Following vehicle control method, vehicle, electronic device, and storage medium

Abstract

Embodiments of the present application provide a vehicle following control method, a vehicle, an electronic device and a storage medium. The method comprises: collecting historical driving data of the vehicle, the historical driving data comprising vehicle body data, sensing data and environment data; determining a historical driving scene of the vehicle based on the environment data; calculating a historical following time interval of the vehicle based on the vehicle body data and the sensing data; associating the historical driving scene with the historical following time interval, and establishing a mapping relationship between a plurality of historical driving scenes and a plurality of historical following time intervals; in an intelligent driving mode, collecting real-time environment data of the vehicle, determining a real-time driving scene of the vehicle based on the real-time environment data; determining a historical following time interval corresponding to the real-time driving scene based on the real-time driving scene and the mapping relationship; and controlling the vehicle to follow the vehicle based on the historical following time interval corresponding to the real-time driving scene. Embodiments of the present application determine the vehicle following time interval based on the historical driving data, so that the following time interval adapts to the individual needs of the driver.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, and in particular to a vehicle following control method, a vehicle, electronic equipment, and a storage medium. Background Technology

[0002] With the development of intelligent driving technology, the application of intelligent driver assistance functions such as ACC (Adaptive Cruise Control), HWA (Highway Assist), and NOA (Navigate on Autopilot) is becoming increasingly widespread. Based on these intelligent driver assistance functions, vehicles can continuously monitor road conditions and the movement of vehicles ahead using onboard sensors (such as radar and cameras), automatically adjusting their speed or acceleration to maintain the distance between themselves and the vehicle in front (i.e., following distance) within a set safe range, or maintaining a safe following distance over a set time interval. However, these driver assistance functions typically use fixed following distances, which cannot adapt to the individual needs of different drivers, thus affecting the driving experience. Summary of the Invention

[0003] In view of the above, it is necessary to provide a following control method, vehicle, electronic device and storage medium to solve the problem that the assisted driving function in the above-mentioned related technologies usually adopts a fixed following distance, which cannot adapt to the personalized needs of different drivers, thus affecting the driving experience.

[0004] In a first aspect, embodiments of this application provide a following control method, the method comprising: Collect historical driving data of the vehicle, including vehicle body data, sensor data, and environmental data; The historical driving scenarios of the vehicle are determined based on the environmental data; Based on the vehicle body data and the sensor data, the historical following distance of the vehicle is calculated; The historical driving scenarios are associated with the historical following distances to establish a mapping relationship between multiple historical driving scenarios and multiple historical following distances; In intelligent driving mode, real-time environmental data of the vehicle is collected, and the real-time driving scenario of the vehicle is determined based on the real-time environmental data; Based on the real-time driving scenario and the mapping relationship, determine the historical following distance corresponding to the real-time driving scenario; The vehicle is controlled to follow another vehicle based on the historical following distance corresponding to the real-time driving scenario.

[0005] In one possible implementation, the sensing data includes the speed v1 of the preceding vehicle, the acceleration a1 of the preceding vehicle, and the distance L between the vehicle and the preceding vehicle; the vehicle body data includes the vehicle speed v2 and the vehicle acceleration a2; and the calculation of the vehicle's historical following distance based on the vehicle body data and the sensing data includes: Calculate the speed difference Δv between the vehicle and the vehicle in front: Δv = v2 - v1; Calculate the acceleration difference Δa = a2 - a1 between the vehicle and the vehicle in front; Based on the speed difference, the acceleration difference, and the distance, it is determined whether a collision may occur between the vehicle and the vehicle in front. If a collision is possible between the vehicle and the vehicle in front, the historical following distance is calculated based on the speed difference, the acceleration difference, and the distance.

[0006] In one possible implementation, determining whether a collision is possible between the vehicle and the vehicle in front based on the speed difference, the acceleration difference, and the distance includes: If the speed difference and the acceleration difference satisfy the first preset condition or the second preset condition, it is determined that the vehicle and the vehicle in front are unlikely to collide. If the speed difference and the acceleration difference do not meet the first preset condition and the second preset condition, it is determined that the vehicle may collide with the vehicle in front. The first preset condition is Δa=0 and Δv≤0, and the second preset condition is Δa<0 and Δv×Δv<2L×∣Δa∣.

[0007] In one possible implementation, calculating the historical following distance based on the speed difference, the acceleration difference, and the distance includes: If Δa=0, calculate the historical following distance t based on the speed difference and the distance, where t=L / Δv; If Δa≠0, the historical following distance t is calculated based on the speed difference, the acceleration difference, and the distance, where, .

