Vehicle path planning system and method

Abstract

The invention provides a vehicle path planning system and method, and belongs to the technical field of automatic driving. The vehicle path planning system is configured on a vehicle and comprises an environment sensing module, a data processing module, a path planning module and a vehicle control module. The environment sensing module is used for acquiring environment sensing data; the data processing module is used for determining target environment data based on the environment perception data, and the target environment data comprises an object recognition result and a three-dimensional environment model; the path planning module is used for determining path data of a target path from a current position corresponding to the vehicle to a target position based on the target environment data; the vehicle control module is used for determining driving control data based on the path data of the target path; and controlling the vehicle to execute corresponding driving actions based on the driving control data. According to the scheme, the dynamic change of the surrounding environment of the vehicle can be sensed and understood in real time, so that the path is dynamically adjusted, and the accuracy and adaptability of path planning are improved.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a vehicle path planning system and method. Background Art

[0002] With the development of artificial intelligence technology, autonomous driving technology is becoming more and more mature. At present, autonomous driving vehicles mainly rely on static maps and traditional path planning algorithms to navigate when driving. However, this traditional path planning method based on static maps has certain limitations. When facing traffic congestion, accidents or construction, due to the deviation between the actual road conditions and the information provided by the static map, if the autonomous driving vehicle continues to drive along the original planned path, it may encounter extremely low traffic efficiency or even be unable to pass. Therefore, the traditional path planning method cannot fully take into account the dynamically changing traffic environment, resulting in low accuracy and poor adaptability of the planned path. Summary of the invention

[0003] The embodiment of the present application provides a vehicle path planning system and method, which can perceive and understand the dynamic changes of the vehicle's surrounding environment in real time, thereby dynamically adjusting the path and improving the accuracy and adaptability of path planning. The technical solution is as follows:

[0004] On the one hand, a vehicle path planning system is provided, which is configured in a vehicle, and the vehicle path planning system includes an environment perception module, a data processing module, a path planning module and a vehicle control module;

[0005] The environment perception module is used to obtain environment perception data, and the environment perception data is used to indicate the road structure and object distribution in the environment around the vehicle; and send the environment perception data to the data processing module;

[0006] The data processing module is used to determine target environment data based on the environment perception data, wherein the target environment data includes object recognition results and a three-dimensional environment model, wherein the object recognition results are used to indicate the object type, spatial position and geometric form of different objects in the vehicle surrounding environment, and the three-dimensional environment model is used to indicate static objects and dynamic objects in the vehicle surrounding environment, wherein the object types include roads, traffic signs, vehicles, pedestrians and obstacles; and send the target environment data to the path planning module;

[0007] The path planning module is used to determine the path data of the target path from the current position corresponding to the vehicle to the target position based on the target environment data; and send the path data of the target path to the vehicle control module;

[0008] The vehicle control module is used to determine driving control data based on the path data of the target path, and the driving control data includes at least one of speed control data, gear control data and steering control data; based on the driving control data, control the vehicle to perform corresponding driving actions.

[0009] In some embodiments, the environment perception module includes a data acquisition module, and the data acquisition module is used to obtain image data, radar data, and sensor data within a preset perception range of the vehicle;

[0010] The environmental perception module also includes a data communication module, which is used to obtain environmental data sent by other vehicles within a preset communication range of the vehicle. The environmental data sent by any vehicle is used to indicate the environment within the preset perception range of the vehicle.

[0011] In some embodiments, the data processing module is used to perform target detection based on the environmental perception data to obtain the object recognition result; and perform modeling based on the object recognition result to obtain the three-dimensional environment model.

[0012] In some embodiments, the path planning module is used to simulate the vehicle driving conditions in different areas of the vehicle surrounding environment based on the target environment data to obtain risk assessment data, and the risk assessment data is used to indicate the risk level of accidents in different areas of the vehicle surrounding environment;

[0013] The path planning module is also used to determine multiple candidate paths from the current location to the target location based on the target environment data; determine multiple preliminary screening paths from the multiple candidate paths based on the path data of the multiple candidate paths and the risk assessment data, and the area included in each preliminary screening path is within a preset risk level range; based on preset rules, select the target path from the multiple preliminary screening paths and determine the path data of the target path.

[0014] In some embodiments, the path planning module is used to predict the movement of dynamic objects in the vehicle's surrounding environment based on the target environment data to obtain object prediction data, wherein the object prediction data is used to indicate the predicted movement trajectories of different dynamic objects in the vehicle's surrounding environment;

[0015] The path planning module is also used to determine a reference path from the current position to the target position based on the data of the static object indicated by the three-dimensional environment model; based on the object prediction data, adjust the local path in the reference path to obtain the target path, and determine the path data of the target path.

