Lidar control method, apparatus, and vehicle

Abstract

The application discloses a laser radar control method and device and a vehicle, and belongs to the technical field of vehicles. The method comprises the following steps: acquiring pedestrian information of a pedestrian and a pitch angle of a target vehicle in the case that the pedestrian is in a transmitting range of a laser radar of the target vehicle; determining a maximum transmitting angle of a laser beam of the laser radar based on the pedestrian information of the pedestrian and the pitch angle of the target vehicle, the maximum transmitting angle being an angle at which the laser beam of the laser radar cannot scan the eyes of the pedestrian; and controlling the laser radar to adjust a vertical field angle of the laser beam based on the maximum transmitting angle. The application determines the maximum transmitting angle of the laser beam in the case that the pedestrian is in the transmitting range of the laser radar, and then controls the laser radar to adjust the vertical field angle of the laser beam based on the maximum transmitting angle. In this way, it is ensured that the laser beam emitted by the laser radar will not cause damage to the eyes of the pedestrian, and the eyes of the pedestrian are protected.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicles, in particular to a laser radar control method and device and vehicle. BACKGROUND

[0002] In the technical field of vehicles, a vehicle can collect environmental information around the vehicle through a laser radar. The laser radar can emit a detection signal (laser beam) to the surrounding environment of the vehicle through a laser emission system, and then receive the reflected laser signal from the environment through a laser receiving system. Then, the information processing system of the laser radar can obtain the shape, physical properties and other information about the objects in the surrounding environment based on the detection signal and the reflected laser signal.

[0003] At present, the wavelength of the laser beam emitted by the laser radar of the vehicle is divided into 905nm (nanometer) and 1550nm. Since the laser beam with a wavelength below 1400nm can penetrate the ocular fluid of the human eye and cause damage to the retina, the laser beam with a wavelength exceeding 1400nm cannot penetrate the ocular fluid, but the human eye can still be burned in the cornea in the front part of the eye when looking directly for a long time. Therefore, when a pedestrian is in the surrounding of the vehicle, the laser beam emitted by the laser radar can cause damage to the human eye. SUMMARY

[0004] The present application provides a laser radar control method, device, vehicle and storage medium, which can control the laser radar to avoid the laser beam emitted by the laser radar from entering the eyes of the pedestrian, thereby avoiding damage to the eyes of the pedestrian. The technical solution is as follows:

[0005] In a first aspect, a laser radar control method is provided, the method comprising:

[0006] In the case that a pedestrian is in the emission range of the laser radar of a target vehicle, obtaining pedestrian information of the pedestrian and a pitch angle of the target vehicle;

[0007] Based on the pedestrian information of the pedestrian and the pitch angle of the target vehicle, determining a maximum emission angle of the laser beam of the laser radar, the maximum emission angle being an angle at which the laser beam of the laser radar cannot scan the eyes of the pedestrian;

[0008] Based on the maximum emission angle, controlling the laser radar to adjust the vertical field angle of the laser beam.

[0009] In the present application, the pedestrian information of the pedestrian and the pitch angle of the target vehicle are acquired in the case that the pedestrian is in the emission range of the laser radar of the target vehicle, that is, the pedestrian information of the pedestrian and the pitch angle of the target vehicle are acquired in the case that the laser radar of the target vehicle is likely to shoot into the eyes of the pedestrian. Then, the maximum emission angle of the laser beam of the laser radar is determined based on the pedestrian information of the pedestrian and the pitch angle of the target vehicle, and the laser beam emitted by the laser radar at the maximum emission angle will not scan the eyes of the pedestrian. Therefore, subsequent control of the laser radar to adjust the vertical field angle of the laser beam based on the maximum emission angle can prevent the emitted laser beam from shooting into the eyes of the pedestrian. In this way, it is ensured that the laser beam emitted by the laser radar will not cause damage to the eyes of the pedestrian, thereby protecting the eyes of the pedestrian.

[0010] Optionally, before the maximum emission angle of the laser beam of the laser radar is determined based on the pedestrian information of the pedestrian and the pitch angle of the target vehicle, the method further comprises:

[0011] In the case that the pitch angle of the target vehicle is less than or equal to a preset angle threshold, it is determined that the target vehicle is on flat ground.

[0012] Optionally, the pedestrian information includes the height of the pedestrian and the distance between the pedestrian and the target vehicle, and the determination of the maximum emission angle of the laser beam of the laser radar based on the pedestrian information of the pedestrian and the pitch angle of the target vehicle comprises:

[0013] In the case that the target vehicle is on flat ground, the height of a target point is determined based on the height of the pedestrian, the target point being any one point below the eye part of the body part of the pedestrian;

[0014] The maximum emission angle is determined by a tangent function based on the height of the target point and the distance between the pedestrian and the target vehicle.

[0015] Optionally, before the maximum emission angle of the laser beam of the laser radar is determined based on the pedestrian information of the pedestrian and the pitch angle of the target vehicle, the method further comprises:

[0016] In the case that the pitch angle of the target vehicle is greater than a preset angle threshold, it is determined that the target vehicle is on a slope.

[0017] Optionally, the pedestrian information includes the height of the pedestrian and the distance between the pedestrian and the target vehicle, and the determination of the maximum emission angle of the laser beam of the laser radar based on the pedestrian information of the pedestrian and the pitch angle of the target vehicle comprises:

[0018] determining the pitch angle as a slope of the slope when the target vehicle is on the slope, and determining an angle between the pedestrian and the slope based on the slope;

[0019] determining the distance between the target vehicle and the target point by the cosine theorem based on the height of the pedestrian, the distance between the pedestrian and the target vehicle, and the angle between the pedestrian and the slope, the target point being any one point below the eye part in the body part of the pedestrian;

[0020] determining the maximum emission angle by the cosine theorem based on the height of the pedestrian, the distance between the pedestrian and the target vehicle, and the distance between the target vehicle and the target point.

[0021] Optionally, before the determining the emission angle of the laser beam of the lidar based on the pedestrian information of the pedestrian, the method further comprises:

[0022] when the pedestrian is not in the emission range of the lidar of the target vehicle, acquiring a motion direction of the pedestrian, a current position of the pedestrian, and a motion speed of the pedestrian;

[0023] determining whether the pedestrian is in the emission range of the lidar after a preset time based on the motion direction of the pedestrian, the current position of the pedestrian, and the motion speed of the pedestrian;

[0024] when the pedestrian is in the emission range of the lidar after the preset time, acquiring pedestrian information of the pedestrian and a pitch angle of the target vehicle, and determining a maximum emission angle of the laser beam of the lidar based on the pedestrian information of the pedestrian and the pitch angle of the target vehicle.

[0025] Optionally, before the acquiring the pedestrian information of the pedestrian when the pedestrian is in the emission range of the lidar of the target vehicle, the method further comprises:

[0026] acquiring environmental information around the target vehicle;

[0027] determining whether there is a pedestrian around the target vehicle based on the environmental information;

[0028] when there is a pedestrian around the target vehicle, determining whether the pedestrian is in the emission range of the lidar.

[0029] Optionally, the method further comprises:

[0030] determining whether there is a target road around the target vehicle, the target road comprising at least one of a pedestrian crossing and a non-motor vehicle lane;

[0031] In a case where the target road exists around the target vehicle, it is determined whether a pedestrian exists around the target vehicle.

[0032] Optionally, in a case where the pedestrian exists around the target vehicle, it is determined whether the pedestrian is in a transmitting range of the lidar, including:

[0033] In a case where the pedestrian exists around the target vehicle, a position of the pedestrian is acquired;

[0034] Based on the position of the lidar and a current field of view angle, a coverage area of a laser beam of the lidar in the surrounding environment is determined;

[0035] In a case where the position of the pedestrian is included in the coverage area, it is determined that the pedestrian is in the transmitting range of the lidar;

[0036] In a case where the position of the pedestrian is not included in the coverage area, it is determined that the pedestrian is not in the transmitting range of the lidar.

[0037] Optionally, the controlling the lidar to adjust the vertical field of view angle of the laser beam based on the maximum transmitting angle includes any one of:

[0038] The lidar is controlled to adjust the vertical field of view angle of the laser beam to the maximum transmitting angle;

[0039] The lidar is controlled to adjust the vertical field of view angle of the laser beam to a target angle, the target angle being less than the maximum transmitting angle.

