A path planning method

Abstract

The present disclosure provides a path planning method, which relates to the field of electric power aerial work. The method can generate a first path planning result and a second path planning result based on the environmental parameters of the aerial work, so that workers can perform aerial work more efficiently and safely. The method includes: obtaining the environmental parameters of the aerial work, the environmental parameters including at least three-dimensional terrain parameters, obstacle parameters, and weather parameters; constructing a target environment model corresponding to the aerial work based on the environmental parameters; analyzing the target environment model to obtain a safety risk level corresponding to the target environment model; and determining a first path planning result and a second path planning result corresponding to the target environment model based on the target environment model and the safety risk level, wherein the first path planning result has a higher priority than the second path planning result.

Description

Technical Field

[0001] The present disclosure relates to the field of electric power climbing operations, and in particular to a path planning method. Background Art

[0002] During electrical power installations, workers must move from one location to another to complete their tasks. However, the environment in which these operations occur is often complex and changeable, potentially impacted by factors such as weather conditions, equipment status, and operating conditions. Planning an optimal path within these complex and changing circumstances to ensure workers can complete their tasks efficiently and safely is a pressing issue. Summary of the Invention

[0003] The present disclosure provides a path planning method that can generate a first path planning result and a second path planning result according to environmental parameters of the altitude operation, so that operators can perform altitude operations more efficiently and safely.

[0004] To achieve the above objectives, the present disclosure adopts the following technical solutions:

[0005] In a first aspect, the present disclosure provides a path planning method, which is applied to electronic equipment, including: obtaining environmental parameters for climbing operations, the environmental parameters including at least three-dimensional terrain parameters, obstacle parameters and weather parameters; based on the environmental parameters, constructing a target environment model corresponding to the climbing operation; analyzing the target environment model to obtain a safety risk level corresponding to the target environment model; based on the target environment model and the safety risk level, determining a first path planning result and a second path planning result corresponding to the target environment model, wherein the priority of the first path planning result is higher than that of the second path planning result.

[0006] Based on the path planning method of the first aspect, after obtaining the environmental parameters for the height-ascending operation, a target environment model can be constructed based on these environmental parameters. This target environment model is then analyzed to determine the safety risk level. Finally, based on the target environment model and the safety risk level, a path planning result corresponding to the target environment model is obtained. This not only ensures efficient operation but also enhances operational safety.

[0007] In combination with the first aspect, in another possible implementation method, based on the target environment model and the safety risk level, determining the first path planning result and the second path planning result corresponding to the target environment model, including: inputting the target environment model and the safety risk level into the prediction model, and the prediction model outputting the first path planning result corresponding to the target environment model, wherein the first path planning result includes at least one first time step and at least one first execution action information, and one first time step corresponds to one first execution action information; based on the target environment model, determining the second path planning result corresponding to the target environment model, the second path planning result includes at least one second time step and at least one second execution action information, and one second time step corresponds to one second execution action information.

[0008] In combination with the first aspect, in another possible implementation method, the method also includes: using a sensor to obtain an action feedback result corresponding to at least one execution action; the action feedback result includes whether an obstacle is detected and whether the target position is reached; at least one execution action is an execution action in the first execution action information, or an execution action in the second execution action information; the reinforcement learning algorithm in the prediction model updates the neural network parameters in the prediction model according to the action feedback result corresponding to the at least one execution action to obtain an updated prediction model.

[0009] In combination with the first aspect, in another possible implementation method, based on the target environment model, determining the second path planning result corresponding to the target environment model includes: obtaining a path configuration library; the path configuration library includes multiple preset environments and preset paths corresponding to each preset environment; based on the target environment model, dividing the target environment model into at least one environment area; comparing at least one environment area with multiple preset environments, and determining the target preset environment that matches the at least one environment area; determining the preset path corresponding to the target preset environment as the second path planning result corresponding to the target environment model.

[0010] In combination with the first aspect, in another possible implementation, the environmental parameters may further include device parameters and safety parameters; and the execution action information includes action direction, action angle, and action quantity.

[0011] In combination with the first aspect, in another possible implementation method, the method also includes: monitoring whether the environmental parameters of the climbing operation and the behavioral data of the operator exceed the threshold; when the environmental parameters exceed the first threshold or the behavioral data of the operator exceeds the second threshold, outputting a warning information, the warning information is used to prompt the operation according to the second path planning result; the warning information includes the second path planning result; the second path planning result is obtained based on historical safe operation cases.

[0012] In combination with the first aspect, in another possible implementation method, a target environment model is constructed based on environmental parameters, including: preprocessing the environmental parameters to obtain processed environmental parameters, the preprocessing including data cleaning, data conversion and data labeling; inputting the processed environmental parameters into a preset engine, and the preset engine outputting the target environment model.

[0013] In a second aspect, embodiments of the present disclosure provide a path planning device that can be applied to an electronic device to implement the method described in the first aspect. The functions of the path planning device can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions, such as an acquisition module, a construction module, and a determination module.

[0014] Among them, the acquisition module is configured to obtain the environmental parameters of the climbing operation, and the environmental parameters include at least three-dimensional terrain parameters, obstacle parameters and weather parameters; the construction module is configured to construct a target environment model corresponding to the climbing operation based on the environmental parameters; the determination module is configured to analyze the target environment model and obtain the safety risk level corresponding to the target environment model; and based on the target environment model and the safety risk level, determine the first path planning result and the second path planning result corresponding to the target environment model, wherein the priority of the first path planning result is higher than that of the second path planning result.

[0015] In combination with the second aspect, in a possible implementation method, the determination module is also configured to input the target environment model and the safety risk level into the prediction model, and the prediction model outputs a first path planning result corresponding to the target environment model, wherein the first path planning result includes at least one first time step and at least one first execution action information, and one first time step corresponds to one first execution action information; based on the target environment model, the second path planning result corresponding to the target environment model is determined, and the second path planning result includes at least one second time step and at least one second execution action information, and one second time step corresponds to one second execution action information.

