measurement point in a target grid is obtained. The target measurement point may be a mapping point corresponding to an obstacle measurement point included in the target grid. A preset convex hull algorithm is used to perform convex hull processing on target measurement points whose distance is less than a second preset distance to generate an obstacle area. The convex hull algorithm may be an algorithm for constructing a convex hull for a set of points to obtain a concise convex polygon boundary. After the convex polygon boundary is obtained according to the convex hull algorithm, the convex polygon boundary is determined as an obstacle area. The generated obstacle area includes target measurement points whose distance is less than the second preset distance. The obstacle area may be an area that characterizes obstacles, for example, an area where obstacles such as walls and roadblocks are located. The second preset distance may be the distance of the target measurement point used to determine the generation of the obstacle area. The specific value of the second preset distance may be set according to actual conditions, for example, it may be 3 centimeters.

[0113] It should be noted that when performing convex hull processing on the target measurement points, target measurement points whose distance from each other is less than a second preset distance are used to construct a point set for the same region, and the convex hull processing is performed on the target measurement points included in the point set. Determining whether a point set belongs to the same region can be performed by obtaining the distance between any target measurement point and other target measurement points. If there are other target measurement points whose distance is less than the second preset distance, the target measurement point and the other target measurement point are determined to belong to the same region.

[0114] Optionally, if the distance between the target measurement point and any target measurement point is greater than the second preset distance, the target measurement point is ignored, or the grid where the target measurement point is located is determined as an obstacle area.

[0115] For example, Figure 6 As shown, Figure 6 The target measurement points are scattered in each target grid. Figure 6 The target measurement points shown can be determined to include four areas. Convex hull processing is performed on the target measurement points in each area to obtain four obstacle areas.

[0116] S206, determining a drivable area of ​​the vehicle based on the obstacle area;

[0117] In one embodiment, the obstacle area is mapped to the real-life map where the vehicle is located, the vehicle size is obtained, and based on the obstacle area and the vehicle size, the drivable area of ​​the vehicle is determined in the real-life map. The real-life map may be a map including a real street scene corresponding to the area where the vehicle is located. The size of the vehicle may be data representing the body shape of the vehicle, for example, the length and width of the vehicle. Based on the obstacle area and the size of the vehicle, it can be determined whether the vehicle can travel in the area formed between different obstacle areas. If the area between different obstacles meets the driving requirements of the vehicle, the area is determined as a drivable area. In order to facilitate user viewing, the drivable area is displayed in the real-life map.

[0118] For example, Figure 7 As shown, Figure 7 The obstacle areas in the real scene map are mapped to the real scene map, and the areas between the obstacle areas are judged according to the size of the vehicle to determine the drivable area in the real scene map that can meet the driving needs of the vehicle.

[0119] Optionally, in addition to mapping to the real-life map, it can also be mapped to a scene map generated by the vehicle. The scene map can be a map generated by the vehicle based on the real-life map. The specific generation method and display method of the scene map can be set according to actual conditions.

[0120] In the embodiment of the present application, the current obstacle probability value of the obstacle is determined by judging the measurement grid corresponding to the obstacle measurement point. This is then combined with historical obstacle probability values ​​to obtain a target obstacle probability value. By combining current and historical data, a target obstacle probability value for the obstacle included in the measurement grid is obtained. The vehicle's drivable area is then determined based on the target obstacle probability value, thereby improving the accuracy of the generated drivable area and the safety and reliability of the vehicle. Furthermore, corresponding judgment methods are used to determine the target grid for different perception sensors, thereby improving compatibility with different perception sensors and the accuracy of the determined drivable area. In addition, when a vehicle includes multiple perception sensors, the measured obstacle probability values ​​corresponding to each perception sensor are fused, so that the target grid is determined by combining the detection results of multiple perception sensors, the accuracy of the missing target grid is improved, and the reliability and safety of the vehicle are improved; further, the obstacle area is determined based on the target measurement points in the determined target grid, and a judgment is made based on the obstacle area and the size of the vehicle to obtain a drivable area that meets the vehicle's driving needs, thereby making it easier for users to view the drivable area and drive the vehicle, providing users with more considerate services, thereby improving the user experience and vehicle reliability.

