Road model generation method and device, vehicle and medium

Abstract

The invention provides a road model generation method and device, a vehicle and a medium, and relates to the technical field of intelligent auxiliary driving. The method comprises the steps that the real-time offset of a vehicle and ADAS map data of the current mark point position of the vehicle are acquired; the ADAS map data are processed, target road data are obtained, and the road data comprise the road curvature, the road gradient, the road offset and the vehicle offset; performing data filtering and caching on the target road data to obtain effective road data; determining corresponding interval road data in the effective road data according to the vehicle real-time offset; and generating a corresponding three-dimensional road model according to the vehicle real-time offset and the interval road data, and outputting and displaying the three-dimensional road model. According to the method, the visual real-time road model can be provided in the driving process of commercial vehicles such as heavy trucks, and the safe driving and intelligent driving requirements of the heavy trucks are met.

Description

Technical Field

[0001] The present application relates to the field of intelligent assisted driving technology, and in particular to a road model generation method, equipment, vehicle and medium. Background Art

[0002] With the development of economy and the progress of society, people have higher and higher requirements for safe and intelligent driving of commercial vehicles such as heavy trucks.

[0003] In related technologies, heavy trucks usually use Advanced Driver Assistance Systems (ADAS) to ensure vehicle safety and driver convenience. ADAS systems can use sensors, cameras, radars and other technologies to perceive the environment around the vehicle and provide real-time information or automated functions to assist the driver. However, existing ADAS systems cannot provide a visual real-time road model, and the visual real-time road model provided by the current navigation system has low accuracy and cannot meet the safety and intelligent driving requirements of heavy trucks.

[0004] Therefore, there is a need for a road model generation solution that can provide a visual real-time road model and meet the needs of safe and intelligent driving of heavy trucks. Summary of the invention

[0005] The embodiments of the present application provide a road model generation method, device, vehicle and medium, which can provide a visual real-time road model during the driving process of commercial vehicles such as heavy trucks, meeting the safe and intelligent driving requirements of heavy trucks.

[0006] In a first aspect, an embodiment of the present application provides a method for generating a road model based on ADAS map data, comprising:

[0007] Get the real-time vehicle offset and ADAS map data of the vehicle's current marker position;

[0008] Processing the ADAS map data to obtain target road data, wherein the road data includes road curvature, road slope, road offset and vehicle offset;

[0009] Filtering and caching the target road data to obtain valid road data;

[0010] Determine the corresponding section road data in the valid road data according to the real-time vehicle offset;

[0011] A corresponding three-dimensional road model is generated according to the real-time vehicle offset and the section road data, and the three-dimensional road model is output and displayed.

[0012] In a possible implementation manner, the processing the ADAS map data to obtain target road data includes:

[0013] Acquire initial road data in the ADAS map data, wherein the initial road data includes road curvature, road slope, road offset, and vehicle offset in an ADAS protocol format;

[0014] Convert the initial road data into a JSON format.

[0015] The road data in the JSON format is converted into a standard format to obtain target road data.

[0016] In a possible implementation manner, filtering and caching the target road data to obtain valid road data includes:

[0017] Performing data filtering processing on the target road data to remove invalid data and erroneous data in the target road data to obtain first road data at the current marking point position;

[0018] Determine the historical vehicle offset of the last marked point location cached in the storage module;

[0019] determining whether a first vehicle offset in the first road data is less than the historical vehicle offset;

[0020] If it is less than, clearing the historical cache data in the storage module, and caching the first road data to the storage module, and determining the valid road data according to the cached data in the storage module;

[0021] If it is not less than, the first road data of the current marking point position is cached to the storage module in chronological order, and the valid road data is determined according to the cached data in the storage module.

[0022] In a possible implementation manner, before performing data filtering processing on the target road data, the method further includes:

[0023] Determine the target distance between the current mark point position and the last mark point position cached in the storage module;

[0024] Determine whether the target distance is less than a distance threshold;

[0025] If the distance is less than the distance threshold, clearing the target road data and determining valid road data based on the data cached in the storage module;

[0026] If it is not less than the distance threshold, the step of performing data filtering processing on the target road data is executed.

[0027] In a possible implementation manner, determining the corresponding section road data in the valid road data according to the real-time vehicle offset includes:

[0028] Determine a vehicle offset interval in which the real-time vehicle offset is located in the valid road data;

[0029] Determining a road offset interval in the valid road data that matches the vehicle offset interval;

[0030] According to the road offset interval, corresponding interval road data in the valid road data is determined.

[0031] In a possible implementation manner, generating a corresponding three-dimensional road model according to the real-time vehicle offset and the interval road data includes:

[0032] Determine a vehicle offset difference between an end offset and a start offset of the vehicle offset interval;

[0033] A three-dimensional road model including the real-time position of the vehicle is generated according to the road curvature, road slope, road offset interval corresponding to the interval road data, the vehicle offset difference and the road generation plug-in.