[0016] On the other hand, a vehicle path planning method is provided, which is applied to a vehicle path planning system configured in a vehicle, wherein the vehicle path planning system includes an environment perception module, a data processing module, a path planning module, and a vehicle control module, and the method includes:

[0017] Acquiring environmental perception data through the environmental perception module, wherein the environmental perception data is used to indicate the road structure and object distribution in the environment surrounding the vehicle; and sending the environmental perception data to the data processing module;

[0018] Determine, by the data processing module, target environment data based on the environment perception data, the target environment data including object recognition results and a three-dimensional environment model, the object recognition results are used to indicate the object type, spatial position and geometric form of different objects in the vehicle surrounding environment, the three-dimensional environment model is used to indicate static objects and dynamic objects in the vehicle surrounding environment, the object types include roads, traffic signs, vehicles, pedestrians and obstacles; send the target environment data to the path planning module;

[0019] Determine, by the path planning module, path data of a target path from a current position corresponding to the vehicle to a target position based on the target environment data; and send the path data of the target path to the vehicle control module;

[0020] Through the vehicle control module, based on the path data of the target path, driving control data is determined, and the driving control data includes at least one of speed control data, gear control data and steering control data; based on the driving control data, the vehicle is controlled to perform corresponding driving actions.

[0021] In some embodiments, the environment perception module includes a data acquisition module and a data communication module;

[0022] The obtaining of environmental perception data through the environmental perception module includes at least one of the following:

[0023] The data acquisition module is used to obtain image data, radar data and sensor data within the preset perception range of the vehicle. The data communication module is used to obtain environmental data sent by other vehicles within the preset communication range of the vehicle. The environmental data sent by any vehicle is used to indicate the environment within the preset perception range of the vehicle.

[0024] In some embodiments, determining target environment data based on the environment perception data by the data processing module includes:

[0025] Through the data processing module, target detection is performed based on the environmental perception data to obtain the object recognition result; modeling is performed based on the object recognition result to obtain the three-dimensional environment model.

[0026] In some embodiments, determining, by the path planning module, path data of a target path from a current position corresponding to the vehicle to a target position based on the target environment data, includes:

[0027] Through the path planning module, based on the target environment data, multiple candidate paths from the current position to the target position are determined; based on the target environment data, the vehicle driving conditions in different areas of the vehicle surrounding environment are simulated to obtain risk assessment data, and the risk assessment data is used to indicate the risk level of accidents in different areas of the vehicle surrounding environment; based on the path data of the multiple candidate paths and the risk assessment data, multiple preliminary screening paths are determined from the multiple candidate paths, and the areas included in each preliminary screening path are within a preset risk level range; based on preset rules, the target path is selected from the multiple preliminary screening paths, and the path data of the target path is determined.

[0028] In some embodiments, determining, by the path planning module, path data of a target path from a current position corresponding to the vehicle to a target position based on the target environment data, includes:

[0029] Through the path planning module, based on the data of the static objects indicated by the three-dimensional environment model, a reference path from the current position to the target position is determined; based on the target environment data, the movement of dynamic objects in the vehicle's surrounding environment is predicted to obtain object prediction data, and the object prediction data is used to indicate the predicted movement trajectories of different dynamic objects in the vehicle's surrounding environment; based on the object prediction data, the local path in the reference path is adjusted to obtain the target path, and the path data of the target path is determined.

[0030] On the other hand, a vehicle-mounted control system is provided, which includes a main control module, the main control module includes a processor and a memory, the memory is used to store at least one computer program, and the at least one computer program is loaded and executed by the processor to implement the vehicle path planning method in an embodiment of the present application.

[0031] On the other hand, a computer-readable storage medium is provided, in which at least one computer program is stored. The at least one computer program is loaded and executed by a processor to implement the vehicle path planning method in an embodiment of the present application.

[0032] On the other hand, a computer program product is provided, including a computer program, wherein the computer program is executed by a processor to implement the vehicle path planning method in the embodiment of the present application.

[0033] The present application provides a vehicle path planning method, the vehicle path planning system is configured in a vehicle, and the system includes an environment perception module, a data processing module, a path planning module and a vehicle control module. The environment perception module can obtain environment perception data in real time to perceive the dynamic changes of the vehicle's surrounding environment in real time. The data processing module can determine the target environment data based on the environment perception data, and the target environment data includes object recognition results and a three-dimensional environment model, which realizes the real-time understanding of the dynamic changes of the vehicle's surrounding environment. The path planning module can determine the path data of the target path from the current position corresponding to the vehicle to the target position based on the target environment data. The vehicle control module can determine the driving control data based on the path data of the target path, and control the vehicle to perform the corresponding driving action based on the driving control data. Through the above-mentioned multiple modules, this solution can perceive and understand the dynamic changes of the vehicle's surrounding environment in real time, thereby dynamically adjusting the path, which not only improves the accuracy and adaptability of path planning, but also ensures safety and high efficiency during driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0035] Figure 1 is a schematic diagram of a vehicle path planning system provided according to an embodiment of the present application;

[0036] Figure 2 is a flow chart of a vehicle path planning method provided according to an embodiment of the present application;

[0037] Figure 3 is a flow chart of another vehicle path planning method provided according to an embodiment of the present application;

[0038] Figure 4 It is a structural schematic diagram of a vehicle control system provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0039] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0040] In this application, the terms "first", "second", etc. are used to distinguish identical or similar items with substantially the same effects and functions. It should be understood that there is no logical or temporal dependency between "first", "second", and "nth", nor are there any limitations on quantity and execution order.

