Motor drive control method and electronic device for electric off-road motorcycles

Abstract

The present invention provides a motor drive control method and electronic equipment for an electric off-road motorcycle, and relates to the field of motor control technology, including: obtaining a target off-road area of ​​a target electric off-road motorcycle, calling a GIS system to extract a terrain roughness distribution map based on the geographical location information of the target off-road area, and obtaining a regional terrain roughness distribution map; obtaining an off-road sub-area set; configuring a sensor monitoring frequency group set of the off-road sub-area set; determining a real-time off-road sub-area set; obtaining a real-time road feature set; using the real-time road feature set as a drive control analysis object, and adaptively driving and controlling the motor of the target electric off-road motorcycle. The method solves the technical problems of slow response speed and low control accuracy of the electric off-road motorcycle motor drive control to the actual road conditions in the prior art, and achieves the technical effect of improving the degree of fit between the motor drive control and the actual road conditions and improving the response speed.

Description

Technical Field

[0001] The present invention relates to the technical field of motor control, and particularly to a motor drive control method and an electronic device for an electric off-road motorcycle. Background Art

[0002] With the popularization of electric off-road motorcycles, the application requirements in complex terrain environments are gradually increasing. Electric off-road motorcycles usually need to cope with uneven and unpredictable off-road roads, and the motor drive control system needs to adjust the output power in real time to adapt to different terrains. However, most of the existing motor control systems rely on predetermined fixed control parameters and cannot be effectively adjusted in real time according to the road terrain. Especially in complex terrain environments, the response speed of the existing motor control systems is slow, and it is difficult to respond to the rapidly changing ground conditions in real time, resulting in a poor driving experience, low control accuracy, and easy occurrence of out-of-control or unstable situations.

[0003] Therefore, how to adjust the control parameters of the motor according to the road conditions in the target driving area of the electric off-road motorcycle has become a technical problem to be solved urgently. Summary of the Invention

[0004] The present application provides a motor drive control method and an electronic device for an electric off-road motorcycle, aiming to solve the technical problems of slow response speed and low control accuracy of the motor drive control of the electric off-road motorcycle in the prior art for the actual road conditions.

[0005] In the first aspect disclosed by the present application, a motor drive control method for an electric off-road motorcycle is provided. The method includes:

[0006] Obtain the target off-road area of the target electric off-road motorcycle, and based on the geographical location information of the target off-road area, call the GIS system to extract the terrain roughness distribution map to obtain the regional terrain roughness distribution map;

[0007] Perform watershed segmentation on the regional terrain roughness distribution map, and divide the target off-road area into sub-regions according to the ridge lines generated during the segmentation process to obtain a set of off-road sub-regions;

[0008] Traverse the set of off-road sub-regions to perform an analysis on the frequency of historical motorcycle drive out-of-control, and configure a set of sensing monitoring frequency groups for the set of off-road sub-regions according to the analysis results, where the off-road sub-regions and the sensing monitoring frequency groups correspond one by one;

[0009] Obtain the real-time positioning information according to the GIS positioning component of the target electric off-road motorcycle, match the real-time positioning information with the set of off-road sub-regions to determine the set of real-time off-road sub-regions;

[0010] Based on the real-time sensing and monitoring frequency group corresponding to the real-time off-road sub-region set in the sensing and monitoring frequency group set, construct an asynchronous extraction dual-channel, use the asynchronous extraction dual-channel to asynchronously extract the road images collected by the depth camera of the target electric off-road motorcycle, and use the fully connected network layer to perform road feature recognition on the extraction results to obtain a real-time road feature set;

[0011] Use the real-time road feature set as the driving control analysis object to perform adaptive driving control on the motor of the target electric off-road motorcycle.

[0012] The second aspect disclosed in this application provides an electronic device, including a memory and a processor. When the processor executes the executable instructions stored in the memory, any step of the first aspect disclosed in this application is implemented.

[0013] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0014] In this application, by obtaining the target off-road area of the target electric off-road motorcycle, based on the geographical location information of the target off-road area, calling the GIS system to extract the terrain roughness distribution map, obtaining the regional terrain roughness distribution map, then performing diffuse water segmentation on the regional terrain roughness distribution map, and dividing the target off-road area into sub-regions according to the ridge lines generated during the segmentation process to obtain an off-road sub-region set. Furthermore, traverse the off-road sub-region set to perform a frequent analysis of the historical motorcycle driving out-of-control frequency. According to the analysis results, configure the sensing and monitoring frequency group set of the off-road sub-region set, where the off-road sub-region and the sensing and monitoring frequency group correspond one by one. Then, according to the GIS positioning component of the target electric off-road motorcycle, obtain the real-time positioning information, match the real-time positioning information with the off-road sub-region set to determine the real-time off-road sub-region set. Based on the real-time sensing and monitoring frequency group corresponding to the real-time off-road sub-region set in the sensing and monitoring frequency group set, construct an asynchronous extraction dual-channel, use the asynchronous extraction dual-channel to asynchronously extract the road images collected by the depth camera of the target electric off-road motorcycle, and use the fully connected network layer to perform road feature recognition on the extraction results to obtain a real-time road feature set. Then, use the real-time road feature set as the driving control analysis object to perform adaptive driving control on the motor of the target electric off-road motorcycle. It achieves the technical effects of improving the driving control response speed of the motor, adaptively adjusting the torque and speed of the motor in real time, making the electric motorcycle perform more smoothly and stably in different off-road environments, improving the degree of fit between the motor control and the actual road conditions, and enhancing the driving experience and safety.

