CN111177869B - Method, device and equipment for determining sensor layout scheme - Google Patents

Abstract

The application discloses a method, a device and equipment for determining a sensor layout scheme, relates to the technical field of intelligent driving, and particularly relates to the technical field of sensor layout. The method comprises the following steps: acquiring vehicle type parameters of a vehicle and identifications of a plurality of candidate sensors, and determining a sensor layout scheme according to the vehicle type parameters of the vehicle, the identifications of the plurality of candidate sensors and obstacle detection models corresponding to the candidate sensors; the sensor layout scheme includes: an identification of a plurality of target sensors and a target mounting location of each target sensor at the vehicle, wherein the plurality of target sensors is a subset of the plurality of candidate sensors. The actual detection process of different candidate sensors on the obstacle is simulated by using the obstacle detection simulation in the process of determining the sensor layout scheme, so that the determined sensor layout scheme is the most suitable for the vehicle, and the perception effect of the sensor can be optimized.

Description

Method, device and equipment for determining sensor layout scheme

technical field

The present application relates to the technical field of intelligent driving, and in particular to a method, device and equipment for determining a sensor layout scheme.

Background technique

Generally, the perception system of an intelligent driving vehicle adopts a multi-sensor fusion perception scheme. As the hardware carrier of the perception system, the sensor directly determines the performance upper limit of the entire perception system. In order to achieve the best perception effect, it is necessary to adopt a systematic and scientific sensor layout scheme.

At present, when determining the sensor layout scheme of an intelligent driving vehicle, the sensing range of each sensor is mainly calculated based on the physical parameters of each sensor, and then the layout scheme of each sensor is determined based on the calculated sensing range of each sensor.

However, the sensor layout scheme determined in the above scheme usually cannot achieve the optimal perception effect.

Contents of the invention

The present application provides a method, device and equipment for determining a sensor layout scheme, which can ensure that the determined sensor layout scheme has an optimal perception effect.

In a first aspect, the present application provides a method for determining a sensor layout scheme, including:

Obtain vehicle model parameters and identifications of multiple candidate sensors; determine a sensor layout scheme according to the vehicle model parameters, the identifications of the multiple candidate sensors, and the obstacle detection model corresponding to each of the candidate sensors, the sensor The layout scheme includes: identifications of multiple target sensors, and target installation positions of each of the target sensors on the vehicle, wherein the multiple target sensors are a subset of the multiple candidate sensors.

When determining the sensor layout scheme, it is determined according to the model parameters of the vehicle and the obstacle detection model corresponding to each candidate sensor, that is, in the process of determining the sensor layout scheme, the obstacle detection model is used to simulate different candidate sensors. The actual detection process of obstacles makes the determined sensor layout scheme most suitable for the vehicle, that is, the sensor layout of the vehicle according to the layout scheme can make the sensor's perception effect optimal.

In a possible implementation manner, the determining the sensor layout scheme according to the model parameters of the vehicle, the identifiers of the plurality of candidate sensors, and the obstacle detection model corresponding to each of the candidate sensors includes: according to the vehicle vehicle model parameters, the identifiers of the multiple candidate sensors, the obstacle detection model corresponding to each of the candidate sensors, and the geometric models of multiple obstacles, determine the sensor layout scheme, and the obstacle detection result corresponding to the sensor layout scheme Meet the preset conditions.

By establishing a geometric model of the obstacle, on the one hand, the characteristics of the obstacle are simplified to reduce the amount of calculation; The accuracy of the obstacle detection results ensures that the determined sensor layout scheme is the optimal scheme for the perception effect.

In a possible implementation manner, the model parameters of the vehicle include a three-dimensional model of the vehicle; The detection model, and the geometric models of multiple obstacles, determine the sensor layout scheme, including: according to the three-dimensional model of the vehicle, and the identification of the plurality of candidate sensors, determine a first layout scheme, the first layout scheme includes The identification of multiple temporary sensors, and the temporary installation position of each of the temporary sensors in the vehicle, the multiple temporary sensors are a subset of the multiple candidate sensors; according to the three-dimensional model of the vehicle, the first An obstacle detection model corresponding to each of the temporary sensors in a layout scheme, and a plurality of geometric models of obstacles, determine the obstacle detection result corresponding to the first layout scheme; determine the obstacle corresponding to the first layout scheme Whether the object detection result satisfies the preset condition; if yes, the first layout scheme is used as the sensor layout scheme; if not, according to the obstacle detection result corresponding to the first layout scheme, and the three-dimensional The first layout scheme is adjusted until the obstacle detection result corresponding to the adjusted layout scheme satisfies the preset condition.

Through the iterative process of this implementation method, the initial layout scheme can be continuously adjusted to obtain the final sensor layout scheme. In the adjustment process, according to the obstacle detection results corresponding to the current layout scheme and the 3D vehicle model, the adjustment iteration The result of obstacle detection in the process is continuously optimized, so that the perception effect corresponding to the final sensor layout scheme is optimal.

In a possible implementation manner, according to the three-dimensional model of the vehicle, the obstacle detection model corresponding to each of the temporary sensors in the first layout scheme, and the geometric models of multiple obstacles, the The obstacle detection result corresponding to the first layout scheme includes: obtaining the effective detection range corresponding to each of the temporary sensors according to the obstacle detection model corresponding to each of the temporary sensors and the three-dimensional model of the vehicle, and obtaining the effective detection range corresponding to each of the temporary sensors according to each of the temporary For the effective detection range corresponding to the sensor and the type to which each temporary sensor belongs, obtain the effective detection range corresponding to each type of sensor in the first layout scheme; for each obstacle in the plurality of obstacles, According to the geometric model of the obstacle and the effective detection range corresponding to each type of sensor in the first layout scheme, the detection result corresponding to the obstacle is obtained; according to the detection results corresponding to each of the plurality of obstacles, Determine an obstacle detection result corresponding to the first layout scheme.

In a possible implementation manner, the obtaining the detection result corresponding to the obstacle according to the geometric model of the obstacle and the effective detection range corresponding to each type of sensor in the first layout scheme includes: according to The geometric model of the obstacle, the installation position and the effective detection range of each type of sensor in the first layout scheme are respectively determined when the obstacle is in the position of each type of sensor in the first layout scheme. In the case of different positions, the detection results of the obstacles; the detection results of the obstacles of various types of sensors in the first layout scheme are fused to obtain the detection results corresponding to the obstacles.

In a possible implementation manner, according to the geometric model of the obstacle, the installation position and effective detection range of each type of sensor in the first layout scheme, respectively determine the When each type of sensor is in a different position of the obstacle, the detection result of the obstacle includes: determining a plurality of position points of the obstacle within a preset range, and the preset range is within a range of The center point of the vehicle is the center; when the obstacle is located at each of the position points, according to the geometric model of the obstacle, and the installation position and location of each type of sensor in the first layout scheme The effective detection range is to determine the number of obstacle detection points and the obstacle detection area obtained by each type of sensor to detect the obstacle; if the number of the obstacle detection points is greater than or equal to the first judgment threshold, And the ratio of the detection area of the obstacle to the area of the obstacle itself is greater than or equal to the second judgment threshold, then it is determined that the detection result of this type of sensor for the obstacle is detected; if the obstacle detection point is less than the first judgment threshold, or the ratio of the obstacle detection area to the obstacle’s own area is smaller than the second judgment threshold, then it is determined that the detection result of this type of sensor for the obstacle is Not detected.