[0040] In a second aspect, a lidar control device is provided, and the device includes:

[0041] A first acquisition module is configured to, in a case where a pedestrian is in a transmitting range of a lidar of a target vehicle, acquire pedestrian information of the pedestrian and a pitch angle of the target vehicle;

[0042] A first determination module is configured to, based on the pedestrian information of the pedestrian and the pitch angle of the target vehicle, determine a maximum transmitting angle of a laser beam of the lidar, the maximum transmitting angle being an angle at which the laser beam of the lidar cannot scan to an eye of the pedestrian;

[0043] A control module is configured to, based on the maximum transmitting angle, control the lidar to adjust a vertical field of view angle of the laser beam.

[0044] Optionally, the device further includes:

[0045] The second determining module is configured to determine that the target vehicle is on a flat ground if the pitch angle of the target vehicle is less than or equal to a preset angle threshold.

[0046] Optionally, the pedestrian information comprises a height of the pedestrian and a distance between the pedestrian and the target vehicle, and the first determining module is configured to:

[0047] The height of the target point is determined based on the height of the pedestrian if the target vehicle is on the flat ground, the target point being any one point below the eye part of the pedestrian.

[0048] The maximum emission angle is determined by a tangent function based on the height of the target point and the distance between the pedestrian and the target vehicle.

[0049] Optionally, the device further comprises:

[0050] The third determining module is configured to determine that the target vehicle is on a slope if the pitch angle of the target vehicle is greater than the preset angle threshold.

[0051] Optionally, the pedestrian information comprises a height of the pedestrian and a distance between the pedestrian and the target vehicle, and the first determining module is configured to:

[0052] The pitch angle is determined as a slope of the slope if the target vehicle is on the slope, and an angle between the pedestrian and the slope is determined based on the slope.

[0053] The distance between the target vehicle and a target point is determined by a cosine theorem based on the height of the pedestrian, the distance between the pedestrian and the target vehicle, and the angle between the pedestrian and the slope, the target point being any one point below the eye part of the pedestrian.

[0054] The maximum emission angle is determined by the cosine theorem based on the height of the pedestrian, the distance between the pedestrian and the target vehicle, and the distance between the target vehicle and the target point.

[0055] Optionally, the device further comprises:

[0056] The second obtaining module is configured to obtain a motion direction of the pedestrian, a current position of the pedestrian, and a motion speed of the pedestrian if the pedestrian is not in a transmission range of a laser radar of the target vehicle.

[0057] The fourth determining module is configured to determine whether the pedestrian is in the transmission range of the laser radar after a preset time length based on the motion direction of the pedestrian, the current position of the pedestrian, and the motion speed of the pedestrian.

[0058] The execution module is configured to, in a case where the pedestrian is in a transmission range of the lidar after a preset time length, acquire pedestrian information of the pedestrian and a pitch angle of the target vehicle, and determine a maximum transmission angle of a laser beam of the lidar based on the pedestrian information of the pedestrian and the pitch angle of the target vehicle.

[0059] Optionally, the device further comprises:

[0060] The third acquisition module is configured to acquire environmental information around the target vehicle.

[0061] The fifth determination module is configured to determine whether there is a pedestrian around the target vehicle based on the environmental information.

[0062] The sixth determination module is configured to, in a case where there is a pedestrian around the target vehicle, determine whether the pedestrian is in a transmission range of the lidar.

[0063] Optionally, the device further comprises:

[0064] The seventh determination module is configured to determine whether there is a target road around the target vehicle, the target road comprising at least one of a pedestrian crossing and a non-motor vehicle lane.

[0065] The eighth determination module is configured to, in a case where there is the target road around the target vehicle, determine whether there is a pedestrian around the target vehicle.

[0066] Optionally, the sixth determination module is configured to:

[0067] In a case where there is a pedestrian around the target vehicle, acquire a position of the pedestrian;

[0068] Determine a coverage area of the laser beam of the lidar in the surrounding environment based on a position of the lidar and a current field of view angle of the lidar;

[0069] In a case where the position of the pedestrian is included in the coverage area, determine that the pedestrian is in the transmission range of the lidar;

[0070] In a case where the position of the pedestrian is not included in the coverage area, determine that the pedestrian is not in the transmission range of the lidar.

[0071] Optionally, the control module is configured to:

[0072] Control the lidar to adjust a vertical field of view angle of the laser beam to the maximum transmission angle; or

[0073] Control the lidar to adjust a vertical field of view angle of the laser beam to a target angle, the target angle being less than the maximum transmission angle.

[0074] In a third aspect, a vehicle is provided, and the vehicle comprises:

[0075] a memory for storing executable program code;

[0076] a processor for invoking and running the executable program code from the memory, so that the vehicle performs the above-mentioned lidar control method.

[0077] In a fourth aspect, a computer-readable storage medium is provided, and the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the above-mentioned lidar control method.

[0078] In a fifth aspect, a computer program product containing instructions is provided, which, when executed on a computer, causes the computer to perform the steps of the above-mentioned lidar control method.

[0079] It can be understood that the beneficial effects of the above-mentioned second aspect, third aspect, fourth aspect and fifth aspect can be referred to the related description in the first aspect, which will not be repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0080] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0081] Figure 1 is a working flow diagram of a lidar provided by the embodiments of the present application;

[0082] Figure 2 is a scene diagram of a lidar control method provided by the embodiments of the present application;

[0083] Figure 3 is a flowchart of a lidar control method provided by the embodiments of the present application;

[0084] Figure 4 is a diagram for determining the maximum emission angle provided by the first embodiment of the present application;

[0085] Figure 5 is a diagram for determining the maximum emission angle provided by the second embodiment of the present application;

[0086] Figure 6 is a diagram for determining the maximum emission angle provided by the third embodiment of the present application;

[0087] Figure 7 is a schematic diagram of a scanning mirror of a laser radar provided by an embodiment of the present application;

[0088] Figure 8 is a flowchart of another laser radar control method provided by an embodiment of the present application;

[0089] Figure 9 is a structural schematic diagram of a laser radar control device provided by an embodiment of the present application;

[0090] Figure 10 is a structural schematic diagram of a vehicle provided by an embodiment of the present application. DETAILED DESCRIPTION

[0091] In order to make the purpose, technical solutions and advantages of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the drawings.

[0092] It should be understood that the "multiple" mentioned in the present application refers to two or more. In the description of the present application, unless otherwise specified, " / " represents the meaning of or, for example, A / B can represent A or B; "and / or" in the present application is only a description of the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which means that there are three cases of A alone, A and B together, and B alone. In addition, in order to clearly describe the technical solutions of the present application, the same items or similar items with basically the same function and role are distinguished by using "first", "second", etc. The skilled in the art can understand that "first", "second", etc. do not limit the quantity and execution order, and "first", "second", etc. also do not limit the difference.

[0093] First, the laser radar related to the embodiments of the present application is explained and described.

[0094] Figure 1 is a working flowchart of a laser radar provided by an embodiment of the present application. Referring to Figure 1 , the laser radar includes a laser emitting system 101, a laser receiving system 102 and an information processing system 103.

[0095] 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 is used to periodically emit laser pulses, and the beam controller 105 can control the direction and beam of the laser emission by changing the direction of the scanning mirror after receiving the laser pulses. Finally, the laser pulses are emitted through the emitting optical system 106 to form a laser beam, thereby realizing the emission of the laser beam to the surrounding environment. Among them, the beam controller can realize the control of the vertical field angle of the laser beam emission by changing the up-down direction of the scanning mirror.

[0096] The laser receiving system 102 includes a receiving optical system 107 and a photoelectric detector 108. The laser beam emitted into the surrounding environment is reflected on the surface of the object when reaching the surface of the object, thereby entering the laser radar through the receiving optical system 107, and the photoelectric detector 108 can receive the laser emitted back through the surface of the object, thereby generating a reflection signal.

[0097] The information processing system 103 includes an amplifier 109 and an information processing module 110. The reflection signal generated by the laser receiving system 102 can enter the amplifier 109, and the amplifier 109 amplifies the emission signal for subsequent processing. After the amplified and processed emission signal is converted into an analog signal, it is sent to the information processing module 110 for calculation, thereby obtaining the shape, physical properties and other information of the object in the surrounding environment.

[0098] Before the method provided by the embodiments of the present application is described in detail, the application scenario of the present application is described.

[0099] At present, the wavelength of the laser beam emitted by the laser radar of the automobile is divided into 905nm (nanometer) and 1550nm. Since the laser beam with a wavelength below 1400nm can penetrate the ocular fluid of the human eye and cause damage to the retina, the laser beam with a wavelength exceeding 1400nm cannot penetrate the ocular fluid, but the human eye can still be burned in the cornea in the front part of the eye in a long time of direct vision, so the laser beam can still cause damage to the human eye.

