Lidar laser energy adjustment method, apparatus, device, and storage medium

Abstract

The application discloses a laser radar laser energy adjusting method and device, equipment and a storage medium, and relates to the technical field of laser radar. The laser radar laser energy adjusting method comprises the following steps: acquiring laser emitter energy of a historical ranging point, distance solution results of the historical ranging point and energy values of historical ranging point reflection pulses to obtain a sample matrix; inputting the sample matrix into a neural network for training to obtain a laser output energy prediction model; and inputting the sample matrix into the laser output energy prediction model for prediction to obtain laser output energy of a next ranging point. The application can improve distance solution accuracy by adjusting the laser.

Description

Technical Field

[0001] This application relates to the field of lidar technology, and in particular to a lidar laser energy adjustment method, apparatus, device, and storage medium. Background Technology

[0002] LiDAR (Light Detection and Ranging) is an active measurement device that uses laser beams to measure the precise distance between objects and sensors. In practical applications, the reflectivity of different obstacles and their relative distance to the LiDAR can vary greatly, leading to significant differences in the intensity of the echo signal received by the receiver. To ensure the received signal is within the receiver's optimal operating range and to guarantee distance calculation accuracy, the laser emission energy needs to be adjusted.

[0003] Currently, laser emission energy adjustment schemes rely on weighted calculations based on previous laser reflection energy data. However, this approach struggles to ensure the next laser reflection energy remains within an appropriate range and cannot handle sudden changes in the reflectivity or distance of the detected object, resulting in low distance calculation accuracy. Therefore, improving distance calculation accuracy through laser adjustment remains a problem that needs to be solved.

[0004] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this application is to provide a method, apparatus, device, and storage medium for adjusting the energy of a lidar laser, aiming to solve the technical problem of how to improve the accuracy of distance calculation by adjusting the laser.

[0006] To achieve the above objectives, this application proposes a method for adjusting the energy of a lidar laser, the method comprising:

[0007] The sample matrix is ​​obtained by acquiring the laser emission energy of historical ranging points, the distance calculation results of historical ranging points, and the energy value of the reflected pulses of historical ranging points.

[0008] The sample matrix is ​​input into a neural network for training to obtain a laser output energy prediction model.

[0009] The sample matrix is ​​input into the laser output energy prediction model to predict the laser output energy at the next ranging point.

[0010] In one embodiment, the step of inputting the sample matrix into a neural network for training to obtain a laser output energy prediction model includes:

[0011] Calculate the target value and the output value based on the sample matrix;

[0012] Calculate the offset between the target value and the output value;

[0013] Based on the offset, a laser output energy prediction model is obtained.

[0014] In one embodiment, the step of calculating the target value and the output value based on the sample matrix includes:

[0015] Based on the sample matrix, the target value is obtained according to the preset algorithm;

[0016] Based on the sample matrix, calculate the outputs of the hidden and output layers of the neural network to obtain the output values.

[0017] In one embodiment, the step of obtaining the target value based on the sample matrix and according to a preset algorithm includes:

[0018] The lower limit and upper limit of energy value acquisition;

[0019] The target value is obtained based on the energy value of the reflected pulse from the historical ranging point, the lower limit of the energy value, and the upper limit of the energy value.

[0020] In one embodiment, the step of obtaining the target value based on the energy value of the reflected pulse from the historical ranging point, the lower limit of the energy value, and the upper limit of the energy value includes:

[0021] When the energy value of the reflected pulse from the historical ranging point is less than the lower limit of the energy value, then the...

[0022] The lower limit of the energy value is used as the target value;

[0023] When the energy value of the reflected pulse from the historical ranging point is greater than the upper limit of the energy value, then the...

[0024] The upper limit of the energy value is used as the target value;

[0025] When the energy value of the historical ranging point reflected pulse is between the lower limit and the upper limit of the energy value, the energy value of the historical ranging point reflected pulse is taken as the target value.

