A vehicle control method, device, medium and product based on road surface data

Abstract

The present application relates to the technical field of vehicle control, and in particular to a vehicle control method, device, medium and product based on road surface data. The method includes: performing road surface modeling based on high-precision map data and real-time road surface data to obtain a three-dimensional road model. Then, trajectory prediction is performed based on real-time traffic data and the three-dimensional road model, and vehicle driving simulation is performed based on multiple selected vehicle trajectories, real-time traffic data and the three-dimensional road model. When a vehicle trajectory selection instruction is detected, the target vehicle trajectory is determined based on the trajectory information. Vehicle control analysis is performed by simulation and driver selection of the determined target vehicle trajectory, so that the vehicle can be automatically controlled to drive according to the target vehicle trajectory, realizing intelligent analysis and decision-making of the vehicle driving process, and providing strong support for the automatic driving system. Vehicle control analysis is performed based on the target vehicle trajectory and the simulation results corresponding to the target vehicle trajectory to determine the vehicle control information.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle control, and in particular to a vehicle control method, device, medium and product based on road surface data. Background Art

[0002] With the rapid development of intelligent transportation systems and autonomous driving technology, vehicle driving control methods based on road data have become a research hotspot. Traditional vehicle driving control mainly relies on the driver's experience and judgment, but in complex and changing traffic environments, this method has great limitations and safety hazards.

[0003] In order to improve the safety and efficiency of vehicle driving, there is an urgent need for a method that can perceive the road conditions in real time and dynamically adjust the vehicle driving control strategy accordingly. At present, the vehicle driving control method based on road data mainly relies on the road data collected by the on-board sensor to perform data analysis, and controls the vehicle driving operation based on the data analysis results. However, due to the complexity of road conditions, the vehicle control method provided by the relevant technology after data analysis cannot accurately adapt to complex road conditions, so that the safety of vehicle driving is threatened.

[0004] Therefore, how to solve the above technical problems is an urgent problem to be solved by technical personnel in this field. Summary of the invention

[0005] The purpose of this application is to provide a vehicle control method, device, medium and product based on road data to solve at least one of the above technical problems.

[0006] The above invention objectives of the present application are achieved through the following technical solutions:

[0007] In a first aspect, the present application provides a vehicle control method based on road surface data, which adopts the following technical solution:

[0008] A vehicle control method based on road surface data, comprising:

[0009] Acquire high-precision map data, real-time traffic data and real-time road surface data, perform road surface modeling based on the high-precision map data and the real-time road surface data, and obtain a three-dimensional road model, wherein the three-dimensional road model can reflect the complex traffic environment related to the road network, traffic signals and road facilities in real time;

[0010] Performing trajectory prediction based on the real-time traffic data and the three-dimensional road model to obtain multiple candidate vehicle trajectories;

[0011] Performing vehicle driving simulation based on the plurality of selected vehicle trajectories, the real-time traffic data and the three-dimensional road model to obtain simulation results, and sending the simulation results to the vehicle terminal to realize visual display of the simulation results;

[0012] When a vehicle trajectory selection instruction carrying trajectory information is detected, a target vehicle trajectory is determined from a plurality of the candidate vehicle trajectories based on the trajectory information;

[0013] A vehicle control analysis is performed based on the target vehicle trajectory and a simulation result corresponding to the target vehicle trajectory to determine vehicle control information, wherein the vehicle control information includes: driving level control, driving speed control, and lane change control.

[0014] By adopting the above technical solution, high-precision map data, real-time traffic data and real-time road surface data are obtained, and road surface modeling is performed based on the high-precision map data and real-time road surface data to obtain a three-dimensional road model. Then, trajectory prediction is performed based on the real-time traffic data and the three-dimensional road model to obtain multiple vehicle trajectories to be selected. In the operation of performing trajectory prediction, by combining the real-time traffic data and the three-dimensional road model, various factors such as the current road conditions, traffic flow, vehicle speed, and vehicle spacing can be fully considered, so that the future driving trajectory of the vehicle can be predicted more accurately. Furthermore, based on the multiple vehicle trajectories to be selected, the real-time traffic data and the three-dimensional road model, the vehicle driving simulation is performed to obtain the simulation results, and the simulation results are sent to the vehicle terminal. When a vehicle trajectory selection instruction carrying trajectory information is detected, the target vehicle trajectory is determined based on the trajectory information. Through simulation and the driver selecting the determined target vehicle trajectory and the corresponding simulation results for vehicle control analysis, the vehicle control information can be accurately determined so that the vehicle can be automatically controlled to drive according to the target vehicle trajectory, realizing intelligent analysis and decision-making of the vehicle driving process, and providing strong support for the automatic driving system. Finally, vehicle control analysis is performed based on the target vehicle trajectory and the simulation results corresponding to the target vehicle trajectory to determine the vehicle control information.

[0015] In a preferred example, the present application may be further configured as follows: performing trajectory prediction based on the real-time traffic data and the three-dimensional road model to obtain multiple candidate vehicle trajectories includes:

[0016] Performing lane change analysis based on the real-time traffic data and the real-time road surface data, and determining a lane analysis result;

[0017] When the lane analysis result is a lane change, lane selection is performed based on the real-time traffic data and the three-dimensional road model to determine a target lane;

[0018] Trajectory prediction is performed based on the target lane, the real-time traffic data and the three-dimensional road model to obtain multiple candidate vehicle trajectories.

[0019] In a preferred example, the present application may be further configured as follows: performing vehicle control analysis based on the target vehicle trajectory and the simulation result corresponding to the target vehicle trajectory to determine vehicle control information includes:

[0020] Performing a driving environment analysis based on the real-time traffic data and the real-time road surface data to determine a driving level control, wherein the driving environment analysis is used to evaluate the complexity and risk level of the current driving environment to select an appropriate driving level;

[0021] Performing a driving speed analysis based on the simulation result and the target vehicle trajectory to determine driving speed control, wherein the driving speed analysis is used to adjust a deviation between a current driving speed and a planned speed;

[0022] Performing lane change analysis based on the lane analysis result corresponding to the target vehicle trajectory and the target lane, and determining lane change control;

[0023] The driving level control, the driving speed control, and the lane change control are integrated to determine vehicle control information.

[0024] In a preferred example, the present application may be further configured as follows: the vehicle driving simulation is performed based on the plurality of selected vehicle trajectories, the real-time traffic data and the three-dimensional road model to obtain a simulation result, including:

[0025] Acquiring road surface state data, wherein the road surface state data includes: road surface moisture content, road surface temperature and road surface freezing state;

[0026] Determining a target influencing parameter based on the road surface state data, and adjusting the road three-dimensional model based on the road surface state data and the target influencing parameter to obtain a target road three-dimensional model;

[0027] A vehicle driving simulation is performed based on the multiple candidate vehicle trajectories, the real-time traffic data and the target road three-dimensional model to obtain a simulation result.

