Road geometry recognition method and device

Abstract

The present application provides a road geometry recognition method and device, which relates to the field of assisted driving or unmanned driving, and is used to determine road geometry based on sensor measurement data, reduce the influence of non-road factors, so as to improve the accuracy of determining road geometry and better assist the vehicle in determining driving strategies. The method includes: generating at least one first cluster based on the measurement data of the sensor, the first cluster includes at least one first measurement data, and the measurement data includes at least the location information of the target object. Then determine the weight value of at least one first grid cell corresponding to the first measurement data in the position grid, and determine the cumulative weight value of the first grid cell based on all the first measurement data in the first cluster. The position grid includes at least one grid cell, and each grid cell corresponds to at least one first parameter. Finally, according to the cumulative weight value of the first grid cell, determine that the target object corresponding to the first measurement data contained in the first cluster is the road geometry.

Description

Technical Field

[0001] The present application relates to the technical field of autonomous driving (including assisted driving and unmanned driving), and in particular to a road geometry recognition method and device. Background Art

[0002] Autonomous driving (including assisted driving and unmanned driving) is an important direction for the development of smart cars, and more and more vehicles are beginning to use autonomous driving systems to realize the vehicle's autonomous driving function. Generally, the autonomous driving system needs to determine the vehicle's drivable area at any time. In the process of determining the drivable area, an important aspect is to determine the road geometry of the current driving road.

[0003] The existing road geometry detection technology currently uses a camera to collect road images, and then determines the road geometry after extraction and analysis by an image recognition system. However, the images collected by the camera are easily affected by multiple factors such as the environment, weather, and lighting, and the road geometry is easily blocked by other vehicles during the driving process. Therefore, under the influence of factors such as weather, lighting, or occlusion, the color, road edge, and other information in the image collected by the existing technology for the same road may be greatly different from the actual situation, thereby reducing the accuracy of determining the road geometry. Summary of the invention

[0004] The present application provides a road geometry recognition method and device to improve the accuracy of determining road geometry, reduce the impact of non-road factors, and better assist vehicles in determining driving strategies.

[0005] In order to achieve the above objectives, this application adopts the following technical solutions:

[0006] In the first aspect, an embodiment of the present application provides a road geometry recognition method, which is applied to a device with an automatic driving (including assisted driving) function, such as a vehicle, a chip system in a vehicle, and an operating system and a driver running on a processor. The method includes: generating at least one first cluster based on the measurement data of the sensor, the first cluster includes at least one first measurement data, and the measurement data includes at least the location information of the target object. Then determine the weight value of at least one first grid unit corresponding to the first measurement data in the position grid, and then determine the cumulative weight value of the first grid unit based on all the first measurement data in the first cluster, the position grid includes at least one grid unit, and each grid unit corresponds to at least one first parameter. Finally, according to the cumulative weight value of the first grid unit, determine that the target object corresponding to the first measurement data contained in the first cluster is road geometry.

[0007] In the road geometry recognition method described in the embodiment of the present application, first, the present application performs clustering processing on the measurement data, which can filter out some irrelevant clutter signals and measurement data of other objects, thereby reducing the workload and complexity of determining the road geometry, and improving the accuracy of determining the road geometry based on the measurement data. Secondly, the cumulative weight value of the first grid cell is determined based on the measurement data, and then whether the target object corresponding to the measurement data is the road geometry is determined based on the cumulative weight value, which can further filter out the interference of non-road information, improve the accuracy of determining the road geometry, and thus better assist the vehicle in determining the driving strategy.

[0008] In one possible design, the road geometry includes at least one of a road edge, a guardrail, and a lane line.

[0009] In one possible design, the position grid is determined according to the detection range of the sensor and / or the resolution unit size of the sensor.

[0010] In a possible design, before determining the weight value of at least one first grid unit corresponding to the first measurement data in the position grid, the method further includes: according to the first preset condition |x k cosθ i +y k sinθ i -ρ j |≤d Thresh , determine at least one first grid unit corresponding to the first measurement data in the position grid, where (x k ,y k ) is the position coordinate of the kth first measurement data, (θ i , ρ j ) is at least one first parameter corresponding to the first grid unit (i, j), d Thresh is a first preset value, and k is an integer greater than 0. In a possible design, the measurement data further includes the echo intensity (EI) of the target object.

[0011] In one possible design, determining a weight value of at least one first grid cell corresponding to the first measurement data in the position grid includes: determining a weight value of at least one first grid cell corresponding to the first measurement data in the position grid based on an echo intensity EI in the first measurement data, or an echo intensity EI and position information in the first measurement data.

[0012] In one possible design, determining the weight value of at least one first grid unit corresponding to the first measurement data in the location grid includes: determining the weight value of at least one first grid unit corresponding to the first measurement data in the location grid according to a first preset algorithm. The first preset algorithm may be in the form of an exponential function: Or the first preset algorithm can be in the form of a logarithmic function: or Or the first preset algorithm can be in the form of a constant: △w i,j =λ / N.

[0013] Among them, △w i,j is the weight value of at least one first grid unit (i, j) corresponding to the kth first measurement data in the position grid, (θ i , ρ j ) is at least one first parameter corresponding to the first grid unit (i, j), EI k is the echo intensity EI in the kth first measurement data, N is the number of first measurement data in the first cluster where the kth first measurement data is located, σ EI and EI RB / GR is the inherent attribute of road geometry, σ EI is the standard deviation of EI of road geometry, EI RB / GR is the EI average value of the road geometry, σ is the second preset value, and λ is the fifth preset value.

[0014] In one possible design, all first grid cells whose cumulative weight values ​​are greater than a predefined threshold are first determined, and then a first expression for representing a first shape of the road geometry is determined based on all first grid cells whose cumulative weight values ​​are greater than the predefined threshold. In the first expression Determined according to the first parameters corresponding to all first grid cells whose cumulative weight values ​​are greater than the predefined threshold, (x, y) is the position coordinate of the road geometry. It should be noted that the predefined threshold can be customized as needed. In one possible design, the M first grid cells with the largest cumulative weights can be directly selected, which is equivalent to setting the predefined threshold so that it is only less than the M first grid cells with the largest cumulative weight values, and determining the first expression for representing the first shape of the road geometry according to the first parameters corresponding to the M first grid cells.

[0015] In the road geometry recognition method described in the embodiment of the present application, the echo intensity EI and the position information in the measurement data are comprehensively considered when determining the weight value of the first grid unit. Therefore, the technical solution of filtering the measurement data corresponding to the target object using the cumulative weight value of the first grid unit to determine the first shape of the road geometry can well reduce the influence of non-road factors and improve the accuracy of determining the first shape of the road geometry. Secondly, the first shape of the road geometry determined according to the cumulative weight value of the first grid unit is at least one short line segment (which can relatively easily represent straight roads and uniform curves). Therefore, this method is more suitable for determining the shape of the road geometry on straight roads and uniform curves, thereby better assisting the vehicle in determining the driving strategy on straight roads and uniform curves.

[0016] In one possible design, at least one second cluster is generated based on the measurement data, and the second cluster includes at least one second measurement data. Then, a weight value of at least one second grid cell corresponding to the second measurement data in the location grid is determined, and then a cumulative weight value of the second grid cell is determined based on all the second measurement data in the second cluster. Finally, the road geometry corresponding to the second measurement data included in the second cluster is determined based on the cumulative weight value of the second grid cell.

[0017] In a possible design, all second grid cells whose cumulative weight values ​​are greater than a predefined threshold are first determined. If all first grid cells whose cumulative weight values ​​are greater than the predefined threshold and all second grid cells whose cumulative weight values ​​are greater than the predefined threshold meet a second preset condition, a second expression is determined based on all first grid cells whose cumulative weight values ​​are greater than the predefined threshold and second grid cells whose cumulative weight values ​​are greater than the predefined threshold. The second expression is used to represent the second shape of the road geometry. The second preset condition is or Determined according to the first parameters corresponding to all first grid cells whose cumulative weight values ​​are greater than a predefined threshold, Determined according to the first parameter corresponding to all second grid cells whose cumulative weight values ​​are greater than the predefined threshold, Thresh is the second preset value, p is the third preset value, and q is the fourth preset value. The second expression is Determined according to the first parameter corresponding to all first grid cells whose cumulative weight values ​​are greater than a predefined threshold and the first parameter corresponding to all second grid cells whose cumulative weight values ​​are greater than a predefined threshold, (x, y) is the location coordinate of the road geometry.

[0018] In a possible design, the value of the predefined threshold is customized to determine the M second grid cells with the largest cumulative weight values ​​and the M first grid cells with the largest cumulative weight values. If the M first grid cells with the largest cumulative weight values ​​and the M second grid cells with the largest cumulative weight values ​​meet the second preset condition, a second expression is determined based on the M first grid cells with the largest cumulative weight values ​​and the M second grid cells with the largest cumulative weight values, and the second expression is used to represent the second shape of the road geometry. The second preset condition is or Determined according to the first parameter corresponding to the M first grid cells with the largest cumulative weight values, Determined according to the first parameter corresponding to the M second grid units with the largest cumulative weight values, Thresh is the second preset value, p is the third preset value, and q is the fourth preset value. The second expression is Determined according to the first parameters corresponding to the M first grid cells with the largest cumulative weight values ​​and the first parameters corresponding to the M second grid cells with the largest cumulative weight values, (x, y) is the location coordinate of the road geometry.

[0019] In the road geometry recognition method described in the embodiment of the present application, firstly, the determination of the cumulative weight value comprehensively considers the position of the target object and the echo intensity EI of the target object, so the use of the cumulative weight value to determine the second expression for representing the second shape of the road geometry can reduce the influence of non-road factors and improve the accuracy of determining the second shape of the road geometry. Secondly, the second shape of the road geometry determined according to all the selected first grid cells and second grid cells is at least one long line segment, so the method can well determine the shape of the road geometry on the long straight road, thereby better assisting the vehicle in determining the driving strategy on the long straight road.

[0020] In one possible design, all second grid units whose cumulative weight values ​​are greater than a predefined threshold are first determined. If all first grid units whose cumulative weight values ​​are greater than the predefined threshold (or the M first grid units with the largest cumulative weight values) and all second grid units whose cumulative weight values ​​are greater than the predefined threshold (or the M second grid units with the largest cumulative weight values) meet the second preset condition, the first cluster and the second cluster are merged to obtain a third cluster, and the third cluster includes at least one third measurement data. A plurality of second parameters are determined based on the third measurement data in the third cluster and the second preset algorithm, wherein the second preset algorithm may be a least squares method or a gradient descent method. Based on the plurality of second parameters, a spiral is determined, and the spiral is used to represent the third shape of the road geometry. The second preset condition is or Determined according to the first parameters corresponding to all first grid cells whose cumulative weight values ​​are greater than a predefined threshold, Determined according to the first parameter corresponding to all second grid cells whose cumulative weight values ​​are greater than the predefined threshold, Thresh is the second preset value, p is the third preset value, q is the fourth preset value, and the expression of the clothoid spiral is y=c0+c1x+c2x 2 +c3x 3 , c0, c1, c2 and c3 are multiple second parameters, and (x, y) are the location coordinates of the road geometry.

[0021] In the road geometry recognition method described in the embodiment of the present application, the third shape of the road geometry is determined based on the measurement data in the third cluster obtained after the first cluster and the second cluster are merged. It can be considered that the data in the third cluster belongs to the same road geometry, excluding the interference of noise and other objects or other road geometry. Therefore, the third shape of the road geometry determined by the above road geometry recognition method is more complete. In addition, using a clothoid spiral to represent the third shape of the road geometry is more practical, and the shape of the road geometry at the turn and various straight / non-straight roads can be determined more accurately, thereby better assisting the vehicle in determining the driving strategy in various road conditions such as bends and straight roads.

[0022] In one possible implementation, the measurement data also includes the radial velocity of the target object and the position information of the target object: including the distance between the target object and the sensor and the angle information of the target object relative to the sensor. The sensor velocity estimation value is determined by calculating all the measurement data corresponding to the road geometry and the sensor velocity estimation algorithm. The sensor velocity estimation algorithm is: , v is the estimated value of the sensor speed, H is the radial speed observation matrix of the road geometry, H is determined according to the angle information of the road geometry relative to the sensor in the measurement data corresponding to the road geometry, H T is the transposed matrix of H, is the radial velocity matrix in the measured data corresponding to the road geometry.

[0023] By adopting the above-mentioned road geometry recognition method, the speed of the sensor is determined according to the measurement data corresponding to the road geometry and the sensor speed estimation algorithm, which generally also corresponds to the speed of the autonomous driving vehicle, so that the autonomous driving vehicle can better determine the driving strategy according to the sensor speed and road geometry to adjust its own speed, position and / or direction.

[0024] In a second aspect, an embodiment of the present application provides a road geometry recognition device, which has the function of implementing any of the road geometry recognition methods in the first aspect. The function can be implemented by hardware, or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions.

[0025] In a third aspect, the present application provides a road geometry recognition device, which may be a vehicle, or a device that can support the vehicle to realize the automatic driving function, and can be used in combination with the vehicle, such as a device in the vehicle (such as a sensor in the vehicle, or an operating system and / or driver running on a computer system of the vehicle). The device includes a generation module and a determination module, which can perform the corresponding functions performed by the road geometry recognition device in any of the design examples of the first aspect above, specifically:

[0026] The generating module is used to generate at least one first cluster according to the measurement data, wherein the first cluster includes at least one first measurement data, and the measurement data includes at least position information of the target object.

[0027] The determination module is used to determine a weight value of at least one first grid unit corresponding to the first measurement data in the location grid, the location grid includes at least one grid unit, wherein each grid unit corresponds to at least one first parameter.

[0028] The determination module is used to determine the cumulative weight value of the first grid unit according to all the first measurement data in the first cluster. According to the cumulative weight value of the first grid unit, it is determined that the target object corresponding to the first measurement data contained in the first cluster is a road geometry.

[0029] In one possible design, the road geometry includes at least one of a road edge, a guardrail, and a lane line.

