Laser transmitter emission control method and system

Abstract

The application discloses a laser emitter emission control method and system, relates to the technical field of laser emission control, and comprises the following steps: extracting the instantaneous distance, radial velocity, contour feature point set and motion trajectory prediction data of a target from original environment perception data; fusing the data to generate a real-time state vector; predicting a plurality of position points of the target in a future period of time based on target motion parameters, judging position safety in combination with a pre-stored safety region boundary, and determining a laser emission level in combination with a target contour feature; obtaining the maximum allowed emission power according to an energy level mapping table and the determined emission level, comparing the maximum allowed emission power with a minimum effective power threshold to determine the final actual execution power, and then generating a laser emission control instruction. Through the above method, adaptive and refined regulation and control of the laser emission power are realized, the safety of the human eye and equipment is effectively ensured, and the efficiency and reliability of the system under different working modes and environmental conditions are taken into account.

Description

Technical Field

[0001] This application relates to the field of laser emission control technology, and in particular to laser emitter emission control methods and systems. Background Technology

[0002] Currently, laser technology is increasingly widely used in ranging, communication, sensing, and target designation. However, traditional laser emission power control methods are mostly based on fixed thresholds or simple distance judgments, lacking a comprehensive assessment of the target's dynamic behavior, attribute characteristics, and future trajectory. This crude control strategy is difficult to effectively cope with complex and ever-changing application scenarios, potentially leading to an inability to reduce power to a safe level in time when potential risks occur (such as human eyes or sensitive devices entering the beam area), or excessive power suppression in situations where strict restrictions are not required, thus affecting system performance. Therefore, existing technologies suffer from insufficient intelligence in laser power control and weak proactive safety assurance capabilities.

[0003] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main purpose of this application is to provide a laser emitter emission control method and system, which aims to solve the technical problems of lack of intelligence and safety in laser power control in the prior art.

[0005] To achieve the above objectives, this application provides a laser emitter emission control method, the method comprising: The instantaneous distance and radial velocity of the target object relative to the laser emitter, as well as the contour feature point set and motion trajectory prediction data of the target object, are extracted from the original environmental perception data. A real-time state vector is obtained by fusing the instantaneous distance, the radial velocity, the contour feature point set, and the motion trajectory prediction data; Based on the target motion parameters of the real-time state vector, calculate multiple predicted position points of the target object within a future preset time period, combine the pre-stored safe area boundary information to judge the predicted position points, obtain the position judgment result, and determine the laser emission level based on the position judgment result and the target contour features in the real-time state vector. The maximum allowable emission power value is determined based on the energy level mapping table and the laser emission level. The actual execution power is determined by the maximum allowable emission power value and the preset minimum effective power threshold. Laser emission control commands are generated based on the actual execution power.

[0006] In one embodiment, the step of extracting the instantaneous distance and radial velocity of the target object relative to the laser emitter, as well as the contour feature point set and motion trajectory prediction data of the target object from the original environmental perception data, includes: Extract lidar point cloud data and image data from the raw environmental perception data; Cluster analysis is performed on the lidar point cloud data to obtain the initial point cloud cluster of the target object; Based on the displacement of the center point of the initial point cloud cluster in multiple consecutive frames, the instantaneous distance and radial velocity of the target object relative to the laser emitter are calculated. The image data is subjected to convolutional neural network feature extraction to obtain the contour feature point set of the target object; Historical motion data of the initial point cloud cluster is extracted, and Kalman filtering is performed on the historical motion data to obtain the motion trajectory prediction data of the target object.

[0007] In one embodiment, the step of fusing the instantaneous distance, the radial velocity, the contour feature point set, and the motion trajectory prediction data to obtain a real-time state vector includes: The instantaneous distance and radial velocity are normalized to obtain standardized motion parameters; Principal component analysis is performed on the contour feature point set to extract principal component features representing the target orientation and shape; The motion trajectory prediction data is projected onto the laser emitter coordinate system to obtain a position coordinate sequence; A real-time state vector is generated based on the standardized motion parameters, the principal component features, and the position coordinate sequence.

[0008] In one embodiment, the step of calculating multiple predicted location points of the target object within a future preset time period based on the target motion parameters of the real-time state vector includes: The current position coordinates, instantaneous velocity vector, and acceleration estimation vector of the target object are parsed from the target motion parameters of the real-time state vector. Based on the instantaneous velocity vector and the acceleration estimation vector, a kinematic prediction model of the target object in the laser emitter coordinate system is constructed. Based on the kinematic prediction model, starting from the current position coordinates, the target object is discretized within a preset time period in the future using a preset time step, and multiple predicted position points of the target object within the preset time period in the future are obtained through iterative calculation.

[0009] In one embodiment, the step of determining the laser emission level based on the predicted location point by combining pre-stored safe area boundary information to obtain a location determination result, and the step of determining the laser emission level based on the location determination result and the target contour features in the real-time state vector includes: Collision detection is performed between the predicted location points and the pre-stored safe area boundary information to count the number of predicted location points that are completely outside the safe area. Determine the ratio of the number of predicted location points that are completely outside the safe zone to the total number of predicted points, and generate a location judgment result based on the ratio; The principal component coefficients of the target contour features are extracted from the real-time state vector, and the principal component coefficients are matched with a pre-stored friendly target feature library to obtain the target identity confidence score. The laser emission level is determined based on the location determination result and the target identity confidence level.

[0010] In one embodiment, before the step of determining the laser emission level based on the location determination result and the target identity confidence level, the method further includes: Determine the confidence level of the motion parameters in the real-time state vector, and calculate the prediction error ellipsoid of the kinematic prediction model at each prediction time step based on the confidence level; Based on the spatial relationship between the prediction error ellipsoid corresponding to all predicted location points and the pre-stored safe area boundary information, the uncertainty of the location judgment result is corrected.

[0011] In one embodiment, after the step of determining the laser emission level based on the location determination result and the target identity confidence level, the method further includes: Real-time acquisition of current atmospheric turbulence intensity and visibility parameters; The target identity confidence score is attenuated and corrected based on the atmospheric turbulence intensity to obtain the corrected target identity confidence score. The location determination result is weighted and adjusted according to the visibility parameter to obtain the weighted and adjusted location determination result. The compensated laser emission level is determined using the corrected target identity confidence level and the weighted adjusted position judgment result.

[0012] In one embodiment, the steps of determining the maximum allowable emission power value based on the energy level mapping table and the laser emission level, determining the actual execution power by comparing the maximum allowable emission power value with a preset minimum effective power threshold, and generating laser emission control commands based on the actual execution power include: Based on the current operating mode and power consumption limits, the power reference value in the energy level mapping table is dynamically adjusted to obtain the dynamically adjusted energy level mapping table. Using the laser emission level as an index, the maximum allowable emission power value is obtained by querying the dynamically adjusted energy level mapping table. Compare the maximum allowable transmit power value with the preset minimum effective power threshold; When the maximum allowable transmission power value is greater than the preset minimum effective power threshold, the maximum allowable transmission power value is taken as the actual execution power; Laser emission control commands are generated based on the actual execution power.

[0013] In one embodiment, the step of dynamically adjusting the power reference value in the energy level mapping table according to the current operating mode and power consumption limitations to obtain a dynamically adjusted energy level mapping table includes: Obtain the current thermal load parameters and remaining battery power, and calculate the real-time maximum support power of the system based on the thermal load parameters and remaining battery power; Based on the priority weight corresponding to the current working mode, the initial power reference value associated with each laser emission level in the energy level mapping table is scaled proportionally to obtain the power reference value after mode adjustment. The power reference value after mode adjustment is compared with the maximum power that the system can support, and the smaller value between the power reference value after mode adjustment and the maximum power that the system can support is taken as the target safe power limit. The energy level mapping table is dynamically adjusted based on the target safe power limit to obtain a dynamically adjusted energy level mapping table.

