A vehicle variable acceleration determination planning method, product, device and medium

Abstract

This application relates to the field of autonomous driving technology, and in particular to a method, product, device, and medium for determining and planning vehicle variable acceleration. The method includes: obtaining the real-time position of the current vehicle, and determining, based on the real-time position, several bumpy sections of the current road on which the current vehicle is located from a preset road section database; determining, from the several bumpy sections, a target bumpy section on the current lane that is closest to the real-time position, and obtaining target point cloud data on the current road; judging, based on the several bumpy sections and the target point cloud data, whether the adjacent lane meets the preset lane change conditions; if the adjacent lane does not meet the preset lane change conditions, determining a target acceleration based on the target bumpy section, and controlling the current vehicle to decelerate according to the target acceleration. This application can achieve precise control of the vehicle's driving acceleration, significantly improving driving safety and comfort.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a vehicle variable acceleration determination planning method, product, device and medium. Background Art

[0002] With the rapid advancement of autonomous driving technology and the continuous improvement of vehicle intelligence, autonomous vehicles are now able to collect and process road and environmental data in real time through various sensors. However, facing complex and changing road conditions, especially those with bumpy sections, how to accurately control vehicle acceleration to ensure driving comfort and safety remains a pressing technical challenge. Summary of the Invention

[0003] In order to solve the problem of inaccurate acceleration control when a vehicle is automatically driving through a bumpy road in the prior art, the present application provides a vehicle variable acceleration determination planning method, product, device and medium.

[0004] In a first aspect, the present application provides a method for determining a vehicle's variable acceleration plan, which employs the following technical solutions:

[0005] A vehicle variable acceleration determination planning method, comprising:

[0006] Obtaining a real-time position of a current vehicle, and determining, based on the real-time position, from a preset road segment database, a number of bumpy sections of a current road on which the current vehicle is located, the current road including a current lane on which the current vehicle is located and adjacent lanes in the same direction as the current lane;

[0007] Determining a target bumpy road section on the current lane that is closest to the real-time position from the plurality of bumpy road sections, and obtaining target point cloud data on the current road, the target point cloud data including point cloud data between a position that is a preset distance from the real-time position in a direction opposite to the current vehicle travel direction and the target bumpy road section;

[0008] determining, based on the plurality of bumpy road sections and the target point cloud data, whether the adjacent lane meets a preset lane change condition;

[0009] If the adjacent lane does not meet the preset lane change condition, a target acceleration is determined based on the target bumpy road section, and the current vehicle is controlled to decelerate according to the target acceleration.

[0010] By adopting the above technical solution, the real-time position of the current vehicle is obtained, which can ensure that subsequent decisions are based on the latest vehicle status. By querying the preset road section database, the vehicle can predict bumpy sections on the road ahead, which helps the vehicle to take safety measures such as deceleration in advance, reducing safety hazards caused by bumps. The nearest target bumpy section is determined and target point cloud data is obtained, providing the vehicle with a detailed perception of the road environment ahead, which helps to more accurately judge road conditions and make decisions. Combining multi-source data (bumpy section information and point cloud data), the vehicle can intelligently determine whether the adjacent lane is suitable for lane changing, avoiding traffic accidents that may be caused by blind lane changes and further improving driving safety. If lane changing is impossible, the vehicle can adaptively adjust the acceleration to pass through the bumpy section in the best state, reducing vehicle vibration and passenger discomfort caused by bumps, improving driving smoothness, and achieving precise control of the vehicle's driving acceleration, significantly improving driving safety and comfort.

[0011] In a preferred example, the present application may be further configured as follows: determining whether the adjacent lane meets a preset lane change condition based on the plurality of bumpy road sections and the target point cloud data includes:

[0012] determining, based on the plurality of bumpy road sections, whether a road section adjacent to the target bumpy road section in the same direction is a bumpy road section;

[0013] Determining whether the current vehicle can change lanes safely based on the target point cloud data;

[0014] If the adjacent road section in the same direction as the target bumpy road section is not a bumpy road section, and the current vehicle can change lanes safely, then determining that the adjacent lane meets the preset lane change condition;

[0015] If the adjacent road section in the same direction of the target bumpy road section is a bumpy road section, or the current vehicle cannot change lanes safely, it is determined that the adjacent lane does not meet the preset lane change condition.