[0026] In one embodiment, the step of obtaining the laser output energy prediction model based on the offset includes:

[0027] If the offset is within the preset allowable range, the training ends and the laser output energy prediction model is obtained.

[0028] If the offset is not within the preset allowable range, the weights of the hidden layer and the output layer of the neural network are updated, and the output value is recalculated, returning to the step of calculating the offset between the target value and the output value.

[0029] In one embodiment, the step of obtaining the laser output energy prediction model based on the offset includes:

[0030] If the offset is within the preset allowable range, the training ends and the laser output energy prediction model is obtained.

[0031] If the offset is not within the preset allowable range, the weights of the hidden layer and the output layer of the neural network are updated, and the output value is recalculated, returning to the step of calculating the offset between the target value and the output value.

[0032] Furthermore, to achieve the above objectives, this application also proposes a lidar laser energy adjustment device, which includes:

[0033] The acquisition module acquires the laser emission energy at the ranging point, the distance calculation result at the ranging point, and the energy value of the reflected pulse at the ranging point, and obtains a sample matrix.

[0034] The training module inputs the sample matrix into the neural network for training to obtain a laser output energy prediction model;

[0035] The calculation module inputs the sample matrix into the laser output energy prediction model to predict the laser output energy at the next ranging point.

[0036] In addition, to achieve the above objectives, this application also proposes a lidar laser energy adjustment device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the lidar laser energy adjustment method described above.

[0037] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the lidar laser energy adjustment method described above.

[0038] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the lidar laser energy adjustment method described above.

[0039] This application provides a method for adjusting the laser energy of a lidar laser. The method first obtains the laser emission energy of historical ranging points, the distance calculation results of historical ranging points, and the energy value of the reflected pulses of historical ranging points to obtain a sample matrix. The sample matrix is ​​then input into a neural network for training to obtain a laser output energy prediction model. Finally, the sample matrix is ​​input into the laser output energy prediction model for prediction to obtain the laser output energy of the next ranging point.

[0040] In summary, this application trains the neural network in real time and uses the neural network to predict the laser output energy required for the next ranging point, which can ensure that the laser echo pulse signal is within the ideal range with a high probability and improve the accuracy of distance calculation. Attached Figure Description

[0041] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0042] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is a flowchart illustrating an embodiment of the lidar laser energy adjustment method of this application.

[0044] Figure 2 This is a flowchart illustrating Embodiment 2 of the lidar laser energy adjustment method of this application;

[0045] Figure 3 This is a schematic diagram of the module structure of the lidar laser energy adjustment device according to an embodiment of this application;

[0046] Figure 4 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the lidar laser energy adjustment method in the embodiments of this application.

[0047] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0048] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0049] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0050] The main solution of this application embodiment is: to obtain the laser emission energy of historical ranging points, the distance calculation results of historical ranging points, and the energy value of the reflected pulse of historical ranging points to obtain a sample matrix; to input the sample matrix into a neural network for training to obtain a laser output energy prediction model; and to input the sample matrix into the laser output energy prediction model for prediction to obtain the laser output energy of the next ranging point.

[0051] Currently, existing laser emission energy adjustment methods are based on weighted calculations of the energy of the previous one or several laser reflections. However, this approach makes it difficult to ensure that the energy of the next laser reflection is within an appropriate range, and it cannot cope with sudden changes in the reflectivity or distance of the object being detected, resulting in low distance calculation accuracy.

[0052] This application trains a neural network in real time to predict the laser output energy required for the next ranging point, which can ensure that the laser echo pulse signal is within the ideal range with a high probability, thereby improving the accuracy of distance calculation.

[0053] Based on this, embodiments of this application provide a method for adjusting the energy of a lidar laser, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the laser energy adjustment method for lidar in this application.

