Data acquisition mode determination method and device, equipment, storage medium and product

Abstract

The invention discloses a data acquisition mode determination method and device, equipment, a storage medium and a product. The method comprises the steps of determining a target road condition score of a road section where a target vehicle is located according to road surface information and vehicle information in the driving process of the target vehicle; wherein the control unit of the data acquisition module in the target vehicle is integrated in the intelligent driving domain controller; determining a target weight corresponding to each target sensor in the data acquisition module according to the target road condition score; wherein the target sensor is used for collecting target data, and the target data is used for determining the road section category of the road section where the target vehicle is located; and fusing the target data acquired by each target sensor according to each target weight to obtain a fused feature vector, and determining a target working mode of the data acquisition module according to the fused feature vector. The working mode of the data acquisition module can be dynamically adjusted according to the road condition information, so that stable operation of the intelligent driving system is ensured.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and in particular to methods, apparatus, equipment, storage media, and products for determining data acquisition modes. Background Technology

[0002] In intelligent driving systems, to ensure real-time data transmission and simplify system architecture, the control unit of the data acquisition module is typically integrated into the vehicle's intelligent driving domain controller. Currently, under this integrated architecture, the data acquisition module usually operates in a uniform mode, resulting in a large amount of redundant data during acquisition, and the data acquisition module continuously consumes the intelligent driving domain controller's computing, storage, and communication resources. Therefore, a more efficient method for determining the data acquisition mode is urgently needed to balance the resource consumption of the intelligent driving domain controller by the data acquisition module and other functional modules, thereby ensuring the stable operation of the intelligent driving system. Summary of the Invention

[0003] This invention provides a method, apparatus, device, storage medium, and product for determining data acquisition modes, so as to enable the working mode of the data acquisition module to be dynamically switched according to road condition information.

[0004] According to one aspect of the present invention, a method for determining a data acquisition mode is provided, comprising: Based on road surface and vehicle information during the target vehicle's driving process, the target road condition score for the road segment where the target vehicle is located is determined; wherein, the control unit of the data acquisition module in the target vehicle is integrated in the intelligent driving domain controller, and the intelligent driving domain controller is used to control the working mode of the data acquisition module; The target weights corresponding to each target sensor in the data acquisition module are determined based on the target road condition score; wherein, the target sensors are used to collect target data, and the target data is used to determine the road segment category of the road segment where the target vehicle is located; The target data collected by each target sensor are fused according to the target weights to obtain a fused feature vector, and the target working mode of the data acquisition module is determined based on the fused feature vector.

[0005] According to another aspect of the present invention, a data acquisition mode determination apparatus is provided, comprising: The road condition score determination module is used to determine the target road condition score of the road segment where the target vehicle is located based on the road surface information and vehicle information during the target vehicle's driving process; wherein, the control unit of the data acquisition module in the target vehicle is integrated in the intelligent driving domain controller, and the intelligent driving domain controller is used to control the working mode of the data acquisition module; The weight determination module is used to determine the target weights corresponding to each target sensor in the data acquisition module based on the target road condition score; wherein, the target sensors are used to collect target data, and the target data is used to determine the road segment category of the road segment where the target vehicle is located; The working mode determination module is used to fuse the target data collected by each target sensor according to the target weights to obtain a fused feature vector, and to determine the target working mode of the data acquisition module based on the fused feature vector.

[0006] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the data acquisition mode determination method according to any embodiment of the present invention.

[0007] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the data acquisition mode determination method according to any embodiment of the present invention.

[0008] According to another aspect of the present invention, a computer program product is provided, the computer program product comprising a computer program that, when executed by a processor, implements the data acquisition mode determination method according to any embodiment of the present invention.