[0030] In a possible design, the generating module is further used to determine the position grid according to the detection range of the sensor and / or the resolution unit size of the sensor.

[0031] In a possible design, the determination module is further used to determine at least one first grid unit corresponding to the first measurement data in the position grid according to a first preset condition. The first preset condition is |x k cosθ i +y k sinθ i -ρ j |≤d Thresh ,(x k ,y k ) is the position coordinate of the kth first measurement data, (θ i , ρ j) is at least one first parameter corresponding to the first grid unit (i, j), d Thresh is a first preset value, and k is an integer greater than 0.

[0032] In a possible design, the measurement data further includes the echo intensity EI of the target object.

[0033] In one possible design, the determination module is specifically used to determine the weight value of at least one first grid unit corresponding to the first measurement data in the position grid based on the echo intensity EI in the first measurement data, or the echo intensity EI and position information in the first measurement data.

[0034] In a possible design, the determination module is specifically used to determine a weight value of at least one first grid cell corresponding to the first measurement data in the location grid according to a first preset algorithm.

[0035] The first preset algorithm may be in the form of an exponential function: or Or the first preset algorithm can be in the form of a logarithmic function: Or the first preset algorithm can be in the form of a constant: △w i,j =λ / N.

[0036] Among them, △w i,j is the weight value of at least one first grid unit (i, j) corresponding to the kth first measurement data in the position grid, (θ i , ρ j ) is at least one first parameter corresponding to the first grid unit (i, j), EI k is the echo intensity EI in the kth first measurement data, N is the number of first measurement data in the first cluster where the kth first measurement data is located, σ EI and EI RB / GR is the inherent attribute of road geometry, σ EI is the standard deviation of EI of road geometry, EI RB / GR is the EI average value of the road geometry, σ is the second preset value, and λ is the fifth preset value.

[0037] In a possible design, the determination module is further used to determine all first grid cells whose cumulative weight values ​​are greater than a predefined threshold. Then, the determination module determines a first expression for representing the first shape of the road geometry based on all first grid cells whose cumulative weight values ​​are greater than the predefined threshold. The first expression is Determined according to the first parameters corresponding to all first grid cells whose cumulative weight values ​​are greater than a predefined threshold, (x, y) is the location coordinate of the road geometry.

[0038] In a possible design, the generating module is further used to generate at least one second cluster according to the measurement data; the second cluster includes at least one second measurement data.

[0039] The determination module is further used to determine the weight value of the second grid unit corresponding to the second measurement data in the position grid. Then, the determination module determines the cumulative weight value of the second grid unit based on all the second measurement data in the second cluster. Finally, the target object corresponding to the second measurement data contained in the second cluster is determined to be a road geometry based on the cumulative weight value of the second grid unit.

[0040] In a possible design, the determination module is further used to determine all second grid cells whose cumulative weight values ​​are greater than a predefined threshold. Then, when all first grid cells whose cumulative weight values ​​are greater than the predefined threshold and all second grid cells whose cumulative weight values ​​are greater than the predefined threshold meet a second preset condition, the determination module determines a second expression according to all first grid cells whose cumulative weight values ​​are greater than the predefined threshold and the second grid cells whose cumulative weight values ​​are greater than the predefined threshold, and the second expression is used to represent the second shape of the road geometry. The second preset condition is or Determined according to the first parameters corresponding to all first grid cells whose cumulative weight values ​​are greater than a predefined threshold, Determined according to the first parameter corresponding to all second grid cells whose cumulative weight values ​​are greater than the predefined threshold, Thresh is the second preset value, p is the third preset value, and q is the fourth preset value. The second expression is Determined according to the first parameters corresponding to all first grid cells whose cumulative weight values ​​are greater than a predefined threshold and the first parameters corresponding to all second grid cells whose cumulative weight values ​​are greater than a predefined threshold, (x, y) is the location coordinate of the road geometry.

[0041] In a possible design, the value of the predefined threshold is customized, and the determination module is further used to determine the M second grid cells with the largest cumulative weight values ​​and the M first grid cells with the largest cumulative weight values. The determination module is used to determine a second expression based on the M first grid cells with the largest cumulative weight values ​​and the M second grid cells with the largest cumulative weight values ​​when the M first grid cells with the largest cumulative weight values ​​and the M second grid cells with the largest cumulative weight values ​​meet the second preset condition, and the second expression is used to represent the second shape of the road geometry. The second preset condition is or Determined according to the first parameter corresponding to the M first grid cells with the largest cumulative weight values, Determined according to the first parameter corresponding to the M second grid units with the largest cumulative weight values, Thresh is the second preset value, p is the third preset value, and q is the fourth preset value. The second expression is Determined according to the first parameters corresponding to the M first grid cells with the largest cumulative weight values ​​and the first parameters corresponding to the M second grid cells with the largest cumulative weight values, (x, y) is the location coordinate of the road geometry.

[0042] In one possible design, the determination module is used to, after determining that all second grid units with cumulative weight values ​​greater than a predefined threshold (or the M second grid units with the largest cumulative weight values), merge the first cluster and the second cluster to obtain a third cluster when all first grid units with cumulative weight values ​​greater than the predefined threshold and all second grid units with cumulative weight values ​​greater than the predefined threshold (or the M second grid units with the largest cumulative weight values) meet a second preset condition. The third cluster includes at least one third measurement data. A plurality of second parameters are determined based on the third measurement data in the third cluster and a second preset algorithm, wherein the second preset algorithm is a least squares method or a gradient descent method. The determination module then determines a spiral of a third shape for representing road geometry based on the plurality of second parameters, wherein the second preset condition is or Determined according to the first parameters corresponding to all first grid cells whose cumulative weight values ​​are greater than a predefined threshold, Determined according to the first parameter corresponding to all second grid cells whose cumulative weight values ​​are greater than the predefined threshold, Thresh is the second preset value, p is the third preset value, and q is the fourth preset value. The spiral is y=c0+c1x+c2x 2 +c3x 3 , c0, c1, c2 and c3 are multiple second parameters, and (x, y) are the location coordinates of the road geometry.

[0043] In one possible design, the determination module is further used to determine the sensor speed estimation value by calculating based on all the measurement data corresponding to the road geometry and the sensor speed estimation algorithm. The sensor speed estimation algorithm is: v is the estimated value of the sensor speed, H is the radial speed observation matrix of the road geometry, H is determined according to the angle information of the road geometry relative to the sensor in the measurement data corresponding to the road geometry, H T is the transposed matrix of H, is the radial velocity matrix in the measured data corresponding to the road geometry.

[0044] In a fourth aspect, a road geometry recognition device is provided, comprising: a processor and a memory; the memory is used to store computer execution instructions, and when the road geometry recognition device is running, the processor executes the computer execution instructions stored in the memory to enable the road geometry recognition device to perform the road geometry recognition method as described in the first aspect and any one of the first aspects.

[0045] In a fifth aspect, a road geometry recognition device is provided, comprising: a processor; the processor is used to couple with a memory, and after reading instructions in the memory, execute the road geometry recognition method as described in the first aspect and any one of the first aspects according to the instructions.

[0046] In the sixth aspect, an embodiment of the present application also provides a computer-readable storage medium, comprising instructions, which, when executed on a computer, enables the computer to execute a road geometry recognition method as described in the first aspect and any one of the first aspects.

[0047] In the seventh aspect, an embodiment of the present application also provides a computer program product, including instructions, which, when executed on a computer, enables the computer to execute a road geometry recognition method as described in the first aspect and any one of the first aspects.

[0048] In an eighth aspect, an embodiment of the present application provides a road geometry recognition device, which may be a chip system, the chip system including a processor and a memory, for implementing the functions of the above method. The chip system may be composed of a chip, or may include a chip and other discrete devices.

[0049] In a ninth aspect, a road geometry recognition device is provided. The device may be a circuit system, wherein the circuit system includes a processing circuit, and the processing circuit is configured to execute a road geometry recognition method as described in the first aspect and any one of the first aspects.

[0050] In the tenth aspect, an embodiment of the present application provides a system, which includes the device of any one of the second to fifth aspects and the eighth and ninth aspects and / or the readable storage medium of the sixth aspect and / or the computer program product of the seventh aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 A schematic diagram of the structure of an autonomous driving vehicle provided in an embodiment of the present application Figure 1 ;

[0052] Figure 2 A schematic diagram of the structure of an autonomous driving vehicle provided in an embodiment of the present application Figure 2 ;

[0053] Figure 3 A schematic diagram of the structure of a computer system provided in an embodiment of the present application;

[0054] Figure 4 A schematic diagram of an application of a cloud-side command for an autonomous driving vehicle provided in an embodiment of the present application;

[0055] Figure 5 A schematic diagram of the structure of a computer program product provided in an embodiment of the present application;

[0056] Figure 6 Schematic diagram of the road geometry recognition method provided in the embodiment of the present application Figure 1 ;

[0057] Figure 6a A schematic diagram of measuring a target object provided in an embodiment of the present application;

[0058] Figure 6b A schematic diagram of a two-dimensional first clustering provided in an embodiment of the present application;

[0059] Figure 6c A schematic diagram of a three-dimensional first clustering provided in an embodiment of the present application;

[0060] Figure 6d A schematic diagram of a location grid provided in an embodiment of the present application;

[0061] Figure 6e A schematic diagram of at least one first grid unit corresponding to a first measurement data in a location grid provided in an embodiment of the present application Figure 1 ;

[0062] Figure 6f A schematic diagram of at least one first grid unit corresponding to a first measurement data in a location grid provided in an embodiment of the present application Figure 2 ;

[0063] Figure 7 Schematic diagram of the road geometry recognition method provided in the embodiment of the present application Figure 2 ;

[0064] Figure 8 Schematic diagram of the road geometry recognition method provided in the embodiment of the present application Figure 3 ;

[0065] Fig. 9 Schematic diagram of the road geometry recognition method provided in the embodiment of the present application Figure 4 ;

[0066] Fig.10 A schematic diagram of the structure of the road geometry recognition device provided in the embodiment of the present application Figure 1 ;

[0067] Fig.11 A schematic diagram of the structure of the road geometry recognition device provided in the embodiment of the present application Figure 2 . DETAILED DESCRIPTION

[0068] For ease of understanding, the relevant terms involved in the embodiments of the present application are explained as follows:

[0069] Autonomous driving: Autonomous driving technology relies on artificial intelligence, visual computing, radar, monitoring devices and global positioning systems to allow computers to automatically and safely operate motor vehicles without any human intervention. According to the classification standards of the Society of Automotive Engineers (SAE), autonomous driving technology is divided into: no automation (L0), driving support (L1), partial automation (L2), conditional automation (L3), high automation (L4) and full automation (L5).

[0070] Radial velocity: A physics term, generally refers to the velocity component of an object's movement in the direction of the observer's line of sight, that is, the projection of the velocity vector in the direction of the line of sight.

[0071] Radar cross section (RCS): RCS is an equivalent area. When the radar energy intercepted by this area is scattered isotropically to the surroundings, the power scattered within a unit solid angle is exactly equal to the power scattered by the target within a unit solid angle in the direction of the receiving antenna. For a certain radar data point, the radar cross section reflects the reflection intensity of the target object corresponding to that point.

[0072] Sonar target strength (sonar TS): Target strength (TS) quantitatively describes the size of the target's reflection ability and describes the acoustic characteristics of the target from the perspective of echo intensity.

[0073] Euclidean distance: The Euclidean metric (also known as the Euclidean distance) is a commonly used distance definition, which refers to the real distance between two points in n-dimensional space, or the natural length of a vector (that is, the distance from the point to the origin). The Euclidean distance in two-dimensional and three-dimensional space is the actual distance between two points. In n-dimensional space, the coordinates of the two points are (x1, x2, ..., x n ) and (y1, y2, …, y n ), then the Euclidean distance between these two points is

[0074] The road geometry recognition method provided in the embodiment of the present application is applied to a vehicle with an automatic driving or assisted driving function, or is applied to other devices (such as cloud servers) with a function of controlling automatic driving. The vehicle can implement the road geometry recognition method provided in the embodiment of the present application through its components (including hardware and software) to identify the road geometry. Alternatively, other devices (such as servers) are used to implement the road geometry recognition method of the embodiment of the present application, identify the road geometry, and determine the vehicle speed (i.e., the sensor speed) to formulate a driving strategy.

[0075] Figure 1 It is a functional block diagram of the vehicle 100 provided in an embodiment of the present application. In one embodiment, the vehicle 100 is configured as an assisted driving or a fully autonomous driving mode. For example, the vehicle 100 can identify the road geometry while being in an assisted driving or fully autonomous driving mode, and formulate a driving strategy based on the identified road geometry, thereby controlling the vehicle 100 to perform automated driving. After identifying the road geometry, the vehicle 100 can also match the road geometry with the stored map information to obtain more accurate environmental information, thereby determining a better driving strategy. When the vehicle 100 is in the autonomous driving mode, the vehicle 100 does not interact with the driver, and autonomously completes actions such as obstacle avoidance, following the vehicle, lane keeping, and automatic parking. When the vehicle 100 is in the assisted driving mode, the vehicle 100 prompts the driver according to the driving strategy, and the driver completes actions such as obstacle avoidance, following the vehicle, lane keeping, and automatic parking according to the prompt.

[0076] The vehicle 100 may include various subsystems, such as a travel system 110, a sensor system 120, a control system 130, one or more peripheral devices 140, and a power supply 150, a computer system 160, and a user interface 170. Optionally, the vehicle 100 may include more or fewer subsystems, and each subsystem may include multiple elements. In addition, each subsystem and element of the vehicle 100 may be interconnected by wire or wirelessly.

[0077] The travel system 110 may include components that provide power to the vehicle 110 , such as an engine, a transmission, and the like.

[0078] The sensor system 120 may include several sensors that sense information about the environment around the vehicle 100. For example, the sensor system 120 may include at least one of a positioning system 121 (the positioning system may be a GPS system, a Beidou system, or other positioning systems), an inertial measurement unit (IMU) 122, a radar sensor 123, a lidar 124, a visual sensor 125, an ultrasonic sensor 126, and a sonar sensor 127. Optionally, the sensor system 120 may also include sensors of the internal systems of the monitored vehicle 100 (e.g., an in-vehicle air quality monitor, a fuel gauge, an oil temperature gauge, etc.). Sensor data from one or more of these sensors may be used to detect objects and their corresponding characteristics (position, shape, direction, speed, etc.). Such detection and recognition are key functions for the safe operation of the autonomous vehicle 100.