[0054] In this embodiment, the laser energy adjustment method for the lidar laser includes steps S10 to S30:

[0055] Step S10: Obtain the laser emission energy of historical ranging points, the distance calculation results of historical ranging points, and the energy value of the reflected pulses of historical ranging points to obtain the sample matrix;

[0056] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device or LiDAR host computer capable of performing the above functions. The following description uses a LiDAR host computer as an example to illustrate this embodiment and the subsequent embodiments.

[0057] It should be noted that historical ranging points refer to points where ranging has already been completed. By obtaining the laser emission energy, distance calculation results, and reflected pulse energy values ​​of historical ranging points, a sample matrix can be obtained, as shown below:

[0058]

[0059] Where S(n) is the laser emission energy at the previous ranging point; L(n) is the distance calculation result at the previous ranging point; E(n) is the energy value of the reflected pulse at the previous ranging point; and m is a positive integer.

[0060] Step S20: Input the sample matrix into the neural network for training to obtain the laser output energy prediction model;

[0061] It should be noted that neural networks consist of a large number of interconnected nodes, capable of processing complex data inputs and performing various tasks such as classification, regression, and pattern recognition. Training a neural network involves adjusting its parameters (such as weights and biases) to optimize its performance, enabling it to accurately predict or classify input data. By inputting the sample matrix into the neural network for training, a laser output energy prediction model is ultimately obtained.

[0062] Step S30: Input the sample matrix into the laser output energy prediction model to predict the laser output energy at the next ranging point.

[0063] It should be noted that by inputting the sample matrix into the laser output energy prediction model, the model processes the data in the sample matrix to obtain the laser output energy at the next ranging point. Simultaneously, the obtained output energy can be used as a sample matrix for real-time training, ensuring the accuracy of the laser output energy prediction model.

[0064] This embodiment first obtains the laser emission energy, distance calculation results, and reflected pulse energy values ​​of historical ranging points to form a sample matrix. The sample matrix is ​​then input into a neural network for training to obtain a laser output energy prediction model. Finally, the sample matrix is ​​input into this model to predict the laser output energy for the next ranging point. This embodiment trains the neural network in real-time, using it to predict the required laser output energy for the next ranging point. This approach ensures that the laser echo pulse signal is within the ideal range with a high probability, improving distance calculation accuracy.

[0065] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in Embodiment 1 above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 Step S20 may include steps S201 to S203:

[0066] Step S201: Calculate the target value and output value based on the sample matrix;

[0067] It should be noted that the target value refers to a relatively accurate value obtained directly from the sample matrix, while the output value is the value calculated and output by the neural network.

[0068] In one available approach, the step of calculating the target value and the actual value based on the sample matrix includes:

[0069] Based on the sample matrix, the target value is obtained according to the preset algorithm;

[0070] Based on the sample matrix, calculate the outputs of the hidden and output layers of the neural network to obtain the actual values.

[0071] It should be noted that, according to the preset algorithm, to obtain the target value, it is first necessary to obtain the lower limit and upper limit of the energy value. Then, based on the energy value of the historical ranging point reflected pulse, the lower limit of the energy value, and the upper limit of the energy value, the target value is obtained. Specifically, when the energy value of the historical ranging point reflected pulse is less than the lower limit of the energy value, the lower limit of the energy value is used as the target value; when the energy value of the historical ranging point reflected pulse is greater than the upper limit of the energy value, the upper limit of the energy value is used as the target value; when the energy value of the historical ranging point reflected pulse is between the lower limit and the upper limit of the energy value, the energy value of the historical ranging point reflected pulse is used as the target value. The specific formula is:

[0072]

[0073]

[0074] Where T(n) is the target value, E(n) is the energy value of the reflected pulse from the previous ranging point, E0 is the lower limit of the energy value, and E1 is the upper limit of the energy value. k is the laser emission energy adjustment coefficient, which is a predetermined constant. Within this energy range, E(n) has the best distance calculation accuracy.

[0075] Step S202: Calculate the offset between the target value and the output value;

[0076] Calculating the offset between the target value and the output value involves calculating the difference between the target value and the output value. By calculating the offset, it is possible to determine whether the current output of the neural network meets the requirements.