[0009] The technical solution of this invention determines the target road condition score of the road segment where the target vehicle is located based on road surface information and vehicle information during the target vehicle's driving process. The control unit of the data acquisition module in the target vehicle is integrated into an intelligent driving domain controller, which controls the operating mode of the data acquisition module. The target weights corresponding to each target sensor in the data acquisition module are determined based on the target road condition score. The target sensors collect target data, which is used to determine the road segment category of the road segment where the target vehicle is located. The target data collected by each target sensor is fused according to each target weight to obtain a fused feature vector, and the target operating mode of the data acquisition module is determined based on the fused feature vector. This invention determines the target road condition score for the current road segment based on road surface and vehicle information, ensuring that the obtained target road condition score fully reflects the road condition information of the current road segment. By determining the target weights of each target sensor based on the target road condition score, dynamic adjustment of the target weights is achieved, and the fused feature vector after fusion can fully reflect the road condition characteristics of the current road segment. This ensures that the determined target operating mode is more adapted to the current road segment, thereby ensuring that the target vehicle can dynamically adjust the operating mode of the data acquisition module according to the road condition information of the current road segment. This balances the resource consumption of the data acquisition module and other functional modules on the controller, ensuring the stable operation of the intelligent driving system in the target vehicle.

[0010] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a flowchart of a data acquisition mode determination method provided in Embodiment 1 of the present invention; Figure 2 This is a flowchart of a data acquisition mode determination method provided in Embodiment 2 of the present invention; Figure 3 This is a schematic diagram of a data acquisition mode determination device according to Embodiment 3 of the present invention; Figure 4 This is a schematic diagram of the structure of an electronic device that implements the data acquisition mode determination method of this invention. Detailed Implementation

[0013] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0014] It should be noted that the terms "first," "second," "initial," and "target," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0015] Example 1 Figure 1 This is a flowchart illustrating a data acquisition mode determination method provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where the data acquisition working mode is adjusted. The method can be executed by a data acquisition mode determination device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes: S101. Based on the road surface information and vehicle information during the target vehicle's driving process, determine the target road condition score for the road segment where the target vehicle is located; wherein, the control unit of the data acquisition module in the target vehicle is integrated in the intelligent driving domain controller, and the intelligent driving domain controller is used to control the working mode of the data acquisition module.

[0016] In this embodiment, the target vehicle can be a vehicle with intelligent driving capabilities, such as a commercial vehicle or a passenger vehicle. The intelligent driving domain controller of the target vehicle integrates a control unit for data acquisition modules (e.g., onboard cameras, LiDAR sensors, and wheel speed sensors). Therefore, the intelligent driving domain controller can be used to control and adjust the operating mode of the data acquisition modules, such as switching the sampling frequency of each sensor in the data acquisition module and controlling the signal transmission of each sensor. Since the target vehicle is driving on unstructured roads, the complex and changing road conditions will cause the data acquisition module to collect a large amount of redundant and low-quality data, resulting in the data acquisition module consuming a large amount of computing, storage, and communication resources in the intelligent driving domain controller. Therefore, the road information and vehicle information during the target vehicle's driving process can be used as the basis for subsequently determining the operating mode of the data acquisition module.

[0017] For example, road surface information may include road information and environmental information during the target vehicle's travel. For instance, road information may include road type and road surface smoothness, while environmental information may include road congestion level and obstacle distribution data. Vehicle information may include vehicle dynamic parameters and vehicle state parameters, such as speed, acceleration, and vehicle attitude.

[0018] For example, road surface information and vehicle information during the current driving process of the target vehicle are obtained, and the target road condition score of the current road segment is determined according to a preset mapping relationship. The preset mapping relationship can be determined based on historical data. For example, a dataset is constructed based on historical road surface information and historical vehicle information collected within a historical period. The sample labels of the dataset are road condition scores (which can be manually labeled). A preset machine learning model (e.g., decision tree and random forest models) is trained using the dataset so that the preset machine learning model can learn the preset mapping relationship between road surface information, vehicle information and road condition scores. During the driving process of the target vehicle, the road surface information and vehicle information can be input into the preset machine learning model, and the target road condition score is determined based on the output of the preset machine learning model.

[0019] S102. Determine the target weights corresponding to each target sensor in the data acquisition module based on the target road condition score; wherein, the target sensor is used to collect target data, and the target data is used to determine the road segment category of the road segment where the target vehicle is located.