[0034] In a possible implementation, generating a three-dimensional road model including a real-time position of a vehicle according to the road curvature, road slope, road offset interval corresponding to the interval road data, the vehicle offset difference, and a road generation plug-in includes:

[0035] Generate an initial road model including the real-time position of the vehicle according to the road curvature, road slope, road offset interval corresponding to the interval road data, the vehicle offset difference and the road generation plug-in;

[0036] Generate a corresponding road boundary line according to the preset road material parameters of the vehicle;

[0037] A three-dimensional road model including the real-time position of the vehicle is generated according to the initial road model and the road boundary line.

[0038] In a second aspect, an embodiment of the present application provides a vehicle-mounted computing device, including:

[0039] A processor, and a memory communicatively connected to the processor;

[0040] Memory is used to store computer executable instructions;

[0041] The processor is used to execute the computer-executable instructions stored in the memory, so that the processor executes the above-mentioned first aspect and / or various possible implementations of the first aspect.

[0042] In a third aspect, an embodiment of the present application provides a vehicle, comprising: an on-board terminal T-BOX, a CAN network, and the on-board computing device as described in the second aspect, wherein the on-board terminal T-BOX is connected to the on-board computing device via the CAN network;

[0043] The vehicle-mounted terminal T-BOX is used to send the vehicle real-time offset and ADAS map data of the position of each marked point of the vehicle to the vehicle-mounted computing device through the CAN network;

[0044] The vehicle-mounted computing device is used to obtain the real-time offset of the vehicle and the ADAS map data of the current mark point position of the vehicle; process the ADAS map data to obtain target road data, the road data including road curvature, road slope, road offset and vehicle offset; filter and cache the target road data to obtain valid road data; determine the corresponding interval road data in the valid road data according to the real-time offset of the vehicle; generate a corresponding three-dimensional road model according to the real-time offset of the vehicle and the interval road data, and output and display the three-dimensional road model.

[0045] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the above-mentioned first aspect and / or various possible implementation methods of the first aspect.

[0046] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, is used to implement the above-mentioned first aspect and / or various possible implementation methods of the first aspect.

[0047] The embodiment of the present application provides a road model generation method, device, vehicle and medium. The on-board computing device can obtain the real-time offset of the vehicle and the ADAS map data of the current mark point position of the vehicle through the on-board terminal T-BOX, and process, filter and cache the ADAS map data to obtain valid road data including road curvature, road slope, road offset and vehicle offset. After that, the corresponding interval road data in the valid road data can be determined according to the real-time offset of the vehicle to determine the accurate position of the vehicle on the road, and finally the corresponding three-dimensional road model can be generated according to the real-time offset of the vehicle and the interval road data. Through such a setting, not only can the three-dimensional road model be constructed in real time using the ADAS map data including information such as road curvature and road slope, but also the real-time positioning of the vehicle in the three-dimensional road model can be realized using the real-time offset of the vehicle, so that the driver can see the visualized real-time road model and the real-time position status of the vehicle through the display screen of the on-board computing device, meeting the safe driving and intelligent driving requirements of heavy trucks. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0049] Figure 1 A system architecture diagram of an embodiment of the present application;

[0050] Figure 2 A flowchart of a method for generating a road model based on ADAS map data according to an embodiment of the present application;

[0051] Figure 3 A schematic diagram of the structure of a vehicle-mounted computing device according to an embodiment of the present application;

[0052] Figure 4 This is a schematic diagram of the structure of a vehicle-mounted computing device according to another embodiment of the present application.

[0053] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0054] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0055] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0056] In the technical solution of this application, the collection, storage, use, processing, transmission, provision and disclosure of information such as financial data or user data involved shall comply with the provisions of relevant laws and regulations and shall not violate public order and good morals.

[0057] It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned, and they should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0058] It should also be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0059] The road model generation method, device, vehicle and medium of the present application can be used in the field of intelligent assisted driving technology, and can also be used in any field other than the field of intelligent assisted driving technology, such as the field of road model generation, etc. The application field of the road model generation method, device, vehicle and medium of the present application is not limited.

[0060] The road model generation method, device, vehicle and medium of the present application can be applied to scenarios in which heavy trucks and other commercial vehicles use ADAS map data to generate road models during driving. Any scenario involving the use of ADAS map data to generate road models can be applied to the road model generation method, device, vehicle and medium of the present application.