[0077] Step S203: Obtain the laser output energy prediction model based on the offset.

[0078] The system determines whether the current output of the neural network meets the requirements based on the offset, and then decides whether to iterate based on the judgment result, so as to finally obtain the laser output energy prediction model.

[0079] In one feasible approach, the step of obtaining the laser output energy prediction model based on the offset includes:

[0080] If the offset is within the preset allowable range, the training ends and the laser output energy prediction model is obtained.

[0081] If the offset is not within the preset allowable range, the weights of the hidden layer and the output layer of the neural network are updated, and the actual values ​​are recalculated, returning to the step of calculating the offset between the target value and the actual value.

[0082] Understandably, when the offset is within the preset allowable range, it indicates that the difference between the target value and the output value is small, which meets the requirements, and the laser output energy prediction model can be obtained. However, when the offset is outside the preset allowable range, it indicates that the difference between the target value and the output value is large, which does not meet the requirements. Therefore, it is necessary to update the weights of the hidden and output layers of the neural network and recalculate the output value to obtain a new offset. This process continues until the offset meets the error requirements. The steps for updating the weights of the hidden and output layers of the neural network can be divided into: calculating the error between the hidden and output layers; calculating the error gradient based on the error; and updating the weights of the hidden and output layers based on the error gradient.

[0083] Furthermore, to handle situations where iteration cannot be stopped, it is necessary to obtain the maximum number of iterations and, at each iteration, check whether the current iteration count has exceeded the maximum number of iterations. If the maximum number of iterations has been reached, the iteration must be stopped.

[0084] This embodiment first calculates the target value and the actual value based on the sample matrix; then it calculates the offset between the target value and the actual value; and finally, based on the offset, it obtains the laser output energy prediction model. The entire process trains the neural network, iteratively adjusting the parameters to ultimately obtain the laser output energy prediction model. This laser output energy prediction model can accurately predict the next laser output energy, improving the accuracy of distance calculation.

[0085] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the laser energy adjustment method of the lidar laser in this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0086] This application also provides a laser energy adjustment device for lidar lasers; please refer to [reference needed]. Figure 3 The laser energy adjustment device for the lidar laser includes:

[0087] Module 10 acquires the laser emission energy at the ranging point, the distance calculation result at the ranging point, and the energy value of the reflected pulse at the ranging point to obtain a sample matrix.

[0088] Training module 20 inputs the sample matrix into the neural network for training to obtain a laser output energy prediction model;

[0089] The calculation module 30 inputs the sample matrix into the laser output energy prediction model to predict the laser output energy at the next ranging point.

[0090] In one embodiment, the training module 20 is further configured to calculate the target value and the actual value based on the sample matrix; calculate the offset between the target value and the actual value; and obtain a laser output energy prediction model based on the offset.

[0091] In one embodiment, the training module 20 is further configured to obtain a target value according to a preset algorithm based on the sample matrix; and to calculate the outputs of the hidden layer and the output layer of the neural network according to the sample matrix to obtain the actual value.

[0092] In one embodiment, the training module 20 is further configured to obtain a lower limit and an upper limit of the energy value; and to obtain a target value based on the energy value of the reflected pulses from the historical ranging points, the lower limit of the energy value, and the upper limit of the energy value.

[0093] In one embodiment, the training module 20 is further configured to: when the energy value of the historical ranging point reflected pulse is less than the lower limit of the energy value, use the lower limit of the energy value as the target value; when the energy value of the historical ranging point reflected pulse is greater than the upper limit of the energy value, use the upper limit of the energy value as the target value; and when the energy value of the historical ranging point reflected pulse is between the lower limit of the energy value and the upper limit of the energy value, use the energy value of the historical ranging point reflected pulse as the target value.

[0094] In one embodiment, the training module 20 is further configured to terminate training and obtain a laser output energy prediction model if the offset is within a preset allowable range; and update the weights of the hidden layer and output layer of the neural network and recalculate the actual value if the offset is not within the preset allowable range, returning to the step of calculating the offset between the target value and the actual value.