[0015] The above description is only an overview of the technical solution of this application. In order to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the specific embodiments of this application are specifically given below. Description of the Drawings

[0016] Figure 1 It is a schematic flowchart of the motor drive control method for the electric off-road motorcycle provided by an embodiment of this application.

[0017] Figure 2 It is an internal structure diagram of the electronic device provided by an embodiment of this application.

[0018] Description of the reference numerals: bus 300, receiver 301, processor 302, transmitter 303, memory 304, bus interface 305. Detailed Embodiments

[0019] By providing the motor drive control method for the electric off-road motorcycle in the embodiment of this application, the technical problems in the prior art that the motor drive control of the electric off-road motorcycle has a slow response speed to the actual road conditions and low control accuracy are solved.

[0020] After introducing the basic principle of this application, the various non-limiting embodiments of this application will be specifically introduced below in conjunction with the drawings of the specification. It should be understood that the specific embodiments described here are only used to explain this application and are not used to limit this application.

[0021] Embodiment, as Figure 1 shown, the embodiment of this application provides a motor drive control method for an electric off-road motorcycle, wherein the method includes:

[0022] Step S100: Obtain the target off-road area of the target electric off-road motorcycle, and based on the geographical location information of the target off-road area, call the GIS system to extract the terrain roughness distribution map to obtain the regional terrain roughness distribution map;

[0023] In one embodiment, the target electric off-road motorcycle refers to an electric off-road motorcycle that is in motion at a specific moment. The target off-road area refers to the geographical area that the target electric off-road motorcycle is expected to travel within a specific time period, typically including multiple different terrains and road conditions. The geographical location information refers to the geographical coordinates or regional location of the target off-road area obtained through technologies such as the Global Positioning System (GPS), usually longitude and latitude coordinates. The GIS system (Geographic Information System) is a system used for storing, analyzing, and displaying geographical data, which can process geographical spatial information and generate different maps and analysis reports. The regional terrain roughness distribution map reflects the roughness distribution of the surface of the target off-road area, usually involving factors such as slope, obstacles, undulations, etc.

[0024] In step S100, first, by obtaining the geographical location information of the target off-road area of the target electric off-road motorcycle, the area where the motorcycle is about to travel is determined. Then, using this location information to call the GIS system, the terrain roughness distribution map of this area is extracted by analyzing the geographical data through the system. This distribution map reflects the roughness degree of different terrains within the target off-road area, including the distribution of flat areas and rugged areas.

[0025] The precise terrain information provides data support for subsequent control decisions, ensuring that the motor drive control of the electric motorcycle can make timely and accurate adjustments under different terrains. Through this step, the system can understand the terrain characteristics of the target off-road area, laying a foundation for subsequent sub-region division and dynamic adjustment of motor control parameters.

[0026] Step S200: Perform watershed segmentation on the regional terrain roughness distribution map, and divide the target off-road area into sub-regions according to the ridge lines generated during the segmentation process to obtain a set of off-road sub-regions;

[0027] Furthermore, perform watershed segmentation on the regional terrain roughness distribution map, and divide the target off-road area into sub-regions according to the ridge lines generated during the segmentation process to obtain a set of off-road sub-regions. Step S200 of the embodiment of the present application further includes:

[0028] Obtain the lowest terrain roughness point of the regional terrain roughness distribution map, use this lowest terrain roughness point as the starting point for simulated water injection into the regional terrain roughness distribution map. When the water surface floods any terrain roughness distribution point in the regional terrain roughness distribution map, determine whether the roughness difference between the terrain roughness distribution point and the lowest terrain roughness point is less than or equal to a preset roughness difference threshold. If so, continue to inject water into the regional terrain roughness distribution map;

[0029] If not, after generating a regional division ridge line between the terrain roughness distribution point and the lowest point of the terrain roughness, continue to pour water into the regional terrain roughness distribution map until the water surface submerges the highest point of the terrain roughness in the regional terrain roughness distribution map, then stop pouring water to obtain a set of regional division ridge lines, where the regional division ridge line rises as the water surface rises;

[0030] Connect the set of regional division ridge lines to each other to divide the target off-road area into sub-areas and obtain the set of off-road sub-areas.