[0061] First, the terms involved in this application are explained:

[0062] ADAS map (Advanced Driver Assistance System Map), a high-precision map specifically designed to support advanced driver assistance systems and autonomous driving functions. Unlike traditional navigation maps, ADAS maps provide more detailed and precise information to meet the needs of autonomous driving and driver assistance systems. The production of ADAS maps usually relies on data collection from lidar, cameras, GPS and other sensors, combined with high-precision geographic information system (GIS) technology for processing and updating. Since autonomous driving and advanced driver assistance systems have high requirements for the real-time and accuracy of maps, ADAS maps need to be updated frequently to reflect changes in road and traffic conditions. ADAS maps provide centimeter-level accuracy to ensure that vehicles can be accurately positioned on the road, including detailed information such as the number of lanes, lane width, lane type (such as main lanes, ramps, turning lanes, etc.), lane markings and lane boundaries, covering the road's curvature, slope, inclination and other geometric features to help vehicles dynamically adjust under different road conditions.

[0063] Vehicle offset, usually refers to the lateral offset of the centerline of the vehicle relative to the centerline of the lane. Vehicle offset can be positive or negative, depending on the direction in which the vehicle deviates from the centerline of the lane. Generally, a positive value indicates that the vehicle is deviating to the right side of the lane, and a negative value indicates that it is deviating to the left side. This offset can be detected by on-board cameras, lidar, or other sensors, and used in the vehicle's path planning and control algorithms to adjust the vehicle's direction and position.

[0064] Road offset usually refers to the deviation of the road itself, such as changes in road curvature, slope changes, or deviations in road markings. This offset can affect vehicle navigation and control because the physical characteristics of the road affect the vehicle's driving path. Road offset information is usually provided by high-precision maps, sensor data, or road infrastructure, and is used to adjust the vehicle's driving strategy to adapt to the actual conditions of the road.

[0065] Among related technologies, heavy trucks usually use Advanced Driver Assistance Systems (ADAS) to ensure vehicle safety and driver convenience. ADAS systems can use sensors, cameras, radars and other technologies to perceive the environment around the vehicle and provide real-time information or automated functions to assist the driver.

[0066] However, the existing ADAS system cannot provide a visual real-time road model. Currently, the only system that can provide a visual real-time road model is the navigation system, but this road model can only provide relatively rough road information such as "go straight ahead" and "turn left in 300 meters ahead", and the focus is on vehicle navigation. The driving routes of heavy trucks are generally relatively fixed, and the demand for navigation is relatively low, but the demand for safe driving and intelligent driving is higher. In addition, the navigation system is a road model generated based on the navigation map and the GPS system. Due to the low accuracy of the navigation map, heavy trucks require high-precision ADAS maps when driving.

[0067] Therefore, the visual real-time road model provided by the current navigation system has low accuracy and cannot meet the safe and intelligent driving requirements of heavy trucks.

[0068] Based on the above technical problems, the inventive concept of this application is: how to provide a road model generation solution that can provide a visual real-time road model and meet the safety and intelligent driving needs of heavy trucks.

[0069] The embodiments of the present application provide a road model generation method, device, vehicle and medium, which can realize the generation of a three-dimensional road model including the real-time position of the vehicle based on ADAS map data. Specifically, after obtaining the ADAS map data of the current marking point position of the vehicle, the ADAS map data can be processed, filtered and cached to obtain valid road data including road curvature, road slope, road offset and vehicle offset, so as to facilitate the subsequent generation of a three-dimensional road model. Afterwards, the interval road data corresponding to the real-time position of the vehicle can be determined according to the real-time offset of the vehicle, and the corresponding three-dimensional road model can be generated according to the real-time offset of the vehicle and the interval road data, so that the three-dimensional road model can display the real-time position status of the vehicle in real time, and provide a visual real-time road model during the driving process of commercial vehicles such as heavy trucks, so as to meet the safety and intelligent driving requirements of heavy trucks.

[0070] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0071] Figure 1 This is a system architecture diagram of an embodiment of the present application, such as Figure 1 As shown, the vehicle includes an on-board terminal T-BOX, a CAN network, and an on-board computing device. The on-board terminal T-BOX transmits the vehicle's real-time offset and the ADAS map data of the vehicle's current marking point position to the on-board computing device through the CAN network. The on-board computing device obtains the vehicle's real-time offset and the ADAS map data of the vehicle's current marking point position; processes the ADAS map data to obtain target road data, which includes road curvature, road slope, road offset, and vehicle offset; filters and caches the target road data to obtain valid road data; determines the corresponding interval road data in the valid road data according to the vehicle's real-time offset; generates a corresponding three-dimensional road model according to the vehicle's real-time offset and the interval road data, and outputs and displays the three-dimensional road model.

[0072] Figure 2 This is a flow chart of a method for generating a road model based on ADAS map data according to an embodiment of the present application. This embodiment uses an on-board computing device as an execution subject to illustrate the method for generating a road model based on ADAS map data. Figure 2 As shown, the road model generation method based on ADAS map data may include the following steps:

[0073] S201: Obtain the real-time offset of the vehicle and the ADAS map data of the current marked point position of the vehicle.