[0014] Furthermore, to achieve the above objectives, this application also proposes a laser emitter emission control system, which includes: The information extraction module is used to extract the instantaneous distance and radial velocity of the target object relative to the laser emitter, as well as the contour feature point set and motion trajectory prediction data of the target object from the original environmental perception data; The state fusion module is used to fuse the instantaneous distance, the radial velocity, the contour feature point set, and the motion trajectory prediction data to obtain a real-time state vector; The evaluation and decision module is used to calculate multiple predicted position points of the target object within a future preset time period based on the target motion parameters of the real-time state vector, judge the predicted position points in combination with the pre-stored safe area boundary information, obtain the position judgment result, and determine the laser emission level based on the position judgment result and the target contour features in the real-time state vector. The power control module is used to determine the maximum allowable emission power value according to the energy level mapping table and the laser emission level, determine the actual execution power by the maximum allowable emission power value and the preset minimum effective power threshold, and generate laser emission control commands according to the actual execution power.

[0015] In addition, to achieve the above objectives, this application also proposes a laser emitter emission control device, which 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 laser emitter emission control method described above.

[0016] In addition, to achieve the above objectives, the present invention 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 laser emitter emission control method described above.

[0017] 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 laser emitter emission control method described above.

[0018] This application provides a laser emitter emission control method. It extracts the instantaneous distance, radial velocity, contour feature point set, and motion trajectory prediction data of the target from raw environmental perception data. These data are then fused to generate a real-time state vector. Based on the target's motion parameters, multiple position points within a future timeframe are predicted. Position safety is assessed by combining this with pre-stored safety zone boundaries, and the laser emission level is determined jointly with the target contour features. The maximum allowable emission power is obtained based on an energy level mapping table and the determined emission level. The final actual execution power is determined by comparing this power with a minimum effective power threshold, thereby generating laser emission control commands. This method achieves adaptive and refined control of the laser emission power, effectively ensuring the safety of human eyes and equipment, while also considering the system's performance and reliability under different operating modes and environmental conditions. Attached Figure Description

[0019] 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.

[0020] 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.

[0021] Figure 1 This is a flowchart illustrating an embodiment of the laser emitter emission control method of this application; Figure 2 This is a schematic diagram of the instruction generation process of an embodiment of the laser emitter emission control method of this application; Figure 3 This is a schematic diagram of the module structure of the laser emitter emission control system according to an embodiment of this application; Figure 4 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the laser emitter emission control method in the embodiments of this application.

[0022] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0023] 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.

[0024] 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.

[0025] The main solution of this application embodiment is: to extract the instantaneous distance and radial velocity of the target object relative to the laser emitter, as well as the contour feature point set and motion trajectory prediction data of the target object from the original environmental perception data; A real-time state vector is obtained by fusing the instantaneous distance, the radial velocity, the contour feature point set, and the motion trajectory prediction data; Based on the target motion parameters of the real-time state vector, calculate multiple predicted position points of the target object within a future preset time period, combine the pre-stored safe area boundary information to judge the predicted position points, obtain the position judgment result, and determine the laser emission level based on the position judgment result and the target contour features in the real-time state vector. The maximum allowable emission power value is determined based on the energy level mapping table and the laser emission level. The actual execution power is determined by the maximum allowable emission power value and the preset minimum effective power threshold. Laser emission control commands are generated based on the actual execution power.

[0026] Currently, laser technology is increasingly widely used in ranging, communication, sensing, and target designation. However, traditional laser emission power control methods are mostly based on fixed thresholds or simple distance judgments, lacking a comprehensive assessment of the target's dynamic behavior, attribute characteristics, and future trajectory. This crude control strategy is difficult to effectively cope with complex and ever-changing application scenarios, potentially leading to an inability to reduce power to a safe level in time when potential risks occur (such as human eyes or sensitive devices entering the beam area), or excessive power suppression in situations where strict restrictions are not required, thus affecting system performance. Therefore, existing technologies suffer from insufficient intelligence in laser power control and weak proactive safety assurance capabilities.

[0027] This application provides a solution that extracts instantaneous distance, radial velocity, contour feature point set, and motion trajectory prediction data of a target from raw environmental perception data; fuses these data to generate a real-time state vector; predicts multiple location points of the target over a future period based on its motion parameters, determines location safety by combining pre-stored safe zone boundaries, and jointly determines the laser emission level with the target contour features; obtains the maximum allowable emission power based on an energy level mapping table and the determined emission level, and determines the final actual execution power by comparing it with a minimum effective power threshold, thereby generating laser emission control commands. Through this method, adaptive and refined control of laser emission power is achieved, effectively ensuring the safety of human eyes and equipment, while also considering the system's performance and reliability under different operating modes and environmental conditions.

[0028] 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 laser emitter control device capable of performing the above functions. This embodiment does not specifically limit the scope of the embodiment. The following description uses a laser emitter control device as an example to illustrate this embodiment and the subsequent embodiments.

[0029] All actions involving the acquisition of signals, information, or data in this application are carried out in accordance with the relevant data protection laws and policies of the country where the application is located, and with the authorization of the owner of the relevant device.

[0030] This application provides a laser emitter emission control method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the laser emitter emission control method of this application.

[0031] In this embodiment, the laser emitter emission control method includes steps S10~S40: Step S10: Extract the instantaneous distance and radial velocity of the target object relative to the laser emitter, as well as the contour feature point set and motion trajectory prediction data of the target object from the original environmental perception data.

[0032] It should be noted that raw environmental perception data refers to unprocessed low-level data collected by sensors such as lidar and cameras; target objects refer to entities within the detection range of the laser emitter that need to be monitored and responded to, such as personnel, vehicles, or other equipment; instantaneous distance and radial velocity represent the real-time straight-line distance between the target and the laser emitter and their approach or departure speed in the line-of-sight direction, respectively; the contour feature point set is a collection of key points describing the geometric features of the target's shape; and motion trajectory prediction data is an estimate of the target's future movement path and position based on its historical motion state.

[0033] In its implementation, the system first processes LiDAR point cloud data and camera image streams in parallel. Individual objects are segmented from the point cloud using clustering algorithms (such as DBSCAN), and instantaneous motion parameters are calculated based on the centroid changes of the targets between consecutive frames. Simultaneously, a trained convolutional neural network (CNN) is used to perform instance segmentation of the images, extracting key points of the target contours. Finally, the historical position sequence of the targets is input into prediction algorithms such as Kalman filtering to generate predicted motion trajectory data for the short term, providing a basis for subsequent risk assessment.

[0034] In one feasible implementation, the step of extracting the instantaneous distance and radial velocity of the target object relative to the laser emitter, as well as the contour feature point set and motion trajectory prediction data of the target object from the original environmental perception data, includes: Extract lidar point cloud data and image data from the raw environmental perception data; Cluster analysis is performed on the lidar point cloud data to obtain the initial point cloud cluster of the target object; Based on the displacement of the center point of the initial point cloud cluster in multiple consecutive frames, the instantaneous distance and radial velocity of the target object relative to the laser emitter are calculated. The image data is subjected to convolutional neural network feature extraction to obtain the contour feature point set of the target object; Historical motion data of the initial point cloud cluster is extracted, and Kalman filtering is performed on the historical motion data to obtain the motion trajectory prediction data of the target object.

