Lidar control method, apparatus, and vehicle

Abstract

The application discloses a laser radar control method and device, a vehicle and a storage medium, and belongs to the technical field of vehicles. The method comprises the following steps: in the case that a slope exists in front of a target vehicle, the slope of the slope is acquired; pedestrian detection is performed on the surroundings of the target vehicle to determine whether pedestrians exist in the surroundings of the target vehicle; in the case that pedestrians exist in the surroundings of the target vehicle, the vertical field angle of a laser beam of a laser radar of the target vehicle is adjusted based on the slope of the slope and pedestrian information of the pedestrians. The application controls the laser radar of the target vehicle to adjust the vertical field angle of the laser beam based on the slope of the slope and the pedestrian information of the pedestrians in the case that the slope exists in front of the target vehicle and the pedestrians exist in the surroundings of the vehicle. In this way, the laser beam emitted by the laser radar can be prevented from causing damage to the eyes of people, so that the eyes of the pedestrians are protected.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a lidar control method, device, and vehicle. Background Technology

[0002] In the field of vehicle technology, automobiles can use lidar to collect information about their surrounding environment. LiDAR emits a detection signal (laser beam) into the environment around the vehicle via a laser emitting system, and then receives the laser signal reflected back from the environment via a laser receiving system. The lidar's information processing system can then use the detection signal and the reflected laser signal to obtain information about objects in the surrounding environment, such as their shape and physical properties.

[0003] However, the laser beams emitted by lidar can damage human eyes, especially when a car is driving on a slope. The coverage area of ​​the lidar beam changes, exacerbating the eye injury. Therefore, a method for controlling lidar in slope scenarios is urgently needed. Summary of the Invention

[0004] This application provides a lidar control method, device, vehicle, and storage medium, which can control the lidar in slope scenarios and prevent the laser beam emitted by the lidar from causing damage to the human eye. The technical solution is as follows:

[0005] Firstly, a lidar control method is provided, the method comprising:

[0006] If there is a ramp in front of the target vehicle, obtain the slope of the ramp;

[0007] Pedestrian detection is performed around the target vehicle to determine whether there are pedestrians around the target vehicle;

[0008] When pedestrians are present around the target vehicle, the vertical field of view of the laser beam of the target vehicle's lidar is adjusted based on the slope of the ramp and the pedestrian information.

[0009] In this application, the presence of a ramp in front of the target vehicle is first determined. If a ramp exists, its slope is obtained. Then, pedestrian detection is performed around the target vehicle to determine if any pedestrians are present. If pedestrians are present, the vertical field of view of the laser radar on the target vehicle is adjusted based on the ramp slope and pedestrian information. In other words, even when pedestrians are present, the vertical field of view is adjusted to prevent the laser beam emitted by the laser radar from entering the pedestrians' eyes. This avoids damage to the pedestrians' eyes from the laser beam emitted by the laser radar, thus protecting their vision.

[0010] Optionally, when pedestrians are present around the target vehicle, controlling the lidar of the target vehicle to adjust the vertical field of view of the laser beam based on the slope of the ramp and the pedestrian information includes:

[0011] If there are pedestrians around the target vehicle, determine the relative positions of the pedestrians and the target vehicle;

[0012] Based on the relative position, the position of the lidar, the slope of the ramp, and the pedestrian information, the lidar of the target vehicle is controlled to adjust the vertical field of view of the laser beam.

[0013] Optionally, controlling the vertical field of view of the laser beam of the target vehicle's laser radar to adjust based on the relative position, the position of the laser radar, the slope of the ramp, and the pedestrian information includes:

[0014] Based on the relative position and the position of the lidar, determine whether the pedestrian is within the emission range of the lidar's laser beam;

[0015] When the pedestrian is within the emission range of the laser beam, the target vehicle's lidar is controlled to adjust the vertical field of view of the laser beam based on the slope of the ramp and the pedestrian's information.

[0016] Optionally, the pedestrian information includes the height of at least one pedestrian and the distance between the at least one pedestrian and the target vehicle. When pedestrians are present around the target vehicle, controlling the vertical field of view of the laser beam of the target vehicle's lidar, based on the slope of the ramp and the pedestrian information, includes:

[0017] The height and target distance of the target pedestrian are obtained from the pedestrian information, wherein the height of the target pedestrian is the lowest among the heights of the at least one pedestrian, and the target distance is the distance between the target pedestrian and the target vehicle;

[0018] Based on the slope of the ramp, the height of the target pedestrian, and the target distance, a first target angle is determined. The first target angle is the angle at which the laser beam of the lidar cannot scan the eyes of at least one pedestrian.

[0019] The lidar controlling the target vehicle adjusts the vertical field of view to the first target angle.

[0020] Optionally, determining the first target angle based on the slope of the ramp, the height of the target pedestrian, and the target distance includes:

[0021] Based on the slope, determine the angle between the target pedestrian and the slope;

[0022] Based on the height of the target pedestrian, the target distance, and the angle between the target pedestrian and the ramp, the distance between the target vehicle and the target point on the target pedestrian is determined by the law of cosines.

[0023] The first target angle is determined using the law of cosines based on the height of the target pedestrian, the target distance, and the distance between the target vehicle and the target point on the target pedestrian.

[0024] Optionally, the method further includes:

[0025] If there are no pedestrians around the target vehicle and the ramp is uphill, and the slope of the ramp is less than or equal to a preset slope threshold, the lidar is controlled to shift the vertical field of view downward by a second target angle; if the slope of the ramp is greater than the preset slope threshold, the lidar is controlled to shift the vertical field of view downward by a third target angle, where the second target angle is the slope of the ramp and the third target angle is the limit shift angle of the vertical field of view.

[0026] If there are no pedestrians around the target vehicle and the ramp is downhill, and the slope of the ramp is less than or equal to the preset slope threshold, the lidar is controlled to shift the vertical field of view upwards to the second target angle; if the slope of the ramp is greater than the preset slope threshold, the lidar is controlled to shift the vertical field of view upwards to the third target angle.

[0027] Optionally, before controlling the lidar of the target vehicle to adjust the vertical field of view of the laser beam based on the slope of the ramp and the pedestrian information, the method further includes:

[0028] Determine the distance between the target vehicle and the starting position of the ramp;

[0029] The step of controlling the vertical field of view of the laser beam of the target vehicle's lidar based on the slope of the ramp and the pedestrian information includes:

[0030] If the distance between the target vehicle and the starting position is less than or equal to a preset distance threshold, the vertical field of view of the laser beam of the target vehicle's lidar is adjusted based on the slope of the ramp and the pedestrian information.

[0031] Optionally, before obtaining the slope of a ramp in front of the target vehicle, the method further includes:

[0032] Based on the location of the target vehicle, obtain road information within a preset road range of the location from a high-precision map;

[0033] If the road information includes ramp information, it is determined that there is a ramp in front of the target vehicle;

[0034] If the road information does not include ramp information, it is determined that there is no ramp in front of the target vehicle.

[0035] Secondly, a lidar control device is provided, the device comprising:

[0036] The first acquisition module is used to acquire the slope of the ramp when there is a ramp in front of the target vehicle.

[0037] The first determining module is used to detect pedestrians around the target vehicle and determine whether there are pedestrians around the target vehicle;

[0038] The first control module is used to control the lidar of the target vehicle to adjust the vertical field of view of the laser beam based on the slope of the ramp and the pedestrian information when there are pedestrians around the target vehicle.

[0039] Optionally, the first control module is used to:

[0040] If there are pedestrians around the target vehicle, determine the relative positions of the pedestrians and the target vehicle;

[0041] Based on the relative position, the position of the lidar, the slope of the ramp, and the pedestrian information, the lidar of the target vehicle is controlled to adjust the vertical field of view of the laser beam.

[0042] Optionally, the first control module is used to:

[0043] Based on the relative position and the position of the lidar, determine whether the pedestrian is within the emission range of the lidar's laser beam;

[0044] When the pedestrian is within the emission range of the laser beam, the target vehicle's lidar is controlled to adjust the vertical field of view of the laser beam based on the slope of the ramp and the pedestrian's information.