[0079] Positioning system 121 may be used to estimate the geographic location of vehicle 100. IMU 122 is used to sense position and orientation changes of vehicle 100 based on inertial acceleration. In one embodiment, IMU 122 may be a combination of an accelerometer and a gyroscope.

[0080] The radar sensor 123 may use electromagnetic wave signals to sense objects in the surrounding environment of the vehicle 100. In some embodiments, in addition to sensing the position of the object, the radar sensor 123 may also be used to sense the radial velocity of the object and / or the radar cross section RCS of the object.

[0081] The ultrasonic sensor 126 may utilize ultrasonic waves to sense objects in the surrounding environment of the vehicle 100. In some embodiments, in addition to sensing the position of an object, the ultrasonic sensor 126 may also be used to sense the radial velocity of the object and / or the amplitude of the echo of the object.

[0082] The sonar sensor 127 may utilize sound waves to sense objects in the surrounding environment of the vehicle 100. In some embodiments, in addition to sensing the position of an object, the sonar sensor 127 may also be used to sense the radial velocity of the object and / or the sonar target strength (sonar TS) of the object.

[0083] Lidar 124 may utilize laser light to sense objects in the environment in which vehicle 100 is located. In some embodiments, Lidar 124 may include one or more laser sources, a laser scanner, and one or more detectors, among other system components.

[0084] The vision sensor 125 may be used to capture multiple images of the surrounding environment of the vehicle 100. The vision sensor 125 may be a still camera or a video camera.

[0085] The control system 130 may control the operation of the vehicle 100 and its components. The control system 130 may include various elements, such as at least one of a computer vision system 131, a path control system 132, and an obstacle avoidance system 133.

[0086] The computer vision system 131 can be operated to process and analyze images captured by the visual sensor 125 and measurement data obtained by the radar sensor 123 to identify objects and / or features in the environment surrounding the vehicle 100. The objects and / or features may include traffic signs, road boundaries, and obstacles. The computer vision system 131 can use object recognition algorithms, structure from motion (SFM) algorithms, video tracking, and other computer vision techniques. In some embodiments, the computer vision system 131 can be used to map the environment, track objects, estimate the speed of objects, and the like.

[0087] The route control system 132 is used to determine the driving route of the vehicle 100. In some embodiments, the route control system 132 can combine data from the radar sensor 123, the positioning system 121, and one or more predetermined maps to determine the driving route for the vehicle 100.

[0088] The obstacle avoidance system 133 is used to identify, evaluate, and avoid or otherwise negotiate potential obstacles in the environment of the vehicle 100 .

[0089] Of course, in one example, the control system 130 may include additional or alternative components other than those shown and described, or may reduce some of the components shown above.

[0090] The vehicle 100 may utilize a wireless communication system 140 to obtain the required information, wherein the wireless communication system 140 may wirelessly communicate with one or more devices directly or via a communication network. For example, the wireless communication system 140 may utilize 3G cellular communications, such as CDMA, EVDO, GSM / GPRS, or 4G cellular communications, such as LTE. Or 5G cellular communications. The wireless communication system 140 may utilize WiFi to communicate with a wireless local area network (WLAN). In some embodiments, the wireless communication system 140 may utilize an infrared link, Bluetooth, or ZigBee to communicate directly with the device. Other wireless protocols, such as various vehicle communication systems, for example, the wireless communication system 140 may include one or more dedicated short range communications (DSRC) devices.

[0091] Some or all functions of the vehicle 100 are controlled by a computer system 160. The computer system 160 may include at least one processor 161 that executes instructions 1621 stored in a non-transitory computer-readable medium such as a data storage device 162. The computer system 160 may also be a plurality of computing devices that control individual components or subsystems of the vehicle 100 in a distributed manner.

[0092] Processor 161 may be any conventional processor, such as a commercially available central processing unit (CPU). Alternatively, the processor may be a dedicated device such as an application specific integrated circuit (ASIC) or other hardware based processor. Figure 1 Functionally illustrated processors, memory, and other elements in the same physical housing, but those of ordinary skill in the art will appreciate that the processor, computer system, or memory may actually include multiple processors, computer systems, or memories that may be stored in the same physical housing, or may include multiple processors, computer systems, or memories that may not be stored in the same physical housing. For example, the memory may be a hard drive, or may be located in other storage media that are different from the physical housing. Therefore, references to processors or computer systems will be understood to include references to a collection of processors or computer systems or memories that may operate in parallel, or references to a collection of processors or computer systems or memories that may not operate in parallel. Different from using a single processor to perform the steps described herein, some components such as steering components and deceleration components may each have their own processors that perform only calculations related to component-specific functions.

[0093] In various aspects described herein, the processor may be located remote from the vehicle and in wireless communication with the vehicle. In other aspects, some of the processes described herein are performed on a processor disposed within the vehicle and others are performed by a remote processor, including taking the necessary steps to perform a single maneuver.

[0094] Optionally, the above components are only examples. In actual applications, the components in the above modules may be added or deleted according to actual needs. Figure 1 It should not be understood as limiting the embodiments of the present application.

[0095] An autonomous driving or assisted driving system car traveling on a road, such as vehicle 100 above, can identify the road geometry in its surrounding environment to determine its driving strategy or make corresponding auxiliary warnings. The road geometry can be lane lines, guardrails, green belts, road edges, or other objects. In some examples, each identified road geometry can be considered independently, and based on the respective characteristics of the road geometry, such as its position, the distance from the vehicle, etc., as well as the vehicle's driving speed, the subsequent route planning, it can be used to determine the driving strategy of the autonomous driving car.

[0096] Optionally, the autonomous vehicle 100 or a computing device associated with the autonomous vehicle 100 (eg, Figure 1 The computer system 160, computer vision system 131, data storage device 162) can predict and identify the road geometry based on the identified measurement data. Optionally, each identified road geometry depends on each other, so all the acquired measurement data can also be considered together to predict and identify a single road geometry. The vehicle 100 can adjust its driving strategy based on the predicted identified road geometry. In other words, the autonomous vehicle can determine what position the vehicle will need to be adjusted to based on the predicted road geometry. In this process, other factors can also be considered to determine the position of the vehicle 100, such as the status of surrounding vehicles during driving of the vehicle 100, weather conditions, etc.

[0097] In addition to providing instructions for identifying road geometry to adjust the driving strategy of the autonomous vehicle, the computing device can also provide instructions for adjusting the speed of the vehicle 100 so that the autonomous vehicle adjusts its speed (e.g., accelerates, decelerates, turns, or stops) to a safe speed to achieve a stable state while following a given trajectory and / or maintaining a safe lateral and longitudinal distance from objects near the autonomous vehicle (e.g., cars in adjacent lanes on the road), or in the assisted driving mode, the driver makes corresponding operations according to the steering, acceleration, and braking instructions on the display to make the vehicle reach a stable state.

[0098] The vehicle 100 may be a car, a truck, a motorcycle, a bus, a ship, an airplane, a helicopter, a lawn mower, an entertainment vehicle, an amusement park vehicle, construction equipment, a tram, a golf cart, a train, a cart, etc., and the embodiments of the present application are not particularly limited.

[0099] In other embodiments of the present application, the autonomous driving vehicle may further include a hardware structure and / or a software module to implement the above functions in the form of a hardware structure, a software module, or a hardware structure plus a software module. Whether one of the above functions is implemented in the form of a hardware structure, a software module, or a hardware structure plus a software module depends on the specific application and design constraints of the technical solution.

[0100] See also Figure 2 , exemplary, the vehicle may include the following modules:

[0101] The environment perception module 201 is used to obtain measurement data information of target objects detected by roadside sensors and vehicle-mounted sensors. The roadside sensors and vehicle-mounted sensors can be laser radars, millimeter wave radars, ultrasonic sensors, sonar sensors, etc. The data obtained by the environment perception module can be point cloud data detected by the radar. The environment perception module can process these data into measurement data such as the position, radial velocity, angle, size, etc. of identifiable target objects, and transmit these data to the rule control module so that the two control modules can generate driving strategies.

[0102] Rule control module 202: This module is a traditional control module of an autonomous driving vehicle, and is used to receive the vehicle's own status information (such as speed, position, etc.) and environmental information (such as road geometry, road conditions, weather conditions, etc.) from the environmental perception module, and identify the road geometry based on this information, generate a corresponding driving strategy, output the action instruction corresponding to the driving strategy, and send the action instruction to the vehicle control module 203, which is used to instruct the vehicle control module 203 to perform autonomous driving control of the vehicle.

[0103] The vehicle control module 203 is used to receive action instructions from the rule control module 202 to control the vehicle to complete the automatic driving operation.

[0104] Vehicle communication module 204 ( Figure 2 Not shown in the figure): used for information exchange between the vehicle and other vehicles.

[0105] Storage component 205 ( Figure 2 The executable code of each module is stored in the memory (not shown in the figure). Running these executable codes can implement part or all of the method flow of the embodiment of the present application.

[0106] In a possible implementation of the embodiment of the present application, as Figure 3 As shown, Figure 1The computer system 160 shown includes a processor 301, which is coupled to a system bus 302. The processor 301 can be one or more processors, each of which can include one or more processor cores. A display adapter 303 can drive a display 309, which is coupled to the system bus 302. The system bus 302 is coupled to an input / output (I / O) bus (BUS) 305 via a bus bridge 304. An I / O interface 306 is coupled to the I / O bus 305. The I / O interface 306 communicates with various I / O devices, such as an input device 307 (e.g., keyboard, mouse, touch screen, etc.), a multimedia disk (media tray) 308, (e.g., CD-ROM, multimedia interface, etc.). A transceiver 315 (which can send and / or receive radio communication signals), a camera 310 (which can capture static and dynamic digital video images), and an external universal serial bus (USB) interface 311. Optionally, the interface connected to the I / O interface 306 may be a USB interface.

[0107] The processor 301 may be any conventional processor, including a reduced instruction set computer (RISC) processor, a complex instruction set computer (CISC) processor, or a combination thereof. Alternatively, the processor may be a dedicated device such as an application specific integrated circuit (ASIC). Alternatively, the processor 301 may be a neural network processor or a combination of a neural network processor and the conventional processors described above.

[0108] Alternatively, in various embodiments described herein, the computer system 160 may be located remotely from the autonomous vehicle and may communicate wirelessly with the autonomous vehicle 100. In other aspects, some of the processes described herein may be set to be executed on a processor within the autonomous vehicle, and other processes may be performed by a remote processor, including taking actions required to perform a single maneuver.

[0109] Computer system 160 can communicate with software deployment server 313 through network interface 312. Network interface 312 is a hardware network interface, such as a network card. Network 314 can be an external network, such as the Internet, or an internal network, such as Ethernet or a virtual private network (VPN). Optionally, network 314 can also be a wireless network, such as a WiFi network, a cellular network, etc.

[0110] In some other embodiments of the present application, the road geometry recognition method of the present application embodiment can also be executed by a chip system. The present application embodiment provides a chip system. The host CPU (Host CPU) and the neural processing unit (neural processing unit, NPU) work together to achieve Figure 1 The corresponding algorithms for the functions required by the vehicle 100 can also be implemented Figure 2 The corresponding algorithms for the required functions of the vehicle shown can also be implemented Figure 3 The corresponding algorithms for the required functions of the computer system 160 are shown.

[0111] In other embodiments of the present application, the computer system 160 can also receive information from other computer systems or transfer information to other computer systems. Alternatively, the sensor data collected from the sensor system 120 of the vehicle 100 can be transferred to another computer, and the data is processed by another computer. The data from the computer system 160 can be transmitted to the computer system on the cloud side via the network for further processing. The network and the intermediate nodes can include various configurations and protocols, including the Internet, the World Wide Web, the intranet, a virtual private network, a wide area network, a local area network, a private network using one or more companies' proprietary communication protocols, Ethernet, WiFi and HTTP, and various combinations of the foregoing. This communication can be performed by any device capable of transmitting data to and from other computers, such as a modem and a wireless interface.

[0112] See also Figure 4 , is an example of interaction between an autonomous driving vehicle and a cloud service center (cloud server). The cloud service center can receive information (such as data collected by vehicle sensors or other information) from autonomous driving vehicles 413, 412 in its environment 400 via a network 411 such as a wireless communication network.

[0113] The cloud service center 420 runs the stored programs related to road geometry recognition based on the received data to recognize the geometry of the road traveled by the autonomous driving vehicles 413 and 412. The programs related to identifying the road geometry based on the measurement data may be: a program for clustering the measurement data, a program for determining the shape of the road geometry, or a program for determining the sensor speed.

[0114] Exemplarily, cloud service center 420 may provide portions of a map to vehicles 413, 412 via network 411. In other examples, operations may be divided between different locations. For example, multiple cloud service centers may receive, verify, combine, and / or send information reports. In some examples, information reports and / or sensor data may also be sent between vehicles. Other configurations are also possible.

[0115] like Figure 5 As shown, in some examples, the signal-bearing medium 501 may include a computer-readable medium 503, such as, but not limited to, a hard drive, a compact disk (CD), a digital video disk (DVD), a digital tape, a memory, a read-only memory (ROM) or a random access memory (RAM), etc. In some embodiments, the signal-bearing medium 501 may include a computer-recordable medium 504, such as, but not limited to, a memory, a read / write (R / W) CD, a R / W DVD, etc. In some embodiments, the signal-bearing medium 501 may include a communication medium 505, such as, but not limited to, a digital and / or analog communication medium (e.g., a fiber optic cable, a waveguide, a wired communication link, a wireless communication link, etc.). Thus, for example, the signal-bearing medium 501 may be communicated by a wireless form of communication medium 505 (e.g., a wireless communication medium that complies with the IEEE802.11 standard or other transmission protocol). One or more program instructions 502 may be, for example, computer executable instructions or logic implementation instructions. In some examples, such as for Figures 1 to 4 The computing device described can be configured to provide various operations, functions, or actions in response to program instructions 502 communicated to the computing device by one or more of computer-readable medium 503, and / or computer-recordable medium 504, and / or communication medium 505. It should be understood that the arrangement described here is only for the purpose of example. Thus, it will be understood by those skilled in the art that other arrangements and other elements (e.g., machines, interfaces, functions, sequences, and functional groups, etc.) can be used instead, and some elements can be omitted together according to the desired results. In addition, many of the elements described are functional entities that can be implemented as discrete or distributed components, or in any appropriate combination and position in combination with other components.