[0100] For example, Figure 2 is a scene schematic diagram of a laser radar control method. Referring to Figure 2 , the automobile is driving on the road, and the laser radar on the automobile emits a laser beam in a certain direction and angle, and there is a pedestrian in front of the automobile, and the pedestrian is in the emission range of the laser radar of the automobile. As Figure 2 indicated, the laser beam of the laser radar can enter the eyes of the pedestrian, which can cause damage to the eyes of the pedestrian.

[0101] Therefore, the embodiments of the present application provide a laser radar control method, which can be applied to the scene of controlling the laser radar when there is a pedestrian around the automobile.

[0102] Specifically, in the case that there is a pedestrian around the vehicle, it is determined whether the pedestrian is in the emission range of the laser radar, in the case that the pedestrian is in the emission range of the laser radar, pedestrian information of the pedestrian is acquired, such as the height of the pedestrian, the distance between the pedestrian and the vehicle, etc., and the pitch angle of the vehicle is acquired. Then, according to the pedestrian information of the pedestrian and the pitch angle of the vehicle, the emission angle at which the laser radar emits the laser beam without shooting into the eyes of the pedestrian is determined, so that the vertical field angle of the laser beam of the laser radar is adjusted based on the emission angle subsequently, so that the laser beam emitted by the laser radar will not shoot into the eyes of the pedestrian. In this way, the damage of the laser beam to the eyes of the pedestrian is avoided, and the eyes of the pedestrian are protected.

[0103] The laser radar control method provided by the embodiment of the present application will be explained and described in detail below.

[0104] Figure 3 is a flowchart of a laser radar control method provided by the embodiment of the present application. The method can be applied to a controller of a vehicle, for example, the controller can be an intelligent driving domain controller of the vehicle. Referring to Figure 3 , the method includes the following steps.

[0105] Step 301: In the case that a pedestrian is in the emission range of the laser radar of the target vehicle, acquire pedestrian information of the pedestrian and a pitch angle of the target vehicle.

[0106] The pedestrian information of the pedestrian is information related to the pedestrian, and the pedestrian information can include the height of the pedestrian, the distance between the pedestrian and the target vehicle, the motion direction of the pedestrian, etc. In addition, the pedestrians around the target vehicle may not all be in the state of walking upright, and the state of the pedestrian may be riding a bicycle, riding a motorcycle, etc.

[0107] The pitch angle of the target vehicle refers to the angle of the vehicle head of the target vehicle being raised or lowered. Since the pitch angle of the target vehicle will affect the coverage range of the laser beam of the laser radar in the surrounding environment, it will affect whether the laser beam of the laser radar will scan the pedestrian or which parts of the pedestrian can be scanned. Therefore, the pitch angle of the target vehicle can also be acquired.

[0108] Optionally, the pitch angle of the target vehicle can be measured by a chassis sensor of the target vehicle, and optionally, the chassis sensor can be an inertial measurement unit (IMU) of the target vehicle.

[0109] It is worth noting that before step 301, the following steps (1)-(3) can also be included.

[0110] (1) Acquire environmental information around the target vehicle.

[0111] The environment information around the target vehicle is used to indicate whether there is a pedestrian around the target vehicle. The environment information around the target vehicle can include information of at least one object in other vehicles, roads, pedestrians, bicycles, motorcycles, etc.

[0112] The operation of step (1) can be implemented in two possible ways.

[0113] In a first possible way, an environment image around the target vehicle is captured by a camera of the target vehicle, so as to obtain the environment information around the target vehicle. In this case, the environment information around the target vehicle is the environment image captured by the camera.

[0114] In a second possible way, a point cloud around the target vehicle is captured by a radar of the target vehicle, so as to obtain the environment information around the target vehicle. In this case, the environment information around the target vehicle is the point cloud captured by the radar. The radar of the target vehicle can be a laser radar, a millimeter wave radar, etc., which is not uniquely limited by the embodiments of the present application.

[0115] Of course, the environment information around the target vehicle can be obtained by any one of the above two ways, or can be obtained by combining the above two ways, which is not limited by the embodiments of the present application.

[0116] (2) Based on the environment information around the target vehicle, it is determined whether there is a pedestrian around the target vehicle.

[0117] In this case, based on the environment information around the target vehicle, it is determined whether there is a pedestrian around the target vehicle, that is, it is detected whether the environment information around the target vehicle includes information about pedestrians, which can include information about pedestrians walking upright, pedestrians riding bicycles, pedestrians riding motorcycles, etc. When the environment information around the target vehicle includes information about pedestrians walking upright and / or pedestrians riding bicycles and / or pedestrians riding motorcycles, it is determined that there is a pedestrian around the target vehicle.

[0118] Specifically, the operation of step (2) can be: performing target detection on the environment information around the target vehicle, in the case that the target detection result is that there is a pedestrian, it is determined that there is a pedestrian around the target vehicle; in the case that the target detection result is that there is no pedestrian, it is determined that there is no pedestrian around the target vehicle.

[0119] The operation of performing target detection on the environment information around the target vehicle can be: inputting the environment information around the target vehicle into a pedestrian detection model, performing pedestrian detection on the environment information by the pedestrian detection model, and outputting a target detection result.

[0120] When the environment information is acquired by the first possible way, the image captured by the camera of the target vehicle is input into the pedestrian detection model, so that the pedestrian detection model performs pedestrian detection on the image and outputs the target detection result.

[0121] When the environment information is acquired by the second possible way, the point cloud captured by the radar of the target vehicle is input into the pedestrian detection model, so that the pedestrian detection model performs pedestrian detection on the point cloud and outputs the target detection result.

[0122] It is worth noting that before the environment information around the target vehicle is input into the pedestrian detection model, the pedestrian detection model can also be trained by a computer device. The computer device is used to train the pedestrian detection model, and the computer device can be a desktop computer, a notebook computer, or a server.

[0123] Optionally, the computer device can acquire a plurality of first training samples, train the neural network model using the plurality of first training samples, and obtain the pedestrian detection model.

[0124] 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 environment sample information, which can include information of a pedestrian walking upright, a pedestrian riding a bicycle, a pedestrian riding a motorcycle, or can not include a pedestrian. The sample labels are detection results corresponding to the environment sample information. The input data in each of the plurality of training samples is the environment sample information, and the sample labels are the detection results corresponding to the environment sample information.

[0125] The neural network model can include a plurality of network layers, including an input layer, a plurality of hidden layers, and an output layer. The input layer is responsible for receiving input data; the output layer is responsible for outputting processed data; the plurality of hidden layers are located between the input layer and the output layer and are responsible for processing data. The plurality of hidden layers are invisible to the outside. For example, the neural network model can be a deep neural network model, and can be a convolutional neural network in a deep neural network.

[0126] 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 is the pedestrian detection model.

[0127] 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.

[0128] 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.

[0129] In this scenario, the pedestrian detection model uses pre-learned pedestrian features to detect the environmental information surrounding the target vehicle and determine whether pedestrian features are present. If the model outputs that a pedestrian exists, it means the model has identified pedestrian features in the environmental information, thus confirming the presence of a pedestrian around the target vehicle. Conversely, if the model outputs that no pedestrian exists, it means the model has not identified pedestrian features in the environmental information, thus confirming the absence of a pedestrian around the target vehicle. This method accurately determines whether a pedestrian is present around the target vehicle.

[0130] Optionally, it can be determined first whether there is a target road around the target vehicle; if there is a target road around the target vehicle, it can be determined whether there are pedestrians around the target vehicle.

[0131] The target road is a road where pedestrians may be present. Optionally, the target road can be a pedestrian crossing, a non-motorized vehicle lane, or other similar road.

[0132] In this case, by first determining whether there is a target road around the target vehicle, that is, first determining whether there is a road around the target vehicle where pedestrians are likely to exist, that is, determining whether there is a pedestrian crossing, a non-motor vehicle lane or the like around the target vehicle. If there is, then determine whether there are pedestrians around the target vehicle, thereby saving computing resources and improving the efficiency of determining whether there are pedestrians around the target vehicle.

[0133] In addition, in the case where there is a target road around the target vehicle, it is determined whether there are pedestrians around the target vehicle, so that subsequent control of the laser radar is performed only in the case where there are pedestrians on the target road. In this way, accurate control of the laser radar can be achieved.

[0134] Specifically, the operation of determining whether there is a target road around the target vehicle can be implemented in the following two possible ways.

[0135] The first possible way is to input the environment information into a road classification model after obtaining the environment information, classify the environment information through the road classification model, and output a classification result. In the case where the road type indicated by the classification result is the type of the target road, it is determined that there is a target road around the target vehicle. In the case where the road type indicated by the classification result is not the type of the target road, it is determined that there is no target road around the target vehicle.