[0045] Optionally, the pedestrian information includes the height of at least one pedestrian and the distance between the at least one pedestrian and the target vehicle, and the first control module is used to:

[0046] The height and target distance of the target pedestrian are obtained from the pedestrian information, wherein the height of the target pedestrian is the lowest among the heights of the at least one pedestrian, and the target distance is the distance between the target pedestrian and the target vehicle;

[0047] Based on the slope of the ramp, the height of the target pedestrian, and the target distance, a first target angle is determined. The first target angle is the angle at which the laser beam of the lidar cannot scan the eyes of at least one pedestrian.

[0048] The lidar controlling the target vehicle adjusts the vertical field of view to the first target angle.

[0049] Optionally, the first control module is used to:

[0050] Based on the slope, determine the angle between the target pedestrian and the slope;

[0051] Based on the height of the target pedestrian, the target distance, and the angle between the target pedestrian and the ramp, the distance between the target vehicle and the target point on the target pedestrian is determined by the law of cosines.

[0052] The first target angle is determined using the law of cosines based on the height of the target pedestrian, the target distance, and the distance between the target vehicle and the target point on the target pedestrian.

[0053] Optionally, the device further includes:

[0054] The second control module is used to, when there are no pedestrians around the target vehicle and the ramp is uphill, control the lidar to shift the vertical field of view downward by a second target angle if the slope of the ramp is less than or equal to a preset slope threshold; and control the lidar to shift the vertical field of view downward by a third target angle if the slope of the ramp is greater than the preset slope threshold. The second target angle is the slope of the ramp, and the third target angle is the limit shift angle of the vertical field of view.

[0055] The third control module is used to, when there are no pedestrians around the target vehicle and the ramp is downhill, control the lidar to shift the vertical field of view upwards to the second target angle if the slope of the ramp is less than or equal to the preset slope threshold; and control the lidar to shift the vertical field of view upwards to the third target angle if the slope of the ramp is greater than the preset slope threshold.

[0056] Optionally, the device further includes:

[0057] The second determining module is used to determine the distance between the target vehicle and the starting position of the ramp;

[0058] Optionally, the first control module is used to:

[0059] If the distance between the target vehicle and the starting position is less than or equal to a preset distance threshold, the vertical field of view of the laser beam of the target vehicle's lidar is adjusted based on the slope of the ramp and the pedestrian information.

[0060] Optionally, the device further includes:

[0061] The second acquisition module is used to acquire road information within a preset road range of the target vehicle from a high-precision map based on the target vehicle's location;

[0062] The third determining module is used to determine that there is a slope in front of the target vehicle when the road information includes slope information;

[0063] The fourth determining module is used to determine that there is no ramp in front of the target vehicle when the road information does not include ramp information.

[0064] Thirdly, a vehicle is provided, the vehicle comprising:

[0065] Memory, used to store executable program code;

[0066] A processor is configured to call and run the executable program code from the memory, causing the vehicle to perform the aforementioned lidar control method.

[0067] Fourthly, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-described lidar control method.

[0068] Fifthly, a computer program product containing instructions is provided, which, when run on a computer, causes the computer to perform the steps of the aforementioned lidar control method.

[0069] It is understood that the beneficial effects of the second, third, fourth, and fifth aspects mentioned above can be found in the relevant descriptions in the first aspect above, and will not be repeated here. Attached Figure Description

[0070] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0071] Figure 1 This is a schematic diagram of the working process of a lidar provided in an embodiment of this application;

[0072] Figure 2 This is a schematic diagram of a lidar emitting a laser beam according to an embodiment of this application;

[0073] Figure 3 This is a flowchart of a lidar control method provided in an embodiment of this application;

[0074] Figure 4 This is a schematic diagram illustrating the determination of the location information of the target vehicle provided in an embodiment of this application;

[0075] Figure 5 This is a schematic diagram illustrating the determination of a first target angle provided in an embodiment of this application;

[0076] Figure 6 This is a schematic diagram illustrating another method for determining the first target angle provided in an embodiment of this application;

[0077] Figure 7 This is a flowchart of another lidar control method provided in the embodiments of this application;

[0078] Figure 8 This is a schematic diagram of the structure of a lidar control device provided in an embodiment of this application;

[0079] Figure 9 This is a schematic diagram of the structure of a vehicle provided in an embodiment of this application. Detailed Implementation

[0080] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0081] It should be understood that "multiple" as mentioned in this application refers to two or more. In the description of this application, unless otherwise stated, " / " indicates "or," for example, A / B can mean A or B; "and / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist, for example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Furthermore, to facilitate a clear description of the technical solutions of this application, the terms "first," "second," etc., are used to distinguish identical or similar items with essentially the same function and effect. Those skilled in the art will understand that the terms "first," "second," etc., do not limit the quantity or execution order, and that "first," "second," etc., do not necessarily imply differences.

[0082] First, the lidar involved in the embodiments of this application will be explained.

[0083] Figure 1 This is a schematic diagram illustrating the workflow of a lidar system provided in an embodiment of this application. See also... Figure 1 The lidar includes a laser emitting system 101, a laser receiving system 102, and an information processing system 103.

[0084] The laser emitting system 101 includes a laser 104, a beam controller 105, and an emitting optical system 106. The beam controller 105 includes a scanning mirror. The laser 104 periodically emits laser pulses. After receiving the laser pulses, the beam controller 105 can control the direction and beam of the laser emission by changing the direction of the scanning mirror. Finally, the laser pulses are emitted as a laser beam through the emitting optical system 106, thereby emitting a laser beam into the surrounding environment. The beam controller can control the vertical field of view of the laser beam emission by changing the up-down direction of the scanning mirror.

[0085] The laser receiving system 102 includes a receiving optical system 107 and a photodetector 108. When a laser beam emitted into the surrounding environment reaches the surface of an object, it is reflected by the surface and enters the lidar through the receiving optical system 107. The photodetector 108 can receive the laser beam reflected back from the surface of the object, thereby generating a reflected signal.

[0086] The information processing system 103 includes an amplifier 109 and an information processing module 110. The reflected signal generated by the laser receiving system 102 can enter the amplifier 109, where the transmitted signal is amplified for subsequent processing. The amplified transmitted signal is then converted from digital to analog and sent to the information processing module 110 for calculation, thereby obtaining information such as the shape and physical properties of objects in the surrounding environment.

[0087] Before providing a detailed description of the methods provided in the embodiments of this application, the application scenarios of this application will be explained first.

[0088] Currently, the laser beams emitted by automotive lidar systems have two wavelengths: 905nm and 1550nm. Laser beams with wavelengths below 1400nm can penetrate the eye's fluids and damage the retina. While laser beams with wavelengths above 1400nm cannot penetrate the eye's fluids, prolonged direct viewing can still burn the cornea, thus causing damage to the eye.

[0089] In addition, when a car is driving on a slope, the coverage of the laser beam emitted by the lidar on the surrounding environment will change, which will increase the damage to the human eye.

[0090] For example, Figure 2 This is a comparison diagram of a laser beam emitted by a lidar on flat ground and a laser beam emitted on a slope. Figure 2 (a) in the diagram is a schematic diagram of a lidar emitting a laser beam on flat ground. Figure 2 (b) is a schematic diagram of a lidar emitting a laser beam on a slope.

[0091] See Figure 2 In diagram (a), a car is driving on flat ground with a pedestrian in front of it. The car's lidar emits a laser beam at a certain direction and angle. As can be seen from the diagram, the height of the laser beam emitted by the lidar only passes the pedestrian's shoulder and does not penetrate the pedestrian's eye.

[0092] See Figure 2 In (b), a car is driving on a slope, and there is a pedestrian in front of it. The car's lidar emits a laser beam in the same direction and angle, but the height of the emitted laser beam has reached the pedestrian's eyes, thus causing damage to the pedestrian's eyes.

[0093] Therefore, this application provides a lidar control method that can be applied to scenarios where lidar is controlled on a slope.

[0094] Specifically, the system first determines if there is a ramp in front of the car. If a ramp exists, its gradient can be determined. Next, it detects if there are pedestrians around the car. If pedestrians are detected, the system adjusts the direction of the laser beam emitted by the car's lidar based on the ramp's gradient and the pedestrian information. In other words, when pedestrians are present, the laser beam's direction is adjusted to avoid hitting their eyes. This prevents the lidar's emitted laser beam from damaging the eyes and ensures pedestrian safety.

[0095] The lidar control method provided in the embodiments of this application will be explained in detail below.