[0095] In one embodiment, the training module 20 is further configured to calculate the error between the hidden layer and the output layer of the neural network; calculate the error gradient based on the error; and update the weights of the hidden layer and the output layer of the neural network based on the error gradient.

[0096] This embodiment first obtains the laser emission energy, distance calculation results, and reflected pulse energy values ​​of historical ranging points to form a sample matrix. The sample matrix is ​​then input into a neural network for training to obtain a laser output energy prediction model. Finally, the sample matrix is ​​input into this model to predict the laser output energy for the next ranging point. This embodiment trains the neural network in real-time, using it to predict the required laser output energy for the next ranging point. This approach ensures that the laser echo pulse signal is within the ideal range with a high probability, improving distance calculation accuracy.

[0097] The lidar laser energy adjustment device provided in this application, employing the lidar laser energy adjustment method described in the above embodiments, can solve the technical problem of how to improve the distance calculation accuracy by adjusting the laser. Compared with the prior art, the beneficial effects of the lidar laser energy adjustment device provided in this application are the same as those of the lidar laser energy adjustment method provided in the above embodiments, and other technical features in the lidar laser energy adjustment device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0098] This application provides a lidar laser energy adjustment device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the lidar laser energy adjustment method in the first embodiment described above.

[0099] The following is for reference. Figure 4 This document illustrates a structural schematic diagram of a lidar laser energy adjustment device suitable for implementing embodiments of this application. The lidar laser energy adjustment device in these embodiments may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 4 The lidar laser energy adjustment device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0100] like Figure 4As shown, the lidar laser energy adjustment device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the lidar laser energy adjustment device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the lidar laser energy conditioning device to communicate wirelessly or wiredly with other devices to exchange data. Although lidar laser energy conditioning devices with various systems are shown in the figures, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented alternatively.

[0101] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0102] The lidar laser energy adjustment device provided in this application, employing the lidar laser energy adjustment method described in the above embodiments, can solve the technical problem of how to improve the distance calculation accuracy by adjusting the laser. Compared with the prior art, the beneficial effects of the lidar laser energy adjustment device provided in this application are the same as those of the lidar laser energy adjustment method provided in the above embodiments, and other technical features of this lidar laser energy adjustment device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0103] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0104] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0105] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the lidar laser energy adjustment method in the above embodiments.

[0106] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0107] The aforementioned computer-readable storage medium may be included in the lidar laser energy conditioning device; or it may exist independently and not assembled into the lidar laser energy conditioning device.

[0108] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the lidar laser energy adjustment device, cause the lidar laser energy adjustment device to: acquire the laser emission energy of historical ranging points, the distance calculation results of historical ranging points, and the energy value of the reflected pulses of historical ranging points, and obtain a sample matrix;

[0109] The sample matrix is ​​input into a neural network for training to obtain a laser output energy prediction model.

[0110] The sample matrix is ​​input into the laser output energy prediction model to predict the laser output energy at the next ranging point.

[0111] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0112] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0113] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0114] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described lidar laser energy adjustment method, which can solve the technical problem of how to improve the accuracy of distance calculation by adjusting the laser. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the lidar laser energy adjustment method provided in the above embodiments, and will not be repeated here.

[0115] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the lidar laser energy adjustment method described above.

[0116] The computer program product provided in this application can solve the technical problem of how to improve the accuracy of distance calculation by adjusting the laser. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the lidar laser energy adjustment method provided in the above embodiments, and will not be repeated here.