[0121] based on Figure 1 The system architecture will be combined with Figure 8 , the drivable area determination device provided in the embodiment of the present application is introduced in detail. It should be noted that, Figure 8 The drivable area determination device in the present application is used to execute Figure 2-Figure 7 For the convenience of explanation, only the part related to the embodiment of the present application is shown. For the specific technical details not disclosed, please refer to the present application. Figure 2-Figure 7 The embodiment shown.

[0122] A grid determination unit 11 is configured to obtain obstacle measurement points in the area where the vehicle is located based on a perception sensor, and determine a measurement grid corresponding to the obstacle measurement point in a preset grid map;

[0123] a current probability value determining unit 12, configured to determine a current obstacle probability value of the perception sensor for the measurement grid based on a preset probability algorithm;

[0124] a target probability value determining unit 13, configured to determine a target obstacle probability value for the measurement grid based on the current obstacle probability value and a historical obstacle probability value of the perception sensor for the measurement grid; the historical obstacle probability value being an obstacle probability value determined by the perception sensor for the measurement grid within a historical detection period;

[0125] The area determination unit 14 is configured to determine a drivable area of ​​the vehicle in the area based on the target obstacle probability value.

[0126] Optionally, the grid determination unit 11 is further configured to:

[0127] Determine, based on the first position corresponding to the obstacle measurement point, a second position corresponding to the perception sensor, where the grid where the first position is located is a first grid;

[0128] A connection line is established between the first position and the second position, a second grid that the connection line passes through within a first preset distance is determined, and the first grid and the second grid are determined as measurement grids.

[0129] Optionally, the current probability value determining unit 12 is further configured to:

[0130] Determining a first obstacle probability value of the perception sensor for the first grid based on a preset probability algorithm;

[0131] A second obstacle probability value corresponding to the second grid is obtained based on a preset attenuation probability value, the first obstacle probability value, and a distance between the first grid and each of the second grids.

[0132] Optionally, the target probability value determining unit 13 is further configured to:

[0133] Obtaining a first historical obstacle probability value corresponding to the first grid by the perception sensor, obtaining a first measured obstacle probability value based on the first historical obstacle probability value and the first obstacle probability value using a Bayesian formula, and obtaining a first target obstacle probability value for the first grid based on the first measured obstacle probability value using a logic function;

[0134] Obtain a second historical obstacle probability value corresponding to the second grid by the perception sensor, obtain a second measured obstacle probability value based on the second historical obstacle probability value and the second obstacle probability value using a Bayesian formula, and obtain a second target obstacle probability value for the second grid based on the second measured obstacle probability value using a logic function.

[0135] Optionally, the target probability value determining unit 13 is further configured to:

[0136] Obtaining a historical obstacle probability value corresponding to the measurement grid from the perception sensor, and obtaining a measured obstacle probability value corresponding to the measurement grid using a Bayesian formula based on the historical obstacle probability value and the current obstacle probability value;

[0137] A logic function is used to obtain a target obstacle probability value of the measurement grid based on the measured obstacle probability value.

[0138] Optionally, the target probability value determining unit 13 is further configured to:

[0139] determining a measured obstacle probability value of the perception sensor for the measurement grid based on the current obstacle probability value and a historical obstacle probability value of the perception sensor for the measurement grid;

[0140] The measured obstacle probability values ​​corresponding to each of the perception sensors are fused to obtain a target obstacle probability value corresponding to the measurement grid.

[0141] Optionally, the target probability value determining unit 13 is further configured to:

[0142] Perform weighted averaging on the measured obstacle probability values ​​to obtain the target obstacle probability value of the measurement grid; or

[0143] A maximum value among the measured obstacle probability values ​​is determined, and the maximum value is determined as the target obstacle probability value of the measurement grid.

[0144] Optionally, the region determining unit 14 is further configured to:

[0145] Determining a target grid in each of the measurement grids based on a preset probability threshold and the target obstacle probability value corresponding to each of the measurement grids;

[0146] Acquire target measurement points in the target grid, and generate obstacle areas based on each of the target measurement points;

[0147] A drivable area of ​​the vehicle is determined based on the obstacle area.

[0148] Optionally, the region determining unit 14 is further configured to:

[0149] Target measurement points in the target grid are acquired, and a preset convex hull algorithm is used to perform convex hull processing on the target measurement points whose distance is less than a second preset distance to generate an obstacle area.