[0096] Figure 3 This is a flowchart illustrating a lidar control method provided in an embodiment of this application. This method can be applied to a vehicle controller, for example, the controller could be a vehicle's intelligent driving domain controller. See also... Figure 3 The method includes the following steps.

[0097] Step 301: If there is a ramp in front of the target vehicle, obtain the slope of the ramp.

[0098] It is worth noting that before step 301, it can be determined whether there is a ramp in front of the target vehicle.

[0099] Specifically, determining whether there is a ramp in front of the target vehicle may include the following steps (1)-(3).

[0100] (1) Based on the location of the target vehicle, obtain road information within the preset road range of the location from the high-precision map.

[0101] High-precision maps, also known as high-resolution maps, include road elements such as lane lines, road signs, traffic signs, traffic lights, zebra crossings, stop lines, curbs, guardrails, bridges, slopes, and curves, as well as attribute information of road elements such as the number of lanes, lane groups, lane curvature, and slope. They also include real-time traffic dynamics information at the lane level and other road information.

[0102] The preset road range can be set in advance, and can also be set by technicians according to actual needs. For example, the preset road range can be set to the road range 200 meters in front of the target vehicle.

[0103] In this way, the high-precision map can accurately obtain road information within the preset road range of the target vehicle, that is, accurately obtain relevant information about the road ahead of the target vehicle.

[0104] Optionally, step (1) can be performed as follows: determine the location information of the target vehicle using a high-precision positioning algorithm; obtain a high-precision map; match the location information of the target vehicle with the high-precision map to obtain the location of the target vehicle on the high-precision map; and obtain road information within a preset road range from the target vehicle from the high-precision map.

[0105] In this scenario, after determining the target vehicle's location, the next step is to find a location on a high-precision map that is relatively close to the target vehicle's location. This location is then the target vehicle's position on the high-precision map. Next, road information within a preset road range from the target vehicle is obtained from the high-precision map.

[0106] Optionally, the target vehicle may be equipped with a GNSS (Global Navigation Satellite System) antenna, which can receive satellite positioning signals. In this case, the operation of determining the location information of the target vehicle through a high-precision positioning algorithm can be as follows: the target vehicle's location information is obtained by the vehicle-to-everything (T-BOX) intelligent terminal based on the satellite positioning signal.

[0107] For example, Figure 4 This is a schematic diagram for determining the location information of a target vehicle. See also... Figure 4 , Figure 4 This includes GNSS antenna 401, RTK (Real Time Kinematic) service 402, vehicle-to-everything (V2X) intelligent terminal 403, GNSS positioning data 404, and IMU (Inertial Measurement Unit) data 405.

[0108] GNSS antenna 401 is used to receive satellite positioning signals, RTK service 402 is used to determine the positioning deviation of the target vehicle, and GNSS positioning data 404 includes satellite positioning signals and positioning deviation. IMU data 405 consists of the vehicle attitude data and lateral velocity of the target vehicle measured by the inertial measurement unit. Vehicle-to-everything (V2X) intelligent terminal 403 is used to perform positioning calculations to obtain the position information of the target vehicle.

[0109] Due to errors caused by satellite positioning signals penetrating the ionosphere and troposphere, errors caused by the Doppler effect from high-speed satellite movement, orbital errors, satellite clock errors, and ephemeris errors, the position information of a target vehicle obtained solely from satellite positioning signals may be inaccurate. Therefore, RTK services can be used to determine the positioning deviation, thereby eliminating the aforementioned errors and obtaining accurate position information for the target vehicle.

[0110] After the GNSS antenna 401 receives the satellite positioning signal, the vehicle-to-everything (V2X) intelligent terminal 403 can acquire the satellite positioning signal. Simultaneously, the target vehicle's RTK service 402 can determine the target vehicle's positioning deviation and send this deviation to the V2X intelligent terminal 403. Then, the V2X intelligent terminal 403 can perform fusion positioning calculation based on the GNSS positioning data 404 and IMU data 405 using a positioning calculation algorithm to obtain the target vehicle's location information.

[0111] In this embodiment of the application, the positioning accuracy of the target vehicle can be improved by determining the location information of the target vehicle based on a high-precision positioning algorithm.

[0112] It should be noted that, in this embodiment, the vehicle-to-everything (V2X) intelligent terminal 403 can perform fusion positioning calculation using any positioning algorithm, and this embodiment does not limit it to a single one. For example, the V2X intelligent terminal 403 can perform positioning calculation using a positioning algorithm based on the Differential Global Navigation Satellite System (DGNSS).

[0113] (2) If the road information includes ramp information, determine that there is a ramp in front of the target vehicle.

[0114] High-precision maps contain road elements such as lane lines, road signs, traffic signs, traffic lights, zebra crossings, stop lines, curbs, guardrails, bridges, ramps, and curves, as well as attribute information for these elements, including the number of lanes, lane groupings, lane curvature, and gradient. They also include real-time lane-level traffic dynamics. Therefore, high-precision maps can provide road information corresponding to a specific road segment, including road elements and their attribute information.

[0115] In this case, if the road information within the preset road range obtained from the high-precision map includes ramp information, it means that the high-precision map contains ramp elements within the preset road range from the target vehicle. In other words, there is a ramp within the preset road range from the target vehicle, thus confirming that there is a ramp in front of the target vehicle.

[0116] (3) If the road information does not include slope information, determine that there is no slope in front of the target vehicle.

[0117] In this case, if the road information within the preset road range obtained from the high-precision map does not include ramp information, it means that the high-precision map does not include ramp elements within the preset road range from the target vehicle. In other words, there is no ramp within the preset road range from the target vehicle, thus it can be determined that there is no ramp in front of the target vehicle.

[0118] It is worth noting that, in this embodiment of the application, road information within a preset road range from the target vehicle can be obtained on a high-precision map, thereby allowing the target vehicle's driving conditions to be known in advance, and thus enabling a decision to control the lidar in advance.

[0119] Furthermore, if it is determined that there is a slope in front of the target vehicle, the slope of the slope can be obtained from the road information within the preset road range.

[0120] Specifically, the road information includes road elements and their attribute information. For example, if the preset road area includes a ramp, and the ramp's attribute information includes that its slope is 30°, then the slope of the ramp can be obtained from the road information.

[0121] Optionally, the operation of determining whether there is a ramp in front of the target vehicle can also be as follows: capturing an image of the front of the target vehicle using the target vehicle's camera; then classifying the image of the front of the target vehicle; if the classification result indicates that there is a ramp, determining that there is a ramp in front of the target vehicle; if the classification result indicates that there is no ramp, determining that there is no ramp in front of the target vehicle.

[0122] The operation of classifying the image in front of the target vehicle can be as follows: input the image in front of the target vehicle into the ramp classification model, classify the image in front of the target vehicle through the ramp classification model, and output the classification result.

[0123] It is worth noting that the ramp classification model can be trained using computer equipment before the image in front of the target vehicle is input into the ramp classification model.

[0124] The computer equipment is used to train the ramp classification model. The computer equipment can be a desktop computer, a laptop computer, or a server.

[0125] Optionally, the computer device can acquire multiple first training samples and use these multiple first training samples to train the neural network model to obtain a ramp classification model.

[0126] The plurality of first training samples can be pre-set. Each of the plurality of first training samples includes sample data and sample labels. The sample data can be a sample image, and the sample labels can be the classification results corresponding to the sample image. The input data for each of the plurality of training samples is the sample image, and the sample labels are the classification results corresponding to the sample image.

[0127] This neural network model can include multiple network layers, including an input layer, multiple hidden layers, and an output layer. The input layer is responsible for receiving input data; the output layer is responsible for outputting the processed data; the multiple hidden layers are located between the input and output layers and are responsible for processing the data. These hidden layers are not visible to the outside world. For example, this neural network model can be a deep neural network model, and it can be a convolutional neural network, etc., within deep neural networks.

[0128] In this process, when a computer device trains a neural network model using multiple first training samples, for each of these first training samples, the input data from that first training sample is input into the neural network model to obtain output data. A loss function is then used to determine the loss value between the output data and the sample labels in that first training sample. The parameters of the neural network model are then adjusted based on this loss value. After adjusting the parameters of the neural network model based on each of these first training samples, the adjusted neural network model becomes the ramp classification model.