[0136] It is worth noting that before inputting the environment information around the target vehicle into the road classification model, the road classification model can also be obtained by training the computer device.

[0137] Optionally, the computer device can obtain a plurality of second training samples, train the neural network model using the plurality of second training samples, and obtain the road classification model.

[0138] 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 environment sample information, and the sample labels are the road types corresponding to the environment sample information. The input data in each of the plurality of training samples is environment sample information, and the sample labels are the road types corresponding to the environment sample information.

[0139] The operation of training the road classification model based on the plurality of second training samples by the computer device is similar to the operation of obtaining the pedestrian detection model based on the plurality of first training samples by the computer device, which will not be described in detail.

[0140] In a second possible manner, the position information of the target vehicle is determined through a high-precision positioning algorithm; a high-precision map is acquired; the road information around the target vehicle is acquired from the high-precision map based on the position information of the target vehicle; in a case where the target road information is included in the road information, it is determined that the target road exists around the target vehicle; and in a case where the target road information is not included in the road information, it is determined that the target road does not exist around the target vehicle.

[0141] The target road information is information related to the target road. For example, for a pedestrian crossing, the target road information can be a zebra crossing.

[0142] Optionally, a GNSS (Global Navigation Satellite System) antenna can be installed on the target vehicle, which can receive a satellite positioning signal. In this case, the positioning calculation unit of the target vehicle can perform positioning calculation on the received satellite positioning signal, thereby obtaining the position information of the target vehicle. For example, the position information of the target vehicle can be obtained through positioning calculation of the T-BOX of the target vehicle based on the satellite positioning signal.

[0143] In the embodiments of the present application, the position information of the target vehicle is determined based on a high-precision positioning algorithm, which can improve the positioning accuracy of the target vehicle.

[0144] It should be noted that in the embodiments of the present application, the positioning calculation unit can perform positioning calculation through any positioning calculation algorithm, which is not uniquely limited in the embodiments of the present application. For example, the positioning calculation unit can perform positioning calculation through a DGNSS (Differential Global Navigation Satellite System) positioning algorithm.

[0145] The high-precision map is also called a high-resolution map, and the high-precision map contains road elements such as lane lines, road signs, traffic signs, traffic lights, zebra crossings, stop lines, non-motor vehicle lane signs, kerbs, guardrails, bridges, curves, and curves, and attribute information of road elements including the number of lanes, lane grouping, lane curvature, and slope, and road information including lane-level real-time traffic dynamic information.

[0146] In this way, the road information around the target vehicle can be accurately obtained from the high-precision map, that is, the relevant information about the road around the target vehicle can be accurately obtained.

[0147] In this case, when the target road information is included in the road information around the target vehicle obtained from the high-definition map, it is indicated that the target road element is included in the high-definition map at the position where the target vehicle is located, and it is determined that the target road exists around the target vehicle. For example, when the zebra crossing is included in the road information, it is determined that the pedestrian crossing exists around the target vehicle. When the target road information is not included in the road information around the target vehicle obtained from the high-definition map, it is indicated that the target road element is not included in the high-definition map at the position where the target vehicle is located, for example, when the zebra crossing, the non-motor vehicle lane sign and the like are not included in the road information, and it is determined that the target road does not exist around the target vehicle.

[0148] (3) In the case where the pedestrian exists around the target vehicle, it is determined whether the pedestrian is in the emission range of the laser radar.

[0149] Optionally, the operation of step (3) can be: in the case where the pedestrian exists around the target vehicle, obtaining the position of the pedestrian; determining the coverage area of the laser beam of the laser radar in the surrounding environment based on the position of the laser radar and the current field of view angle; in the case where the position of the pedestrian is included in the coverage area, determining that the pedestrian is in the emission range of the laser radar; and in the case where the position of the pedestrian is not included in the coverage area, determining that the pedestrian is not in the emission range of the laser radar.

[0150] The coverage area of the laser beam in the surrounding environment is the area formed by the positions scanned by the laser beam emitted by the laser radar with the current field of view angle in the surrounding environment.

[0151] In this case, in the case where the position of the pedestrian is included in the coverage area, it is indicated that the laser beam scans the position where the pedestrian is located in the surrounding environment, and it is said that the pedestrian is in the emission range of the laser radar, and at this time, the laser beam can cause damage to the pedestrian. In the case where the position of the pedestrian is not included in the coverage area, it is indicated that the laser beam does not scan the position where the pedestrian is located in the surrounding environment, and the laser beam does not cause damage to the eyes of the pedestrian.

[0152] The position of the pedestrian can be obtained by the sensor of the target vehicle, and the sensor of the target vehicle can be the laser radar, the millimeter wave radar, the ultrasonic radar, the camera and the like, which are not uniquely limited by the embodiments of the present application.

[0153] Optionally, in the case where it is determined in step (2) that the pedestrian does not exist around the target vehicle, or in the case where it is determined in this step that the pedestrian is not in the emission range of the laser radar, the laser radar can be controlled not to be adjusted.

[0154] In the case where it is determined that the pedestrian is in the emission range of the laser radar of the target vehicle, the above step 301 can be performed to obtain the pedestrian information of the pedestrian.

[0155] Specifically, the operation of step 301 can be: performing information separation on the environmental information around the target vehicle to obtain pedestrian information of the pedestrian.

[0156] The information separation is used to separate the information about the pedestrian from the environmental information.

[0157] The pedestrian information can include the height of the pedestrian, and can also include the state (still, walking, cycling, motorcycling, etc.) of the pedestrian, the distance between the pedestrian and the target vehicle, etc.

[0158] Optionally, the operation of performing information separation on the environmental information around the target vehicle to obtain pedestrian information of the pedestrian can be: separating the pedestrian from the environmental information around the target vehicle, and then identifying the separated pedestrian to obtain the pedestrian information of the pedestrian.

[0159] For example, the pedestrian can be separated from the environmental information around the target vehicle by a target segmentation algorithm, and then the separated pedestrian is identified to obtain the pedestrian information of the pedestrian.

[0160] Optionally, in the case that there is at least one pedestrian in the environment around the target vehicle, the pedestrian information can further include a pedestrian identifier for uniquely identifying the at least one pedestrian. For example, there are two pedestrians in the environment around the target vehicle, and the pedestrian identifier of the first pedestrian can be 1, and the pedestrian identifier of the second pedestrian can be 2.

[0161] Step 302: determining a maximum emission angle of a laser beam of the lidar based on the pedestrian information of the pedestrian and the pitch angle of the target vehicle, the maximum emission angle being an angle at which the laser beam of the lidar cannot scan the eyes of the pedestrian.

[0162] In this case, by determining the maximum emission angle of the laser beam of the lidar based on the pedestrian information of the pedestrian and the pitch angle of the target vehicle, and subsequently emitting the laser beam of the lidar at the maximum emission angle, the laser beam can not scan the eyes of the pedestrian, thereby avoiding damage to the eyes of the pedestrian.

[0163] Optionally, in the case that the pedestrian is not in the emission range of the lidar of the target vehicle, the motion direction of the pedestrian, the current position of the pedestrian, and the motion speed of the pedestrian can also be obtained; based on the motion direction of the pedestrian, the current position of the pedestrian, and the motion speed of the pedestrian, it is determined whether the pedestrian will be in the emission range of the lidar after a preset time; in the case that the pedestrian is in the emission range of the lidar after the preset time, the pedestrian information of the pedestrian and the pitch angle of the target vehicle are obtained, and based on the pedestrian information of the pedestrian and the pitch angle of the target vehicle, the maximum emission angle of the laser beam of the lidar is determined.

[0164] The movement direction of the pedestrian is used to indicate whether the pedestrian is moving close to or away from the target vehicle.

[0165] The preset time length can be set in advance, and the preset time length can be set by a technician according to actual needs. For example, the preset time length can be set to 10 seconds.

[0166] In this case, it can be determined whether the pedestrian will be in the emission range of the laser radar after the preset time length. If the pedestrian will be in the emission range of the laser radar after the preset time length, it means that the eyes of the pedestrian can be damaged by the laser beam of the laser radar, and then steps 301-302 can be performed to determine the maximum emission angle of the laser beam of the laser radar. If the pedestrian will not be in the emission range of the laser radar after the preset time length, it means that the eyes of the pedestrian will not be damaged by the laser beam emitted by the laser radar, and the laser radar can be controlled not to operate.

[0167] Optionally, the operation of obtaining the movement direction and the movement speed of the pedestrian can be: capturing multiple images of the pedestrian in the surrounding environment through the camera of the target vehicle, performing optical flow calculation based on the multiple images to obtain the movement direction and the movement speed of the pedestrian.