[0150] Optionally, the region determining unit 14 is further configured to:

[0151] Mapping the obstacle area to a real-world map of the vehicle to obtain the vehicle size of the vehicle;

[0152] Based on the obstacle area and the vehicle size, a drivable area of ​​the vehicle is determined in the real-world map.

[0153] In the embodiment of the present application, the current obstacle probability value of the obstacle is determined by judging the measurement grid corresponding to the obstacle measurement point. This is then combined with historical obstacle probability values ​​to obtain a target obstacle probability value. By combining current and historical data, a target obstacle probability value for the obstacle included in the measurement grid is obtained. The vehicle's drivable area is then determined based on the target obstacle probability value, thereby improving the accuracy of the generated drivable area and the safety and reliability of the vehicle. Furthermore, corresponding judgment methods are used to determine the target grid for different perception sensors, thereby improving compatibility with different perception sensors and the accuracy of the determined drivable area. In addition, when a vehicle includes multiple perception sensors, the measured obstacle probability values ​​corresponding to each perception sensor are fused, so that the target grid is determined by combining the detection results of multiple perception sensors, the accuracy of the missing target grid is improved, and the reliability and safety of the vehicle are improved; further, the obstacle area is determined based on the target measurement points in the determined target grid, and a judgment is made based on the obstacle area and the size of the vehicle to obtain a drivable area that meets the vehicle's driving needs, thereby making it easier for users to view the drivable area and drive the vehicle, providing users with more considerate services, thereby improving the user experience and vehicle reliability.

[0154] See Figure 9 , provides a structural diagram of a vehicle according to an embodiment of the present application. Figure 9 As shown, the vehicle 500 includes a processor 501 and a memory 502. The processor 501 is electrically connected to the memory 502.

[0155] Processor 501 is the control center of vehicle 500 and may include one or more processing cores. Processor 501 utilizes various interfaces and circuits to connect various components of vehicle 500. By running or invoking computer programs stored in memory 502 and accessing data stored in memory 502, it executes various functions of vehicle 500 and processes data, thereby providing overall control over vehicle 500. Optionally, processor 501 may be implemented using at least one of the following hardware forms: digital signal processing (DSP), field programmable gate array (FPGA), or programmable logic array (PLA). Processor 501 may integrate one or a combination of a CPU, a graphics processing unit (GPU), and a modem. The CPU primarily processes the operating system, user interfaces, and applications; the GPU is responsible for rendering and drawing display content; and the modem handles wireless communications. It is understood that the modem may not be integrated into processor 501 and may instead be implemented via a separate communications chip.

[0156] Memory 502 can be used to store software programs and modules. Processor 501 executes various functional applications and data processing by running the computer programs and modules stored in memory 502. Memory 502 may primarily include a program storage area and a data storage area. The program storage area may store an operating system, computer programs required for at least one function, and the like; the data storage area may store data generated based on the use of vehicle 500.

[0157] In addition, the memory 502 may include a high-speed random access memory and a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device. Accordingly, the memory 502 may also include a memory controller to provide the processor 501 with access to the memory 502.

[0158] In this embodiment, the processor 501 in the vehicle 500 loads instructions corresponding to one or more computer program processes into the memory 502 according to the following steps, and the processor 501 runs the computer program stored in the memory 502 to implement various functions as follows:

[0159] Obtaining obstacle measurement points in the area where the vehicle is located based on a perception sensor, and determining a measurement grid corresponding to the obstacle measurement point in a preset grid map;

[0160] Determining a current obstacle probability value of the perception sensor for the measurement grid based on a preset probability algorithm;

[0161] Determining a target obstacle probability value of the measurement grid based on the current obstacle probability value and a historical obstacle probability value of the perception sensor for the measurement grid; the historical obstacle probability value is an obstacle probability value determined by the perception sensor for the measurement grid within a historical detection period;

[0162] A drivable area of ​​the vehicle is determined in the area based on the target obstacle probability value.

[0163] Optionally, when the sensing sensor is an ultrasonic sensor, the processor 501 specifically performs the following when determining the measurement grid corresponding to the obstacle measurement point in the preset grid map:

[0164] Determine, based on the first position corresponding to the obstacle measurement point, a second position corresponding to the perception sensor, where the grid where the first position is located is a first grid;

[0165] A connection line is established between the first position and the second position, a second grid that the connection line passes through within a first preset distance is determined, and the first grid and the second grid are determined as measurement grids.