[0028] In a preferred example, the present application may be further configured as follows: after performing vehicle control analysis based on the target vehicle trajectory and the simulation result corresponding to the target vehicle trajectory and determining the vehicle control information, the configuration further includes:

[0029] When the vehicle is traveling according to the vehicle control information, a driving image of a preceding vehicle is acquired, and behavior extraction is performed based on the driving image of the preceding vehicle to determine the driving behavior of the preceding vehicle;

[0030] A danger level analysis is performed based on the driving behavior of the preceding vehicle, a danger level analysis result is determined, and when the danger level analysis result is dangerous, the vehicle is controlled to adopt an emergency avoidance strategy.

[0031] In a preferred example, the present application may be further configured as follows: performing road modeling based on the high-precision map data and the real-time road data to obtain a three-dimensional road model includes:

[0032] Based on the high-precision map data, a preliminary model is constructed to obtain a preliminary three-dimensional model, wherein the preliminary three-dimensional model can reflect the distribution of road networks and road facilities;

[0033] Data fusion is performed based on the preliminary three-dimensional model and the real-time road surface data to obtain a three-dimensional road model, wherein the data fusion is used to reflect the actual condition of the road in real time in the three-dimensional road model.

[0034] In a second aspect, the present application provides an electronic device, which adopts the following technical solution:

[0035] at least one processor;

[0036] Memory;

[0037] At least one application, wherein the at least one application is stored in the memory and is configured to be executed by at least one processor, and the at least one application is configured to: execute the above-mentioned vehicle control method based on road surface data.

[0038] In a third aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0039] A computer-readable storage medium stores a computer program, which, when executed in a computer, causes the computer to execute the above-mentioned vehicle control method based on road surface data.

[0040] In a fourth aspect, the present application provides a computer program product, which adopts the following technical solution:

[0041] A computer program product includes a computer program, and when the computer program is executed by a processor, the vehicle control method based on road surface data is implemented.

[0042] In summary, the present application includes at least one of the following beneficial technical effects:

[0043] High-precision map data, real-time traffic data and real-time road data are obtained, and road modeling is performed based on the high-precision map data and real-time road data to obtain a three-dimensional road model. Then, trajectory prediction is performed based on the real-time traffic data and the three-dimensional road model to obtain multiple candidate vehicle trajectories. In the operation of performing trajectory prediction, the current road conditions, traffic flow, vehicle speed, vehicle spacing and other factors can be fully considered by combining the real-time traffic data and the three-dimensional road model, so that the future driving trajectory of the vehicle can be predicted more accurately. Then, vehicle driving simulation is performed based on multiple candidate vehicle trajectories, real-time traffic data and the three-dimensional road model to obtain simulation results, and the simulation results are sent to the vehicle terminal. When a vehicle trajectory selection instruction carrying trajectory information is detected, the target vehicle trajectory is determined based on the trajectory information. Through simulation and the driver selecting the determined target vehicle trajectory and the corresponding simulation results for vehicle control analysis, the vehicle control information can be accurately determined so that the vehicle can be automatically controlled to drive according to the target vehicle trajectory, realizing intelligent analysis and decision-making of the vehicle driving process, and providing strong support for the automatic driving system. Finally, vehicle control analysis is performed based on the target vehicle trajectory and the simulation results corresponding to the target vehicle trajectory to determine the vehicle control information.

[0044] The driving environment is analyzed based on real-time traffic data and real-time road data to determine the driving level control. At the same time, the driving speed is analyzed based on the simulation results and the target vehicle trajectory to determine the driving speed control. The lane change analysis is performed based on the lane analysis results corresponding to the target vehicle trajectory and the target lane to determine the lane change control. Finally, the driving level control, driving speed control, and lane change control are integrated to determine the vehicle control information. When performing vehicle control analysis, the vehicle control is analyzed from three dimensions: driving environment, driving speed, and lane change, which achieves comprehensive optimization of vehicle control and improves driving safety and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a flow chart of a vehicle control method based on road surface data according to one embodiment of the present application;

[0046] Figure 2 It is a structural schematic diagram of a vehicle control device based on road surface data in one embodiment of the present application;

[0047] Figure 3 It is a structural schematic diagram of an electronic device according to one embodiment of the present application. DETAILED DESCRIPTION

[0048] The following combination Figures 1 to 3 This application is described in further detail.

[0049] This specific embodiment is merely an explanation of the present application and is not a limitation of the present application. After reading this specification, a person skilled in the art may make non-creative modifications to the present embodiment as needed, but such modifications are protected by the patent law as long as they are within the scope of the present application.

[0050] In order to make the purpose, technical scheme and advantages of the embodiment of the present application clearer, the technical scheme in the embodiment of the present application will be clearly and completely described in conjunction with the drawings in the embodiment of the present application. Obviously, the described embodiment is a part of the embodiment of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application. 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 data related to the object is involved in the embodiment of the present application, it needs to be obtained through the authorization and consent of the object, the authorization and consent of the relevant departments, and in accordance with the relevant laws, regulations and standards of the country and region. If personal information is involved in the embodiment, the acquisition of all personal information needs to obtain the consent of the individual. If sensitive information is involved, the separate consent of the information subject needs to be obtained, and the embodiment also needs to be implemented with the authorization and consent of the object.

[0051] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0052] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0053] The embodiment of the present application provides a vehicle control method based on road surface data, which is executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. 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. Figure 1As shown, the method includes step S101, step S102, step S103, step S104 and step S105, wherein:

[0054] Step S101: Obtain high-precision map data, real-time traffic data and real-time road surface data, perform road surface modeling based on the high-precision map data and real-time road surface data, and obtain a three-dimensional road model, wherein the three-dimensional road model can reflect the complex traffic environment related to the road network, traffic signals, and road facilities in real time.

[0055] For the embodiment of the present application, the high-precision map data is obtained by using a variety of sensor technologies to comprehensively scan and collect data on the road network. The various sensor technologies include but are not limited to: laser radar, vehicle-mounted cameras, high-precision global positioning systems and inertial measurement units, etc. The various sensors can capture detailed information such as road set structures, traffic signs, lane lines, obstacles, etc. in real time, and extract road vector element information (for example, lane line position, type, width, etc.) and fixed object information around the lane (for example, traffic lights, traffic signs, obstacles, etc.), forming an accurate three-dimensional representation of the road network, that is, a high-precision map. Traffic flow monitoring equipment, vehicle networking technology and mobile sensors are used to collect information such as traffic flow, vehicle speed, accidents, congestion, etc. on the road in real time, and the above information collected in real time is integrated to obtain real-time traffic data, that is, real-time traffic data is used to characterize the traffic conditions on the road. For real-time road surface data, vehicle-mounted sensors (for example, cameras, radars, etc.) are used to monitor road surface conditions in real time, including but not limited to: road slipperiness, potholes, etc., to determine real-time road surface data.