[0168] Specifically, the operation of performing optical flow calculation based on the multiple images to obtain the movement direction and the movement speed of the pedestrian can be: inputting the multiple images into an optical flow estimation model, performing optical flow estimation on the multiple images through the optical flow estimation model, and outputting an optical flow map; obtaining the movement direction of the pedestrian from the optical flow map and determining the movement distance of the pedestrian based on the optical flow map, the movement distance being the movement distance of the pedestrian within the photographing time of the multiple images; determining the movement speed of the pedestrian based on the photographing time of the multiple images and the movement distance of the pedestrian within the photographing time.

[0169] Since the optical flow map can indicate the direction in the movement process of the pedestrian and the displacement of the pedestrian in the multiple images, the optical flow map is obtained through the optical flow estimation model, so that the movement direction of the pedestrian and the displacement of the pedestrian in the multiple images can be directly obtained from the optical flow map. The movement distance of the pedestrian within the photographing time can be determined based on the displacement of the pedestrian, and then the movement speed of the pedestrian can be obtained. In this way, the efficiency of obtaining the movement direction and the movement speed of the pedestrian can be improved, and more accurate movement direction and movement speed can be obtained.

[0170] The operation of determining whether a pedestrian will be within the LiDAR's emission range after a preset time period, based on the pedestrian's movement direction, current position, and speed, can be as follows: multiply the pedestrian's speed by the preset time period to obtain the distance the pedestrian travels during the preset time period; determine the pedestrian's position after the preset time period based on the pedestrian's movement direction, current position, and distance traveled during the preset time period; if the coverage area includes the pedestrian's position after the preset time period, determine that the pedestrian will be within the LiDAR's emission range after the preset time period; if the coverage area does not include the pedestrian's position after the preset time period, determine that the pedestrian will not be within the LiDAR's emission range after the preset time period.

[0171] In this scenario, the first step is to determine the distance the pedestrian might travel within a preset time period. Then, based on the pedestrian's direction of movement and using their current location as a starting point, the system determines the pedestrian's likely location after the preset time period. Subsequently, it assesses whether the laser beam's coverage area in the surrounding environment includes the pedestrian's location after the preset time period, thus accurately determining whether the pedestrian is within the lidar's emission range after that time period.

[0172] Optionally, before step 302, it can be determined whether the target vehicle is on flat ground or a slope based on the pitch angle of the target vehicle.

[0173] Specifically, if the pitch angle of the target vehicle is less than or equal to a preset angle threshold, the target vehicle is determined to be on flat ground; if the pitch angle of the target vehicle is greater than the preset angle threshold, the target vehicle is determined to be on a slope.

[0174] The preset angle threshold is used to define the critical angle between flat ground and a slope. The preset angle threshold can be set in advance, and can also be set by technicians according to actual needs.

[0175] In this scenario, if the target vehicle's pitch angle is less than or equal to a preset angle threshold, it indicates that the target vehicle's pitch angle is less than the critical angle between flat ground and a slope, meaning the target vehicle's pitch angle has not reached the angle range of a slope, and therefore the target vehicle can be determined to be on flat ground. If the target vehicle's pitch angle is greater than the preset angle threshold, it indicates that the target vehicle's pitch angle is greater than the critical angle between flat ground and a slope, meaning the target vehicle's pitch angle has reached the angle range of a slope, and therefore the target vehicle can be determined to be on a slope.

[0176] For example, if the preset angle threshold is 5° and the target vehicle's pitch angle is 10°, and the target vehicle's pitch angle (10°) is greater than the preset angle threshold (5°), it means that the target vehicle's pitch angle has reached the angle range of the ramp, and therefore it can be determined that the target vehicle is on the ramp.

[0177] Furthermore, when the target vehicle is on flat ground, step 302 can be performed as follows: determine the height of the target point based on the height of the pedestrian; determine the maximum launch angle using the tangent function based on the height of the target point and the distance between the pedestrian and the target vehicle.

[0178] The target point can be any point below the eyes of the pedestrian's body. Optionally, the target point can be two-thirds of the pedestrian's height. Since two-thirds of the height is below the head, setting the target point to two-thirds of the pedestrian's height ensures that the laser beam will not enter the person's eyes when the lidar emits the laser beam at the maximum emission angle.

[0179] For example, Figure 4 This is a schematic diagram for determining the maximum launch angle. See also... Figure 4 , Figure 4 The diagram includes points A, B, and C. Point A represents the location of the target vehicle, point B represents the location of the pedestrian, and point C represents the target point on the pedestrian, located at two-thirds of the pedestrian's height. The lidar's laser beam is emitted from point A into the surrounding environment.

[0180] Figure 4 In the diagram, points A, B, and C form a right triangle, where side AB is the distance between the target vehicle and the pedestrian, and side CB is the height of the target point, which is two-thirds of the pedestrian's height.

[0181] To prevent the laser beam from entering the human eye, the laser light at the outer edge of the beam must not reach the pedestrian's eyes. 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 lengths AC and AB, thus ensuring that the pedestrian's eyes are not damaged.

[0182] The operation of determining the maximum launch angle based on the height of the target point and the distance between the pedestrian and the target vehicle using the tangent function can be achieved by the following formula (1).

[0183]

[0184] from Figure 4 As can be seen, when the maximum emission angle is β, the laser beam emitted by the lidar will reach the target point without entering the pedestrian's eyes. This protects the pedestrian's eyes.

[0185] For example, if the pedestrian's height is 1.5 meters and the distance between the pedestrian and the target vehicle is 2 meters, then the height of the target point can be determined first. The maximum launch angle can then be determined using the formula (1) above:

[0186]

[0187] The tangent value of the maximum emission angle is 0.5, and the maximum emission angle is about 26.56°.

[0188] It is worth noting that in the case that at least one pedestrian around the target vehicle is in the emission range of the laser radar, the operation of step 302 can be: obtaining the height of the target pedestrian and the target distance from the pedestrian information of the at least one pedestrian; determining the height of the target point based on the height of the target pedestrian; determining the maximum emission angle based on the height of the target point and the target distance through the tangent function.

[0189] The height of the target pedestrian is the lowest height in the heights of the at least one pedestrian, and the target pedestrian is the pedestrian with the lowest height in the at least one pedestrian. The target distance is the distance between the target pedestrian and the target vehicle.

[0190] In this case, by obtaining the lowest height in the heights of the at least one pedestrian, and then determining the height of the target point and the maximum emission angle based on this, the laser radar can be prevented from emitting laser beams at the maximum emission angle into the eyes of each of the at least one pedestrian, thereby ensuring that the eyes of each of the at least one pedestrian can be protected.

[0191] In the case that the target vehicle is on a slope, the operation of step 302 can be: determining the pitch angle of the target vehicle as the slope of the slope, and determining the angle between the pedestrian and the slope based on the slope; determining the distance between the target vehicle and the target point through the cosine law based on the height of the pedestrian, the distance between the pedestrian and the target vehicle, and the angle between the pedestrian and the slope; determining the maximum emission angle through the cosine law based on the height of the pedestrian, the distance between the pedestrian and the target vehicle, and the distance between the target vehicle and the target point.

[0192] Since the target vehicle is parallel to the slope during the process of the target vehicle driving on the slope, the pitch angle of the target vehicle is also the slope of the slope. Therefore, the pitch angle of the target vehicle can be determined as the slope of the slope.

[0193] The operation of determining the angle between the pedestrian and the slope based on the slope of the slope can be: in the case that the slope is an uphill, adding 90° to the slope of the slope to obtain the angle between the pedestrian and the slope; in the case that the slope is a downhill, subtracting the slope of the slope from 90° to obtain the angle between the pedestrian and the slope.

[0194] The operation of determining the maximum emission angle when the target vehicle is on the slope is described below.

[0195] For example, Figure 5 is a schematic diagram for determining the maximum emission angle when the slope is uphill. Referring to Figure 5 , Figure 5 A point, B point, and C point are included in the figure. The A point is used to represent the position of the target vehicle, the B point is used to represent the position of the pedestrian, and the C point is used to represent the target point, wherein the C point is at two-thirds of the height of the pedestrian. Among them, the laser beam of the lidar is emitted from the A point to the surrounding environment.

[0196] Figure 5 In the figure, the A point, the B point, and the C point form an obtuse triangle, wherein the length of side AB is the distance between the target vehicle and the pedestrian, and the length of side CB is the height of the target point, that is, two-thirds of the height of the pedestrian. The angle α between the length of side AB and the length of side CB is the angle between the pedestrian and the slope.