[0016] In combination with the second aspect, in one possible implementation, the acquisition module is further configured to use a sensor to obtain an action feedback result corresponding to at least one execution action; the action feedback result includes whether an obstacle is detected and whether the target position is reached; at least one execution action is an execution action in the first execution action information, or an execution action in the second execution action information; the determination module is further configured to update the neural network parameters in the prediction model according to the action feedback result corresponding to at least one execution action by the reinforcement learning algorithm in the prediction model to obtain an updated prediction model.

[0017] In combination with the second aspect, in a possible implementation method, the determination module is further configured to obtain a path configuration library; the path configuration library includes multiple preset environments and preset paths corresponding to each preset environment; based on the target environment model, the target environment model is divided into at least one environmental area; the at least one environmental area is compared with the multiple preset environments to determine the target preset environment that matches the at least one environmental area; the preset path corresponding to the target preset environment is determined as the second path planning result corresponding to the target environment model.

[0018] In conjunction with the second aspect, in a possible implementation, the environmental parameters may further include device parameters and safety parameters; and the execution action information includes action direction, action angle, and action quantity.

[0019] In conjunction with the second aspect, in one possible implementation, the path planning device further includes a monitoring module and an output module. The monitoring module is configured to monitor whether environmental parameters of the height-based operation and the operator's behavioral data exceed thresholds; the output module is configured to output a warning message when an environmental parameter exceeds a first threshold or the operator's behavioral data exceeds a second threshold, the warning message being used to prompt the operator to operate according to the second path planning result; the warning message includes the second path planning result; and the second path planning result is obtained based on historical safe operation cases.

[0020] In combination with the second aspect, in a possible implementation method, the construction module is also configured to preprocess the environmental parameters to obtain processed environmental parameters, and the preprocessing includes data cleaning, data conversion and data labeling; the processed environmental parameters are input into the preset engine, and the preset engine outputs the target environment model.

[0021] In combination with the second aspect, in one possible implementation, the determination module is further configured to set risk factors based on environmental parameters, the risk factors including the distribution of obstacles, the complexity of the terrain, and changes in weather conditions; construct a risk assessment model based on the risk factors; analyze the target environment model based on the risk assessment model, derive the safety risk level corresponding to the target environment model, and display the safety risk level corresponding to the target environment model.

[0022] In a third aspect, the present disclosure provides an electronic device comprising: a memory, a display, and one or more processors; the memory, display, and processors are coupled. The memory is configured to store computer program code, which includes computer instructions; when the electronic device is in operation, the processor is configured to execute the one or more computer instructions stored in the memory, causing the electronic device to perform any of the path planning methods described in the first aspect.

[0023] In a fourth aspect, the present disclosure provides a computer storage medium comprising computer instructions, which, when executed on an electronic device, enables the electronic device to execute the path planning method as described in any one of the first aspects.

[0024] In a fifth aspect, the present disclosure provides a computer program product. When the computer program product is run on an electronic device, the electronic device executes the path planning method as described in any one of the first aspects.

[0025] In a sixth aspect, an apparatus (for example, a system-on-chip) is provided. The apparatus includes a processor configured to support a first device in implementing the functions described in the first aspect. In one possible design, the apparatus further includes a memory configured to store program instructions and data necessary for the first device. When the apparatus is a system-on-chip, it may consist solely of a chip or include a chip and other discrete components.

[0026] It should be understood that the beneficial effects of the second to sixth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 This is one of the flow charts of a path planning method provided in an embodiment of the present disclosure.

[0028] Figure 2 This is a second flow chart of a path planning method provided in an embodiment of the present disclosure.

[0029] Figure 3 This is a third flow chart of a path planning method provided in an embodiment of the present disclosure.

[0030] Figure 4 This is a fourth flowchart of a path planning method provided in an embodiment of the present disclosure.

[0031] Figure 5 This is a fifth flow chart of a path planning method provided in an embodiment of the present disclosure.

[0032] Figure 6 This is a sixth flowchart of a path planning method provided in an embodiment of the present disclosure.

[0033] Figure 7 FIG7 is a flowchart of a path planning method provided in an embodiment of the present disclosure.

[0034] Figure 8 A schematic diagram of the structure of a path planning device provided in an embodiment of the present disclosure.

[0035] Figure 9 A schematic structural diagram of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0036] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0037] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The data involved in the present disclosure may be data authorized by the user or fully authorized by all parties. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0038] It will also be understood that the term “comprising” indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements and / or components.

[0039] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0040] In aerial work scenarios in the power industry, workers must move between different locations to advance their work. However, the aerial work environment is full of variables, such as climate fluctuations and changes in equipment operating conditions. Therefore, how to design an efficient and safe movement route for workers in these situations is a pressing issue.

[0041] To address the above issues, the disclosed embodiments provide a path planning method. Once the environmental parameters for altitude work are understood, a target environment model is constructed based on these parameters. This target environment model is then analyzed to determine the safety risk level. Finally, based on the target environment model and the safety risk level, a path planning result corresponding to the target environment model is obtained. This method not only ensures efficient operation but also enhances operational safety.

[0042] The following is an exemplary description of the wind speed warning method provided by the embodiment of the present disclosure:

[0043] The path planning method provided by the present disclosure can be applied to electronic devices.

[0044] In some embodiments, the electronic device may be a server or a terminal, which is not limited in this disclosure. The server may be a single server or a server cluster consisting of multiple servers. In some implementations, the server cluster may also be a distributed cluster. This disclosure also does not limit the specific implementation of the server.

