A laser radar control method, device, equipment and medium

Abstract

The present invention provides a control method, device, equipment and medium of a laser radar, and relates to the technical field of laser radar. The method inputs environmental information of a target laser radar into a preset neural network model to obtain a target atmospheric particle concentration, inputs the target atmospheric particle concentration into a target neural network model to obtain an estimated laser propagation distance corresponding to a target laser emitter in the target laser radar, further obtains a key weight corresponding to the target laser emitter, obtains a laser propagation distance corresponding to the target laser radar according to the estimated laser propagation distance and the key weight, and adjusts the working parameters of the target laser radar based on the laser propagation distance to control the target laser radar. It can be seen that the present invention controls the target laser radar based on the laser propagation distance, does not need to set a laser radar working mapping table, can enhance the effect of reducing the influence of atmospheric particles on the target laser radar, and is beneficial to improving the measurement accuracy of the target laser radar.

Description

Technical Field

[0001] The present invention relates to the field of laser radar technology, and in particular to a control method, device, equipment and medium for a laser radar. Background Art

[0002] Atmospheric particles are particles in the air that can affect the transmission of laser energy, including dust, water droplets, pollen, microorganisms (bacteria, fungal spores), aerosol particles (such as smoke, salt particles, volcanic ash, etc.) and pollutants emitted by humans. These atmospheric particles can reflect the laser emitted by the laser transmitter in the lidar, which may lead to misidentification of the lidar and reduce its measurement accuracy.

[0003] The method of reducing the impact of atmospheric particles on the laser radar in the prior art is to monitor the weather state level in real time, determine the scanning range and power of the laser radar based on the weather state level and a set laser radar working mapping table, and control the laser radar based on the scanning range and power to reduce the impact of atmospheric particles on the laser radar.

[0004] However, the above method also has the following technical problems:

[0005] Real-time monitoring of weather status levels may be affected by the accuracy of monitoring equipment and data transmission delays, resulting in inaccurate monitoring results. Due to the diversity and unpredictability of weather conditions, the set lidar working mapping table may not be able to adapt to all changes in weather conditions. Therefore, the above method is generally ineffective in reducing the impact of atmospheric particles on lidar. Summary of the invention

[0006] In view of the above technical problems, the technical solution adopted by the present invention is:

[0007] According to a first aspect of the present invention, a laser radar control method is provided, the method is used to control a target laser radar, and the method comprises the following steps:

[0008] S1. Acquire environmental information of a target laser radar, where the environmental information includes weather type and weather warning level of a target geographical area, where the target geographical area is a rectangular geographical area where the geographical coordinates of the target laser radar correspond to the geographical location.

[0009] S2. Input the environmental information of the target laser radar into the preset neural network model and use the atmospheric particle concentration output by the preset neural network model as the target atmospheric particle concentration E corresponding to the target geographical area.

[0010] S3, input E into the target neural network model and obtain the estimated laser propagation distance list F={F1, F2, ..., F i, ..., F m}, F i is the estimated laser propagation distance corresponding to the i-th target laser emitter, i ranges from 1 to m, m is the number of target laser emitters in the target lidar, the target laser emitter is the laser emitter in the target lidar, and the target neural network model is different from the preset neural network model.

[0011] S4. According to F i Get the key weight G corresponding to the i-th target laser emitter i , G i Meet the following conditions:

[0012] G i =(F i / C 0 i ) / ∑ m i=1 (F i / C 0 i ), where C 0 i is the laser propagation distance corresponding to the i-th target laser emitter when the atmospheric particle concentration is 0.

[0013] S5. According to F i and G i Get the laser propagation distance H corresponding to the target laser radar, where H meets the following conditions:

[0014] H=∑ m i=1 (G i ×F i ).

[0015] S6. Based on H, the operating parameters of the target laser radar are adjusted to control the target laser radar. The operating parameters of the target laser radar include scanning frequency, pulse repetition frequency, pulse width, laser emission power and scanning mode.