[0074] In this embodiment, the on-board computing device can be a computing device in the vehicle that includes a display screen, such as a large central control screen of a heavy truck. The specific type of the on-board computing device can be flexibly set by those skilled in the art. As long as the on-board computing device contains a display screen and can support the generation of a road model based on ADAS map data, no restrictions are made here.

[0075] In this embodiment, the vehicle computing device can be connected to the vehicle terminal T-BOX through the CAN network, and the vehicle terminal T-BOX can be connected to various sensors of the vehicle to obtain data such as the real-time offset of the vehicle detected by the sensors. The vehicle terminal T-BOX can also be connected to the ADAS system to obtain the ADAS map data transmitted by the ADAS system.

[0076] In this embodiment, the real-time offset of the vehicle can be detected by an on-board camera, laser radar or other sensors on the vehicle. The sensor can send the real-time offset of the vehicle to the on-board terminal T-BOX, and the on-board terminal T-BOX will send the real-time offset of the vehicle to the on-board computing device through the CAN network.

[0077] In this embodiment, the ADAS map data may be map data of a distance ahead of the vehicle (usually 8 kilometers) acquired by the ADAS system on the vehicle using a high-precision ADAS map, including information such as road curvature, road slope, road offset, and vehicle offset. After acquiring the ADAS map data transmitted by the ADAS system, the vehicle-mounted terminal T-BOX may send the ADAS map data to the vehicle-mounted computing device through the CAN network.

[0078] In this embodiment, the on-board computing device can obtain the real-time vehicle offset and ADAS map data through the ADASIS V2 protocol, and obtain the corresponding CAN message based on this; the use of the ADASIS V2 protocol ensures the standardization and efficiency of data transmission, and provides data support for subsequent path calculation, environmental simulation and other functions.

[0079] In this embodiment, the real-time offset of the vehicle is sent to the on-board computing device in real time, while the ADAS map data is sent to the on-board computing device each time the vehicle reaches a marked point (offset point), that is, the ADAS map data is point-by-point data.

[0080] For example, after the vehicle is powered on, the on-board computing device acquires ADAS map data once at the starting point, acquires ADAS map data once when the vehicle travels to a position 20 m away from the starting point, acquires ADAS map data once when the vehicle travels to a position 40 m away from the starting point, and so on, thereby acquiring ADAS map data at the position of each marked point during the driving process.

[0081] S202: Process the ADAS map data to obtain target road data, where the road data includes road curvature, road slope, road offset, and vehicle offset.

[0082] In this embodiment, the ADAS map data has a large amount of data, while the computing power of the on-board computing device is limited. Therefore, the ADAS map data needs to be processed to obtain only the target road data required to generate the road model.

[0083] In this embodiment, the road curvature can be used to dynamically adjust the vehicle's steering process, and the road slope change can be used to affect the vehicle's vertical displacement (deltaY), thereby accurately simulating the three-dimensional coordinate changes during vehicle driving and achieving dynamic simulation of complex road networks.

[0084] In this embodiment, the real-time position of the vehicle can be accurately determined by using the road offset and vehicle offset of each mark point position and the real-time offset of the vehicle.

[0085] S203: Filter and cache the target road data to obtain valid road data.

[0086] In this embodiment, the amount of target road data at each marking point is very large, but the computing power of the on-board computing device is limited, so it is necessary to filter the target road data to retain real and valid data.

[0087] In this embodiment, after the data is filtered, the data can also be cached. Since the ADAS map data may stop transmitting due to the vehicle power off, and the amount of calculation required to generate a road model based on all the road data each time is large, the filtered data can be cached after the target road data is filtered. While retaining the historical data, the corresponding road data can be called from the cache when the road model is generated later. It is not necessary to use all the road data, which greatly reduces the amount of calculation of the on-board computing device.

[0088] S204: Determine the corresponding section road data in the valid road data according to the real-time offset of the vehicle.

[0089] In this embodiment, the effective road data can be all the data on the road during the vehicle's driving process (data 8 kilometers in front of the vehicle), and the road model does not need to display the entire road, but only needs to display the roads in a fixed area around the vehicle (usually 300m in front of the vehicle and 50m behind the vehicle). Therefore, the real-time offset of the vehicle can be used for matching to determine the real-time position of the vehicle on the road, thereby determining the road section where the position is located, that is, the section road data used for road model generation.

[0090] S205: Generate a corresponding three-dimensional road model according to the real-time vehicle offset and the section road data, and output and display the three-dimensional road model.