In a possible implementation manner, the detection result corresponding to the obstacle is used to indicate which types of sensors detect the obstacle at different positions.

In a possible implementation manner, the obtaining the effective detection range corresponding to each of the temporary sensors according to the obstacle detection model corresponding to each of the temporary sensors and the three-dimensional model of the vehicle includes: for each of the temporary The sensor, according to the obstacle detection model corresponding to the temporary sensor, determines the actual detection range corresponding to the temporary sensor; according to the obstacle detection model corresponding to the temporary sensor and the three-dimensional model of the vehicle, determines the occlusion detection range corresponding to the temporary sensor ; Determine the effective detection range of the temporary sensor according to the actual detection range and the occlusion detection range.

In this implementation manner, the method of determining the effective detection range of the sensor can improve the accuracy of the effective detection range compared with the existing method of determining the effective detection range only based on the physical parameters of the sensor.

In a possible implementation manner, the determining the first layout scheme according to the three-dimensional model of the vehicle and the identifiers of the plurality of candidate sensors includes: determining the corresponding layout of the vehicle according to the three-dimensional model of the vehicle. A plurality of candidate positions for installing the sensors; according to the plurality of candidate positions and identifications of the plurality of candidate sensors, a first layout scheme is determined.

In a second aspect, the present application provides a device for determining a sensor layout scheme, including:

An acquisition module, configured to acquire model parameters of the vehicle and identifications of multiple candidate sensors;

A determining module, configured to determine a sensor layout scheme according to the model parameters of the vehicle, the identifiers of the plurality of candidate sensors, and the obstacle detection model corresponding to each of the candidate sensors, the sensor layout scheme including: a plurality of target sensors , and the target installation position of each of the target sensors in the vehicle, wherein the multiple target sensors are a subset of the multiple candidate sensors.

In a possible implementation manner, the determination module is specifically configured to: according to the model parameters of the vehicle, the identifiers of the plurality of candidate sensors, the obstacle detection model corresponding to each of the candidate sensors, and the plurality of obstacle detection models The geometric model of the sensor layout scheme is determined, and the obstacle detection result corresponding to the sensor layout scheme satisfies a preset condition.

In a possible implementation manner, the model parameters of the vehicle include a three-dimensional model of the vehicle; the determining module is specifically configured to: determine the first A layout plan, the first layout plan includes identifications of a plurality of temporary sensors, and a temporary installation position of each of the temporary sensors in the vehicle, and the plurality of temporary sensors is a subset of the plurality of candidate sensors; According to the three-dimensional model of the vehicle, the obstacle detection model corresponding to each of the temporary sensors in the first layout scheme, and the geometric models of multiple obstacles, determine the obstacle detection result corresponding to the first layout scheme ; Judging whether the obstacle detection result corresponding to the first layout scheme satisfies the preset condition; if so, using the first layout scheme as the sensor layout scheme; The obstacle detection result and the three-dimensional model of the vehicle are adjusted to the first layout scheme until the obstacle detection result corresponding to the adjusted layout scheme satisfies the preset condition.

In a possible implementation manner, the determining module is specifically configured to: obtain the effective detection range corresponding to each of the temporary sensors according to the obstacle detection model corresponding to each of the temporary sensors and the three-dimensional model of the vehicle, and obtain the effective detection range corresponding to each of the temporary sensors; For the effective detection range corresponding to the temporary sensor and the type to which each of the temporary sensors belongs, obtain the effective detection range corresponding to each type of sensor in the first layout scheme; for each of the plurality of obstacles Obstacles, according to the geometric model of the obstacle and the effective detection range corresponding to each type of sensor in the first layout scheme, obtain the detection result corresponding to the obstacle; The detection result is to determine the obstacle detection result corresponding to the first layout scheme.

In a possible implementation manner, the determining module is specifically configured to: respectively determine the Each type of sensor in the first layout scheme detects the obstacle when the obstacle is in a different position; the various types of sensors in the first layout scheme detect the obstacle The detection results of the obstacles are fused to obtain the detection results corresponding to the obstacles.

In a possible implementation manner, the determination module is specifically configured to: determine a plurality of position points of the obstacle within a preset range, the preset range centered on the center point of the vehicle; When the obstacle is located at each of the position points, each type of sensor is determined according to the geometric model of the obstacle, and the installation position and effective detection range of each type of sensor in the first layout scheme The number of obstacle detection points and the obstacle detection area obtained by detecting the obstacle; if the number of the obstacle detection points is greater than or equal to the first judgment threshold, and the obstacle detection area is the same as the obstacle detection area If the ratio of its own area is greater than or equal to the second judgment threshold, it is determined that the detection result of this type of sensor for the obstacle is detected; if the number of the obstacle detection points is less than the first judgment threshold, or the If the ratio of the detection area of the obstacle to the area of the obstacle itself is less than the second judgment threshold, it is determined that the detection result of the obstacle by this type of sensor is not detected.

In a possible implementation manner, the detection result corresponding to the obstacle is used to indicate which types of sensors detect the obstacle at different positions.

In a possible implementation manner, the determining module is specifically configured to: for each temporary sensor, determine the actual detection range corresponding to the temporary sensor according to the obstacle detection model corresponding to the temporary sensor; Determine the occlusion detection range corresponding to the temporary sensor based on the obstacle detection model and the three-dimensional model of the vehicle; determine the effective detection range of the temporary sensor according to the actual detection range and the occlusion detection range.

In a possible implementation manner, the determination module is specifically configured to: determine a plurality of candidate positions corresponding to the vehicle where sensors can be installed according to the three-dimensional model of the vehicle; according to the plurality of candidate positions, and the Identifying a plurality of candidate sensors to determine a first layout scheme.

In a third aspect, the present application provides an electronic device, including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor, the instructions are executed by the at least one processor, so that the at least one processor can perform the method according to any one of the first aspect .

In a fourth aspect, the present application provides a non-transitory computer-readable storage medium storing computer instructions, the computer instructions are used to make the computer execute the method according to any one of the first aspect.

The method, device and equipment for determining the sensor layout scheme provided by the present application, the method includes: acquiring the model parameters of the vehicle and the identifiers of multiple candidate sensors, and according to the model parameters of the vehicle, the identifiers of the multiple candidate sensors and each The obstacle detection model corresponding to the candidate sensor determines the sensor layout scheme, the sensor layout scheme includes: the identification of a plurality of target sensors and the target installation position of each target sensor in the vehicle, wherein the multiple The target sensor is a subset of the plurality of candidate sensors. When determining the sensor layout scheme, it is determined according to the model parameters of the vehicle and the obstacle detection model corresponding to the candidate sensor, that is to say, in the process of determining the sensor layout scheme, the obstacle detection model is used to simulate different candidate sensor pairs. The actual detection process of obstacles makes the determined sensor layout scheme most suitable for the vehicle, that is, the sensor layout of the vehicle according to the layout scheme can make the sensor's perception effect optimal.