[0016] According to a second aspect of the present invention, a control device for a laser radar is provided, the device is used to control a target laser radar, and the device comprises:

[0017] The environmental information acquisition module is used to obtain the environmental information of the target laser radar. The environmental information includes the weather type and weather warning level of the target geographical area. The target geographical area is a rectangular geographical area where the geographical coordinates of the target laser radar correspond to the geographical location.

[0018] The target atmospheric particle concentration acquisition module is used to input the environmental information of the target laser radar into the preset neural network model and use the atmospheric particle concentration output by the preset neural network model as the target atmospheric particle concentration E corresponding to the target geographical area.

[0019] The estimated laser propagation distance list acquisition module is used to input E into the target neural network model and obtain the estimated laser propagation distance list F={F1, F2, ..., F i , ..., F m}, F i is the estimated laser propagation distance corresponding to the i-th target laser emitter, i ranges from 1 to m, m is the number of target laser emitters in the target lidar, the target laser emitter is the laser emitter in the target lidar, and the target neural network model is different from the preset neural network model.

[0020] Key weight acquisition module, used to obtain the i Get the key weight G corresponding to the i-th target laser emitter i , G i Meet the following conditions:

[0021] G i =(F i / C 0 i ) / ∑ m i=1 (F i / C 0 i ), where C 0 i is the laser propagation distance corresponding to the i-th target laser emitter when the atmospheric particle concentration is 0.

[0022] Laser propagation distance acquisition module is used to obtain the laser propagation distance according to F i and G i Get the laser propagation distance H corresponding to the target laser radar, where H meets the following conditions:

[0023] H=∑ m i=1 (G i ×F i ).

[0024] The target laser radar control module is used to adjust the working parameters of the target laser radar based on H to control the target laser radar. The working parameters of the target laser radar include scanning frequency, pulse repetition frequency, pulse width, laser emission power and scanning mode.

[0025] According to a third aspect of the present invention, there is provided a non-transitory computer-readable storage medium, in which a computer program is stored. The computer program is loaded and executed by a processor to implement the aforementioned method.

[0026] According to a fourth aspect of the present invention, there is provided an electronic device, comprising: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the aforementioned method when executing the computer program.

[0027] The present invention has at least the following beneficial effects:

[0028] The present invention provides a control method, device, equipment and medium of a laser radar. The method inputs environmental information of a target laser radar into a preset neural network model to obtain a target atmospheric particle concentration, inputs the target atmospheric particle concentration into the target neural network model to obtain an estimated laser propagation distance list corresponding to a target laser emitter in the target laser radar, obtains a key weight corresponding to the target laser emitter in the target laser radar according to the estimated laser propagation distance, obtains the laser propagation distance corresponding to the target laser radar according to the estimated laser propagation distance and the key weight, and adjusts the working parameters of the target laser radar based on the laser propagation distance corresponding to the target laser radar to control the target laser radar. It can be seen that the present invention can obtain the estimated laser propagation distance corresponding to the target laser emitter in the target laser radar based on the environmental information of the target laser radar, the preset neural network model and the target neural network model, obtain the key weight corresponding to the target laser emitter in the target laser radar according to the estimated laser propagation distance corresponding to the target laser emitter in the target laser radar, further obtain the laser propagation distance corresponding to the target laser radar, and adjust the working parameters of the target laser radar based on the laser propagation distance corresponding to the target laser radar to control the target laser radar. There is no need to set a laser radar working mapping table, and the effect of reducing the influence of atmospheric particles on the target laser radar can be enhanced, which is beneficial to improving the measurement accuracy of the target laser radar. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0030] Figure 1 A flowchart of a laser radar control method provided in Embodiment 1 of the present invention;

[0031] Figure 2 A schematic diagram of the structure of a control device for a laser radar provided in Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0033] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar tasks, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0034] Embodiment 1

[0035] Embodiment 1 of the present invention provides a laser radar control method, the method is used to control a target laser radar, the method comprises the following steps: Figure 1 As shown:

[0036] S1. Obtain environmental information of the target laser radar, wherein the environmental information includes the weather type and meteorological alert level of the target geographical area. The target geographical area is a rectangular geographical area where the geographical location corresponding to the geographical coordinates of the target laser radar is located. Those skilled in the art know that the length and width of the rectangular geographical area are set by those skilled in the art according to actual needs. In the prior art, any method for obtaining the weather type and meteorological alert level of a geographical area falls within the protection scope of the present invention, for example: obtaining the weather type and meteorological alert level of a geographical area based on weather forecast information, which will not be repeated here.