[0016] By adopting the above technical solution and considering whether the target bumpy road section and its adjacent road section in the same direction are bumpy sections, the vehicle can choose a smoother and safer driving path. The point cloud data provides detailed three-dimensional information about the vehicle's surrounding environment, including the position, speed and driving direction of other vehicles in adjacent lanes. By analyzing this information, the vehicle can accurately determine whether there is a collision risk during the lane change process, thereby avoiding accidents. The combination of the two key steps of road condition assessment and safe lane change judgment enables the vehicle to make intelligent decisions based on real-time data and preset conditions, helping the vehicle to better cope with complex and changing road environments, reduce emergency braking or lane change operations caused by emergencies, and improve overall driving stability and safety.

[0017] In a preferred example, the present application may be further configured as follows: determining whether the current vehicle can change lanes safely based on the target point cloud data includes:

[0018] Acquiring historical lane change data of the current vehicle, the historical lane change data including lane change duration and lane change distance;

[0019] determining whether the distance between the real-time position and the target bumpy road section is greater than the lane change distance, and if so, determining an area corresponding to the lane change distance extending from the real-time position along the adjacent lane in the current vehicle travel direction as the lane change area;

[0020] Predicting, based on the target point cloud data, whether there are other vehicles passing through the lane change area on the adjacent lane within the lane change duration;

[0021] If so, it is determined that the current vehicle cannot change lanes safely.

[0022] By adopting the above technical solution, combined with the current vehicle's historical lane change data (such as lane change duration and lane change distance), the feasibility of the vehicle's lane change under current road conditions can be more accurately assessed. After confirming that the distance between the real-time position and the target bumpy road section is greater than the lane change distance, the lane change area is further defined, and the vehicle dynamics in adjacent lanes within the area are predicted based on the target point cloud data. When it is predicted that other vehicles will pass through the lane change area within the lane change duration, the vehicle can make a timely judgment that it cannot change lanes safely, thereby avoiding potential collision risks.

[0023] In a preferred example, the present application may be further configured as follows: the method further includes:

[0024] Obtain vehicle vibration data of vehicles that have historically passed through various roads;

[0025] Comparing the vehicle vibration data with a preset bumpy condition, taking a road section corresponding to the vehicle vibration data that meets the preset bumpy condition as an initial bumpy road section, to obtain a plurality of initial bumpy road sections;

[0026] Obtain point cloud data corresponding to each of the multiple initial bumpy road sections, input the point cloud data corresponding to each of the multiple initial bumpy road sections into a preset recognition model, obtain multiple bumpy road sections represented by longitude and latitude coordinates, and store the multiple bumpy road sections represented by longitude and latitude coordinates in a preset road section database.

[0027] By adopting the above technical solution, vehicle vibration data of vehicles that have historically passed through various roads are obtained, and these data are compared with preset bumpy conditions, so that accurate identification of bumpy sections can be achieved. The sections corresponding to the vehicle vibration data that meet the preset bumpy conditions are used as initial bumpy sections, and the point cloud data corresponding to these sections are obtained. The point cloud data corresponding to multiple initial bumpy sections are input into a preset recognition model, and the point cloud data are deeply analyzed. Finally, multiple bumpy sections represented by latitude and longitude coordinates are obtained, which improves the accuracy and reliability of recognition. The bumpy sections are stored in a preset section database, forming a data resource that can be queried and used in real time.

[0028] In a preferred example, the present application may be further configured as follows: the vehicle vibration data includes vibration frequency and amplitude;

[0029] The vehicle vibration data is compared with a preset bumpy condition, and a road section corresponding to the vehicle vibration data that meets the preset bumpy condition is used as an initial bumpy road section to obtain multiple initial bumpy road sections, including:

[0030] comparing the vibration frequency in the vehicle vibration data corresponding to each road with a preset vibration frequency threshold, and comparing the amplitude in the vehicle vibration data with a preset amplitude threshold;

[0031] A road section in each road where the vibration frequency exceeds the preset vibration frequency threshold and the amplitude exceeds the preset amplitude threshold is taken as an initial bumpy road section, to obtain multiple initial bumpy road sections.

[0032] By adopting the above technical solution, the vibration frequency and amplitude in the vehicle vibration data are compared with the preset vibration frequency threshold and amplitude threshold respectively, thereby realizing a multi-dimensional assessment of the road bumps, which can more comprehensively reflect the actual conditions of the road surface and improve the accuracy and reliability of bumpy road section identification.

[0033] In a preferred example, the present application may be further configured as follows: determining the target acceleration based on the target bumpy road section includes:

[0034] Obtaining the current speed of the current vehicle and determining a target speed for passing through the target bumpy road section according to the preset road section database;

[0035] Determining a distance from the real-time position to the target bumpy road section;

[0036] The target acceleration is calculated according to the current speed, the target speed and the distance value.