[0116] The road geometry recognition methods provided in the embodiments of the present application are all applied in automatic / semi-automatic driving scenarios, and can be Figure 1-Figure 4 The processor 161 and the processor 301 shown are executed. The road geometry recognition method of the embodiment of the present application is described in detail below with reference to various drawings.

[0117] The present application embodiment provides a road geometry recognition method, such as Figure 6 As shown, the method includes the following steps, Figure 6 , the embodiments of the present application are described:

[0118] S101. Generate at least one first cluster according to measurement data of a sensor.

[0119] The measurement data in the first cluster is first measurement data, the first cluster includes at least one first measurement data, the measurement data includes at least location information of the target object, and the target object is a road geometry or non-road geometry object such as other vehicles.

[0120] It is worth noting that before performing step S101, it is necessary to first obtain measurement data of the target object detected by the sensor. The measurement data at least includes the position information of the target object, and the position information of the target object includes the distance between the target object and the sensor and / or the angle information of the target object relative to the sensor (the angle information includes the azimuth angle and / or the pitch angle).

[0121] Optionally, the sensor in the embodiment of the present application is a radar sensor, an ultrasonic sensor or a sonar sensor, or other sensors, such as a laser radar. At this time, the measurement data also includes the echo intensity EI of the target object and / or the radial velocity of the target object relative to the sensor. When the sensor is a radar sensor or a laser radar, the EI in the measurement data is the radar scattering cross-sectional area RCS, when the sensor is a sonar sensor, the EI in the measurement data is the sonar target intensity sonar TS, and when the sensor is an ultrasonic sensor, the EI in the measurement data is the echo amplitude. Among them, the echo intensity is the intensity of the electromagnetic wave or sound wave reflected from the corresponding medium interface after the electromagnetic wave or sound wave is sent to different medium interfaces.

[0122] For example, the sensor is a radar sensor, the measurement data includes the position information of the target object, the RCS of the target object, and the radial velocity of the target object relative to the radar sensor, and the angle information in the position information of the target object is the azimuth. Figure 6a As shown, a coordinate system is established with the position of the radar sensor (i.e., the position of the vehicle) as the origin O. The x-axis direction is the movement direction of the radar sensor, the y-axis direction is perpendicular to the movement direction of the radar sensor, and the z-axis is established perpendicular to the x-axis and y-axis. The coordinates of the x-axis and y-axis represent the direct distance and lateral distance of the target object relative to the radar sensor, respectively, and the coordinate of the z-axis represents the radial velocity of the target object. The coordinates of the x-axis and y-axis can be obtained by the distance measurement and azimuth measurement collected by the radar sensor. The measurement data obtained by measuring the target object can be represented by the vector (x, y, z). If A is the target object, the measurement data obtained by the sensor measuring A is (x A ,y A , z A ), where x A and AThey represent the facing distance and lateral distance of A relative to the radar sensor, α represents the azimuth angle of A relative to the radar sensor, the length of line segment OA is the distance from the radar sensor to A, and z A Represents the radial velocity of A. If the volume (or area) of A is used to represent the RCS size of A, the measurement data can be expressed by the vector (x A ,y A , z A , RCS A ) means that if the pitch angle information of the target object is added, the original vector can be expanded to (x A ,y A , z A , v A , RCS A ).

[0123] In a possible implementation, after the measurement data of the sensor is acquired, the measurement data is clustered by using a clustering algorithm to obtain at least one first cluster.

[0124] Exemplarily, the clustering algorithm can be a density-based spatial clustering of applications with noise (DBSCAN) method, an ordering points to identify the clustering structure (OPTICS) method, or a hierarchical density-based spatial clustering of applications with noise (HDBSCAN) method. It is worth noting that the clustering algorithm can also be a model-based clustering method, and is not limited to the clustering algorithms mentioned in the embodiments of the present application.

[0125] For example, the measurement data includes the location information of the target object (including the distance and azimuth between the target object and the sensor), and the clustering algorithm is DBSCAN. The measurement data can be represented by a vector (x, y), where x represents the distance of the target object relative to the sensor, and y represents the lateral distance of the target object relative to the sensor. x and y can be obtained by the distance measurement and azimuth measurement collected by the sensor. There are 9 measurement data, namely A, B, C, D, E, F, G, H, and I. These 9 measurement data are represented by vectors (x, y, and y). A ,y A )、(x B ,y B )、(xC ,y C )、(x D ,y D )、(x E ,y E )、(x F ,y F )、(x G ,y G )、(x H ,y H )、(x I ,y I ) is represented by. The Euclidean distances between the nine measurement data are calculated, and according to the size of the Euclidean distances between the nine measurement data, the measurement data with smaller Euclidean distances and not greater than a preset threshold are classified into the same cluster, and multiple clusters are obtained, such as Figure 6b As shown, the first cluster is a cluster including A, B, and C, or a cluster including D, E, and F, or a cluster including G, H, and I.

[0126] For example, the measurement data includes the position information of the target object and the radial velocity of the target object, and the clustering algorithm is DBSCAN. The measurement data can be represented by a vector (x, y, z), where x represents the distance of the target object relative to the sensor, y represents the lateral distance of the target object relative to the sensor, and z represents the radial velocity of the target object. x and y can be obtained by the distance measurement and azimuth measurement collected by the sensor. There are 6 measurement data, namely A, B, C, D, E, and F. These 6 measurement data are represented by (x A ,y A , z A )、(x B ,y B , z B )、(x C ,y C , z C )、(x D ,y D , z D )、(x E ,y E , z E )、(x F ,y F , z F ) is represented by. The Euclidean distances between the six measurement data are calculated. According to the size of the Euclidean distances between the six measurement data, the measurement data with smaller Euclidean distances and not greater than a preset threshold are classified into the same cluster, and multiple clusters are obtained, such as Figure 6c As shown, the first cluster is a cluster including A, B, and C or a cluster including D, E, and F.

[0127] For example, the measurement data includes the location information of the target object (including the distance between the target object and the sensor, the azimuth and pitch angle of the target object relative to the sensor), and the clustering algorithm is DBSCAN. The measurement data is represented by a vector (x, y, v), where x represents the direct distance of the target object relative to the sensor, y represents the lateral distance of the target object relative to the sensor, and v represents the height of the target object relative to the sensor. x, y, and v can be obtained by the distance measurement, azimuth measurement, and pitch angle measurement collected by the sensor. There are 6 measurement data, namely A, B, C, D, E, and F. These 6 measurement data are represented by (x, y, v). A ,y A , v A )、(x B ,y B , v B )、(x C ,y C , v C )、(x D ,y D , v D )、(x E ,y E , v E )、(x F ,y F , v F ) is represented by. The Euclidean distances between the six measurement data are calculated, and according to the size of the Euclidean distances between the six measurement data, the measurement data with smaller Euclidean distances (not greater than a preset threshold) are classified into the same cluster to obtain multiple clusters. Among them, the first cluster is a cluster including A, B, and C or a cluster including D, E, and F.

[0128] For example, the measurement data includes the location information of the target object (including the distance between the target object and the sensor, and the azimuth of the target object relative to the sensor), and the clustering algorithm is DBSCAN. The measurement data is represented by a vector (d, ) represents, d represents the distance between the target object and the sensor, Indicates the azimuth of the target object relative to the sensor. There are three measurement data, A, B, and C. These three measurement data are represented by (d A , )、(d B , ) and (d C , ) represents. The Euclidean distances between the three measurement data are calculated, and clustering is performed according to the size of the Euclidean distances between the three measurement data. The measurement data with a smaller Euclidean distance and not greater than a preset threshold are divided into the same cluster, and the first cluster is obtained as a cluster including A, B, and C.

[0129] For example, the measurement data includes the position information of the target object (including the distance between the target object and the sensor, the azimuth of the target object relative to the sensor), the radial velocity of the target object relative to the sensor, and the clustering algorithm is DBSCAN. The measurement data is represented by a vector (d, z) represents, d represents the distance between the target object and the sensor, represents the azimuth angle of the target object relative to the sensor, and z represents the radial velocity of the object. There are three measurement data, namely A, B and C, which are expressed as (d A , z A )、(d B , z B ) and (d C , z C ) represents. The Euclidean distance between the three measurement data is calculated, and the three measurement data are clustered according to the size of the Euclidean distance between them. The measurement data with a smaller Euclidean distance and not greater than a preset threshold are divided into the same cluster, and the first cluster is obtained as a cluster including A, B, and C.

[0130] Optionally, when the measurement data includes the echo intensity EI of the target object, this parameter can be added during clustering. For example, the measurement data includes the three-dimensional position information of the target object, which can be represented as a vector (x, y, v), where x represents the direct distance of the target object relative to the sensor, y represents the tangential distance of the target object relative to the sensor, and v represents the height of the target object relative to the sensor. x, y, and v can be obtained by the distance measurement, azimuth measurement, and pitch angle measurement collected by the sensor. If the measurement data also includes the echo intensity EI of the target object, the measurement data can be represented as a vector (x, y, v, e), where e represents the echo intensity EI of the target object. Similarly, the clustering result is determined based on the Euclidean distance between each measurement data vector.

[0131] It should be noted that, first of all, compared with the solution of determining the road edge using images collected by the camera, the radar sensor, sonar sensor or ultrasonic sensor used in the embodiment of the present application has higher accuracy and stability in the measurement data collected, and is not easily affected by factors such as light. Therefore, determining the road geometry based on the measurement data can improve the accuracy of determining the road geometry. In addition, through the above process, clustering processing is performed on the measurement data collected by the sensor, which can effectively filter out interference information in the measurement data, such as irrelevant clutter signals and measurement data of other objects, reduce the workload and complexity of data processing, and improve the accuracy of determining the road geometry, thereby better assisting the vehicle in determining the driving strategy.

[0132] S102: Determine at least one first grid unit corresponding to the first measurement data in the location grid.

[0133] The measurement data in the first cluster is first measurement data, each first cluster includes at least one first measurement data, the location grid includes at least one grid unit, and each grid unit corresponds to at least one first parameter.

[0134] Optionally, before step S102, it is also necessary to determine the position grid based on the detection range of the sensor and the resolution unit size of the sensor, wherein the detection range of the sensor is used to determine the size of the position grid, and the resolution unit size of the sensor is used to determine the preset grid resolution unit size, and then the position grid is determined based on the size of the position grid and the preset grid resolution unit size, and the size of the preset grid resolution unit can also be determined based on actual conditions.

[0135] For example, Figure 6d As shown in the figure, at least one first parameter (i.e., the coordinate of the lower left corner of the grid cell) corresponding to each grid cell in the position grid is (ρ, θ). If the maximum detection distance of the sensor is Rm and the resolution unit size is 0.1m, then the value range of ρ is [0, 2R] or [-R, R], the value range of θ is [0, π] or [-π / 2, π / 2], and the resolution unit size of ρ is ρ res The size can be 0.1m, the resolution unit size of θ res The size can be 0.1°.

[0136] In a possible implementation, at least one first grid unit corresponding to the first measurement data in the location grid is determined according to a first preset condition. The first preset condition is used to determine an area in the location grid according to the first measurement data, and the grid units in the area are at least one first grid unit corresponding to the first measurement data in the location grid. The first preset condition is |x k cosθ i +y k sinθ i -ρ j |≤d Thresh ,(x k ,y k ) is the position coordinate of the kth first measurement data, (θ i , ρ j ) is at least one first parameter corresponding to the first grid unit (i, j), d Thresh is a first preset value, and k is an integer greater than 0.

[0137] Exemplarily, the first preset value d Thresh =0, the first preset condition is |x k cosθi +y k sinθ i -ρ j |=0. If the cluster containing the measurement data A and B is the first cluster, then for the first cluster, the value of k is 1 and 2. According to the first measurement data A and B in the first cluster and the first preset condition, two straight lines in the position grid can be obtained, namely, straight line 1 and straight line 2. Figure 6e As shown, each straight line passes through at least one first grid unit, and the corresponding relationship between the first measurement data in the first cluster and the first grid unit is shown in Table 1. If the cluster containing the measurement data C, D and E is the first cluster, then for the first cluster, the values ​​of k are 1, 2 and 3. According to the first measurement data C, D, E in the first cluster and the first preset condition, three straight lines in the position grid can be obtained, namely, straight line 3, straight line 4 and straight line 5, as shown in Figure 6f As shown, each straight line passes through at least one first grid unit, and the corresponding relationship between the first measurement data in the first cluster and the first grid unit is shown in Table 2 below.

[0138] Table 1

[0139]

[0140] Table 2

[0141]

[0142] It should be noted that the first preset value d in the first preset condition Thresh It is not limited to the 0 mentioned in the above embodiment, and can also be 2ρ res The preset values ​​are as follows, specifically, the first preset value d Thresh It can be determined according to the actual situation.

[0143] S103: Determine a weight value of at least one first grid cell corresponding to the first measurement data in the location grid.

[0144] Optionally, in a possible implementation, after using step S102 to determine at least one first grid unit corresponding to the first measurement data in the position grid, the weight value of at least one first grid unit corresponding to the first measurement data in the position grid is determined based on the echo intensity EI in the first measurement data, or the echo intensity EI and position information in the first measurement data, and a first preset algorithm.

[0145] The first preset algorithm can be in the form of an exponential function: or Or the first preset algorithm can be in the form of a logarithmic function: Or the first preset algorithm can be in the form of a constant: △wi,j =λ / N.