[0045] The terminal may be a mobile phone, tablet computer, desktop computer, laptop computer, handheld computer, notebook computer, ultra-mobile personal computer (UMPC), netbook computer, cellular phone, personal digital assistant (PDA), augmented reality (AR) or virtual reality (VR) device, etc. The present disclosure does not impose any particular restrictions on the specific form of the electronic device. The terminal may interact with the user through one or more methods such as a keyboard, touchpad, touch screen, remote control, voice interaction, or handwriting device.

[0046] The following will be combined with the accompanying drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the embodiments described are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of the present disclosure.

[0047] like Figure 1 As shown, when the path planning method is applied to an electronic device, the path planning method may include:

[0048] Step 101: Obtain environmental parameters for altitude work.

[0049] Environmental parameters include at least three-dimensional terrain parameters, obstacle parameters, and weather parameters. For example, three-dimensional terrain parameters include terrain height parameters and slope parameters. Obstacle parameters include obstacle location, size, and shape. Weather parameters include wind speed, temperature, and air temperature in the altitude work area.

[0050] In some examples, the process of the electronic device acquiring environmental parameters for the high-altitude operation may include: the electronic device using a collection device to collect the environmental parameters for the high-altitude operation. The collection device may include an image sensor (such as a camera), radar, lidar, global positioning system, or other sensor for detecting environmental parameters for the high-altitude operation.

[0051] Environmental parameters may include image data, radar data, lidar data, and positioning data. Image data, radar data, lidar data, and positioning data may be used to determine the three-dimensional terrain parameters, obstacle parameters, and weather parameters for altitude operations.

[0052] Electronic equipment can also determine the high-altitude work area through positioning data, and then use weather stations or third parties to obtain weather parameters of the high-altitude work area.

[0053] For example, a camera can continuously capture images of the surrounding environment (e.g., the terrain) of the aerial work site to obtain image data. Radar acquires radar data by emitting electromagnetic waves and receiving reflected waves. When the electromagnetic waves hit an object, they are reflected back. The radar calculates terrain height, slope, and other information based on the time and frequency variations of the reflected waves. LiDAR uses a laser beam to scan the surrounding environment, providing highly accurate distance measurements and object outline information. By rapidly rotating and emitting a laser beam, LiDAR data (e.g., a 3D point cloud) of the surrounding environment can be generated. Analysis of this LiDAR data can reveal the location, size, and shape of obstacles.

[0054] In some examples, the electronic device can also obtain required parameters for high-altitude operations, such as operating height, operating illumination, operating space size, operating temperature, and operating humidity.

[0055] In some examples, environmental parameters may also include device parameters and safety parameters. Device parameters include device type, device performance indicators, and device status. Safety parameters include protective equipment, safety equipment, and safety operations.

[0056] Step 102: Based on the environmental parameters, a target environment model corresponding to the altitude operation is constructed.

[0057] After obtaining the environmental parameters of the climbing operation, a target environment model corresponding to the climbing operation can be constructed based on the environmental parameters.

[0058] Optional, such as Figure 2 As shown, in step 102, based on the environmental parameters, constructing a target environment model corresponding to the climbing operation includes:

[0059] Step 201: Preprocess the environmental parameters to obtain processed environmental parameters. The preprocessing includes data cleaning, data conversion, and data labeling.

[0060] In some examples, when the environmental parameters are three-dimensional terrain parameters, data cleaning of the three-dimensional terrain parameters may include checking for missing values ​​in the three-dimensional terrain parameters; if missing values ​​exist, filling them with the average of the terrain parameters of the adjacent points. For example, if the terrain parameters of a point are missing, and the terrain parameters of its four adjacent points are h1, h2, h3, and h4, respectively, the filling value for the point is (h1+h2+h3+h4) / 4.

[0061] After data cleaning of environmental parameters, data conversion can be performed on the environmental parameters. For example, if three-dimensional terrain parameters are recorded in meters, while other data are recorded in feet, the units of the three-dimensional terrain parameters can be unified with the units of other data through data conversion.

[0062] After cleaning the environmental parameters, you can continue to annotate them. For example, the three-dimensional terrain parameters include a terrain height map. On the terrain height map, areas with special features, such as mountain tops, valleys, cliffs, etc., are marked. Different characters can be used for marking to quickly identify these key areas when building the target environment model.

[0063] It is understandable that when the environmental parameters are other parameters, such as slope parameters, the location of obstacles, the size of obstacles and the shape of obstacles, wind speed, temperature, air temperature, etc. in the climbing work area, the environmental parameters can also be processed by referring to the above-mentioned data cleaning, data conversion and data labeling methods, and they will not be repeated here.

[0064] Step 202: Input the processed environmental parameters into a preset engine, and the preset engine outputs a target environment model.

[0065] Exemplarily, the preset engine includes at least one of Unity3D, Unreal Engine or GIS software.

[0066] In some examples, the process of inputting the processed environmental parameters into the preset engine and the preset engine outputting the target environmental model may include: starting the preset engine, inputting the processed environmental parameters into the preset engine, and constructing the target environmental model based on the processed environmental parameters.

[0067] After obtaining the target environment model, simulations can be performed on it. This simulation can determine the impact of different weather conditions (such as wind speed and direction variations, rainfall patterns like heavy rain, drizzle, and snow), different equipment states (such as normal operation, minor faults, and major faults), and obstacles on the target environment model. The first and second path planning results corresponding to the target environment model can then be adjusted based on the simulation results.

[0068] Step 103: Analyze the target environment model to obtain the security risk level corresponding to the target environment model.

[0069] After obtaining the target environment model, the target environment model can be analyzed to obtain the security risk level corresponding to the target environment model.

[0070] Optional, such as Figure 3 As shown, in step 103, the target environment model is analyzed to obtain the security risk level corresponding to the target environment model, including:

[0071] Step 301: Set risk factors according to environmental parameters.

[0072] Among them, risk factors include the distribution of obstacles, the complexity of the terrain and changes in weather conditions.