[0031] In a possible embodiment, it is used to perform floodwater segmentation on the regional terrain roughness distribution map by simulating the process of the water surface rising, and divide the regional terrain roughness distribution map into multiple sub-areas. During this process, the water surface expands from the lowest point to the surrounding areas until a certain segmentation condition is reached. The ridge lines generated during the segmentation are used to define the boundaries of different terrain areas. By obtaining the set of off-road sub-areas, the regional terrain roughness distribution map is divided, laying a foundation for setting the extraction frequency of road images for motor drive control of off-road sub-areas with different terrains in the future.

[0032] In the embodiment of the present application, the roughness difference refers to the roughness difference between two terrain roughness distribution points, and is used to determine whether to continue the water surface expansion or generate a ridge line. The terrain roughness distribution point refers to each specific point in the regional terrain roughness distribution map, and each specific point has roughness characteristics (such as slope, undulation, etc.). The preset roughness difference threshold is a threshold set by those skilled in the art according to experience or algorithms. When the difference between the terrain roughness distribution point and the lowest point is greater than this threshold, the water surface rising process will temporarily stop, and a ridge line will be generated to divide the area. The set of regional division ridge lines is used to divide the target off-road area into sub-areas and reflects the boundaries of each sub-area.

[0033] In step S200, first, perform floodwater segmentation on the terrain roughness distribution map, find the lowest point of the terrain roughness in the map and use it as the starting point for flooding. Then, simulate the expansion of the water surface around and gradually pour water. When the water surface submerges a certain terrain roughness distribution point, judge whether the roughness difference between this point and the lowest point is less than or equal to the preset roughness difference threshold. If it meets the condition, continue to pour water into the regional terrain roughness distribution map and the water surface continues to expand; if it does not meet the condition, the system will generate a ridge line between the two compared points and continue to pour water until the water surface submerges the highest point of the terrain roughness. The set of regional division ridge lines generated during this process divides different areas into multiple off-road sub-areas. Finally, all the generated ridge lines are connected to each other to complete the sub-area division of the target off-road area, thereby obtaining the set of off-road sub-areas.

[0034] By efficiently dividing different sub-regions according to the roughness differences of different terrains within the region, it provides more detailed geographical data support for subsequent monitoring and drive control, ensuring that the control system can adaptively obtain the road conditions of the target electric off-road motorcycle when driving in different sub-regions and quickly adjust the control parameters of the motor according to different terrain characteristics.

[0035] Further, connect the ridge line sets of the region division, divide the target off-road region into sub-regions, and obtain the set of off-road sub-regions. Step S200 of the embodiment of the present application further includes:

[0036] Connect the ridge line sets of the region division, divide the target off-road region according to the connection result, and obtain an initial set of off-road sub-regions;

[0037] Traverse the initial set of off-road sub-regions to count the sub-region areas and obtain an initial set of off-road sub-region areas;

[0038] When the initial set of off-road sub-region areas is less than or equal to the preset off-road sub-region area threshold, add the corresponding initial off-road sub-region to the set of off-road sub-regions to be fused;

[0039] When the initial set of off-road sub-region areas is greater than the preset off-road sub-region area threshold, add the corresponding initial off-road sub-region to the set of off-road sub-regions that can be fused;

[0040] Based on the sub-region positions of the set of off-road sub-regions to be fused and the set of off-road sub-regions that can be fused, perform initial off-road sub-region fusion to obtain the set of off-road sub-regions.

[0041] Further, based on the sub-region positions of the set of off-road sub-regions to be fused and the set of off-road sub-regions that can be fused, perform initial off-road sub-region fusion to obtain the set of off-road sub-regions. Step S200 of the embodiment of the present application further includes:

[0042] Randomly extract a first off-road sub-region to be fused from the set of off-road sub-regions to be fused;

[0043] According to the sub-region position, match the neighborhood of the first off-road sub-region to be fused from the set of off-road sub-regions that can be fused to obtain a first neighborhood of off-road sub-regions that can be fused;

[0044] Obtain a first set of areas of the first neighborhood of off-road sub-regions that can be fused for the first neighborhood of off-road sub-regions that can be fused;

[0045] Traverse and count the distances from the first neighborhood of off-road sub-regions that can be fused to the first off-road sub-region to be fused to obtain a first set of distances of the first neighborhood of off-road sub-regions that can be fused;

[0046] Perform weighted calculation on the first set of neighborhood areas of the first off-road sub-region that can be fused and the first set of neighborhood distances of the first off-road sub-region that can be fused to obtain the first set of neighborhood fusion coefficients of the first off-road sub-region that can be fused;

[0047] Integrate the first off-road sub-region to be fused into the off-road sub-region that can be fused corresponding to the maximum value in the first set of neighborhood fusion coefficients of the first off-road sub-region that can be fused to obtain the first off-road sub-region;

[0048] Perform initial off-road sub-region fusion on the sub-region positions of the set of off-road sub-regions to be fused and the set of off-road sub-regions that can be fused to obtain the set of off-road sub-regions.

