An intelligent driving control method and system based on multi-module interaction

Abstract

The present invention relates to an intelligent driving control method and system based on multi-module interaction. The intelligent driving control method includes: determining perception data of the environment and objects around a vehicle based on data collected by various sensors; obtaining real-time vehicle posture information and local map information within a set range with the vehicle posture information as a reference; performing error compensation on the vehicle posture information based on the local map information and the perception data; performing path planning based on the perception data, vehicle posture information, and local map information to obtain a local trajectory, and performing trajectory control on the vehicle based on the calculated local trajectory. Based on the technology of the early key intelligent driving modules, a multi-module interactive intelligent driving product solution is proposed, thereby greatly improving the rationality of the product and reducing resource waste.

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving, and in particular to an intelligent driving control method and system based on multi-module interaction. Background Art

[0002] Intelligent driving products are generally divided into the following key modules: high-precision positioning module, perception and fusion module, planning and control module, and human-computer interaction module. At present, the design of intelligent driving products mostly adopts solutions based on signal transmission, such as Figure 1 The figure shows a block diagram of an intelligent driving system in the prior art. Figure 1 While this distributed design ensures the independence of each module, it also presents some significant challenges. For example, the currently controversial planning and control solution has two different designs from different manufacturers. Solution 1: A perception-based solution prioritizes perception over positioning in the planning and control process; Solution 2: A positioning-based solution prioritizes positioning over positioning. Both solutions also suffer from the problem of one-way signal transmission, resulting in significant resource waste. Summary of the Invention

[0003] In response to the technical problems existing in the prior art, the present invention provides an intelligent driving control method and system based on multi-module interaction. Based on the technology of the early intelligent driving key modules, a multi-module interactive intelligent driving product solution is proposed, thereby greatly improving the rationality of the product and reducing the waste of resources.

[0004] According to a first aspect of the present invention, there is provided an intelligent driving control method based on multi-module interaction, comprising:

[0005] Determine perception data of the environment and objects around the vehicle based on data collected by various sensors;

[0006] Acquiring real-time vehicle posture information and local map information within a set range with the vehicle posture information as a reference; and performing error compensation on the vehicle posture information based on the local map information and the perception data;

[0007] Path planning is performed based on the perception data, vehicle posture information, and local map information to obtain a local trajectory, and trajectory control of the vehicle is performed based on the calculated local trajectory.

[0008] On the basis of the above technical solution, the present invention can also make the following improvements.

[0009] Optionally, the process of determining the perception data of the environment and objects around the vehicle based on data collected by various sensors includes:

[0010] The objects in the data collected by various sensors are identified separately by deep learning, and the object information output by different sensors is fused to obtain the perception data; the data collected by the sensors include: data collected by cameras and radars.

[0011] Optionally, after obtaining the perception data, the method further includes:

[0012] Differentiating the perception data based on the local trajectory, and marking objects of particular interest based on the vehicle's driving context and set rules;

[0013] The motion trajectory of the focused object is predicted using the local map information.

[0014] Optionally, the process of obtaining real-time vehicle posture information and local map information within a set range with the vehicle posture information as a reference includes:

[0015] The positioning data is fused using the information from GNSS_RTK, IMU, VCU, and HD_MAP to obtain high-precision vehicle posture information and the local map information.

[0016] Optionally, the algorithm for calculating the local trajectory based on the perception data, vehicle posture information and local map information includes: A-star algorithm and Dijkstra algorithm;

[0017] The algorithm for controlling the trajectory of the vehicle based on the calculated local trajectory is a PID algorithm.

[0018] Optionally, the intelligent driving control method further includes:

[0019] Determine, based on the current control rules of the path planning, the degree to which the current intelligent driving relies on the perception data and the vehicle posture information respectively;

[0020] When it is determined during the real-time calculation of one of the perception data and the vehicle posture information that the own data has an error and needs to be corrected, and when it is determined that the path planning can be completed relying on the other data, the error correction is directly performed.

[0021] Optionally, the data collected by the sensor includes:

[0022] Select the rear axle center as the target positioning point and the right front upper part as the vehicle coordinate system. Use a 3D vehicle model to measure the installation posture parameters between each sensor and the target positioning point, and calibrate all sensors to the target positioning point coordinate system.

[0023] The intelligent driving control method also includes: setting a human-computer interaction module, which is used to receive assistance information provided by the algorithm layer and display information about the environment and vehicle status.