[0008] In one possible implementation, the environmental data includes at least one of the following: weather, road conditions, time, lighting conditions, and road type. Determining the vehicle's historical driving scenario based on the environmental data includes: If the environmental data includes one of the following: weather, road conditions, time, lighting conditions, and road type, the environmental data is determined as the vehicle's historical driving scenario. If the environmental data includes multiple factors such as weather, road conditions, time, lighting conditions, and road type, the combination of multiple environmental data factors is determined as the historical driving scenario of the vehicle.

[0009] In one possible implementation, the environmental data includes multimodal driving data, and determining the vehicle's historical driving scenarios based on the environmental data includes: Based on the multimodal driving data, the historical driving scenarios of the vehicle are determined using a scenario analysis model, including: The multimodal driving data is preprocessed, wherein the preprocessing includes spatiotemporal alignment, outlier removal, and data encoding; The preprocessed multimodal driving data is input into the scene analysis model, and the scene analysis model is used to extract the feature vector of the multimodal driving data. The scene analysis model is used to perform convolution, pooling, and classification on the feature vectors of the multimodal driving data to obtain the probability distribution of various driving scenarios. The driving scenario with the highest probability among the various driving scenarios is identified as the historical driving model corresponding to the multimodal driving data.

[0010] In one possible implementation, determining the historical following distance corresponding to the real-time driving scenario based on the real-time driving scenario and the mapping relationship includes: Determine that the mapping relationship includes historical driving scenarios of the real-time driving scenario; The historical following distance corresponding to the historical driving scenario that includes the real-time driving scenario in the mapping relationship is determined as the historical following distance corresponding to the real-time driving scenario.

[0011] In one possible implementation, the method further includes: If the mapping relationship does not include the historical driving scenario of the real-time driving scenario, the vehicle will follow the vehicle based on the preset following distance.

[0012] In one possible implementation, the method further includes: If the vehicle switches from the intelligent driving mode to the manual driving mode, determine whether the following distance of the vehicle has changed. If the following distance of the vehicle changes, the historical following distance corresponding to the historical driving scenario that contains the real-time driving scenario in the mapping relationship is updated based on the changed following distance.

[0013] Secondly, embodiments of this application provide a vehicle, the vehicle including a memory and a processor: wherein the memory is used to store program instructions; the processor is used to read and execute the program instructions stored in the memory, and when the program instructions are executed by the processor, the vehicle performs the above-described following control method.

[0014] Thirdly, embodiments of this application provide an electronic device, the electronic device including a memory and a processor: wherein the memory is used to store program instructions; the processor is used to read and execute the program instructions stored in the memory, and when the program instructions are executed by the processor, the electronic device performs the above-described vehicle following control method.

[0015] Fourthly, embodiments of this application provide a computer storage medium storing program instructions that, when executed on a vehicle or electronic device, cause the processor of the vehicle or electronic device to perform the aforementioned vehicle-following control method.

[0016] Fifthly, embodiments of this application provide a following control device, the device comprising: a data acquisition module for acquiring historical driving data of a vehicle, the historical driving data including vehicle body data, sensor data, and environmental data; an analysis module for determining historical driving scenarios of the vehicle based on the environmental data; the analysis module further for calculating historical following distances of the vehicle based on the vehicle body data and the sensor data; an establishment module for associating the historical driving scenarios with the historical following distances, establishing a mapping relationship between multiple historical driving scenarios and multiple historical following distances; the analysis module further for acquiring real-time environmental data of the vehicle in intelligent driving mode, and determining the real-time driving scenario of the vehicle based on the real-time environmental data; the analysis module further for determining the historical following distance corresponding to the real-time driving scenario based on the real-time driving scenario and the mapping relationship; and a control module for controlling the vehicle to follow other vehicles based on the historical following distances corresponding to the real-time driving scenario.

[0017] The following control method, vehicle, electronic device, and storage medium provided in this application embodiment can analyze the vehicle's historical driving scenarios and historical following distances based on the vehicle's historical driving data, and establish a mapping relationship between multiple historical driving scenarios and multiple historical following distances. In the actual intelligent driving mode of the vehicle, by collecting the vehicle's real-time driving data, the real-time driving scenario of the vehicle can be determined. Combined with the above mapping relationship, the corresponding following distance can be quickly determined. The following distance is determined based on historical driving data, which can adapt to the driver's driving habits, meet the driver's personalized needs, and effectively improve the driving experience. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0019] Figure 1 This is a schematic diagram illustrating an application scenario of the vehicle following control method provided in one embodiment of this application.

[0020] Figure 2 This is a flowchart of a vehicle following control method provided in an embodiment of this application.

[0021] Figure 3 This is a flowchart of a vehicle following control method provided in another embodiment of this application.

[0022] Figure 4 This is a schematic diagram of the following control device provided in one embodiment of this application.