[0129] The operation of adjusting the parameters in the neural network model based on the loss value by the computer device can refer to relevant technologies, and will not be described in detail in the embodiments of this application.

[0130] For example, computer equipment can use formulas This allows for the adjustment of any parameter in the neural network model. These are the adjusted parameters. W is the parameter before adjustment. α is the learning rate, which can be preset, such as 0.001, 0.000001, etc., and this embodiment does not limit this to a single value. dW is the derivative of the loss function with respect to W, which can be obtained from the loss value.

[0131] In this scenario, if the classification result indicates the presence of a ramp, it means the ramp classification model has identified a ramp in the image, thus confirming that a ramp exists in front of the target vehicle. Conversely, if the classification result indicates the absence of a ramp, it means the ramp classification model has identified a ramp not existing in the image, thus confirming that a ramp does not exist in front of the target vehicle. This allows for accurate determination of whether a ramp exists in front of the target vehicle.

[0132] Optionally, the vehicle's body attitude information can be measured through the target vehicle's chassis controller, so that it can be determined whether there is a slope in front of the target vehicle based on the target vehicle's body attitude information.

[0133] For example, the target vehicle's body attitude information includes its pitch angle. In this case, if the absolute value of the target vehicle's pitch angle is greater than or equal to a preset pitch angle threshold, it is determined that there is a ramp in front of the target vehicle; if the absolute value of the target vehicle's pitch angle is less than the preset pitch angle threshold, it is determined that there is no ramp in front of the target vehicle.

[0134] The preset pitch angle threshold can be set in advance, and the preset pitch angle threshold can be set relatively large. If the absolute value of the target vehicle's pitch angle is greater than or equal to the preset pitch angle threshold, it indicates that the target vehicle's pitch angle is large, meaning that the angle at which the front of the target vehicle tilts up or down is large. This suggests that the target vehicle is likely on a slope, and therefore, it can be confirmed that there is a slope in front of the target vehicle. If the absolute value of the target vehicle's pitch angle is less than the preset pitch angle threshold, it indicates that the target vehicle's pitch angle is small, meaning that the front of the target vehicle does not tilt up or down significantly. This suggests that the target vehicle is likely on flat ground, and therefore, it can be confirmed that there is no slope in front of the target vehicle.

[0135] Furthermore, if there is a slope in front of the target vehicle, the slope can be measured using the inertial sensors of the target vehicle.

[0136] Step 302: Perform pedestrian detection around the target vehicle to determine whether there are pedestrians around the target vehicle.

[0137] Specifically, the operation of step 302 may include the following steps (1)-(2).

[0138] (1) Obtain environmental information around the target vehicle.

[0139] The environmental information around the target vehicle is used to indicate whether there are pedestrians around the target vehicle.

[0140] The operation in step (1) can be achieved in the following two possible ways.

[0141] The first possible approach is to obtain environmental information about the target vehicle by capturing images of the surrounding environment using the vehicle's camera. In this case, the environmental information is the environmental image captured by the camera.

[0142] The second possible approach is to obtain environmental information about the target vehicle's surroundings by acquiring point clouds from the vehicle's radar. In this case, the environmental information around the target vehicle is the point cloud acquired by the radar.

[0143] Of course, environmental information around the target vehicle can be collected using either of the two methods mentioned above, or by combining both methods.

[0144] (2) Based on this environmental information, determine whether there are pedestrians around the target vehicle.

[0145] Specifically, step (2) can be performed as follows: target detection is performed on the environmental information around the target vehicle. If the target detection result indicates that there are pedestrians, it is determined that there are pedestrians around the target vehicle; if the target detection result indicates that there are no pedestrians, it is determined that there are no pedestrians around the target vehicle.

[0146] The operation of detecting targets in the environment around the target vehicle can be as follows: input the environmental information around the target vehicle into the pedestrian detection model, perform pedestrian detection on the environmental information through the pedestrian detection model, and output the target detection result.

[0147] It is worth noting that before inputting the environmental information around the target vehicle into the pedestrian detection model, the pedestrian detection model can also be trained using computer equipment.

[0148] Optionally, the computer device can acquire multiple second training samples and use these multiple second training samples to train the neural network model to obtain a pedestrian detection model.

[0149] The plurality of second training samples can be pre-set. Each of the plurality of second training samples includes sample data and sample labels. The sample data can be environmental sample information, and the sample labels are the detection results corresponding to the environmental sample information. The input data of each of the plurality of training samples is environmental sample information, and the sample labels are the detection results corresponding to the environmental sample information.

[0150] Specifically, the operation of the computer device training the pedestrian detection model based on the multiple second training samples is similar to the operation of the computer device training the ramp classification model based on the multiple first training samples, and will not be described in detail in the embodiments of this application.

[0151] Furthermore, if it is determined that there are pedestrians around the target vehicle, the pedestrian information can also be determined based on the environmental information around the target vehicle.

[0152] Optionally, the operation of determining pedestrian information based on the environmental information around the target vehicle can be: performing information separation on the environmental information around the target vehicle to obtain the pedestrian information.

[0153] Information separation is used to extract information about pedestrians from environmental information.

[0154] The pedestrian information may include the pedestrian's height, as well as the pedestrian's status (stationary, walking, etc.) and the distance between the pedestrian and the target vehicle.

[0155] Optionally, the operation of separating the environmental information around the target vehicle to obtain the pedestrian information can be as follows: separating the pedestrian from the environmental information around the target vehicle, and then identifying the separated pedestrian to obtain the pedestrian information.

[0156] For example, a target segmentation algorithm can separate pedestrians from the environmental information around a target vehicle, and then identify the separated pedestrians to obtain their information.

[0157] Optionally, if at least one pedestrian is present in the environment surrounding the target vehicle, the pedestrian information may further include a pedestrian identifier, which is used to uniquely identify the at least one pedestrian. For example, if there are two pedestrians in the environment surrounding the target vehicle, the pedestrian identifier for the first pedestrian can be 1, and the pedestrian identifier for the second pedestrian can be 2.

[0158] It is worth noting that when there is a ramp in front of the target vehicle, the area around the target vehicle includes the ramp. Therefore, when performing pedestrian detection around the target vehicle, it is possible to detect whether there are pedestrians on the ramp in front of the target vehicle.

[0159] Thus, step 302 above can determine whether there are pedestrians around the target vehicle.

[0160] Furthermore, when there are no pedestrians around the target vehicle, the vertical field of view of the laser beam of the target vehicle's lidar is adjusted based on the slope of the ramp.

[0161] The vertical field of view of the laser beam can be adjusted using the laser radar's beam controller.

[0162] When a target vehicle is traveling on a slope, the coverage area of ​​the laser beam emitted by its lidar changes compared to when it's on flat ground. For example, when the target vehicle is going uphill, its pitch angle increases, causing the lidar beam's coverage area to tilt upwards. This results in some laser beams being emitted ineffectively, preventing the lidar from accurately detecting environmental information on the slope. Therefore, when a target vehicle is traveling on a slope, the vertical field of view of the lidar beam can be adjusted based on the slope's gradient.

[0163] In this situation, the LiDAR of the target vehicle can adaptively adjust the vertical field of view of the laser beam according to the slope of the ramp to constrain invalid laser beam emission and ensure that the laser beam emitted into the surrounding environment is effective as much as possible. Thus, the LiDAR can accurately detect the environmental information of the ramp and improve driving safety.

[0164] Specifically, based on the slope of the ramp, the operation of adjusting the vertical field of view of the laser beam of the lidar controlling the target vehicle can be achieved in the following two possible scenarios.

[0165] First, if the slope is uphill and the slope is less than or equal to a preset slope threshold, the lidar will be controlled to shift the vertical field of view downwards by a second target angle; if the slope is greater than the preset slope threshold, the lidar will be controlled to shift the vertical field of view downwards by a third target angle.

[0166] The second target angle is the slope of the ramp, and the third target angle is the limit offset angle of the vertical field of view.

[0167] Because the slope is steep, the target vehicle's pitch angle will also be very large. Consequently, the laser beam emitted by the lidar will cover a significantly higher area in the surrounding environment, resulting in a large number of ineffective laser beams. Since the vertical field of view of the lidar can only be shifted by a fixed angle, it's impossible to ensure all laser beams emitted by the lidar are effective simply by adjusting the vertical field of view on a steep slope. In this situation, to minimize ineffective laser beams, the lidar's vertical field of view can be shifted downwards by a maximum offset angle.