[0024] According to a second aspect of the present invention, there is provided an intelligent driving control system based on multi-module interaction, comprising: a sensor layer, an algorithm layer and an interaction layer, wherein the algorithm layer comprises: a perception fusion module, a high-precision positioning module, a planning and control module and an interaction module;

[0025] The perception fusion module is used to determine the perception data of the environment and objects around the vehicle based on the data collected by various sensors;

[0026] The high-precision positioning module is used to obtain real-time vehicle posture information and local map information within a set range with the vehicle posture information as a reference; and perform error compensation on the vehicle posture information based on the local map information and the perception data;

[0027] The planning and control module is configured to perform path planning based on the perception data, vehicle posture information, and local map information to obtain a local trajectory, and to perform trajectory control on the vehicle based on the calculated local trajectory;

[0028] The interaction module is used to judge the degree of dependence of the current intelligent driving on the perception fusion module and the high-precision positioning module respectively based on the current control rules of the path planning; when it is judged that there is an error in the data of one module of the perception fusion module and the high-precision positioning module that needs to be corrected during the real-time calculation of the data, and when it is judged that the path planning can be completed relying on the data of the other module, the error correction is directly performed.

[0029] According to a third aspect of the present invention, an electronic device is provided, comprising a memory and a processor, wherein the processor is configured to implement the steps of an intelligent driving control method based on multi-module interaction when executing a computer management program stored in the memory.

[0030] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which a computer management program is stored. When the computer management program is executed by a processor, the steps of the intelligent driving control method based on multi-module interaction are implemented.

[0031] The present invention provides an intelligent driving control method, system, electronic device and storage medium based on multi-module interaction. On the basis of the technology of the previous key modules of intelligent driving, a multi-module interactive intelligent driving product solution is proposed. The method uses local map information obtained from the high-precision map and the perception data obtained from the perception fusion module to compensate for the error of the positioning information, realizes data interaction and improves data accuracy; distinguishes the perception data based on the local trajectory obtained by planning, and marks the focus objects based on the driving situation of the vehicle and the setting rules to further ensure driving safety; judges the degree of dependence of the current intelligent driving on the data of each module based on the control rules of the current path planning. When the high-precision positioning module or the perception fusion module determines that its own data has errors and needs to be corrected and the path planning module can rely on the data of another module to complete the path planning, the error correction is directly performed; thereby greatly improving the rationality of the product and reducing the waste of resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 The figure shows a structural block diagram of an intelligent driving system in the prior art;

[0033] Figure 2 A flowchart of an intelligent driving control method based on multi-module interaction provided by the present invention;

[0034] Figure 3 A structural block diagram of an embodiment of an intelligent driving control system based on multi-module interaction provided by the present invention;

[0035] Figure 4 A schematic diagram of the hardware structure of a possible electronic device provided by the present invention;

[0036] Figure 5 A schematic diagram of the hardware structure of a possible computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION

[0037] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention.

[0038] Figure 2 The present invention provides a flow chart of an intelligent driving control method based on multi-module interaction, such as Figure 2 As shown, the intelligent driving control method includes:

[0039] Determine the perception data of the environment and objects around the vehicle based on data collected by various sensors.

[0040] Acquire real-time vehicle posture information and local map information within a set range based on the vehicle posture information; perform error compensation on the vehicle posture information based on the local map information and perception data.

[0041] In a specific implementation, the vehicle posture information includes: the vehicle's position and heading angle, which is matched and positioned in combination with the perception data of map information and surrounding environment information, and the error value is compensated to the positioning result of the vehicle posture information.

[0042] Path planning is performed based on perception data, vehicle posture information, and local map information to obtain a local trajectory, and the vehicle trajectory is controlled based on the calculated local trajectory.

[0043] Traditional intelligent driving system modules use one-way distributed communication and unidirectional signal transmission, which results in a huge waste of resources. To better solve the above problems and design better intelligent driving products, the present invention provides an intelligent driving control method based on multi-module interaction. Based on the technical foundation of the early intelligent driving key modules, a multi-module interactive intelligent driving product solution is proposed, thereby greatly improving the rationality of the product and reducing resource waste.

[0044] Example 1

[0045] The embodiment 1 provided by the present invention is an embodiment of an intelligent driving control method based on multi-module interaction provided by the present invention, combined with Figure 2 It can be seen that the embodiments of the intelligent driving control method include:

[0046] The center of the rear axle is selected as the target positioning point and the upper right front as the vehicle coordinate system. The installation posture parameters between each sensor and the target positioning point are measured using a 3D vehicle model, and all sensors are calibrated to the target positioning point coordinate system.