[0049] In one embodiment, the preset off-road sub-region area threshold is an area value predetermined by those skilled in the art and is used to determine whether a certain sub-region needs further processing (such as merging). First, connect the set of regional division ridgelines to each other, and perform segmentation on the target off-road area according to the connection result to obtain the initial set of off-road sub-regions, that is, multiple sub-regions initially divided according to the terrain roughness distribution map. Next, traverse these initial off-road sub-regions, count the area of each initial off-road sub-region, and compare it with the preset off-road sub-region area threshold. If the area of a certain sub-region is less than or equal to the preset off-road sub-region area threshold, it indicates that the area of this initial off-road sub-region is too small, and then this sub-region is added to the set of off-road sub-regions to be fused; if the area is greater than the preset off-road sub-region area threshold, it indicates that the area of this initial off-road sub-region is qualified and does not need to be actively merged, and then this sub-region is added to the set of off-road sub-regions that can be fused. According to the areas and sub-region positions of these sets of off-road sub-regions to be fused and the set of off-road sub-regions that can be fused, perform initial off-road sub-region fusion to obtain the set of off-road sub-regions.

[0050] Optionally, randomly extract the first off-road sub-region to be fused from the set of off-road sub-regions to be fused, and match the neighborhood of the first off-road sub-region to be fused from the set of off-road sub-regions that can be fused according to the sub-region position to obtain the first neighborhood of the off-road sub-region that can be fused. Obtain the first set of neighborhood areas of the first neighborhood of the off-road sub-region that can be fused, and further, respectively count the distances from each off-road sub-region that can be fused in the first neighborhood of the off-road sub-region that can be fused to the first off-road sub-region to be fused to obtain the first set of neighborhood distances of the first neighborhood of the off-road sub-region that can be fused.

[0051] Furthermore, perform weighted calculations on the first set of neighborhood areas of the off-road sub-regions that can be fused and the first set of neighborhood distances of the off-road sub-regions that can be fused according to the weights preset by those skilled in the art to obtain the first set of neighborhood fusion coefficients of the off-road sub-regions that can be fused. Among them, the first set of neighborhood fusion coefficients of the off-road sub-regions that can be fused reflects the fusion quality of each off-road sub-region that can be fused in the neighborhood of the first off-road sub-region that can be fused. The larger the coefficient, the higher the fusion quality. According to the maximum value of the fusion coefficient, select the best merging object and merge the area to be fused with it to finally obtain the optimized first off-road sub-region.

[0052] Integrate the first off-road sub-region to be fused into the off-road sub-region that can be fused corresponding to the maximum value in the first set of neighborhood fusion coefficients of the off-road sub-regions that can be fused to obtain the first off-road sub-region. Based on the same principle of obtaining the first off-road sub-region, perform initial off-road sub-region fusion on the sub-region positions of the set of off-road sub-regions to be fused and the set of off-road sub-regions that can be fused to obtain the set of off-road sub-regions.

[0053] By refining and optimizing the initially divided areas and performing fusion operations, the division of off-road sub-regions becomes more reasonable and accurate, thereby improving the adaptability and control accuracy of the electric motorcycle in different off-road environments.

[0054] Step S300: Traverse the set of off-road sub-regions to analyze the frequency of historical motorcycle driving out of control, and configure the set of sensing monitoring frequency groups of the set of off-road sub-regions according to the analysis results, where each off-road sub-region corresponds to a sensing monitoring frequency group;

[0055] Furthermore, traverse the set of off-road sub-regions to analyze the frequency of historical motorcycle driving out of control, and configure the set of sensing monitoring frequency groups of the set of off-road sub-regions according to the analysis results. Step S300 of the embodiment of the present application further includes:

[0056] Analyze the frequency of historical motorcycle driving out of control of the set of off-road sub-regions according to the preset set of out-of-control indicators to determine the set of historical driving out-of-control frequencies of the sub-regions;

[0057] Divide the historical driving out-of-control frequency of each sub-region in the set of historical driving out-of-control frequencies of the sub-regions by the sum of the set of historical driving out-of-control frequencies of the sub-regions to obtain the set of out-of-control coefficients;

[0058] Multiply the set of out-of-control coefficients by the preset set of sensing monitoring frequency groups respectively to obtain the set of sensing monitoring frequency groups.

[0059] In an embodiment of the present application, the frequency of drive loss of control occurring during the driving of electric off-road motorcycles passing through the off-road sub-region set within a historical time is statistically analyzed. The purpose is to understand which sub-regions have a higher frequency of drive loss of control, so as to provide a basis for subsequent monitoring and control. The set of sensing monitoring frequency groups reflects the frequency group situation of the target electric off-road motorcycle analyzing road characteristics when passing through different off-road sub-regions. Among them, the off-road sub-regions and the sensing monitoring frequency groups correspond one by one.