Other effects of the above optional manner will be described below in conjunction with specific embodiments.

Description of drawings

The accompanying drawings are used to better understand the solution, and do not constitute a limitation to the application. in:

FIG. 1A is a schematic diagram of a possible application scenario of the embodiment of the present application;

Fig. 1B is a schematic diagram of the determination principle of the sensor layout scheme in the embodiment of the present application;

FIG. 2 is a schematic flowchart of a method for determining a sensor layout scheme provided by an embodiment of the present application;

FIG. 3A is a schematic diagram of an obstacle detection model corresponding to a camera provided in an embodiment of the present application;

FIG. 3B is a schematic diagram of an obstacle detection model corresponding to the lidar provided in the embodiment of the present application;

FIG. 3C is a schematic diagram of an obstacle detection model corresponding to the millimeter-wave radar provided in the embodiment of the present application;

FIG. 4 is a schematic diagram of a geometric model of an obstacle provided in an embodiment of the present application;

FIG. 5 is a schematic flowchart of a method for determining a sensor layout scheme provided by another embodiment of the present application;

FIG. 6 is a schematic diagram of a determination process of an obstacle detection result provided by an embodiment of the present application;

Fig. 7 is a schematic diagram of detection results of obstacles provided by an embodiment of the present application;

FIG. 8 is a schematic structural diagram of a device for determining a sensor layout scheme provided by an embodiment of the present application;

FIG. 9 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

Detailed ways

Exemplary embodiments of the present application are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present application to facilitate understanding, and they should be regarded as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

FIG. 1A is a schematic diagram of a possible application scenario of the embodiment of the present application. The perception system of the intelligent driving vehicle adopts a multi-sensor fusion perception scheme, that is, multiple sensors need to be installed on the intelligent driving vehicle. Among them, there can be many kinds of sensors used in the perception system of intelligent driving vehicles, including but not limited to: cameras, laser radars, millimeter wave radars, ultrasonic radars, night vision devices, etc. As shown in FIG. 1A , after the model of the vehicle is determined, multiple sensors need to be installed at appropriate positions on the vehicle. For example, the sensor 1 is installed at the front of the vehicle, the sensor 2 is installed at the rear of the vehicle, and the like. Sensors are the hardware carrier of the perception system, and the layout of multiple sensors on the vehicle will affect the perception effect of the entire perception system.

At present, when determining the sensor layout scheme of an intelligent driving vehicle, the sensing range of each sensor is mainly calculated based on the physical parameters of each sensor, and then the layout scheme of each sensor is determined based on the calculated sensing range of each sensor. For example, taking a camera as an example, it is necessary to determine the perception range of the camera according to parameters such as the field of view and resolution of the camera, and then determine the installation position of the camera. However, the sensing range determined according to the physical parameters of each sensor in the above solution is not accurate enough, so that the determined sensor layout solution cannot obtain an optimal sensing effect.

In order to solve the above problems, the present application provides a method for determining a sensor layout scheme. FIG. 1B is a schematic diagram of the determination principle of the sensor layout scheme in the embodiment of the present application. As shown in FIG. 1B , the method of this embodiment may be executed by a device for determining a sensor layout scheme. The device can be in the form of software and/or hardware, and the device can also be integrated into electronic equipment. Referring to Fig. 1B, input the model parameters of the vehicle and the identifiers of multiple candidate sensors into the device, and the device determines and outputs Sensor layout scheme. In this embodiment, the sensor layout scheme is determined according to the model parameters of the vehicle, the identification of multiple candidate sensors, and the obstacle detection model corresponding to each candidate sensor, that is to say, when determining the sensor layout scheme, the sensors in the vehicle are considered. The actual detection process makes the determined sensor layout scheme most suitable for the vehicle, that is, the sensor layout of the vehicle according to the layout scheme can make the perception effect of the sensor optimal.

The technical solution of the present application will be described in detail below in conjunction with several specific embodiments. The following embodiments may be combined with each other, and the same or similar content may not be repeatedly described in some embodiments.

FIG. 2 is a schematic flowchart of a method for determining a sensor layout scheme provided by an embodiment of the present application. As shown in Figure 2, the method of this embodiment includes:

S201: Obtain model parameters of the vehicle and identifiers of multiple candidate sensors.

Wherein, the model parameter of the vehicle refers to the parameter used to indicate the model of the vehicle, including but not limited to: the model of the vehicle, the unique identifier of the vehicle, the three-dimensional model of the vehicle, and the like. According to the vehicle model parameters, the vehicle body structure, internal and external dimensions, etc. can be determined. It can be understood that, generally, vehicle parameters of the same model (such as body structure, internal and external dimensions, etc.) are the same. The vehicle model parameters may be different for different models of vehicles. After the vehicle model parameters are determined, the location where the vehicle can be used to install the sensor is also determined.

Candidate sensors are sensors that can be optionally installed on the vehicle. In this embodiment, the candidate sensor may be any type of sensor, including but not limited to: camera, laser radar, millimeter wave radar, ultrasonic radar, night vision device, and the like. It can be understood that the candidate sensors are a relatively large selectable range, and the actually determined sensor layout solution may only include some sensors in the range. For example, the candidate sensors include 10 sensors, and the finally determined sensor layout scheme may be to select only 5 of them to be installed in corresponding positions of the vehicle.

In this embodiment, the identifier of a sensor refers to any identifier that can identify a sensor, including but not limited to: the model of the sensor, the serial number of the sensor, the name of the sensor, and the like. In addition, the candidate sensors in this embodiment may be of various types. For example, the 10 candidate sensors may be of the following 3 types: cameras (for example, 3), lidars (for example, 3), and millimeter-wave radars (for example, 4). The models corresponding to each type of sensor may be the same or different, for example, the three candidate cameras may be of the same model or of different models. This embodiment does not limit the types and quantities of multiple candidate sensors.

In a possible implementation manner, the candidate sensors are determined according to the cost requirements of the vehicle perception system. It can be understood that generally, the higher the unit price of a sensor, the better the sensing effect of the sensor. Therefore, in practical applications, it is necessary to comprehensively consider the cost factor and the perceived effect to achieve a balance between the two. Exemplarily, on the premise that a certain cost requirement is met, identifications of multiple candidate sensors that can be optionally installed are determined. Then, select from multiple candidate sensors to determine the sensor layout scheme with the best perceptual effect.

S202: Determine a sensor layout scheme according to the model parameters of the vehicle, the identifiers of the multiple candidate sensors, and the obstacle detection model corresponding to each of the candidate sensors, where the sensor layout scheme includes: identifiers of multiple target sensors, And each of the target sensors is at a target installation position of the vehicle, wherein the multiple target sensors are a subset of the multiple candidate sensors.