[0146] Among them, △w i,j is the weight value of at least one first grid unit (i, j) corresponding to the kth first measurement data in the position grid, (θ i , ρ j ) is at least one first parameter corresponding to the first grid unit (i, j), EI k is the echo intensity EI in the kth first measurement data, N is the number of first measurement data in the first cluster where the kth first measurement data is located, σ EI and EI RB / GR is the inherent attribute of road geometry, σ EI is the standard deviation of EI of road geometry, EI RB / GR is the EI average value of the road geometry, σ is the second preset value, and λ is the fifth preset value.

[0147] For example, as shown in Table 1 above, if the first cluster is a cluster including measurement data A and B, there are two first measurement data in the first cluster, that is, N=2, and at least one first grid unit corresponding to the first first measurement data in the first cluster in the position grid is grid unit a. If σ=2ρ res , EI RB / GR =0.1,σ EI =0.1, the fifth preset value λ=1, then the weight value of the first grid unit a is or or or or If the first cluster is a cluster containing measurement data C, D, and E, then there are three first measurement data in the first cluster, that is, N=3, and the at least one first grid unit corresponding to the second first measurement data in the first cluster in the position grid is grid unit b, c, d, e, and f. If σ=2ρ res , EI RB / GR =0.1,σ EI =0.1, the fifth preset value λ=1, σ=2ρ res , the weight value of the first grid unit d or or or or

[0148] It should be noted that the value of σ can be determined according to actual conditions and is not limited to σ=2ρ involved in the embodiments of the present application. res .

[0149] Exemplarily, when the sensor is a radar sensor, the first preset algorithm is or or or △w i,j is the weight value of at least one first grid unit (i, j) corresponding to the kth first measurement data in the location grid, RCS k is the radar cross-sectional area RCS in the kth first measurement data, N is the number of all first measurement data in the first cluster where the kth first measurement data is located, σ RCS and RCS RB / GR is the inherent attribute of road geometry, σ RCS is the standard deviation of the RCS of the road geometry, RCS RB / GR is the RCS average value of the road geometry, and σ is the second preset value.

[0150] S104: Determine a cumulative weight value of a first grid unit according to all first measurement data in the first cluster.

[0151] The accumulated weight value of the first grid unit is obtained by summing up at least one weight value corresponding to the first grid unit.

[0152] Exemplarily, there are two first measurement data corresponding to the first cluster, so N=2, and the value of k is 1 or 2. In the first cluster, at least one first grid unit corresponding to the first first measurement data in the position grid is grid unit a, and its weight value is The first grid units corresponding to the second first measurement data are grid units a and c, and the weight value of the first grid unit a is The weight value of the first grid cell c is Therefore, the cumulative weight value of the first grid unit a corresponding to the first cluster is The cumulative weight value of the first grid cell c is The remaining grid cells have a cumulative weight of zero.

[0153] Exemplarily, if there are 3 first measurement data corresponding to the first cluster, then N=3, and the value of k is 1, 2 or 3. In the first cluster, at least one first grid unit corresponding to the first first measurement data in the location grid is grid units s, b, c and e, and the corresponding weight values ​​are 1, 2, 3 and 4 respectively, at least one first grid unit corresponding to the second first measurement data in the location grid is grid units b, d, c, e and f, and the corresponding weight values ​​are 1, 2, 3, 4 and 5 respectively, and at least one first grid unit corresponding to the third first measurement data in the location grid is grid units b, d, c, e, f, g and h, and the corresponding weight values ​​are 1, 2, 3, 4, 5, 6 and 7 respectively. Therefore, the cumulative weight values ​​of the first grid units s, b, c, e, f, g and h corresponding to the first cluster in the location grid are 1, 4, 9, 12, 10, 6 and 7 respectively. If there are 2 first measurement data corresponding to the first cluster, then N=2, and the value of k is 1 or 2. In the first cluster, at least one first grid unit corresponding to the first first measurement data in the location grid is grid unit a, and the corresponding weight value is 6, and at least one first grid unit corresponding to the second first measurement data in the location grid is grid units a and c, and the corresponding weight values ​​are 5 and 9, respectively. Therefore, the cumulative weight values ​​corresponding to the first grid units a and c corresponding to the first cluster in the location grid are 11 and 9, respectively.

[0154] It should be noted that in the process of determining the cumulative weight value of the first grid unit, the position information of the target object collected by the sensor, the echo intensity EI of the target object and / or the radial velocity of the target object relative to the sensor are taken into account. Comprehensive considerations make the cumulative weight value more reflective of the characteristics of the target object, reduce the impact of non-road information, and thus improve the accuracy of determining the road geometry.

[0155] S105 . Determine, according to the accumulated weight value of the first grid unit, that the target object corresponding to the first measurement data included in the first cluster is a road geometry.

[0156] The road geometry includes at least one of a road edge, a guardrail, and a lane line.

[0157] Optionally, in a possible implementation, if among at least one first grid cell corresponding to all first measurement data in the first cluster in the location grid, there is a first grid cell whose cumulative weight value is greater than a predefined threshold, then the target object corresponding to the first measurement data contained in the first cluster is road geometry.

[0158] Exemplarily, take the predefined threshold of 11 as an example. If the cumulative weight values ​​of the first grid cells s, b, c, e, f, g and h corresponding to the first cluster in the location grid are 1, 4, 9, 12, 10, 6 and 7 respectively, and the cumulative weight value of the first grid cell e corresponding to the first cluster is greater than the predefined threshold, then the target object corresponding to the first measurement data in the first cluster is road geometry. If the cumulative weight values ​​of the first grid cells a and c corresponding to the first cluster in the location grid are 11 and 9 respectively, and the cumulative weight values ​​of the first grid cells corresponding to the first cluster do not exceed the predefined threshold, then the target object corresponding to the first measurement data in the first cluster is not road geometry.

[0159] Optionally, in a possible implementation, if among at least one first grid cell corresponding to all the first measurement data in the first cluster in the location grid, there exists a first grid cell whose cumulative weight value is greater than a predefined threshold, then it is determined that the target object corresponding to the first measurement data corresponding to the first grid cell whose cumulative weight value is greater than the predefined threshold is road geometry.

[0160] In another possible implementation, first determine the first grid cell p with the largest cumulative weight value among the first grid cells corresponding to the first cluster, and then determine whether the cumulative weight value of the first grid cell p is greater than a predefined threshold. If so, determine that the target object corresponding to the first measurement data in the first cluster is road geometry.

[0161] Exemplarily, take the predefined threshold of 9 as an example. If the cumulative weight values ​​of the first grid cells s, b, c, e, f, g and h corresponding to the first cluster in the location grid are 1, 4, 9, 12, 10, 6 and 7 respectively, among the first grid cells corresponding to the first cluster, the first grid cell with the largest cumulative weight value is the first grid cell e, 12>9, then the target object corresponding to the first measurement data in the first cluster is road geometry. If the cumulative weight values ​​of the first grid cells a and c corresponding to the first cluster in the location grid are 11 and 9, among the first grid cells corresponding to the first cluster, the first grid cell with the largest cumulative weight value is the first grid cell a, 11>9, then the target object corresponding to the first measurement data in the first cluster is road geometry.

[0162] Optionally, in another possible implementation, it is considered that the first measurement data in the first cluster must correspond to road geometry. M first grid cells can be directly screened out from the first grid cells corresponding to the first cluster based on the value of M, and the target object corresponding to the first measurement data corresponding to these M first grid cells is determined to be road geometry.

[0163] Exemplarily, M=1 is set. If the first grid units a and c corresponding to the first cluster in the location grid have corresponding cumulative weight values ​​of 11 and 9, then according to the value of M, a first grid unit a with a larger cumulative weight value can be screened out from the first cluster, and it is determined that the target object corresponding to the first measurement data corresponding to the first cluster is road geometry.

[0164] Optionally, in another possible implementation, it should be noted that S102 determining the first grid unit corresponding to each first measurement data is an optional step. If this step is skipped and S103 is executed directly, the first grid unit corresponding to each first measurement data position grid is all grid units in the position grid. When calculating the weight value, the weight value of all grid units is initialized to 0. S102 can effectively reduce the computational complexity of determining the weight value of the subsequent first grid unit. In addition, if step S102 is skipped and step S103 is executed directly, the first preset algorithm is or

[0165] In a possible implementation, first, according to a first preset condition, the first grid unit corresponding to all the measurement data (not clustered) collected by the sensor in the location grid is determined. According to the measurement data, the weight value of the first grid unit is determined. Then, according to all the measurement data, the cumulative weight value of the first grid unit is determined. All first grid units with cumulative weight values ​​greater than a predefined threshold are determined (or M first grid units with the largest cumulative weight values ​​are selected), and in the location grid space, according to the coordinate vector (θ i , ρ j ) cluster these first grid units, and divide the first grid units with similar distances (not exceeding a preset threshold) into the same cluster. The measurement data corresponding to the first grid units in the same cluster can be considered as measurement data of the same road geometry.

[0166] For example, there are 5 measurement data, and according to the position information in the 5 measurement data and the first preset condition |x k cosθ i +y k sinθ i -ρ j|=0, the five straight lines corresponding to the five measurement data in the position grid can be determined. According to the grid cells passed by the five straight lines, the first grid cell corresponding to each measurement data can be determined, for example, the first grid cell corresponding to measurement data 1 is a, the first grid cells corresponding to measurement data 2 are a and b, the first grid cells corresponding to measurement data 3 are a, b, c, the first grid cells corresponding to measurement data 4 are a, b, c, d, and the first grid cells corresponding to measurement data 5 are a, b, c, d, e. Then, the weight values ​​of the first grid cells are determined according to the first preset algorithm and the measurement data. The weight value of the first grid cell a corresponding to measurement data 1 is 1, the weight values ​​of the first grid cells a and b corresponding to measurement data 2 are 1 and 2 respectively, the weight values ​​of the first grid cells a, b, c corresponding to measurement data 3 are 1, 2, 3, the weight values ​​of the first grid cells a, b, c, d corresponding to measurement data 4 are 1, 2, 3, 4 respectively, and the weight values ​​of the first grid cells a, b, c, d, e corresponding to measurement data 5 are 1, 2, 3, 4, 5 respectively. According to all the measurement data, the cumulative weight value of the first grid unit is determined. The cumulative weight value of the first grid unit a is 5, the cumulative weight value of the first grid unit b is 8, the cumulative weight value of the first grid unit c is 6, the cumulative weight value of the second grid unit d is 8, and the cumulative weight value of the first grid unit e is 5. If the predefined threshold is 7, there are two first grid units that exceed the predetermined threshold, namely the first grid unit b and the first grid unit d, and the coordinates of the two first grid units are (θ1, ρ1) and (θ2, ρ2), respectively. Cluster these two network units. If the Euclidean distance between the first grid units b and d does not exceed the preset threshold, the two grid units are in the same cluster, and the measurement data corresponding to the two grid units are measurement data 2-5, then it is determined that the target object corresponding to measurement data 2-5 is the same road geometry.

[0167] For example, there are 5 measurement data, and the straight lines corresponding to the 5 measurement data are determined according to the first preset condition as follows: Figure 6e and Figure 6f As shown, the first grid units corresponding to the five measurement data in the position grid are determined, as well as the weight values ​​of the first grid units corresponding to the various measurement data, and then the cumulative weight values ​​of the first grid units are determined according to all the measurement data. Taking the first grid units exceeding the predefined threshold as the first grid units a and d as an example, if the Euclidean distance between the first grid units a and d exceeds the preset threshold, the first grid units a and d are located in different clusters, the measurement data corresponding to the cluster containing the first grid unit a is measurement data 1-2, and it is determined that the target object corresponding to the measurement data 1-2 is the same road geometry, and the measurement data corresponding to the cluster containing the first grid unit d is measurement data 3-5, and it is determined that the target object corresponding to the measurement data 3-5 is another road geometry.

[0168] It should be noted that the measurement data contains the location information of the target object, as well as the echo intensity EI and / or the radial velocity of the target object relative to the sensor. Therefore, by determining the cumulative weight value of each grid cell in the location grid based on the measurement data, and then determining the road geometry through the cumulative weight value, it is possible to effectively filter out non-road information, that is, interference from measurement data of irrelevant objects (such as vehicles, etc.), thereby improving the accuracy of determining the road geometry and better assisting the vehicle in determining the driving strategy.

[0169] The embodiment of the present application provides a road geometry recognition method, which generates at least one first cluster according to the measurement data of the sensor, wherein the first cluster contains at least one first measurement data, and the measurement data at least includes the location information of the target object. Then, the weight value of at least one first grid unit corresponding to the first measurement data in the location grid is determined, and then the cumulative weight value of the first grid unit is determined according to all the first measurement data in the first cluster. Finally, according to the cumulative weight value of the first grid unit, it is determined that the target object corresponding to the first measurement data contained in the first cluster is the road geometry. In the road geometry recognition method described in the embodiment of the present application, clustering processing is performed on the measurement data, which can filter out some irrelevant clutter signals and measurement data of other objects. In addition, the determination of the weight value takes into account the location information of the target object and the echo intensity of the target object, and can further filter out the interference of non-road information. Therefore, through the above process, the interference of non-road information can be reduced, the workload and complexity of determining road geometry can be reduced, and the accuracy of determining road geometry can be improved, thereby better assisting the vehicle in determining the driving strategy.

[0170] based on Figure 6 After the road geometry recognition method shown in the figure determines the road geometry, the embodiment of the present application also provides a road geometry recognition method, which can further determine the first shape of the road geometry. Figure 7 As shown, in Figure 6 After step S105, steps S201-S202 are also included. Figure 7 , the embodiments of the present application are described:

[0171] S201. Determine all first grid cells whose cumulative weight values ​​are greater than a predefined threshold.

[0172] For the first cluster corresponding to the road geometry, a first grid cell having a cumulative weight value greater than the predefined threshold among the first grid cells corresponding to the first cluster is determined according to the predefined threshold.