[0020] In this embodiment, the target sensor may include an in-vehicle camera, an in-vehicle LiDAR, and an in-vehicle positioning sensor. The target sensor is used to collect target data, which can be used to subsequently determine the road segment category of the target vehicle's current location. The target data may include image data, point cloud data, and 3D coordinate data. Different road segments may correspond to different road segment categories, which can be divided according to actual application scenarios, such as muddy roads, gravel roads, steep slopes, and waterlogged roads. Each target sensor may correspond to a target weight, which can be determined based on the target road condition score. For example, a pre-defined table of correspondence between road condition scores and target weights can be used to determine the target weight of each target sensor using a lookup table.

[0021] S103. Based on the weight of each target, the target data collected by each target sensor is fused to obtain a fused feature vector, and the target working mode of the data acquisition module is determined based on the fused feature vector.

[0022] For example, feature extraction is performed on the target data collected by each target sensor using a preset neural network model (e.g., a convolutional neural network model) to obtain the feature vectors corresponding to each sensor; the feature vectors are aligned and then fused according to the target weights corresponding to each sensor to obtain a fused feature vector; the road segment category of the current road segment is determined based on the fused feature vector, and then the target working mode of the data acquisition module is determined based on the road segment category; wherein, the working state of the data acquisition module is different under different working modes, for example, the sampling frequency and the data transmission rate are different.

[0023] This invention provides a method for determining a data acquisition mode. By determining the target road condition score of the current road segment based on road surface information and vehicle information, it ensures that the obtained target road condition score fully reflects the road condition information of the current road segment. By determining the target weight of each target sensor based on the target road condition score, it achieves dynamic adjustment of the target weight and ensures that the fused feature vector after fusion fully reflects the road condition characteristics of the current road segment. This ensures that the determined target working mode is more adapted to the current road segment, thereby ensuring that the target vehicle can dynamically adjust the working mode of the data acquisition module according to the road condition information of the current road segment. This balances the occupation of controller resources by the data acquisition module and other functional modules, ensuring the stable operation of the intelligent driving system in the target vehicle.

[0024] Example 2 Figure 2 This is a flowchart of a data acquisition mode determination method provided in Embodiment 2 of the present invention. This embodiment is a refinement based on the above embodiments. Figure 2 As shown, the method includes: S201. Determine the road surface adhesion coefficient based on the wheel speed difference of the target vehicle and the braking state of the target vehicle.

[0025] In this embodiment, the wheel speed difference of the target vehicle can be determined based on the data collected by the wheel speed sensor. For example, the wheel speed difference can be determined based on the rotational speed of each wheel collected by the wheel speed sensor. The braking state of the target vehicle can be determined based on the trigger signal of the Electronic Braking System (EBS).

[0026] For example, based on the rotational speed and radius of each wheel collected by the wheel speed sensor, the linear velocity of each wheel is determined, thereby obtaining the left-right wheel speed difference and the front-rear wheel speed difference. The current braking state of the target vehicle (e.g., no braking, light braking, and heavy braking, etc., the category and criteria for braking state can be set according to the actual application scenario) is determined based on the EBS trigger signal (e.g., brake pedal trigger signal, and brake master cylinder pressure signal, etc.). The corresponding road adhesion coefficient is queried in a preset relationship table using the wheel speed difference and braking state as index information. The preset relationship table records the correspondence between different wheel speed differences and road adhesion coefficients under different braking states. The preset relationship table can include the correspondence between wheel speed difference intervals and road adhesion coefficients under various braking states. This preset relationship table can be pre-built; for example, under different road adhesion coefficients, the preset relationship table can be obtained by multiple calibrations based on historical wheel speed differences and historical braking states collected over a historical period.

[0027] S202. Determine the road slope based on the acceleration collected by the inertial measurement unit of the target vehicle.

[0028] For example, the acceleration can be the longitudinal acceleration output by the inertial measurement unit of the target vehicle (which can be understood as the acceleration perpendicular to the road surface direction), and the road slope can be determined according to the trigonometric function relationship between the longitudinal acceleration and the gravitational acceleration.

[0029] S203. Determine the vehicle load based on the air pressure data collected by the air pressure sensor and the displacement data collected by the suspension displacement sensor of the target vehicle.

[0030] In this embodiment, the air pressure data can be the air pressure of the suspension airbag collected by the air pressure sensor, and the displacement data can be the extension and retraction displacement of the suspension airbag collected by the suspension displacement sensor.