[0037] By adopting the above technical solution, the current speed of the current vehicle is obtained, and the target speed for passing the target bumpy section is determined based on a preset road section database. The system can plan a smooth transition from the current speed to the target speed, which helps to reduce the discomfort caused by sudden acceleration or deceleration, improve the passenger riding experience, and may reduce the vehicle's energy consumption and wear. Combining the current speed, target speed and distance values, the system can accurately calculate the required acceleration to ensure that the vehicle can reach the target speed before reaching the bumpy section.

[0038] In a preferred example, the present application may be further configured as follows: determining the target speed for passing the target bumpy road section according to the preset road section database includes:

[0039] determining a bumpiness level of the target bumpy road section from a preset road section database;

[0040] A target speed for passing through the target bumpy road section is determined according to the bumpiness level.

[0041] By adopting the above technical solution, the bumpiness level of the target bumpy road section is determined from the preset road section database, and different speed planning strategies can be formulated for different degrees of bumpy road conditions, which helps to reduce driving instability and potential risks caused by improper speed. Whether it is slight bumps or severe bumps, the system can adjust the target speed according to the specific situation to ensure that the vehicle can pass through the bumpy section at the most suitable speed.

[0042] In a second aspect, the present application provides a computer program product that employs the following technical solution:

[0043] A computer program product includes a computer program. When the computer program is executed by a processor, it implements the vehicle variable acceleration determination planning method as described in any one of the first aspects.

[0044] In a third aspect, the present application provides an electronic device, which adopts the following technical solution:

[0045] one or more processors;

[0046] Memory;

[0047] At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the vehicle variable acceleration determination planning method as described in any one of the first aspects.

[0048] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0049] A computer-readable storage medium stores a computer program thereon, which, when executed in a computer, causes the computer to execute the vehicle variable acceleration determination planning method as described in any one of the first aspects.

[0050] In summary, this application has the following beneficial technical effects:

[0051] By obtaining the real-time position of the current vehicle, this application can ensure that subsequent decisions are based on the latest vehicle status. By querying the preset road section database, the vehicle can predict bumpy sections on the road ahead, which helps the vehicle to take safety measures such as deceleration in advance, reduce safety hazards caused by bumps, determine the nearest target bumpy section, and obtain target point cloud data, providing the vehicle with a detailed perception of the road environment ahead, which helps to more accurately judge road conditions and make decisions. By combining multi-source data (bumpy section information and point cloud data), the vehicle can intelligently determine whether the adjacent lane is suitable for lane changing, avoiding traffic accidents that may be caused by blind lane changing, and further improving driving safety. When lane changing is impossible, the vehicle can adaptively adjust the acceleration to pass through the bumpy section in the best state, reducing vehicle vibration and passenger discomfort caused by bumps, improving driving smoothness, and realizing precise control of the vehicle's driving acceleration, significantly improving driving safety and comfort. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 This is a flow chart of a method for determining a plan for variable acceleration of a vehicle provided in an embodiment of the present application;

[0053] Figure 2 This is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0054] The following is combined with Figure 1 -Attached Figure 2 This application is described in further detail.

[0055] This specific embodiment is merely an explanation of the present application and is not a limitation of the present application. After reading this specification, those skilled in the art may make non-creative modifications to the present embodiment as needed, but as long as they are within the scope of the claims of the present application, they are protected by the patent law.

[0056] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0057] In this document, the term "and / or" simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document, unless otherwise specified, generally indicates an "or" relationship between the related objects.

[0058] It should be noted that in the optional embodiments of the present application, the object information and other related data involved, when the embodiments in the present application are applied to specific products or technologies, need to obtain the permission or consent of the object, and the collection, use and processing of the relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions. In other words, if the embodiments of the present application involve data related to the object, it needs to be obtained through the authorization and consent of the object, the authorization and consent of the relevant departments, and in compliance with the relevant laws, regulations and standards of the country and region. If personal information is involved in the embodiments, the acquisition of all personal information requires the consent of the individual. If sensitive information is involved, the separate consent of the information subject needs to be obtained. The embodiments also need to be implemented with the authorization and consent of the object.

[0059] The embodiment of the present application provides a method for determining a vehicle variable acceleration plan, such as Figure 1 As shown, the method provided in the embodiment of the present application is performed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smartphone, a tablet computer, a laptop computer, a desktop computer, a car console, etc., but is not limited to these. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiment of the present application. The method includes steps S101 to S104, wherein:

[0060] S101. Obtain the real-time position of the current vehicle of the automatic driving system, and determine, based on the real-time position, several bumpy sections of the current road where the current vehicle is located from a preset road section database, where the current road includes a current lane where the current vehicle is located and adjacent lanes in the same direction as the current lane.