[0168] The preset slope threshold corresponds to the limit offset angle. When the slope of the ramp is less than the preset slope threshold, the vertical field of view of the LiDAR can be offset within an angle range smaller than the limit offset angle. When the slope of the ramp is greater than the preset slope threshold, the vertical field of view of the LiDAR reaches the maximum offset angle (limit offset angle) and cannot be offset further. The preset slope threshold can be set in advance, and the preset slope threshold can be set to the same as the limit offset angle of the vertical field of view. For example, if the limit offset angle of the vertical field of view is 45°, the preset slope threshold can be set to 45°.

[0169] In this scenario, if the slope of the ramp is less than or equal to a preset slope threshold, it indicates a relatively small slope, and the vertical field of view of the LiDAR can be shifted within an angle range less than or equal to the limit offset angle. Furthermore, when the target vehicle is going uphill, due to the slope, the coverage area of ​​the laser beam emitted by the LiDAR in the surrounding environment will also be tilted upwards at the same angle as the slope. Therefore, the LiDAR's vertical field of view can be subsequently controlled to shift downwards by the same angle as the slope, i.e., to shift the vertical field of view downwards by a second target angle. This ensures that the laser beam emitted by the LiDAR is effective when the target vehicle is going uphill.

[0170] If the slope of the ramp exceeds a preset slope threshold, it indicates that the slope is too steep, and the vertical field of view of the lidar has reached its maximum offset angle (limit offset angle), making further offset impossible. Furthermore, when the target vehicle is going uphill, due to the slope, the coverage area of ​​the lidar's emitted laser beam in the surrounding environment will also be tilted upwards at the same angle as the slope. Therefore, to minimize the amount of invalid laser beams emitted by the lidar, the vertical field of view can be controlled to shift downwards by the limit offset angle, that is, to shift the vertical field of view downwards by the third target angle.

[0171] Second, if the slope is downhill and the slope is less than or equal to a preset slope threshold, the lidar will be controlled to shift the vertical field of view upwards by a second target angle; if the slope is greater than the preset slope threshold, the lidar will be controlled to shift the vertical field of view upwards by a third target angle.

[0172] In this scenario, if the slope of the ramp is less than or equal to a preset slope threshold, it indicates a relatively small slope, and the vertical field of view of the LiDAR can be shifted within an angle range less than or equal to the limit offset angle. Furthermore, when the target vehicle is descending a slope, due to the slope, the coverage area of ​​the laser beam emitted by the LiDAR in the surrounding environment will decrease by the same angle as the slope. Therefore, the LiDAR can be subsequently controlled to shift its vertical field of view upwards by the same angle as the slope, i.e., to shift the vertical field of view upwards by a second target angle. This ensures that the laser beam emitted by the LiDAR is effective when the target vehicle is descending a slope.

[0173] If the slope of the ramp exceeds a preset slope threshold, it indicates that the slope is too steep, and the vertical field of view of the lidar has reached its maximum offset angle (limit offset angle), making further offset impossible. Furthermore, when the target vehicle is descending a slope, the coverage area of ​​the lidar's emitted laser beam in the surrounding environment will decrease by the same angle as the slope due to the slope. Therefore, to minimize the amount of invalid laser beams emitted by the lidar, the vertical field of view can be controlled to shift upwards by the limit offset angle, which is equivalent to shifting the lidar's vertical field of view upwards by a third target angle.

[0174] Step 303: When there are pedestrians around the target vehicle, control the LiDAR of the target vehicle to adjust the vertical field of view of the laser beam based on the slope of the ramp and the pedestrian information.

[0175] Since there are pedestrians around the target vehicle, it indicates that there may also be pedestrians on the slope. Therefore, when the target vehicle is driving on the slope, the laser beam emitted by the lidar may cause damage to the eyes of pedestrians. Thus, the lidar controlling the target vehicle adjusts the vertical field of view of the laser beam.

[0176] In this situation, by controlling the vertical field of view of the lidar based on the slope of the ramp and pedestrian information, the laser beam emitted by the lidar can be kept away from the eyes of pedestrians when the target vehicle is driving on the ramp, thereby avoiding damage to the eyes by the laser beam and protecting the eyes of pedestrians.

[0177] Optionally, after determining that there is a ramp in front of the target vehicle, the distance between the target vehicle and the starting position of the ramp can also be determined.

[0178] Optionally, the distance between the target vehicle and the starting position of the ramp can be determined in real time during the target vehicle's journey.

[0179] In this case, step 303 can be performed as follows: when the distance between the target vehicle and the starting position of the ramp is less than or equal to a preset distance threshold, the vertical field of view of the laser beam of the target vehicle's lidar is adjusted based on the slope of the ramp and pedestrian information.

[0180] The preset distance threshold can be set in advance, and the preset distance threshold can be set to a relatively small value. For example, the preset distance threshold can be set to 2 meters.

[0181] In this case, if the distance between the target vehicle and the starting position of the ramp is less than or equal to a preset distance threshold, it means that the distance between the target vehicle and the starting position of the ramp is small, that is, the target vehicle is about to reach the ramp. Therefore, based on the slope of the ramp and pedestrian information, the vertical field of view of the laser beam of the target vehicle's lidar can be adjusted so that the laser beam emitted by the lidar will not enter the eyes of the person after the target vehicle enters the ramp.

[0182] If the distance between the target vehicle and the starting position of the ramp is greater than the preset distance threshold, it means that the target vehicle is far from the starting position of the ramp. In other words, the target vehicle is currently driving on flat ground and far from the ramp. In order to ensure the effectiveness of the laser beam emitted by the lidar on flat ground, the vertical field of view of the lidar can be adjusted without controlling it.

[0183] Of course, if the target vehicle has already entered the ramp, the vertical field of view of the laser beam of the target vehicle's lidar can be adjusted based on the slope of the ramp and pedestrian information to avoid the laser beam from entering the human eye. This application does not limit this.

[0184] Specifically, the operation of step 303 may include the following steps (1)-(3).

[0185] (1) Obtain the height and target distance of the target pedestrian from the pedestrian information.

[0186] If there is at least one pedestrian in the surrounding environment of the target vehicle, the pedestrian information is the pedestrian information of that at least one pedestrian.

[0187] Wherein, the target pedestrian's height is the shortest among at least one pedestrian's height, and the target pedestrian is the shortest among those at least one pedestrian. The target distance is the distance between the target pedestrian and the target vehicle.

[0188] In this case, by obtaining the lowest height among the at least one pedestrians and then adjusting the vertical field of view accordingly, the laser beam emitted by the lidar can be prevented from entering the eyes of any of the at least one pedestrians, thus ensuring the protection of the eyes of each of the at least one pedestrians.

[0189] (2) Determine the first target angle based on the slope of the ramp, the height of the target pedestrian and the target distance.

[0190] The first target angle is the angle at which the laser beam of the lidar cannot scan the eyes of each of the at least one pedestrian.

[0191] Optionally, step (2) can be performed as follows: based on the slope of the ramp, determine the angle between the target pedestrian and the ramp; based on the height of the target pedestrian, the target distance, and the angle between the target pedestrian and the ramp, determine the distance between the target vehicle and the target point on the target pedestrian using the law of cosines; based on the height of the target pedestrian, the target distance, and the distance between the target vehicle and the target point on the target pedestrian, determine the first target angle using the law of cosines.

[0192] The target point can be any point on the body below the eyes of the target pedestrian. Optionally, the target point can be two-thirds of the height of the target pedestrian. Since two-thirds of a person's height is below the head, setting the target point to two-thirds of the height of the target pedestrian ensures that the laser beam will not enter the person's eyes when the vertical field of view of the lidar is at the first target angle.

[0193] The operation of determining the angle between the target pedestrian and the ramp based on the ramp's slope can be as follows: if the ramp is uphill, add 90° to the ramp's slope to obtain the angle between the target pedestrian and the ramp; if the ramp is downhill, subtract the ramp's slope from 90° to obtain the angle between the target pedestrian and the ramp.

[0194] For example, Figure 5 This is a schematic diagram illustrating how to determine the first target angle when the slope is uphill. See also... Figure 5 , Figure 5The system includes points A, B, and C. Point A indicates the location of the target vehicle, point B indicates the location of the target pedestrian, and point C indicates the target point on the pedestrian's body, located at two-thirds of the pedestrian's height. The laser beam from the lidar is emitted from point A into the surrounding environment.