[0166] Optionally, when the processor 501 determines the current obstacle probability value of the perception sensor for the measurement grid based on a preset probability algorithm, the processor 501 specifically performs:

[0167] Determining a first obstacle probability value of the perception sensor for the first grid based on a preset probability algorithm;

[0168] A second obstacle probability value corresponding to the second grid is obtained based on a preset attenuation probability value, the first obstacle probability value, and a distance between the first grid and each of the second grids.

[0169] Optionally, when determining the target obstacle probability value of the measurement grid based on the current obstacle probability value and the historical obstacle probability value of the perception sensor for the measurement grid, the processor 501 specifically performs:

[0170] Obtaining a first historical obstacle probability value corresponding to the first grid by the perception sensor, obtaining a first measured obstacle probability value based on the first historical obstacle probability value and the first obstacle probability value using a Bayesian formula, and obtaining a first target obstacle probability value for the first grid based on the first measured obstacle probability value using a logic function;

[0171] Obtain a second historical obstacle probability value corresponding to the second grid by the perception sensor, obtain a second measured obstacle probability value based on the second historical obstacle probability value and the second obstacle probability value using a Bayesian formula, and obtain a second target obstacle probability value for the second grid based on the second measured obstacle probability value using a logic function.

[0172] Optionally, when the perception sensor is a visual sensor, the processor 501 determines the target obstacle probability value of the measurement grid based on the current obstacle probability value and the historical obstacle probability value of the perception sensor for the measurement grid, specifically performing:

[0173] Obtaining a historical obstacle probability value corresponding to the measurement grid from the perception sensor, and obtaining a measured obstacle probability value corresponding to the measurement grid using a Bayesian formula based on the historical obstacle probability value and the current obstacle probability value;

[0174] A logic function is used to obtain a target obstacle probability value of the measurement grid based on the measured obstacle probability value.

[0175] Optionally, when there are multiple perception sensors, the processor 501, when determining the target obstacle probability value of the measurement grid based on the current obstacle probability value and the historical obstacle probability values ​​of the perception sensors for the measurement grid, specifically executes:

[0176] determining a measured obstacle probability value of the perception sensor for the measurement grid based on the current obstacle probability value and a historical obstacle probability value of the perception sensor for the measurement grid;

[0177] The measured obstacle probability values ​​corresponding to each of the perception sensors are fused to obtain a target obstacle probability value corresponding to the measurement grid.

[0178] Optionally, when the processor 501 performs the fusion of the measured obstacle probability values ​​corresponding to the perception sensors to obtain the target obstacle probability value corresponding to the measurement grid, the processor 501 specifically performs:

[0179] Perform weighted averaging on the measured obstacle probability values ​​to obtain the target obstacle probability value of the measurement grid; or

[0180] A maximum value among the measured obstacle probability values ​​is determined, and the maximum value is determined as the target obstacle probability value of the measurement grid.

[0181] Optionally, when determining the drivable area of ​​the vehicle in the area based on the target obstacle probability value, the processor 501 specifically performs:

[0182] Determining a target grid in each of the measurement grids based on a preset probability threshold and the target obstacle probability value corresponding to each of the measurement grids;

[0183] Acquire target measurement points in the target grid, and generate obstacle areas based on each of the target measurement points;

[0184] A drivable area of ​​the vehicle is determined based on the obstacle area.

[0185] Optionally, when executing acquiring the target measurement points in the target grid and generating the obstacle area based on each of the target measurement points, the processor 501 specifically executes:

[0186] Target measurement points in the target grid are acquired, and a preset convex hull algorithm is used to perform convex hull processing on the target measurement points whose distance is less than a second preset distance to generate an obstacle area.

[0187] Optionally, when determining the drivable area of ​​the vehicle based on the obstacle area, the processor 501 specifically performs:

[0188] Mapping the obstacle area to a real-world map of the vehicle to obtain the vehicle size of the vehicle;

[0189] Based on the obstacle area and the vehicle size, a drivable area of ​​the vehicle is determined in the real-world map.