[0060] Optionally, the preset loss-of-control index set refers to a set of indexes preset by those skilled in the art, which are used to measure whether a loss of control occurs during the off-road driving of an electric off-road motorcycle. These indexes may include abnormal vehicle speed, wheel slip, insufficient power, steering failure, etc. The sub-region historical drive loss-of-control frequency set is a frequency data set of loss-of-control events occurring in each off-road sub-region during historical driving, reflecting the loss-of-control frequency of different regions. The loss-of-control coefficient set is a coefficient set obtained by calculating the ratio of the loss-of-control frequency of each sub-region to the total loss-of-control frequency of all sub-regions. Each loss-of-control coefficient reflects the proportion of the loss-of-control risk of each sub-region relative to the entire region. The preset sensing monitoring frequency group set is a set of sensor monitoring frequencies preset by those skilled in the art.

[0061] In step S300, first, a frequent analysis of the historical motorcycle drive loss-of-control frequency of the off-road sub-region set is performed. The purpose of this analysis is to identify, through the statistics of historical data, which sub-regions have a higher frequency of drive loss of control. This step requires evaluating the historical loss-of-control frequency of each sub-region according to the preset loss-of-control index set to determine the sub-region historical drive loss-of-control frequency of each sub-region, and obtaining the sub-region historical drive loss-of-control frequency set. Furthermore, by calculating the ratio of the number of times of historical drive loss of control in each sub-region to the total number of times, the loss-of-control coefficient set is obtained. These loss-of-control coefficients reflect the relative risk of loss of control in each region.

[0062] Next, the greater the loss-of-control coefficient, the higher the risk of motor drive loss of control in this region, and the higher the sensing monitoring frequency should be. Multiply the loss-of-control coefficient set by the preset sensing monitoring frequency group set respectively to generate a sensing monitoring frequency group set corresponding to each sub-region one by one. Specifically, regions with a high loss-of-control coefficient (i.e., high-risk regions) will correspond to a higher sensor monitoring frequency, and regions with a low loss-of-control coefficient (i.e., low-risk regions) will correspond to a lower monitoring frequency.

[0063] By intelligently adjusting the working frequency of the sensor according to the historical loss-of-control data, the monitoring of high-risk regions is made more frequent and accurate, thereby improving the driving safety of electric off-road motorcycles in complex off-road environments.

[0064] Step S400: Obtain real-time positioning information according to the GIS positioning component of the target electric off-road motorcycle, match the real-time positioning information with the off-road sub-region set, and determine the real-time off-road sub-region set;

[0065] In a possible embodiment, the GIS positioning component refers to the Global Positioning System (GPS) or other positioning technology modules equipped on the target electric off-road motorcycle, which can obtain the geographical location information of the motorcycle in real time. The GIS (Geographic Information System) is used to process and analyze these geographical information.

[0066] First, obtain the geographical location information of the target electric off-road motorcycle in real time through the GIS positioning component. These location information may include parameters such as the longitude, latitude, and altitude of the motorcycle. Next, match these real-time positioning information with the previously generated off-road sub-region set. The process of position matching is to compare the current geographical location of the motorcycle with the boundaries of each off-road sub-region to determine the specific sub-region where the motorcycle is located.

[0067] Through this process, the system can determine the real-time off-road sub-region set where the motorcycle is located at each moment. This information is very crucial because different off-road sub-regions may have different terrain features and driving requirements. The real-time positioning information can help the system dynamically adjust the motor drive control parameters (such as torque and speed) of the motorcycle to ensure stability and safety during the driving process.

[0068] Step S500: Based on the real-time sensing and monitoring frequency group corresponding to the real-time off-road sub-region set in the sensing and monitoring frequency group set, construct an asynchronous extraction dual channel, use the asynchronous extraction dual channel to asynchronously extract the road images collected by the depth camera of the target electric off-road motorcycle, and use the fully connected network layer to perform road feature recognition on the extraction results to obtain the real-time road feature set;

[0069] In one embodiment, the real-time sensing and monitoring frequency group is a set of sensor monitoring frequencies matched for a real-time off-road sub-region, and this set of frequencies determines the frequency of monitoring the motorcycle driving road environment under real-time conditions. The asynchronous extraction dual-channel means that the two channels can work in parallel, but their extraction processes are not completely synchronized. This method can accelerate data processing and improve processing efficiency. The road image is the image data collected by the depth camera of the target electric off-road motorcycle, and usually includes information such as the texture of the road, obstacles, and slope. The fully connected network layer is a structure of a neural network, usually used to process image data. In this layer, all input nodes and output nodes are fully connected, and through these connections, feature learning can be performed on the extraction results. The real-time road feature set is a set of features of the road image processed by the fully connected network layer, and these feature information is used to analyze the current road conditions, including road surface conditions, obstacles, etc.