[0073] In some examples, after obtaining the environmental parameters for the height-ascending operation, the distribution of obstacles can be determined based on the environmental parameters. For electrical height-ascending operations, obstacles may include utility poles, high-voltage pylons, and buildings.

[0074] Specifically, the high-altitude operation area can be divided into multiple grids according to the three-dimensional terrain parameters and obstacle parameters in the environmental parameters, and the obstacles in each grid as well as the number and type of obstacles can be determined to obtain the obstacle distribution in the risk factors.

[0075] The terrain complexity can also be derived based on the slope in the three-dimensional terrain parameter in the environmental parameter. For example, the terrain complexity includes multiple slope intervals of the terrain slope, such as a low slope of 0 to 10 degrees, a medium slope of 10 to 30 degrees, a high slope of 30 to 60 degrees, and an extreme slope of more than 60 degrees.

[0076] Weather parameters within the environmental parameters can also be used to determine changes in weather conditions. Different weather conditions affect equipment and workers in different ways. For example, rainy days can make the work surface slippery, increasing the risk of slips for workers; strong winds can cause aerial work equipment to shake, affecting its stability. Weather conditions can also affect the electrical and mechanical performance of equipment. For example, humid weather can cause electrical equipment to short-circuit.

[0077] That is, after obtaining the environmental parameters, the risk factors can be set according to the environmental parameters.

[0078] Step 302: Construct a risk assessment model based on the risk factors.

[0079] For example, the risk assessment model can be a logistic regression model or a random forest algorithm. The logistic regression model is a linear model used for binary classification problems. The complexity of the logistic regression model can be controlled by adjusting parameters. The random forest algorithm is an ensemble learning algorithm composed of multiple decision trees and has high accuracy and stability.

[0080] Based on the risk factors, the process of constructing a risk assessment model may include: first, collecting sample data through sensors, then selecting an initial risk assessment model, and training the initial risk assessment model using the sample data and risk factors to obtain a risk assessment model.

[0081] The process of training the initial risk assessment model using sample data and risk factors to obtain the risk assessment model may include: dividing the sample data into training set data and test set data, training the initial risk assessment model using the training set data and risk factors to adjust the parameters of the initial risk assessment model to obtain the risk assessment model. Then, the risk assessment model is evaluated using the test set data to determine the accuracy and generalization ability of the risk assessment model. The sample data includes sample distribution data of obstacles (such as the location, number, type of obstacles, etc.), terrain sample data (such as slope, undulation, landform type, etc.), and weather sample data (such as wind speed, humidity, temperature, etc.).

[0082] Step 303: Analyze the target environment model according to the risk assessment model, obtain the security risk level corresponding to the target environment model, and display the security risk level corresponding to the target environment model.

[0083] After obtaining the risk assessment model, the target environment model can be input into the risk assessment model so that the risk assessment model outputs a security risk level corresponding to the target environment model. For example, the security risk level may include multiple levels, such as low risk, medium risk, and high risk.

[0084] After obtaining the safety risk level corresponding to the target environment model, the corresponding safety risk level can be displayed in the target environment model. In this way, for high-risk areas, measures such as adding safety equipment, strengthening personnel training, and adjusting operating hours can be taken to reduce operational risks. For low-risk areas, safety measures can be appropriately simplified to improve operational efficiency. Through steps 301-303, safety risks in the operating environment can be effectively identified and assessed, allowing the formulation of reasonable safety strategies to ensure the safety of operators and the normal operation of equipment.

[0085] Step 104: Based on the target environment model and the security risk level, determine a first path planning result and a second path planning result corresponding to the target environment model, wherein the first path planning result has a higher priority than the second path planning result.

[0086] After obtaining the target environment model and the security risk level corresponding to the target environment model, a first path planning result and a second path planning result corresponding to the target environment model can be obtained based on the target environment model and the security risk level corresponding to the target environment model.

[0087] In some examples, a first path planning result and a second path planning result corresponding to the target environment model can be determined based on the target environment model and the safety risk level. After obtaining the first and second path planning results, the operator can perform the operation according to the first path planning result or the second path planning result.

[0088] In other examples, the first path planning result has a higher priority than the second path planning result. After obtaining the first and second path planning results, the operator can prioritize the first path planning result. If an exception occurs during the operation according to the first path planning result, the operator can then proceed according to the second path planning result.

[0089] Optional, such as Figure 4 As shown, in step 104, based on the target environment model and the security risk level, a first path planning result corresponding to the target environment model is determined, including:

[0090] Step 401: Input the target environment model and the safety risk level into the prediction model, and the prediction model outputs a first path planning result corresponding to the target environment model.

[0091] The first path planning result includes at least one first time step and at least one first execution action information, and one first time step corresponds to one first execution action information.

[0092] The first time step may be a plurality of time segments during the climbing operation. For example, a time step may be one minute. The first execution action information is an action instruction to be executed within each time step.

[0093] In some examples, the prediction model is a model that has been trained and optimized using sample data. For example, the prediction model can be composed of a deep learning model, a generative model, and a reinforcement learning algorithm. The deep learning model can be a convolutional neural network (CNN), a recurrent neural network (RNN), or a graph neural network (GNN). The generative model can be a generative adversarial network (GAN) or a variational autoencoder (VAE). The reinforcement learning algorithm can be Q-learning, a deep Q network (DQN), a policy gradient algorithm, etc.

[0094] The target environment model and the safety risk level are input into the prediction model, and the prediction model can extract features of the target environment model.

[0095] After obtaining the characteristics of the target environment model, a generative model can be used to generate a first path planning result based on the characteristics of the target environment model and the safety risk level. The operator can then perform the high-altitude operation according to the first path planning result.