[0173] Exemplarily, if the target object corresponding to the first measurement data in the first cluster is road geometry, and the cumulative weight values ​​of the first grid units a and c corresponding to the first cluster in the location grid are 9 and 11, and the predefined threshold is 8, then for the first cluster, the first grid units whose cumulative weight values ​​are greater than the predefined threshold are the first grid units a and c.

[0174] Optionally, among the first grid cells corresponding to the first cluster corresponding to the road geometry, M first grid cells with the largest cumulative weight values ​​are directly selected.

[0175] S202: Determine a first expression according to all first grid cells whose cumulative weight values ​​are greater than a predefined threshold.

[0176] The first expression is used to represent the first shape of the road geometry. The first expression is in Determined according to the first parameters corresponding to all first grid cells whose cumulative weight values ​​are greater than a predefined threshold, (x, y) is the location coordinate of the road geometry.

[0177] In a possible implementation manner, the first expression is determined according to the first parameter corresponding to the first grid unit whose cumulative weight value exceeds a predefined threshold determined in step S201.

[0178] When there is only one first grid unit whose cumulative weight value is greater than the predefined threshold, that is, the first grid unit with the largest cumulative weight value, the first grid unit with the largest cumulative weight value (i * , j * ) corresponds to at least one parameter Used to determine the first expression.

[0179] Exemplarily, the target object corresponding to the first measurement data in the first cluster is road geometry. The first cluster corresponds to the first grid cells a and c in the location grid, wherein there is only one first grid cell with a cumulative weight value greater than a predefined threshold, namely, the first grid cell a with the largest cumulative weight value. For the first cluster, according to at least one first parameter corresponding to the first grid cell a, Determine the first expression as

[0180] Optionally, when there are multiple first grid cells with cumulative weight values ​​greater than a predefined threshold, the first grid cell with the largest cumulative weight value (i * , j * ) corresponds to at least one parameter Determine a first expression, or average at least one first parameter corresponding to a plurality of first grid units whose cumulative weights are greater than a predefined threshold, and determine the first expression according to the average of the first parameters corresponding to the plurality of first grid units.

[0181] Exemplarily, the target object corresponding to the first cluster is road geometry, and the first cluster corresponds to the first grid units d, f, g, and h in the location grid, wherein there are two first grid units with cumulative weight values ​​greater than the predefined threshold, namely, the first grid unit g with the largest cumulative weight value and another first grid unit f. Then, according to at least one first parameter corresponding to the first grid unit g with the largest cumulative weight value Determine the first expression as Or the first parameter corresponding to the first grid cell g The first parameter corresponding to the first grid cell f Taking the mean, we get in, Determine the first expression as

[0182] Optionally, for the first cluster corresponding to road geometry, a weighted operation may be performed on the first parameters corresponding to the first grid cells that exceed a predefined threshold and the average may be calculated based on the number of first measurement data corresponding to each first grid cell; finally, an expression for the first shape of the road geometry corresponding to the first measurement data in the first cluster may be determined based on the calculation result.

[0183] Exemplarily, the target object corresponding to the first cluster is road geometry 2. The first cluster corresponds to first grid cells d, f, g, and h in the location grid, where there are two first grid cells with cumulative weight values ​​greater than the predefined threshold, namely, the first grid cell g with the largest cumulative weight value and another first grid cell f. There are three first measurement data corresponding to the first grid cell g, and one first measurement data corresponding to the first grid cell f. The first parameter corresponding to the first grid cell f Taking the weighted average, we get in, Determine the first expression as

[0184] In a possible implementation, all the measurement data (not clustered) collected by the sensor are first used in combination with the first preset condition to determine the first grid unit corresponding to the measurement data in the location grid. Based on the measurement data, the weight value of the first grid unit is determined. Then, based on all the measurement data, the cumulative weight value of the first grid unit is determined. All first grid units whose cumulative weight values ​​are greater than a predefined threshold are determined, and these first grid units whose cumulative weight values ​​are greater than the predefined threshold are clustered, and the first grid units with similar distances (not exceeding the preset threshold) are divided into the same cluster. The measurement data corresponding to the first grid units in the same cluster can be considered as the measurement data of the same road geometry. The at least one first parameter corresponding to the first grid units in the same cluster is averaged, and a first expression of the first shape of the obtained road geometry is obtained according to the cluster.

[0185] For example, if the cluster contains only one first grid unit (θ p , ρ q ), then the first expression for determining the first shape of the road geometry corresponding to the cluster is x*cosθ p +y*sinθ p =ρ q If the cluster contains two first grid units, respectively (θ m1 , ρ n1 ) and (θ m2 , ρ n2 ), then the first expression for determining the first shape of the road geometry corresponding to the cluster is x*cosθ m3 +y*sinθ m3 =ρ n3 , where θ m3 =(θ m1 +θ m2 ) / 2,ρ n3 =(ρ n1 +ρ n2 ) / 2.

[0186] In the road geometry recognition method described in the embodiment of the present application, for the first cluster of the corresponding road geometry, all the first grid cells whose cumulative weight values ​​are greater than the predefined threshold are first determined, and then the first expression for representing the first shape of the road geometry is determined according to all the first grid cells whose cumulative weight values ​​are greater than the predefined threshold. First, the echo intensity EI and the position information in the measurement data are comprehensively considered when determining the cumulative weight value of the first grid cell. Therefore, the technical solution of filtering the measurement data corresponding to the target object using the cumulative weight value of the first grid cell and determining the first shape of the road geometry can well reduce the influence of non-road factors and improve the accuracy of determining the first shape of the road geometry. Secondly, the first shape of the road geometry determined according to the cumulative weight value of the first grid cell is a plurality of short line segments (a plurality of short line segments can be combined into a uniform curve), therefore, the method is more suitable for determining the shape of the road geometry on a straight road and a uniform curve, so as to better assist the vehicle in determining the driving strategy on a straight road and a uniform curve to adjust the speed, position and / or direction of the vehicle.

[0187] based on Figure 6 After the road geometry recognition method shown in the figure determines the road geometry, the embodiment of the present application also provides another road geometry recognition method, which can further determine the second shape of the road geometry. Figure 8 As shown, in Figure 6 After step S105, steps S301-S307 are also included. Figure 8 , the embodiments of the present application are described:

[0188] S301. Generate at least one second cluster according to measurement data.

[0189] The second cluster includes at least one second measurement data.

[0190] S302: Determine at least one second grid unit corresponding to the second measurement data in the location grid.

[0191] S303: Determine a weight value of at least one second grid cell corresponding to the second measurement data in the location grid.

[0192] S304: Determine a cumulative weight value of a second grid unit according to all second measurement data in the second cluster.

[0193] S305 , determining, according to the accumulated weight value of the second grid unit, that the target object corresponding to the second measurement data included in the second cluster is a road geometry.

[0194] The specific implementation of the above steps S301-S305 can refer to the embodiments of steps S101-S105, and step S302 is also optional.

[0195] S306: Determine all second grid cells whose cumulative weight values ​​are greater than a predefined threshold.

[0196] The specific implementation process of the above step S306 refers to the embodiment in step S201.

[0197] S307: Determine a second expression.

[0198] Wherein, the second expression is used to represent the second shape of the road geometry.

[0199] If all first grid cells whose cumulative weight values ​​are greater than the predefined threshold and all second grid cells whose cumulative weight values ​​are greater than the predefined threshold meet the second preset condition, then a second expression is determined according to all first grid cells whose cumulative weight values ​​are greater than the predefined threshold and the second grid cells whose cumulative weight values ​​are greater than the predefined threshold. The second preset condition is or Determined according to the first parameters corresponding to all first grid cells whose cumulative weight values ​​are greater than a predefined threshold, Determined according to the first parameter corresponding to all second grid cells whose cumulative weight values ​​are greater than the predefined threshold, Thresh is the second preset value, p is the third preset value, and q is the fourth preset value. The second expression is Determined according to the first parameter corresponding to all first grid cells whose cumulative weight values ​​are greater than a predefined threshold and the first parameter corresponding to all second grid cells whose cumulative weight values ​​are greater than a predefined threshold, (x, y) is the location coordinate of the road geometry.

[0200] Exemplarily, the target object corresponding to the first cluster is road geometry 1. The first cluster corresponds to first grid units a and c in the location grid, wherein there is only one first grid unit with a cumulative weight value greater than a predefined threshold, namely, the first grid unit a with the largest cumulative weight value, and the at least one first parameter corresponding to the first grid unit a is Then the first expression used to represent the shape of road geometry 1 is The target object corresponding to the second cluster is road geometry 2. The second cluster corresponds to second grid cells d, f, g, and h in the location grid. There are two second grid cells whose cumulative weight values ​​are greater than the predefined threshold, namely, the second grid cell g with the largest cumulative weight value and another second grid cell f. At least one first parameter corresponding to these two second grid cells is and Calculate the average value of at least one first parameter corresponding to the two second grid cells in like and The second precondition is met, namely or Then the second expression is determined as in, or It should be noted that the parameters of the second expression can be weighted averaged not only by the grid unit, but also by the number of measurement data corresponding to the grid unit. For example, there are 3 measurement data corresponding to grid unit g, 5 measurement data corresponding to grid unit f, and 4 measurement data corresponding to grid unit a. Then It should be noted that Thresh, p and q are preset values, which can be determined according to actual conditions and are not limited to the values ​​given in the embodiments of the present application.

[0201] For example, Thresh = 2ρ res , p=0, q=0.1.

[0202] In a possible implementation, after obtaining the measurement data, all the measurement data (not clustered) collected by the sensor are first used in combination with the first preset condition to determine the first grid unit corresponding to the measurement data in the location grid, or the weight value of the first grid unit is determined directly based on the measurement data. Then, the cumulative weight value of the first grid unit is determined based on all the measurement data. All first grid units whose cumulative weight values ​​are greater than a predefined threshold are determined, and these first grid units whose cumulative weight values ​​are greater than the predefined threshold are clustered, and the first grid units with similar distances (not exceeding the preset threshold) are divided into the same cluster. The measurement data corresponding to the first grid units in the same cluster can be considered as the measurement data of the same road geometry. The mean value of at least one first parameter corresponding to the first grid units in the same cluster is calculated. If the mean value of at least one first parameter corresponding to the first grid units in different clusters meets the second preset condition, the second expression is determined based on the mean value of at least one first parameter corresponding to the first grid units in different clusters that meet the second preset condition.

[0203] For example, if the cluster contains a first grid unit (θ p , ρ q ), then the first expression for determining the first shape of the road geometry corresponding to the cluster is x*cosθ p +y*sinθ p =ρ q If the cluster contains two first grid units, respectively (θ m1 , ρ n1 ) and (θ m2 , ρ n2), then the first expression for determining the first shape of the road geometry corresponding to the cluster is x*cosθ m3 +y*sinθ m3 =ρ n3 , where θ m3 =(θ m1 +θ m2 ) / 2,ρ n3 =(ρ n1 +ρ n2 ) / 2. If (θ p , ρ q ) and (θ m3 , ρ n3 ) satisfies the second preset condition, then the second expression for representing the second shape of the road geometry is x*cosθ m4 +y*sinθ m4 =ρ n4 , where θ m4 =(θ m3 +θ p ) / 2,ρ n4 =(ρ n3 +ρ q ) / 2.

[0204] Through the above process, a second expression for representing the second shape of the road geometry can be obtained. Compared with the first expression, the shape of the road geometry represented by the second expression is closer to reality, integrates multiple similar small line segments, removes unnecessary interference, has higher accuracy, and can better assist the vehicle in determining driving strategies.

[0205] In the road geometry recognition method described in the embodiment of the present application, the determination of the cumulative weight value comprehensively considers the position of the target object and the echo intensity of the target object. Therefore, the use of the cumulative weight value to determine the second expression for representing the second shape of the road geometry can reduce the influence of non-road factors and improve the accuracy of determining the second shape of the road geometry. The second shape of the road geometry determined according to all the first grid cells whose cumulative weight values ​​are greater than the predefined threshold and all the second grid cells whose cumulative weight values ​​are greater than the predefined threshold is at least one long line segment or a relatively uniform curve. Therefore, the method can well determine the shape of the road geometry on a long straight road, thereby better assisting the vehicle in determining the driving strategy on a long straight or uniformly curved road to adjust the speed, position and / or direction of the vehicle.

[0206] based on Figure 8 After the road geometry recognition method shown in the figure determines the road geometry, the embodiment of the present application also provides another road geometry recognition method, which can be further used to represent that the third shape of the road geometry is a clothoid spiral. Fig. 9 As shown, in Figure 8After step S305 shown in the figure, steps S308-S310 are also included. Fig. 9 The embodiments of the present application are described as follows:

[0207] S308: Merge the first cluster and the second cluster to obtain a third cluster.

[0208] The third cluster includes at least one third measurement data, and the third measurement data includes the first measurement data in the first cluster and the second measurement data in the second cluster.

[0209] If all first grid units whose cumulative weight values ​​are greater than a predefined threshold and all second grid units whose cumulative weight values ​​are greater than a predefined threshold meet a second preset condition, the first cluster and the second cluster are merged to obtain a third cluster, and the third cluster includes at least one third measurement data.

[0210] The second preset condition is or Determined according to the first parameters corresponding to all first grid cells whose cumulative weight values ​​are greater than a predefined threshold, It is determined according to the first parameter corresponding to all second grid units whose cumulative weight values ​​are greater than the predefined threshold, Thresh is the second preset value, p is the third preset value, and q is the fourth preset value.

[0211] Exemplarily, the first cluster corresponding to all first grid units whose cumulative weight values ​​satisfying the second preset condition are greater than the predefined threshold and the second cluster corresponding to all second grid units whose cumulative weight values ​​are greater than the predefined threshold are merged to obtain a third cluster. The first cluster contains two first measurement data, namely A and B, and the second cluster contains three second measurement data, namely C, D and E. The first cluster and the second cluster are merged to obtain a third cluster, and the third cluster contains multiple third measurement data, and the multiple third measurement data are A, B, C, D and E respectively.

[0212] S309 , performing calculations according to the third measurement data in the third cluster and the second preset algorithm to determine a plurality of second parameters.

[0213] The second preset algorithm may be a least squares method or a gradient descent method, and the third measurement data in the same third cluster corresponds to the same road geometry.