[0070] In step S500, first, the asynchronous extraction frequency of the road image collected by the depth camera is determined according to the real-time sensing and monitoring frequency group corresponding to the current real-time off-road sub-region set. The real-time sensing and monitoring frequency group specifies how often the collected road image is collected and extracted, so as to perform appropriate control according to the terrain conditions. Then, an asynchronous extraction dual-channel is constructed, that is, the road image information is asynchronously extracted from two different data streams in parallel, avoiding the delay that may be brought by synchronous processing.

[0071] These road images are collected by the depth camera of the electric off-road motorcycle. The depth camera can generate images with depth information, enabling the system to clearly perceive the road surface features. Next, the image data will be analyzed and processed through the fully connected network layer to extract useful road features (such as rough road surface, obstacles, slope, etc.). This set of extracted real-time road features provides a basis for subsequent motor drive control.

[0072] Furthermore, based on the real-time sensing and monitoring frequency group corresponding to the real-time off-road sub-region set in the sensing and monitoring frequency group set, an asynchronous extraction dual-channel is constructed, and the road image collected by the depth camera of the target electric off-road motorcycle is asynchronously extracted by using the asynchronous extraction dual-channel, and the road feature recognition is performed on the extraction result by using the fully connected network layer to obtain the real-time road feature set. Step S500 of the embodiment of the present application further includes:

[0073] Extract the first real-time sensing and monitoring frequency and the second real-time sensing and monitoring frequency in the real-time sensing and monitoring frequency group, wherein the first real-time sensing and monitoring frequency is less than the second real-time sensing and monitoring frequency;

[0074] Obtain a set of multiple sample road images and a set of multiple sample first asynchronous extraction results obtained by extracting the set of multiple sample road images according to the first real-time sensing monitoring frequency, and construct a first asynchronous extraction sub-channel;

[0075] Obtain a set of multiple sample road images and a set of multiple sample second asynchronous extraction results obtained by extracting the set of multiple sample road images according to the second real-time sensing monitoring frequency, and construct a second asynchronous extraction sub-channel;

[0076] Connect the first asynchronous extraction sub-channel and the second asynchronous extraction sub-channel in parallel to obtain the asynchronous extraction dual-channel.

[0077] Furthermore, step S500 of the embodiment of the present application further includes:

[0078] Obtain a set of multiple sample road feature sets corresponding to the set of multiple sample road images;

[0079] Based on the set of multiple sample road feature sets, the set of multiple sample first asynchronous extraction results, and the set of multiple sample second asynchronous extraction results, perform network layer training until convergence to obtain the trained fully connected network layer.

[0080] In an embodiment of the present application, the real-time sensing monitoring frequency group includes a first real-time sensing monitoring frequency and a second real-time sensing monitoring frequency. These two respectively represent different data acquisition frequencies for road images in real-time monitoring. The images extracted at the first real-time sensing monitoring frequency are used to monitor the overall terrain features, and the images extracted at the second real-time sensing monitoring frequency are used to monitor instantaneous dynamic changes.

[0081] Obtain a set of multiple sample road images and a set of multiple sample first asynchronous extraction results obtained by extracting the set of multiple sample road images according to the first real-time sensing monitoring frequency. Use the set of multiple sample road images, the first real-time sensing monitoring frequency, and the set of multiple sample first asynchronous extraction results as training data, and use the backpropagation algorithm to train the framework constructed based on the convolutional neural network, and gradually adjust the network parameters so that the network can more accurately extract images according to the first real-time sensing monitoring frequency until the training converges to obtain the trained first asynchronous extraction sub-channel.

[0082] Obtain a set of multiple sample road images and a set of multiple sample second asynchronous extraction results obtained by extracting the set of multiple sample road images according to the second real-time sensing monitoring frequency. Use the set of multiple sample road images, the second real-time sensing monitoring frequency, and the set of multiple sample second asynchronous extraction results as training data, and train the second asynchronous extraction sub-channel based on the same principle as obtaining the first asynchronous extraction sub-channel.

[0083] Optionally, the first asynchronous extraction sub-channel is used to extract the road images collected by the depth camera at the first real-time sensing monitoring frequency to obtain a first asynchronous extraction result. The second asynchronous extraction sub-channel is used to extract the road images collected by the depth camera at the second real-time sensing monitoring frequency to obtain a second asynchronous extraction result. Then, these two sub-channels are combined together in a parallel connection manner to achieve the overall operation of the asynchronous extraction dual-channel. The first asynchronous extraction result and the second asynchronous extraction result are used as the inputs of the fully connected network layer. Through the training of a large number of sample data, the network can optimize its feature extraction ability and learn more accurate road features. The purpose of this process is to ensure that the system can accurately identify and understand road features according to the changes in the real-time environment, and provide accurate information support for the subsequent motor control.

[0084] In a possible embodiment, deep learning training is performed by obtaining multiple sample road feature sets and corresponding multiple sample first asynchronous extraction results and multiple sample second asynchronous extraction results. The goal of network training is to use these data to optimize the weights of the fully connected network layer and improve the recognition ability of different road features. The fully connected network layer is trained through the backpropagation algorithm, and its parameters are gradually adjusted so that the network can more accurately identify road features. This process will continue during training until the network reaches the optimal state, that is, convergence. Through such training, the system can better extract useful information from road images, improve the accuracy of road feature recognition, and provide more accurate data support for the motor drive control of the electric motorcycle.