In this embodiment, the obstacle detection model refers to a geometric model that simulates the obstacle detection process established for the sensor according to the detection mechanism of the sensor. The detection models of obstacles corresponding to different types of sensors may be different. The following takes the camera, lidar and millimeter-wave radar as examples to describe the obstacle detection models corresponding to these three sensors. The establishment process of obstacle detection models corresponding to other types of sensors is similar to these three sensors, and will not be described in detail in this embodiment.

FIG. 3A is a schematic diagram of an obstacle detection model corresponding to a camera provided in an embodiment of the present application. As shown in FIG. 3A , the camera adopts central projection for equivalent, and an object in the three-dimensional space generates a corresponding image on the camera image plane through the central projection.

FIG. 3B is a schematic diagram of an obstacle detection model corresponding to a lidar provided in an embodiment of the present application. As shown in Figure 3B, lidar can be equivalent to a collection of rays emitted from the origin in three-dimensional space, and each ray intersects with an object to generate a detection point. LiDAR can be equipped with multiple lasers in the vertical direction, and the installation angles of each laser can be the same or different. The angle of each ray is determined according to the installation angle (angle with the vertical direction) of the hardware laser of the lidar. The lidar can rotate 360 degrees in the horizontal direction, so the horizontal direction covers 360 degrees. The coverage in the vertical direction is determined according to the installation angle of the hardware laser of the lidar. For example, if the angle between laser 1 and the vertical direction is 90 degrees, then laser 1 emits rays along the horizontal direction, and if the angle between laser 2 and the vertical direction is 45 degrees, then the laser emits rays along the direction of 45 degrees between the horizontal direction Rays. According to the angle of the first ray and the angle of the last ray in the vertical direction, the vertical coverage of the lidar can be determined.

FIG. 3C is a schematic diagram of an obstacle detection model corresponding to the millimeter-wave radar provided in the embodiment of the present application. The detection principle of millimeter-wave radar is similar to that of lidar. One of the differences is that the laser emitted by lidar is non-divergent. Therefore, lidar can be equivalent to a collection of rays. The millimeter wave emitted by the millimeter wave radar is divergent. Therefore, as shown in FIG. 3C , the millimeter wave radar can be equivalent to a set of sector surfaces in a three-dimensional space. Another difference between millimeter-wave radar and lidar is that millimeter-wave radar only emits millimeter waves in the horizontal direction. Therefore, the vertical angle range of millimeter-wave radar is the top angle of a fan. When the fan-shaped surface intersects with the object, a detection point is generated when the intersection angle exceeds a certain threshold.

It can be understood that although sensors of the same type may adopt an obstacle detection model with the same detection principle, the parameters in the obstacle detection model corresponding to different types of sensors of the same type may be different. For example, different types of lidars may have different vertical/horizontal coverages.

In this embodiment, the sensor layout scheme can be determined according to vehicle model parameters, identifiers of multiple candidate sensors, and obstacle detection models corresponding to each candidate sensor. Wherein, the sensor layout scheme is the layout scheme with the best corresponding perception effect. The sensor layout solution in this embodiment includes: the identification of multiple target sensors and the target installation position of each target sensor in the vehicle. That is to say, this embodiment can determine which target sensors need to be selected from the candidate sensors, and determine where each target sensor needs to be installed on the vehicle. It can be understood that the target sensor in the finally determined sensor layout scheme is a subset of the candidate sensors.

3A to 3C, after the obstacle detection model corresponding to each candidate sensor is determined, different layout modes of each candidate sensor can be simulated according to the model parameters of the vehicle and the obstacle detection model (that is, each candidate sensor is installed on the vehicle According to the obstacle detection results corresponding to the different positions of the candidate sensors, the sensor layout mode corresponding to the optimal detection result is determined according to the obstacle detection results corresponding to the different layout modes of each candidate sensor, so as to obtain the final sensor layout scheme. Since this embodiment determines the sensor layout scheme, it is determined according to the model parameters of the vehicle, the identification of multiple candidate sensors, and the obstacle detection model corresponding to each candidate sensor, that is to say, using the obstacle detection model to simulate a The actual detection process of obstacles by different candidate sensors makes the determined sensor layout scheme most suitable for the vehicle, that is, the sensor layout of the vehicle according to the layout scheme can make the perception effect of the sensor optimal.

In a possible implementation manner, geometric modeling can also be performed on multiple obstacles, and then, according to the model parameters of the vehicle, the identification of multiple candidate sensors, the obstacle detection model corresponding to each candidate sensor, and multiple The geometric model of the obstacle determines the sensor layout scheme. Wherein, the multiple obstacles may be different types of obstacles, including but not limited to: motor vehicles, bicycles, pedestrians, cones and the like.

Exemplarily, FIG. 4 is a schematic diagram of a geometric model of an obstacle provided in an embodiment of the present application. Rectangular solid frames of different sizes may be used to represent different obstacles. It should be noted that in practical applications, different types of obstacles may be modeled in different manners, which is not limited in this embodiment, and that shown in FIG. 4 is only a possible example. By establishing a geometric model of the obstacle, on the one hand, the characteristics of the obstacle are simplified to reduce the amount of calculation; The accuracy of the obstacle detection results ensures that the determined sensor layout scheme is the optimal scheme for the perception effect.

Usually, the evaluation of the pros and cons of the sensor layout scheme can be measured by the longest detection distance and the blind spot distance. If a sensor layout scheme corresponds to a farther detection distance and a smaller blind zone distance, it means that the sensor layout scheme has a better perception effect. It should be noted that the sensor layout scheme with the best perceptual effect described in this embodiment refers to the sensor layout scheme that meets the preset detection requirements in the current actual application scenario. In other words, the obstacle detection result corresponding to the sensor layout scheme determined in this embodiment satisfies a preset condition (for example: satisfying a preset farthest detection distance and a preset blind zone distance, etc.).

The method for determining the sensor layout scheme provided in this embodiment includes: acquiring vehicle model parameters and identifications of multiple candidate sensors, and according to the vehicle model parameters, identifications of multiple candidate sensors, and obstacles corresponding to each candidate sensor Detect the model and determine the sensor layout scheme. When determining the sensor layout scheme, it is determined according to the model parameters of the vehicle and the obstacle detection model corresponding to each candidate sensor, that is, in the process of determining the sensor layout scheme, the obstacle detection model is used to simulate different candidate sensors. The actual detection process of obstacles makes the determined sensor layout scheme most suitable for the vehicle, that is, the sensor layout of the vehicle according to the layout scheme can make the sensor's perception effect optimal.

Fig. 5 is a schematic flowchart of a method for determining a sensor layout scheme provided by another embodiment of the present application. As shown in Figure 5, the method of this embodiment includes:

S501: Acquiring model parameters of the vehicle and identifiers of multiple candidate sensors, wherein the model parameters of the vehicle include a three-dimensional model of the vehicle.

In this embodiment, the specific implementation manner of S501 is similar to that of S201 in FIG. 2 , and details are not described here.

S502: Determine a first layout scheme according to the three-dimensional model of the vehicle and the identifiers of the plurality of candidate sensors.