[0056] Then, using high-precision map data and real-time road data, a three-dimensional road model is constructed through three-dimensional modeling software. The three-dimensional road model can reflect the complex traffic environment related to the road network, traffic signals, and road facilities in real time. There are many ways to implement road modeling. In one feasible way, a preliminary model is constructed based on high-precision map data to obtain a preliminary three-dimensional model, wherein the preliminary three-dimensional model can reflect the distribution of the road network and road facilities; data fusion is performed based on the preliminary three-dimensional model and real-time road data to obtain a three-dimensional road model, wherein data fusion is used to reflect the actual road conditions in real time in the three-dimensional road model, and provide drivers with instant road condition information to facilitate subsequent control of vehicle driving conditions.

[0057] Step S102: performing trajectory prediction based on real-time traffic data and a three-dimensional road model to obtain a plurality of candidate vehicle trajectories.

[0058] For the embodiments of the present application, during the automatic driving process, trajectory prediction is performed based on real-time traffic data and a three-dimensional road model to obtain multiple vehicle trajectories to be selected. There are multiple ways to predict trajectories. In one feasible way, lane change analysis is performed based on real-time traffic data and real-time road surface data to determine the lane analysis result; when the lane analysis result is a lane change, lane selection is performed based on real-time traffic data and a three-dimensional road model to determine the target lane; trajectory prediction is performed based on the target lane, real-time traffic data and a three-dimensional road model to obtain multiple vehicle trajectories to be selected. In the operation of performing trajectory prediction, by combining real-time traffic data and a three-dimensional road model, multiple factors such as the current road conditions, traffic flow, vehicle speed, and vehicle spacing can be fully considered, so that the future driving trajectory of the vehicle can be predicted more accurately. At the same time, potential traffic conflicts and dangerous situations can be predicted and avoided in advance, which helps to reduce the occurrence of traffic accidents and improve the safety of road traffic. The candidate vehicle trajectory is used to characterize the possible driving path and related characteristics of the vehicle in the future, including but not limited to: trajectory position information (including: coordinate point sequence, timestamp, etc.), trajectory attribute information (including: speed, acceleration, driving direction, etc.), uncertainty information (including: probability distribution of vehicle trajectory), additional information (including: traffic rules and special events corresponding to the vehicle trajectory, etc.), etc. The candidate vehicle trajectory including multiple aspects of information together constitutes a comprehensive description and prediction of the future driving status of the vehicle.

[0059] Step S103: Perform vehicle driving simulation based on multiple candidate vehicle trajectories, real-time traffic data and road three-dimensional models to obtain simulation results, and send the simulation results to the vehicle terminal to achieve visual display of the simulation results.

[0060] For the embodiments of the present application, executing the vehicle driving simulation can demonstrate the effect presented by the vehicle driving according to each selected vehicle trajectory, which helps to familiarize the road conditions in advance and deal with possible situations, so that the driver can intuitively understand the vehicle driving conditions and traffic environment, and improve the driving experience and safety. Therefore, based on multiple selected vehicle trajectories, real-time traffic data and road three-dimensional models, vehicle driving simulation is performed to obtain simulation results. There are many ways to simulate vehicle driving. In one feasible way, road surface state data is obtained, wherein the road surface state data includes: road surface moisture content, road surface temperature and road surface freezing state; based on the road surface state data, the target influencing parameters are determined, and the road three-dimensional model is adjusted based on the road surface state data and the target influencing parameters to obtain the target road three-dimensional model; based on multiple selected vehicle trajectories, real-time traffic data and target road three-dimensional models, vehicle driving simulation is performed to obtain simulation results. For the simulation operation process of the simulation, it is as follows: set up a simulation environment in the simulation software, including: a three-dimensional model of the target road, a real-time traffic data interface, a vehicle dynamics model and a traffic behavior model, wherein the real-time traffic data interface is used to obtain real-time traffic data in the simulation environment, the vehicle dynamics model is used to describe the physical behavior of the vehicle during driving (including: acceleration, deceleration, turning, etc.), and the traffic behavior model is used to simulate the decision-making process of the driver during driving and the dynamic changes of the traffic flow. Then, input the initial conditions such as the initial position, speed, acceleration, and real-time traffic data of the vehicle, and start the simulation, so that the vehicle drives according to each preset candidate vehicle trajectory in the simulation environment, and records the key data such as the vehicle's driving trajectory, speed, acceleration, fuel consumption, etc. during the vehicle driving simulation. Then, send the simulation results to the vehicle terminal to realize the visualization of the simulation results, so that the driver can intuitively understand the process and results of the vehicle driving according to each candidate vehicle trajectory.

[0061] Step S104: when a vehicle trajectory selection instruction carrying trajectory information is detected, a target vehicle trajectory is determined from a plurality of candidate vehicle trajectories based on the trajectory information.

[0062] For the embodiment of the present application, the driver in the automatic driving system will have his own judgment, preference or immediate demand. If the electronic device only provides the driver with a vehicle trajectory that can be selected, it cannot meet the user's personalized needs well, which will affect the experience of automatic driving to a certain extent. Therefore, after sending the simulation results to the vehicle terminal to realize the visual display of the simulation results, the driver can select the most suitable trajectory from multiple selected vehicle trajectories verified by simulation according to his own judgment, preference and demand, so that the trajectory selection can better meet the user's personalized needs, improve the driver's satisfaction and trust in the entire vehicle control system, and ensure the flexibility and safety of vehicle driving. Therefore, the driver can click to select the vehicle trajectory at the display interface of the vehicle terminal to generate a corresponding vehicle trajectory selection instruction carrying trajectory information. When the vehicle trajectory selection instruction carrying trajectory information is detected, the target vehicle trajectory is determined from multiple selected vehicle trajectories based on the trajectory information.

[0063] Step S105: Perform vehicle control analysis based on the target vehicle trajectory and the simulation result corresponding to the target vehicle trajectory to determine vehicle control information, wherein the vehicle control information includes: driving level control, driving speed control, and lane change control.