[0214] Exemplarily, the third measurement data in the third cluster is calculated according to the least square method or the gradient descent method to determine a set of second parameters as c0, c1, c2, and c3.

[0215] S310. Determine a clothoid spiral according to a plurality of second parameters.

[0216] Among them, the clothoid spiral is used to represent the third shape of road geometry. The expression of the clothoid spiral is y=c0+c1x+c2x 2 +c3x 3 , c0, c1, c2 and c3 are the second parameters, and (x, y) are the location coordinates of the road geometry.

[0217] For example, if the least square method is used to calculate the third measurement data in the third cluster, the second parameters are c0=c1=0, c2=1, c3=2, then the expression of the clothoid spiral of the third shape of the road geometry corresponding to the third cluster is y=x 2 +2x 3 If the third measurement data in the third cluster is calculated using the least squares method, the second parameters obtained are c0=1, c1=3, c2=1, c3=2, then the expression of the clothoid spiral representing the third shape of the road geometry corresponding to the third cluster is y=1+3x+x 2 +2x 3 .

[0218] In a possible implementation, after obtaining the measurement data, all the measurement data (not clustered) collected by the sensor are first used in combination with the first preset condition to determine the first grid unit corresponding to the measurement data in the location grid, or the weight value of the first grid unit is determined directly based on the measurement data. Then, the cumulative weight value of the first grid unit is determined based on all the measurement data. All first grid units with cumulative weight values ​​greater than a predefined threshold are determined, and these first grid units with cumulative weight values ​​greater than the predefined threshold are clustered, and the first grid units with similar distances (not exceeding the preset threshold) are divided into the same cluster. The at least one first parameter corresponding to the first grid units in different clusters is averaged respectively, and the clusters corresponding to the means that meet the second preset condition are merged, and multiple second parameters are determined based on the merged measurement data and the second preset algorithm, and then the spiral of the third shape used to represent the road geometry is determined based on these multiple second parameters.

[0219] Exemplarily, if there are two clusters, the mean of at least one first parameter corresponding to the first grid cells in the two clusters is calculated respectively. The mean of at least one first parameter corresponding to the first grid cell in a cluster is The mean of at least one parameter corresponding to the first grid cell in another cluster is like and The second preset condition is met, the clusters corresponding to the two means are merged, and the plurality of second parameters c0, c1, c2 and c3 are determined according to the measurement data corresponding to the two first grid units in the merged cluster and the second preset algorithm, i.e., the least square method or the gradient descent method, to obtain the expression of the clothoid spiral of the third shape representing the road geometry as y=c0+c1x+c2x 2 +c3x 3 .

[0220] It should be noted that through the above process, a third shape of the clothoid spiral can be obtained to represent the road geometry. Compared with the second expression, the shape of the road geometry represented by the clothoid spiral is closer to reality and has higher accuracy, which can better assist the vehicle in determining the driving strategy.

[0221] In the road geometry recognition method described in the embodiment of the present application, the third shape of the road geometry is determined based on the measurement data in the third cluster obtained by merging the first cluster and the second cluster. The third cluster has more measurement data, and it can be considered that the data in the same third cluster all belong to the same road geometry, which can more completely and accurately represent the road geometry. Therefore, the third shape of the road geometry determined by the above road geometry recognition method is more accurate. In addition, using a clothoid spiral to represent the third shape of the road geometry is more practical, and the shape of the road geometry at turns and other non-straight roads can be determined more accurately, thereby better assisting the vehicle in determining the autonomous driving strategy at turns or other non-straight roads to adjust the speed, position and / or direction of the vehicle.

[0222] based on Figure 6 After the road geometry recognition method shown determines the road geometry, the embodiment of the present application also provides another road geometry recognition method, which can further determine the speed of the sensor. The embodiment of the present application also provides a road geometry recognition method, which also includes step S401 (not shown in the drawings), and step S401 is described below:

[0223] S401 . Determine a sensor speed estimation value by performing calculations based on all measurement data corresponding to the road geometry and a sensor speed estimation algorithm.

[0224] The measurement data also includes the radial velocity of the target object, and the position information of the target object includes the distance between the target object and the sensor and the angle information of the target object relative to the sensor. The sensor velocity estimation algorithm is: v is the estimated value of the sensor speed, H is the radial speed observation matrix of the road geometry, H is determined according to the angle information of the road geometry relative to the sensor in the measurement data corresponding to the road geometry, H T is the transposed matrix of H, is the radial velocity matrix in the measured data corresponding to the road geometry.

[0225] For example, in, is the radial velocity matrix of the target object, H is the radial velocity observation matrix of the road geometry, and H T is the transposed matrix of H.

[0226] In another possible implementation, the sensor speed estimation algorithm is R is the radial velocity observation noise matrix, is the observation noise standard deviation of the radial velocity in the ith measurement data, that is, the difference between the radial velocity in the ith measurement data and its corresponding actual radial velocity.

[0227] The above-mentioned road geometry recognition method is adopted to determine the speed of the sensor according to the measurement data corresponding to the road geometry and the sensor speed estimation algorithm to improve the accuracy of determining the speed of the sensor, so that the autonomous driving vehicle can better determine the autonomous driving strategy according to the sensor speed and road geometry to adjust its own speed, position and / or direction.

[0228] In the embodiment of the present application, the road geometry recognition device can be divided into functional modules according to the above method example. In the case of dividing each functional module according to each function, Fig.10 A possible structural schematic diagram of the road geometry recognition device involved in the above embodiment is shown. Fig.10 As shown, the road geometry recognition device includes a generating module 401 and a determining module 402. Of course, the road geometry recognition device may also include other functional modules, or the road geometry recognition device may include fewer functional modules.

[0229] The generating module 401 is used to generate at least one first cluster according to the measurement data of the sensor, wherein the first cluster includes at least one first measurement data, and the measurement data includes at least the location information of the target object.

[0230] Optionally, the measurement data also includes the echo intensity EI of the target object.

[0231] The determination module 402 is used to determine a weight value of at least one first grid cell corresponding to the first measurement data in the location grid.

[0232] Specifically, the determination module 402 is used to determine the weight value of at least one first grid cell corresponding to the first measurement data in the position grid according to the echo intensity EI in the first measurement data, or the echo intensity EI and position information in the first measurement data.

[0233] Exemplarily, the determination module 402 is used to determine the weight value of at least one first grid cell corresponding to the first measurement data in the position grid according to a first preset algorithm. The measurement data also includes the echo intensity EI of the target object. The first preset algorithm is in exponential form: or Or the first preset algorithm is in the form of a logarithmic function: or Or the first preset algorithm is in constant form: △w i,j =λ / N. Among them, △w i,j is the weight value of at least one first grid unit (i, j) corresponding to the kth first measurement data in the position grid, EI k is the echo intensity EI in the kth first measurement data, N is the number of first measurement data in the first cluster where the kth first measurement data is located, σ EI and EI RB / GR is the inherent attribute of road geometry, σ EI is the EI standard deviation of road geometry, EI RB / GR is the EI average value of the road geometry, σ is the second preset value, and λ is the fifth preset value.

[0234] Optionally, before the determination module 402 determines the weight value of at least one first grid unit corresponding to the first measurement data in the location grid, the generation module 401 is further used to determine the location grid according to the detection range of the sensor and the resolution unit size of the sensor. The location grid includes at least one grid unit, and each grid unit corresponds to at least one first parameter.

[0235] Optionally, before determining the weight value of at least one first grid unit corresponding to the first measurement data in the location grid, the determination module 402 is further configured to determine at least one first grid unit corresponding to the first measurement data in the location grid.

[0236] Specifically, the determination module 402 is used to determine at least one first grid unit corresponding to the first measurement data in the position grid according to a first preset condition. The first preset condition is |x k cosθ i +y k sinθ i -ρ j |≤d Thresh ,(x k ,y k ) is the position coordinate of the kth first measurement data, (θ i , ρ j ) is at least one first parameter corresponding to the first grid unit (i, j), d Thresh is a first preset value, and k is an integer greater than 0.

[0237] The determination module 402 is further configured to determine the cumulative weight value of the first grid unit according to all the first measurement data in the first cluster. The target object corresponding to the first measurement data included in the first cluster is determined to be a road geometry according to the cumulative weight value of the first grid unit. The road geometry includes at least one of a road edge, a guardrail, and a lane line.

[0238] In one possible design, the determination module 402 is further used to determine all first grid cells whose cumulative weight values ​​are greater than a predefined threshold. The determination module 402 is further used to determine a first expression based on all first grid cells whose cumulative weight values ​​are greater than a predefined threshold. The first expression is used to represent the first shape of the road geometry, and the first expression is Determined according to the first parameters corresponding to all first grid cells whose cumulative weight values ​​are greater than a predefined threshold, (x, y) is the location coordinate of the road geometry.

[0239] In one possible design, the generation module 401 is further used to generate at least one second cluster based on the measurement data, and the second cluster includes at least one second measurement data. The determination module 402 is further used to directly determine the weight value of the second grid cell corresponding to the second measurement data in the location grid, or after determining the second grid cell corresponding to the second measurement data in the location grid, determine the weight value of the second grid cell corresponding to the second measurement data in the location grid. Then the determination module 402 is further used to determine the cumulative weight value of the second grid cell based on all the second measurement data in the second cluster, and determine the road geometry corresponding to the second measurement data contained in the second cluster based on the cumulative weight value of the second grid cell.

[0240] In a possible design, the determination module 402 is further used to determine all second grid cells whose cumulative weight values ​​are greater than a predefined threshold. Then, when all first grid cells whose cumulative weight values ​​are greater than the predefined threshold and all second grid cells whose cumulative weight values ​​are greater than the predefined threshold meet the second preset condition, the determination module 402 determines a second expression according to all first grid cells whose cumulative weight values ​​are greater than the predefined threshold and the second grid cells whose cumulative weight values ​​are greater than the predefined threshold, and the second expression is used to represent the second shape of the road geometry. The second preset condition is or Determined according to the first parameters corresponding to all first grid cells whose cumulative weight values ​​are greater than a predefined threshold, Determined according to the first parameter corresponding to all second grid cells whose cumulative weight values ​​are greater than the predefined threshold, Thresh is the second preset value, p is the third preset value, and q is the fourth preset value. The second expression is Determined according to the first parameter corresponding to all first grid cells whose cumulative weight values ​​are greater than a predefined threshold and the first parameter corresponding to all second grid cells whose cumulative weight values ​​are greater than a predefined threshold, (x, y) is the location coordinate of the road geometry.

[0241] In one possible design, the determination module 402 is also used to determine all second grid cells whose cumulative weight values ​​are greater than a predefined threshold. Then, when all first grid cells whose cumulative weight values ​​are greater than the predefined threshold and all second grid cells whose cumulative weight values ​​are greater than the predefined threshold meet the second preset condition, the determination module 402 merges the first cluster and the second cluster to obtain a third cluster, where the third cluster includes at least one third measurement data. A plurality of second parameters are determined based on the third measurement data in the third cluster and a second preset algorithm, where the second preset algorithm is a least squares method or a gradient descent method. Finally, the determination module 402 determines a spiral based on the plurality of second parameters, where the spiral is used to represent a third shape of road geometry. Wherein, the second preset condition is or Determined according to the first parameters corresponding to all first grid cells whose cumulative weight values ​​are greater than a predefined threshold, Determined according to the first parameter corresponding to all second grid cells whose cumulative weight values ​​are greater than the predefined threshold, Thresh is the second preset value, p is the third preset value, and q is the fourth preset value. The spiral is y=c0+c1x+c2x 2 +c3x 3 , c0, c1, c2 and c3 are multiple second parameters, and (x, y) are the location coordinates of the road geometry.

[0242] In one possible design, the measurement data also includes the radial velocity of the target object, and the position information of the target object includes the distance between the target object and the sensor and the angle information of the target object relative to the sensor. The determination module 402 is further configured to perform calculations based on all the measurement data corresponding to the road geometry and the sensor velocity estimation algorithm to determine the sensor velocity estimation value. The sensor velocity estimation algorithm is: v is the estimated value of the sensor speed, H is the radial speed observation matrix of the road geometry, H is determined according to the angle information of the road geometry relative to the sensor in the measurement data corresponding to the road geometry, H T is the transposed matrix of H, is the radial velocity matrix in the measured data corresponding to the road geometry.

[0243] See also Fig.11The present application also provides a road geometry recognition device, including a processor 510 and a memory 520. The processor 510 is connected to the memory 520 (eg, connected to each other via a bus 540).

[0244] Optionally, the road geometry recognition device may further include a transceiver 530 , which is connected to the processor 510 and the memory 520 , and is used to receive / send data.

[0245] The processor 510 may execute Figure 6-Figure 9 The operations of any one of the corresponding embodiments and various feasible implementations thereof, for example, are used to execute the operations of the generation module 401, the determination module 402, and / or other operations described in the embodiments of the present application.

[0246] The processor 510 (or described as a controller) can implement or execute various exemplary logic blocks, unit modules and circuits described in conjunction with the disclosure of the present application. The processor or controller can be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a transistor logic device, a hardware component or any combination thereof. It can implement or execute various exemplary logic blocks, unit modules and circuits described in conjunction with the disclosure of the present application. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0247] The bus 540 may be an extended industry standard architecture (EISA) bus, etc. The bus 540 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.11 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0248] For the specific working process of the processor, memory, bus and transceiver, please refer to the above and will not be repeated here.

[0249] The present application also provides a road geometry recognition device, including a non-volatile storage medium and a central processing unit, wherein the non-volatile storage medium stores an executable program, and the central processing unit is connected to the non-volatile storage medium and executes the executable program to implement the present application. Figure 6-Figure 9 The road geometry recognition method shown.

[0250] Another embodiment of the present application further provides a computer-readable storage medium, the computer-readable storage medium comprising one or more program codes, the one or more programs comprising instructions, when the processor executes the program code, the road geometry recognition device performs the following Figure 6-Figure 9 The road geometry recognition method shown.