[0023] Figure 5 This is a schematic diagram of the hardware structure of a vehicle provided in one embodiment of this application.

[0024] Figure 6 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0025] The terms "first" and "second" used in the embodiments of this application are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more features. In the description of the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0026] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. The terminology used in this application's specification is for the purpose of describing particular embodiments only and is not intended to limit the application. It should be understood that, unless otherwise stated, " / " in this application means "or". For example, A / B can mean A or B. "And / or" in this application is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. "At least one" refers to one or more. "More than one" refers to two or more. For example, at least one of a, b, or c can represent: a, b, c, a and b, a and c, b and c, and a, b, and c. Where there is no conflict, the following embodiments and features described herein can be combined with each other.

[0027] With the development of intelligent driving technology, the application of intelligent driver assistance functions such as ACC, HWA, and NOA is becoming increasingly widespread. Based on these functions, vehicles can continuously monitor road conditions and the movement of vehicles ahead using onboard sensors (such as radar and cameras), automatically adjusting their speed or acceleration to maintain the distance between themselves and the vehicle in front (i.e., following distance) within a set safe range, or maintaining a following time distance within a set safe time distance. However, these driver assistance functions typically use fixed following time distances, which cannot adapt to the individual needs of different drivers, thus affecting the driving experience.

[0028] To address the issue that the assisted driving functions in the aforementioned technologies typically employ fixed following distances, failing to adapt to the personalized needs of different drivers and thus impacting the driving experience, this application provides a following control method. This method analyzes the vehicle's historical driving scenarios and historical following distances based on historical driving data, establishing mapping relationships between multiple historical driving scenarios and multiple historical following distances. In actual intelligent driving mode, by collecting real-time driving data, the real-time driving scenario of the vehicle is determined. Combining this with the aforementioned mapping relationship, the corresponding following distance can be quickly determined. Since the following distance is determined based on historical driving data, it can adapt to the driver's driving habits, meet the driver's personalized needs, and effectively improve the driving experience.

[0029] See Figure 1 The diagram shown illustrates an application scenario of the following control method provided in an embodiment of this application. The following control method provided in this embodiment can be applied to, for example... Figure 1The vehicle-following control system 100 shown includes, but is not limited to, a vehicle 10 and electronic devices 20. The electronic devices 20 can be a personal computer or a server; for example, the server can be a single server, a server cluster, or a cloud server. The vehicle 10 includes, but is not limited to, a data acquisition module, a vehicle-to-cloud interaction module, and an intelligent driving control module. The electronic devices 20 include, but are not limited to, a user data management module and a user data analysis module.

[0030] In one embodiment of this application, the vehicle-cloud interaction module establishes a two-way vehicle-cloud authentication, sends the packaged data from the data acquisition module to the electronic device, and downloads intelligent driving data from the electronic device for use by the intelligent driving control module. The user data analysis module processes the data uploaded by the vehicle. The user data management module manages the data processed by the user data analysis module according to the user and distributes it to the vehicle.

[0031] See Figure 2 The diagram shown is a flowchart of a vehicle-following control method provided in an embodiment of this application. The vehicle-following control method is applied to a vehicle or electronic device, and includes: S101 collects historical driving data of the vehicle.

[0032] In one embodiment of this application, the historical driving data includes intelligent driving status data, vehicle body data, sensor data, and environmental data. The intelligent driving status data includes, but is not limited to: autonomous driving time interval level, ACC / HWA / NOA status data. The vehicle body data includes, but is not limited to: accelerator pedal position, brake pedal position, vehicle speed, and vehicle acceleration. The sensor data includes, but is not limited to: the size of the vehicle in front, the speed of the vehicle in front, the acceleration of the vehicle in front, the model of the vehicle in front, and the distance between the vehicle and the vehicle in front. The environmental data includes, but is not limited to: weather, road conditions, time, lighting conditions, and road type.

[0033] In one embodiment of this application, the vehicle's data acquisition module collects the historical driving data at preset intervals, serializes and packages the historical driving data, and sends it to the vehicle-cloud interaction module. The vehicle-cloud interaction module then uploads the historical driving data to the electronic device. For example, the preset interval can be 1 hour, 12 hours, 1 day, etc.

[0034] In one embodiment of this application, the historical driving data is associated with vehicle information and user information. For example, the vehicle information includes the vehicle VIN code, and the user information includes user contact information, ID card number, etc. The vehicle also includes a desensitization module, used to desensitize the historical driving data, remove privacy information (such as driver's name, license plate number, etc.) from the historical driving data, and send the desensitized historical driving data to the data acquisition module.

[0035] S102, determine the vehicle's historical driving scenarios based on environmental data.