[0037] Specifically, weather types include sunny, cloudy, overcast, rain, snow, fog, haze and sandstorms.

[0038] Specifically, the weather alert level can be NULL.

[0039] S2. Input the environmental information of the target laser radar into the preset neural network model and use the atmospheric particle concentration output by the preset neural network model as the target atmospheric particle concentration E corresponding to the target geographical area.

[0040] Specifically, the input of the preset neural network model is environmental information, and the output of the preset neural network model is atmospheric particle concentration, which is the concentration of atmospheric particles in the air. Atmospheric particles are particles in the air that can affect laser energy transmission, including dust, water droplets, pollen, microorganisms (bacteria, fungal spores), aerosol particles (such as smoke, salt particles, volcanic ash, etc.) and pollutants emitted by humans.

[0041] S3, input E into the target neural network model and obtain the estimated laser propagation distance list F={F1, F2, ..., F i , ..., F m}, F i is the estimated laser propagation distance corresponding to the i-th target laser emitter, i ranges from 1 to m, m is the number of target laser emitters in the target lidar, the target laser emitter is the laser emitter in the target lidar, the target neural network model is different from the preset neural network model, the number of target laser emitters in the target lidar can be understood as the total number of laser emitters in the target lidar, for example: there are 10 laser emitters in the target lidar, then the total number of laser emitters in the target lidar is 10, then the number of target laser emitters in the target lidar is 10, that is, m=10.

[0042] Specifically, the input of the target neural network model is the atmospheric particle concentration, and the output of the target neural network model is the laser propagation distance corresponding to each target laser emitter.

[0043] Specifically, before step S3, the following steps are also included to obtain the target neural network model:

[0044] S10, obtain a preset atmospheric particle concentration list D = {D1, D2, ..., D j , ..., D n}, where D j is the jth preset atmospheric particle concentration, the value range of j is 1 to n, and n is the number of preset atmospheric particle concentrations.

[0045] Specifically, when j=1, D j =0.

[0046] Specifically, D (j+1) >D j , D (j+1) is the j+1th preset atmospheric particle concentration.

[0047] S20, obtain the intermediate laser emission distance list set C = {C1, C2, ..., C j , ..., C n}, C j D j The corresponding list of intermediate laser propagation distances, D j The corresponding intermediate laser propagation distance list includes each target laser emitter and D j The corresponding intermediate laser propagation distance, the intermediate laser propagation distance corresponding to the target laser emitter and the preset atmospheric particle concentration is the laser propagation distance corresponding to the target laser emitter when the atmospheric particle concentration is the same as the preset atmospheric particle concentration. The laser propagation distance corresponding to the target laser emitter can be understood as the propagation distance of the laser emitted by the target laser emitter. Those skilled in the art know that any method of obtaining the propagation distance of the laser emitted by the laser emitter in the prior art belongs to the protection scope of the present invention and will not be repeated here.

[0048] S30, D j and C j As a training sample and construct a training sample set; it can be understood that the training sample set is {(D1, C1), (D2, C2), ..., (D j , C j ),……,(D n , C n )}.

[0049] S40. Based on the training sample set, the initial neural network model is trained to obtain the target neural network model. Those skilled in the art know that any method in the prior art for training a model based on a training sample set to obtain a trained model falls within the scope of protection of the present invention and will not be described in detail herein.

[0050] Specifically, the initial neural network model is different from the preset neural network model. Those skilled in the art know that they can select a neural network model from all existing neural network models as the initial neural network model according to actual needs, which will not be repeated here.

[0051] Through the above steps, a set of preset atmospheric particle concentration lists and intermediate laser emission distance lists are obtained, the preset atmospheric particle concentration and its corresponding intermediate laser emission distance list are used as a training sample and a training sample set is constructed, and the initial neural network model is trained based on the training sample set to obtain the target neural network model, which is beneficial to improving the output accuracy of the target neural network model.