[0031] For example, the vehicle load is determined based on the air pressure data collected by the air pressure sensor and the displacement data collected by the suspension displacement sensor of the target vehicle, according to the dynamic balance characteristics. For instance, for a single suspension airbag, the pressure-bearing area of ​​the suspension airbag can be determined based on the expansion and contraction displacement of the suspension airbag, and the bearing pressure of the suspension airbag is determined based on the product of the pressure-bearing area and the air pressure of the suspension airbag. The bearing pressures of all suspension airbags in the target vehicle are summed to obtain the total bearing pressure, and then the vehicle load is determined based on the ratio of the total bearing pressure to the gravitational acceleration.

[0032] S204. Based on the road surface information and vehicle information during the target vehicle's journey, determine the target road condition score for the road segment where the target vehicle is located; whereby the road surface information includes the road surface adhesion coefficient and the road surface slope; and the vehicle information includes the vehicle load.

[0033] For example, the road surface adhesion coefficient, road surface slope, and vehicle load during the target vehicle's driving process are weighted and summed according to preset weights. Based on the weighted summation result, the target road condition score of the road segment where the target vehicle is located is determined. The road surface adhesion coefficient, road surface slope, and vehicle load each correspond to a preset weight. The values ​​of each preset weight can be set based on experience or optimized using models such as machine learning or genetic learning.

[0034] When determining the road segment score, the road surface adhesion coefficient, road surface slope, and vehicle load are introduced to ensure that the calculated target road condition score can fully reflect the actual road condition characteristics and vehicle characteristics of the road segment. This ensures that the sensor weights determined based on the target road condition score are more closely matched with the road condition characteristics, thereby improving the accuracy of road segment category identification.

[0035] Optionally, the target road condition score for the road segment where the target vehicle is located is determined based on the weighted summation result, including: obtaining an initial road condition score based on the weighted summation result; applying a preset correction value to the initial road condition score using a linear offset correction to obtain the target road condition score for the road segment where the target vehicle is located; wherein, the preset weights and the preset correction value are determined based on a preset genetic algorithm, and the fitness function of the preset genetic algorithm is constructed based on the prediction accuracy of the road condition score. By applying a preset correction value to the initial road condition score using a linear offset correction, the correlation between the target road condition score and the road surface adhesion coefficient, road surface slope, and vehicle load can be further strengthened, thereby making the target road condition score more accurate; and constructing the fitness function of the preset genetic algorithm based on the prediction accuracy of the road condition score can ensure that the selected combination of preset weights and preset correction values ​​can avoid the deviation set by manual settings, further improving the matching degree between the target road condition score and the actual road conditions.

[0036] For example, the target road condition score is determined using the following expression: ; in, Represents the target road condition score; Represents the road surface adhesion coefficient. The preset weights represent the road surface adhesion coefficients. Represents the vehicle's load capacity. The preset weights represent the vehicle's load capacity. Represents the road surface slope. The preset weights represent the road surface slope; Represents the preset correction value; where, , , ,as well as The parameters are determined according to a preset genetic algorithm. For example, an initial parameter population can be constructed, which includes multiple parameter combinations. Each parameter combination includes various weight values ​​and correction values. The fitness function can be constructed based on the preset accuracy of the road condition score, for example, based on the root mean square error function. The predicted road condition score can be determined according to the formula for calculating the target road condition score. In each iteration, the population is subjected to selection, crossover, and mutation operations to screen parameter combinations whose fitness values ​​meet preset conditions (e.g., fitness is less than a first preset fitness threshold). The above iteration process is repeated until the optimization conditions are met (e.g., the number of iterations reaches an iteration threshold or the fitness value meets a second preset fitness threshold), thus obtaining the preset weight and preset correction value combination.

[0037] S205. Determine the target weights corresponding to each target sensor in the data acquisition module based on the target road condition score; wherein, the target sensor is used to collect target data, and the target data is used to determine the road segment category of the road segment where the target vehicle is located.

[0038] S206. Based on the weight of each target, the target data collected by each target sensor is fused to obtain a fused feature vector, and the target working mode of the data acquisition module is determined based on the fused feature vector.