[0117] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for adjusting the energy of a lidar laser, characterized in that, The method includes: The sample matrix is ​​obtained by acquiring the laser emission energy of historical ranging points, the distance calculation results of historical ranging points, and the energy value of the reflected pulses of historical ranging points. The sample matrix is ​​input into a neural network for training to obtain a laser output energy prediction model. The sample matrix is ​​input into the laser output energy prediction model for prediction to obtain the laser output energy at the next ranging point; The step of inputting the sample matrix into a neural network for training to obtain a laser output energy prediction model includes: Based on the sample matrix, the target value and the output value are calculated. The target value is obtained through the sample matrix, and the output value is calculated and output by the neural network. Calculate the offset between the target value and the output value; Based on the offset, a laser output energy prediction model is obtained; The steps for calculating the target value and the output value based on the sample matrix include: Based on the sample matrix, the target value is obtained according to a preset algorithm, which includes: Where T(n) is the target value, E(n) is the energy value of the reflected pulse at the previous ranging point, E0 is the lower limit of the energy value, E1 is the upper limit of the energy value, k is the laser emission energy adjustment term coefficient, which is a predetermined fixed value, and S(n) is the laser emission energy at the previous ranging point. Based on the sample matrix, calculate the outputs of the hidden and output layers of the neural network to obtain the output values.

2. The method as described in claim 1, characterized in that, The step of obtaining the target value based on the sample matrix and according to a preset algorithm includes: The lower limit and upper limit of energy value acquisition; The target value is obtained based on the energy value of the reflected pulse from the historical ranging point, the lower limit of the energy value, and the upper limit of the energy value.

3. The method as described in claim 2, characterized in that, The step of obtaining the target value based on the energy value of the reflected pulse from the historical ranging point, the lower limit of the energy value, and the upper limit of the energy value includes: If the energy value of the reflected pulse from the historical ranging point is less than the lower limit of the energy value, then the lower limit of the energy value is taken as the target value. If the energy value of the reflected pulse from the historical ranging point is greater than the upper limit of the energy value, then the upper limit of the energy value is taken as the target value. When the energy value of the historical ranging point reflected pulse is between the lower limit and the upper limit of the energy value, the energy value of the historical ranging point reflected pulse is taken as the target value.

4. The method as described in claim 1, characterized in that, The step of obtaining the laser output energy prediction model based on the offset includes: If the offset is within the preset allowable range, the training ends and the laser output energy prediction model is obtained. If the offset is not within the preset allowable range, the weights of the hidden layer and the output layer of the neural network are updated, and the output value is recalculated, returning to the step of calculating the offset between the target value and the output value.

5. The method as described in claim 4, characterized in that, The steps for updating the weights of the hidden layer and the output layer of the neural network include: Calculate the error between the hidden layer and the output layer of the neural network; Calculate the error gradient based on the error. Update the weights of the hidden and output layers of the neural network based on the error gradient.

6. A laser energy adjustment device for lidar, characterized in that, The device includes: The acquisition module acquires the laser emission energy at the ranging point, the distance calculation result at the ranging point, and the energy value of the reflected pulse at the ranging point, and obtains a sample matrix. The training module inputs the sample matrix into the neural network for training to obtain a laser output energy prediction model; The calculation module inputs the sample matrix into the laser output energy prediction model to predict the laser output energy at the next ranging point. The training module is also used to calculate a target value and an output value based on the sample matrix, wherein the target value is obtained through the sample matrix and the output value is obtained by the neural network. Calculate the offset between the target value and the output value; Based on the offset, a laser output energy prediction model is obtained; The training module is further configured to obtain target values ​​based on the sample matrix according to a preset algorithm, wherein the preset algorithm includes: Where T(n) is the target value, E(n) is the energy value of the reflected pulse at the previous ranging point, E0 is the lower limit of the energy value, E1 is the upper limit of the energy value, k is the laser emission energy adjustment term coefficient, which is a predetermined fixed value, and S(n) is the laser emission energy at the previous ranging point. Based on the sample matrix, calculate the outputs of the hidden and output layers of the neural network to obtain the output values.

7. A laser energy adjustment device for lidar, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the lidar laser energy modulation method as described in any one of claims 1 to 5.

8. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the lidar laser energy adjustment method as described in any one of claims 1 to 5.

Images