[0035] It should be noted that LiDAR point cloud data refers to the set of coordinates of a large number of three-dimensional points in the environment acquired by LiDAR through emitting and receiving laser beams. Each point contains information such as distance, azimuth, and reflection intensity. Image data refers to a two-dimensional pixel array captured by an optical camera, containing information about the target's color, texture, and two-dimensional shape. Center point displacement refers to the change in the position of the geometric center (centroid) of the point cloud cluster of the same target object in two or more consecutive frames of point cloud data.

[0036] In its implementation, the system first receives raw data streams from the LiDAR and camera in parallel. For the LiDAR point cloud, a target segmentation algorithm such as Euclidean clustering is used. The core of this algorithm is to set a distance threshold and group points in space that are less than this threshold into one cluster. For each initial point cloud cluster obtained by clustering, its three-dimensional centroid coordinates are calculated. This represents the instantaneous position of the target. It is achieved by tracking the displacement of the centroid of the same target between consecutive frames (e.g., frame k and frame (k-1)). And combined with the inter-frame time interval The instantaneous distance can then be calculated. and radial velocity .in, These are the three-dimensional coordinates of the target in the current sensor coordinate system. It is the Euclidean distance between the centroids of adjacent frames.

[0037] Simultaneously, image data is fed into a pre-trained convolutional neural network (such as a pose estimation network based on HRNet or CPM). This network outputs the pixel coordinates of a series of key points (such as the corners of the bounding box or feature points of the object) of the target contour, forming a contour feature point set. Finally, to predict the future motion of the target, the system stores the historical position sequence of the target point cloud cluster. (in The observed values ​​are input into a Kalman filter. The Kalman filter dynamically maintains the optimal state estimate of the target through its two core steps: prediction and update. (Typically includes position and velocity), and can extrapolate future states based on the current state and motion model, i.e., motion trajectory prediction data. Its core prediction equation can be simplified to... ,in It is a state transition matrix, which is based on a pre-defined motion model (such as a uniform motion model) and the current optimal state. To predict the optimal state at the next moment. .

[0038] Step S20: The instantaneous distance, radial velocity, contour feature point set, and motion trajectory prediction data are fused to obtain a real-time state vector.

[0039] It should be noted that the real-time state vector is a structured data object, each dimension (element) of which quantitatively describes a key state attribute (such as position, velocity, shape, and future threat level) of the target object in relation to the laser emitter at a specific moment. This vector will serve as the direct input to the subsequent risk assessment model.

[0040] Understandably, the system first preprocesses each input data, performing timestamp alignment and coordinate system normalization to ensure spatiotemporal consistency. Then, scalar data such as instantaneous distance and radial velocity are directly used as the first few dimensions of the vector; the contour feature point set is dimensionality-reduced by calculating the size of its outer rectangle or statistical characteristics between key points (such as maximum width), forming feature dimensions describing the shape; motion trajectory prediction data can extract key indicators such as the minimum relative distance or collision time in the near future. Finally, all these processed and filtered values ​​are sequentially concatenated to form a real-time state vector containing complete dynamic information about the target.

[0041] In one feasible implementation, the step of fusing the instantaneous distance, the radial velocity, the contour feature point set, and the motion trajectory prediction data to obtain the real-time state vector includes: The instantaneous distance and radial velocity are normalized to obtain standardized motion parameters; Principal component analysis is performed on the contour feature point set to extract principal component features representing the target orientation and shape; The motion trajectory prediction data is projected onto the laser emitter coordinate system to obtain a position coordinate sequence; A real-time state vector is generated based on the standardized motion parameters, the principal component features, and the position coordinate sequence.

[0042] It should be noted that the position coordinate sequence refers to the array of three-dimensional coordinates (x, y, z) of the target object relative to the laser emitter at multiple consecutive points in the future, arranged in chronological order. It intuitively describes the predicted motion trajectory.

[0043] Understandably, normalization aims to scale data with different dimensions and numerical ranges (such as distance and velocity) to a uniform interval (e.g., [0,1]) through linear transformation, eliminating orders-of-magnitude differences and ensuring that each feature plays a fair role in the subsequent fusion model. Principal component analysis (PCA) is a classic dimensionality reduction statistical method that transforms a set of potentially correlated variables (such as the numerous coordinates of a contour point set) into a set of linearly uncorrelated principal components through orthogonal transformation. The first few principal components can retain the most significant variance of the original data and are often used to extract the main distribution direction (such as target orientation) and structural features of the data.

[0044] In practical implementation, the core of constructing the real-time state vector is to standardize and structure features of different types and dimensions to form a unified numerical vector. First, the instantaneous distance... and radial velocity Normalization is performed. The system will preset a reasonable maximum value (such as the effective range of the lidar). and the maximum relative speed that the system is concerned with Then use the formula Perform calculations, where The original parameters to be normalized ( or ), and These are its preset upper and lower bounds. This ensures that motion parameters are scaled to a similar numerical range.

[0045] Next, principal component analysis (PCA) is performed on the contour feature point set (a set of two-dimensional or three-dimensional coordinate points). PCA finds the direction with the largest data variance by calculating the eigenvalues ​​and eigenvectors of the covariance matrix. The first principal component eigenvector indicates the longest extension direction of the target, i.e., the target orientation; its corresponding eigenvalue reflects the extent of extension along that direction, characterizing the length information of the target shape. The second principal component represents the second largest extension direction perpendicular to it. Using the orientation angles and principal eigenvalues ​​of these eigenvectors as principal component features can effectively reduce the dimensionality of the contour data while preserving key shape information. Simultaneously, the predicted future trajectory points... Through coordinate transformation matrix Transform to LiDAR coordinate system: The position coordinate sequence is obtained. .

[0046] Finally, a real-time state vector is generated. All the processed features are concatenated into a one-dimensional vector: .in, and These are the normalized motion parameters. It is the target orientation angle obtained from principal component analysis. and The target length and width dimensions are derived from the principal component eigenvalues. It is a future point in time. The sequence of position coordinates. This vector comprehensively represents the target's instantaneous dynamics, shape geometry, and future movement trend.

[0047] Step S30: Calculate multiple predicted position points of the target object within a future preset time period based on the target motion parameters of the real-time state vector, and judge the predicted position points in combination with the pre-stored safe area boundary information to obtain the position judgment result. Determine the laser emission level based on the position judgment result and the target contour features in the real-time state vector.

[0048] It should be noted that the predicted location point is calculated by extrapolation from a kinematic model based on the target's current real-time state vector. The safety zone boundary information refers to one or more predefined three-dimensional spatial regions in the laser emitter coordinate system, used to delineate different safety levels (e.g., prohibited emission zones, warning zones, safe zones). This boundary can be dynamically configured according to human eye safety standards, regulations, and application scenarios. The location determination result is a qualitative or quantitative result obtained by the system after analyzing the spatial relationship between each predicted location point and the safety zone boundary, such as the point being located within a prohibited zone or the point being less than a threshold distance from the boundary. The laser emission level is the power or energy output level that the laser should adopt, determined based on the comprehensive risk assessment results, and is usually a discrete level (e.g., off, low power, high power).

[0049] Understandably, the current velocity, position, and motion model from the real-time state vector are used first (e.g., if uniform motion is assumed, the predicted position is...). ,in Current position For velocity vectors, For future time points, predictive location points are calculated over a future time series. Then, collision detection or inclusion relationship judgment is performed between each predicted location point and the pre-stored safe zone boundary (usually represented as a polygon or geometric object in three-dimensional space) to obtain the location judgment result (e.g., counting how many predicted points fall into the danger zone). Finally, this result is combined with the target contour features (such as size, used to assess the potential hazard level) in the state vector and mapped to a specific laser emission level through a set of preset decision rules or a lightweight classifier.