[0039] This invention, based on data collected by vehicle-mounted sensors (e.g., wheel speed difference, vehicle status, acceleration, air pressure data, and displacement data), determines the road surface adhesion coefficient, road surface slope, and vehicle load through a simple and efficient calculation method, without requiring additional equipment and reducing production costs. Specifically, combining wheel speed difference and braking status accurately reflects the actual road surface adhesion characteristics, ensuring a more precise road surface adhesion coefficient. The road surface slope is determined based on acceleration collected by the inertial measurement unit, and the vehicle load is determined based on air pressure data collected by the air pressure sensor and displacement data collected by the suspension displacement sensor. These steps fully integrate geometric and physical characteristics, ensuring a simple calculation process and, compared to black-box computation, guaranteeing accurate and interpretable results. When determining the road condition score, by introducing the road surface adhesion coefficient, road surface slope, and vehicle load, the calculated target road condition score fully reflects the actual road condition characteristics and vehicle characteristics, thereby ensuring that the sensor weights determined based on the target road condition score are more closely matched to the road condition characteristics, improving the accuracy of road segment category identification.

[0040] In some embodiments, determining the target weights corresponding to each target sensor in the data acquisition module based on the target road condition score includes: querying a target preset road condition score corresponding to the target road condition score in a preset mapping table; wherein, the preset mapping table is used to record the mapping relationship between different preset road condition scores and preset weights of each target sensor; and determining the target weights corresponding to each target sensor in the data acquisition module based on the preset weights of each target sensor corresponding to the target preset road condition score in the preset mapping table. The advantage of this setup is that determining the target weights of each target sensor using a lookup table reduces computational complexity, ensures that the vehicle can save computational resources under complex road conditions, quickly determine target weights, reserve more computational resources for other modules, and ensure stable vehicle operation.

[0041] In this embodiment, the preset mapping table may include multiple pieces of structured data. Each piece of structured data may include a preset road condition score and the preset weights of each target sensor corresponding to the preset road condition score. The preset road condition score is generally a score range, and the preset weights of each target sensor may be parameter combinations. Different preset road condition scores correspond to different preset weight parameter combinations. Each preset weight parameter combination may be predetermined, for example, set according to empirical values ​​or determined according to a machine learning algorithm model. If the preset weight parameter combinations are determined based on a cluster learning algorithm model, a loss function can be constructed based on the classification accuracy of road segment categories. Thus, the preset weight parameters can be optimized through the backpropagation mechanism of the machine learning algorithm to achieve a deep association between the preset weight parameters and road segment categories. This ensures that during actual driving, the fused feature vector obtained by fusing target data according to the target weights can fully reflect the characteristics of different road segment categories.

[0042] For example, taking a target sensor including an in-vehicle camera, an in-vehicle LiDAR, and an in-vehicle positioning sensor as an example, the calculated target road condition score is x, and the corresponding target preset road condition score in the preset mapping table is the y interval. The preset weight parameter combination of each sensor corresponding to the y interval is queried (e.g., z1, z2, and z3). Then, when fusing the target data collected by each sensor, z1, z2, and z3 can be used as target weights.

[0043] In some embodiments, determining the target operating mode of the data acquisition module based on the fused feature vector includes: determining the road segment category corresponding to the fused feature vector using a preset classifier; and querying the target operating mode corresponding to the road segment category in a preset parameter mapping table. The preset parameter mapping table records the mapping relationship between different road segment categories and various operating modes, with different operating modes associated with different combinations of acquisition parameters. The advantage of this setup is that associating road segment categories with the operating modes of the data acquisition module ensures that the vehicle can automatically switch the operating modes of the data acquisition module under different road conditions. This ensures that the vehicle uses different acquisition parameters under simple and complex road conditions, thereby ensuring that the autonomous driving system can reasonably allocate resources to different modules under different road conditions, thus guaranteeing driving safety.

[0044] In this embodiment, the preset classifier is a pre-trained classifier, which can be a classifier built based on a machine learning model. Inputting the fused feature vector into the preset classifier will output a label corresponding to the road segment category. The preset parameter mapping table may include a road segment category field and a working mode field. The road segment category field can store identification information related to the road segment category, such as the label corresponding to the road segment category. The working mode field can store the combination of acquisition parameters of the data acquisition module in this working mode, such as acquisition frequency parameters, data transmission rate, and the start / stop status of each sensor.