[0061] In this embodiment, a positioning module (such as GPS, RTK-GPS) is pre-installed on the current autonomous vehicle. The electronic device obtains the real-time position of the current vehicle collected by the positioning module. The real-time position can be expressed in longitude and latitude. Combining the real-time position and the map library, the road information of the current road where the current vehicle is located can be determined. The road information includes the road name and the location of the road.

[0062] The preset database can be used to obtain vehicle vibration data from vehicles that have historically traveled on various roads. For each road, the corresponding vehicle vibration data is compared with preset bumpy conditions. The road sections corresponding to the vehicle vibration data that meet the preset bumpy conditions are identified as bumpy sections. This process generates the bumpy sections for each road and stores them in the preset database. For the current road, the preset database can be used to obtain several bumpy sections, including those in the current lane and adjacent lanes.

[0063] S102. Determine a target bumpy road section on the current lane that is closest to the real-time position from a plurality of bumpy road sections, and obtain target point cloud data on the current road, wherein the target point cloud data includes point cloud data from a position that is a preset distance from the real-time position in a direction opposite to the current vehicle's driving direction to the target bumpy road section.

[0064] In this embodiment, based on the vehicle's current real-time position, a target bumpy road section closest to the vehicle's real-time position in the direction of travel is searched from among the several obtained bumpy road sections. This target bumpy road section is located in the current lane. The target point cloud data can be collected by a lidar device installed on the vehicle or retrieved from a pre-built, preset point cloud database containing 3D point cloud data for various roads. The section between the target bumpy road section and a location a preset distance from the vehicle's real-time position in the direction opposite to the vehicle's current direction of travel is designated as the target road section. The point cloud data corresponding to the target road section in the current lane and adjacent lanes is designated as the target point cloud data.

[0065] S103: Determine whether an adjacent lane meets a preset lane change condition based on the bumpy road sections and the target point cloud data.

[0066] In this embodiment, it is possible to search among several bumpy road sections to determine whether the adjacent road sections in the same direction of the target bumpy road section include bumpy road sections. If so, the adjacent road sections in the same direction are determined to be bumpy sections. And based on the target point cloud data, it is determined whether the current vehicle can safely change lanes from the current lane to the adjacent lane, that is, it will not collide with the vehicle in the adjacent lane during the lane change process of the current vehicle.

[0067] In one possible scenario, the adjacent road segment in the same direction as the target bumpy road segment is not bumpy, and the current vehicle can safely change lanes from the current lane to the adjacent lane. In this case, the adjacent lane is determined to meet the preset lane change conditions. In another possible scenario, the adjacent road segment in the same direction as the target bumpy road segment is bumpy, or the current vehicle cannot safely change lanes from the current lane to the adjacent lane. In this case, the adjacent lane is determined to not meet the preset lane change conditions.

[0068] S104: If the adjacent lane does not meet the preset lane change condition, determine a target acceleration based on the target bumpy road section, and control the current vehicle to decelerate according to the target acceleration.

[0069] In this embodiment, if the adjacent lane does not meet the preset lane change conditions, the current speed of the current vehicle, the target speed in the target bumpy road section, and the distance value from the real-time position to the target bumpy road section are obtained, and then the target acceleration can be calculated based on the current speed, target speed and distance value.

[0070] If the adjacent lane meets the preset lane change conditions, the current vehicle is controlled to change lanes from the current lane to the adjacent lane. At this time, the adjacent lane before the lane change becomes the current lane where the current vehicle is located, and the deceleration or lane change method continues to be determined according to the vehicle acceleration change planning method provided in this application.

[0071] By obtaining the real-time position of the current vehicle, the embodiment of the present application can ensure that subsequent decisions are based on the latest vehicle status. By querying the preset road section database, the vehicle can predict bumpy sections on the road ahead, which helps the vehicle to take safety measures such as deceleration in advance, reduce safety hazards caused by bumps, determine the nearest target bumpy section, and obtain target point cloud data, providing the vehicle with a detailed perception of the road environment ahead, which helps to more accurately judge the road conditions and make decisions. By combining multi-source data (bumpy section information and point cloud data), the vehicle can intelligently determine whether the adjacent lane is suitable for lane changing, avoiding traffic accidents that may be caused by blind lane changing, and further improving driving safety. When lane changing is impossible, the vehicle can adaptively adjust the acceleration to pass through the bumpy section in the best state, reducing vehicle vibration and passenger discomfort caused by bumps, improving driving smoothness, and realizing precise control of the vehicle's driving acceleration, significantly improving driving safety and comfort.