[0195] Figure 5 In the diagram, points A, B, and C form an obtuse triangle. Side AB represents the distance between the target vehicle and the target pedestrian (target distance), and side CB represents the height of the target point, which is two-thirds of the pedestrian's height. The angle α between side AB and side CB is the angle between the pedestrian and the ramp.

[0196] To prevent the laser beam from entering the human eye, the laser light at the outer edge of the beam must not reach the eye. In this example, the laser light at the outer edge of the beam should reach the target point at its highest point. This is done so that the laser beam is emitted at an angle β between side length AC and side length AB, ensuring that the pedestrian's eyes are not damaged.

[0197] Therefore, based on the height of the target pedestrian, the target distance, and the angle between the target pedestrian and the ramp, the operation of determining the distance between the target vehicle and the target point on the target pedestrian using the cosine theorem can be achieved by the following formula (1).

[0198] AC 2 =AB 2 +BC 2 -2×AB×BC×cosα (1)

[0199] Where AC is the distance between the target vehicle and the target point, which is the distance from the outer edge of the laser beam emitted from the lidar to the target point.

[0200] Subsequently, based on the height of the target pedestrian, the target distance, and the distance between the target vehicle and the target point on the target pedestrian, the operation of determining the first target angle through the law of cosines can be achieved by the following formula (2).

[0201]

[0202] Where β is the first target angle, from Figure 5 As can be seen, when the vertical field of view of the lidar is the first target angle, the laser beam emitted by it will not enter the eyes of the target pedestrian, and thus will not enter the eyes of other pedestrians, thereby protecting the pedestrians' eyes.

[0203] For example, if the target pedestrian's height is 1.5m, the target distance is 3m, and the slope of the ramp is 30°, then the angle α between the target pedestrian and the ramp is 120°. The distance between the target vehicle and the target point can then be obtained using the above formula (1):

[0204]

[0205] The distance between the target vehicle and the target point is 3.61 meters. Then, the first target angle is obtained using the above formula (2):

[0206]

[0207] The cosine value of the first target angle is 0.971011, so the first target angle is 13.83°.

[0208] For example, Figure 6 This is a schematic diagram illustrating how to determine the first target angle when the slope is downhill. See also... Figure 6 , Figure 6 The system includes points A, B, and C. Point A indicates the location of the target vehicle, point B indicates the location of the target pedestrian, and point C indicates the target point on the pedestrian's body, located at two-thirds of the pedestrian's height. The laser beam from the lidar is emitted from point A into the surrounding environment.

[0209] Figure 6 In the diagram, points A, B, and C form an acute triangle. Side AB represents the distance between the target vehicle and the target pedestrian (target distance), and side CB represents the height of the target point, which is two-thirds of the target pedestrian's height. The angle α between side AB and side CB is the angle between the target pedestrian and the ramp.

[0210] For example, if the target pedestrian's height is 1.5m, the target distance is 3m, and the slope of the ramp is 30°, then the angle α between the target pedestrian and the ramp is 60°. The distance between the target vehicle and the target point can then be obtained using the above formula (1):

[0211]

[0212] The distance between the target vehicle and the target point is 2.65m. Then, the first target angle is obtained using the above formula (2):

[0213]

[0214] The cosine value of the first target angle is 0.944811, so the first target angle is 19.12°.

[0215] In this way, when the vertical field of view of the lidar is the first target angle, the laser beam emitted by it will not enter the eyes of the target pedestrian, and therefore will not enter the eyes of other pedestrians among the at least one pedestrian, thus protecting the pedestrian's eyes.

[0216] (3) The lidar controlling the target vehicle adjusts the vertical field of view to the first target angle.

[0217] Since the first target angle is the angle at which the laser beam of the lidar cannot scan the eyes of at least one pedestrian, controlling the lidar to adjust its vertical field of view to the first target angle ensures that the laser beam emitted by the lidar cannot scan the eyes of at least one pedestrian when the target vehicle is going uphill or downhill, thus protecting the eyes of at least one pedestrian.

[0218] The vertical field of view can be adjusted to the first target angle using the laser radar's beam controller.

[0219] Optionally, after determining the first target angle, a control message can be sent to the lidar, carrying the first target angle. Upon receiving the control message, the lidar adjusts its vertical field of view to the first target angle.

[0220] Optionally, if it is determined that there are pedestrians around the target vehicle, the vertical field of view of the laser beam of the target vehicle's lidar can be adjusted according to the location of the pedestrians, the slope of the ramp, and the pedestrian information.

[0221] Specifically, the relative positions of pedestrians and target vehicles are determined; based on these relative positions, the position of the lidar, the slope of the ramp, and the pedestrian information, the lidar of the target vehicle is controlled to adjust the vertical field of view of the laser beam.

[0222] In this situation, determining the relative position of the pedestrian and the target vehicle allows us to know the pedestrian's position around the target vehicle. Then, based on this relative position, the position of the lidar, the slope of the ramp, and the pedestrian's information, we can jointly control the lidar to adjust the field of view of the laser beam. We can flexibly control the lidar to adjust the vertical field of view of the laser beam according to the pedestrian's position.

[0223] Optionally, the relative position of the pedestrian and the target vehicle can be detected by the target vehicle's sensors. These sensors can be lidar, millimeter-wave radar, ultrasonic sensors, cameras, etc. This application embodiment does not limit this to a single type.

[0224] Optionally, based on the relative position, the position of the lidar, the slope of the ramp, and the pedestrian information, the operation of controlling the lidar of the target vehicle to adjust the vertical field of view of the laser beam can be as follows: based on the relative position and the position of the lidar, determine whether the pedestrian is within the emission range of the lidar's laser beam; if the pedestrian is within the emission range of the laser beam, based on the slope of the ramp and the pedestrian information, control the lidar of the target vehicle to adjust the vertical field of view of the laser beam.

[0225] First, based on the relative positions of the pedestrian and the target vehicle, and the position of the lidar, it is determined whether the pedestrian is within the lidar's laser beam emission range. In other words, it's determined whether the pedestrian's location will be scanned by the laser beam, and therefore whether the laser beam might cause eye damage. Once it's determined that the pedestrian is within the laser beam emission range, the vertical field of view of the target vehicle's lidar is adjusted. This means that, given the potential for eye damage, the vertical field of view of the laser beam is adjusted accordingly. This allows for precise control of the lidar, ensuring its normal operating performance while precisely preventing eye damage from the laser beam.

[0226] Furthermore, when pedestrians are not within the emission range of the laser beam, the lidar of the target vehicle is not controlled, that is, the vertical field of view of the laser beam is not adjusted.

[0227] In this scenario, if the pedestrian is not within the laser beam's emission range, it means the pedestrian's location will not be scanned by the laser beam. Therefore, it can be determined that the laser beam will not cause damage to the pedestrian's eyes, and thus, no control over the lidar is required; that is, the laser beam's field of view does not need to be adjusted. This allows the lidar to normally acquire environmental information around the target vehicle, ensuring that the lidar's normal operating performance is not degraded.

[0228] The operation of determining whether a pedestrian is within the laser beam emission range of the lidar based on the relative position and the lidar position can be as follows: determine the laser beam emission range based on the lidar position; determine whether the relative position is within the laser beam emission range; if the relative position is within the laser beam emission range, determine that the pedestrian is within the lidar laser beam emission range; if the relative position is not within the lidar laser beam emission range, determine that the pedestrian is not within the lidar laser beam emission range.

[0229] Optionally, the emission range of the laser beam can be a fan-shaped area with the current field of view of the laser beam as the target angle and a preset distance as the radius. The preset distance is the maximum distance that the laser beam can propagate in the surrounding environment.

[0230] Optionally, lidar can be installed on multiple parts of the target vehicle, such as the front, left front, and right front of the vehicle. In this case, the vertical field of view of the lidar on the corresponding parts of the target vehicle can be adjusted based on the pedestrian's position, the slope of the ramp, and the pedestrian's information.

[0231] In this way, by adjusting the vertical field of view of the corresponding part of the lidar on the target vehicle according to the position of the pedestrian, the lidar can still collect environmental information around the target vehicle normally without damaging the human eye, thus ensuring that the working performance of the lidar is not reduced.