[0197] Since the laser beam cannot enter the human eye, the laser on the outer edge of the laser beam cannot reach the human eye, and in this example, the laser on the outer edge of the laser beam can reach the target point at most. This is to make the emission angle of the laser beam be emitted at an angle β between the length of side AC and the length of side AB, which can ensure that the eyes of the pedestrian are not damaged.

[0198] Alternatively, the operation of determining the distance between the target vehicle and the target point based on the height of the pedestrian, the distance between the pedestrian and the target vehicle, and the angle between the pedestrian and the slope can be achieved by the following formula (2) through the cosine theorem.

[0199] AC 2 = AB 2 + BC 2 - 2 × AB × BC × cos α (2)

[0200] Among them, AC is the distance between the target vehicle and the target point, that is, the distance from the laser on the outer edge of the laser beam to the target point from the lidar.

[0201] Then, the operation of determining the maximum emission angle based on the height of the pedestrian, the distance between the pedestrian and the target vehicle, and the distance between the target vehicle and the target point can be achieved by the following formula (3) through the cosine theorem.

[0202]

[0203] Among them, β is the maximum emission angle, and Figure 5 As can be seen from the figure, when the lidar emits the laser beam at the maximum emission angle, the laser beam will not enter the eyes of the pedestrian. In this way, the eyes of the pedestrian are protected.

[0204] For example, the height of the pedestrian is 1.5 m, the distance between the pedestrian and the target vehicle is 2 m, and the slope of the slope is 30°. The angle a between the pedestrian and the slope is 120°. The distance between the target vehicle and the target point can be obtained by the above formula (2) as follows:

[0205]

[0206] The distance between the target vehicle and the target point is 2.64 m. Then, the maximum emission angle can be obtained by the above formula (3) as follows:

[0207]

[0208] The cosine value of the maximum emission angle is 0.944091, and the maximum emission angle is about 19.25°.

[0209] For another example, Figure 6 is a schematic diagram for determining the maximum emission angle when the slope is a downhill. Referring to Figure 6 , Figure 6 includes A point, B point and C point. The A point is used to represent the position of the target vehicle, the B point is used to represent the position of the pedestrian, and the C point is used to represent the target point, wherein the C point is at two-thirds of the height of the pedestrian. The laser beam of the lidar is emitted from the A point to the surrounding environment.

[0210] Figure 6 In the A point, B point and C point form an acute triangle, wherein the length of the side AB is the distance between the target vehicle and the pedestrian, the length of the side CB is the height of the target point, i.e. two-thirds of the height of the pedestrian. The angle a between the length of the side AB and the length of the side CB is the angle between the pedestrian and the slope.

[0211] For example, the height of the pedestrian is 1.5 m, the distance between the pedestrian and the target vehicle is 2 m, and the slope of the slope is 30°. The angle a between the pedestrian and the slope is 60°. The distance between the target vehicle and the target point can be obtained by the above formula (2) as follows:

[0212]

[0213] The distance between the target vehicle and the target point is 1.73 m. Then, the maximum emission angle can be obtained by the above formula (3) as follows:

[0214]

[0215] The cosine value of the maximum emission angle is 0.866026, and the maximum emission angle is about 29.9°.

[0216] In this way, when the laser radar emits the laser beam at the maximum emission angle, the laser beam will not enter the eyes of the pedestrian. In this way, the eyes of the pedestrian are protected.

[0217] It is worth noting that in the case that at least one pedestrian around the target vehicle is in the emission range of the laser radar, the operation of step 302 can be: obtaining the height of the target pedestrian and the target distance from the pedestrian information of the at least one pedestrian; determining the pitch angle of the target vehicle as the slope of the slope, and determining the angle between the pedestrian and the slope based on the slope; determining the distance between the target vehicle and the target point by the cosine law based on the height of the target pedestrian, the target distance, and the angle between the pedestrian and the slope; determining the maximum emission angle by the cosine law based on the height of the target pedestrian, the target distance, and the distance between the target vehicle and the target point.

[0218] Since the height of the target pedestrian is the lowest height in the heights of the at least one pedestrian, the target pedestrian is the pedestrian with the lowest height among the at least one pedestrian. The target distance is the distance between the target pedestrian and the target vehicle.

[0219] In this case, by obtaining the lowest height in the heights of the at least one pedestrian, and then determining the maximum emission angle based on the height of the target pedestrian, the target distance, and the angle between the target pedestrian and the slope, the laser beam emitted by the laser radar will not enter the eyes of each pedestrian in the at least one pedestrian, thereby ensuring that the eyes of each pedestrian in the at least one pedestrian are protected.

[0220] Step 303: based on the maximum emission angle, controlling the laser radar to adjust the vertical field of view angle of the laser beam.

[0221] The vertical field of view angle of the laser beam is used to constrain the height of the laser beam emitted by the laser radar, thereby controlling the laser radar to adjust the vertical field of view angle of the laser beam, that is, controlling the laser radar to constrain the emission height of the laser beam, so that the laser beam will not scan the eyes of the pedestrian.

[0222] Since the maximum emission angle is an angle at which the laser beam of the laser radar cannot scan the eyes of the pedestrian, and in the case that the laser beam is emitted at a higher level, the eyes of the pedestrian will not be scanned, therefore, based on the maximum emission angle, the laser radar is controlled to adjust the vertical field of view angle of the laser beam, so that the laser beam emitted by the laser radar will not enter the eyes of the pedestrian, thereby avoiding the laser beam from causing damage to the eyes of the pedestrian, and protecting the eyes of the pedestrian.

[0223] Optionally, the operation of step 303 can be implemented in the following two possible ways.

[0224] In a first possible manner, the laser radar is controlled to adjust the vertical field of view angle of the laser beam to a maximum emission angle.

[0225] In this case, the laser radar is controlled to adjust the vertical field of view angle to the maximum emission angle, which can ensure that the eyes of the pedestrian will not be scanned in the case that the laser beam emitted by the laser radar is relatively high, so that the laser radar can normally acquire the surrounding environment information of the target vehicle, and thus the working performance of the laser radar is ensured not to be reduced.

[0226] Optionally, when the maximum emission angle is determined, a first control message can be sent to the laser radar, and the maximum emission angle is carried in the first control message. After the laser radar receives the first control message, the vertical field of view angle can be adjusted to the maximum emission angle.

[0227] For example, the maximum emission angle is 30 degrees, and the first control message can be sent to the laser radar, and the maximum emission angle (30 degrees) is carried in the first control message, so that the laser radar can adjust the vertical field of view angle to 30 degrees when receiving the first control message.

[0228] In a second possible manner, the laser radar is controlled to adjust the vertical field of view angle of the laser beam to a target angle.

[0229] The target angle is less than the maximum emission angle.

[0230] Since the maximum emission angle is an angle that will not scan the eyes of the pedestrian, the laser radar is controlled to adjust the vertical field of view angle of the laser beam to the maximum emission angle, which can ensure that the laser beam will not scan the eyes of the pedestrian. In this case, the laser radar is controlled to adjust the vertical field of view angle of the laser beam to an angle less than the maximum emission angle, which can also ensure that the laser beam will not scan the eyes of the pedestrian.

[0231] Optionally, after the maximum emission angle is determined, the target angle can be determined based on the maximum emission angle, and then a second control message can be sent to the laser radar, and the target angle can be carried in the second control message. After the laser radar receives the second control message, the vertical field of view angle can be adjusted to the target angle.

[0232] It is worth noting that the laser radar can adjust the vertical field of view angle of the laser beam by adjusting the angle of the scanning mirror.

[0233] For example, Figure 7 is a schematic diagram of a scanning mirror of a laser radar, referring to Figure 7 , Figure 7 The scanning mirror 701 is included in the laser radar. In the laser radar, the laser emitted by the laser reaches the scanning mirror, and by adjusting the angle of the scanning mirror, the coverage range of the emitted laser beam in the surrounding environment is different.

[0234] Therefore, after the laser radar receives the first control message or the second control message, the vertical field of view can be adjusted by adjusting the up-down angle of the scanning mirror, so that the laser beam is emitted at the maximum emission angle or at the target angle, so that the laser beam will not scan the eyes of the pedestrian.

[0235] More notably, during the driving of the target vehicle, the distance between the target vehicle and the pedestrian can change, which will affect the maximum emission angle of the laser beam. Therefore, during the driving of the target vehicle, the pedestrian information of the pedestrian can be acquired in real time, so that the maximum emission angle can be determined in real time according to the real-time acquired pedestrian information and the pitch angle of the target vehicle, and the vertical field of view of the laser beam of the laser radar can be controlled in real time to adjust the vertical field of view of the laser beam, so as to ensure that the laser beam emitted by the laser radar will not enter the eyes of the pedestrian during the driving of the vehicle.