[0047] Determine the perception data of the environment and objects around the vehicle based on data collected by various sensors.

[0048] In one possible embodiment, the process of determining perception data of the environment and objects around the vehicle based on data collected by various sensors includes:

[0049] Through deep learning, objects in the data collected by various sensors are identified separately, and the object information output by different sensors is integrated to obtain perception data; the data collected by sensors includes: data collected by cameras and radars.

[0050] In a possible embodiment, after obtaining the perception data, the method further includes:

[0051] The perception data is differentiated based on local trajectories, and objects of focus are marked based on the vehicle's driving context and setting rules.

[0052] For example, when a vehicle turns left, objects directly in front of, directly behind, and to the left of the vehicle are marked as objects of focus.

[0053] Use local map information to predict the trajectory of key objects, such as focusing on vehicles in the right turn lane.

[0054] Acquire real-time vehicle posture information and local map information within a set range based on the vehicle posture information; perform error compensation on the vehicle posture information based on the local map information and perception data.

[0055] In one possible embodiment, the process of obtaining real-time vehicle position information and local map information within a set range based on the vehicle position information includes:

[0056] By using information such as GNSS_RTK (Global Navigation Satellite System-Real Time Kinematic), IMU (Inertial Measurement Unit), VCU (Vehicle Control Unit), and HD_MAP (High-Definition Map) to fuse positioning data, we can obtain high-precision vehicle posture information and local map information.

[0057] Path planning is performed based on perception data, vehicle posture information, and local map information to obtain a local trajectory, and the vehicle trajectory is controlled based on the calculated local trajectory.

[0058] In a possible embodiment, algorithms for calculating local trajectories based on perception data, vehicle posture information, and local map information include: A-star algorithm and Dijkstra algorithm.

[0059] The algorithm for controlling the vehicle trajectory based on the calculated local trajectory is PID (

[0060] Proportion Integral Differential (Proportional-Integral-Differential) algorithm.

[0061] In one possible embodiment, the intelligent driving control method further includes:

[0062] Based on the control rules of the current path planning, the current intelligent driving relies on perception data and vehicle posture information respectively.

[0063] When it is determined during the real-time calculation of one of the perception data and vehicle posture information that the data itself has errors and needs to be corrected, and when it is determined that the path planning can be completed relying on the other data, the error correction is directly performed.

[0064] For example, during driving, the system uses the positioning information in the vehicle's posture information, combined with the planned and controlled local trajectory, to determine in real time the degree of confidence between the vehicle's current lane and this positioning information. If the vehicle's posture information indicates it has entered the wrong lane, the system determines that path planning and control using perception data can be used, and feedback of the positioning data can be used to directly switch lanes.

[0065] In specific implementation, when it is determined that the perception data and vehicle posture data are wrong and need to be corrected during the real-time calculation process, another data can be used for path planning within the set time.

[0066] In a possible embodiment, a trust weight may be set for the perception data and the vehicle posture data, and the degree of dependence of the perception data and the vehicle posture data may be selected based on the trust weight.

[0067] When a data set of perception data and vehicle posture data is calculated in real time and it is determined that the data itself is wrong and needs to be corrected, the trust weight of the module can be reduced within a set time to perform path planning.

[0068] In a possible embodiment, the scene in which the vehicle is located selected by the user through the human-computer interaction module may also be received, and different trust weights may be set for the perception data and the vehicle posture data in different scenes in which the vehicle is located.

[0069] For example, if the vehicle is on a foggy urban expressway, due to the low visibility, the data collected by the visual and radar sensors about the vehicle's driving environment will be noisier and less accurate than data collected on clear days. Therefore, a higher trust weight can be assigned to the vehicle's position data when the vehicle is on a foggy urban expressway. On an urban expressway, the road conditions are generally good, with a lower likelihood of potholes, pedestrians, and other moving obstacles. Therefore, a lower trust weight can be assigned to the perception data in this scenario. For another example, if the vehicle is on a rural market, the road conditions are complex, with many pedestrians and vendors, and rural roads are prone to potholes. Therefore, a higher trust weight can be assigned to the perception data when the vehicle is on a rural market.

[0070] In a possible embodiment, the intelligent driving control method further includes: setting a human-computer interaction module, which is used to receive assistance information provided by the algorithm layer, and display information about the environment and vehicle status.

[0071] For example, in elevated areas, the interactive module sends information to passengers to confirm the location of the vehicle. If the current traffic light status cannot be detected at the intersection, the passengers will be reminded to confirm the traffic light information in advance.