[0050] In one feasible implementation, the step of calculating multiple predicted location points of the target object within a future preset time period based on the target motion parameters of the real-time state vector includes: The current position coordinates, instantaneous velocity vector, and acceleration estimation vector of the target object are parsed from the target motion parameters of the real-time state vector. Based on the instantaneous velocity vector and the acceleration estimation vector, a kinematic prediction model of the target object in the laser emitter coordinate system is constructed. Based on the kinematic prediction model, starting from the current position coordinates, the target object is discretized within a preset time period in the future using a preset time step, and multiple predicted position points of the target object within the preset time period in the future are obtained through iterative calculation.

[0051] In practical implementation, the core of determining multiple predicted locations of a target object within a preset time period lies in predicting its future trajectory using a mathematical model based on the target object's current motion state. This process begins with the constructed real-time state vector. The key dynamic parameters are extracted from the data. These typically include: Current position coordinates: denoted as a vector , representing the target's position relative to the laser emitter at the current moment.

[0052] Instantaneous velocity vector: denoted as It describes the target's current speed and direction of motion.

[0053] Acceleration estimation vector: denoted as It can be obtained directly from sensor measurements or by differential calculation of velocity vectors from consecutive frames.

[0054] Next, the system constructs a kinematic prediction model based on these parameters. The most commonly used is the uniformly accelerated linear motion model, which assumes that the target maintains its current acceleration during the prediction period. Its general formula is:

[0055] The predicted position coordinates of the target at any future time t (relative to the current time).

[0056] The target's current position coordinates (initial position).

[0057] The instantaneous velocity vector of the target.

[0058] : The target's acceleration estimation vector.

[0059] The future point in time calculated from the current moment.

[0060] Finally, discretized iterative calculations are performed. The system sets a total prediction duration T (e.g., 0.5 seconds) and a time step Δt (e.g., 0.05 seconds). Then, starting from t=Δt, t=Δt, 2Δt, 3Δt, ..., T are successively substituted into the above kinematic model for calculation, thereby obtaining a series of discrete predicted positions P(Δt), P(2Δt), P(3Δt), ..., P(T) at future time points.

[0061] In one feasible implementation, the step of determining the predicted location point by combining pre-stored safe area boundary information to obtain a location determination result, and determining the laser emission level based on the location determination result and the target contour features in the real-time state vector includes: Collision detection is performed between the predicted location points and the pre-stored safe area boundary information to count the number of predicted location points that are completely outside the safe area. Determine the ratio of the number of predicted location points that are completely outside the safe zone to the total number of predicted points, and generate a location judgment result based on the ratio; The principal component coefficients of the target contour features are extracted from the real-time state vector, and the principal component coefficients are matched with a pre-stored friendly target feature library to obtain the target identity confidence score. The laser emission level is determined based on the location determination result and the target identity confidence level.

[0062] It should be noted that collision detection refers to the process of determining whether one or more geometric elements, such as points, lines, or surfaces, intersect or contain the boundary of a safe area through geometric calculations. This is used to determine whether the predicted location point is outside the predefined safe area. The friendly target feature library contains contour feature templates of targets known to be "friendly" or "permissive." Target identity confidence represents the system's level of confidence in whether a currently detected target is a friendly target, based on the degree of matching between its contour features and templates in the friendly target feature library. This value is typically between 0 and 1; a higher value indicates a better match and a greater probability of it being a friendly target. Laser emission level defines the power level or mode that the laser should operate in (e.g., "OFF," "LOW," "HIGH"). This level is the decision output after comprehensively considering the target's future trajectory position determination and the target identity confidence.

[0063] In the specific implementation, firstly, the system calculates each predicted location point... (in , Collision detection is performed on the total number of predicted points. This is typically done using computational geometry algorithms (such as ray casting) to determine whether a point is inside a polygon (2D safe zone) or a polyhedron (3D safe zone). The number of all points falling outside the safe zone is counted and denoted as . Then, the proportion of dangerous points is calculated:

[0064] : Danger point ratio, representing the risk level of the predicted trajectory, with a value range of [0,1].

[0065] The number of points that fall outside the safe zone.

[0066] N: Total number of prediction points.

[0067] This proportion of danger points This is the key location determination result, which quantifies the risk of the target trajectory intruding into the safe area in the future.

[0068] Simultaneously, the system extracts the principal component coefficients of the target contour features from the real-time state vector (for example, the projection coefficients of the first k principal components constitute a feature vector). This feature vector is compared with multiple template feature vectors in the friendly target feature library. ( , Matching is performed based on the number of templates. The degree of matching is typically measured by calculating cosine similarity.

[0069] The cosine similarity between the current target feature and the j-th friendly target template has a value range of [-1, 1]. The closer it is to 1, the more similar the shape and orientation are.

[0070] Feature vectors extracted from the current target contour.

[0071] The j-th template feature vector in the friendly target feature library.

[0072] Take the maximum value among all similarities. It is then mapped or normalized to the [0,1] interval and used as the target identity confidence score. .

[0073] Finally, the system according to and These two inputs determine the laser emission level through a pre-defined decision logic (e.g., a lookup table or fuzzy inference rules). A simplified example of the rule is as follows: like If the risk threshold is high, the launch level will be "off" regardless of the user's identity. If the medium risk threshold High risk threshold and If the confidence threshold is reached, the transmission level will be set to "low power" as a warning. like Very low or If the value is very high, then "high power" operation is allowed.

[0074] In one feasible implementation, before the step of determining the laser emission level based on the location determination result and the target identity confidence level, the method further includes: Determine the confidence level of the motion parameters in the real-time state vector, and calculate the prediction error ellipsoid of the kinematic prediction model at each prediction time step based on the confidence level; Based on the spatial relationship between the prediction error ellipsoid corresponding to all predicted location points and the pre-stored safe area boundary information, the uncertainty of the location judgment result is corrected.

[0075] It should be noted that the confidence level of motion parameters refers to the quantitative assessment of the uncertainty of the estimated values ​​of motion parameters such as position, velocity, and acceleration in the real-time state vector. It reflects the reliability of the parameters due to factors such as sensor measurement noise and model matching errors. The prediction error ellipsoid describes the confidence region in which the true position of the target may deviate from the predicted position at a specific point in the future.

[0076] In practical implementation, the position determination result may be inaccurate due to various reasons. Therefore, to improve decision robustness, a Kalman filter is used to output the confidence level of the motion parameters. It is assumed that the real-time state vector and its estimation uncertainty are determined by a mean state vector. and a covariance matrix Joint description. The elements on the diagonal are the variances of each state variable (including position, velocity, etc.), reflecting their confidence level. The larger the variance, the lower the confidence level.

[0077] Next, the system uses a kinematic model and the law of uncertainty propagation to calculate the prediction error ellipsoid for each prediction time step. For a linear or linearized kinematic model... (in (This is the state transition matrix), and the uncertainty covariance matrix of the prediction step. It can be propagated through the following formula:

[0078] exist The prediction state covariance matrix at time (i.e., the (k+1)th prediction step) defines the prediction error ellipsoid at that time.

[0079] :from arrive The state transition matrix is ​​determined by the kinematic model.

[0080] exist The state covariance matrix at time P0 (initial time P0).

[0081] The process noise covariance matrix represents the uncertainty of the model itself.

[0082] For each prediction time point, the primary concern is the uncertainty of the location component. From the complete... Extract the positional components (e.g., the first 3x3 submatrix). This matrix describes the predicted location points. The surrounding error distribution. An error ellipsoid containing a high probability (e.g., 95%) of the true position is given by the equation Define , where c is a constant related to the selected confidence probability.