[0052] S4. According to F i Get the key weight G corresponding to the i-th target laser emitter i , G i Meet the following conditions:

[0053] G i =(F i / C0 i ) / ∑ m i=1 (F i / C 0 i ), where C 0 i is the laser propagation distance corresponding to the i-th target laser emitter when the atmospheric particle concentration is 0.

[0054] Specifically, G. i Used to characterize the importance of the i-th target laser emitter.

[0055] Furthermore, G. i The larger it is, the more important the i-th target laser emitter is.

[0056] S5. According to F i and G i Get the laser propagation distance H corresponding to the target laser radar, where H meets the following conditions:

[0057] H=∑ m i=1 (G i ×F i ).

[0058] S6. Based on H, the operating parameters of the target laser radar are adjusted to control the target laser radar. The operating parameters of the target laser radar include scanning frequency, pulse repetition frequency, pulse width, laser emission power and scanning mode.

[0059] Through the above steps, the estimated laser propagation distance corresponding to the target laser emitter in the target laser radar is obtained based on the environmental information of the target laser radar, the preset neural network model and the target neural network model, the key weight corresponding to the target laser emitter in the target laser radar is obtained according to the estimated laser propagation distance corresponding to the target laser emitter in the target laser radar, and the laser propagation distance corresponding to the target laser radar is further obtained. Based on the laser propagation distance corresponding to the target laser radar, the working parameters of the target laser radar are adjusted to control the target laser radar. There is no need to set a laser radar working mapping table, which can enhance the effect of reducing the impact of atmospheric particles on the target laser radar, and is beneficial to improving the measurement accuracy of the target laser radar.

[0060] Embodiment 2

[0061] Embodiment 2 of the present invention provides a laser radar control device, the device is used to control a target laser radar, such as Figure 2 As shown, the device comprises:

[0062] The environmental information acquisition module 1 is used to obtain the environmental information of the target laser radar, and the environmental information includes the weather type and meteorological alert level of the target geographical area. The target geographical area is a rectangular geographical area where the geographical location corresponding to the geographical coordinates of the target laser radar is located. Those skilled in the art know that the length and width of the rectangular geographical area are set by those skilled in the art according to actual needs. In the prior art, any method for obtaining the weather type and meteorological alert level of a geographical area belongs to the protection scope of the present invention, for example: obtaining the weather type and meteorological alert level of a geographical area based on weather forecast information, which will not be repeated here.

[0063] Specifically, weather types include sunny, cloudy, overcast, rain, snow, fog, haze and sandstorms.

[0064] Specifically, the weather alert level can be NULL.

[0065] The target atmospheric particle concentration acquisition module 2 is used to input the environmental information of the target laser radar into the preset neural network model and use the atmospheric particle concentration output by the preset neural network model as the target atmospheric particle concentration E corresponding to the target geographical area.

[0066] Specifically, the input of the preset neural network model is environmental information, and the output of the preset neural network model is atmospheric particle concentration, which is the concentration of atmospheric particles in the air. Atmospheric particles are particles in the air that can affect laser energy transmission, including dust, water droplets, pollen, microorganisms (bacteria, fungal spores), aerosol particles (such as smoke, salt particles, volcanic ash, etc.) and pollutants emitted by humans.

[0067] The estimated laser propagation distance list acquisition module 3 is used to input E into the target neural network model and obtain the estimated laser propagation distance list F={F1, F2, ..., F i , ..., F m}, F i is the estimated laser propagation distance corresponding to the i-th target laser emitter, i ranges from 1 to m, m is the number of target laser emitters in the target lidar, the target laser emitter is the laser emitter in the target lidar, the target neural network model is different from the preset neural network model, the number of target laser emitters in the target lidar can be understood as the total number of laser emitters in the target lidar, for example: there are 10 laser emitters in the target lidar, then the total number of laser emitters in the target lidar is 10, then the number of target laser emitters in the target lidar is 10, that is, m=10.