[0096] In some examples, the first action information includes a first action direction, a first action angle, and a first action quantity. The first action direction is used to represent the direction in which the operator or the climbing equipment moves during the climbing operation. The first action angle is related to the action direction and is used to represent the deflection angle in the action direction. The first action quantity is used to represent a quantitative indicator of the movement, for example, moving forward 5 meters, raising the climbing equipment 10 centimeters, etc.

[0097] Step 402: Based on the target environment model, determine a second path planning result corresponding to the target environment model.

[0098] The second path planning result includes at least one second time step and at least one second execution action information, and one second time step corresponds to one second execution action information.

[0099] After obtaining the target environment model, a second path planning result corresponding to the target environment model can be obtained based on the target environment model. It is understood that the content of the second time step can refer to the first time step, and the second execution action information can refer to the first execution action information, which will not be repeated here.

[0100] In some examples, the process of determining a second path planning result corresponding to the target environment model based on the target environment model may include: determining the second path planning result corresponding to the target environment model based on the target environment model and historical safety operation cases.

[0101] In some examples, the first path planning result may be the same as or different from the second path planning result.

[0102] Optional, such as Figure 5 As shown, step 402 determines a second path planning result corresponding to the target environment model based on the target environment model, including:

[0103] Step 501: Obtain a path configuration library.

[0104] The path configuration library includes multiple preset environments and preset paths corresponding to each preset environment.

[0105] In some examples, the path configuration library can be a pre-established database. The preset environments in the path configuration library can be categorized by terrain, obstacles, and weather conditions. Each categorized preset environment has a corresponding preset path. These preset paths can be generated by analyzing historical high-altitude operation cases and following successful execution paths.

[0106] Step 502: Based on the target environment model, divide the target environment model into at least one environment area.

[0107] After obtaining the target environment model, it can be divided into at least one environmental region in various ways. For example, the target environment model can be divided into at least one environmental region based on the similarity of terrain features. Alternatively, the target environment model can be divided into at least one environmental region based on the distribution of obstacles. Alternatively, the target environment model can be divided into at least one environmental region based on the degree to which weather conditions affect different regions.

[0108] Step 503: Compare the at least one environmental area with a plurality of preset environments to determine a target preset environment that matches the at least one environmental area.

[0109] After obtaining at least one environment region, each environment region is compared with multiple preset environments. If the similarity exceeds a preset threshold, the preset environment is considered to be a target preset environment that matches the at least one environment region. For example, the preset threshold is 80%.

[0110] For example, if the terrain type, slope, undulation and other characteristics in at least one environmental area are 80% consistent with the terrain characteristics of a preset environment, the preset environment is determined as the target preset environment.

[0111] Step 504: Determine the preset path corresponding to the target preset environment as the second path planning result corresponding to the target environment model.

[0112] After the target preset environment is obtained, based on the path configuration library, the preset path corresponding to the target preset environment in the path configuration library is determined as the second path planning result.

[0113] Optional, such as Figure 6As shown, after determining the first path planning result and the second path planning result corresponding to the target environment model based on the target environment model and the security risk level in step 104, the method further includes:

[0114] Step 601: Utilize a sensor to obtain an action feedback result corresponding to at least one execution action.

[0115] The action feedback result includes whether an obstacle is detected and whether the target position is reached. The at least one execution action is an execution action in the first execution action information or an execution action in the second execution action information.

[0116] After obtaining the first path planning result and the second path planning result, the operator can perform the operation according to the first path planning result or the second path planning result.

[0117] During the operation of the operator, the sensor can be used to collect action feedback results corresponding to at least one executed action, for example, the action feedback result is reaching the target position.

[0118] Step 602: The reinforcement learning algorithm in the prediction model updates the neural network parameters in the prediction model according to the action feedback result corresponding to at least one execution action to obtain an updated prediction model.

[0119] After using sensors to collect action feedback results corresponding to at least one execution action, the action feedback results corresponding to at least one execution action can be input into the prediction model, so that the reinforcement learning algorithm in the preset model updates the neural network parameters in the prediction model according to the action feedback results corresponding to at least one execution action, thereby obtaining an updated prediction model.

[0120] For example, if the action feedback result for at least one executed action is the detection of an obstacle, the reinforcement learning algorithm in the preset model will output a negative reward and adjust the neural network parameters based on the negative reward feedback, so that in this environment, the output action is to avoid the obstacle. For another example, if the action feedback result for at least one executed action is the arrival at the target location, the reinforcement learning algorithm in the preset model will output a positive reward and continue to plan the next executed action based on the positive reward. Through continuous iteration and updating, the prediction model can provide more accurate and efficient path planning results.

[0121] Optional, such as Figure 7 As shown, the method further includes:

[0122] Step 701: Monitor whether the environmental parameters of the altitude operation and the operator's behavior data exceed the threshold.

[0123] When the operator performs the operation according to the first path planning result or the second path planning result, since the environmental parameters of the high-altitude operation area may change, the environmental parameters of the high-altitude operation and the operator's behavior data can be detected and continuously monitored.

[0124] For example, the threshold of the environmental parameter is the first threshold, and the threshold of the operator's behavioral data is the second threshold. The behavioral data may include the operator's movement speed, the way he operates the climbing equipment, and whether he wears personal protective equipment correctly.

[0125] Step 702: Output a warning message when an environmental parameter exceeds a first threshold or the operator's behavior data exceeds a second threshold.

[0126] Among them, the early warning information is used to prompt the operator to operate according to the second path planning result; the early warning information includes the second path planning result; the second path planning result is obtained based on historical safe operation cases.

[0127] If a monitored environmental parameter exceeds the first threshold, it indicates that the current working environment has a high safety risk. For example, if the wind speed in the environmental parameter exceeds the set first wind speed threshold, it may cause the climbing equipment to be unstable, increasing the risk of falling for the operator.