[0083] Finally, uncertainty correction is performed based on the error ellipsoid. The original "point" judgment is replaced by a "region" judgment. For each prediction step, the system calculates the spatial relationship between the prediction error ellipsoid and the safe zone boundary. For example, it can assess the probability of the ellipsoid intersecting the safe boundary, or calculate the proportion of the volume within the ellipsoid that lies outside the safe zone. The original binary judgment result (proportion of dangerous points) is now replaced. It can be modified to a risk probability that takes uncertainty into account. ,For example:

[0084] The revised overall risk probability takes into account forecast uncertainty.

[0085] The probability that the actual location is not within the safe zone at the k-th predicted point can be estimated based on the geometric relationship between the error ellipsoid and the safe zone.

[0086] Total number of predicted points.

[0087] This revised This will serve as a more reliable location determination result, which will then be combined with the target identity confidence level to jointly determine the laser emission level, thereby significantly improving the system's safety and reliability in noisy environments.

[0088] In one feasible implementation, after the step of determining the laser emission level based on the location determination result and the target identity confidence level, the method further includes: Real-time acquisition of current atmospheric turbulence intensity and visibility parameters; The target identity confidence score is attenuated and corrected based on the atmospheric turbulence intensity to obtain the corrected target identity confidence score. The location determination result is weighted and adjusted according to the visibility parameter to obtain the weighted and adjusted location determination result. The compensated laser emission level is determined using the corrected target identity confidence level and the weighted adjusted position judgment result.

[0089] It should be noted that atmospheric turbulence intensity describes a physical quantity that describes the random fluctuations in the refractive index of air caused by uneven temperature and pressure in the atmosphere, and the refractive index structure constant is commonly used. or its logarithmic form (e.g.) (This is represented by the symbol ). High turbulence intensity can cause laser beam expansion, drift, and flicker, reducing image quality and thus affecting the accuracy of target recognition based on contour features. The visibility parameter refers to the maximum horizontal distance at which a target can be distinguished from the background by normal human vision. Low visibility is usually caused by meteorological conditions such as fog, haze, rain, and snow, which can lead to increased laser transmission attenuation, shorten the effective range, and affect the reliability of accurate detection and prediction of target location.

[0090] In practical implementation, the system needs to acquire real-time atmospheric turbulence intensity and visibility parameters. This can be achieved through real-time measurements using meteorological sensors integrated into the laser emission platform (such as scatterometers to measure visibility, scintillators, or temperature difference sensors to indirectly estimate turbulence intensity), or by receiving data from external meteorological observation stations via a data link. Let the turbulence intensity parameter be... (For example, after normalization) (Value), visibility parameter is (Unit: meters)

[0091] First, the target identity confidence is attenuated and corrected based on the intensity of atmospheric turbulence. Turbulence causes blurring and distortion of the acquired target contour image, significantly reducing the reliability of feature extraction and matching. The correction function can be designed as a decay factor that monotonically decreases with increasing turbulence intensity. The corrected target identity confidence is then calculated. It can be calculated as:

[0092] Target identity confidence after turbulence attenuation correction.

[0093] Original target identity confidence level.

[0094] The turbulence attenuation factor is a function of the turbulence intensity TI, and its value range is typically (0,1). For example, Where k is the empirical attenuation coefficient. When TI is large ( When the current is very strong, A value close to 0 indicates poor image quality, unreliable identity recognition results, and a significant reduction in confidence.

[0095] Secondly, the location assessment results are weighted and adjusted based on visibility parameters. Low visibility means increased atmospheric attenuation of laser light, a shorter effective detection range, and potentially increased ranging errors, thus affecting the accuracy of trajectory prediction. Therefore, location risk assessments based on predicted trajectories should be approached with greater caution in low visibility conditions. The weighting adjustment can be reflected in the proportion of risk. Visibility-based weighted scaling is applied. The resulting position determination is after weighted adjustment. It can be represented as:

[0096] Location determination result after visibility weighting adjustment.

[0097] Original position determination result.

[0098] The visibility weighting factor is a function of visibility (VIS). Its design should ensure that under good visibility (high VIS value), Trust the original judgment; when visibility is poor (VIS value is low), This amplifies the risk assessment value and reflects the principle of prudence. For example, ,in To adjust the coefficients, the system ultimately uses the corrected target identity confidence score. and the position judgment result after weighted adjustment The original decision-making logic is then applied again to determine the compensated laser emission level. This process enables the laser emission control strategy to dynamically adapt to changes in the external atmospheric environment, automatically adopting a more conservative operating mode under severe weather conditions, further enhancing the overall safety and environmental robustness of the system.

[0099] Step S40: Determine the maximum allowable emission power value according to the energy level mapping table and the laser emission level; determine the actual execution power by using the maximum allowable emission power value and the preset minimum effective power threshold; and generate a laser emission control command based on the actual execution power.

[0100] It should be noted that the energy level mapping table maps different laser emission levels to corresponding specific power values ​​or power ranges, transforming abstract decision levels into executable physical quantities. The maximum permissible emission power value refers to the upper limit of the maximum output power allowed under the current laser emission level, based on the energy level mapping table and possible safety rules. The preset minimum effective power threshold is the lowest power limit that must be met for the laser to achieve the desired effect; emission below this threshold is considered invalid or a safety redundancy operation. The actual execution power is a specific power setting value between the maximum permissible emission power and the minimum effective power, designed to ensure effectiveness while adhering to safety limits. Laser emission control commands are used to directly drive the laser's control system, causing it to operate at the set power level.

[0101] Understandably, the system first queries a pre-built energy level mapping table and retrieves the corresponding maximum allowable emission power value (e.g., based on the determined laser emission level (e.g., "HIGH")) ), and then, this Compared with the system's preset minimum effective power threshold ( ) compare: if Less than This indicates that valid transmission is not permitted under current safety rules, in which case the actual execution power is set to 0 (i.e., off); otherwise, the actual execution power is usually set to [value missing]. Or one in The value selected within the interval based on the strategy (e.g., directly taking) (To maximize efficiency). Finally, the system generates a laser emission control command containing this actual executed power value and sends it to the laser driver module to perform power control.

[0102] In one feasible implementation, the steps of determining the maximum allowable emission power value based on the energy level mapping table and the laser emission level, determining the actual execution power by comparing the maximum allowable emission power value with a preset minimum effective power threshold, and generating laser emission control commands based on the actual execution power include: Based on the current operating mode and power consumption limits, the power reference value in the energy level mapping table is dynamically adjusted to obtain the dynamically adjusted energy level mapping table. Using the laser emission level as an index, the maximum allowable emission power value is obtained by querying the dynamically adjusted energy level mapping table. Compare the maximum allowable transmit power value with the preset minimum effective power threshold; When the maximum allowable transmission power value is greater than the preset minimum effective power threshold, the maximum allowable transmission power value is taken as the actual execution power; Laser emission control commands are generated based on the actual execution power.

[0103] It should be noted that the operating mode refers to the current task stage or operating configuration of the laser system, such as "search mode", "tracking mode", "standby mode" or "power saving mode".

[0104] In the specific implementation, refer to Figure 2 , Figure 2 This is a schematic diagram of the instruction generation process. The system first dynamically adjusts the power baseline value in the energy level mapping table based on the current operating mode and power consumption limitations. (Basic energy level mapping table) The reference power corresponding to each transmission level L in standard mode is defined. (For example, , Dynamic adjustment aims to generate a mapping table that adapts to real-time constraints. The adjustment strategy can be modeled as a function, the core of which is to calculate a dynamic adjustment factor. Then, the reference power for each level is scaled:

[0105] The allowed power value corresponding to level L in the dynamically adjusted mapping table is the entry in the new mapping table.