[0064] For the embodiment of the present application, the vehicle control analysis is performed by simulation and the driver selecting the determined target vehicle trajectory and the corresponding simulation results, and the vehicle control information can be accurately determined so that the vehicle can be automatically controlled to travel according to the target vehicle trajectory, realizing intelligent analysis and decision-making of the vehicle driving process, and providing strong support for the automatic driving system. Therefore, based on the target vehicle trajectory and the simulation results corresponding to the target vehicle trajectory, the vehicle control analysis is performed to determine the vehicle control information, wherein, when performing the vehicle control analysis, the driving complexity and safety of the vehicle during the driving process can be considered to determine the driving level, the road conditions and real-time traffic conditions on the target vehicle trajectory can be considered to determine the driving speed, and the traffic conditions of the adjacent lanes, the vehicle blind spots, and the vehicle speed and distance on the target lane are evaluated to determine whether the lane table change operation needs to be performed. There are multiple implementation processes for vehicle control analysis, which are not limited in the embodiments of the present application. In one feasible method, a driving environment analysis is performed based on real-time traffic data and real-time road surface data to determine driving level control, wherein the driving environment analysis is used to evaluate the complexity and risk level of the current driving environment to select an appropriate driving level; a driving speed analysis is performed based on simulation results, target vehicle trajectory and real-time traffic data to determine driving speed control, wherein the driving speed analysis is used to adjust the deviation between the current driving speed and the planned speed; a lane change analysis is performed based on the lane analysis results corresponding to the target vehicle trajectory and the target lane to determine lane change control; and vehicle control information is determined by integrating driving level control, driving speed control and lane change control.

[0065] It can be seen that in the embodiment of the present application, high-precision map data, real-time traffic data and real-time road data are obtained, and road modeling is performed based on the high-precision map data and real-time road data to obtain a road three-dimensional model. Then, trajectory prediction is performed based on the real-time traffic data and the road three-dimensional model to obtain multiple vehicle trajectories to be selected. In the operation of performing trajectory prediction, by combining the real-time traffic data and the road three-dimensional model, the current road conditions, traffic flow, vehicle speed, vehicle spacing and other factors can be fully considered, so that the future driving trajectory of the vehicle can be more accurately predicted. Furthermore, based on the multiple vehicle trajectories to be selected, the real-time traffic data and the road three-dimensional model are used to perform vehicle driving simulation, and the simulation results are obtained, and the simulation results are sent to the vehicle terminal. When a vehicle trajectory selection instruction carrying trajectory information is detected, the target vehicle trajectory is determined based on the trajectory information. Through simulation and the driver selecting the determined target vehicle trajectory and the corresponding simulation results for vehicle control analysis, the vehicle control information can be accurately determined, so that the vehicle can be automatically controlled to travel according to the target vehicle trajectory, realizing intelligent analysis and decision-making of the vehicle driving process, and providing strong support for the automatic driving system. Finally, vehicle control analysis is performed based on the target vehicle trajectory and the simulation results corresponding to the target vehicle trajectory to determine the vehicle control information.

[0066] Furthermore, in order to improve the safety of road driving, in an embodiment of the present application, trajectory prediction is performed based on real-time traffic data and a three-dimensional road model to obtain multiple candidate vehicle trajectories, including:

[0067] Perform lane change analysis based on real-time traffic data and real-time road surface data to determine lane analysis results;

[0068] When the lane analysis result indicates lane change, lane selection is performed based on real-time traffic data and the three-dimensional road model to determine the target lane;

[0069] Trajectory prediction is performed based on the target lane, real-time traffic data and road three-dimensional model to obtain multiple candidate vehicle trajectories.

[0070] For the embodiments of the present application, in order to enable the vehicle to perceive the dynamic changes of the surrounding environment in a timely manner, so as to react in advance and avoid accidents such as collisions, in the process of executing trajectory prediction, lane change analysis is preferentially performed based on real-time traffic data and real-time road surface data to determine the lane analysis results, wherein the lane analysis results include: changing lanes and maintaining the original lanes. Since reasonable lane changes can reduce traffic congestion and bottlenecks, performing lane change analysis can predict the potential risks and opportunities after changing lanes, which helps to avoid traffic accidents caused by blind lane changes and improve road driving safety.

[0071] Specifically, lane change analysis rules are pre-stored in the electronic device, and lane change analysis is performed based on the lane change analysis rules, real-time traffic data, and real-time road surface data. The lane change analysis rules are formulated by experts in this field based on a large number of experimental verifications, traffic regulations, road design, vehicle dynamics, traffic flow theory and other factors, and users can also set them according to actual needs. In one case, the dimensions corresponding to the lane change analysis rule include: vehicle congestion detection, road smoothness assessment, road obstacle detection, and lane line distribution detection. For vehicle congestion detection, when it is detected that the vehicle density in the target lane is too high, resulting in a significant reduction in driving speed or a long parking waiting time, consider executing a lane change and avoiding changing to the lane; for road smoothness assessment, when the road smoothness is abnormal, for example, there are serious potholes, bumps or uneven sections, and these sections pose a threat to vehicle driving safety, consider executing a lane change and avoiding changing to the lane; for road obstacle detection, when it is detected that there are fixed or moving obstacles on the road (for example, construction facilities, faulty vehicles, scattered objects, etc.), and these obstacles pose a direct threat to vehicle driving, consider executing a lane change and avoiding changing to the lane; for lane line distribution detection, when the vehicle approaches the end of the lane line and there is no suitable lane ahead to continue driving (for example, road construction, lane closure, etc.), consider executing a lane change and avoiding changing to the lane; the specific evaluation value setting in the lane change analysis rule is not limited in the embodiment of the present application.

[0072] When the lane analysis result is to maintain the original lane, the vehicle is controlled to continue driving in the original lane; when the lane analysis result is to change the lane, the lane is selected based on the real-time traffic data and the three-dimensional road model to determine the target lane. When performing the lane selection operation, the three-dimensional road model and the real-time traffic data are used for spatial analysis to evaluate the relative position relationship between the vehicle and the lane line, roadside obstacles, and other moving vehicles during the lane change process. If the corresponding relative position relationship during the lane change process is within the safe range, the lane is determined to be the target lane. When there are multiple target lanes, the closest lane is selected as the target lane. Of course, the occupancy rate of the lane can also be considered in lane selection, so that the lane with a lower occupancy rate can be selected, which helps to reduce traffic congestion and bottlenecks. Then, the detailed information of the target lane (for example, lane width, curvature, slope, etc.) is combined with the real-time traffic data, and the real-time traffic data, the three-dimensional road model, and the target lane information are input into the trajectory prediction model, wherein the trajectory prediction model is a model constructed based on machine learning or deep learning, which can consider multiple factors such as vehicle dynamics, traffic rules, and driver behavior. Then, the trajectory prediction model generates multiple candidate vehicle trajectories based on the input data.