[0128] When the operator's behavior data exceeds the second threshold, it indicates that the operator's behavior does not comply with safety regulations. For example, the operator does not wear personal protective equipment correctly, which may lead to a safety accident.

[0129] In these situations, the system will output a warning message to alert operators and managers to potential safety risks and to take appropriate measures. Because the first path planning result has a higher priority than the second path planning result, operators will typically follow the first path planning result. Because the second path planning result is based on historical safe operation cases, the second path planning result has a higher safety level than the first path planning result. Therefore, in this case, the warning message can be used to prompt operators to follow the second path planning result, thereby ensuring their safety.

[0130] Combination of the above Figure 1-Figure 7The method provided by the embodiment of the present disclosure is described in detail. In order to realize the above functions, the path planning device includes hardware structures and / or software modules corresponding to the execution of each function, and these hardware structures and / or software modules corresponding to the execution of each function can constitute a path planning device. It should be easy for those skilled in the art to realize that, in combination with the algorithm steps of each example described in the embodiments disclosed herein, the present disclosure can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in a hardware or computer software driven hardware manner depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present disclosure.

[0131] The embodiment of the present disclosure can divide the path planning device into functional modules according to the above method example. For example, the path planning device can divide each functional module into corresponding functional modules, or integrate two or more functions into one processing module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present disclosure is schematic and is only a logical functional division. There may be other division methods in actual implementation.

[0132] The following, combined Figure 8 The path planning device provided by the embodiment of the present disclosure is described in detail. It should be understood that the description of the device embodiment corresponds to the description of the method embodiment. Therefore, for matters not described in detail, reference can be made to the method embodiment above. For the sake of brevity, they will not be repeated here.

[0133] Figure 8 FIG. 1 is a logical structure diagram of a path planning device according to an exemplary embodiment. Figure 8 The path planning device includes: an acquisition module 810, a construction module 820 and a determination module 830.

[0134] An acquisition module 810 is configured to acquire environmental parameters for the altitude operation, the environmental parameters including at least three-dimensional terrain parameters, obstacle parameters, and weather parameters;

[0135] A construction module 820 is configured to construct a target environment model corresponding to the climbing operation based on the environmental parameters;

[0136] Determination module 830 is configured to analyze the target environment model to obtain the security risk level corresponding to the target environment model; and based on the target environment model and the security risk level, determine the first path planning result and the second path planning result corresponding to the target environment model, wherein the priority of the first path planning result is higher than the second path planning result.

[0137] Optionally, the determination module 830 is further configured to input the target environment model and the safety risk level into the prediction model, and the prediction model outputs a first path planning result corresponding to the target environment model, wherein the first path planning result includes at least one first time step and at least one first execution action information, and one first time step corresponds to one first execution action information; based on the target environment model, determine the second path planning result corresponding to the target environment model, the second path planning result includes at least one second time step and at least one second execution action information, and one second time step corresponds to one second execution action information.

[0138] Optionally, the acquisition module 810 is further configured to use a sensor to obtain an action feedback result corresponding to at least one execution action; the action feedback result includes whether an obstacle is detected and whether the target position is reached; at least one execution action is an execution action in the first execution action information, or an execution action in the second execution action information; the determination module is further configured to update the neural network parameters in the prediction model according to the action feedback result corresponding to at least one execution action by the reinforcement learning algorithm in the prediction model to obtain an updated prediction model.

[0139] Optionally, the determination module 830 is further configured to obtain a path configuration library; the path configuration library includes multiple preset environments and preset paths corresponding to each preset environment; based on the target environment model, the target environment model is divided into at least one environment area; the at least one environment area is compared with the multiple preset environments to determine the target preset environment that matches the at least one environment area; the preset path corresponding to the target preset environment is determined as the second path planning result corresponding to the target environment model.

[0140] Optionally, the environmental parameters may also include device parameters and safety parameters; the execution action information includes action direction, action angle, and action quantity.

[0141] Optionally, the path planning device further includes a monitoring module 840 and an output module 850. The monitoring module 840 is configured to monitor whether the environmental parameters of the height-ascending operation and the operator's behavioral data exceed a threshold; the output module 850 is configured to output a warning message when the environmental parameters exceed a first threshold or the operator's behavioral data exceeds a second threshold, the warning message being used to prompt the operator to operate according to the second path planning result; the warning message includes the second path planning result; the second path planning result is obtained based on historical safe operation cases.

[0142] Optionally, the construction module 820 is further configured to preprocess the environmental parameters to obtain processed environmental parameters, where the preprocessing includes data cleaning, data conversion, and data labeling; the processed environmental parameters are input into a preset engine, and the preset engine outputs a target environment model.

[0143] Optionally, the determination module 830 is further configured to set risk factors based on environmental parameters, the risk factors including the distribution of obstacles, the complexity of the terrain and changes in weather conditions; construct a risk assessment model based on the risk factors; analyze the target environment model based on the risk assessment model, derive the safety risk level corresponding to the target environment model, and display the safety risk level corresponding to the target environment model.

[0144] Of course, the path selection device provided by the embodiments of the present disclosure includes but is not limited to the above modules. For example, the path selection device may further include a storage module 860. The storage module 860 may be used to store program code of the write path selection device and may also be used to store data generated during operation of the write path selection device, such as data in a write request.

[0145] Figure 9 FIG. 1 shows a possible structural diagram of the electronic device involved in the above embodiment. Figure 9 As shown, the electronic device 90 includes a processor 901 and a memory 902 .

[0146] I understand. Figure 9 The electronic device 90 shown can implement all the functions of the above-mentioned speech recognition model generation method. The functions of each module in the above-mentioned path planning device can be implemented in the processor 901 of the electronic device 90. The storage module of the path planning device is equivalent to the memory 902 of the electronic device 90.

[0147] The processor 901 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 90 may include an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU). Different processing units may be independent devices or integrated into one or more processors.