[0106] : The base power of level L in the basic mapping table.

[0107] The absolute maximum power allowed by the laser subsystem's hardware is a fixed safety limit.

[0108] Scaling factor based on operating mode. For example, in "Power Saving Mode", It can be set to 0.5, halving the power requirements for all levels; in "High Precision Tracking Mode", It may be 1.0 or slightly higher than 1.0 (if conditions permit).

[0109] : A scaling factor based on power consumption constraints. If the total available power of the system... Tension, this factor can be calculated as:

[0110] Ensure that the total power requirements of all levels after adjustment do not exceed the system budget.

[0111] Subsequently, the system uses the laser emission level as an index to query the dynamically adjusted energy level mapping table to obtain the maximum allowable emission power value. Next, a comparison. With preset minimum effective power threshold .when Greater than This indicates that under the current constraints, it is both safe and effective, therefore... Directly used as actual execution power This strategy prioritizes maximizing the effectiveness of the laser within safety limits.

[0112] Ultimately, the system determines the power output based on the actual execution power. Generate laser emission control commands. These commands are typically a set of commands containing the target power value. The digital or analog signal is sent to the laser's power drive circuitry, thereby precisely controlling the laser's output intensity. This dynamic adjustment mechanism ensures that laser power management can flexibly adapt to changes in internal resource status and external task requirements.

[0113] In one feasible implementation, the step of dynamically adjusting the power reference value in the energy level mapping table according to the current operating mode and power consumption limitations to obtain the dynamically adjusted energy level mapping table includes: Obtain the current thermal load parameters and remaining battery power, and calculate the real-time maximum support power of the system based on the thermal load parameters and remaining battery power; Based on the priority weight corresponding to the current working mode, the initial power reference value associated with each laser emission level in the energy level mapping table is scaled proportionally to obtain the power reference value after mode adjustment. The power reference value after mode adjustment is compared with the maximum power that the system can support, and the smaller value between the power reference value after mode adjustment and the maximum power that the system can support is taken as the target safe power limit. The energy level mapping table is dynamically adjusted based on the target safe power limit to obtain a dynamically adjusted energy level mapping table.

[0114] It should be noted that thermal load parameters refer to the accumulated heat or temperature index generated by the laser and surrounding devices during operation, usually measured by a temperature sensor. Excessive thermal load can affect laser performance, lifespan, and even cause hardware damage. Remaining battery capacity refers to the percentage or absolute value of the system's current available battery charge capacity, usually expressed as a percentage or voltage. In low-battery states, power output needs to be limited to extend system runtime or prevent over-discharge of the battery. Initial power reference value refers to the nominal power value corresponding to each laser emission level, predefined in the energy level mapping table, without considering real-time system status and operating mode.

[0115] In the actual implementation, the system first needs to obtain the current thermal load parameters and the remaining battery power. Thermal load parameters This can be the core temperature (unit: °C) or the remaining battery capacity. Typically expressed as a percentage (0-100%). The maximum power that a real-time system can support. It is calculated using a function that comprehensively considers thermal and electrical constraints, for example:

[0116] The calculated maximum power that the system can support.

[0117] The maximum nominal power of a laser under rated, ideal conditions.

[0118] The heat reduction factor is about The decreasing function approaches 0 as the temperature nears the safe upper limit, severely limiting power.

[0119] The derating factor is about The decreasing function is used to save energy and protect the battery when power is low.

[0120] Next, the system determines the priority weight corresponding to the current working mode. The initial power reference value associated with each laser emission level in the energy level mapping table. Perform scaling. Power reference value after mode adjustment. The calculation is as follows:

[0121] The power reference value of level L after mode adjustment.

[0122] The initial power reference value for level L.

[0123] : The priority weight of the current working mode (e.g., emergency tracking mode may be 1.2, and energy saving mode may be 0.7).

[0124] Then the system will and The two values ​​are compared, and the smaller value is taken as the target safe power limit for that level. :

[0125] This minimum value operation ensures that the final power setting meets the needs of the current task mode without exceeding the safe tolerance of the system hardware (thermal and electrical) under the current condition.

[0126] Ultimately, based on the calculated target safe power limit for each level... The energy level mapping table is updated to generate a dynamically adjusted energy level mapping table. This new mapping table will be used in subsequent steps to determine the specific transmission power, enabling power management to adapt to the system's internal state (thermal and electrical) and external mission requirements (operating mode).

[0127] This embodiment provides a laser emitter emission control method. It extracts the target's instantaneous distance, radial velocity, contour feature point set, and motion trajectory prediction data from raw environmental perception data. These data are fused to generate a real-time state vector. Based on the target's motion parameters, multiple position points within a future timeframe are predicted. Position safety is assessed by combining this with pre-stored safety zone boundaries, and the laser emission level is determined jointly with the target's contour features. The maximum allowable emission power is obtained based on an energy level mapping table and the determined emission level. The final actual execution power is determined by comparing this power with a minimum effective power threshold, thereby generating a laser emission control command. This method achieves adaptive and refined control of the laser emission power, effectively ensuring the safety of human eyes and equipment, while also considering the system's performance and reliability under different operating modes and environmental conditions.

[0128] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the laser emitter emission control method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0129] This application also provides a laser emitter emission control system; please refer to... Figure 3 The laser emitter emission control system includes: Information extraction module 10 is used to extract the instantaneous distance and radial velocity of the target object relative to the laser emitter, as well as the contour feature point set and motion trajectory prediction data of the target object from the original environmental perception data; State fusion module 20 is used to fuse the instantaneous distance, the radial velocity, the contour feature point set and the motion trajectory prediction data to obtain a real-time state vector; The evaluation and decision module 30 is used to calculate multiple predicted position points of the target object within a future preset time period based on the target motion parameters of the real-time state vector, judge the predicted position points in combination with the pre-stored safe area boundary information, obtain the position judgment result, and determine the laser emission level based on the position judgment result and the target contour features in the real-time state vector. The power control module 40 is used to determine the maximum allowable emission power value according to the energy level mapping table and the laser emission level, determine the actual execution power by the maximum allowable emission power value and the preset minimum effective power threshold, and generate laser emission control commands according to the actual execution power.

[0130] In one feasible implementation, the information extraction module 10 is further used to extract lidar point cloud data and image data from the original environmental perception data; Cluster analysis is performed on the lidar point cloud data to obtain the initial point cloud cluster of the target object; Based on the displacement of the center point of the initial point cloud cluster in multiple consecutive frames, the instantaneous distance and radial velocity of the target object relative to the laser emitter are calculated. The image data is subjected to convolutional neural network feature extraction to obtain the contour feature point set of the target object; Historical motion data of the initial point cloud cluster is extracted, and Kalman filtering is performed on the historical motion data to obtain the motion trajectory prediction data of the target object.

[0131] In one feasible implementation, the state fusion module 20 is further configured to normalize the instantaneous distance and the radial velocity to obtain standardized motion parameters. Principal component analysis is performed on the contour feature point set to extract principal component features representing the target orientation and shape; The motion trajectory prediction data is projected onto the laser emitter coordinate system to obtain a position coordinate sequence; A real-time state vector is generated based on the standardized motion parameters, the principal component features, and the position coordinate sequence.

[0132] In one feasible implementation, the evaluation decision module 30 is further configured to parse the current position coordinates, instantaneous velocity vector and acceleration estimation vector of the target object from the target motion parameters of the real-time state vector; Based on the instantaneous velocity vector and the acceleration estimation vector, a kinematic prediction model of the target object in the laser emitter coordinate system is constructed. Based on the kinematic prediction model, starting from the current position coordinates, the target object is discretized within a preset time period in the future using a preset time step, and multiple predicted position points of the target object within the preset time period in the future are obtained through iterative calculation.