[0236] For ease of understanding, the embodiments of the present application will be described below in combination with Figure 8 The laser radar control method provided by the embodiments of the present application is exemplarily described. Referring to Figure 8 , Figure 8 The method comprises the following steps 801-807.

[0237] Step 801: acquiring environment information around a target vehicle.

[0238] Step 802: judging whether there is a pedestrian around the target vehicle based on the environment information.

[0239] Step 803: in the case that there is a pedestrian around the target vehicle, determining whether the pedestrian is in the emission range of the laser radar of the target vehicle.

[0240] Step 804: in the case that the pedestrian is in the emission range of the laser radar of the target vehicle, acquiring pedestrian information of the pedestrian and a pitch angle of the target vehicle.

[0241] Step 805: determining whether the target vehicle is on a flat ground or on a slope based on the pitch angle of the target vehicle.

[0242] Step 806: in the case that the target vehicle is on the flat ground, determining the maximum emission angle based on the pedestrian information of the pedestrian, and in the case that the target vehicle is on the slope, determining the maximum emission angle based on the pedestrian information of the pedestrian and the pitch angle of the target vehicle.

[0243] Step 807: controlling the laser radar to adjust the vertical field of view of the laser beam to the maximum emission angle or a target angle, the target angle being an angle smaller than the maximum emission angle.

[0244] In the embodiment of the present application, the controller acquires the pedestrian information of the pedestrian and the pitch angle of the target vehicle in the case that the pedestrian is in the emission range of the laser radar of the target vehicle, that is, acquires the pedestrian information of the pedestrian and the pitch angle of the target vehicle in the case that the laser radar of the target vehicle is very likely to shoot into the eyes of the pedestrian. Then, the maximum emission angle of the laser beam of the laser radar is determined based on the pedestrian information of the pedestrian and the pitch angle of the target vehicle, and the laser beam emitted by the laser radar at the maximum emission angle will not scan the eyes of the pedestrian. Therefore, the vertical field angle of the laser beam of the laser radar is controlled to be adjusted based on the maximum emission angle, so that the emitted laser beam will not shoot into the eyes of the pedestrian. In this way, it is ensured that the laser beam emitted by the laser radar will not cause damage to the eyes of the pedestrian, and the eyes of the pedestrian are protected.

[0245] Figure 9 FIG. 1 is a structural schematic diagram of a laser radar control device provided by an embodiment of the present application. The laser radar control device can be realized by software, hardware or a combination of both to become part or all of a vehicle, which can be a vehicle shown in the following Figure 10 Figure 9 The device includes a first acquisition module 901, a first determination module 902 and a control module 903.

[0246] The first acquisition module 901 is configured to acquire pedestrian information of a pedestrian and a pitch angle of a target vehicle in the case that the pedestrian is in the emission range of the laser radar of the target vehicle.

[0247] The first determination module 902 is configured to determine a maximum emission angle of a laser beam of the laser radar based on the pedestrian information of the pedestrian and the pitch angle of the target vehicle, the maximum emission angle being an angle at which the laser beam of the laser radar cannot scan the eyes of the pedestrian.

[0248] The control module 903 is configured to control the laser radar to adjust the vertical field angle of the laser beam based on the maximum emission angle.

[0249] Optionally, the device further includes:

[0250] The second determination module is configured to determine that the target vehicle is on flat ground in the case that the pitch angle of the target vehicle is less than or equal to a preset angle threshold.

[0251] Optionally, the pedestrian information includes the height of the pedestrian and the distance between the pedestrian and the target vehicle, and the first determination module 902 is configured to:

[0252] In the case that the target vehicle is on flat ground, determine the height of the target point based on the height of the pedestrian, the target point being any one point below the eye part of the body part of the pedestrian.

[0253] ​The maximum emission angle is determined by a tangent function based on the height of the target point, and the distance between the pedestrian and the target vehicle.

[0254] Optionally, the apparatus further comprises:

[0255] The third determination module is configured to determine that the target vehicle is on a slope if the pitch angle of the target vehicle is greater than a preset angle threshold.

[0256] Optionally, the pedestrian information comprises the height of the pedestrian, the distance between the pedestrian and the target vehicle, and the first determination module 902 is configured to:

[0257] In the case that the target vehicle is on a slope, the pitch angle is determined as the slope of the slope, and the angle between the pedestrian and the slope is determined based on the slope.

[0258] The distance between the target vehicle and the target point is determined by the cosine theorem based on the height of the pedestrian, the distance between the pedestrian and the target vehicle, and the angle between the pedestrian and the slope, the target point being any one point below the eye part of the body part of the pedestrian.

[0259] The maximum emission angle is determined by the cosine theorem based on the height of the pedestrian, the distance between the pedestrian and the target vehicle, and the distance between the target vehicle and the target point.

[0260] Optionally, the apparatus further comprises:

[0261] The second acquisition module is configured to acquire the motion direction of the pedestrian, the current position and the motion speed of the pedestrian if the pedestrian is not in the emission range of the laser radar of the target vehicle.

[0262] The fourth determination module is configured to determine whether the pedestrian is in the emission range of the laser radar after a preset time period based on the motion direction of the pedestrian, the current position and the motion speed of the pedestrian.

[0263] The execution module is configured to acquire the pedestrian information of the pedestrian and the pitch angle of the target vehicle and determine the maximum emission angle of the laser beam of the laser radar based on the pedestrian information of the pedestrian and the pitch angle of the target vehicle if the pedestrian is in the emission range of the laser radar after the preset time period.

[0264] Optionally, the apparatus further comprises:

[0265] The third acquisition module is configured to acquire the environmental information around the target vehicle.

[0266] The fifth determination module is configured to determine whether there is a pedestrian around the target vehicle based on the environmental information.

[0267] The sixth determination module is configured to determine whether the pedestrian is in the emission range of the laser radar if there is a pedestrian around the target vehicle.

[0268] Optionally, the apparatus further comprises:

[0269] a seventh determining module configured to determine whether there is a target road around the target vehicle, the target road comprising at least one of a pedestrian crossing and a non-motor vehicle lane;

[0270] an eighth determining module configured to, in a case where there is a target road around the target vehicle, determine whether there is a pedestrian around the target vehicle.

[0271] Optionally, the sixth determining module is configured to:

[0272] in a case where there is a pedestrian around the target vehicle, acquire a position of the pedestrian;

[0273] determine a coverage area of the laser beam of the lidar in the surrounding environment based on the position of the lidar and a current field of view angle of the lidar;

[0274] in a case where the position of the pedestrian is included in the coverage area, determine that the pedestrian is in a transmission range of the lidar;

[0275] in a case where the position of the pedestrian is not included in the coverage area, determine that the pedestrian is not in the transmission range of the lidar.

[0276] Optionally, the control module 903 is configured to:

[0277] control the lidar to adjust the vertical field of view angle of the laser beam to a maximum transmission angle; or

[0278] control the lidar to adjust the vertical field of view angle of the laser beam to a target angle, the target angle being smaller than the maximum transmission angle.

[0279] In the embodiments of the present application, in a case where the pedestrian is in the transmission range of the lidar of the target vehicle, the pedestrian information of the pedestrian and the pitch angle of the target vehicle are acquired, that is, in a case where the lidar of the target vehicle is very likely to shoot into the eyes of the pedestrian, the pedestrian information of the pedestrian and the pitch angle of the target vehicle are acquired. Then, the maximum transmission angle of the laser beam of the lidar is determined based on the pedestrian information of the pedestrian and the pitch angle of the target vehicle, and the laser beam emitted by the lidar at the maximum transmission angle will not scan the eyes of the pedestrian. Therefore, the vertical field of view angle of the laser beam is controlled by the lidar based on the maximum transmission angle, so that the emitted laser beam will not shoot into the eyes of the pedestrian. In this way, it is ensured that the laser beam emitted by the lidar will not cause damage to the eyes of the pedestrian, and the eyes of the pedestrian are protected.

[0280] It should be noted that the above embodiment provides a laser radar control device, when the laser radar is controlled, only the above-mentioned division of each functional module is exemplified, and in actual application, the above-mentioned function distribution can be completed by different functional modules according to the needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above.

[0281] Each functional unit and module in the above embodiment can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for mutual distinction, and do not limit the protection scope of the embodiments of the present application.

[0282] The laser radar control device and method provided in the above embodiment belong to the same concept, and the specific working process of the unit and module in the above embodiment and the resulting technical effects can be referred to in the method embodiment part, which will not be repeated here.

[0283] Figure 10 It is a structure schematic diagram of a vehicle provided by the embodiments of the present application.