[0041] In the present application, the term "at least one" means one or more, and the term "plurality" means two or more.

[0042] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions. For example, the environmental perception data involved in this application is obtained with full authorization.

[0043] Figure 1 is a schematic diagram of a vehicle path planning system provided according to an embodiment of the present application. Figure 1 The vehicle path planning system includes an environment perception module 101 , a data processing module 102 , a path planning module 103 and a vehicle control module 104 . The vehicle path planning system is configured in a vehicle 100 .

[0044] The environment perception module 101 is used to obtain environment perception data, and the environment perception data is used to indicate the road structure and object distribution in the vehicle's surrounding environment; the environment perception data is sent to the data processing module 102; the data processing module 102 is used to determine the target environment data based on the environment perception data, and the target environment data includes object recognition results and a three-dimensional environment model, and the object recognition results are used to indicate the object type, spatial position and geometric shape of different objects in the vehicle's surrounding environment, and the three-dimensional environment model is used to indicate static objects and dynamic objects in the vehicle's surrounding environment, and the object types include roads, traffic signs, vehicles, pedestrians and obstacles; the target environment data is sent to the path planning module 103; the path planning module 103 is used to determine the path data of the target path from the current position corresponding to the vehicle to the target position based on the target environment data; the path data of the target path is sent to the vehicle control module 104; the vehicle control module 104 is used to determine the driving control data based on the path data of the target path, and the driving control data includes at least one of the speed control data, the gear control data and the steering control data; based on the driving control data, the vehicle 100 is controlled to perform the corresponding driving action.

[0045] In some embodiments, the environmental perception module 101 includes a data acquisition module 1011, which is used to obtain image data, radar data and sensor data within a preset perception range of the vehicle; the environmental perception module 101 also includes a data communication module 1012, which is used to obtain environmental data sent by other vehicles within the preset communication range of the vehicle. The environmental data sent by any vehicle is used to indicate the environment within the preset perception range of the vehicle.

[0046] In some embodiments, the data processing module 102 is used to perform target detection based on the environmental perception data to obtain an object recognition result; and to perform modeling based on the object recognition result to obtain a three-dimensional environmental model.

[0047] In some embodiments, the path planning module 103 is used to simulate the vehicle driving conditions in different areas of the vehicle's surrounding environment based on the target environment data to obtain risk assessment data, and the risk assessment data is used to indicate the risk level of accidents in different areas of the vehicle's surrounding environment; the path planning module 103 is also used to determine multiple candidate paths from the current position to the target position based on the target environment data; based on the path data and risk assessment data of the multiple candidate paths, determine multiple preliminary screening paths from the multiple candidate paths, and the areas included in each preliminary screening path are within a preset risk level range; based on preset rules, select a target path from the multiple preliminary screening paths, and determine the path data of the target path.

[0048] In some embodiments, the path planning module 103 is used to predict the movement of dynamic objects in the vehicle's surrounding environment based on the target environment data to obtain object prediction data, and the object prediction data is used to indicate the predicted movement trajectories of different dynamic objects in the vehicle's surrounding environment; the path planning module 103 is also used to determine a reference path from the current position to the target position based on the data of static objects indicated by the three-dimensional environment model; based on the object prediction data, adjust the local path in the reference path to obtain the target path, and determine the path data of the target path.

[0049] It should be noted that: the vehicle path planning system provided in the above embodiment only uses the division of the above functional modules as an example when running an application program. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the terminal is divided into different functional modules to complete all or part of the functions described above. In addition, the vehicle path planning system provided in the above embodiment and the vehicle path planning method embodiment described below belong to the same concept, and the specific implementation process is shown in the method embodiment.

[0050] Figure 2is a flow chart of a vehicle path planning method provided according to an embodiment of the present application. The method is executed by a vehicle path planning system configured in a vehicle. The vehicle path planning system includes an environment perception module, a data processing module, a path planning module and a vehicle control module. Figure 2 As shown, the method comprises the following steps:

[0051] 201. The system obtains environmental perception data through the environmental perception module and sends the environmental perception data to the data processing module. The environmental perception data is used to indicate the road structure and object distribution around the vehicle.

[0052] In the embodiment of the present application, the environmental perception module is mainly used to collect data on the vehicle's surrounding environment, obtain environmental perception data, and perform data transmission and data communication on the environmental perception data.

[0053] Optionally, the system acquires environmental perception data through multiple devices that have a communication relationship with the system. The multiple devices that have a communication relationship with the system may include acquisition devices such as laser radar, camera, radar sensor, and ultrasonic sensor, and may also include communication devices for sending and receiving signals, which can communicate with other vehicles. The embodiments of the present application do not limit the content of the multiple devices.