[0232] In this scenario, the location of pedestrians can also be detected. Optionally, the location of pedestrians can be detected using sensors on the target vehicle. These sensors can be lidar, millimeter-wave radar, ultrasonic sensors, cameras, etc., and this application does not limit this to a single type.

[0233] For example, if a pedestrian is detected in front of the target vehicle, the lidar mounted on the front of the target vehicle can be adjusted to change its vertical field of view. Similarly, if a pedestrian is detected to be on the right front side of the target vehicle, the lidar on the right front side of the target vehicle can be adjusted to change its vertical field of view.

[0234] It is worth noting that if at least one pedestrian is present around the target vehicle, and if the at least one pedestrian is detected to be in a different position relative to the target vehicle, the vertical field of view of the lidar corresponding to the position of the at least one pedestrian can be adjusted based on the slope of the ramp and the pedestrian information of the at least one pedestrian.

[0235] For example, if there are two pedestrians around a target vehicle, and one pedestrian is detected in front of the target vehicle while the other is located to the right front of the target vehicle, then the vertical field of view of the LiDAR located at the front of the target vehicle can be adjusted based on the slope of the ramp and the pedestrian information of the first pedestrian. Similarly, the vertical field of view of the LiDAR located at the front of the target vehicle can be adjusted based on the slope of the ramp and the pedestrian information of the second pedestrian.

[0236] It is worth noting that the distance between the target vehicle and the pedestrian may change as the target vehicle moves, which will affect the emission angle (vertical field of view) of the laser beam. Therefore, while the target vehicle is moving, pedestrian information can be determined in real time. Subsequently, based on the real-time pedestrian information and slope, the vertical field of view of the laser radar can be adjusted to ensure that the laser beam emitted by the laser radar will never enter the person's eyes while the vehicle is moving.

[0237] To facilitate understanding, we will now combine... Figure 7 The lidar control method provided in the embodiments of this application is illustrated by way of example. See also Figure 7 , Figure 7 This includes steps 701-708.

[0238] Step 701: The vehicle-to-everything (V2X) intelligent terminal of the target vehicle determines the location information of the target vehicle and then sends the location information of the target vehicle to the intelligent driving domain controller.

[0239] Step 702: The intelligent driving domain controller acquires a high-precision map.

[0240] Step 703: The intelligent driving domain controller determines whether there is a ramp in front of the target vehicle based on the target vehicle's location information and high-precision map.

[0241] Step 704: When there is a slope in front of the target vehicle, the intelligent driving domain controller obtains the slope of the slope.

[0242] Step 705: The intelligent driving domain controller performs pedestrian detection around the target vehicle to determine whether there are pedestrians around the target vehicle.

[0243] Step 706: When there are pedestrians around the target vehicle, the intelligent driving domain controller determines a first target angle based on the slope of the ramp and the pedestrian information. The first target angle is the angle at which the laser beam of the lidar cannot scan the eyes of at least one pedestrian.

[0244] Step 707: The intelligent driving domain controller sends a control message to the lidar to control the lidar to adjust the vertical field of view to the first target angle.

[0245] Step 708: The lidar adjusts the vertical field of view to the first target angle through the beam controller, thereby ensuring that the laser beam emitted by the lidar will not enter the human eye, thus protecting the human eye.

[0246] In this embodiment, the controller first determines whether a ramp exists in front of the target vehicle. If a ramp exists, it obtains the ramp's slope. Then, it performs pedestrian detection around the target vehicle to determine if any pedestrians are present. If pedestrians are present, based on the ramp's slope and the pedestrian information, it controls the target vehicle's lidar to adjust the vertical field of view of the laser beam. In other words, when pedestrians are present, adjusting the vertical field of view prevents the lidar's laser beam from entering the pedestrians' eyes. This avoids damage to the pedestrians' eyes from the lidar's laser beam, thus protecting their vision.

[0247] Figure 8 This is a schematic diagram of a lidar control device provided in an embodiment of this application. The lidar control device can be implemented by software, hardware, or a combination of both as part or all of a vehicle, which can be described below. Figure 9 The vehicle shown. See also Figure 8 The device includes: a first acquisition module 801, a first determination module 802, and a first control module 803.

[0248] The first acquisition module 801 is used to acquire the slope of a ramp when there is a ramp in front of the target vehicle.

[0249] The first determining module 802 is used to detect pedestrians around the target vehicle and determine whether there are pedestrians around the target vehicle.

[0250] The first control module 803 is used to control the lidar of the target vehicle to adjust the vertical field of view of the laser beam based on the slope of the ramp and the pedestrian information when there are pedestrians around the target vehicle.

[0251] Optionally, the first control module 803 is used for:

[0252] If there are pedestrians around the target vehicle, determine the relative positions of the pedestrians and the target vehicle;

[0253] Based on the relative position, the position of the lidar, the slope of the ramp, and pedestrian information, the lidar of the target vehicle is controlled to adjust the vertical field of view of the laser beam.

[0254] Optionally, the first control module 803 is used for:

[0255] Based on the relative position and the position of the lidar, it is determined whether the pedestrian is within the emission range of the lidar's laser beam;

[0256] When a pedestrian is within the emission range of the laser beam, the target vehicle's lidar adjusts the vertical field of view of the laser beam based on the slope of the ramp and the pedestrian's information.

[0257] Optionally, the pedestrian information includes the height of at least one pedestrian and the distance between the at least one pedestrian and the target vehicle. The first control module 803 is used for:

[0258] The height and target distance of the target pedestrian are obtained from the pedestrian information. The height of the target pedestrian is the lowest among the heights of at least one pedestrian, and the target distance is the distance between the target pedestrian and the target vehicle.

[0259] Based on the slope of the ramp, the height of the target pedestrian, and the target distance, a first target angle is determined. The first target angle is the angle at which the laser beam of the lidar cannot scan the eyes of at least one pedestrian.

[0260] The lidar controlling the target vehicle adjusts the vertical field of view to the first target angle.

[0261] Optionally, the first control module 803 is used for:

[0262] Based on this slope, determine the angle between the target pedestrian and the slope;

[0263] Based on the target pedestrian's height, target distance, and the angle between the target pedestrian and the ramp, the distance between the target vehicle and the target point on the target pedestrian is determined by the law of cosines.

[0264] Based on the height of the target pedestrian, the target distance, and the distance between the target vehicle and the target point on the target pedestrian, the first target angle is determined using the law of cosines.

[0265] Optionally, the device further includes:

[0266] The second control module is used to control the lidar to shift the vertical field of view downward by a second target angle when there are no pedestrians around the target vehicle and the ramp is uphill. If the slope of the ramp is less than or equal to a preset slope threshold, the lidar will shift the vertical field of view downward by a third target angle. The second target angle is the slope of the ramp, and the third target angle is the limit shift angle of the vertical field of view.

[0267] The third control module is used to control the lidar to shift the vertical field of view upwards to the second target angle when there are no pedestrians around the target vehicle and the slope is downhill. If the slope of the slope is less than or equal to the preset slope threshold, the lidar will shift the vertical field of view upwards to the third target angle.

[0268] Optionally, the device further includes:

[0269] The second determining module is used to determine the distance between the target vehicle and the starting position of the ramp;

[0270] Optionally, the first control module 803 is used for:

[0271] If the distance between the target vehicle and the starting position of the ramp is less than or equal to a preset distance threshold, the vertical field of view of the laser beam of the target vehicle's lidar is adjusted based on the slope of the ramp and the pedestrian information.

[0272] Optionally, the device further includes:

[0273] The second acquisition module is used to acquire road information within a preset road range of the target vehicle's location from a high-precision map.

[0274] The third determining module is used to determine whether there is a slope in front of the target vehicle when the road information includes slope information;

[0275] The fourth determination module is used to determine that there is no slope in front of the target vehicle when the road information does not include slope information.

[0276] In this embodiment, it is first determined whether there is a ramp in front of the target vehicle. If a ramp exists, its slope is obtained. Then, pedestrian detection is performed around the target vehicle to determine if any pedestrians are present. If pedestrians are present, based on the ramp slope and pedestrian information, the vertical field of view of the target vehicle's lidar is adjusted. In other words, when pedestrians are present, the vertical field of view is adjusted to prevent the lidar-emitted laser beam from entering the pedestrians' eyes. This avoids damage to the pedestrians' eyes from the lidar-emitted laser beam, thus protecting their eyes.