[0036] In one embodiment of this application, if the environmental data includes one of weather, road conditions, time, lighting conditions, and road type, the environmental data is determined as the vehicle's historical driving scenario. For example, if the environmental data includes weather and the weather is rainy, then the vehicle's historical driving scenario is a rainy day scenario. If the environmental data includes road conditions and the road conditions are congested, then the vehicle's historical driving scenario is a congested day scenario.

[0037] If the environmental data includes multiple factors such as weather, road conditions, time, lighting conditions, and road type, the combination of these factors is determined as the vehicle's historical driving scenario. For example, if the environmental data includes weather and road conditions, and the weather is rainy and the road conditions are congested, then the vehicle's historical driving scenario is a rainy, congested road scenario. If the environmental data includes weather, road conditions, and lighting conditions, and the weather is rainy, the road conditions are congested, and the lighting conditions are low light, then the vehicle's historical driving scenario is a rainy, low-light, congested road scenario.

[0038] In another embodiment of this application, the environmental data may include multimodal driving data, which includes, but is not limited to, illumination information, radar sensing information, and road type. Based on the multimodal driving data, a scene analysis model is used to determine the vehicle's historical driving scenarios.

[0039] For example, the scene analysis model can be a convolutional neural network model. Using historical multimodal driving data from multiple vehicles and corresponding historical driving scenarios as training data, the convolutional neural network model can be trained to obtain the scene analysis model. After collecting the multimodal driving data, the multimodal driving data is preprocessed. This preprocessing includes spatiotemporal alignment, outlier removal, and data encoding. The preprocessed multimodal driving data is input into the scene analysis model, which extracts feature vectors from the multimodal driving data. The scene analysis model then performs convolution, pooling, and classification processing on the feature vectors of the multimodal driving data to obtain the probability distributions of various driving scenarios. The driving scenario with the highest probability among these various driving scenarios is determined as the historical driving model corresponding to the multimodal driving data.

[0040] Specifically, the system extracts the first feature of illumination information through normalization processing, projects radar sensing information into a bird's-eye view grid, encodes the height, density, and reflection intensity of each cell in the bird's-eye view grid, and extracts the second feature of the radar sensing information. A third feature of road type is extracted through an embedding layer. The first, second, and third features are then fused to obtain a fused feature. The fused feature in the scene analysis model undergoes convolution processing to extract implicit semantic features such as "congestion level" and "weather humidity index." The final output feature is compressed into a fixed-length one-dimensional global feature vector (e.g., 1024-dimensional) through global average pooling. This vector represents the vehicle's comprehensive understanding of the current environment. This vector is input into a fully connected layer with the number of neurons equal to the preset number of scene categories (e.g., smooth traffic, congestion, rain, snow, night, etc.). The probability distribution is calculated using the Softmax function. The system takes the category corresponding to the highest probability value as the final output.

[0041] For example, the scenario analysis model uses the Kalman filter algorithm. This algorithm processes pre-processed multimodal driving data to output a high-precision dynamic traffic situation map, which indicates the driving scenario. Specifically, based on the collected state data of other vehicles (i.e., other vehicles relative to the driver), the Kalman filter algorithm is used to establish state equations and observation equations for each other vehicle. The state equations predict where the other vehicle might go or its next location, while the observation equations determine its actual location. The state and observation equations are then weighted and corrected to obtain a final corrected state, which can be a state vector. The state vectors of other vehicles are then fused with the high-precision map to generate the dynamic traffic situation map. This dynamic traffic situation map can be a bird's-eye view or a vector semantic map. For example, it can include current lane lines, intersection shapes, stop lines, the absolute positions and speed vectors of other vehicles in space, their predicted future trajectories, and the congestion and smoothness of the driver's lane and surrounding lanes.

[0042] S103 calculates the vehicle's historical following distance based on vehicle body data and sensor data.

[0043] In one embodiment of this application, the vehicle body data includes the vehicle speed v2 and the vehicle acceleration a2, and the sensing data includes the distance L between the vehicle and the vehicle in front, the speed v1 of the vehicle in front, and the acceleration a1 of the vehicle in front. When the intelligent driving status data in the historical driving data and the vehicle body data indicate that the vehicle is in manual driving mode, that is, when the historical driving data is collected when the vehicle is in manual driving mode, the historical following distance of the vehicle is calculated. For example, if the ACC status, HWA status, and NOA status in the intelligent driving status data are all inactive, and the vehicle body data includes the accelerator pedal position and / or brake pedal position, it indicates that the vehicle is in manual driving mode.

[0044] Specifically, the speed difference Δv = v2 - v1 between the vehicle and the vehicle in front is calculated, and the acceleration difference Δa = a2 - a1 between the vehicle and the vehicle in front is calculated. Based on the speed difference Δv, the acceleration difference Δa, and the distance L, it is determined whether a collision between the vehicle and the vehicle in front is possible. If a collision between the vehicle and the vehicle in front is possible, the historical following distance t is calculated based on the speed difference, the acceleration difference, and the distance.