[0073] It can be seen that in the embodiment of the present application, performing lane change analysis can predict the potential risks and opportunities after changing lanes, help avoid traffic accidents caused by blind lane changes, improve road driving safety, and perform lane change analysis based on real-time traffic data and real-time road surface data to determine the lane analysis result. When the lane analysis result is a lane change, lane selection is performed based on real-time traffic data and a three-dimensional road model to determine the target lane. Then, trajectory prediction is performed based on the target lane, real-time traffic data, and a three-dimensional road model to obtain multiple vehicle trajectories to be selected.

[0074] Furthermore, in order to improve driving safety and efficiency and achieve comprehensive optimization of vehicle control, in an embodiment of the present application, vehicle control analysis is performed based on the target vehicle trajectory and the simulation results corresponding to the target vehicle trajectory to determine vehicle control information, including:

[0075] Perform driving environment analysis based on real-time traffic data and real-time road data to determine driving level control, where the driving environment analysis is used to assess the complexity and risk level of the current driving environment to select the appropriate driving level;

[0076] Based on the simulation results and the target vehicle trajectory, a driving speed analysis is performed to determine the driving speed control, wherein the driving speed analysis is used to adjust the deviation between the current driving speed and the planned speed;

[0077] Perform lane change analysis based on the lane analysis results corresponding to the target vehicle trajectory and the target lane, and determine lane change control;

[0078] Integrated driving level control, driving speed control, lane change control, and vehicle control information are determined.

[0079] For the embodiment of the present application, a driving environment analysis is performed based on real-time traffic data and real-time road surface data, and the driving environment analysis includes: complexity assessment and risk level classification, wherein, for complexity assessment, the congestion level, traffic density, vehicle speed distribution, etc. of the target vehicle trajectory are analyzed based on real-time traffic data to evaluate the complexity and dynamics of traffic flow; the flatness, slipperiness, and presence of obstacles of the road surface are evaluated based on real-time road surface data; for risk level classification, the accident risk level of the current road section is evaluated based on the historical accident data and real-time traffic conditions corresponding to the target vehicle trajectory, and the road conditions, weather factors (such as rain, snow, fog, etc.) and the behavior of traffic participants (such as pedestrians, non-motor vehicles, etc.) are taken into consideration to comprehensively evaluate potential safety hazards. Then, according to the corresponding results of complexity assessment and risk level classification in driving environment analysis, the appropriate driving level is selected. The driving level can be divided into low-level driving and medium- and high-level driving. The driving level is selected as follows: when the traffic environment is relatively simple and the risk level is low, a low-level automatic driving mode is selected, that is, the driver needs to stay alert and be ready to take over control at any time; when the traffic environment is complex and the risk level is high, a medium- and high-level automatic driving mode is selected. Medium- and high-level driving can cope with more complex traffic conditions and road conditions.

[0080] At the same time, based on the vehicle speed corresponding to the target vehicle trajectory in the simulation results, the planned speed change corresponding to the target vehicle trajectory is determined, and based on the current driving speed of the vehicle, the corresponding driving speed control of the vehicle is determined. The driving speed control is a sequence of multiple control modes in chronological order. The control modes include acceleration, deceleration, and speed maintenance. The driving speed analysis is used to adjust the deviation between the current driving speed and the planned speed so that the autonomous driving vehicle can drive according to the situation in the simulation results. Then, based on the lane analysis results corresponding to the target vehicle trajectory and the target lane, a lane change analysis is performed to determine the lane change control. That is, when the lane analysis result is to change the lane, the change direction and change timing are determined based on the position distribution between the current lane and the target lane of the vehicle, which is recorded as the lane change control; when the lane analysis result is to maintain the original lane, the lane change control is determined to be empty, so that the vehicle can continue to drive in the original lane. Finally, the driving level control, driving speed control, and lane change control are integrated to determine the vehicle control information. When performing vehicle control analysis, the vehicle control is analyzed from three dimensions: driving environment, driving speed, and lane change, achieving comprehensive optimization of vehicle control and improving driving safety and efficiency.

[0081] It can be seen that in the embodiment of the present application, the driving environment analysis is performed based on the real-time traffic data and the real-time road surface data to determine the driving level control. At the same time, the driving speed analysis is performed based on the simulation results and the target vehicle trajectory to determine the driving speed control, and the lane change analysis is performed based on the lane analysis results corresponding to the target vehicle trajectory and the target lane to determine the lane change control. Finally, the driving level control, driving speed control, and lane change control are integrated to determine the vehicle control information. When performing the vehicle control analysis, the vehicle control is analyzed from three dimensions: driving environment, driving speed, and lane change, which achieves a comprehensive optimization of the vehicle control and improves the safety and efficiency of driving.

[0082] Furthermore, in order to improve the real-time performance and accuracy of the simulation and make the simulation results closer to the actual situation, in the embodiment of the present application, a vehicle driving simulation is performed based on multiple candidate vehicle trajectories, real-time traffic data and a three-dimensional road model to obtain simulation results, including:

[0083] Acquiring road surface condition data, wherein the road surface condition data includes: road surface moisture content, road surface temperature and road surface freezing state;

[0084] Determine a target influencing parameter based on the road surface state data, and adjust the road three-dimensional model based on the road surface state data and the target influencing parameter to obtain a target road three-dimensional model;

[0085] The vehicle driving simulation is performed based on multiple candidate vehicle trajectories, real-time traffic data and a three-dimensional model of the target road to obtain simulation results.

[0086] For the embodiment of the present application, a variety of sensors are deployed in the road network, including but not limited to: temperature sensors, humidity sensors (for indirect estimation of road surface moisture), and possible freezing point sensors or sensors specific to detecting road surface freezing state. These sensors should be distributed in key sections and traffic nodes to ensure the comprehensiveness and representativeness of the data. The electronic device collects data from the sensor network in real time by wireless means to obtain road surface state data, wherein the road surface state data includes: road surface moisture, road surface temperature and road surface freezing state. Then, based on the road surface state data, an in-depth analysis is performed to determine the target influencing parameters that have a significant impact on vehicle driving, wherein the target influencing parameters include but are not limited to: road surface friction coefficient, vehicle driving resistance, road surface material performance (e.g., elastic modulus, shear strength, etc.), braking performance (e.g., braking response speed), tire adhesion, etc. For example, the moisture on the road surface will significantly reduce the friction coefficient between the tire and the road surface, and will also increase the air resistance and rolling resistance when the vehicle is driving; the road surface temperature will affect the performance of the road surface material, and will also affect the performance of the vehicle braking system. Therefore, the target influencing parameters are determined based on the road surface state data, and the specific values ​​of the target influencing parameters are determined according to the corresponding relationship between the road surface state data and the target influencing parameters. Then, the road 3D model is adjusted based on the road surface state data and the target influencing parameters to obtain the target road 3D model, which can more accurately reflect the actual road conditions, making the simulation results closer to the real situation and improving the real-time and accuracy of the simulation. Finally, the vehicle driving simulation is carried out based on multiple candidate vehicle trajectories, real-time traffic data and the target road 3D model to obtain the simulation results.