[0277] It should be noted that the lidar control device provided in the above embodiments is only illustrated by the division of the above functional modules when controlling lidar. In actual applications, the above 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.

[0278] The functional units and modules in the above embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of the embodiments of this application.

[0279] The lidar control device and lidar control method embodiments provided in the above embodiments belong to the same concept. The specific working process and technical effects of the units and modules in the above embodiments can be found in the method embodiment section, and will not be repeated here.

[0280] Figure 9 This is a schematic diagram of the structure of a vehicle provided in an embodiment of this application.

[0281] For example, such as Figure 9 As shown, the vehicle includes a memory 91 and a processor 90, wherein the memory 91 stores executable program code 92, and the processor 90 is used to call and execute the executable program code 92 to perform the aforementioned lidar control method.

[0282] This embodiment can divide the vehicle into functional modules according to the above method example. For example, each function can be assigned to a separate module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0283] When each functional module is divided according to its corresponding function, the vehicle may include: a first acquisition module, a first determination module, and a first control module. It should be noted that all relevant content of each step involved in the above method embodiments can be referenced from the functional descriptions of the corresponding functional modules, and will not be repeated here.

[0284] The vehicle provided in this embodiment is used to execute the above-described lidar control method, and therefore can achieve the same effect as the above-described implementation method.

[0285] When using integrated units, the vehicle may include a processing module and a storage module. The processing module is used to control and manage the vehicle's actions. The storage module supports the vehicle in executing program code and data.

[0286] The processing module may be a processor or a controller, which can implement or execute various exemplary logic blocks, modules, and circuits as disclosed in this application. The processor may also be a combination of computing functions, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and microprocessors, etc., and the storage module may be a memory.

[0287] This embodiment also provides a computer-readable storage medium storing computer program code. When the computer program code is run on a computer, the computer executes the aforementioned method steps to implement the aforementioned method for controlling a lidar in the above embodiment.

[0288] This embodiment also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned related steps to implement the aforementioned method for controlling a lidar in the above embodiment.

[0289] In this embodiment, the vehicle, computer-readable storage medium, computer program product, or chip are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects of the corresponding methods provided above, and will not be repeated here.

[0290] Through the above description of the embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above 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.

[0291] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0292] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A lidar control method, characterized in that, The method includes: If there is a ramp in front of the target vehicle, the slope of the ramp is obtained, and the target vehicle is equipped with lidar in multiple parts. Pedestrian detection is performed around the target vehicle to determine whether there are pedestrians around the target vehicle; When there are pedestrians around the target vehicle, the vertical field of view of the laser beam of the corresponding part of the laser radar on the target vehicle is adjusted according to the position of the pedestrians, the slope of the ramp and the pedestrian information. The step of controlling the vertical field of view of the laser beam of the corresponding part of the target vehicle's lidar to be adjusted based on the pedestrian's position, the slope of the ramp, and the pedestrian's information includes: Based on the location of the pedestrian, determine the corresponding location of the lidar on the target vehicle; The height and target distance of the target pedestrian are obtained from the pedestrian information, wherein the height of the target pedestrian is the lowest among at least one pedestrian's height, and the target distance is the distance between the target pedestrian and the target vehicle; Based on the slope, determine the angle between the target pedestrian and the slope; Based on the height of the target pedestrian, the target distance, and the angle between the target pedestrian and the ramp, the distance between the target vehicle and the target point on the target pedestrian is determined by the law of cosines. The target point is located at two-thirds of the height of the target pedestrian. Based on the height of the target pedestrian, the target distance, and the distance between the target vehicle and the target point on the target pedestrian, a first target angle is determined by the law of cosines. The first target angle is the angle at which the laser beam of the lidar cannot scan the eyes of at least one pedestrian. The lidar on the corresponding part of the target vehicle is controlled to adjust the vertical field of view to the first target angle.

2. The method as described in claim 1, characterized in that, In the case where pedestrians are present around the target vehicle, based on the slope of the ramp and the pedestrian information, the system controls the lidar of the target vehicle to adjust the vertical field of view of the laser beam, including: If there are pedestrians around the target vehicle, determine the relative positions of the pedestrians and the target vehicle; Based on the relative position, the position of the lidar, the slope of the ramp, and the pedestrian information, the lidar of the target vehicle is controlled to adjust the vertical field of view of the laser beam.

3. The method as described in claim 2, characterized in that, The step of controlling the vertical field of view of the laser beam of the target vehicle's laser radar to adjust based on the relative position, the position of the laser radar, the slope of the ramp, and the pedestrian information includes: Based on the relative position and the position of the lidar, determine whether the pedestrian is within the emission range of the lidar's laser beam; When the pedestrian is within the emission range of the laser beam, the target vehicle's lidar is controlled to adjust the vertical field of view of the laser beam based on the slope of the ramp and the pedestrian's information.

4. The method as described in claim 1, characterized in that, The method further includes: If there are no pedestrians around the target vehicle and the ramp is uphill, and the slope of the ramp is less than or equal to a preset slope threshold, the lidar is controlled to shift the vertical field of view downward by a second target angle; if the slope of the ramp is greater than the preset slope threshold, the lidar is controlled to shift the vertical field of view downward by a third target angle, where the second target angle is the slope of the ramp and the third target angle is the limit shift angle of the vertical field of view. If there are no pedestrians around the target vehicle and the ramp is downhill, and the slope of the ramp is less than or equal to the preset slope threshold, the lidar is controlled to shift the vertical field of view upwards to the second target angle; if the slope of the ramp is greater than the preset slope threshold, the lidar is controlled to shift the vertical field of view upwards to the third target angle.

5. The method as described in claim 1, characterized in that, Before controlling the vertical field of view of the laser beam of the target vehicle's lidar to adjust based on the slope of the ramp and the pedestrian information, the method further includes: Determine the distance between the target vehicle and the starting position of the ramp; The step of controlling the vertical field of view of the laser beam of the target vehicle's lidar based on the slope of the ramp and the pedestrian information includes: If the distance between the target vehicle and the starting position is less than or equal to a preset distance threshold, the vertical field of view of the laser beam of the target vehicle's lidar is adjusted based on the slope of the ramp and the pedestrian information.

6. The method as described in claim 1, characterized in that, Before obtaining the slope of a ramp in front of the target vehicle, the method further includes: Based on the location of the target vehicle, obtain road information within a preset road range of the location from a high-precision map; If the road information includes ramp information, it is determined that there is a ramp in front of the target vehicle; If the road information does not include ramp information, it is determined that there is no ramp in front of the target vehicle.

7. A lidar control device, characterized in that, The device includes: The first acquisition module is used to acquire the slope of the ramp when there is a ramp in front of the target vehicle, wherein the target vehicle is equipped with lidar at multiple locations. The first determining module is used to detect pedestrians around the target vehicle and determine whether there are pedestrians around the target vehicle; The first control module is used to, when there are pedestrians around the target vehicle, control the lidar at the corresponding part of the target vehicle to adjust the vertical field of view of the laser beam based on the position of the pedestrians, the slope of the ramp, and the pedestrian information. The first control module is specifically used for: determining the corresponding LiDAR location on the target vehicle based on the pedestrian's position; obtaining the target pedestrian's height and target distance from the pedestrian information, wherein the target pedestrian's height is the lowest among at least one pedestrian's height, and the target distance is the distance between the target pedestrian and the target vehicle; determining the angle between the target pedestrian and the slope based on the slope; determining the distance between the target vehicle and a target point on the target pedestrian using the law of cosines based on the target pedestrian's height, target distance, and the angle between the target pedestrian and the slope, wherein the target point is located at two-thirds of the target pedestrian's height; determining a first target angle using the law of cosines based on the target pedestrian's height, target distance, and the distance between the target vehicle and the target point on the target pedestrian, wherein the first target angle is the angle at which the laser beam of the LiDAR cannot scan the eyes of at least one pedestrian; and controlling the LiDAR on the corresponding location on the target vehicle to adjust the vertical field of view to the first target angle.

8. A vehicle, characterized in that, The vehicles include: Memory, used to store executable program code; A processor for calling and running the executable program code from the memory, causing the vehicle to perform the method as described in any one of claims 1 to 6.

Images