[0054] Accordingly, the environmental perception data includes at least one of the radar data collected by the laser radar, the image data collected by the camera, the sensor data collected by the radar sensor, the sensor data collected by the ultrasonic sensor, and the signals sent by other vehicles. The radar data collected by the laser radar is high-resolution point cloud data, which can provide the vehicle with high-precision information such as distance, speed, direction, and obstacle shape. The image data collected by the camera can indicate visual information such as color, texture, shape, etc. in the vehicle's surrounding environment, which is convenient for identifying road signs, pedestrians, and vehicles. The sensor data collected by the radar sensor can reflect dynamic objects in a distant environment. The sensor data collected by the ultrasonic sensor can reflect the information of obstacles at close range. The signals sent by other vehicles contain environmental data collected by other vehicles. Environmental perception data can reflect information in the vehicle's surrounding environment, such as roads, traffic signs, pedestrians, other vehicles, and obstacles.

[0055] 202. The system determines the target environment data based on the environment perception data through the data processing module, and sends the target environment data to the path planning module. The target environment data includes object recognition results and a three-dimensional environment model. The object recognition results are used to indicate the object type, spatial position and geometric shape of different objects in the vehicle's surrounding environment. The three-dimensional environment model is used to indicate static objects and dynamic objects in the vehicle's surrounding environment.

[0056] In the embodiment of the present application, after acquiring the environmental perception data, the data processing module can perform data processing based on the environmental perception data to obtain the target environmental data, and perform data transmission and data communication for the target environmental data. More specifically, by identifying objects and performing environmental modeling, object recognition results and three-dimensional environmental models can be obtained, thereby achieving a comprehensive understanding of the vehicle's surrounding environment. The goal of this stage is to identify safe passage areas and potential dangers.

[0057] The data processing process performed by the data processing module may include data preprocessing and data fusion. Data fusion includes image processing, target detection, semantic segmentation, and data modeling. This stage involves computer vision technology, deep learning algorithms, and data modeling algorithms. In order to fully understand the surrounding environment of the vehicle, objects are divided into different object types, including roads, traffic signs, vehicles, pedestrians, and obstacles. Roads and traffic signs can reflect the road structure around the vehicle, and pedestrians, vehicles, and obstacles can reflect the distribution of objects around the vehicle.

[0058] Among them, the object recognition results can reflect the shape, width, curvature of the road, the type and location of traffic signs, the speed, direction, and location of vehicles and pedestrians, and the size, shape, and location of obstacles, etc. The three-dimensional environment model can be used to predict the behavior of vehicles and pedestrians.

[0059] 203. The system determines the path data of the target path from the current position corresponding to the vehicle to the target position based on the target environment data through the path planning module, and sends the path data of the target path to the vehicle control module.

[0060] In the embodiment of the present application, after acquiring the target environment data, the path planning module can determine the path data of the target path based on the target environment data, and perform data transmission and data communication for the path data of the target path. It should be noted that factors such as traffic rules, speed limits, obstacle locations, and dynamic environmental changes will be considered at this stage to ensure safety and efficiency.

[0061] Among them, the path planning module is used to predict traffic conditions, road condition changes, and the behavior of other vehicles and pedestrians based on the target environment data to achieve efficient and safe path generation. After obtaining the location data of the current location and the location data of the target location, the path planning module can directly generate the target path in combination with the target environment data; it can also generate an initial path first, and then modify it in combination with the target environment data to obtain the target path; it can also generate multiple candidate paths, and then screen them in combination with the target environment data to obtain the target path. The embodiment of the present application does not select a specific method for determining the target path.

[0062] 204. The system determines driving control data based on the path data of the target path through the vehicle control module. The driving control data includes at least one of speed control data, gear control data and steering control data. Based on the driving control data, the system controls the vehicle to perform corresponding driving actions.

[0063] In the embodiment of the present application, after acquiring the path planning data, the vehicle control module can calculate the specific driving action based on the path planning data and obtain the driving control data, that is, the corresponding control instructions. The system controls the vehicle by sending the above control instructions to multiple controllers that have a communication relationship with the system, so that the vehicle travels according to the target path. Among them, the multiple controllers that have a communication relationship with the system include a motor controller, a transmission controller, and a steering controller.

[0064] The embodiment of the present application provides a vehicle path planning method, which can realize vehicle path planning and automatic driving by configuring a vehicle path planning system in the vehicle. The environmental perception module can obtain environmental perception data in real time to perceive the dynamic changes of the vehicle's surrounding environment in real time. The data processing module can determine the target environmental data such as object recognition results and three-dimensional environmental models based on the environmental perception data, and then the path planning module can determine the path data of the target path, and the vehicle control module can control the vehicle to perform corresponding driving actions, so as to travel according to the target path. This solution can perceive and understand the dynamic changes of the vehicle's surrounding environment in real time, so as to dynamically adjust the path, which not only improves the accuracy and adaptability of path planning, but also ensures safety and high efficiency during driving.