[0091] In this embodiment, after determining the real-time position of the vehicle based on the real-time offset of the vehicle and determining the road section in which the position is located based on the section road data, a corresponding three-dimensional road model can be generated based on the real-time offset of the vehicle and the section road data to generate a real-time three-dimensional road model, and the on-board computing device can output and display the three-dimensional road model in real time through a display screen.

[0092] In this embodiment, the vehicle-mounted computing device may include a digital twin system, which may use input road data, relevant algorithms, and the unity3D real-time three-dimensional road model and the position of the vehicle in the model to simulate the real operation scene. The digital twin system may use the digital twin technology to generate a road model in real time, and locate the vehicle in the model according to the actual position of the vehicle, thereby forming a one-to-one mapping relationship between the actual operation scene of the vehicle and the digital road and digital vehicle in the vehicle-mounted computing device.

[0093] In this embodiment, the vehicle-mounted computing device can obtain the real-time offset of the vehicle and the ADAS map data of the current mark point position of the vehicle through the vehicle-mounted terminal T-BOX, and process, filter and cache the ADAS map data to obtain valid road data including road curvature, road slope, road offset and vehicle offset. Afterwards, the corresponding interval road data in the valid road data can be determined according to the real-time offset of the vehicle to determine the exact position of the vehicle on the road, and finally the corresponding three-dimensional road model can be generated according to the real-time offset of the vehicle and the interval road data. Through such a setting, not only can the three-dimensional road model be constructed in real time using the ADAS map data including information such as road curvature and road slope, but also the real-time positioning of the vehicle in the three-dimensional road model can be realized using the real-time offset of the vehicle, so that the driver can see the visualized real-time road model and the real-time position status of the vehicle through the display screen of the vehicle-mounted computing device, meeting the safe driving and intelligent driving requirements of heavy trucks.

[0094] In a possible implementation, the above step S202 processes the ADAS map data to obtain the target road data, which may include:

[0095] S11: Acquire initial road data in the ADAS map data, where the initial road data includes road curvature, road slope, road offset, and vehicle offset in an ADAS protocol format.

[0096] S12: Convert the format of the initial road data to obtain road data in JSON format.

[0097] S13: Convert the road data in JSON format into a standard format to obtain target road data.

[0098] In this implementation, the vehicle computing device can use the Android to Unity road data interface to convert the initial road data in the CAN message obtained by the ADAS V2 protocol into JSON format data, and then use the pathpoint script to convert the obtained JSON data into a standard format to obtain the target road data that can be used by the Unity platform. Of course, other scripts can also be used to convert JSON data into target road data that can be used by the Unity platform, and there is no limitation here.

[0099] In this embodiment, the on-board computing device receives the ADAS map data obtained by the CAN message through the ADASIS V2 protocol. The ADAS map data cannot be directly used by the on-board computing device, and the ADAS map data includes various road and traffic information. Therefore, it is first necessary to obtain the initial road data used to build the road model in the ADAS map data to reduce the amount of calculation of the on-board computing device. After that, the initial road data is converted into road data in JSON format so that the on-board computing device can use it. Finally, the road data in JSON format is converted into target road data in a standard format so that the target road data can be used by the digital twin system (unity) for road model generation in the on-board computing device.

[0100] In a possible implementation, the above step S203 filters and caches the target road data to obtain valid road data, which may include:

[0101] S21: Perform data filtering processing on the target road data to remove invalid data and erroneous data in the target road data to obtain first road data at the current marking point position.

[0102] S22: Determine the historical vehicle offset of the last marked point position cached in the storage module.

[0103] S23: Determine whether the first vehicle offset in the first road data is smaller than the historical vehicle offset.

[0104] S24: If it is less than, clear the historical cache data in the storage module, cache the first road data to the storage module, and determine the valid road data according to the cached data in the storage module.

[0105] S25: If it is not less than, the first road data of the current marking point position is cached to the storage module in chronological order, and the valid road data is determined according to the cached data in the storage module.

[0106] In this embodiment, the attribute isOk can be used to check whether the data is valid, filter out invalid data (invalid values ​​or error values) in the data to obtain valid data, and cache the valid data in a specific storage module (such as a dictionary Cache, etc.), thereby updating the road data in the cache.

[0107] In this embodiment, after filtering to obtain valid first road data, it is also necessary to determine whether the road attribute of the current mark point position has changed, that is, whether the current mark point position and the historical mark point position are on the same road (whether the vehicle enters a fork in the road, etc.). As the vehicle's offset increases as the vehicle travels, if the vehicle offset at the current mark point position becomes smaller than the historical vehicle offset at the previous mark point position, and the vehicle heading changes, it can be considered that the road attribute has changed, and it is necessary to reset the offset and position in the data, clear the old cached road data, and load the new section of road data.