[0072] A possible implementation of the embodiment of the present application is to determine whether an adjacent lane meets a preset lane change condition based on a number of bumpy road sections and target point cloud data, including:

[0073] determining, based on a plurality of bumpy road sections, whether a road section adjacent to a target bumpy road section in the same direction is a bumpy road section;

[0074] Determine whether the current vehicle can change lanes safely based on the target point cloud data;

[0075] If the adjacent road section in the same direction as the target bumpy road section is not a bumpy road section and the current vehicle can change lanes safely, then it is determined that the adjacent lane meets the preset lane change conditions;

[0076] If the adjacent road section in the same direction of the target bumpy road section is a bumpy road section, or the current vehicle cannot change lanes safely, it is determined that the adjacent lane does not meet the preset lane change conditions.

[0077] The embodiment of the present application simultaneously considers whether the target bumpy road section and its adjacent road section in the same direction are bumpy sections, which helps the vehicle choose a smoother and safer driving path. The point cloud data provides detailed three-dimensional information about the vehicle's surrounding environment, including the position, speed and driving direction of other vehicles in adjacent lanes. By analyzing this information, the vehicle can accurately determine whether there is a collision risk during the lane change process, thereby avoiding accidents. It combines the two key steps of road condition assessment and safe lane change judgment, enabling the vehicle to make intelligent decisions based on real-time data and preset conditions, helping the vehicle to better cope with complex and changing road environments, reduce emergency braking or lane change operations caused by emergencies, and improve the overall driving stability and safety.

[0078] A possible implementation of the embodiment of the present application is to determine whether the current vehicle can change lanes safely based on the target point cloud data, including:

[0079] Obtain the current vehicle's historical lane change data, including lane change duration and distance;

[0080] Determine whether the distance between the real-time location and the target bumpy road section is greater than the lane change distance. If so, extend the area corresponding to the lane change distance along the adjacent lane in the current vehicle travel direction from the real-time location to the lane change area.

[0081] Predict whether there are other vehicles passing through the lane change area in the adjacent lane within the lane change duration based on the target point cloud data;

[0082] If so, it is determined that the current vehicle cannot change lanes safely.

[0083] In this embodiment, historical lane change data for the current vehicle can be obtained from the current vehicle's data recording system. The lane change distance is the distance traveled in the forward direction from the start of the lane change to the completion of the lane change, and the lane change duration is the driving time corresponding to the lane change distance. If the distance between the real-time location and the target bumpy road section is not greater than the lane change distance, it indicates that the current vehicle may reach the target bumpy road section during the lane change process, i.e., there is insufficient distance to change lanes. In this case, it can be determined that the current vehicle cannot safely change lanes. If the distance between the real-time location and the target bumpy road section is greater than the lane change distance, it indicates that the current vehicle will not reach the target bumpy road section during the lane change process, i.e., there is sufficient distance to change lanes.

[0084] Furthermore, for the target point cloud data, preprocessing steps such as denoising and filtering can be used to improve its accuracy. Ground points can then be removed from the point cloud using a random sampling consensus algorithm or a height-based threshold segmentation algorithm to reduce the complexity of subsequent processing. Clustering algorithms (such as DBSCAN and K-means) or deep learning-based segmentation methods (such as PointNet++ and VoteNet) can then be used to segment the remaining point cloud into distinct object clusters, each representing a potential vehicle. Classifiers (such as SVMs, random forests, or deep learning models) can then be used to classify each cluster and determine whether it is a vehicle. Data association algorithms (such as the Hungarian algorithm or a Kalman filter combined with IOU matching) can be used to associate vehicles in the point cloud of the current frame with tracked vehicles in the previous frame or frames. For each associated vehicle, a Kalman filter, particle filter, or more complex tracking algorithm (such as extended Kalman filter, unscented Kalman filter) is used to estimate and update its state (including position, velocity, acceleration, direction, etc.). Based on the vehicle's current state and possible motion modes (such as constant speed, acceleration, deceleration, turning, etc.), a motion model (such as constant speed model, constant acceleration model, dynamic model, etc.) or a learning-based prediction model (such as LSTM, Transformer, etc.) is used to predict the vehicle's trajectory during the lane change duration.

[0085] If the obtained trajectories of other vehicles pass through the lane change area within the lane change time, it indicates that there is a collision risk, and it is determined that the current vehicle cannot change lanes safely; if the obtained trajectories of other vehicles do not pass through the lane change area within the lane change time, it indicates that there is no collision risk, and it is determined that the current vehicle can change lanes safely.