[0148] The memory 902 may include one or more computer-readable storage media, which may be non-transitory. The memory 902 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices and flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 902 is used to store at least one instruction, which is used to be executed by the processor 901 to implement the speech recognition model generation method provided by the embodiment of the method of the present disclosure.

[0149] In some embodiments, the electronic device 90 may optionally include a peripheral device interface 903 and at least one peripheral device. The processor 901, memory 902, and peripheral device interface 903 may be connected via a bus or signal lines. Each peripheral device may be connected to the peripheral device interface 903 via a bus, signal lines, or circuit boards. Specifically, the peripheral device may include at least one of a radio frequency circuit 904, a touch screen display 905, a camera 906, an audio circuit 907, a positioning component 908, and a power supply 909.

[0150] The peripheral device interface 903 can be used to connect at least one I / O (Input / Output)-related peripheral device to the processor 901 and the memory 902. In some embodiments, the processor 901, the memory 902, and the peripheral device interface 903 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 901, the memory 902, and the peripheral device interface 903 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0151] The RF circuit 904 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 904 communicates with communication networks and other communication devices via electromagnetic signals. The RF circuit 904 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals into electrical signals. Optionally, the RF circuit 904 includes an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, and the like. The RF circuit 904 can communicate with other path planning devices via at least one wireless communication protocol. Such wireless communication protocols include, but are not limited to, metropolitan area networks, various generations of mobile communication networks (2G, 3G, 4G, and 6G), wireless local area networks, and / or Wi-Fi (Wireless Fidelity) networks. In some embodiments, the RF circuit 904 may also include circuits related to NFC (Near Field Communication), which is not limited in this disclosure.

[0152] The display screen 905 is used to display a UI (User Interface). The UI may include graphics, text, icons, videos, and any combination thereof. When the display screen 905 is a touch screen display, the display screen 905 also has the ability to collect touch signals on the surface or above the surface of the display screen 905. The touch signal can be input as a control signal to the processor 901 for processing. At this time, the display screen 905 can also be used to provide virtual buttons and / or virtual keyboards, also known as soft buttons and / or soft keyboards. In some embodiments, the display screen 905 can be one, and the front panel of the electronic device 90 is set; the display screen 905 can be made of materials such as LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), etc.

[0153] The camera assembly 906 is used to capture images or videos. Optionally, the camera assembly 906 includes a front-facing camera and a rear-facing camera. Typically, the front-facing camera is located on the front panel of the path planning device, and the rear-facing camera is located on the back of the path planning device. The audio circuit 907 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, converting them into electrical signals that are then input into the processor 901 for processing, or into the RF circuit 404 for voice communication. For stereo sound acquisition or noise reduction, multiple microphones may be provided, located in different locations on the electronic device 90. The microphone may also be an array microphone or an omnidirectional microphone. The speaker is used to convert electrical signals from the processor 901 or the RF circuit 904 into sound waves. The speaker may be a traditional thin-film speaker or a piezoelectric ceramic speaker. A piezoelectric ceramic speaker can convert electrical signals not only into audible sound waves but also into inaudible sound waves for purposes such as distance measurement. In some embodiments, the audio circuit 907 may also include a headphone jack.

[0154] Positioning component 908 is used to locate the current geographic location of electronic device 90 to implement navigation or LBS (Location Based Service). Positioning component 908 can be based on the US GPS (Global Positioning System), China's Beidou system, Russia's Greninja system, or the European Union's Galileo system.

[0155] The power supply 909 is used to power the various components of the electronic device 90. The power supply 909 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When the power supply 909 includes a rechargeable battery, the rechargeable battery can support wired charging or wireless charging. The rechargeable battery can also be used to support fast charging technology.

[0156] In some embodiments, the electronic device 90 further includes one or more sensors 910. The one or more sensors 910 include, but are not limited to, an acceleration sensor, a gyroscope sensor, a pressure sensor, a fingerprint sensor, an optical sensor, and a proximity sensor.

[0157] The acceleration sensor can detect the magnitude of acceleration on the three coordinate axes of the coordinate system established with the electronic device 90. The gyroscope sensor can detect the body direction and rotation angle of the electronic device 90. The gyroscope sensor can cooperate with the acceleration sensor to collect the user's 3D actions on the electronic device 90. The pressure sensor can be set on the side frame of the electronic device 90 and / or the lower layer of the touch display screen 906. When the pressure sensor is set on the side frame of the electronic device 90, it can detect the user's grip signal on the electronic device 90. The fingerprint sensor is used to collect the user's fingerprint. The optical sensor is used to collect the ambient light intensity. The proximity sensor, also known as the distance sensor, is usually set on the front panel of the electronic device 90. The proximity sensor is used to collect the distance between the user and the front of the electronic device 90.

[0158] The present disclosure also provides a computer-readable storage medium having instructions stored thereon. When the instructions in the storage medium are executed by a processor of a path planning device, the path planning device is enabled to execute the speech recognition model generation method provided by the present disclosure.

[0159] An embodiment of the present disclosure also provides a computer program product containing instructions, which, when executed on a path planning device, enables the path planning device to execute the speech recognition model generation method provided by the present disclosure.

[0160] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the following claims.