[0108] It should be noted that the decrease in the vehicle offset at the current marker position may be caused by a change in road properties (entering a new fork in the road) or by exceeding the maximum offset range of the ADAS map data (8 kilometers ahead of the vehicle). Therefore, after determining that the first vehicle offset is less than the historical vehicle offset, it is also necessary to make a judgment based on whether new ADAS map data is received or whether the vehicle heading has changed. If the on-board computing device receives new ADAS map data (ADAS map data exceeding the maximum offset range) or the vehicle heading changes, the road properties have changed and the cache needs to be cleared. If the on-board computing device does not receive new ADAS map data (ADAS map data exceeding the maximum offset range) and the vehicle heading has changed, the road properties have not changed and the cache does not need to be cleared.

[0109] In this embodiment, as the current marking point position is continuously updated during the driving of the vehicle, new road data is continuously generated and processed, thereby updating the data in the cache so that the road data in the cache can be subsequently called to dynamically generate a road model.

[0110] In this embodiment, roads are dynamically cleared and switched by receiving road data, caching and filtering such data, and updating roads. This process involves close interaction with the EasyRoad3D plug-in and complex processing of road data to achieve dynamic road generation and car navigation.

[0111] In this implementation, the road model does not reflect the location information of the entire road section, but rather intercepts the road distance in equal amounts and only displays the roads in a fixed area around the vehicle (usually 300m in front of the vehicle and 50m behind it). When the vehicle's driving distance exceeds the maximum offset range of the ADAS map data (8 kilometers ahead of the vehicle) or enters a new fork in the road, the road data will be reset synchronously in real time and the calculation will be restarted. The advantage of this caching mechanism is that the offset range recorded can theoretically be infinite, and it greatly reduces the computing power required for the system to process data, thereby improving computing performance.

[0112] In this embodiment, the target road data at each marking point is very large, and the computing power of the on-board computing device is limited. Therefore, it is necessary to filter the target road data, remove invalid data and erroneous data in the target road data, and obtain the first road data at the current marking point. After data filtering, the data can also be cached. Since the ADAS map data may stop transmitting due to the vehicle power off, and the amount of calculation to generate a road model based on all road data each time is large and unnecessary, the filtered data can be cached after the target road data is filtered. While retaining the historical data, the corresponding road data can be called from the cache when the road model is generated later. It is not necessary to use all the road data, which greatly reduces the amount of calculation of the on-board computing device. Furthermore, since the previous road data is unavailable after each road change of the vehicle, in order to save storage space and reduce the amount of calculation, the original cache can be cleared when the current vehicle offset is less than the historical vehicle offset, that is, after determining that the vehicle changes roads each time.

[0113] In a possible implementation manner, before performing data filtering processing on the target road data in the above step S21, the following steps may also be included:

[0114] S31: Determine a target distance between the current marking point position and the previous marking point position cached in the storage module.

[0115] S32: Determine whether the target distance is less than a distance threshold.

[0116] S33: If the distance is less than the distance threshold, the target road data is cleared, and valid road data is determined according to the data cached in the storage module.

[0117] S34: If the distance is not less than the distance threshold, a step of filtering the target road data is performed.

[0118] In this implementation, the specific distance threshold can be flexibly set by those skilled in the art. For example, the distance threshold can be 10 m, 8 m, or other values, and no limitation is made here.

[0119] For example, if the current marker point position is 50m away from the starting point, and the previous marker point position is 45m away from the starting point, and the target distance between the two is 5m, which is less than the distance threshold of 10m, then the road data of the current marker point position can be cleared and the road data in the current cache can be directly called to generate the road model.

[0120] In this embodiment, when the distance between two marking point positions is small during vehicle execution, the road attributes, road data, etc. do not change much. In order to further save the computing power of the on-board computing equipment and improve computing efficiency, the marking point positions can be filtered. When the target distance between the new marking point position and the previous marking point position is less than the distance threshold, the road data corresponding to the new marking point position is not calculated.

[0121] In a possible implementation, the above step S204 determines the corresponding section road data in the valid road data according to the real-time vehicle offset, which may include:

[0122] S41: Determine the vehicle offset interval in which the real-time vehicle offset is located in the valid road data.

[0123] S42: Determine a road offset interval in the valid road data that matches the vehicle offset interval.

[0124] S43: Determine the corresponding interval road data in the valid road data according to the road offset interval.

[0125] In this implementation, the CalculatePath method in PathPoint can be used to calculate the path point, and the accurate position of the vehicle on the road can be calculated in combination with the cached road data, and the position and direction of the vehicle can be updated. Based on the above, the vehicle position is set according to the real-time offset of the vehicle through the SetCarPosition method, and the road segment where the vehicle's current position is located can be determined by matching the corresponding road starting point offset startOffset and end point offset endOffset (road offset interval).