[0086] The embodiment of the present application combines the historical lane change data of the current vehicle (such as lane change duration and lane change distance) to more accurately evaluate the feasibility of the vehicle's lane change under current road conditions. After confirming that the distance between the real-time position and the target bumpy road section is greater than the lane change distance, the lane change area is further defined, and the vehicle dynamics in adjacent lanes within the area are predicted based on the target point cloud data. When it is predicted that other vehicles will pass through the lane change area within the lane change duration, the vehicle can make a timely judgment that it cannot change lanes safely, thereby avoiding potential collision risks.

[0087] In a possible implementation of the embodiment of the present application, the method further includes:

[0088] Obtain vehicle vibration data of vehicles that have historically passed through various roads, and compare the vehicle vibration data with preset bumpy conditions;

[0089] The road section corresponding to the vehicle vibration data that meets the preset bumpy conditions is used as an initial bumpy road section to obtain multiple initial bumpy road sections;

[0090] Obtain point cloud data corresponding to each of the multiple initial bumpy road sections, input the point cloud data corresponding to each of the multiple initial bumpy road sections into a preset recognition model, obtain multiple bumpy road sections represented by latitude and longitude coordinates, and store the multiple bumpy road sections represented by latitude and longitude coordinates in a preset road section database.

[0091] In this embodiment, a vibration sensor, such as an accelerometer, can be pre-installed on the vehicle to collect vehicle vibration data. During vehicle travel, the vibration sensor collects real-time vehicle vibration data, including vibration frequency and amplitude. This vibration data is recorded synchronously with the vehicle's travel time and location (latitude and longitude). For any road, the corresponding vehicle vibration data includes vehicle vibration data collected from multiple vehicles passing through the road. The average of the vehicle vibration data from each vehicle passing through the road is used as the vehicle vibration data for that road. For example, if a road corresponds to vehicle vibration data from three vehicles passing through it, the vibration frequency (or amplitude) corresponding to any location on the road can be calculated as the average of the vibration frequencies (or amplitudes) in the vehicle vibration data corresponding to the three vehicles at that location. This provides the vibration frequency and amplitude for each location on the road.

[0092] The preset bumpy conditions can be determined based on experience or experimental data, including a preset vibration frequency threshold and a preset amplitude threshold. The vehicle vibration data is compared with the preset bumpy conditions. Optionally, a road section in the vehicle vibration data where the vibration frequency exceeds the preset vibration frequency threshold and the amplitude exceeds the preset amplitude threshold can be set as the initial bumpy section. The road section in the vehicle vibration data where the vibration frequency exceeds the preset vibration frequency threshold or the amplitude exceeds the amplitude threshold can also be set as the initial bumpy section. This embodiment does not make specific limitations.

[0093] A machine learning or deep learning model is pre-trained for identifying bumpy road sections. The training process includes collecting point cloud data of bumpy and non-bumpy road sections, labeling the point cloud data with the bumpiness type (bumpy / non-bumpy), and further labeling the bumpy road section point cloud data with a bumpiness level. The bumpiness level can be set according to actual needs and can optionally include mild, moderate, and severe bumps. The model is trained using the labeled point cloud data to obtain a preset recognition model. After determining the initial bumpy road section, the point cloud data corresponding to the initial bumpy road section is retrieved from a preset point cloud database based on the location of the initial bumpy road section. The point cloud data contains road geometry, texture, and obstacle information. The point cloud data of the initial bumpy road section is input into the preset recognition model to further accurately identify whether the initial bumpy road section is a correct bumpy road section and the bumpy road section's bumpy level. A preset road section database is designed to store information about the bumpy road sections, including latitude and longitude coordinates, section length, and bumpiness level.

[0094] The embodiment of the present application can achieve accurate identification of bumpy road sections by obtaining vehicle vibration data of vehicles that have historically passed through various roads, and using this data to compare with preset bumpy conditions. The road sections corresponding to the vehicle vibration data that meet the preset bumpy conditions are used as initial bumpy road sections, and the point cloud data corresponding to these road sections are obtained. The point cloud data corresponding to multiple initial bumpy road sections are input into a preset recognition model, and the point cloud data are deeply analyzed to finally obtain multiple bumpy road sections represented by latitude and longitude coordinates, thereby improving the accuracy and reliability of recognition. The bumpy road sections are stored in a preset road section database, forming a data resource that can be queried and used in real time.