[0065] Above Figure 2 The main process of the vehicle path planning method provided in the embodiment of the present application is exemplified, and various contents of the method are described in detail below. Figure 3 is a flow chart of another vehicle path planning method provided according to an embodiment of the present application, the method is executed by a vehicle path planning system configured in a vehicle, see Figure 3 As shown, the method comprises the following steps:

[0066] 301. The system obtains environmental data within a preset perception range of the vehicle through an environmental perception module, where the environmental data includes at least one of image data, radar data, and sensor data.

[0067] In the embodiment of the present application, the environment perception module includes a data acquisition module, and the data acquisition module acquires data through multiple connected acquisition devices. The multiple acquisition devices include laser radars, cameras, radar sensors, and ultrasonic sensors. The multiple acquisition devices are used to collect information about the vehicle's surrounding environment in real time. The system acquires environmental perception data by acquiring data sent by multiple acquisition devices through the data acquisition module.

[0068] The preset sensing range refers to the coverage area where the environmental sensing module collects information in real time by integrating multiple components. The preset sensing range can be dynamically adjusted according to the driving needs of the vehicle to comprehensively detect the surrounding environment of the vehicle. For example, when the road conditions are more complicated, a larger preset sensing range is used to obtain more data; when the road conditions are simpler, a smaller preset sensing range is used to save performance.

[0069] 302. The system obtains environmental data sent by other vehicles within a preset communication range of the vehicle through an environmental perception module. The environmental data sent by any vehicle is used to indicate the environment within the preset perception range of the vehicle.

[0070] In an embodiment of the present application, the environment perception module includes a data communication module, and the data communication module is connected to a communication device for sending and receiving signals to obtain data. The communication device can obtain wireless broadcast signals sent by other vehicles within the preset communication range of the vehicle. After the communication device obtains the wireless broadcast signal, the system obtains the corresponding data of the wireless broadcast signal sent by the communication device through the data communication module and parses it, thereby obtaining environment perception data.

[0071] The wireless broadcast signal includes not only the environmental data within the preset sensing range of the vehicle sending the signal, but also the coordinates of the vehicle sending the signal and the direction of travel of the vehicle sending the signal. When the current vehicle obtains the wireless broadcast signal, it can determine the relative position between the vehicle sending the signal and the current vehicle, which facilitates subsequent object recognition and modeling based on the environmental data carried by the wireless broadcast signal.

[0072] Among them, the preset communication range refers to the coverage area of ​​the environmental perception module by acquiring wireless broadcast signals sent by other vehicles. The preset communication range can be dynamically adjusted according to the driving needs of the vehicle, so as to comprehensively detect the surrounding environment of the vehicle. For example, when the road conditions are more complicated, a larger preset communication range is used to obtain environmental data in a larger range around the vehicle, so as to facilitate the planning of the route in advance for subsequent road conditions; when the road conditions are relatively simple, there is no need to obtain data in a too large range, and a smaller preset communication range can be used to save performance. For example, the preset communication range refers to a range of ten meters centered on the current vehicle; or the preset communication range refers to a preset angle range in front of the current vehicle; or the preset communication range refers to the range of five meters before and after the current lane and the adjacent lane, etc.

[0073] It should be noted that the above steps 301 and 302 are two exemplary ways of obtaining environmental perception data through the environmental perception module. Optionally, the system may only execute step 301 or step 302, or may execute step 301 and step 302 at the same time, which is not limited in the embodiment of the present application. The data obtained by the system executing the above steps are all environmental perception data, and the environmental perception data is sent to the data processing module through the environmental perception module.

[0074] 303. The system determines target environmental data based on environmental perception data through a data processing module. The environmental perception data includes environmental data within a preset perception range of the vehicle and environmental data sent by other vehicles. The target environmental data includes object recognition results and a three-dimensional environmental model.

[0075] In the embodiment of the present application, the principle by which the system determines the target environment data is the same as step 202 and will not be repeated here.

[0076] In some embodiments, the system obtains object recognition results and three-dimensional environment models in sequence based on the environmental perception data. Accordingly, after acquiring the environmental perception data, the data processing module first performs data preprocessing. Data preprocessing is used to organize the original environmental perception data to ensure the effectiveness and accuracy of subsequent processing steps. Data preprocessing may include at least one of data cleaning, data format conversion, data normalization or standardization, and data dimensionality reduction. Data cleaning is used to remove noise, fill missing values, or correct erroneous data; data format conversion is used to adapt to different algorithm requirements; data normalization or standardization is used to eliminate dimensional differences between different data sources; data dimensionality reduction is used to reduce the complexity of data by extracting key features.

[0077] After obtaining the pre-processed environmental perception data, the data processing module obtains the object recognition result based on the environmental perception data through image processing, target detection and semantic segmentation. Image processing is used to improve the quality and extract key features of the image data collected by the camera, such as denoising, contrast enhancement, edge sharpening, etc. Target detection is used to identify and locate different objects from the image. Semantic segmentation is used to further refine the recognition task. On the basis of locating different objects, it classifies based on the pixels in the image to distinguish the object types of different objects. After obtaining the object recognition result, the data processing module obtains a three-dimensional environment model through data modeling based on the object recognition result.