[0045] For example, by inputting the fused feature vector into a preset classifier, it can be determined that the target vehicle is currently driving on a steep slope. Then, the operating parameters of each sensor in the data acquisition module on the steep slope can be queried from the preset parameter mapping table, thereby determining the target operating mode. For example, the sampling frequency of vision sensors, radar sensors, and the Controller Area Network (CAN) bus can be reduced to the corresponding preset frequency.

[0046] Optionally, when the target operating mode of the data acquisition module is determined based on the fused feature vector, the target vehicle switches its driving mode to the target driving mode; wherein, the target driving mode is associated with the target operating mode. The advantage of this setup is that, by associating the data acquisition module with the vehicle's driving mode, the vehicle can automatically switch between the operating mode of the data acquisition module and the driving mode under different road conditions, further ensuring driving safety.

[0047] For example, if the current target vehicle is determined to be traveling on a flooded road section based on a preset classifier, the operating parameters corresponding to the data acquisition module under the flooded road section can be queried from a preset parameter mapping table. For example, the data transmission from visual sensors and radar sensors to the intelligent driving domain controller can be stopped, and the driving mode can be switched to the target driving mode corresponding to the current target operating mode, such as triggering a path planning algorithm to replan the path. The relationship between the target operating mode and the target driving mode can be recorded through table information, or the corresponding driving mode can be found by identifying the keywords of the operating mode. This invention does not limit the way the two are associated.

[0048] For example, a target detection model and a Kalman filter trajectory prediction model are deployed in the vehicle's industrial control computer. During the vehicle's operation, visual sensors collect image data in real time and compress the collected image data. Vehicle attitude sensors (e.g., inertial measurement units and wheel speed sensors) collect vehicle chassis data (e.g., vehicle acceleration and wheel speed difference) in real time. The collected image data and vehicle chassis data are transmitted back to the vehicle's industrial control computer at a preset rate (e.g., 500kbps) via a Controller Area Network with Flexible Data-Rate (CAN-FD) bus. In the vehicle's industrial control computer, the collected image data are fused according to the weights of each sensor to obtain a fused feature vector. The target detection model extracts various features (e.g., pedestrian features, vehicle features, and obstacle features) from the fused feature vector to determine the current road segment category. The working mode of the data acquisition module is switched, and the predicted target trajectory is obtained through the Kalman filter trajectory prediction model. The target vehicle switches to the driving mode associated with the current road segment category and determines a new driving route based on the target trajectory.

[0049] Example 3 Figure 3 This is a schematic diagram of a data acquisition mode determination device provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes: a road condition score determination module 301, a weight determination module 302, and a working mode determination module 303.

[0050] The road condition score determination module is used to determine the target road condition score of the road segment where the target vehicle is located based on the road surface information and vehicle information during the target vehicle's driving process; wherein, the control unit of the data acquisition module in the target vehicle is integrated in the intelligent driving domain controller, and the intelligent driving domain controller is used to control the working mode of the data acquisition module; The weight determination module is used to determine the target weights corresponding to each target sensor in the data acquisition module based on the target road condition score; wherein, the target sensors are used to collect target data, and the target data is used to determine the road segment category of the road segment where the target vehicle is located; The working mode determination module is used to fuse the target data collected by each target sensor according to the target weights to obtain a fused feature vector, and to determine the target working mode of the data acquisition module based on the fused feature vector.

[0051] This invention provides a data acquisition mode determination device. By determining the target road condition score of the current road segment based on road surface information and vehicle information, it ensures that the obtained target road condition score fully reflects the road condition information of the current road segment. By determining the target weight of each target sensor based on the target road condition score, it achieves dynamic adjustment of the target weight and ensures that the fused feature vector after fusion can fully reflect the road condition characteristics of the current road segment. This ensures that the determined target working mode is more adapted to the current road segment, thereby ensuring that the target vehicle can dynamically adjust the working mode of the data acquisition module according to the road condition information of the current road segment. This balances the occupation of controller resources by the data acquisition module and other functional modules, ensuring the stable operation of the intelligent driving system in the target vehicle.