[0133] In one feasible implementation, the evaluation decision module 30 is further configured to perform collision detection between the predicted location point and the pre-stored safe area boundary information, and count the number of predicted location points that are completely outside the safe area. Determine the ratio of the number of predicted location points that are completely outside the safe zone to the total number of predicted points, and generate a location judgment result based on the ratio; The principal component coefficients of the target contour features are extracted from the real-time state vector, and the principal component coefficients are matched with a pre-stored friendly target feature library to obtain the target identity confidence score. The laser emission level is determined based on the location determination result and the target identity confidence level.

[0134] In one feasible implementation, the evaluation decision module 30 is further configured to determine the confidence level of the motion parameters in the real-time state vector, and calculate the prediction error ellipsoid of the kinematic prediction model at each prediction time step based on the confidence level. Based on the spatial relationship between the prediction error ellipsoid corresponding to all predicted location points and the pre-stored safe area boundary information, the uncertainty of the location judgment result is corrected.

[0135] In one feasible implementation, the evaluation and decision module 30 is also used to acquire the current atmospheric turbulence intensity and visibility parameters in real time; The target identity confidence score is attenuated and corrected based on the atmospheric turbulence intensity to obtain the corrected target identity confidence score. The location determination result is weighted and adjusted according to the visibility parameter to obtain the weighted and adjusted location determination result. The compensated laser emission level is determined using the corrected target identity confidence level and the weighted adjusted position judgment result.

[0136] In one feasible implementation, the power control module 40 is further configured to dynamically adjust the power reference value in the energy level mapping table according to the current operating mode and power consumption limit, so as to obtain a dynamically adjusted energy level mapping table. Using the laser emission level as an index, the maximum allowable emission power value is obtained by querying the dynamically adjusted energy level mapping table. Compare the maximum allowable transmit power value with the preset minimum effective power threshold; When the maximum allowable transmission power value is greater than the preset minimum effective power threshold, the maximum allowable transmission power value is taken as the actual execution power; Laser emission control commands are generated based on the actual execution power.

[0137] In one feasible implementation, the power control module 40 is further configured to acquire the current thermal load parameters and the remaining battery power, and calculate the real-time maximum system power based on the thermal load parameters and the remaining battery power. Based on the priority weight corresponding to the current working mode, the initial power reference value associated with each laser emission level in the energy level mapping table is scaled proportionally to obtain the power reference value after mode adjustment. The power reference value after mode adjustment is compared with the maximum power that the system can support, and the smaller value between the power reference value after mode adjustment and the maximum power that the system can support is taken as the target safe power limit. The energy level mapping table is dynamically adjusted based on the target safe power limit to obtain a dynamically adjusted energy level mapping table.

[0138] The laser emitter emission control system provided in this application, employing the laser emitter emission control method described in the above embodiments, can solve the technical problems of lack of intelligence and safety in laser power control. Compared with the prior art, the beneficial effects of the laser emitter emission control system provided in this application are the same as those of the laser emitter emission control method provided in the above embodiments, and other technical features in the laser emitter emission control system are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0139] This application provides a laser emitter emission control 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 laser emitter emission control method in the above embodiment 1.

[0140] The following is for reference. Figure 4 The diagram illustrates a structural schematic suitable for implementing a laser emitter emission control device according to embodiments of this application. The laser emitter emission control device in embodiments of this application 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), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 4 The laser emitter emission control device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0141] like Figure 4As shown, the laser emitter emission control 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 ROM (Read Only Memory) 1002 or a program loaded from storage device 1003 into RAM (Random Access Memory) 1004. RAM 1004 also stores various programs and data required for the operation of the laser emitter emission control device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via bus 1005. 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, touch screens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, LCDs (Liquid Crystal Displays), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. The communication device 1009 allows the laser emitter control equipment to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows laser emitter control equipment with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0142] 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.

[0143] The laser emitter emission control device provided in this application, employing the laser emitter emission control method in the above embodiments, can solve the technical problem of laser emitter emission control. Compared with the prior art, the beneficial effects of the laser emitter emission control device provided in this application are the same as those of the laser emitter emission control method provided in the above embodiments, and other technical features in this laser emitter emission control device are the same as those disclosed in the method of the previous embodiment, and will not be repeated here.

[0144] 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.

[0145] The above are merely specific embodiments 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.

[0146] 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 laser emitter emission control method in the above embodiments.

[0147] 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, RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable Read Only Memory or Flash Memory), optical fibers, CD-ROM (CD-Read Only Memory), 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.

[0148] The aforementioned computer-readable storage medium may be included in the laser emitter emission control device; or it may exist independently and not assembled into the laser emitter emission control device.

[0149] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the laser emitter emission control device, cause the laser emitter emission control device to: extract from the original environmental perception data the instantaneous distance and radial velocity of the target object relative to the laser emitter, as well as the contour feature point set and motion trajectory prediction data of the target object; A real-time state vector is obtained by fusing the instantaneous distance, the radial velocity, the contour feature point set, and the motion trajectory prediction data; Based on the target motion parameters of the real-time state vector, calculate multiple predicted position points of the target object within a future preset time period, combine the pre-stored safe area boundary information to judge the predicted position points, obtain the position judgment result, and determine the laser emission level based on the position judgment result and the target contour features in the real-time state vector. The maximum allowable emission power value is determined based on the energy level mapping table and the laser emission level. The actual execution power is determined by the maximum allowable emission power value and the preset minimum effective power threshold. Laser emission control commands are generated based on the actual execution power.

[0150] 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++, as well as 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 LAN (Local Area Network) or WAN (Wide Area Network)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0151] 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.

[0152] 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.

[0153] 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 laser emitter emission control method, thereby solving the technical problem of laser emitter emission control. 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 laser emitter emission control method provided in the above embodiments, and will not be repeated here.

[0154] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the laser emitter emission control method described above.

[0155] The computer program product provided in this application can solve the technical problem of laser emitter emission control. 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 laser emitter emission control method provided in the above embodiments, and will not be repeated here.