[0078] It should be noted that the multiple data processing processes in step 303 can be implemented by the environmental perception model. The environmental perception model is a deep learning model suitable for intelligent driving scenarios, which is used to accurately perceive and understand dynamic information such as roads, obstacles and traffic flows from environmental perception data. The environmental perception model uses a large amount of training data such as driving data and environmental perception data during the training phase. The training data includes sensor data, vehicle status information, and road condition data. In the process of collecting training data, data preprocessing and labeling are also required so that the environmental information can be accurately identified and understood when training the model, which will not be described in detail.

[0079] 304. The system determines, through a path planning module, path data of a target path from a current position corresponding to the vehicle to a target position based on the target environment data.

[0080] In the embodiment of the present application, the principle by which the system determines the path data of the target path is the same as step 203 and will not be repeated here.

[0081] In some embodiments, the system determines the target path in combination with the risk assessment data. Accordingly, the system determines multiple candidate paths from the current position to the target position based on the target environment data through the path planning module; based on the target environment data, simulates the vehicle driving conditions in different areas of the vehicle's surrounding environment to obtain risk assessment data; based on the path data and risk assessment data of multiple candidate paths, determines multiple preliminary screening paths from multiple candidate paths; based on preset rules, selects the target path from multiple preliminary screening paths, and determines the path data of the target path. Among them, the risk assessment data is used to indicate the risk level of accidents in different areas of the vehicle's surrounding environment. The areas included in each preliminary screening path are within the preset risk level range. That is, if any candidate path passes through an area outside the preset risk level range, the candidate path is discarded; if any candidate path does not pass through an area outside the preset risk level range, the candidate path is retained and determined as the preliminary screening path.

[0082] In some embodiments, the system determines the target path in combination with the object prediction data. Accordingly, the system determines the reference path from the current position to the target position through the path planning module based on the data of the static objects indicated by the three-dimensional environment model; based on the target environment data, the movement of the dynamic objects in the vehicle's surrounding environment is predicted to obtain the object prediction data; based on the object prediction data, the local path in the reference path is adjusted to obtain the target path, and the path data of the target path is determined. Among them, the object prediction data is used to indicate the predicted movement trajectory of different dynamic objects in the vehicle's surrounding environment. For example, the object prediction data is used to indicate the predicted movement trajectory of pedestrians or other vehicles. Optionally, the object prediction data may also include a predicted movement speed.

[0083] It should be noted that the data processing process in step 304 can be implemented by a path planning algorithm for dynamic environments. The path planning algorithm for dynamic environments can dynamically adjust the path according to environmental information and vehicle status in real time, taking into account traffic conditions, road conditions, and the behavior of other vehicles, and achieve efficient and safe path generation. The algorithm combines deep learning and traditional path planning algorithms, such as A*, Dijkstra, and neural RRT*, which enables the system to make full use of environmental perception data for path optimization.

[0084] It should be noted that the system integrates an environmental perception model and a path planning algorithm for dynamic environments, and the system performance can be continuously improved through online learning and optimization strategies. This includes work in system architecture design, algorithm implementation, hardware platform adaptation, etc., to ensure that the system can run stably and perform well in different scenarios.

[0085] 305. The system determines driving control data based on the path data of the target path through the vehicle control module, and controls the vehicle to perform corresponding driving actions based on the driving control data. The driving control data includes at least one of speed control data, gear control data and steering control data.

[0086] In the embodiment of the present application, the principle of the system controlling the vehicle to perform the corresponding driving action is the same as step 204, which will not be repeated here. During the operation of the system, the system performance is continuously improved by monitoring the system operation status and collecting feedback data.

[0087] The embodiment of the present application provides a vehicle path planning method, which can realize vehicle path planning and automatic driving by configuring a vehicle path planning system in the vehicle. The system can collect environmental data around the current vehicle in real time, or obtain environmental data sent by other vehicles, so as to perceive the dynamic changes of the vehicle's surrounding environment in real time. After determining the target environmental data based on the environmental perception data, the system can determine the path data of the target path in combination with the risk assessment data or the object prediction data, thereby controlling the vehicle to perform the corresponding driving action, so as to travel according to the target path.

[0088] The embodiments of the present application can achieve at least the following technical effects: (1) Dynamic environment perception: It can perceive and understand the dynamic changes of the vehicle's surrounding environment in real time, including information such as traffic flow, road conditions and obstacles. This fully takes into account the dynamic traffic conditions, road conditions and the behavior of other vehicles, so that the system can understand the real-time traffic conditions more accurately, thereby performing more reliable path planning. Even in the face of real-time traffic congestion, accidents or construction, the system can obtain the optimal path planning; (2) Real-time path planning: Combined with the environmental perception model, a path planning algorithm for dynamic environments is obtained. The algorithm can dynamically adjust the path according to real-time environmental information and vehicle status, and the system can make timely and safe driving decisions, ensuring safety and efficiency during driving; (3) Online learning and optimization: By introducing an online learning mechanism, the system can continuously optimize the environmental perception model and path planning algorithm to adapt to different driving scenarios and user needs, thereby improving the accuracy and adaptability of path planning. This enables the system to continuously improve and adapt to new driving environments and maintain a high level of path planning capabilities.