[0068] Specifically, the input of the target neural network model is the atmospheric particle concentration, and the output of the target neural network model is the laser propagation distance corresponding to each target laser emitter.

[0069] Specifically, the device also includes a target neural network model acquisition module, which is used to acquire the target neural network model.

[0070] Specifically, the target neural network model acquisition module includes:

[0071] The preset atmospheric particle concentration list acquisition unit is used to acquire the preset atmospheric particle concentration list D={D1, D2, ..., D j , ..., D n}, where D j is the jth preset atmospheric particle concentration, the value range of j is 1 to n, and n is the number of preset atmospheric particle concentrations.

[0072] Specifically, when j=1, D j =0.

[0073] Specifically, D (j+1) >D j , D (j+1) is the j+1th preset atmospheric particle concentration.

[0074] The intermediate laser emission distance list set acquisition unit is used to acquire the intermediate laser emission distance list set C={C1, C2, ..., C j , ..., C n}, C j D j The corresponding list of intermediate laser propagation distances, D j The corresponding intermediate laser propagation distance list includes each target laser emitter and D j The corresponding intermediate laser propagation distance, the intermediate laser propagation distance corresponding to the target laser emitter and the preset atmospheric particle concentration is the laser propagation distance corresponding to the target laser emitter when the atmospheric particle concentration is the same as the preset atmospheric particle concentration. The laser propagation distance corresponding to the target laser emitter can be understood as the propagation distance of the laser emitted by the target laser emitter. Those skilled in the art know that any method of obtaining the propagation distance of the laser emitted by the laser emitter in the prior art belongs to the protection scope of the present invention and will not be repeated here.

[0075] The training sample set acquisition unit is used to convert D j and C j As a training sample and construct a training sample set; it can be understood that the training sample set is {(D1, C1), (D2, C2), ..., (D j , C j ),……,(D n, C n )}.

[0076] The target neural network model acquisition unit is used to train the initial neural network model based on the training sample set to obtain the target neural network model. Those skilled in the art know that any method in the prior art for training a model based on a training sample set to obtain a trained model falls within the scope of protection of the present invention and will not be described in detail herein.

[0077] Specifically, the initial neural network model is different from the preset neural network model. Those skilled in the art know that they can select a neural network model from all existing neural network models as the initial neural network model according to actual needs, which will not be repeated here.

[0078] Key weight acquisition module 4 is used to obtain the key weight according to F i Get the key weight G corresponding to the i-th target laser emitter i , G i Meet the following conditions:

[0079] G i =(F i / C 0 i ) / ∑ m i=1 (F i / C 0 i ), where C 0 i is the laser propagation distance corresponding to the i-th target laser emitter when the atmospheric particle concentration is 0.

[0080] Specifically, G. i Used to characterize the importance of the i-th target laser emitter.

[0081] Furthermore, G. i The larger it is, the more important the i-th target laser emitter is.

[0082] Laser propagation distance acquisition module 5 is used to obtain the laser propagation distance according to F i and G i Get the laser propagation distance H corresponding to the target laser radar, where H meets the following conditions:

[0083] H=∑ m i=1 (G i ×F i ).

[0084] The target laser radar control module 6 is used to adjust the working parameters of the target laser radar based on H to control the target laser radar. The working parameters of the target laser radar include scanning frequency, pulse repetition frequency, pulse width, laser emission power and scanning mode.

[0085] An embodiment of the present invention also provides a non-transitory computer-readable storage medium, which can be set in an electronic device to store a computer program related to a method in a method embodiment, and the computer program is loaded and executed by the processor to implement the method provided in the above embodiment.

[0086] An embodiment of the present invention further provides an electronic device, comprising: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method provided in the above embodiment when executing the computer program.

[0087] An embodiment of the present invention further provides a computer program product, which includes program code. When the program product is run on an electronic device, the program code is used to enable the electronic device to execute the steps of the method according to various exemplary embodiments of the present invention described above in this specification.