[0284] For example, as shown in the figure, Figure 10 The vehicle includes a memory 101 and a processor 100, wherein the memory 101 stores executable program code 102, and the processor 100 is configured to call and execute the executable program code 102 to execute the above-mentioned laser radar control method.

[0285] The embodiment can divide the functional modules of the vehicle according to the above-mentioned method example, for example, each functional module can be divided, or two or more functions can be integrated in one processing module, and the integrated module can be realized in the form of hardware. It should be noted that the division of the modules in the embodiment is illustrative, and is only a logical function division. In actual implementation, there can be another division method.

[0286] In the case of dividing each functional module according to each function, the vehicle can include a first acquisition module, a first determination module, and a control module. It should be noted that all related contents of each step involved in the above-mentioned method embodiment can be cited in the function description of the corresponding functional module, which will not be repeated here.

[0287] The vehicle provided by the embodiment is used to execute the above-mentioned laser radar control method, so as to achieve the same effect as the above-mentioned implementation method.

[0288] In the case of employing the integrated unit, the vehicle can include a processing module, a storage module. The processing module can be used to control and manage the actions of the vehicle. The storage module can be used to support the vehicle to execute mutual program codes and data, etc.

[0289] The processing module can be a processor or a controller, which can realize or execute various exemplary logical blocks, modules and circuits in combination with the disclosure of the present application. The processor can also be a combination of computing functions, such as including one or more microprocessor combinations, digital signal processing (DSP) and microprocessor combinations, etc. The storage module can be a memory.

[0290] The embodiment also provides a computer readable storage medium, which stores computer program codes, when the computer program codes are run on a computer, the computer executes the above related method steps to realize the above method of laser radar control in the above embodiment.

[0291] The embodiment also provides a computer program product, when the computer program product is run on a computer, the computer executes the above related steps to realize the above method of laser radar control in the above embodiment.

[0292] The vehicle, computer readable storage medium, computer program product or chip provided by the embodiment are used to execute the corresponding method provided above, so the beneficial effects achieved thereby can refer to the beneficial effects of the corresponding method provided above, which will not be described here.

[0293] Through the description of the above embodiments, those skilled in the art can understand that, for the convenience and brevity of description, only the above division of functional modules is taken as an example, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above.

[0294] In the 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 modules or units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another device, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed mutual units can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0295] The above merely provides the specific implementation of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of the changes or replacements within the technical range disclosed by the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A lidar control method, characterized by, The method comprises: acquiring environment information around a target vehicle; determining whether a target road exists around the target vehicle, the target road comprising at least one of a pedestrian crossing and a non-motor vehicle lane; in a case where the target road exists around the target vehicle, determining, based on the environment information, whether a pedestrian exists around the target vehicle; in a case where the pedestrian exists around the target vehicle, determining whether the pedestrian is within a transmission range of a laser radar of the target vehicle; in a case where the pedestrian is within the transmission range of the laser radar of the target vehicle, acquiring pedestrian information of the pedestrian and a pitch angle of the target vehicle; based on the pedestrian information of the pedestrian and the pitch angle of the target vehicle, determining a maximum transmission angle of a laser beam of the laser radar, the maximum transmission angle being an angle at which the laser beam of the laser radar cannot scan an eye of the pedestrian; based on the maximum transmission angle, controlling the laser radar to adjust a vertical field of view angle of the laser beam, the vertical field of view angle being used to constrain a height at which the laser radar transmits the laser beam; the determining, based on the pedestrian information of the pedestrian and the pitch angle of the target vehicle, of the maximum transmission angle of the laser beam of the laser radar comprises: in a case where the target vehicle is on flat ground, determining a height of a target point based on a height of the pedestrian, the target point being at two-thirds of the height of the pedestrian; based on the height of the target point and a distance between the pedestrian and the target vehicle, determining the maximum transmission angle by a tangent function.

2. The method of claim 1, wherein, before the determining, based on the pedestrian information of the pedestrian and the pitch angle of the target vehicle, of the maximum transmission angle of the laser beam of the laser radar, the method further comprises: in a case where the pitch angle of the target vehicle is less than or equal to a preset angle threshold, determining that the target vehicle is on flat ground.

3. The method of claim 1, wherein, before the determining, based on the pedestrian information of the pedestrian and the pitch angle of the target vehicle, of the maximum transmission angle of the laser beam of the laser radar, the method further comprises: in a case where the pitch angle of the target vehicle is greater than a preset angle threshold, determining that the target vehicle is on a slope; the pedestrian information comprises the height of the pedestrian, the distance between the pedestrian and the target vehicle, and the determining, based on the pedestrian information of the pedestrian and the pitch angle of the target vehicle, of the maximum transmission angle of the laser beam of the laser radar comprises: in a case where the target vehicle is on a slope, determining the pitch angle as a slope of the slope, and determining, based on the slope, an angle between the pedestrian and the slope; based on the height of the pedestrian, the distance between the pedestrian and the target vehicle, and the angle between the pedestrian and the slope, determining a distance between the target vehicle and a target point by a cosine theorem, the target point being any one point below an eye part of the pedestrian among body parts of the pedestrian; based on the height of the pedestrian, the distance between the pedestrian and the target vehicle, and the distance between the target vehicle and the target point, determining the maximum transmission angle by the cosine theorem.

4. The method of claim 1, wherein, Before the determining the emitting angle of the laser beam of the lidar based on the pedestrian information of the pedestrian, the method further comprises: In a case that the pedestrian is not in the emitting range of the lidar of the target vehicle, obtaining the moving direction of the pedestrian, the current position of the pedestrian and the moving speed of the pedestrian; Determining whether the pedestrian is in the emitting range of the lidar after a preset time length based on the moving direction of the pedestrian, the current position of the pedestrian and the moving speed of the pedestrian; In a case that the pedestrian is in the emitting range of the lidar after the preset time length, obtaining the pedestrian information of the pedestrian and the pitch angle of the target vehicle and determining the maximum emitting angle of the laser beam of the lidar based on the pedestrian information of the pedestrian and the pitch angle of the target vehicle.

5. The method of claim 1, wherein, The determining whether the pedestrian is in the emitting range of the lidar in a case that there is a pedestrian around the target vehicle comprises: In a case that there is a pedestrian around the target vehicle, obtaining the position of the pedestrian; Determining the coverage area of the laser beam of the lidar in the surrounding environment based on the position of the lidar and the current field of view angle of the lidar; In a case that the position of the pedestrian is contained in the coverage area, determining that the pedestrian is in the emitting range of the lidar; In a case that the position of the pedestrian is not contained in the coverage area, determining that the pedestrian is not in the emitting range of the lidar.

6. The method of claim 1, wherein, The controlling the lidar to adjust the vertical field of view angle of the laser beam based on the maximum emitting angle comprises any one of the following: Controlling the lidar to adjust the vertical field of view angle of the laser beam to the maximum emitting angle; Controlling the lidar to adjust the vertical field of view angle of the laser beam to a target angle, the target angle being smaller than the maximum emitting angle.

7. A lidar control device, characterized by, The apparatus comprises: a third obtaining module configured to obtain environment information around a target vehicle; a seventh determining module configured to determine whether there is a target road around the target vehicle, the target road comprising at least one of a pedestrian crossing and a non-motor vehicle lane; an eighth determining module configured to, in a case that there is the target road around the target vehicle, determine whether there is a pedestrian around the target vehicle based on the environment information; a sixth determining module configured to, in a case that there is a pedestrian around the target vehicle, determine whether the pedestrian is in the emitting range of the lidar; a first obtaining module configured to, in a case that a pedestrian is in the emitting range of the lidar of the target vehicle, obtain pedestrian information of the pedestrian and a pitch angle of the target vehicle; a first determining module configured to determine a maximum emitting angle of a laser beam of the lidar based on the pedestrian information of the pedestrian and the pitch angle of the target vehicle, the maximum emitting angle being an angle at which the laser beam of the lidar cannot scan an eye of the pedestrian; a control module configured to control the lidar to adjust a vertical field of view angle of the laser beam based on the maximum emitting angle, the vertical field of view angle being used to constrain the height of the laser beam emitted by the lidar; The first determining module is specifically used for determining the height of a target point, which is two-thirds of the height of the pedestrian, based on the height of the pedestrian when the target vehicle is on flat ground. The maximum emission angle is determined by a tangent function based on the height of the target point and the distance between the pedestrian and the target vehicle.

8. A vehicle characterized by comprising: The vehicle comprises: a memory for storing executable program code; a processor for calling and running the executable program code from the memory, so that the vehicle executes the method according to any one of claims 1 to 6.

Images