[0126] In this implementation, the road offset interval that matches the vehicle offset interval is generally determined in two situations. First, the vehicle road condition data list unityRoadDatas is checked in the SetCarPosition method to see if it is empty. If it is empty, it means that the vehicle has entered a new fork in the road or has completed a round of 8km and re-recorded. At this time, the method provided by EasyRoads3Dv3 will be used to set the default position of the vehicle. If the list is not empty, the road offset that matches the vehicle offset will be found.

[0127] For example, the real-time vehicle offset is 55, and the vehicle offsets in the valid road data are 20, 40, 60, ..., respectively. The vehicle offset interval in which the real-time vehicle offset is located is [40, 60], and the road offset interval in the valid road data that matches the vehicle offset interval [40, 60] is [5, 355]. The road data corresponding to the road offset interval [5, 355] is the interval road data.

[0128] In this embodiment, the effective road data is the road data within the maximum offset range of the ADAS map data, but the road model does not need to reflect the location information of the entire road section, but intercepts the road in a fixed area around the vehicle (usually 300m in front of the vehicle and 50m behind the vehicle). The vehicle offset in the effective road data corresponds to the position of each mark point. Therefore, it is necessary to first determine the vehicle offset interval where the vehicle real-time offset is located, determine the position of the vehicle on the road, and then simply and accurately determine the interval road data for which the road model needs to be generated based on the road offset interval that matches the vehicle offset interval.

[0129] In a possible implementation, the above step S205 generates a corresponding three-dimensional road model according to the real-time vehicle offset and the interval road data, which may include:

[0130] S51: Determine a vehicle offset difference between an end point offset and a start point offset of a vehicle offset interval.

[0131] S52: Generate a three-dimensional road model including the real-time position of the vehicle according to the road curvature, road slope, road offset interval, vehicle offset difference and road generation plug-in corresponding to the interval road data.

[0132] In this embodiment, the end point offset may be the maximum vehicle offset in the vehicle offset interval, the start point offset may be the minimum vehicle offset in the vehicle offset interval, and the vehicle offset difference between the end point offset and the start point offset is the actual offset of the road section.

[0133] In this embodiment, the GetPosition method can be used to calculate the exact position of the vehicle on the road based on the actual offset realOffset, that is, the difference in the vehicle offset between the end point offset and the starting point offset; in this way, real-time positioning of the vehicle on the road is achieved, and the road generation result can be dynamically adjusted according to the input. The position information of the vehicle and the road will be updated in real time according to the data in the code to ensure that the position status of the vehicle can be accurately located in different time periods.

[0134] In this embodiment, after determining the vehicle offset difference and the road curvature, road slope, and road offset interval corresponding to the interval road data, the EastRoads3Dv3 plug-in can be used to manage and generate the corresponding road model. The EastRoads3Dv3 plug-in can efficiently and accurately add new roads, manage existing roads, and set the global properties of the road network.

[0135] In this embodiment, as the current marker position is continuously updated as the vehicle travels, the ERRoad.SetMarkerPosition method can be used to update the marker position on the road based on the provided road data, and the generation of the road model can be dynamically adjusted based on the dynamic behavior of the vehicle to accurately reflect the real-time situation of the road. Through the flexibility and simplicity of the EasyRoads3Dv3 plug-in, we can efficiently create and modify complex road networks in the Unity environment.

[0136] In this embodiment, the actual vehicle offset of the corresponding road section can be determined according to the vehicle offset difference between the end offset and the start offset, so as to calculate the accurate position of the vehicle on the road and realize the real-time positioning of the vehicle on the road. According to the road curvature, road slope, road offset interval, vehicle offset difference and road generation plug-in corresponding to the interval road data, a real-time three-dimensional road model can be generated, and the real-time position status of the vehicle can be displayed in real time in the model, meeting the safe driving and intelligent driving requirements of heavy trucks.

[0137] In a possible implementation, the above step S52 generates a three-dimensional road model including the real-time position of the vehicle according to the road curvature, road slope, road offset interval, vehicle offset difference and road generation plug-in corresponding to the interval road data, which may include:

[0138] S61: Generate an initial road model including the real-time position of the vehicle according to the road curvature, road slope, road offset interval, vehicle offset difference and road generation plug-in corresponding to the interval road data.

[0139] S62: Generate a corresponding road boundary line according to preset road material parameters of the vehicle.

[0140] S63: Generate a three-dimensional road model including the real-time position of the vehicle based on the initial road model and the road boundary line.

[0141] In this embodiment, since the driving route of a heavy truck is generally relatively fixed, the corresponding road material parameters can be set in advance according to the driving route of the vehicle and saved in the on-board computing device. When the road model of the vehicle needs to be generated, it can be directly called.