[0085] Step S600: Using the real-time road feature set as the drive control analysis object, perform adaptive drive control on the motor of the target electric off-road motorcycle.

[0086] In one embodiment, the previously obtained real-time road feature set is used as the drive control analysis object to perform motor adaptive drive control. That is, according to the real-time obtained road information (such as slope, ground roughness, obstacles, etc.), the motor of the electric motorcycle is dynamically adjusted to change the torque and speed of the motor. This adjustment can make the motorcycle better adapt to the current road conditions and improve the driving smoothness and safety. For example, on rough terrain, the output of the motor may need to be increased to provide greater driving force, while on a flat road, the output of the motor may be appropriately reduced to save energy.

[0087] In summary, the motor drive control method for an electric off-road motorcycle provided by the embodiments of the present application has the following technical effects:

[0088] This application obtains the terrain roughness distribution map and sensing data, dynamically adjusts the driving parameters of the motor (such as torque and speed), realizes rapid response to different off-road terrains, thereby improving the stability and driving experience of the motorcycle in complex environments. At the same time, it uses a depth camera and asynchronous extraction of dual channels to efficiently extract road features, and accurately identifies them through a fully connected neural network to grasp the road conditions in real time, providing accurate basis for motor control. In addition, by combining historical out-of-control frequency analysis and configuring adaptive monitoring frequencies according to different off-road sub-regions, the efficiency and accuracy of sensor data collection are improved, achieving the technical effect of improving the fitting degree between motor drive control and the actual road and improving the control quality.

[0089] Embodiment 2, as Figure 2 shown, is a schematic structural diagram of an exemplary electronic device of this application. In Figure 2 , the bus architecture is represented by bus 300. Bus 300 can include any number of interconnected buses and bridges. Bus 300 connects various circuits including one or more processors represented by processor 302 and a memory represented by memory 304 together. Bus 300 can also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art, so they will not be further described herein. Bus interface 305 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 can be the same element, that is, a transceiver, providing a unit for communicating with various other devices on the transmission medium. Processor 302 is responsible for managing bus 300 and general processing, while memory 304 can be used to store data used by processor 302 when performing operations.

[0090] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0091] The above description of the disclosed embodiments enables those skilled in the art to implement or use this application. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application will not be limited to these embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A motor drive control method for an electric off-road motorcycle, characterized in that: The method comprises: Obtaining a target off-road area for a target electric off-road motorcycle, and based on the geographical location information of the target off-road area, calling a GIS system to extract a terrain roughness distribution map to obtain a regional terrain roughness distribution map; Performing flood segmentation on the regional terrain roughness distribution map, dividing the target off-road area into sub-areas according to the ridge lines generated in the segmentation process, and obtaining an off-road sub-area set; Traversing the off-road sub-area set to perform a frequency analysis of the historical motorcycle driving out-of-control frequency, and configuring a sensor monitoring frequency group set of the off-road sub-area set according to the analysis result, wherein the off-road sub-area and the sensor monitoring frequency group correspond one to one; According to the GIS positioning component of the target electric off-road motorcycle, real-time positioning information is acquired, and the real-time positioning information is matched with the off-road sub-area set to determine the real-time off-road sub-area set; Based on the real-time sensor monitoring frequency group corresponding to the real-time off-road sub-area set in the sensor monitoring frequency group set, an asynchronous extraction dual channel is constructed, and the road image collected by the depth camera of the target electric off-road motorcycle is asynchronously extracted by using the asynchronous extraction dual channel, and the road feature recognition is performed on the extraction result by using a fully connected network layer to obtain a real-time road feature set, including: Extracting a first real-time sensing monitoring frequency and a second real-time sensing monitoring frequency from the real-time sensing monitoring frequency group, wherein the first real-time sensing monitoring frequency is less than the second real-time sensing monitoring frequency; Acquire a plurality of sample road image sets and a plurality of sample first asynchronous extraction results obtained after extracting the plurality of sample road image sets according to a first real-time sensing monitoring frequency, and construct a first asynchronous extraction subchannel; Acquire multiple sample road image sets and multiple sample second asynchronous extraction results obtained after extracting the multiple sample road image sets according to a second real-time sensing monitoring frequency, and construct a second asynchronous extraction sub-channel; Connecting the first asynchronous extraction sub-channel and the second asynchronous extraction sub-channel in parallel to obtain the asynchronous extraction dual-channel; The real-time road feature set is used as a driving control analysis object, and adaptive driving control is performed on the electric motor of the target electric off-road motorcycle.