[0088] The present invention provides a control method, device, equipment and medium of a laser radar. The method inputs environmental information of a target laser radar into a preset neural network model to obtain a target atmospheric particle concentration, inputs the target atmospheric particle concentration into the target neural network model to obtain an estimated laser propagation distance list corresponding to a target laser emitter in the target laser radar, obtains a key weight corresponding to the target laser emitter in the target laser radar according to the estimated laser propagation distance, obtains the laser propagation distance corresponding to the target laser radar according to the estimated laser propagation distance and the key weight, and adjusts the working parameters of the target laser radar based on the laser propagation distance corresponding to the target laser radar to control the target laser radar. It can be seen that the present invention can obtain the estimated laser propagation distance corresponding to the target laser emitter in the target laser radar based on the environmental information of the target laser radar, the preset neural network model and the target neural network model, obtain the key weight corresponding to the target laser emitter in the target laser radar according to the estimated laser propagation distance corresponding to the target laser emitter in the target laser radar, further obtain the laser propagation distance corresponding to the target laser radar, and adjust the working parameters of the target laser radar based on the laser propagation distance corresponding to the target laser radar to control the target laser radar. There is no need to set a laser radar working mapping table, and the effect of reducing the influence of atmospheric particles on the target laser radar can be enhanced, which is beneficial to improving the measurement accuracy of the target laser radar.

[0089] Although some specific embodiments of the present invention have been described in detail by way of example, it should be understood by those skilled in the art that the above examples are only for illustration, not for limiting the scope of the present invention. It should also be understood by those skilled in the art that various modifications may be made to the embodiments without departing from the scope and spirit of the present invention.

Claims

1. A laser radar control method, the method is used to control a target laser radar, characterized in that: The method comprises the following steps: S1. Acquire environmental information of a target laser radar, wherein the environmental information includes weather type and weather warning level of a target geographical area, where the target geographical area is a rectangular geographical area where the geographical coordinates of the target laser radar correspond to; S2. Input the environmental information of the target laser radar into a preset neural network model and use the atmospheric particle concentration output by the preset neural network model as the target atmospheric particle concentration E corresponding to the target geographical area; the input of the preset neural network model is the environmental information, and the output of the preset neural network model is the atmospheric particle concentration, which is the concentration of atmospheric particles in the air, and the atmospheric particles are particles in the air that can affect the transmission of laser energy; S3, input E into the target neural network model and obtain the estimated laser propagation distance list F={F1, F2, ..., F i , ..., F m }, F i is the estimated laser propagation distance corresponding to the i-th target laser emitter, i ranges from 1 to m, m is the number of target laser emitters in the target laser radar, the target laser emitter is the laser emitter in the target laser radar, the target neural network model is different from the preset neural network model; the input of the target neural network model is the atmospheric particle concentration, and the output of the target neural network model is the laser propagation distance corresponding to each target laser emitter; S4. According to F i Get the key weight G corresponding to the i-th target laser emitter i , G i Meet the following conditions: G i =(F i / C 0 i ) / ∑ m i=1 (F i / C 0 i ), where C 0 i is the laser propagation distance corresponding to the i-th target laser emitter when the atmospheric particle concentration is 0; S5. According to F i and G i Get the laser propagation distance H corresponding to the target laser radar, where H meets the following conditions: H=∑ m i=1 (G i ×F i ); S6. Adjusting the operating parameters of the target laser radar based on H to control the target laser radar, the operating parameters of the target laser radar including scanning frequency, pulse repetition frequency, pulse width, laser transmission power and scanning mode; Before step S3, the following steps are also included to obtain the target neural network model: S10, obtain a preset atmospheric particle concentration list D = {D1, D2, ..., D j , ..., D n }, where D j is the jth preset atmospheric particle concentration, the value range of j is 1 to n, and n is the number of preset atmospheric particle concentrations; S20, obtain the intermediate laser emission distance list set C = {C1, C2, ..., C j , ..., C n }, C j D j The corresponding list of intermediate laser propagation distances, D j The corresponding intermediate laser propagation distance list includes each target laser emitter and D j The corresponding intermediate laser propagation distance, the intermediate laser propagation distance corresponding to the target laser emitter and the preset atmospheric particle concentration is the laser propagation distance corresponding to the target laser emitter when the atmospheric particle concentration is the same as the preset atmospheric particle concentration; S30, D j and C j As a training sample and construct a training sample set; S40: Training the initial neural network model based on the training sample set to obtain a target neural network model.