[0072] Example 2

[0073] Embodiment 2 provided by the present invention is an embodiment of an intelligent driving control system based on multi-module interaction provided by the present invention. Figure 3 The structure diagram of a multi-module interactive intelligent driving control system provided by the embodiment of the present invention is as follows: Figure 3 It can be seen that the interaction between modules of the traditional intelligent driving system adopts a one-way distributed design. The intelligent driving control system provided by the present invention is based on a multi-module interactive anthropomorphic intelligent driving system that adopts a centralized design with two-way interaction between modules.

[0074] Combine Figure 2 and Figure 3 As can be seen, this embodiment of the intelligent driving control system includes a sensor layer, an algorithm layer, and an interaction layer. The sensor layer is primarily responsible for sensing vehicle movement, location, and environmental information; the algorithm layer is primarily responsible for processing sensor data and controlling vehicle movements; and the human-computer interaction layer is primarily responsible for interaction between the human and the vehicle computer.

[0075] The design process of the sensor layer includes:

[0076] Install the sensors according to the traditional intelligent driving system sensor installation design plan.

[0077] The center of the rear axle is selected as the target positioning point and the upper right front as the vehicle coordinate system. The installation posture parameters between each sensor and the target positioning point are measured using a 3D vehicle model, and all sensors are calibrated to the target positioning point coordinate system.

[0078] The algorithm layer includes: perception fusion module, high-precision positioning module, planning and control module, and interaction module. The design process of the algorithm layer includes:

[0079] The perception fusion module is used to determine the perception data of the environment and objects around the vehicle based on the data collected by various sensors.

[0080] In one possible embodiment, the process of determining perception data of the environment and objects around the vehicle based on data collected by various sensors includes:

[0081] Through deep learning, objects in the data collected by various sensors are identified separately, and the object information output by different sensors is integrated to obtain perception data; the data collected by sensors includes: data collected by cameras and radars.

[0082] In a possible embodiment, after obtaining the perception data, the method further includes:

[0083] The perception data is differentiated based on local trajectories, and objects of focus are marked based on the vehicle's driving context and setting rules.

[0084] For example, when a vehicle turns left, objects directly in front of, directly behind, and to the left of the vehicle are marked as objects of focus.

[0085] Use local map information to predict the trajectory of key objects, such as focusing on vehicles in the right turn lane.

[0086] The high-precision positioning module is used to obtain real-time vehicle posture information and local map information within a set range based on the vehicle posture information; it compensates for errors in the vehicle posture information based on the local map information and perception data; in specific implementations, the vehicle posture information includes: the vehicle's position and heading angle.

[0087] In one possible embodiment, the process of obtaining real-time vehicle position information and local map information within a set range based on the vehicle position information includes:

[0088] Utilize GNSS_RTK, IMU, VCU, HD_MAP and other information to fuse positioning data and obtain high-precision vehicle posture information and local map information.

[0089] Based on the positioning information in the vehicle posture information and the local trajectory calculated by the planning and control module, the degree of trust between the current lane of the vehicle and the positioning information is solved.

[0090] The map information and the perception data of the surrounding environment are combined for matching and positioning, and the error value is compensated to the positioning result of the vehicle posture information.

[0091] The planning and control module is used to plan the path based on the perception data, vehicle posture information and local map information to obtain a local trajectory, and to control the vehicle trajectory based on the calculated local trajectory.

[0092] In a possible embodiment, algorithms for calculating local trajectories based on perception data, vehicle posture information, and local map information include: A-star algorithm and Dijkstra algorithm.

[0093] The algorithm for controlling the vehicle trajectory based on the calculated local trajectory is the PID algorithm.

[0094] After trajectory planning, the obtained local trajectory is output to the high-precision positioning module and the perception fusion module.

[0095] The interaction module receives perception fusion results, high-precision positioning results, planning and control results, and human-computer interaction data.

[0096] It is used to judge the control rules based on the current path planning, the degree of dependence of the current intelligent driving on the perception fusion module and the high-precision positioning module respectively, and feedback to the corresponding modules; when one module of the perception fusion module and the high-precision positioning module determines that there is an error in its own data that needs to be corrected during the real-time calculation of data, and when it is determined that the path planning can be completed relying on the data of the other module, the error correction is directly performed.

[0097] For example, during driving, the system uses the positioning information in the vehicle's posture information, combined with the planned and controlled local trajectory, to determine in real time the degree of confidence between the vehicle's current lane and this positioning information. If the vehicle's posture information indicates it has entered the wrong lane, the system determines that path planning and control using perception data can be used, and feedback of the positioning data can be used to directly switch lanes.