[0087] It can be seen that in the embodiment of the present application, the road surface state data is obtained, the target influence parameter is determined based on the road surface state data, and the road three-dimensional model is adjusted based on the road surface state data and the target influence parameter to obtain the target road three-dimensional model. The target road three-dimensional model can more accurately reflect the actual road conditions, make the simulation results closer to the real situation, and improve the real-time and accuracy of the simulation. Then, based on multiple selected vehicle trajectories, real-time traffic data and the target road three-dimensional model, a vehicle driving simulation is performed to obtain a simulation result.

[0088] Furthermore, in order to improve the safety of vehicle driving, in the embodiment of the present application, after performing vehicle control analysis based on the target vehicle trajectory and the simulation result corresponding to the target vehicle trajectory and determining the vehicle control information, it also includes:

[0089] When the vehicle is driving according to the vehicle control information, a driving image of the vehicle in front is obtained, and behavior extraction is performed based on the driving image of the vehicle in front to determine the driving behavior of the vehicle in front;

[0090] The danger level analysis is performed based on the driving behavior of the preceding vehicle, and the danger level analysis result is determined. When the danger level analysis result is dangerous, the vehicle is controlled to adopt an emergency avoidance strategy.

[0091] For the embodiment of the present application, when the vehicle is driving according to the vehicle control information, the camera installed in front of the vehicle is used to collect the driving image of the vehicle in front in real time, and the computer vision algorithm is used to detect the target of the driving image of the vehicle in front, and identify the position and outline of the vehicle in front. Then, by analyzing the driving trajectory, speed change, direction change and other features of the vehicle in front, the driving characteristics of the vehicle in front are extracted, wherein the behavior extraction operation uses the optical flow method, trajectory tracking algorithm and other technologies to track and analyze the vehicle in continuous frames. Then, the extracted driving characteristics of the vehicle in front are matched with the preset driving behavior pattern to determine the driving behavior of the vehicle in front, which includes but is not limited to: acceleration, deceleration, turning, changing lanes, emergency braking, sudden lane changes, etc.

[0092] Then, according to the current vehicle speed, road conditions, speed of the vehicle in front, etc., the safe distance between the vehicle in front is calculated, and the driving behavior of the vehicle in front is compared and analyzed with the safe distance to evaluate the danger level in the current driving state. That is, if the driving behavior of the vehicle in front may cause the distance between the two vehicles to be less than the safe distance, or the driving behavior of the vehicle in front itself is highly dangerous (such as sudden braking, sudden lane change, etc.), then the danger level analysis result is determined to be dangerous; if the distance can be kept above the safe distance, then the danger level analysis result is determined to be safe. When the danger level analysis result is dangerous, an emergency avoidance strategy is immediately formulated, wherein the emergency avoidance strategy may include deceleration, lane change, sudden braking, etc., and the emergency avoidance strategy is converted into specific control instructions for execution by the vehicle control system. By acquiring the driving image of the vehicle in front in real time and extracting the behavior, the driving state of the vehicle in front can be quickly identified, so as to timely evaluate the potential collision risk. When there is danger, an emergency avoidance strategy is adopted to avoid the potential danger, thereby improving the safety of vehicle driving.

[0093] It can be seen that in the embodiment of the present application, when the vehicle is driving according to the vehicle control information, the driving image of the vehicle in front is obtained, and the behavior extraction is performed based on the driving image of the vehicle in front to determine the driving behavior of the vehicle in front. The danger level analysis is performed based on the driving behavior of the vehicle in front to determine the danger level analysis result, and when the danger level analysis result is dangerous, the vehicle is controlled to adopt an emergency avoidance strategy. By acquiring the driving image of the vehicle in front in real time and performing behavior extraction, the driving status of the vehicle in front can be quickly identified, so as to timely evaluate the potential collision risk. When there is danger, an emergency avoidance strategy is adopted to avoid potential danger, thereby improving the safety of vehicle driving.

[0094] Furthermore, in order to make the actual condition of the road reflected in real time in the three-dimensional road model, in the embodiment of the present application, road modeling is performed based on high-precision map data and real-time road surface data to obtain a three-dimensional road model, including:

[0095] A preliminary model is constructed based on high-precision map data to obtain a preliminary three-dimensional model, wherein the preliminary three-dimensional model can reflect the distribution of road networks and road facilities;

[0096] Data fusion is performed based on the preliminary three-dimensional model and the real-time road surface data to obtain a three-dimensional road model, wherein the data fusion is used to reflect the actual condition of the road in real time in the three-dimensional road model.

[0097] For the embodiment of the present application, the high-precision map data is converted into a format suitable for three-dimensional modeling, such as Shapefile, GeoJSON, etc., and the data is standardized to ensure that the data between different data sources can be compatible and integrated. Then, a preliminary model is constructed based on the high-precision map data to obtain a preliminary three-dimensional model, wherein the preliminary model construction includes: road network modeling, road facility modeling, and material texture mapping. For road network modeling, a three-dimensional modeling software is used to construct a three-dimensional model of the road network according to the road vector data in the high-precision map data. When building this three-dimensional model, the road width, height, curvature and other attributes, as well as the connection relationship between roads are considered to ensure that the three-dimensional model of the road network can accurately reflect the actual road conditions. For road facility modeling, according to the location and attribute information of the road facilities in the high-precision map data, road facilities are added one by one in the three-dimensional model; for facilities with specific shapes and structures such as traffic signs and signal lights, the modeling tools in the three-dimensional modeling software can be used for fine modeling; for other types of road facilities, such as curbs, guardrails, etc., simplified model representations can be used to improve modeling efficiency. As for material texture mapping, add materials and texture mapping to the roads and road facilities in the 3D model to improve the realism and visual effects of the model; the selection of materials and texture mapping should be consistent with the appearance of the actual roads and facilities.

[0098] Then, the real-time road surface data is preprocessed, wherein the preprocessing includes but is not limited to: denoising, filtering, calibration and other steps to improve the accuracy and reliability of the data, and the preprocessed real-time road surface data is spatially aligned with the preliminary three-dimensional model to ensure that the two are in the same coordinate system. Then, the preprocessed real-time road surface data is integrated into the preliminary three-dimensional model, and the preliminary three-dimensional model is dynamically updated to adjust the presentation of the road surface in the preliminary three-dimensional model, such as the slipperiness of the road, potholes, etc., so that the actual condition of the road is reflected in real time in the road three-dimensional model.