[0190] In the embodiment of the present application, the current obstacle probability value of the obstacle is determined by judging the measurement grid corresponding to the obstacle measurement point. This is then combined with historical obstacle probability values ​​to obtain a target obstacle probability value. By combining current and historical data, a target obstacle probability value for the obstacle included in the measurement grid is obtained. The vehicle's drivable area is then determined based on the target obstacle probability value, thereby improving the accuracy of the generated drivable area and the safety and reliability of the vehicle. Furthermore, corresponding judgment methods are used to determine the target grid for different perception sensors, thereby improving compatibility with different perception sensors and the accuracy of the determined drivable area. In addition, when a vehicle includes multiple perception sensors, the measured obstacle probability values ​​corresponding to each perception sensor are fused, so that the target grid is determined by combining the detection results of multiple perception sensors, the accuracy of the missing target grid is improved, and the reliability and safety of the vehicle are improved; further, the obstacle area is determined based on the target measurement points in the determined target grid, and a judgment is made based on the obstacle area and the size of the vehicle to obtain a drivable area that meets the vehicle's driving needs, thereby making it easier for users to view the drivable area and drive the vehicle, providing users with more considerate services, thereby improving the user experience and vehicle reliability.

[0191] It should be understood that the device provided in the embodiment of the present application is used to execute the above-mentioned method for determining a drivable area, and thus can achieve the same effect as the above-mentioned implementation method.

[0192] In the case of an integrated unit, the device may include a processing module and a storage module. When the device is used in a vehicle, the processing module may be used to control and manage the vehicle's movements. The storage module may be used to support the vehicle's execution of program codes, etc.

[0193] The processing module may be a processor or controller that implements or executes various exemplary logic blocks, modules, and circuits disclosed herein. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a digital signal processing system (DSP) and a microprocessor, and the storage module may be a memory.

[0194] In addition, the device provided in the embodiment of the present application can specifically be a chip, component or module, and the chip may include a connected processor and memory; wherein the memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute a method for determining a drivable area provided in the above embodiment.

[0195] An embodiment of the present application also provides a computer-readable storage medium, which stores computer program code. When the computer program code runs on a computer, the computer executes the above-mentioned related method steps to implement a method for determining a drivable area provided in the above embodiment.

[0196] This embodiment further provides a computer program product. When the computer program product is run on a computer, it enables the computer to execute the above-mentioned related steps to implement a method for determining a drivable area provided in the above embodiment.

[0197] Among them, the device, computer-readable storage medium, computer program product or chip provided in this embodiment are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0198] Through the description of the above implementation methods, technical personnel in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0199] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0200] The above content is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A method for determining a drivable area, characterized in that: Applied to a vehicle, the method comprises: Obtaining obstacle measurement points in the area where the vehicle is located based on a perception sensor, and determining a measurement grid corresponding to the obstacle measurement point in a preset grid map; Determining a current obstacle probability value of the perception sensor for the measurement grid based on a preset probability algorithm; Determining a target obstacle probability value of the measurement grid based on the current obstacle probability value and a historical obstacle probability value of the perception sensor for the measurement grid; the historical obstacle probability value is an obstacle probability value determined by the perception sensor for the measurement grid within a historical detection period; A drivable area of ​​the vehicle is determined in the area based on the target obstacle probability value.

2. The method according to claim 1, characterized in that The perception sensor is an ultrasonic sensor, and determining the measurement grid corresponding to the obstacle measurement point in a preset grid map includes: Determine, based on the first position corresponding to the obstacle measurement point, a second position corresponding to the perception sensor, where the grid where the first position is located is a first grid; A connection line is established between the first position and the second position, a second grid that the connection line passes through within a first preset distance is determined, and the first grid and the second grid are determined as measurement grids.

3. The method according to claim 2, characterized in that The determining, based on a preset probability algorithm, a current obstacle probability value of the perception sensor for the measurement grid includes: Determining a first obstacle probability value of the perception sensor for the first grid based on a preset probability algorithm; A second obstacle probability value corresponding to the second grid is obtained based on a preset attenuation probability value, the first obstacle probability value, and a distance between the first grid and each of the second grids.