[0045] In one embodiment of this application, if the speed difference Δv and the acceleration difference Δa satisfy either a first preset condition or a second preset condition, it is determined that a collision between the vehicle and the vehicle in front is impossible. If the speed difference Δv and the acceleration difference Δa satisfy neither the first preset condition nor the second preset condition, it is determined that a collision between the vehicle and the vehicle in front is possible. The first preset condition is Δa = 0 and Δv ≤ 0, and the second preset condition is Δa < 0 and Δv × Δv < 2L × |Δa|.

[0046] In one embodiment of this application, if Δa = 0, the historical following distance t is calculated based on the speed difference Δv and the distance L. Where t = L / Δv. If Δa ≠ 0, the historical following distance t is calculated based on the speed difference Δv, the acceleration difference Δa, and the distance L. .

[0047] In another embodiment of this application, when the electronic device (e.g., a cloud server) executes S103, the sensing data can be restored. Taking the vehicle as the origin, the current lane and adjacent lanes of the vehicle can be restored, and the target vehicle in front of the lane where the vehicle is located can be restored, thereby determining the vehicle in front. Based on the restored vehicle, lane and vehicle in front, the following distance between the vehicle and the vehicle in front can be calculated.

[0048] S104, associate the historical driving scenarios with the historical following distances to establish a mapping relationship between multiple historical driving scenarios and multiple historical following distances.

[0049] In one embodiment of this application, a driving scenario label is added to the calculated historical following distance, thus associating the historical driving scenario with the historical following distance. After collecting historical driving data of the vehicle multiple times, multiple historical driving scenarios and multiple historical following distances can be obtained. Based on the association between historical driving scenarios and historical following distances, a mapping relationship between multiple historical driving scenarios and multiple historical following distances can be established. One historical driving scenario can correspond to one or more historical following distances.

[0050] S105, In intelligent driving mode, collect real-time environmental data of the vehicle, and determine the real-time driving scenario of the vehicle based on the real-time environmental data.

[0051] In one embodiment of this application, the intelligent driving mode may be ACC mode, HWA mode, or NOA mode. If the real-time environmental data includes one of weather, road conditions, time, lighting conditions, and road type, the real-time environmental data is determined as the real-time driving scenario of the vehicle. For example, if the real-time environmental data includes weather, and the weather is rainy, then the real-time driving scenario of the vehicle is a rainy weather scenario. If the real-time environmental data includes road conditions, and the road conditions are congested, then the real-time driving scenario of the vehicle is a congested traffic scenario.

[0052] If the real-time environmental data includes multiple factors such as weather, road conditions, time, lighting conditions, and road type, the combination of these factors is used to determine the real-time driving scenario of the vehicle. For example, if the real-time environmental data includes weather and road conditions, and the weather is rainy and the road conditions are congested, then the real-time driving scenario of the vehicle is a rainy and congested scenario. If the real-time environmental data includes weather, road conditions, and lighting conditions, and the weather is rainy, the road conditions are congested, and the lighting conditions are low light, then the real-time driving scenario of the vehicle is a rainy, low-light, and congested scenario.

[0053] In another embodiment of this application, the real-time environmental data, i.e., real-time multimodal driving data, is input into the scene analysis model, and the real-time driving scene is identified using the scene analysis model.

[0054] S106, Based on the real-time driving scenario and the mapping relationship, determine the historical following distance corresponding to the real-time driving scenario.

[0055] In one embodiment of this application, it is determined whether a historical driving scenario containing the real-time driving scenario exists in the mapping relationship. Specifically, if any historical driving scenario is the same as the real-time driving scenario, or if the real-time scenario is a subset of any historical driving scenario, then it is determined that any historical driving scenario contains the real-time driving scenario. For example, if the real-time driving scenario is a rainy day scenario and the historical driving scenario is a rainy day traffic jam scenario, then the rainy day traffic jam scenario contains the rainy day scenario. If all historical driving scenarios are different from the real-time driving scenario, or if the real-time scenario is not a subset of historical driving scenarios, then it is determined that no historical driving scenario containing the real-time driving scenario exists in the mapping relationship.

[0056] In one embodiment of this application, the historical following distance corresponding to a historical driving scenario that includes the real-time driving scenario in the mapping relationship is determined as the historical following distance corresponding to the real-time driving scenario. The historical following distance corresponding to the real-time driving scenario may include one or more.