2. The motor drive control method of an electric off-road motorcycle according to claim 1, characterized in that: Performing flood segmentation on the regional terrain roughness distribution map, dividing the target off-road area into sub-areas according to the ridge lines generated in the segmentation process, and obtaining an off-road sub-area set, including: Obtaining the lowest point of terrain roughness of the regional terrain roughness distribution map, taking the lowest point of terrain roughness as the flooding starting point, simulating water injection into the regional terrain roughness distribution map, and when the water surface overflows any terrain roughness distribution point in the regional terrain roughness distribution map, determining whether the roughness difference between the terrain roughness distribution point and the lowest point of terrain roughness is less than or equal to a preset roughness difference threshold, and if so, continuing to inject water into the regional terrain roughness distribution map; If not, after generating a regional dividing ridge line between the terrain roughness distribution point and the lowest point of the terrain roughness, continue to inject water into the regional terrain roughness distribution map until the water surface overflows the highest point of the terrain roughness in the regional terrain roughness distribution map, stop injecting water, and obtain a set of regional dividing ridge lines, wherein the regional dividing ridge lines rise as the water surface rises; The area dividing ridge line sets are connected to each other, and the target off-road area is divided into sub-areas to obtain the off-road sub-area set.

3. The motor drive control method of the electric off-road motorcycle according to claim 2, characterized in that: Connecting the area dividing ridge line sets to each other, dividing the target off-road area into sub-areas, and obtaining the off-road sub-area set, including: Connecting the area dividing ridge line sets to each other, dividing the target off-road area according to the connection results, and obtaining an initial off-road sub-area set; Traversing the initial off-road sub-region set to perform sub-region area statistics to obtain an initial off-road sub-region area set; When the area set of the initial off-road sub-regions is less than or equal to the preset off-road sub-region area threshold, the corresponding initial off-road sub-region is added to the off-road sub-region set to be merged; When the area set of the initial off-road sub-region is larger than the preset off-road sub-region area threshold, the corresponding initial off-road sub-region is added into the fused off-road sub-region set; Initial off-road sub-region fusion is performed based on the sub-region positions of the off-road sub-region set to be fused and the off-road sub-region set that can be fused, so as to obtain the off-road sub-region set.

4. The motor drive control method for an electric off-road motorcycle according to claim 3, characterized in that: Performing initial off-road sub-region fusion based on the sub-region positions of the off-road sub-region set to be fused and the off-road sub-region set that can be fused to obtain the off-road sub-region set includes: Randomly extracting a first off-road sub-region to be fused from the set of off-road sub-regions to be fused; According to the sub-region position, the neighborhood of the first off-road sub-region to be fused is matched from the set of off-road sub-regions that can be fused, so as to obtain the neighborhood of the first off-road sub-region that can be fused; Acquire a first fused off-road sub-region neighborhood area set of the first fused off-road sub-region neighborhood; Traversing and counting the distances from the first fused off-road sub-region neighborhood to the first to-be-fused off-road sub-region, to obtain a first fused off-road sub-region neighborhood distance set; Performing weighted calculation on the first fused off-road sub-region neighborhood area set and the first fused off-road sub-region neighborhood distance set to obtain a first fused off-road sub-region neighborhood fusion coefficient set; The first off-road sub-region to be fused is integrated into the off-road sub-region that can be fused corresponding to the maximum value in the neighborhood fusion coefficient set of the first off-road sub-region that can be fused, to obtain the first off-road sub-region; The sub-region positions of the off-road sub-region set to be merged and the off-road sub-region set that can be merged are initially merged into an off-road sub-region to obtain the off-road sub-region set.

5. The motor drive control method for an electric off-road motorcycle according to claim 1, characterized in that: Traversing the off-road sub-area set to perform a frequency analysis of the historical motorcycle driving out-of-control frequency, and configuring the sensor monitoring frequency group set of the off-road sub-area set according to the analysis result, including: Analyzing the frequency of historical motorcycle driving out-of-control in the off-road sub-area set according to a preset out-of-control index set to determine a sub-area historical driving out-of-control frequency set; Dividing the historical driving out-of-control frequency of each sub-region in the historical driving out-of-control frequency set of the sub-regions by the sum of the historical driving out-of-control frequency set of the sub-regions, respectively, to obtain an out-of-control coefficient set; The out-of-control coefficient set is multiplied by the preset sensor monitoring frequency group set respectively to obtain the sensor monitoring frequency group set.

6. The motor drive control method for an electric off-road motorcycle according to claim 1, characterized in that: include: Acquire a plurality of sample road feature sets corresponding to the plurality of sample road image sets; Based on the multiple sample road feature sets, the multiple sample first asynchronous extraction results and the multiple sample second asynchronous extraction results, network layer training is performed until convergence to obtain the trained fully connected network layer.

7. An electronic device, characterized in that: The electronic device comprises: A memory for storing executable instructions; The processor is used to implement the motor drive control method of the electric off-road motorcycle according to any one of claims 1 to 6 when executing the executable instructions stored in the memory.

Images