In this embodiment, the first layout scheme may also be referred to as an initial layout scheme. That is, an initial layout scheme is determined according to the three-dimensional model of the vehicle and identifications of multiple candidate sensors. The first layout scheme includes identifications of a plurality of temporary sensors, and a temporary installation position of each of the temporary sensors in the vehicle, and the plurality of temporary sensors are a subset of the plurality of candidate sensors. Exemplarily, according to the three-dimensional model of the vehicle, determine a plurality of candidate positions corresponding to the vehicle where sensors can be installed; and determine an initial layout scheme according to the plurality of candidate positions and identifications of the plurality of candidate sensors. For example, some sensors are randomly selected from multiple candidate sensors as temporary sensors, and each temporary sensor is respectively arranged on multiple candidate positions. It can be understood that there may be various initial layout schemes. The perceptual effect of the initial layout scheme is not considered in the process of determining the initial layout scheme. Subsequently, it is necessary to iterate the initial layout scheme one or more times according to the perception effect of the initial layout scheme to determine the final sensor layout scheme.

S503: Determine the obstacle corresponding to the first layout scheme according to the three-dimensional model of the vehicle, the obstacle detection model corresponding to each of the temporary sensors in the first layout scheme, and the geometric models of multiple obstacles detection results.

Specifically, according to the temporary installation position of each temporary sensor in the three-dimensional model of the vehicle in the first layout scheme, the first layout scheme is determined according to the obstacle detection model corresponding to each temporary sensor and the geometric models of multiple obstacles Corresponding obstacle detection results. For example: how far the first layout scheme can detect obstacles, or how big an obstacle can be detected; for a certain obstacle, it can be detected by several types of sensors, or it can be detected by several temporary detected by the sensor; the size of the obstacle detection blind zone corresponding to the first layout scheme, and so on.

S504: Determine whether an obstacle detection result corresponding to the first layout scheme satisfies a preset condition. If yes, execute S505; if not, execute S506.

It can be understood that the preset condition may be determined according to the current application scenario and perception requirements, and this embodiment does not specifically limit the specific form and content of the preset condition.

S505: Use the first layout scheme as the sensor layout scheme.

That is to say, each temporary sensor in the first layout scheme is used as a target sensor, and the temporary installation position of each temporary sensor is used as a target installation position of the target sensor.

S506: According to the obstacle detection result corresponding to the first layout scheme and the three-dimensional model of the vehicle, adjust the first layout scheme until the obstacle detection result corresponding to the adjusted layout scheme satisfies the predetermined set conditions.

Wherein, the way of adjusting the first layout scheme includes at least one of the following: changing the identification of the temporary sensor corresponding to at least one position; changing the installation position of at least one temporary sensor; increasing the number of temporary sensors; the number of sensors.

If the obstacle detection result corresponding to the first layout scheme satisfies the preset condition, the first layout scheme is used as the final sensor layout scheme; if the obstacle detection result corresponding to the first layout scheme does not meet the preset condition, the The obstacle detection results corresponding to the layout scheme and the three-dimensional model of the vehicle are adjusted to the first layout scheme (for example: replacing a temporary sensor at a certain installation position with another model, or replacing a temporary sensor from one position to another position, or, add a temporary sensor, or, subtract a temporary sensor, etc.). After the first layout scheme is adjusted to obtain a new layout scheme, the new layout scheme is used as the first layout scheme, and S503 to S506 in this embodiment are re-executed.

Through the iterative process of this embodiment, the initial layout scheme can be continuously adjusted to obtain the final sensor layout scheme. During the adjustment process, according to the obstacle detection results corresponding to the current layout scheme and the three-dimensional model of the vehicle, the adjustment The result of obstacle detection in the iterative process is continuously optimized, so that the perception effect corresponding to the final sensor layout scheme is optimal.

The following describes how to determine the obstacle detection result corresponding to the first layout scheme in conjunction with a specific embodiment.

FIG. 6 is a schematic diagram of a determination process of an obstacle detection result provided by an embodiment of the present application. The method of this embodiment is used to determine the obstacle detection result corresponding to the first layout scheme. As shown in Figure 6, the method of this embodiment includes:

S601: According to the obstacle detection model corresponding to each temporary sensor and the three-dimensional model of the vehicle, obtain the effective detection range corresponding to each temporary sensor, and according to the effective detection range corresponding to each temporary sensor and the location of each temporary sensor type, and obtain the effective detection range corresponding to each type of sensor in the first layout scheme.

In this embodiment, the effective detection range of the sensor refers to an area where the sensor can effectively detect obstacles. It can be understood that when the sensor is installed on the vehicle, the sensor may detect the body area of the own vehicle during the process of detecting obstacles, and this part of the area may also be called the blocked area of the own vehicle. In this embodiment, the area within the detection range of the sensor that is not blocked by the own vehicle is referred to as an effective detection range.

In a possible implementation manner, for each temporary sensor, the actual detection range corresponding to the temporary sensor is determined according to the obstacle detection model corresponding to the temporary sensor. It can be understood that the actual detection range is the theoretical range obtained according to the obstacle detection model. According to the obstacle detection model corresponding to the temporary sensor and the three-dimensional model of the vehicle, the occlusion detection range corresponding to the temporary sensor is determined. Wherein, the occlusion detection range refers to the range that the sensor cannot detect due to the occlusion of the own vehicle; the effective detection range of the temporary sensor is determined according to the actual detection range and the occlusion detection range. For example: after removing the occlusion detection range in the actual detection range, the remaining range is the effective detection range of the temporary sensor.

Taking the lidar as an example, when the lidar is installed in the front area of the vehicle, in the vertical direction, the lidar does not have an occlusion area (the area blocked by the vehicle). In the horizontal direction, lidar can only detect the area in front of the car, but cannot detect the area behind the car. Therefore, the area behind the car is called the occlusion area in the horizontal direction. In an example, it is possible to determine which rays in the laser radar ray set are shot into the occlusion area and which rays are shot into the non-blocking area, so that the ray set is used to describe the effective detection range of the laser radar. For example: the (horizontal angle, vertical angle) of the ray can be used to represent the effective detection range of the lidar, that is, the ray within the range of the horizontal angle/vertical angle is not blocked by the vehicle.

The millimeter-wave radar is similar to the laser radar, the difference is that the millimeter-wave radar detects in the horizontal direction. Therefore, it is only necessary to determine the sector set of the millimeter-wave radar in the horizontal direction that is not blocked by the vehicle. For example, the horizontal angle of the sector can be used to represent the effective detection range of the millimeter-wave radar, that is, the sector within which horizontal angle range is not blocked by the own vehicle.

Taking the camera as an example, when the camera is installed on the roof of the car, the camera may capture the body of the car during the shooting process, that is, there may be a body in the captured image, and the pixels corresponding to the body area in the image are called occlusion pixels. The remaining pixels are called unoccluded pixels. The effective detection range of the camera can be represented by the unoccluded pixels in the image.

S602: For each obstacle in the plurality of obstacles, according to the geometric model of the obstacle and the effective detection range corresponding to each type of sensor in the first layout scheme, obtain the corresponding detection results.