[0057] In one embodiment of this application, if the mapping relationship does not include historical driving scenarios of the real-time driving scenario, following is performed based on a preset following distance. For example, the preset following distance is sent to the intelligent driving control module through vehicle control, and the intelligent driving control module follows the vehicle based on the preset following distance.

[0058] S107, control the vehicle to follow the vehicle based on the historical following distance corresponding to the real-time driving scenario.

[0059] In one embodiment of this application, if the real-time driving scenario corresponds to a historical following distance, the historical following distance corresponding to the real-time driving scenario is determined as the real-time following distance, and the vehicle is controlled to follow the vehicle based on the real-time following distance.

[0060] In one embodiment of this application, if the real-time driving scenario corresponds to multiple historical following distances, the average value of the multiple historical following distances is calculated, and the average value of the multiple historical following distances corresponding to the real-time driving scenario is determined as the real-time following distance, and the vehicle is controlled to follow the vehicle based on the real-time following distance.

[0061] See Figure 3 The diagram shown is a flowchart of a vehicle-following control method provided in an embodiment of this application. The vehicle-following control method is applied to a vehicle or electronic device, and includes: S201 collects historical driving data of the vehicle.

[0062] S202, determines the vehicle's historical driving scenarios based on environmental data.

[0063] S203 calculates the vehicle's historical following distance based on vehicle body data and sensor data.

[0064] S204, associate the historical driving scenarios with the historical following distances to establish a mapping relationship between multiple historical driving scenarios and multiple historical following distances.

[0065] S205, in intelligent driving mode, collect real-time environmental data of the vehicle, and determine the real-time driving scenario of the vehicle based on the real-time environmental data.

[0066] S206, Based on the real-time driving scenario and the mapping relationship, determine the historical following distance corresponding to the real-time driving scenario.

[0067] S207, control the vehicle to follow the vehicle based on the historical following distance corresponding to the real-time driving scenario.

[0068] The specific implementation methods of S201-S207 are the same as those of S101-S107, and will not be described in detail here.

[0069] S208, if the vehicle switches from the intelligent driving mode to the manual driving mode, determine whether the following distance of the vehicle has changed. If the following distance of the vehicle has changed, the process proceeds to S209; if the following distance of the vehicle has not changed, the process returns to S207.

[0070] In one embodiment of this application, if the vehicle switches from the intelligent driving mode to the manual driving mode, the vehicle's body data and sensor data are acquired. The following distance in the manual driving mode is calculated using the method in S103. The following distance in the manual driving mode is compared with the following distance in the intelligent driving mode to determine whether the following distance in the manual driving mode is the same as the following distance in the intelligent driving mode. If the following distance in the manual driving mode is the same as the following distance in the intelligent driving mode, it is determined that the vehicle's following distance has not changed. If the following distance in the manual driving mode is different from the following distance in the intelligent driving mode, it is determined that the vehicle's following distance has changed.

[0071] S209, based on the changed following distance, update the historical following distance corresponding to the historical driving scenario that contains the real-time driving scenario in the mapping relationship.

[0072] In one embodiment of this application, the modified following distance is added to the historical following distance corresponding to the historical driving scenario that includes the real-time driving scenario, thereby updating the historical following distance corresponding to the historical driving scenario.

[0073] The embodiments described above can analyze the vehicle's historical driving scenarios and historical following distances based on the vehicle's historical driving data, and establish a mapping relationship between multiple historical driving scenarios and multiple historical following distances. In the actual intelligent driving mode of the vehicle, by collecting the vehicle's real-time driving data, the real-time driving scenario of the vehicle can be determined. Combined with the above mapping relationship, the corresponding following distance can be quickly determined. The following distance is determined based on historical driving data, which can adapt to the driver's driving habits, meet the driver's personalized needs, and effectively improve the driving experience.

[0074] See Figure 4 The diagram shown is a structural schematic of a following control device provided in one embodiment of this application. In one embodiment of this application, the following control device 200 may include multiple functional modules composed of computer program segments. The computer program segments in the following control device 200 may be stored in the memory of an electronic device and executed by at least one processor to perform the following control function.

[0075] In one embodiment of this application, the following control device 200 can be divided into multiple functional modules according to the functions it performs. The functional modules of the following control device 200 may include: a data acquisition module 201, an analysis module 202, a construction module 203, and a control module 204. In this embodiment, a module refers to a series of computer program segments that can be executed by at least one processor and perform a fixed function, and are stored in memory.

[0076] The acquisition module 201 is used to collect historical driving data of the vehicle, including vehicle body data, sensor data and environmental data.

[0077] The analysis module 202 is used to determine the historical driving scenarios of the vehicle based on the environmental data.

[0078] The analysis module 202 is also used to calculate the historical following distance of the vehicle based on the vehicle body data and the sensing data.