[0052] Optionally, the road surface information includes the road surface adhesion coefficient and road surface slope; the vehicle information includes the vehicle load; and the device further includes: The road surface adhesion coefficient determination module is used to determine the road surface adhesion coefficient based on the wheel speed difference of the target vehicle and the braking state of the target vehicle before determining the target road condition score of the road segment where the target vehicle is located based on the road surface information and vehicle information during the target vehicle's driving process. The road slope determination module is used to determine the road slope based on the acceleration collected by the inertial measurement unit of the target vehicle before determining the target road condition score of the road segment where the target vehicle is located based on the road surface information and vehicle information during the target vehicle's driving process. The vehicle load determination module is used to determine the vehicle load based on the air pressure data collected by the air pressure sensor of the target vehicle and the displacement data collected by the suspension displacement sensor.

[0053] Optional, the road condition score determination module is specifically used for: The road surface adhesion coefficient, road surface slope, and vehicle load during the target vehicle's driving process are weighted and summed according to preset weights. Based on the weighted summation result, the target road condition score of the road segment where the target vehicle is located is determined.

[0054] Optional, the road condition score determination module includes: The summation unit is used to perform weighted summation of the road adhesion coefficient, road slope, and vehicle load during the target vehicle's driving process according to preset weights. The initial road condition score determination unit is used to obtain the initial road condition score based on the weighted summation result; The target road condition score determination unit is used to perform linear offset correction on the initial road condition score using a preset correction value to obtain the target road condition score of the road segment where the target vehicle is located; wherein, the preset weight and the preset correction value are determined according to a preset genetic algorithm, and the fitness function of the preset genetic algorithm is constructed based on the prediction accuracy of the road condition score.

[0055] Optionally, the weight determination module includes: The query unit is used to query the target preset road condition score corresponding to the target road condition score in a preset mapping table; wherein, the preset mapping table is used to record the mapping relationship between different preset road condition scores and preset weights of each target sensor; The target weight determination unit is used to determine the target weight corresponding to each target sensor in the data acquisition module based on the preset weight of each target sensor corresponding to the preset road condition score in the preset mapping table.

[0056] Optionally, the operating mode determination module includes: The fusion unit is used to fuse the target data collected by each target sensor according to the weight of each target to obtain a fused feature vector; The road segment category determination unit is used to determine the road segment category corresponding to the fused feature vector using a preset classifier; The target working mode determination unit is used to query the target working mode corresponding to the road segment category in a preset parameter mapping table; wherein, the preset parameter mapping table is used to record the mapping relationship between different road segment categories and each working mode, and different working modes are associated with different combinations of acquisition parameters.

[0057] The data acquisition mode device provided in the embodiments of the present invention can execute the data acquisition mode method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0058] Example 4 Figure 4 A schematic diagram of an electronic device 400 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0059] like Figure 4As shown, the electronic device 400 includes at least one processor 401 and a memory, such as a read-only memory (ROM) 402 or a random access memory (RAM) 403, communicatively connected to the at least one processor 401. The memory stores computer programs executable by the at least one processor. The processor 401 can perform various appropriate actions and processes based on the computer program stored in the ROM 402 or loaded into the RAM 403 from storage unit 408. The RAM 403 may also store various programs and data required for the operation of the electronic device 400. The processor 401, ROM 402, and RAM 403 are interconnected via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0060] Multiple components in electronic device 400 are connected to I / O interface 405, including: input unit 406, such as keyboard, mouse, etc.; output unit 407, such as various types of displays, speakers, etc.; storage unit 408, such as disk, optical disk, etc.; and communication unit 409, such as network card, modem, wireless transceiver, etc. Communication unit 409 allows electronic device 400 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0061] Processor 401 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 401 performs the various methods and processes described above, such as the data acquisition pattern determination method.

[0062] In some embodiments, the data acquisition mode determination method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by processor 401, one or more steps of the data acquisition mode determination method described above may be performed. Alternatively, in other embodiments, processor 401 may be configured to perform the data acquisition mode determination method by any other suitable means (e.g., by means of firmware).

[0063] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0064] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0065] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0066] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0067] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0068] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0069] This disclosure provides a computer program product, including a computer program that, when executed by a processor, implements the data acquisition mode determination method provided in the above embodiments.