4. The method according to claim 3, characterized in that The determining, based on the current obstacle probability value and the historical obstacle probability value of the perception sensor for the measurement grid, a target obstacle probability value of the measurement grid includes: Obtaining a first historical obstacle probability value corresponding to the first grid by the perception sensor, obtaining a first measured obstacle probability value based on the first historical obstacle probability value and the first obstacle probability value using a Bayesian formula, and obtaining a first target obstacle probability value for the first grid based on the first measured obstacle probability value using a logic function; Obtain a second historical obstacle probability value corresponding to the second grid by the perception sensor, obtain a second measured obstacle probability value based on the second historical obstacle probability value and the second obstacle probability value using a Bayesian formula, and obtain a second target obstacle probability value for the second grid based on the second measured obstacle probability value using a logic function.

5. The method according to claim 1, wherein The perception sensor is a visual sensor, and determining a target obstacle probability value of the measurement grid based on the current obstacle probability value and a historical obstacle probability value of the measurement grid by the perception sensor includes: Obtaining a historical obstacle probability value corresponding to the measurement grid from the perception sensor, and obtaining a measured obstacle probability value corresponding to the measurement grid using a Bayesian formula based on the historical obstacle probability value and the current obstacle probability value; A logic function is used to obtain a target obstacle probability value of the measurement grid based on the measured obstacle probability value.

6. The method according to claim 1, wherein There are multiple perception sensors, and determining a target obstacle probability value of the measurement grid based on the current obstacle probability value and historical obstacle probability values ​​of the perception sensors for the measurement grid includes: determining a measured obstacle probability value of the perception sensor for the measurement grid based on the current obstacle probability value and a historical obstacle probability value of the perception sensor for the measurement grid; The measured obstacle probability values ​​corresponding to each of the perception sensors are fused to obtain a target obstacle probability value corresponding to the measurement grid.

7. The method according to claim 6, characterized in that The fusing the measured obstacle probability values ​​corresponding to the perception sensors to obtain the target obstacle probability value corresponding to the measurement grid includes: Perform weighted averaging on the measured obstacle probability values ​​to obtain the target obstacle probability value of the measurement grid; or A maximum value among the measured obstacle probability values ​​is determined, and the maximum value is determined as the target obstacle probability value of the measurement grid.

8. The method according to claim 1, characterized in that The determining of the drivable area of ​​the vehicle in the area based on the target obstacle probability value includes: Determining a target grid in each of the measurement grids based on a preset probability threshold and the target obstacle probability value corresponding to each of the measurement grids; Acquire target measurement points in the target grid, and generate obstacle areas based on each of the target measurement points; A drivable area of ​​the vehicle is determined based on the obstacle area.

9. The method according to claim 8, characterized in that The acquiring target measurement points in the target grid and generating an obstacle area based on each target measurement point includes: Target measurement points in the target grid are acquired, and a preset convex hull algorithm is used to perform convex hull processing on the target measurement points whose distance is less than a second preset distance to generate an obstacle area.

10. The method according to claim 8, characterized in that The determining of the drivable area of ​​the vehicle based on the obstacle area includes: Mapping the obstacle area to a real-world map of the vehicle to obtain the vehicle size of the vehicle; Based on the obstacle area and the vehicle size, a drivable area of ​​the vehicle is determined in the real-world map.

11. A device for determining a drivable area, characterized in that: Applied to a vehicle, the device comprises: a grid determination unit, configured to obtain obstacle measurement points in the area where the vehicle is located based on a perception sensor, and determine a measurement grid corresponding to the obstacle measurement point in a preset grid map; a current probability value determining unit, configured to determine a current obstacle probability value of the perception sensor for the measurement grid based on a preset probability algorithm; a target probability value determining unit, configured to determine a target obstacle probability value for the measurement grid based on the current obstacle probability value and a historical obstacle probability value of the perception sensor for the measurement grid; the historical obstacle probability value being an obstacle probability value determined by the perception sensor for the measurement grid within a historical detection period; An area determination unit is configured to determine a drivable area of ​​the vehicle in the area based on the target obstacle probability value.

12. A vehicle, characterized in that: The vehicle comprises: a memory for storing executable program code; A processor is configured to call and run the executable program code from the memory, so that the vehicle executes the method according to any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer program code, and when the computer program code is executed, the method according to any one of claims 1 to 10 is implemented.

Images