[0089] Figure 4 It is a structural schematic diagram of a vehicle control system provided according to an embodiment of the present application.

[0090] Generally, the vehicle control system 400 includes: a main control module 401 and a CAN interface 402. The main control module 401 is connected to the CAN interface 402.

[0091] The main control module 401 generally includes a processor and a memory. The main control module is configured with the vehicle path planning system provided in the system embodiment of the present application. The main control module is used to implement the vehicle path planning method provided in the method embodiment of the present application.

[0092] Among them, the processor may include one or more processing cores, such as a 4-core processor, a 4-core processor, etc. The processor may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the vehicle display screen. In some embodiments, the processor may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning. The memory may include one or more computer-readable storage media, which may be non-transitory. The memory may also include a high-speed random access memory and a non-volatile memory, such as one or more disk storage devices and flash storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory is used to store at least one computer program, which is used to be executed by the processor to implement the vehicle path planning method provided by the method embodiment of the present application.

[0093] The CAN interface 402 may include a plurality of controller interfaces for communicating with a motor controller, a transmission controller, and a steering controller, etc. The main control module 401 can be connected to a plurality of controllers through the above-mentioned plurality of controller interfaces, and send control instructions to the plurality of controllers to realize control of the vehicle. Among them, the motor controller, the transmission controller, and the steering controller, etc. are all the executive components of the vehicle. The motor controller is used to control the motor speed and torque output of the vehicle to realize speed control and power output. The transmission controller is used to adjust the gear of the vehicle to match the current driving speed and power demand. The steering controller is used to control the steering system of the vehicle to realize steering control.

[0094] The CAN interface 402 may also include multiple acquisition device interfaces for communicating with LiDAR (Light Detection And Ranging), cameras, radar sensors, and ultrasonic sensors. The main control module 401 can be connected to multiple acquisition devices through the above-mentioned multiple acquisition device interfaces to obtain data sent by multiple acquisition devices to realize the collection of environmental data around the vehicle. Among them, the laser radar can generate high-resolution point cloud data by emitting a laser beam and obtaining the signal reflected back. The camera can capture images of the vehicle's surrounding environment. The radar sensor has long-distance detection capabilities and is not affected by lighting conditions. It can collect information about dynamic objects in a distant environment. The ultrasonic sensor can collect information about obstacles at close range.

[0095] The CAN interface 402 may also include a device interface for communicating with a communication device. The main control module 401 can be connected to the communication device through the above device interface to obtain the corresponding data of the wireless broadcast signal sent by the communication device. Since the wireless broadcast signal is a signal containing environmental data sent by other vehicles within the preset communication range of the current vehicle, the main control module 401 can collect the environmental data around the vehicle by parsing the corresponding data of the wireless broadcast signal.

[0096] Those skilled in the art will understand that Figure 4 The structure shown in the figure does not constitute a limitation on the vehicle control system 400, and may include more or less components than those shown in the figure, or combine certain components, or adopt a different component arrangement.

[0097] The embodiment of the present application also provides a computer-readable storage medium, in which at least one computer program is stored, and the at least one computer program is loaded and executed by a processor to implement the vehicle path planning method in the above embodiment. For example, the computer-readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), a magnetic tape, a floppy disk, and an optical data storage device.

[0098] The embodiment of the present application also provides a computer program product, including a computer program, which is executed by a processor to implement the vehicle path planning method in the embodiment of the present application.

[0099] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0100] The above description is only an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A vehicle path planning system, characterized in that: Configured in a vehicle, the vehicle path planning system includes an environment perception module, a data processing module, a path planning module and a vehicle control module; The environment perception module is used to obtain environment perception data, and the environment perception data is used to indicate the road structure and object distribution in the environment around the vehicle; and send the environment perception data to the data processing module; The data processing module is used to determine target environment data based on the environment perception data, wherein the target environment data includes object recognition results and a three-dimensional environment model, wherein the object recognition results are used to indicate the object type, spatial position and geometric form of different objects in the vehicle surrounding environment, and the three-dimensional environment model is used to indicate static objects and dynamic objects in the vehicle surrounding environment, wherein the object types include roads, traffic signs, vehicles, pedestrians and obstacles; and send the target environment data to the path planning module; The path planning module is used to determine path data of a target path from a current position corresponding to the vehicle to a target position based on the target environment data; sending the path data of the target path to the vehicle control module; The vehicle control module is used to determine driving control data based on the path data of the target path, and the driving control data includes at least one of speed control data, gear control data and steering control data; based on the driving control data, control the vehicle to perform corresponding driving actions.