It can be understood that after knowing the installation positions of various types of sensors in the vehicle in the first layout scheme, the detection results corresponding to obstacles can be determined according to the effective detection ranges corresponding to each type of sensors and the geometric model of obstacles. For example: if the obstacle is outside the effective detection range of a sensor, it is determined that the obstacle cannot be detected by the sensor; if the obstacle is within the effective detection range of a sensor, it is determined that the obstacle can be detected by the sensor . If a part of the obstacle is within the effective detection range of a sensor, it can be determined whether the obstacle can be detected by the sensor according to the size of the part of the area.

In a possible implementation manner, according to the geometric model of the obstacle, the installation position and the effective detection range of each type of sensor in the first layout scheme, each type of sensor in the first layout scheme is determined separately. Types of sensors detect the obstacles when the obstacles are in different positions.

FIG. 7 is a schematic diagram of detection results of obstacles provided by an embodiment of the present application. Exemplarily, as shown in FIG. 7 , a plurality of position points of the obstacle are determined within a preset range, and the preset range is centered on the center point of the vehicle. For example, the preset range may be the range within 200 meters from the center point of the vehicle to the left, right, front and rear respectively, that is, a rectangular area as shown in FIG. 7 . Draw checkerboard lines at preset intervals within the preset range, and the intersections between the checkerboard lines are used as location points to obtain multiple location points as shown in Figure 7 (the black dots in Figure 7 represent location points).

When the obstacle is located at each of the position points, according to the geometric model of the obstacle, and the installation position and effective detection range of each type of sensor in the first layout scheme, the The number of obstacle detection points and the obstacle detection area obtained by detecting the obstacle by each type of sensor in the first layout scheme. If the number of the obstacle detection points is greater than or equal to the first judgment threshold, and the ratio of the obstacle detection area to the area of the obstacle itself is greater than or equal to the second judgment threshold, then it is determined that this type of sensor is suitable for all The detection result of the obstacle is detected; if the number of detection points of the obstacle is less than the first judgment threshold, or the ratio of the detection area of the obstacle to the area of the obstacle itself is less than the second judgment threshold , then it is determined that the detection result of this type of sensor for the obstacle is not detected.

Referring to FIG. 7 , it is assumed that the first layout scheme includes three types of sensors, namely: camera, laser radar, and millimeter wave radar. Taking the camera as an example, the obstacle is moved between the position points. When the obstacle is located at each position point, the detection of the obstacle detected by the camera can be determined according to the geometric model of the obstacle and the effective detection range of the camera. points (for example: pixels belonging to obstacles in the image captured by the camera), and the area of the obstacle detected by the camera can also be determined (for example, the number of pixels that the obstacle is photographed can be used to determine Of course, other representation forms may also be used, which is not limited in this embodiment). If the number of detection points is greater than or equal to the first judgment threshold, and the ratio of the detection area to the area of the obstacle itself is greater than or equal to the second judgment threshold, it is determined that the obstacle can be detected at this point, and the The corresponding location points are set to 1. If the number of detection points is less than the first judgment threshold, or the ratio of the detection area to the area of the obstacle itself is less than the second judgment threshold, it is determined that the obstacle cannot be detected at this point, and the corresponding position in Figure 7 can be Points are set to 0. In this way, the detection result of the camera to the obstacle can be obtained (the detection result is in the form of a checkerboard as shown in FIG. 7 , and the value of each position point is 0 or 1, indicating that it has not been detected or detected).

Similarly, when the obstacle moves at different positions, the detection results of the obstacle by the laser radar and the millimeter-wave radar can also be obtained, which can also be represented in the form of a checkerboard as shown in Figure 7 .

After the above process, the detection results of the obstacles of various types of sensors in the first layout scheme may be fused to obtain the detection results corresponding to the obstacles. That is to say, the detection results of the obstacle obtained by the camera, lidar and millimeter-wave radar respectively obtained in the above process are fused to obtain the detection result corresponding to the obstacle.

Wherein, the detection result corresponding to the obstacle is used to indicate which types of sensors detect the obstacle at different positions.

In a possible implementation manner, when performing fusion of detection results, different representations may be used for identification of the following eight situations. (1) Only lidar is detected; (2) Only camera is detected; (3) Only millimeter wave radar is detected; (4) Lidar and camera are detected at the same time, but millimeter wave radar is not detected; (5) Simultaneously detected by lidar and millimeter-wave radar, but not detected by camera; (6) detected by both camera and millimeter-wave radar, but not detected by lidar; (7) simultaneously detected by lidar, camera and millimeter-wave radar Detected; (8) Not detected by all sensors. In an example, the fused detection results are still expressed in the form of a chessboard as shown in FIG. 7 , where each location point is marked with a value 1-8, and each value corresponds to the above-mentioned 8 situations.

S603: Determine an obstacle detection result corresponding to the first layout scheme according to the detection results corresponding to the plurality of obstacles.

After the detection result corresponding to each obstacle is obtained in S602, the detection results corresponding to multiple obstacles may be fused to obtain the obstacle detection result corresponding to the first layout scheme. In this way, according to the obstacle detection result corresponding to the first layout scheme, information such as the furthest detection distance corresponding to the layout scheme and the size of the blind area can be intuitively obtained. Using this information, the perceptual effect of the first layout scheme can be accurately evaluated.

In this embodiment, the effective detection range of the sensor is determined according to the obstacle detection model corresponding to the sensor, and the obstacle detection result is determined according to the obstacle geometric model and the effective detection range of the sensor, and then the sensory effect is evaluated by using the obstacle detection result. Compared with determining the perception effect only according to the physical parameters of the sensors in the prior art, the evaluation accuracy of the perception effect can be improved, thereby ensuring that the determined sensor layout scheme is the scheme with the best perception effect.

FIG. 8 is a schematic structural diagram of an apparatus for determining a sensor layout scheme provided by an embodiment of the present application. The apparatus in this embodiment may be in the form of software and/or hardware. As shown in FIG. 8 , an apparatus 800 for determining a sensor layout scheme provided in this embodiment includes: an acquisition module 801 and a determination module 802 . in,

An acquisition module 801, configured to acquire vehicle model parameters and identifications of multiple candidate sensors;

The determining module 802 is configured to determine a sensor layout scheme according to the model parameters of the vehicle, the identifiers of the multiple candidate sensors, and the obstacle detection model corresponding to each of the candidate sensors, and the sensor layout scheme includes: multiple targets The identification of the sensor and the target installation position of each of the target sensors on the vehicle, wherein the multiple target sensors are a subset of the multiple candidate sensors.

In a possible implementation manner, the determining module 802 is specifically configured to: according to the model parameters of the vehicle, the identifiers of the multiple candidate sensors, the obstacle detection model corresponding to each of the candidate sensors, and the multiple obstacle detection models The geometric model of the object is used to determine the sensor layout scheme, and the obstacle detection result corresponding to the sensor layout scheme satisfies the preset condition.