[0098] In a specific implementation, when one of the perception fusion module and the high-precision positioning module determines that its own data has errors and needs to be corrected during the real-time calculation of data, the interaction module can also send a message that the error needs to be corrected to the planning control module, and the planning control module controls the use of the data of another module for path planning within the set time.

[0099] In a possible embodiment, a trust weight may be set for the data of the perception fusion module and the high-precision positioning module, and the planning control module selects the degree of dependence on the data of the perception fusion module and the high-precision positioning module according to the trust weight.

[0100] When one of the perception fusion module and the high-precision positioning module determines during the real-time data calculation process that its own data has errors and needs to be corrected, the interaction module can also send a message that the error needs to be corrected to the planning control module. The planning control module controls the path planning by reducing the trust weight of the module within the set time.

[0101] In a possible embodiment, the interaction module may further receive the scene selected by the user through the human-computer interaction module, and set different trust weights for the perception fusion module and the high-precision positioning module in different vehicle scenes.

[0102] For example, if the vehicle is on a foggy urban expressway, due to the low visibility, the data collected by the visual and radar sensors about the vehicle's driving environment is noisier than data collected on clear days, resulting in lower accuracy. Therefore, a higher trust weight can be assigned to the high-precision positioning module when the vehicle is on a foggy urban expressway. On an urban expressway, since the road conditions are generally good and potholes, pedestrians, and other moving obstacles are less likely to appear, a lower trust weight can be assigned to the perception fusion module in this scenario. For another example, if the vehicle is on a rural market, since market conditions are complex, with many pedestrians and vendors, and rural roads are prone to potholes, a higher trust weight can be assigned to the perception fusion module when the vehicle is on a rural market.

[0103] The design process of the interaction layer includes:

[0104] Design a human-computer interaction module, which is used to receive assistance information provided by the algorithm layer and display information about the environment and vehicle status.

[0105] For example, in elevated areas, the interactive module sends information to passengers to confirm the location of the vehicle. If the current traffic light status cannot be detected at the intersection, the passengers will be reminded to confirm the traffic light information in advance.

[0106] See also Figure 4 , Figure 4 Schematic diagram of an embodiment of an electronic device provided by an embodiment of the present invention. Figure 4 As shown, an embodiment of the present invention provides an electronic device, including a memory 1310, a processor 1320, and a computer program 1311 stored in the memory 1310 and executable on the processor 1320. When the processor 1320 executes the computer program 1311, the following steps are implemented: determining perception data of the environment and objects around the vehicle based on data collected by various sensors; obtaining real-time vehicle posture information and local map information within a set range with the vehicle posture information as a reference; performing error compensation on the vehicle posture information based on the local map information and the perception data; performing path planning based on the perception data, the vehicle posture information, and the local map information to obtain a local trajectory, and performing trajectory control on the vehicle based on the calculated local trajectory.

[0107] See also Figure 5 , Figure 5 Schematic diagram of an embodiment of a computer-readable storage medium provided by the present invention. Figure 5As shown, this embodiment provides a computer-readable storage medium 1400, on which a computer program 1411 is stored. When the computer program 1411 is executed by a processor, the following steps are implemented: determining perception data of the environment and objects around the vehicle based on data collected by various sensors; obtaining real-time vehicle posture information and local map information within a set range with the vehicle posture information as a reference; performing error compensation on the vehicle posture information based on the local map information and the perception data; performing path planning based on the perception data, the vehicle posture information and the local map information to obtain a local trajectory, and performing trajectory control on the vehicle based on the calculated local trajectory.

[0108] The embodiments of the present invention provide an intelligent driving control method, system, electronic device and storage medium based on multi-module interaction. Based on the technology of the previous key modules of intelligent driving, a multi-module interactive intelligent driving product solution is proposed. The method uses local map information obtained from the high-precision map and the perception data obtained from the perception fusion module to compensate for the error of the positioning information, realize data interaction and improve data accuracy; distinguish the perception data based on the local trajectory obtained by planning, and mark the focus objects based on the vehicle's driving situation and setting rules to further ensure driving safety; judge the degree of dependence of the current intelligent driving on the data of each module based on the control rules of the current path planning. When the high-precision positioning module or the perception fusion module determines that its own data has errors and needs to be corrected and the path planning module can rely on the data of another module to complete the path planning, the error correction is directly performed; thereby greatly improving the rationality of the product and reducing the waste of resources.