[0079] The module 203 is used to associate the historical driving scenarios with the historical following distances and to establish a mapping relationship between multiple historical driving scenarios and multiple historical following distances.

[0080] The analysis module 202 is also used to collect real-time environmental data of the vehicle in intelligent driving mode, and determine the real-time driving scenario of the vehicle based on the real-time environmental data.

[0081] The analysis module 202 is also used to determine the historical following distance corresponding to the real-time driving scenario based on the real-time driving scenario and the mapping relationship.

[0082] The control module 204 is used to control the vehicle to follow another vehicle based on the historical following distance corresponding to the real-time driving scenario.

[0083] See Figure 5 The diagram shown is a schematic representation of the hardware structure of a vehicle according to an embodiment of this application. The vehicle following control method provided in this embodiment can be applied to a vehicle 10. The vehicle 10 includes, but is not limited to, a processor 110 and a memory 120 connected via a communication bus 130. Figure 5 This is merely an example of a vehicle and does not constitute a limitation thereof. In other embodiments, the vehicle may include more components than those shown in the figure.

[0084] See Figure 6 The diagram shown is a hardware structure schematic of an electronic device provided in an embodiment of this application. The vehicle following control method provided in this embodiment can also be applied to electronic device 20. Electronic device 10 includes, but is not limited to, a processor 210 and a memory 220 connected via a communication bus 230. Figure 6This is merely an example of an electronic device and does not constitute a limitation thereof. In other embodiments, the electronic device may include more components than those shown in the figure.

[0085] Memory may include one or more Random Access Memory (RAM) and one or more Non-Volatile Memory (NVM). RAM can be directly read and written by the processor and can be used to store executable programs (such as machine instructions) of the operating system or other running programs, as well as user and application data. RAM may include Static Random-Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), and Double Data Rate Synchronous Dynamic Random Access Memory (DDR SDRAM), etc.

[0086] Non-volatile memory can also store executable programs and user and application data, and can be pre-loaded into random access memory for direct read and write operations by the processor. Non-volatile memory can include disk storage devices and flash memory.

[0087] The memory is used to store one or more computer programs. These one or more computer programs are configured to be executed by a processor. The one or more computer programs include multiple instructions that, when executed by the processor, enable a vehicle-following control method to be performed on a vehicle or electronic device.

[0088] In other embodiments, the vehicle or electronic device further includes an external memory interface for connecting to an external memory to expand the storage capacity of the vehicle or electronic device.

[0089] A processor may include one or more processing units, such as an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processing unit (NPU). Different processing units may be independent devices or integrated into one or more processors.

[0090] The processor provides computing and control capabilities; for example, the processor is used to execute computer programs stored in memory to implement the vehicle following control method described above.

[0091] A communication bus is used at least to provide a channel for communication between memory and processor in a vehicle or electronic device.

[0092] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the vehicle or electronic device. In other embodiments of this application, the vehicle or electronic device may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0093] This application also provides a computer storage medium storing computer instructions. When the computer instructions are executed on a vehicle or electronic device, the vehicle or electronic device performs the aforementioned related method steps to realize the following control method in the above embodiments.

[0094] This application also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned steps to implement the vehicle following control method described in the above embodiments.

[0095] In addition, embodiments of this application also provide an apparatus, which may specifically be a chip, component or module. The apparatus may include a connected processor and a memory; wherein, the memory is used to store computer execution instructions, and when the apparatus is running, the processor may execute the computer execution instructions stored in the memory to cause the chip to execute the vehicle following control method in the above method embodiments.

[0096] In this application, the vehicle, electronic device, computer storage medium, computer program product or chip provided in the embodiments are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0097] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0098] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0099] The units described as separate components may or may not be physically separate. A component shown as a unit can be one or more physical units; that is, it can be located in one place or distributed in multiple different locations. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0100] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0101] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, or the parts or all or part of the technical solutions that contribute to the prior art, can be embodied in the form of a software product. The software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0102] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit it. Although this application has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of this application without departing from the spirit and scope of the technical solutions of this application.

Claims

1. A vehicle following control method, characterized in that, The method includes: Collect historical driving data of the vehicle, including vehicle body data, sensor data, and environmental data; The historical driving scenarios of the vehicle are determined based on the environmental data; Based on the vehicle body data and the sensor data, the historical following distance of the vehicle is calculated; The historical driving scenarios are associated with the historical following distances to establish a mapping relationship between multiple historical driving scenarios and multiple historical following distances; In intelligent driving mode, real-time environmental data of the vehicle is collected, and the real-time driving scenario of the vehicle is determined based on the real-time environmental data; Based on the real-time driving scenario and the mapping relationship, determine the historical following distance corresponding to the real-time driving scenario; The vehicle is controlled to follow another vehicle based on the historical following distance corresponding to the real-time driving scenario.