In a possible implementation manner, the model parameters of the vehicle include a three-dimensional model of the vehicle; the determining module 802 is specifically configured to: determine according to the three-dimensional model of the vehicle and the identifiers of the plurality of candidate sensors A first layout scheme, the first layout scheme including identification of a plurality of temporary sensors, and a temporary installation position of each of the temporary sensors in the vehicle, the plurality of temporary sensors being a subset of the plurality of candidate sensors ; According to the three-dimensional model of the vehicle, the obstacle detection model corresponding to each of the temporary sensors in the first layout scheme, and the geometric models of multiple obstacles, determine the obstacle detection corresponding to the first layout scheme Result; determine whether the obstacle detection result corresponding to the first layout scheme satisfies the preset condition; if yes, use the first layout scheme as the sensor layout scheme; if not, then correspond to the sensor according to the first layout scheme The obstacle detection result and the three-dimensional model of the vehicle are adjusted to the first layout scheme until the obstacle detection result corresponding to the adjusted layout scheme satisfies the preset condition.

In a possible implementation manner, the determination module 802 is specifically configured to: obtain the effective detection range corresponding to each of the temporary sensors according to the obstacle detection model corresponding to each of the temporary sensors and the three-dimensional model of the vehicle, and according to For the effective detection range corresponding to each of the temporary sensors and the type to which each of the temporary sensors belongs, obtain the effective detection range corresponding to each type of sensor in the first layout scheme; for each of the plurality of obstacles According to the geometric model of the obstacle and the effective detection range corresponding to each type of sensor in the first layout scheme, the detection result corresponding to the obstacle is obtained; according to the corresponding The detection result of the obstacle detection result corresponding to the first layout scheme is determined.

In a possible implementation manner, the determining module 802 is specifically configured to: determine the set of obstacles according to the geometric model of the obstacle, the installation position and effective detection range of each type of sensor in the first layout scheme, respectively. The detection results of each type of sensor in the first layout scheme for the obstacle when the obstacle is in a different position; The detection results of the obstacles are fused to obtain the detection results corresponding to the obstacles.

In a possible implementation manner, the determination module 802 is specifically configured to: determine multiple position points of the obstacle within a preset range, the preset range centered on the center point of the vehicle; When the obstacle is located at each of the position points, according to the geometric model of the obstacle, and the installation position and effective detection range of each type of sensor in the first layout scheme, determine each type of sensor The number of obstacle detection points and the obstacle detection area obtained by the sensor detecting the obstacle; if the number of the obstacle detection points is greater than or equal to the first judgment threshold, and the obstacle detection area is the same as the obstacle detection area If the ratio of the area of the object itself is greater than or equal to the second judgment threshold, it is determined that the detection result of this type of sensor for the obstacle is detected; if the number of detection points of the obstacle is less than the first judgment threshold, or If the ratio of the detection area of the obstacle to the area of the obstacle itself is smaller than the second judgment threshold, it is determined that the detection result of the obstacle by this type of sensor is not detected.

In a possible implementation manner, the detection result corresponding to the obstacle is used to indicate which types of sensors detect the obstacle at different positions.

In a possible implementation manner, the determining module 802 is specifically configured to: for each of the temporary sensors, determine the actual detection range corresponding to the temporary sensor according to the obstacle detection model corresponding to the temporary sensor; The corresponding obstacle detection model and the three-dimensional model of the vehicle determine the occlusion detection range corresponding to the temporary sensor; and determine the effective detection range of the temporary sensor according to the actual detection range and the occlusion detection range.

In a possible implementation manner, the determination module 802 is specifically configured to: determine a plurality of candidate positions corresponding to the vehicle where sensors can be installed according to the three-dimensional model of the vehicle; The identifiers of the plurality of candidate sensors are used to determine a first layout scheme.

The device for determining the sensor layout scheme provided in this embodiment can be used to implement the technical solution in any of the above method embodiments, and its implementation principle and technical effect are similar, and will not be repeated here.

According to the embodiments of the present application, the present application also provides an electronic device and a readable storage medium.

As shown in FIG. 9 , it is a block diagram of an electronic device according to a method for determining a sensor layout scheme according to an embodiment of the present application. Electronic device is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are by way of example only, and are not intended to limit implementations of the applications described and/or claimed herein.

As shown in FIG. 9, the electronic device includes: one or more processors 701, a memory 702, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are interconnected using different buses and can be mounted on a common motherboard or otherwise as desired. The processor may process instructions executed within the electronic device, including instructions stored in or on the memory, to display graphical information of a GUI on an external input/output device such as a display device coupled to an interface. In other implementations, multiple processors and/or multiple buses may be used with multiple memories and multiple memories, if desired. Likewise, multiple electronic devices may be connected, with each device providing some of the necessary operations (eg, as a server array, a set of blade servers, or a multi-processor system). In FIG. 9, a processor 701 is taken as an example.

The memory 702 is a non-transitory computer-readable storage medium provided in this application. Wherein, the memory stores instructions executable by at least one processor, so that the at least one processor executes the method for determining a sensor layout scheme provided in the present application. The non-transitory computer-readable storage medium of the present application stores computer instructions, and the computer instructions are used to make the computer execute the method for determining the sensor layout scheme provided in the present application.

The memory 702, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs and modules, such as the program instructions/modules corresponding to the method for determining the sensor layout scheme in the embodiment of the present application ( For example, the acquisition module 801 and the determination module 802 shown in Fig. 8). The processor 701 executes various functional applications and data processing of the server or terminal device by running the non-transitory software programs, instructions and modules stored in the memory 702, that is, to realize the method for determining the sensor layout scheme in the above method embodiments.

The memory 702 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application program required by at least one function; the data storage area may store data created by using the electronic device, and the like. In addition, the memory 702 may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory 702 may optionally include a memory that is remotely located relative to the processor 701, and these remote memories may be connected to the electronic device through a network. Examples of the aforementioned networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The electronic device may further include: an input device 703 and an output device 704 . The processor 701, the memory 702, the input device 703, and the output device 704 may be connected through a bus or in other ways, and connection through a bus is taken as an example in FIG. 9 .

The input device 703 can receive input digital or character information, and generate key signal input related to user settings and function control of electronic equipment, such as touch screen, keypad, mouse, trackpad, touchpad, pointing stick, one or more Input devices such as mouse buttons, trackballs, joysticks, etc. The output device 704 may include a display device, an auxiliary lighting device (eg, LED), a tactile feedback device (eg, a vibration motor), and the like. The display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display, and a plasma display. In some implementations, the display device may be a touch screen.

Various implementations of the systems and techniques described herein can be implemented in digital electronic circuitry, integrated circuit systems, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include being implemented in one or more computer programs executable and/or interpreted on a programmable system including at least one programmable processor, the programmable processor Can be special-purpose or general-purpose programmable processor, can receive data and instruction from storage system, at least one input device, and at least one output device, and transmit data and instruction to this storage system, this at least one input device, and this at least one output device an output device.