[0070] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0071] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for determining a data acquisition mode, characterized in that, include: Based on road surface and vehicle information during the target vehicle's driving process, the target road condition score for the road segment where the target vehicle is located is determined; wherein, the control unit of the data acquisition module in the target vehicle is integrated in the intelligent driving domain controller, and the intelligent driving domain controller is used to control the working mode of the data acquisition module; The target weights corresponding to each target sensor in the data acquisition module are determined based on the target road condition score; wherein, the target sensors are used to collect target data, and the target data is used to determine the road segment category of the road segment where the target vehicle is located; The target data collected by each target sensor are fused according to the target weights to obtain a fused feature vector, and the target working mode of the data acquisition module is determined based on the fused feature vector.

2. The data acquisition mode determination method according to claim 1, characterized in that, The road surface information includes the road surface adhesion coefficient and the road surface slope; the vehicle information includes the vehicle load. Before determining the target road condition score for the road segment where the target vehicle is located based on road and vehicle information during the target vehicle's journey, the process also includes: The road adhesion coefficient is determined based on the wheel speed difference of the target vehicle and the braking state of the target vehicle; The road slope is determined based on the acceleration collected by the inertial measurement unit of the target vehicle; The vehicle load is determined based on the air pressure data collected by the air pressure sensor of the target vehicle and the displacement data collected by the suspension displacement sensor.

3. The data acquisition mode determination method according to claim 2, characterized in that, The step of determining the target road condition score for the road segment where the target vehicle is located based on road surface and vehicle information during the target vehicle's journey includes: The road surface adhesion coefficient, road surface slope, and vehicle load during the target vehicle's driving process are weighted and summed according to preset weights. Based on the weighted summation result, the target road condition score of the road segment where the target vehicle is located is determined.

4. The data acquisition mode determination method according to claim 3, characterized in that, The step of determining the target road condition score for the road segment where the target vehicle is located based on the weighted summation result includes: The initial road condition score is obtained based on the weighted summation result; The initial road condition score is linearly offset by a preset correction value to obtain the target road condition score of the road segment where the target vehicle is located; wherein the preset weight and the preset correction value are determined according to a preset genetic algorithm, and the fitness function of the preset genetic algorithm is constructed based on the prediction accuracy of the road condition score.

5. The data acquisition mode determination method according to claim 1, characterized in that, The step of determining the target weights corresponding to each target sensor in the data acquisition module based on the target road condition score includes: Query the target preset road condition score corresponding to the target road condition score in the preset mapping table; wherein, the preset mapping table is used to record the mapping relationship between different preset road condition scores and preset weights of each target sensor; Based on the preset weights of each target sensor corresponding to the preset road condition score in the preset mapping table, the target weights of each target sensor in the data acquisition module are determined.

6. The data acquisition mode determination method according to claim 1, characterized in that, Determining the target operating mode of the data acquisition module based on the fused feature vector includes: The road segment category corresponding to the fused feature vector is determined using a preset classifier; The target working mode corresponding to the road segment category is queried in the preset parameter mapping table; wherein, the preset parameter mapping table is used to record the mapping relationship between different road segment categories and each working mode, and different working modes are associated with different combinations of acquisition parameters.

7. A data acquisition mode determination device, characterized in that, include: The road condition score determination module is used to determine the target road condition score of the road segment where the target vehicle is located based on the road surface information and vehicle information during the target vehicle's driving process; wherein, the control unit of the data acquisition module in the target vehicle is integrated in the intelligent driving domain controller, and the intelligent driving domain controller is used to control the working mode of the data acquisition module; The weight determination module is used to determine the target weights corresponding to each target sensor in the data acquisition module based on the target road condition score; wherein, the target sensors are used to collect target data, and the target data is used to determine the road segment category of the road segment where the target vehicle is located; The working mode determination module is used to fuse the target data collected by each target sensor according to the target weights to obtain a fused feature vector, and to determine the target working mode of the data acquisition module based on the fused feature vector.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the data acquisition pattern determination method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that are used to cause a processor to execute the data acquisition mode determination method according to any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the data acquisition mode determination method according to any one of claims 1-6.

Images