[0099] It can be seen that in the embodiment of the present application, a preliminary model is constructed based on high-precision map data to obtain a preliminary three-dimensional model, wherein the preliminary three-dimensional model can reflect the distribution of road networks and road facilities. Then, data fusion is performed based on the preliminary three-dimensional model and real-time road surface data to obtain a road three-dimensional model, so that the road three-dimensional model reflects the actual conditions of the road in real time.

[0100] The above-mentioned embodiment introduces a vehicle control method based on road surface data from the perspective of method flow, and the following embodiment introduces a vehicle control device based on road surface data from the perspective of a virtual module or a virtual unit. For details, please refer to the following embodiments.

[0101] The present application embodiment provides a vehicle control device based on road surface data, such as Figure 2 As shown, the vehicle control device based on road surface data may specifically include:

[0102] The road surface modeling module 210 is used to obtain high-precision map data, real-time traffic data and real-time road surface data, and perform road surface modeling based on the high-precision map data and real-time road surface data to obtain a three-dimensional road model, wherein the three-dimensional road model can reflect the complex traffic environment related to the road network, traffic signals and road facilities in real time;

[0103] A trajectory prediction module 220 is used to perform trajectory prediction based on real-time traffic data and a three-dimensional road model to obtain multiple candidate vehicle trajectories;

[0104] The simulation module 230 is used to perform vehicle driving simulation based on multiple candidate vehicle trajectories, real-time traffic data and a three-dimensional road model, obtain simulation results, and send the simulation results to the vehicle terminal to realize visual display of the simulation results;

[0105] A trajectory selection module 240, configured to determine a target vehicle trajectory from a plurality of candidate vehicle trajectories based on the trajectory information when a vehicle trajectory selection instruction carrying trajectory information is detected;

[0106] The control analysis module 250 is used to perform vehicle control analysis based on the target vehicle trajectory and the simulation results corresponding to the target vehicle trajectory, and determine vehicle control information, wherein the vehicle control information includes: driving level control, driving speed control, and lane change control.

[0107] For the embodiment of the present application, high-precision map data, real-time traffic data and real-time road surface data are obtained, and road surface modeling is performed based on the high-precision map data and real-time road surface data to obtain a road three-dimensional model. Then, trajectory prediction is performed based on the real-time traffic data and the road three-dimensional model to obtain multiple vehicle trajectories to be selected. In the operation of performing trajectory prediction, by combining the real-time traffic data and the road three-dimensional model, multiple factors such as the current road conditions, traffic flow, vehicle speed, and vehicle spacing can be fully considered, so that the future driving trajectory of the vehicle can be more accurately predicted. Furthermore, based on the multiple vehicle trajectories to be selected, the real-time traffic data and the road three-dimensional model are used to perform vehicle driving simulation, and the simulation results are obtained, and the simulation results are sent to the vehicle terminal. When a vehicle trajectory selection instruction carrying trajectory information is detected, the target vehicle trajectory is determined based on the trajectory information. Through simulation and the driver selecting the determined target vehicle trajectory and the corresponding simulation results for vehicle control analysis, the vehicle control information can be accurately determined so that the vehicle can be automatically controlled to travel according to the target vehicle trajectory, realizing intelligent analysis and decision-making of the vehicle driving process, and providing strong support for the automatic driving system. Finally, vehicle control analysis is performed based on the target vehicle trajectory and the simulation results corresponding to the target vehicle trajectory to determine the vehicle control information.

[0108] In a possible implementation of the embodiment of the present application, when the trajectory prediction module 220 performs trajectory prediction based on real-time traffic data and a three-dimensional road model to obtain multiple candidate vehicle trajectories, it is used to:

[0109] Perform lane change analysis based on real-time traffic data and real-time road surface data to determine lane analysis results;

[0110] When the lane analysis result indicates lane change, lane selection is performed based on real-time traffic data and the three-dimensional road model to determine the target lane;

[0111] Trajectory prediction is performed based on the target lane, real-time traffic data and road three-dimensional model to obtain multiple candidate vehicle trajectories.

[0112] In a possible implementation of the embodiment of the present application, when the control analysis module 250 performs vehicle control analysis based on the target vehicle trajectory and the simulation result corresponding to the target vehicle trajectory to determine the vehicle control information, it is used to:

[0113] Perform driving environment analysis based on real-time traffic data and real-time road data to determine driving level control, where the driving environment analysis is used to assess the complexity and risk level of the current driving environment to select the appropriate driving level;

[0114] Based on the simulation results and the target vehicle trajectory, a driving speed analysis is performed to determine the driving speed control, wherein the driving speed analysis is used to adjust the deviation between the current driving speed and the planned speed;

[0115] Perform lane change analysis based on the lane analysis results corresponding to the target vehicle trajectory and the target lane, and determine lane change control;

[0116] Integrated driving level control, driving speed control, lane change control, and vehicle control information are determined.

[0117] In a possible implementation of the embodiment of the present application, the simulation module 230 performs a vehicle driving simulation based on multiple selected vehicle trajectories, real-time traffic data and a three-dimensional road model to obtain a simulation result, and is used to:

[0118] A parameter adjustment module is used to obtain road surface status data, wherein the road surface status data includes: road surface moisture content, road surface temperature and road surface freezing state;

[0119] Determine a target influencing parameter based on the road surface state data, and adjust the road three-dimensional model based on the road surface state data and the target influencing parameter to obtain a target road three-dimensional model;

[0120] The vehicle driving simulation is performed based on multiple candidate vehicle trajectories, real-time traffic data and a three-dimensional model of the target road to obtain simulation results.

[0121] In a possible implementation of the embodiment of the present application, the vehicle control device based on road surface data further includes:

[0122] The emergency avoidance module is used to obtain the driving image of the vehicle in front when the vehicle is driving according to the vehicle control information, extract the behavior based on the driving image of the vehicle in front, and determine the driving behavior of the vehicle in front;

[0123] The danger level analysis is performed based on the driving behavior of the preceding vehicle, and the danger level analysis result is determined. When the danger level analysis result is dangerous, the vehicle is controlled to adopt an emergency avoidance strategy.

[0124] In a possible implementation of the embodiment of the present application, when the road modeling module 210 performs road modeling based on high-precision map data and real-time road data to obtain a three-dimensional road model, it is used to:

[0125] A preliminary model is constructed based on high-precision map data to obtain a preliminary three-dimensional model, wherein the preliminary three-dimensional model can reflect the distribution of road networks and road facilities;

[0126] Data fusion is performed based on the preliminary three-dimensional model and the real-time road surface data to obtain a three-dimensional road model, wherein the data fusion is used to reflect the actual condition of the road in real time in the three-dimensional road model.