[0095] In a possible implementation of the embodiment of the present application, the vehicle vibration data includes vibration frequency and amplitude;

[0096] The vehicle vibration data is compared with the preset bumpy conditions, and the road section corresponding to the vehicle vibration data that meets the preset bumpy conditions is used as the initial bumpy road section, thereby obtaining multiple initial bumpy road sections, including:

[0097] Comparing the vibration frequency in the vehicle vibration data corresponding to each road with a preset vibration frequency threshold, and comparing the amplitude in the vehicle vibration data with a preset amplitude threshold;

[0098] A road section in each road where the vibration frequency exceeds a preset vibration frequency threshold and the amplitude exceeds a preset amplitude threshold is taken as an initial bumpy road section, and a plurality of initial bumpy road sections are obtained.

[0099] The embodiment of the present application achieves a multi-dimensional assessment of road bumps by comparing the vibration frequency and amplitude in the vehicle vibration data with preset vibration frequency thresholds and amplitude thresholds, which can more comprehensively reflect the actual conditions of the road surface and improve the accuracy and reliability of bumpy road section identification.

[0100] A possible implementation of the embodiment of the present application is to determine a target acceleration based on a target bumpy road section, including:

[0101] Obtain the current speed of the vehicle and determine the target speed for passing the target bumpy road section based on the preset road section database;

[0102] Determine the distance from the real-time location to the target bumpy road section;

[0103] Calculate the target acceleration based on the current speed, target speed, and distance.

[0104] In this embodiment, the current vehicle speed u can be obtained through a speed sensor or GPS data. The bumpiness level of the target bumpy road section is searched from the preset road section database. Then, the target speed v for passing the target bumpy road section is determined based on the bumpiness level. The distance from the real-time position to the target bumpy road section is expressed as s. According to the formula a=(v 2 -u 2 ) / 2s to calculate the target acceleration a.

[0105] In the embodiment of the present application, by obtaining the current speed of the current vehicle and determining the target speed for passing the target bumpy section based on a preset road section database, the system can plan a smooth transition from the current speed to the target speed, which helps to reduce the discomfort caused by sudden acceleration or deceleration, improve the passenger riding experience, and may reduce the vehicle's energy consumption and wear. Combining the current speed, target speed and distance value, the system can accurately calculate the required acceleration to ensure that the vehicle can reach the target speed before reaching the bumpy section.

[0106] A possible implementation of the embodiment of the present application is to determine a target speed for passing through a target bumpy road section based on a preset road section database, including:

[0107] determining a bumpiness level of a target bumpy road section from a preset road section database;

[0108] The target speed for passing the target bumpy road section is determined according to the bumpiness level.

[0109] In this embodiment, the correspondence between the bumpiness level and the target speed can be determined in advance through experiments. Optionally, when the bumpiness level is mild, the target speed can be 90% of the road speed limit; when the bumpiness level is moderate, the target speed can be 80% of the road speed limit; and when the bumpiness level is severe, the target speed can be 60% of the road speed limit. The bumpiness level of the target bumpy road section is used as input, and the target speed for passing the target bumpy road section is determined based on the pre-determined correspondence.

[0110] The embodiment of the present application determines the bumpiness level of the target bumpy road section from a preset road section database, and can formulate different speed planning strategies for different degrees of bumpy road conditions, which helps to reduce driving instability and potential risks caused by improper speed. Whether it is slight bumps or severe bumps, the system can adjust the target speed according to the specific situation to ensure that the vehicle can pass through the bumpy section at the most suitable speed.

[0111] An embodiment of the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, the contents shown in the aforementioned vehicle variable acceleration determination planning method embodiment are implemented.

[0112] An electronic device is provided in an embodiment of the present application, such as Figure 2 As shown, Figure 2 The electronic device 200 shown includes a processor 201 and a memory 203. The processor 201 and the memory 203 are connected, for example, via a bus 202. Optionally, the electronic device 200 may further include a transceiver 204. It should be noted that in actual applications, the number of transceivers 204 is not limited to one, and the structure of the electronic device 200 does not constitute a limitation on the embodiments of the present application.

[0113] Processor 201 can be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 201 can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0114] The bus 202 may include a path for transmitting information between the above components. The bus 202 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 202 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2 Only one thick line is used in the diagram, but it does not mean that there is only one bus or one type of bus.

[0115] The memory 203 may be a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0116] The memory 203 is used to store application code for executing the solution of the present application, and is controlled by the processor 201. The processor 201 is used to execute the application code stored in the memory 203 to implement the content shown in the embodiment of the vehicle variable acceleration determination planning method.

[0117] Figure 2 The electronic device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0118] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer-readable storage medium is run on a computer, the computer can execute the contents shown in the aforementioned embodiment of the vehicle variable acceleration determination planning method.