[0251] In another embodiment of the present application, a computer program product is further provided, the computer program product comprising computer executable instructions, the computer executable instructions being stored in a computer readable storage medium. At least one processor of the road geometry recognition device can read the computer executable instructions from the computer readable storage medium, and at least one processor executes the computer executable instructions so that the road geometry recognition device performs the execution Figure 6-Figure 9 The corresponding steps in the road geometry recognition method shown.

[0252] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0253] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by a software program, all or part of the embodiments may appear in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions according to the embodiments of the present application are generated.

[0254] The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL0)) or wireless (e.g., infrared, wireless, microwave, etc.) means. Computer-readable storage media may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated therein. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state disk, SSD), etc.

[0255] Through the description of the above implementation methods, technical personnel in the relevant field can clearly 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 assigned to 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.

[0256] In the several embodiments provided in the present 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 only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, 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.

[0257] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0258] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0259] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0260] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A road geometry recognition method, characterized in that: include: Generate at least one first cluster according to the measurement data of the sensor, wherein the first cluster includes at least one first measurement data, and the measurement data includes at least position information of the target object and the echo intensity EI of the target object; Determine, according to the echo intensity EI in the first measurement data, or the echo intensity EI and the position information in the first measurement data, a weight value of at least one first grid cell corresponding to the first measurement data in a position grid, wherein the position grid includes at least one grid cell, wherein each grid cell corresponds to at least one first parameter; Determine a cumulative weight value of a first grid unit according to all first measurement data in the first cluster; According to the accumulated weight value of the first grid unit, it is determined that the target object corresponding to the first measurement data contained in the first cluster is road geometry; the road geometry includes at least one of a road edge, a guardrail and a lane line.

2. The road geometry recognition method according to claim 1, characterized in that: Before determining the weight value of at least one first grid unit corresponding to the first measurement data in the location grid, the method further includes: The position grid is determined according to the detection range of the sensor and / or the resolution unit size of the sensor.

3. The road geometry recognition method according to claim 1 or 2, characterized in that: Before determining the weight value of at least one first grid unit corresponding to the first measurement data in the location grid, the method further includes: According to a first preset condition, determining at least one first grid unit corresponding to the first measurement data in the position grid; Among them, the first preset condition is |x k cosθ i +y k sinθ i -ρ j |≤d Thresh ,(x k ,y k ) is the position coordinate of the kth first measurement data, (θ i , ρ j ) is at least one first parameter corresponding to the first grid unit (i, j), d Thresh is a first preset value, and k is an integer greater than 0.

4. The road geometry recognition method according to claim 1 or 2, characterized in that: The method further comprises: Determine all first grid cells whose cumulative weight values ​​are greater than a predefined threshold; Determine a first expression based on all first grid cells whose cumulative weight values ​​are greater than a predefined threshold, wherein the first expression is used to represent a first shape of road geometry; Wherein, the first expression is x*cosθ i* +y*sinθ i* =ρ j* , (θ i* , ρ j* ) is determined according to the first parameter corresponding to all first grid cells whose cumulative weight values ​​are greater than a predefined threshold, where (x, y) is the location coordinate of the road geometry.

5. The road geometry recognition method according to claim 1 or 2, characterized in that: The method further comprises: generating at least one second cluster according to the measurement data, wherein the second cluster includes at least one second measurement data; Determine a weight value of a second grid cell corresponding to the second measurement data in the position grid; Determining a cumulative weight value of a second grid unit according to all second measurement data in the second cluster; The road geometry corresponding to the second measurement data included in the second cluster is determined according to the accumulated weight value of the second grid unit.

6. The road geometry recognition method according to claim 5, characterized in that: The method further comprises: Determine all second grid cells whose cumulative weight values ​​are greater than a predefined threshold; If all first grid cells whose cumulative weight values ​​are greater than a predefined threshold and all second grid cells whose cumulative weight values ​​are greater than the predefined threshold meet a second preset condition, determining a second expression according to all first grid cells whose cumulative weight values ​​are greater than the predefined threshold and all second grid cells whose cumulative weight values ​​are greater than the predefined threshold, the second expression being used to represent a second shape of the road geometry; Wherein, the second preset condition is ||[θ i* ,ρ j* ]-[θ m* ,ρ n* ]||<Thresh,or||[θ i* -θ m* ]||<p,||[ρ j* -ρ n* ]||<q,(θ i* , ρ j* ) is determined according to the first parameter corresponding to all first grid cells whose cumulative weight values ​​are greater than a predefined threshold, (θ m* , ρ n* ) is determined according to the first parameter corresponding to all second grid cells whose cumulative weight values ​​are greater than a predefined threshold, Thresh is a second preset value, p is a third preset value, and q is a fourth preset value; The second expression is x*cosθ e* +y*sinθ e* =ρ f* , (θ e* , ρ f* ) is determined according to the first parameter corresponding to all first grid cells whose cumulative weight values ​​are greater than a predefined threshold and the first parameter corresponding to all second grid cells whose cumulative weight values ​​are greater than a predefined threshold, where (x, y) is the location coordinate of the road geometry.

7. The road geometry recognition method according to claim 5, characterized in that: The method further comprises: Determine all second grid cells whose cumulative weight values ​​are greater than a predefined threshold; If all first grid cells whose cumulative weight values ​​are greater than a predefined threshold and all second grid cells whose cumulative weight values ​​are greater than a predefined threshold meet a second preset condition, merging the first cluster and the second cluster to obtain a third cluster, wherein the third cluster includes at least one third measurement data; Performing calculations based on the third measurement data in the third cluster and a second preset algorithm to determine a plurality of second parameters, wherein the second preset algorithm is a least squares method or a gradient descent method; Determine a clothoid spiral based on the plurality of second parameters, the clothoid spiral being used to represent a third shape of the road geometry; Among them, the second preset condition is ||[θ i* ,ρ j* ]-[θ m* ,ρ n* ]||<Thresh,or||[θ i* -θ m* ]||<p,||[ρ j* -ρ n* ]||<q,(θ i* , ρ j* ) is determined according to the first parameter corresponding to all first grid cells whose cumulative weight values ​​are greater than a predefined threshold, (θ m* , ρ n* ) is determined according to the first parameter corresponding to all second grid cells whose cumulative weight values ​​are greater than a predefined threshold, Thresh is a second preset value, p is a third preset value, and q is a fourth preset value; The spiral is y=c0+c1x+c2x 2 +c3x 3 , c0, c1, c2 and c3 are the multiple second parameters, and (x, y) are the location coordinates of the road geometry.

8. The road geometry recognition method according to claim 1 or 2, characterized in that: The measurement data also includes the radial velocity of the target object, and the position information of the target object includes the distance between the target object and the sensor and the angle information of the target object relative to the sensor; Determine a sensor speed estimate based on all measurement data corresponding to the road geometry and a sensor speed estimation algorithm; Among them, the sensor speed estimation algorithm is: v is the estimated value of the sensor speed, H is the radial speed observation matrix of the road geometry, H is determined according to the angle information of the road geometry relative to the sensor, and H T is the transposed matrix of H, is the radial velocity matrix of the target object.

9. A road geometry recognition device, characterized in that: include: A generating module, configured to generate at least one first cluster according to the measurement data of the sensor, wherein the first cluster includes at least one first measurement data, and the measurement data includes at least position information of a target object and an echo intensity EI of the target object; a determination module, configured to determine, according to the echo intensity EI in the first measurement data, or the echo intensity EI and the position information in the first measurement data, a weight value of at least one first grid cell corresponding to the first measurement data in a position grid, wherein the position grid includes at least one grid cell, wherein each grid cell corresponds to at least one first parameter; A determination module, configured to determine a cumulative weight value of a first grid unit according to all first measurement data in a first cluster; The determination module is further used to determine, based on the accumulated weight value of the first grid unit, that the target object corresponding to the first measurement data contained in the first cluster is road geometry; the road geometry includes at least one of a road edge, a guardrail and a lane line.

10. The road geometry recognition device according to claim 9, characterized in that: The generating module is further used to determine the position grid according to the detection range of the sensor and / or the resolution unit size of the sensor.

11. The road geometry recognition device according to claim 9 or 10, characterized in that: The determination module is further used to determine at least one first grid unit corresponding to the first measurement data in the position grid according to the first preset condition; Among them, the first preset condition is |x k cosθ i +y k sinθ i -ρ j |≤d Thresh ;(x k ,y k ) is the position coordinate of the kth first measurement data, (θ i , ρ j ) is at least one first parameter corresponding to the first grid unit (i, j), d Thresh is a first preset value, and k is an integer greater than 0.

12. The road geometry recognition device according to claim 9 or 10, characterized in that: The determination module is further used to determine all first grid cells whose cumulative weight values ​​are greater than a predefined threshold; The determination module is further used to determine a first expression based on all first grid cells whose cumulative weight values ​​are greater than a predefined threshold, wherein the first expression is used to represent a first shape of the road geometry; Wherein, the first expression is x*cosθ i* +y*sinθ i* =ρ j* , (θ i* , ρ j* ) is determined according to the first parameter corresponding to all first grid cells whose cumulative weight values ​​are greater than a predefined threshold, where (x, y) is the location coordinate of the road geometry.

13. The road geometry recognition device according to claim 9 or 10, characterized in that: The generating module is further configured to generate at least one second cluster according to the measurement data, wherein the second cluster includes at least one second measurement data; The determination module is further used to determine a weight value of a second grid unit corresponding to the second measurement data in the position grid; The determination module is further used to determine the cumulative weight value of the second grid unit according to all the second measurement data in the second cluster; The determination module is further configured to determine the road geometry corresponding to the second measurement data included in the second cluster according to the accumulated weight value of the second grid unit.

14. The road geometry recognition device according to claim 13, characterized in that: The determination module is further used to determine all second grid cells whose cumulative weight values ​​are greater than a predefined threshold; The determination module is further configured to determine a second expression according to all the first grid cells whose cumulative weight values ​​are greater than the predefined threshold and the second grid cells whose cumulative weight values ​​are greater than the predefined threshold when all the first grid cells whose cumulative weight values ​​are greater than the predefined threshold meet a second preset condition, wherein the second expression is used to represent a second shape of the road geometry; Wherein, the second preset condition is ||[θ i* ,ρ j* ]-[θ m* ,ρ n* ]||<Thresh,or||[θ i* -θ m* ]|||<p,||[ρ j* -ρ n* ]||<q,(θ i* , ρ j* ) is determined according to the first parameter corresponding to all first grid cells whose cumulative weight values ​​are greater than a predefined threshold, (θ m* , ρ n* ) is determined according to the first parameter corresponding to all second grid cells whose cumulative weight values ​​are greater than a predefined threshold, Thresh is a second preset value, p is a third preset value, and q is a fourth preset value; The second expression is x*cosθ e* +y*sinθ e* =ρ f* , (θ e* , ρ f* ) is determined according to the first parameter corresponding to all first grid cells whose cumulative weight values ​​are greater than a predefined threshold and the first parameter corresponding to all second grid cells whose cumulative weight values ​​are greater than a predefined threshold, where (x, y) is the location coordinate of the road geometry.

15. The road geometry recognition device according to claim 13, characterized in that: The determination module is further used to determine all second grid cells whose cumulative weight values ​​are greater than a predefined threshold; The determination module is further configured to merge the first cluster and the second cluster to obtain a third cluster when all first grid units whose cumulative weight values ​​are greater than a predefined threshold and all second grid units whose cumulative weight values ​​are greater than a predefined threshold meet a second preset condition, wherein the third cluster includes at least one third measurement data; The determination module is further used to perform calculations based on the third measurement data in the third cluster and a second preset algorithm to determine a plurality of second parameters, wherein the second preset algorithm is a least squares method or a gradient descent method; The determination module is further used to determine a clothoid spiral according to the plurality of second parameters, wherein the clothoid spiral is used to represent a third shape of the road geometry; Wherein, the second preset condition is ||[θ i* ,ρ j* ]-[θ m* ,ρ n* ]||<Thresh,or||[θ i* -θ m* ]||<p,||[ρ j* -ρ n* ]||<q,(θ i* , ρ j* ) is determined according to the first parameter corresponding to all first grid cells whose cumulative weight values ​​are greater than a predefined threshold, (θ m* , ρ n* ) is determined according to the first parameter corresponding to all second grid cells whose cumulative weight values ​​are greater than a predefined threshold, Thresh is a second preset value, p is a third preset value, and q is a fourth preset value; The spiral is y=c0+c1x+c2x 2 +c3x 3 , c0, c1, c2 and c3 are the multiple second parameters, and (x, y) are the location coordinates of the road geometry.

16. The road geometry recognition device according to claim 9 or 10, characterized in that: The measurement data also includes the radial velocity of the target object, and the position information of the target object includes the distance between the target object and the sensor and the angle information of the target object relative to the sensor; The determination module is further used to perform calculations based on all measurement data corresponding to the road geometry and the sensor speed estimation algorithm to determine the sensor speed estimation value; Among them, the sensor speed estimation algorithm is: v is the estimated value of the sensor speed, H is the radial speed observation matrix of the road geometry, H is determined according to the angle information of the road geometry relative to the sensor, and H T is the transposed matrix of H, is the radial velocity matrix of the target object.

17. A road geometry recognition device, characterized in that: include: A processor, a memory and a communication interface; wherein the communication interface is used to communicate with other devices or communication networks, and the memory is used to store one or more programs, wherein the one or more programs include computer-executable instructions, and when the device is running, the processor executes the computer-executable instructions stored in the memory so that the device executes the road geometry recognition method as described in any one of claims 1-8.

18. A computer-readable storage medium, characterized in that: The invention comprises a program and instructions. When the program or instructions are run on a computer, the road geometry recognition method as claimed in any one of claims 1 to 8 is implemented.

19. A computer program product comprising instructions, characterized in that When the computer program product is run on a computer, the computer is enabled to execute the road geometry recognition method according to any one of claims 1 to 8.

20. A chip system, characterized in that: The invention comprises a processor, the processor is coupled to a memory, the memory stores program instructions, and when the program instructions stored in the memory are executed by the processor, the road geometry recognition method according to any one of claims 1 to 8 is implemented.

Images