These computing programs (also referred to as programs, software, software applications, or codes) include machine instructions for a programmable processor and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine language calculation program. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or means for providing machine instructions and/or data to a programmable processor ( For example, magnetic disks, optical disks, memories, programmable logic devices (PLDs), including machine-readable media that receive machine instructions as machine-readable signals. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.

To provide for interaction with the user, the systems and techniques described herein can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user. ); and a keyboard and pointing device (eg, a mouse or a trackball) through which a user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and can be in any form (including Acoustic input, speech input or, tactile input) to receive input from the user.

The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., as a a user computer having a graphical user interface or web browser through which a user can interact with embodiments of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system. The components of the system can be interconnected by any form or medium of digital data communication, eg, a communication network. Examples of communication networks include: Local Area Network (LAN), Wide Area Network (WAN) and the Internet.

A computer system may include clients and servers. Clients and servers are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other.

It should be understood that steps may be reordered, added or deleted using the various forms of flow shown above. For example, the steps described in the present application may be executed in parallel, sequentially, or in a different order, as long as the desired result of the technical solution disclosed in the present application can be achieved, no limitation is imposed herein.

The above specific implementation methods are not intended to limit the protection scope of the present application. It should be apparent to those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made depending on design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of this application shall be included within the protection scope of this application.

Claims (10)

1. A method for determining a sensor layout scheme, comprising: Obtain vehicle model parameters and identifications of multiple candidate sensors; the vehicle model parameters include a three-dimensional model of the vehicle; According to the three-dimensional model of the vehicle and the identifications of the plurality of candidate sensors, a first layout scheme is determined; the first layout scheme includes identifications of a plurality of temporary sensors, and the temporary location of each temporary sensor in the vehicle installation locations, the plurality of temporary sensors being a subset of the plurality of candidate sensors; According to the obstacle detection model corresponding to each of the temporary sensors and the three-dimensional model of the vehicle, the effective detection range corresponding to each of the temporary sensors is obtained, and according to the effective detection range corresponding to each of the temporary sensors and the location of each temporary sensor type, obtaining the effective detection range corresponding to each type of sensor in the first layout scheme; For each obstacle in the plurality of obstacles, according to the geometric model of the obstacle and the effective detection range corresponding to each type of sensor in the first layout scheme, obtain the detection result corresponding to the obstacle ; determining an obstacle detection result corresponding to the first layout scheme according to detection results corresponding to each of the plurality of obstacles; If the obstacle detection result corresponding to the first layout scheme satisfies a preset condition, the first layout scheme is used as the sensor layout scheme. 2. The method according to claim 1, further comprising: If the obstacle detection result corresponding to the first layout scheme does not meet the preset condition, perform the first layout scheme according to the obstacle detection result corresponding to the first layout scheme and the three-dimensional model of the vehicle. Adjust until the obstacle detection result corresponding to the adjusted layout scheme satisfies the preset condition. 3. The method according to claim 1, characterized in that, according to the geometric model of the obstacle and the effective detection range corresponding to each type of sensor in the first layout scheme, the corresponding detection range of the obstacle is obtained. detection results, including: According to the geometric model of the obstacle, the installation position and the effective detection range of each type of sensor in the first layout scheme, respectively determine the position of each type of sensor in the first layout scheme in the obstacle In the case of different positions, the detection result of the obstacle; The detection results of the obstacles of the various types of sensors in the first layout scheme are fused to obtain the detection results corresponding to the obstacles. 4. The method according to claim 3, characterized in that, according to the geometric model of the obstacle, the installation position and the effective detection range of each type of sensor in the first layout scheme, the The detection results of each type of sensor in the first layout scheme to the obstacle when the obstacle is in a different position include: determining a plurality of position points of the obstacle within a preset range, the preset range being centered on the center point of the vehicle; When the obstacle is located at each of the position points, according to the geometric model of the obstacle, and the installation position and effective detection range of each type of sensor in the first layout scheme, each The number of obstacle detection points and the obstacle detection area obtained by detecting the obstacle by the type of sensor; If the number of the obstacle detection points is greater than or equal to the first judgment threshold, and the ratio of the obstacle detection area to the area of the obstacle itself is greater than or equal to the second judgment threshold, then it is determined that this type of sensor is suitable for all The detection result of the obstacle is detected; if the number of detection points of the obstacle is less than the first judgment threshold, or the ratio of the detection area of the obstacle to the area of the obstacle itself is less than the second judgment threshold , then it is determined that the detection result of this type of sensor for the obstacle is not detected. 5 . The method according to claim 4 , wherein the detection result corresponding to the obstacle is used to indicate which types of sensors detect the obstacle at different positions. 6. The method according to claim 1, wherein the obtaining the effective detection range corresponding to each of the temporary sensors according to the obstacle detection model corresponding to each of the temporary sensors and the three-dimensional model of the vehicle includes : For each of the temporary sensors, according to the obstacle detection model corresponding to the temporary sensor, determine the actual detection range corresponding to the temporary sensor; Determine the occlusion detection range corresponding to the temporary sensor according to the obstacle detection model corresponding to the temporary sensor and the three-dimensional model of the vehicle; The effective detection range of the temporary sensor is determined according to the actual detection range and the occlusion detection range. 7. The method according to claim 1, wherein said determining a first layout scheme according to the three-dimensional model of the vehicle and the identifications of the plurality of candidate sensors comprises: According to the three-dimensional model of the vehicle, determine a plurality of candidate positions corresponding to the vehicle where sensors can be installed; A first layout scheme is determined according to the plurality of candidate positions and the identifiers of the plurality of candidate sensors. 8. A device for determining a sensor layout scheme, characterized in that it comprises: An acquisition module, configured to acquire model parameters of the vehicle and identifications of a plurality of candidate sensors; the model parameters of the vehicle include a three-dimensional model of the vehicle; A determining module, configured to determine a first layout scheme according to the three-dimensional model of the vehicle and the identifications of the plurality of candidate sensors; the first layout scheme includes identifications of a plurality of temporary sensors, and each of the temporary sensors is The temporary installation position of the vehicle, the plurality of temporary sensors are a subset of the plurality of candidate sensors; according to the obstacle detection model corresponding to each of the temporary sensors and the three-dimensional model of the vehicle, each of the temporary For the effective detection range corresponding to the sensor, according to the effective detection range corresponding to each of the temporary sensors and the type to which each of the temporary sensors belongs, obtain the effective detection range corresponding to each type of sensor in the first layout scheme; For each obstacle in the plurality of obstacles, according to the geometric model of the obstacle and the effective detection range corresponding to each type of sensor in the first layout scheme, the detection result corresponding to the obstacle is obtained; according to The detection results corresponding to each of the plurality of obstacles are determined to determine the obstacle detection results corresponding to the first layout scheme; if the obstacle detection results corresponding to the first layout scheme meet the preset conditions, the first The layout scheme is used as the sensor layout scheme. 9. An electronic device, characterized in that it comprises: at least one processor; and a memory communicatively coupled to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, the instructions are executed by the at least one processor, so that the at least one processor can perform any one of claims 1 to 7. Methods. 10. A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to make the computer execute the method according to any one of claims 1-7.