[0109] It should be noted that, in the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0110] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0111] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0112] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0113] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0114] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0115] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. An intelligent driving control method based on multi-module interaction, characterized in that: The intelligent driving control method includes: Determine perception data of the environment and objects around the vehicle based on data collected by various sensors; Acquiring real-time vehicle posture information and local map information within a set range with the vehicle posture information as a reference; and performing error compensation on the vehicle posture information based on the local map information and the perception data; Performing path planning based on the perception data, vehicle posture information, and local map information to obtain a local trajectory, and performing trajectory control on the vehicle based on the calculated local trajectory; The intelligent driving control method further includes: Determine, based on the current control rules of the path planning, the degree to which the current intelligent driving relies on the perception data and the vehicle posture information respectively; When it is determined during the real-time calculation of one of the perception data and the vehicle posture information that the own data has an error and needs to be corrected, and when it is determined that the path planning can be completed relying on the other data, the error correction is directly performed.

2. The intelligent driving control method according to claim 1, characterized in that: The process of determining the perception data of the environment and objects around the vehicle based on the data collected by various sensors includes: The objects in the data collected by various sensors are identified separately by deep learning, and the object information output by different sensors is fused to obtain the perception data; the data collected by the sensors include: data collected by cameras and radars.

3. The intelligent driving control method according to claim 1, characterized in that: After obtaining the perception data, the method further includes: Differentiating the perception data based on the local trajectory, and marking objects of particular interest based on the vehicle's driving context and set rules; The motion trajectory of the focused object is predicted using the local map information.

4. The intelligent driving control method according to claim 1, characterized in that: The process of obtaining real-time vehicle position information and local map information within a set range based on the vehicle position information includes: The positioning data is fused using the information from GNSS_RTK, IMU, VCU, and HD_MAP to obtain high-precision vehicle posture information and the local map information.

5. The intelligent driving control method according to claim 1, characterized in that: The algorithm for calculating the local trajectory based on the perception data, vehicle posture information and local map information includes: A star algorithm and Dijkstra algorithm; The algorithm for controlling the trajectory of the vehicle based on the calculated local trajectory is a PID algorithm.

6. The intelligent driving control method according to claim 1, characterized in that: The data collected by the sensor previously includes: Select the rear axle center as the target positioning point and the right front upper part as the vehicle coordinate system. Use a 3D vehicle model to measure the installation posture parameters between each sensor and the target positioning point, and calibrate all sensors to the target positioning point coordinate system. The intelligent driving control method also includes: setting a human-computer interaction module, which is used to receive assistance information provided by the algorithm layer and display information about the environment and vehicle status.

7. An intelligent driving control system based on multi-module interaction, the intelligent driving control system comprising: The sensor layer, algorithm layer and interaction layer are characterized in that the algorithm layer includes: a perception fusion module, a high-precision positioning module, a planning and control module and an interaction module; The perception fusion module is used to determine the perception data of the environment and objects around the vehicle based on the data collected by various sensors; The high-precision positioning module is used to obtain real-time vehicle posture information and local map information within a set range with the vehicle posture information as a reference; and perform error compensation on the vehicle posture information based on the local map information and the perception data; The planning and control module is configured to perform path planning based on the perception data, vehicle posture information, and local map information to obtain a local trajectory, and to perform trajectory control on the vehicle based on the calculated local trajectory; The interaction module is configured to determine, based on the current control rules of the path planning, the degree of dependence of the current intelligent driving on the perception fusion module and the high-precision positioning module respectively; when one of the perception fusion module and the high-precision positioning module determines during the real-time data calculation process that its own data has errors and needs to be corrected, and when it is determined that the path planning can be completed relying on the data of the other module, directly correct the errors; The intelligent driving control system further includes: Determine, based on the current control rules of the path planning, the degree to which the current intelligent driving relies on the perception data and the vehicle posture information respectively; When it is determined during the real-time calculation of one of the perception data and the vehicle posture information that the own data has an error and needs to be corrected, and when it is determined that the path planning can be completed relying on the other data, the error correction is directly performed.

8. An electronic device, characterized in that: It includes a memory and a processor, and the processor is used to implement the steps of the multi-module interactive intelligent driving control method according to any one of claims 1 to 6 when executing a computer management program stored in the memory.

9. A computer-readable storage medium, characterized in that A computer management program is stored thereon, and when the computer management program is executed by the processor, the steps of the intelligent driving control method based on multi-module interaction as described in any one of claims 1 to 6 are implemented.

Images