2. The vehicle path planning system according to claim 1, characterized in that: The environment perception module includes a data acquisition module, and the data acquisition module is used to obtain image data, radar data and sensor data within a preset perception range of the vehicle; The environmental perception module also includes a data communication module, which is used to obtain environmental data sent by other vehicles within a preset communication range of the vehicle. The environmental data sent by any vehicle is used to indicate the environment within the preset perception range of the vehicle.

3. The vehicle path planning system according to claim 1, characterized in that: The data processing module is used to perform target detection based on the environmental perception data to obtain the object recognition result; and to perform modeling based on the object recognition result to obtain the three-dimensional environment model.

4. The vehicle path planning system according to claim 1, characterized in that: The path planning module is used to simulate the vehicle driving conditions in different areas of the vehicle surrounding environment based on the target environment data to obtain risk assessment data, wherein the risk assessment data is used to indicate the risk level of accidents in different areas of the vehicle surrounding environment; The path planning module is further used to determine a plurality of candidate paths from the current location to the target location based on the target environment data; determine a plurality of preliminary screening paths from the plurality of candidate paths based on the path data of the plurality of candidate paths and the risk assessment data, wherein the area included in each preliminary screening path is within a preset risk level range; Based on preset rules, the target path is selected from the multiple preliminary screening paths, and the path data of the target path is determined.

5. The vehicle path planning system according to claim 1, characterized in that: The path planning module is used to predict the movement of dynamic objects in the vehicle's surrounding environment based on the target environment data to obtain object prediction data, wherein the object prediction data is used to indicate the predicted movement trajectories of different dynamic objects in the vehicle's surrounding environment; The path planning module is also used to determine a reference path from the current position to the target position based on the data of the static object indicated by the three-dimensional environment model; based on the object prediction data, adjust the local path in the reference path to obtain the target path, and determine the path data of the target path.

6. A vehicle path planning method, characterized in that: A vehicle path planning system is applied to a vehicle, the vehicle path planning system includes an environment perception module, a data processing module, a path planning module and a vehicle control module, and the method includes: Acquiring environmental perception data through the environmental perception module, wherein the environmental perception data is used to indicate the road structure and object distribution in the environment surrounding the vehicle; and sending the environmental perception data to the data processing module; Determine, by the data processing module, target environment data based on the environment perception data, the target environment data including object recognition results and a three-dimensional environment model, the object recognition results are used to indicate the object type, spatial position and geometric form of different objects in the vehicle surrounding environment, the three-dimensional environment model is used to indicate static objects and dynamic objects in the vehicle surrounding environment, the object types include roads, traffic signs, vehicles, pedestrians and obstacles; send the target environment data to the path planning module; Determine, by the path planning module, path data of a target path from a current position corresponding to the vehicle to a target position based on the target environment data; and send the path data of the target path to the vehicle control module; Through the vehicle control module, based on the path data of the target path, driving control data is determined, and the driving control data includes at least one of speed control data, gear control data and steering control data; based on the driving control data, the vehicle is controlled to perform corresponding driving actions.

7. The vehicle path planning method according to claim 6, characterized in that: The environment perception module includes a data acquisition module and a data communication module; The obtaining of environmental perception data through the environmental perception module includes at least one of the following: Acquiring, through the data acquisition module, image data, radar data, and sensor data within a preset sensing range of the vehicle; The data communication module is used to obtain environmental data sent by other vehicles within the preset communication range of the vehicle, and the environmental data sent by any vehicle is used to indicate the environment within the preset perception range of the vehicle.

8. The vehicle path planning method according to claim 6, characterized in that: The step of determining target environment data based on the environment perception data by the data processing module includes: Through the data processing module, target detection is performed based on the environmental perception data to obtain the object recognition result; modeling is performed based on the object recognition result to obtain the three-dimensional environment model.

9. The vehicle path planning method according to claim 6, characterized in that: The determining, by the path planning module, path data of a target path from a current position corresponding to the vehicle to a target position based on the target environment data includes: Through the path planning module, based on the target environment data, multiple candidate paths from the current position to the target position are determined; based on the target environment data, the vehicle driving conditions in different areas of the vehicle surrounding environment are simulated to obtain risk assessment data, and the risk assessment data is used to indicate the risk level of accidents in different areas of the vehicle surrounding environment; based on the path data of the multiple candidate paths and the risk assessment data, multiple preliminary screening paths are determined from the multiple candidate paths, and the areas included in each preliminary screening path are within a preset risk level range; based on preset rules, the target path is selected from the multiple preliminary screening paths, and the path data of the target path is determined.

10. The vehicle path planning method according to claim 6, characterized in that: The determining, by the path planning module, path data of a target path from a current position corresponding to the vehicle to a target position based on the target environment data includes: Through the path planning module, based on the data of the static objects indicated by the three-dimensional environment model, a reference path from the current position to the target position is determined; based on the target environment data, the movement of dynamic objects in the vehicle's surrounding environment is predicted to obtain object prediction data, and the object prediction data is used to indicate the predicted movement trajectories of different dynamic objects in the vehicle's surrounding environment; based on the object prediction data, the local path in the reference path is adjusted to obtain the target path, and the path data of the target path is determined.

Images