[0156] The above are only some embodiments of this application and do 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 laser emitter emission control method, characterized in that, The laser emitter emission control method includes: The instantaneous distance and radial velocity of the target object relative to the laser emitter, as well as the contour feature point set and motion trajectory prediction data of the target object, are extracted from the original environmental perception data. A real-time state vector is obtained by fusing the instantaneous distance, the radial velocity, the contour feature point set, and the motion trajectory prediction data; Based on the target motion parameters of the real-time state vector, calculate multiple predicted position points of the target object within a future preset time period, combine the pre-stored safe area boundary information to judge the predicted position points, obtain the position judgment result, and determine the laser emission level based on the position judgment result and the target contour features in the real-time state vector. The maximum allowable emission power value is determined according to the energy level mapping table and the laser emission level. The actual execution power is determined by the maximum allowable emission power value and the preset minimum effective power threshold. A laser emission control command is generated according to the actual execution power. The steps of extracting the instantaneous distance and radial velocity of the target object relative to the laser emitter, as well as the contour feature point set and motion trajectory prediction data of the target object from the original environmental perception data, include: Extract lidar point cloud data and image data from the raw environmental perception data; Cluster analysis is performed on the lidar point cloud data to obtain the initial point cloud cluster of the target object; Based on the displacement of the center point of the initial point cloud cluster in multiple consecutive frames, the instantaneous distance and radial velocity of the target object relative to the laser emitter are calculated. The image data is subjected to convolutional neural network feature extraction to obtain the contour feature point set of the target object; Historical motion data of the initial point cloud cluster is extracted, and Kalman filtering is performed on the historical motion data to obtain the motion trajectory prediction data of the target object; The steps of determining the laser emission level based on the predicted location point by combining pre-stored safe zone boundary information to obtain a location determination result, and the target contour features in the real-time state vector, include: Collision detection is performed between the predicted location points and the pre-stored safe area boundary information to count the number of predicted location points that are completely outside the safe area. Determine the ratio of the number of predicted location points that are completely outside the safe zone to the total number of predicted points, and generate a location judgment result based on the ratio; The principal component coefficients of the target contour features are extracted from the real-time state vector, and the principal component coefficients are matched with a pre-stored friendly target feature library to obtain the target identity confidence score. The laser emission level is determined based on the location determination result and the target identity confidence level; Before the step of determining the laser emission level based on the location determination result and the target identity confidence level, the method further includes: Determine the confidence level of the motion parameters in the real-time state vector, and calculate the prediction error ellipsoid of the kinematic prediction model at each prediction time step based on the confidence level; Based on the spatial relationship between the prediction error ellipsoid corresponding to all predicted location points and the pre-stored safe area boundary information, the uncertainty of the location judgment result is corrected. After the step of determining the laser emission level based on the location determination result and the target identity confidence level, the method further includes: Real-time acquisition of current atmospheric turbulence intensity and visibility parameters; The target identity confidence score is attenuated and corrected based on the atmospheric turbulence intensity to obtain the corrected target identity confidence score. The location determination result is weighted and adjusted according to the visibility parameter to obtain the weighted and adjusted location determination result. The compensated laser emission level is determined using the corrected target identity confidence level and the weighted adjusted position judgment result.

2. The method as described in claim 1, characterized in that, The step of fusing the instantaneous distance, the radial velocity, the contour feature point set, and the motion trajectory prediction data to obtain the real-time state vector includes: The instantaneous distance and radial velocity are normalized to obtain standardized motion parameters; Principal component analysis is performed on the contour feature point set to extract principal component features representing the target orientation and shape; The motion trajectory prediction data is projected onto the laser emitter coordinate system to obtain a position coordinate sequence; A real-time state vector is generated based on the standardized motion parameters, the principal component features, and the position coordinate sequence.

3. The method as described in claim 1, characterized in that, The steps of calculating multiple predicted location points of the target object within a future preset time period based on the target motion parameters of the real-time state vector include: The current position coordinates, instantaneous velocity vector, and acceleration estimation vector of the target object are parsed from the target motion parameters of the real-time state vector. Based on the instantaneous velocity vector and the acceleration estimation vector, a kinematic prediction model of the target object in the laser emitter coordinate system is constructed. Based on the kinematic prediction model, starting from the current position coordinates, the target object is discretized within a preset time period in the future using a preset time step, and multiple predicted position points of the target object within the preset time period in the future are obtained through iterative calculation.

4. The method as described in claim 1, characterized in that, The steps of determining the maximum allowable emission power value based on the energy level mapping table and the laser emission level, determining the actual execution power by comparing the maximum allowable emission power value with a preset minimum effective power threshold, and generating laser emission control commands based on the actual execution power include: Based on the current operating mode and power consumption limits, the power reference value in the energy level mapping table is dynamically adjusted to obtain the dynamically adjusted energy level mapping table. Using the laser emission level as an index, the maximum allowable emission power value is obtained by querying the dynamically adjusted energy level mapping table. Compare the maximum allowable transmit power value with the preset minimum effective power threshold; When the maximum allowable transmission power value is greater than the preset minimum effective power threshold, the maximum allowable transmission power value is taken as the actual execution power; Laser emission control commands are generated based on the actual execution power.

5. The method as described in claim 4, characterized in that, The step of dynamically adjusting the power reference value in the energy level mapping table according to the current operating mode and power consumption limitations to obtain the dynamically adjusted energy level mapping table includes: Obtain the current thermal load parameters and remaining battery power, and calculate the real-time maximum support power of the system based on the thermal load parameters and remaining battery power; Based on the priority weight corresponding to the current working mode, the initial power reference value associated with each laser emission level in the energy level mapping table is scaled proportionally to obtain the power reference value after mode adjustment. The power reference value after mode adjustment is compared with the maximum power that the system can support, and the smaller value between the power reference value after mode adjustment and the maximum power that the system can support is taken as the target safe power limit. The energy level mapping table is dynamically adjusted based on the target safe power limit to obtain a dynamically adjusted energy level mapping table.

6. A laser emitter emission control system, characterized in that, The laser emitter emission control system includes: The information extraction module is used to extract the instantaneous distance and radial velocity of the target object relative to the laser emitter, as well as the contour feature point set and motion trajectory prediction data of the target object from the original environmental perception data; The state fusion module is used to fuse the instantaneous distance, the radial velocity, the contour feature point set, and the motion trajectory prediction data to obtain a real-time state vector; The evaluation and decision module is used to calculate multiple predicted position points of the target object within a future preset time period based on the target motion parameters of the real-time state vector, judge the predicted position points in combination with the pre-stored safe area boundary information, obtain the position judgment result, and determine the laser emission level based on the position judgment result and the target contour features in the real-time state vector. The power control module is used to determine the maximum allowable emission power value according to the energy level mapping table and the laser emission level, determine the actual execution power by the maximum allowable emission power value and the preset minimum effective power threshold, and generate laser emission control commands according to the actual execution power. The steps of extracting the instantaneous distance and radial velocity of the target object relative to the laser emitter, as well as the contour feature point set and motion trajectory prediction data of the target object from the original environmental perception data, include: Extract lidar point cloud data and image data from the raw environmental perception data; Cluster analysis is performed on the lidar point cloud data to obtain the initial point cloud cluster of the target object; Based on the displacement of the center point of the initial point cloud cluster in multiple consecutive frames, the instantaneous distance and radial velocity of the target object relative to the laser emitter are calculated. The image data is subjected to convolutional neural network feature extraction to obtain the contour feature point set of the target object; Historical motion data of the initial point cloud cluster is extracted, and Kalman filtering is performed on the historical motion data to obtain the motion trajectory prediction data of the target object; The steps of determining the laser emission level based on the predicted location point by combining pre-stored safe zone boundary information to obtain a location determination result, and the target contour features in the real-time state vector, include: Collision detection is performed between the predicted location points and the pre-stored safe area boundary information to count the number of predicted location points that are completely outside the safe area. Determine the ratio of the number of predicted location points that are completely outside the safe zone to the total number of predicted points, and generate a location judgment result based on the ratio; The principal component coefficients of the target contour features are extracted from the real-time state vector, and the principal component coefficients are matched with a pre-stored friendly target feature library to obtain the target identity confidence score. The laser emission level is determined based on the location determination result and the target identity confidence level; Before the step of determining the laser emission level based on the location determination result and the target identity confidence level, the method further includes: Determine the confidence level of the motion parameters in the real-time state vector, and calculate the prediction error ellipsoid of the kinematic prediction model at each prediction time step based on the confidence level; Based on the spatial relationship between the prediction error ellipsoid corresponding to all predicted location points and the pre-stored safe area boundary information, the uncertainty of the location judgment result is corrected. After the step of determining the laser emission level based on the location determination result and the target identity confidence level, the method further includes: Real-time acquisition of current atmospheric turbulence intensity and visibility parameters; The target identity confidence score is attenuated and corrected based on the atmospheric turbulence intensity to obtain the corrected target identity confidence score. The location determination result is weighted and adjusted according to the visibility parameter to obtain the weighted and adjusted location determination result. The compensated laser emission level is determined using the corrected target identity confidence level and the weighted adjusted position judgment result.

Images