2. The control method of the laser radar according to claim 1, characterized in that: Weather types include sunny, cloudy, overcast, rain, snow, fog, haze and sandstorm.

3. The control method of the laser radar according to claim 1, characterized in that: When j=1, D j =0.

4. The control method of the laser radar according to claim 1, characterized in that: D (j+1) >D j , D (j+1) is the j+1th preset atmospheric particle concentration.

5. A laser radar control device, the device is used to control a target laser radar, characterized in that: The device comprises: An environmental information acquisition module is used to acquire environmental information of a target laser radar, wherein the environmental information includes weather type and weather warning level of a target geographical area, where the target geographical area is a rectangular geographical area where the geographical coordinates of the target laser radar correspond to; A target atmospheric particle concentration acquisition module is used to input the environmental information of the target laser radar into a preset neural network model and use the atmospheric particle concentration output by the preset neural network model as the target atmospheric particle concentration E corresponding to the target geographical area; the input of the preset neural network model is the environmental information, and the output of the preset neural network model is the atmospheric particle concentration, which is the concentration of atmospheric particles in the air, and the atmospheric particles are particles in the air that can affect the transmission of laser energy; The estimated laser propagation distance list acquisition module is used to input E into the target neural network model and obtain the estimated laser propagation distance list F={F1, F2, ..., F i , ..., F m }, F i is the estimated laser propagation distance corresponding to the i-th target laser emitter, i ranges from 1 to m, m is the number of target laser emitters in the target laser radar, the target laser emitter is the laser emitter in the target laser radar, the target neural network model is different from the preset neural network model; the input of the target neural network model is the atmospheric particle concentration, and the output of the target neural network model is the laser propagation distance corresponding to each target laser emitter; The key weight acquisition module is used to obtain the i Get the key weight G corresponding to the i-th target laser emitter i , G i Meet the following conditions: G i =(F i / C 0 i ) / ∑ m i=1 (F i / C 0 i ), where C 0 i is the laser propagation distance corresponding to the i-th target laser emitter when the atmospheric particle concentration is 0; Laser propagation distance acquisition module is used to obtain the laser propagation distance according to F i and G i Get the laser propagation distance H corresponding to the target laser radar, where H meets the following conditions: H=∑ m i=1 (G i ×F i ); A target laser radar control module, used for adjusting the working parameters of the target laser radar based on H to control the target laser radar, the working parameters of the target laser radar including scanning frequency, pulse repetition frequency, pulse width, laser emission power and scanning mode; The device also includes a target neural network model acquisition module, which is used to acquire the target neural network model; The target neural network model acquisition module includes: The preset atmospheric particle concentration list acquisition unit is used to acquire the preset atmospheric particle concentration list D={D1, D2, ..., D j , ..., D n }, where D j is the jth preset atmospheric particle concentration, the value range of j is 1 to n, and n is the number of preset atmospheric particle concentrations; The intermediate laser emission distance list set acquisition unit is used to acquire the intermediate laser emission distance list set C={C1, C2, ..., C j , ..., C n }, C j D j The corresponding list of intermediate laser propagation distances, D j The corresponding intermediate laser propagation distance list includes each target laser emitter and D j The corresponding intermediate laser propagation distance, the intermediate laser propagation distance corresponding to the target laser emitter and the preset atmospheric particle concentration is the laser propagation distance corresponding to the target laser emitter when the atmospheric particle concentration is the same as the preset atmospheric particle concentration; The training sample set acquisition unit is used to convert D j and C j As a training sample and construct a training sample set; The target neural network model acquisition unit is used to train the initial neural network model based on the training sample set to acquire the target neural network model.

6. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores a computer program, which is loaded and executed by a processor to implement the control method of the laser radar as described in any one of claims 1 to 4.

7. An electronic device comprising: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the laser radar control method as described in any one of claims 1 to 4 when executing the computer program.

Images