[0127] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the vehicle control device based on road data described above can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0128] An electronic device is provided in an embodiment of the present application, such as Figure 3 As shown, Figure 3 The electronic device 300 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 300 does not constitute a limitation on the embodiments of the present application.

[0129] The processor 301 may 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 may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 301 may 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.

[0130] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but it does not mean that there is only one bus or only one type of bus.

[0131] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices 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 compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0132] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0133] The electronic devices include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0134] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment.

[0135] The embodiment of the present application provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the method in any of the above embodiments is implemented. Compared with the related art, the embodiment of the present application obtains high-precision map data, real-time traffic data and real-time road data, and performs road modeling based on the high-precision map data and the real-time road data to obtain a three-dimensional road model. Then, trajectory prediction is performed based on the real-time traffic data and the three-dimensional road model to obtain multiple vehicle trajectories to be selected. In the operation of performing trajectory prediction, by combining the real-time traffic data and the three-dimensional road model, multiple factors such as the current road conditions, traffic flow, vehicle speed, and vehicle spacing can be fully considered, so that the future driving trajectory of the vehicle can be more accurately predicted. Furthermore, based on the multiple vehicle trajectories to be selected, the real-time traffic data and the three-dimensional road model are used to perform vehicle driving simulation, and the simulation results are obtained, and the simulation results are sent to the vehicle terminal. When a vehicle trajectory selection instruction carrying trajectory information is detected, the target vehicle trajectory is determined based on the trajectory information. Through simulation and driver selection, the target vehicle trajectory and the corresponding simulation results are used for vehicle control analysis, which can accurately determine the vehicle control information so that the vehicle can be automatically controlled to drive according to the target vehicle trajectory, realizing intelligent analysis and decision-making of the vehicle driving process, and providing strong support for the automatic driving system. Finally, the vehicle control analysis is performed based on the target vehicle trajectory and the simulation results corresponding to the target vehicle trajectory to determine the vehicle control information.

[0136] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence 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 a part of the steps in the flowchart 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 part of the sub-steps or stages of other steps.

[0137] The above are only some 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 control method based on road surface data, characterized in that: include: Acquire high-precision map data, real-time traffic data and real-time road surface data, perform road surface modeling based on the high-precision map data and the real-time road surface data, and obtain a three-dimensional road model, wherein the three-dimensional road model can reflect the complex traffic environment related to the road network, traffic signals and road facilities in real time; Performing trajectory prediction based on the real-time traffic data and the three-dimensional road model to obtain multiple candidate vehicle trajectories; Performing vehicle driving simulation based on the plurality of selected vehicle trajectories, the real-time traffic data and the three-dimensional road model to obtain simulation results, and sending the simulation results to the vehicle terminal to realize visual display of the simulation results; When a vehicle trajectory selection instruction carrying trajectory information is detected, a target vehicle trajectory is determined from a plurality of the candidate vehicle trajectories based on the trajectory information; Performing vehicle control analysis based on the target vehicle trajectory and the simulation result corresponding to the target vehicle trajectory to determine vehicle control information, wherein the vehicle control information includes: driving level control, driving speed control, and lane change control; The trajectory prediction based on the real-time traffic data and the three-dimensional road model is performed to obtain multiple candidate vehicle trajectories, including: Performing lane change analysis based on the real-time traffic data and the real-time road surface data, and determining a lane analysis result; When the lane analysis result is a lane change, lane selection is performed based on the real-time traffic data and the three-dimensional road model to determine a target lane; Performing trajectory prediction based on the target lane, the real-time traffic data and the three-dimensional road model to obtain multiple candidate vehicle trajectories; Wherein, performing vehicle control analysis based on the target vehicle trajectory and the simulation result corresponding to the target vehicle trajectory to determine vehicle control information includes: Performing a driving environment analysis based on the real-time traffic data and the real-time road surface data to determine a driving level control, wherein the driving environment analysis is used to evaluate the complexity and risk level of the current driving environment to select an appropriate driving level; Performing a driving speed analysis based on the simulation result and the target vehicle trajectory to determine driving speed control, wherein the driving speed analysis is used to adjust a deviation between a current driving speed and a planned speed; Performing lane change analysis based on the lane analysis result corresponding to the target vehicle trajectory and the target lane, and determining lane change control; The driving level control, the driving speed control, and the lane change control are integrated to determine vehicle control information.

2. The vehicle control method based on road surface data according to claim 1, characterized in that: The vehicle driving simulation is performed based on the plurality of selected vehicle trajectories, the real-time traffic data and the three-dimensional road model to obtain a simulation result, including: Acquiring road surface state data, wherein the road surface state data includes: road surface moisture content, road surface temperature and road surface freezing state; Determining a target influence parameter based on the road surface state data, and adjusting the road three-dimensional model based on the road surface state data and the target influence parameter to obtain a target road three-dimensional model; A vehicle driving simulation is performed based on the multiple candidate vehicle trajectories, the real-time traffic data and the target road three-dimensional model to obtain a simulation result.

3. The vehicle control method based on road surface data according to claim 1, characterized in that: After performing vehicle control analysis based on the target vehicle trajectory and the simulation result corresponding to the target vehicle trajectory and determining vehicle control information, the method further includes: When the vehicle is traveling according to the vehicle control information, a driving image of a preceding vehicle is acquired, and behavior extraction is performed based on the driving image of the preceding vehicle to determine the driving behavior of the preceding vehicle; A danger level analysis is performed based on the driving behavior of the preceding vehicle, a danger level analysis result is determined, and when the danger level analysis result is dangerous, the vehicle is controlled to adopt an emergency avoidance strategy.

4. The vehicle control method based on road surface data according to claim 1, characterized in that: The performing road modeling based on the high-precision map data and the real-time road data to obtain a three-dimensional road model includes: Based on the high-precision map data, a preliminary model is constructed to obtain a preliminary three-dimensional model, wherein the preliminary three-dimensional model can reflect the distribution of road networks and road facilities; Data fusion is performed based on the preliminary three-dimensional model and the real-time road surface data to obtain a three-dimensional road model, wherein the data fusion is used to reflect the actual condition of the road in real time in the three-dimensional road model.

5. 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 control method based on road surface data as described in any one of claims 1 to 4.

6. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed in a computer, the computer is caused to execute the vehicle control method based on road surface data as described in any one of claims 1 to 4.

7. A computer program product, characterized in that The method comprises a computer program, wherein the computer program is executed by a processor to implement the vehicle control method based on road surface data as claimed in any one of claims 1 to 4.

Images