2. The following vehicle control method as described in claim 1, characterized in that, The sensing data includes the speed v1 of the preceding vehicle, the acceleration a1 of the preceding vehicle, and the distance L between the vehicle and the preceding vehicle. The vehicle body data includes the vehicle speed v2 and the vehicle acceleration a2. The calculation of the vehicle's historical following distance based on the vehicle body data and the sensing data includes: Calculate the speed difference Δv between the vehicle and the vehicle in front: Δv = v2 - v1; Calculate the acceleration difference Δa = a2 - a1 between the vehicle and the vehicle in front; Based on the speed difference, the acceleration difference, and the distance, it is determined whether a collision may occur between the vehicle and the vehicle in front. If a collision is possible between the vehicle and the vehicle in front, the historical following distance is calculated based on the speed difference, the acceleration difference, and the distance.

3. The following vehicle control method as described in claim 2, characterized in that, The method of determining whether a collision is possible between the vehicle and the vehicle in front based on the speed difference, the acceleration difference, and the distance includes: If the speed difference and the acceleration difference satisfy the first preset condition or the second preset condition, it is determined that the vehicle and the vehicle in front are unlikely to collide. If the speed difference and the acceleration difference do not meet the first preset condition and the second preset condition, it is determined that the vehicle may collide with the vehicle in front. The first preset condition is Δa=0 and Δv≤0, and the second preset condition is Δa<0 and Δv×Δv<2L×∣Δa∣.

4. The following vehicle control method as described in claim 2, characterized in that, The calculation of the historical following distance based on the speed difference, the acceleration difference, and the distance includes: If Δa=0, calculate the historical following distance t based on the speed difference and the distance, where t=L / Δv; If Δa≠0, the historical following distance t is calculated based on the speed difference, the acceleration difference, and the distance, where, .

5. The following vehicle control method as described in claim 1, characterized in that, The environmental data includes at least one of the following: weather, road conditions, time, lighting conditions, and road type. Determining the vehicle's historical driving scenarios based on the environmental data includes: If the environmental data includes one of the following: weather, road conditions, time, lighting conditions, and road type, the environmental data is determined as the vehicle's historical driving scenario. If the environmental data includes multiple factors such as weather, road conditions, time, lighting conditions, and road type, the combination of multiple environmental data factors is determined as the historical driving scenario of the vehicle.

6. The following vehicle control method as described in claim 1, characterized in that, The environmental data includes multimodal driving data, and determining the vehicle's historical driving scenarios based on the environmental data includes: Based on the multimodal driving data, the historical driving scenarios of the vehicle are determined using a scenario analysis model, including: The multimodal driving data is preprocessed, wherein the preprocessing includes spatiotemporal alignment, outlier removal, and data encoding; The preprocessed multimodal driving data is input into the scene analysis model, and the scene analysis model is used to extract the feature vector of the multimodal driving data. The scene analysis model is used to perform convolution, pooling, and classification on the feature vectors of the multimodal driving data to obtain the probability distribution of various driving scenarios. The driving scenario with the highest probability among the various driving scenarios is identified as the historical driving model corresponding to the multimodal driving data.

7. The following vehicle control method as described in claim 1, characterized in that, The step of determining the historical following distance corresponding to the real-time driving scenario based on the real-time driving scenario and the mapping relationship includes: Determine that the mapping relationship includes historical driving scenarios of the real-time driving scenario; The historical following distance corresponding to the historical driving scenario that includes the real-time driving scenario in the mapping relationship is determined as the historical following distance corresponding to the real-time driving scenario.

8. The following vehicle control method as described in claim 1, characterized in that, The method further includes: If the vehicle switches from the intelligent driving mode to the manual driving mode, determine whether the following distance of the vehicle has changed. If the following distance of the vehicle changes, the historical following distance corresponding to the historical driving scenario that contains the real-time driving scenario in the mapping relationship is updated based on the changed following distance.

9. A vehicle, characterized in that, The vehicle includes a memory and a processor: The memory is used to store program instructions; The processor is configured to read and execute the program instructions stored in the memory, and when the program instructions are executed by the processor, cause the vehicle to perform the following control method as described in any one of claims 1 to 8.

10. An electronic device, characterized in that, The electronic device includes a memory and a processor: The memory is used to store program instructions; The processor is configured to read and execute the program instructions stored in the memory, and when the program instructions are executed by the processor, the electronic device performs the following control method as described in any one of claims 1 to 8.

11. A computer storage medium, characterized in that, The computer storage medium stores program instructions that, when executed on a vehicle or electronic device, cause the processor of the vehicle or electronic device to perform the following control method as described in any one of claims 1 to 8.

Images