[0119] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the flowcharts of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0120] The above are only some of the implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A vehicle variable acceleration determination planning method, characterized in that: include: Obtaining a real-time position of a current vehicle, and determining, based on the real-time position, from a preset road segment database, a number of bumpy sections of a current road on which the current vehicle is located, the current road including a current lane on which the current vehicle is located and adjacent lanes in the same direction as the current lane; Determining a target bumpy road section on the current lane that is closest to the real-time position from the plurality of bumpy road sections, and obtaining target point cloud data on the current road, the target point cloud data including point cloud data between a position that is a preset distance from the real-time position in a direction opposite to the current vehicle travel direction and the target bumpy road section; determining, based on the plurality of bumpy road sections and the target point cloud data, whether the adjacent lane meets a preset lane change condition; If the adjacent lane does not meet the preset lane change condition, determining a target acceleration based on the target bumpy road section, and controlling the current vehicle to decelerate according to the target acceleration; The determining, based on the plurality of bumpy road sections and the target point cloud data, whether the adjacent lane satisfies a preset lane change condition includes: determining, based on the plurality of bumpy road sections, whether a road section adjacent to the target bumpy road section in the same direction is a bumpy road section; Determining whether the current vehicle can change lanes safely based on the target point cloud data; If the adjacent road section in the same direction as the target bumpy road section is not a bumpy road section, and the current vehicle can change lanes safely, then determining that the adjacent lane meets the preset lane change condition; If the adjacent road section in the same direction of the target bumpy road section is a bumpy road section, or the current vehicle cannot change lanes safely, determining that the adjacent lane does not meet the preset lane change condition; The determining, based on the target point cloud data, whether the current vehicle can change lanes safely includes: Acquiring historical lane change data of the current vehicle, the historical lane change data including lane change duration and lane change distance; determining whether the distance between the real-time position and the target bumpy road section is greater than the lane change distance, and if so, determining an area corresponding to the lane change distance extending from the real-time position along the adjacent lane in the current vehicle travel direction as the lane change area; Predicting, based on the target point cloud data, whether there are other vehicles passing through the lane change area on the adjacent lane within the lane change duration; If so, it is determined that the current vehicle cannot change lanes safely.

2. The vehicle variable acceleration determination planning method according to claim 1, characterized in that: The method further comprises: Obtain vehicle vibration data of vehicles that have historically passed through various roads; Comparing the vehicle vibration data with a preset bumpy condition, taking a road section corresponding to the vehicle vibration data that meets the preset bumpy condition as an initial bumpy road section, to obtain a plurality of initial bumpy road sections; Obtain point cloud data corresponding to each of the multiple initial bumpy road sections, input the point cloud data corresponding to each of the multiple initial bumpy road sections into a preset recognition model, obtain multiple bumpy road sections represented by longitude and latitude coordinates, and store the multiple bumpy road sections represented by longitude and latitude coordinates in a preset road section database.

3. The vehicle variable acceleration determination planning method according to claim 2, characterized in that: The vehicle vibration data includes vibration frequency and amplitude; The vehicle vibration data is compared with a preset bumpy condition, and a road section corresponding to the vehicle vibration data that meets the preset bumpy condition is used as an initial bumpy road section to obtain multiple initial bumpy road sections, including: comparing the vibration frequency in the vehicle vibration data corresponding to each road with a preset vibration frequency threshold, and comparing the amplitude in the vehicle vibration data with a preset amplitude threshold; A road section in each road where the vibration frequency exceeds the preset vibration frequency threshold and the amplitude exceeds the preset amplitude threshold is taken as an initial bumpy road section, to obtain multiple initial bumpy road sections.

4. The vehicle variable acceleration determination planning method according to claim 1, characterized in that: The determining of the target acceleration based on the target bumpy road section includes: Obtaining the current speed of the current vehicle and determining a target speed for passing through the target bumpy road section according to the preset road section database; Determining a distance from the real-time position to the target bumpy road section; The target acceleration is calculated according to the current speed, the target speed and the distance value.

5. The vehicle variable acceleration determination planning method according to claim 4, characterized in that: The determining of the target speed for passing the target bumpy road section according to the preset road section database includes: determining a bumpiness level of the target bumpy road section from a preset road section database; A target speed for passing through the target bumpy road section is determined according to the bumpiness level.

6. A computer program product, characterized in that The method comprises a computer program, which, when executed by a processor, implements the steps of the vehicle variable acceleration determination planning method according to any one of claims 1 to 5.

7. An electronic device, characterized in that: include: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the vehicle variable acceleration determination planning method described in any one of claims 1-5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed in a computer, the computer is caused to execute the vehicle variable acceleration determination planning method according to any one of claims 1 to 5.

Images