[0161] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A path planning method, characterized in that: The method comprises: Acquiring environmental parameters for the altitude operation, wherein the environmental parameters include at least three-dimensional terrain parameters, obstacle parameters, and weather parameters; Based on the environmental parameters, a target environment model corresponding to the climbing operation is constructed; Analyzing the target environment model to obtain a security risk level corresponding to the target environment model; Determining, based on the target environment model and the security risk level, a first path planning result and a second path planning result corresponding to the target environment model, wherein the first path planning result has a higher priority than the second path planning result; Determining a first path planning result and a second path planning result corresponding to the target environment model based on the target environment model and the security risk level includes: Inputting the target environment model and the safety risk level into a prediction model, wherein the prediction model outputs the first path planning result corresponding to the target environment model; Determining a second path planning result corresponding to the target environment model based on the target environment model; The determining, based on the target environment model, a second path planning result corresponding to the target environment model includes: Obtain a path configuration library; the path configuration library includes multiple preset environments and preset paths corresponding to each preset environment; Based on the target environment model, dividing the target environment model into at least one environment area; comparing the at least one environmental area with the plurality of preset environments to determine a target preset environment that matches the at least one environmental area; Determining the preset path corresponding to the target preset environment as the second path planning result corresponding to the target environment model; The step of analyzing the target environment model to obtain a security risk level corresponding to the target environment model includes: Setting risk factors based on the environmental parameters, the risk factors including the distribution of obstacles, the complexity of the terrain, and changes in weather conditions; Constructing a risk assessment model based on the risk factors; Analyzing the target environment model according to the risk assessment model to obtain a security risk level corresponding to the target environment model, and displaying the security risk level corresponding to the target environment model; The step of constructing a target environment model based on the environmental parameters includes: Preprocessing the environmental parameters to obtain processed environmental parameters, wherein the preprocessing includes data cleaning, data conversion, and data labeling; Inputting the processed environmental parameters into a preset engine, which outputs the target environment model; the preset engine includes at least one of Unity3D, Unreal Engine, or GIS software; Wherein, when the environmental parameter is a three-dimensional terrain parameter, performing data cleaning on the three-dimensional terrain parameter includes: Checking whether there are missing values ​​in the three-dimensional terrain parameters; If there are missing values, they are filled with the average value of the terrain parameters of the adjacent points; The method further comprises: Performing simulation on the target environment model; Adjusting the first path planning result and the second path planning result corresponding to the target environment model according to the simulation result; Among them, the first path planning result includes at least one first time step and at least one first execution action information, and one first time step corresponds to one first execution action information; the second path planning result includes at least one second time step and at least one second execution action information, and one second time step corresponds to one second execution action information.

2. The method according to claim 1, characterized in that The method further comprises: Obtaining, using a sensor, an action feedback result corresponding to at least one execution action; the action feedback result includes whether an obstacle is detected and whether a target location is reached; the at least one execution action is an execution action in the first execution action information or an execution action in the second execution action information; The reinforcement learning algorithm in the prediction model updates the neural network parameters in the prediction model according to the action feedback result corresponding to the at least one execution action to obtain an updated prediction model.

3. The method according to claim 1, characterized in that The environmental parameters may further include equipment parameters and safety parameters; the execution action information may include action direction, action angle, and action quantity.

4. The method according to any one of claims 1 to 3, characterized in that The method further comprises: Monitoring whether the environmental parameters of the climbing operation and the behavioral data of the operator exceed the threshold; When the environmental parameter exceeds a first threshold or the operator's behavior data exceeds a second threshold, an early warning message is output, and the early warning message is used to prompt the operator to operate according to the second path planning result; the early warning message includes the second path planning result; the second path planning result is obtained based on historical safe operation cases.

5. A path planning device, characterized in that: The device comprises: An acquisition module is configured to acquire environmental parameters of the climbing operation, wherein the environmental parameters include at least three-dimensional terrain parameters, obstacle parameters, and weather parameters; A construction module is configured to construct a target environment model corresponding to the climbing operation based on the environmental parameters; a determination module configured to analyze the target environment model to obtain a security risk level corresponding to the target environment model; and determine, based on the target environment model and the security risk level, a first path planning result and a second path planning result corresponding to the target environment model, wherein the first path planning result has a higher priority than the second path planning result; The determination module is further configured to input the target environment model and the security risk level into the prediction model, and the prediction model outputs a first path planning result corresponding to the target environment model; based on the target environment model, determine a second path planning result corresponding to the target environment model; and obtain a path configuration library; the path configuration library includes multiple preset environments and preset paths corresponding to each preset environment; based on the target environment model, divide the target environment model into at least one environment area; compare the at least one environment area with the multiple preset environments, and determine a target preset environment that matches the at least one environment area; and determine the preset path corresponding to the target preset environment as the second path planning result corresponding to the target environment model; The construction module is further configured to pre-process the environmental parameters to obtain processed environmental parameters, where the pre-processing includes data cleaning, data conversion, and data labeling; input the processed environmental parameters into a preset engine, which outputs a target environmental model; when the environmental parameters are three-dimensional terrain parameters, check whether there are missing values ​​in the three-dimensional terrain parameters; if there are missing values, fill them with the average value of the terrain parameters of adjacent points; the preset engine includes at least one of Unity3D, Unreal Engine, or GIS software; The determination module is further configured to set risk factors based on environmental parameters, the risk factors including the distribution of obstacles, the complexity of the terrain and changes in weather conditions; construct a risk assessment model based on the risk factors; analyze the target environment model based on the risk assessment model to obtain the safety risk level corresponding to the target environment model, and display the safety risk level corresponding to the target environment model; simulate the target environment model; adjust the first path planning result and the second path planning result corresponding to the target environment model based on the simulation results; wherein the first path planning result includes at least one first time step and at least one first execution action information, and one first time step corresponds to one first execution action information; the second path planning result includes at least one second time step and at least one second execution action information, and one second time step corresponds to one second execution action information.

6. An electronic device, characterized in that: include: A touch screen comprising a touch sensor and a display screen; one or more processors; Memory; Wherein, one or more computer programs are stored in the memory, and the one or more computer programs include instructions. When the instructions are executed by the electronic device, the electronic device executes a path planning method as described in any one of claims 1 to 4.

7. A computer-readable storage medium having computer program instructions stored thereon; characterized in that: When the computer program instructions are executed by an electronic device, the electronic device implements a path planning method according to any one of claims 1 to 4.

Images