[0142] In this implementation, the SideObject class in the Unity platform is used to manage objects on both sides of the road. Through the GetSideObjectByName method, the road boundary lines can be obtained according to the provided name parameters (road material parameters) and used in road design to enhance the authenticity and functionality of the road model.

[0143] In this embodiment, the initial road model generated according to the road curvature, road slope, road offset interval, vehicle offset difference and road generation plug-in corresponding to the interval road data is a jagged model. In order to be more suitable for the real road, the corresponding road boundary line can also be generated according to the preset road material parameters of the vehicle, and a three-dimensional road model including the real-time position of the vehicle is generated based on the initial road model and the road boundary line, thereby improving the authenticity of the three-dimensional road model.

[0144] The road model generation method based on ADAS map data of the present application is described below with a specific embodiment.

[0145] In a specific embodiment, a heavy truck transports goods along a predetermined route. During the driving process of the vehicle, the onboard computing device of the heavy truck generates a three-dimensional road model in real time based on ADAS map data. The specific road model generation process is as follows:

[0146] In the first step, after the vehicle is powered on and starts driving at the starting point, the on-board terminal T-BOX transmits the vehicle's real-time offset and the ADAS map data of the vehicle's current marker position to the on-board computing device through the CAN network.

[0147] In the second step, the vehicle computing device obtains the real-time offset of the vehicle and the ADAS map data of the vehicle's current marker position. The initial road data in the ADAS map data is obtained, and the format of the initial road data is converted to obtain the road data in JSON format. The PathPoint script is used to convert the road data in JSON format to a standard format to obtain the target road data.

[0148] In the third step, the on-board computing device determines the target distance between the current marking point position and the previous marking point position cached in the storage module, and determines that the target distance is greater than the distance threshold, then performs data filtering on the target road data, removes invalid data and erroneous data in the target road data, and obtains the first road data of the current marking point position.

[0149] In the fourth step, the on-board computing device determines the historical vehicle offset of the previous marking point position cached in the storage module, and determines that the first vehicle offset in the first road data is not less than the historical vehicle offset, then caches the first road data of the current marking point position to the storage module in chronological order, and determines the valid road data based on the data cached in the storage module.

[0150] In the fifth step, the on-board computing device determines the vehicle offset interval in the valid road data where the real-time offset of the vehicle is located, determines the road offset interval in the valid road data that matches the vehicle offset interval, and determines the corresponding interval road data in the valid road data based on the road offset interval.

[0151] In the sixth step, the on-board computing device determines the vehicle offset difference between the end offset and the starting offset of the vehicle offset interval, and generates an initial road model containing the real-time position of the vehicle based on the road curvature, road slope, road offset interval, vehicle offset difference and road generation plug-in corresponding to the interval road data.

[0152] In the seventh step, the on-board computing device generates corresponding road boundary lines according to the preset road material parameters of the vehicle, and generates a three-dimensional road model including the real-time position of the vehicle according to the initial road model and the road boundary lines.

[0153] In the eighth step, the on-board computing device outputs and displays the three-dimensional road model in real time through the display screen.

[0154] Figure 3 This is a schematic diagram of the structure of a vehicle-mounted computing device according to an embodiment of the present application. Figure 3 As shown, the vehicle-mounted computing device includes: an acquisition module 31, which is used to obtain the real-time offset of the vehicle and the ADAS map data of the current mark point position of the vehicle; a processing module 32, which is used to process the ADAS map data to obtain target road data, the road data including road curvature, road slope, road offset and vehicle offset; filter and cache the target road data to obtain valid road data; determine the corresponding interval road data in the valid road data according to the real-time offset of the vehicle; generate a corresponding three-dimensional road model according to the real-time offset of the vehicle and the interval road data, and output and display the three-dimensional road model.

[0155] The vehicle-mounted computing device provided in the embodiment of the present application can execute the technical solution shown in the above method embodiment, and its implementation principle and beneficial effects are similar, which will not be repeated here.

[0156] Figure 4 This is a schematic diagram of the structure of a vehicle-mounted computing device according to an embodiment of the present application. Figure 4 As shown, the vehicle-mounted computing device includes: a processor 401, and a memory 402 that is communicatively connected to the processor 401; the memory 402 stores computer-executable instructions; the processor 401 executes the computer-executable instructions stored in the memory 402 to implement the steps of the road model generation method based on ADAS map data in the above-mentioned method embodiments.

[0157] In the above-mentioned vehicle-mounted computing device, the memory 402 and the processor 401 are electrically connected directly or indirectly to realize data transmission or interaction. For example, these elements can be electrically connected to each other through one or more communication buses or signal lines, such as through a bus connection. The memory 402 stores computer-executable instructions for implementing the data access control method, including at least one software function module that can be stored in the memory 402 in the form of software or firmware. The processor 401 executes various functional applications and data processing by running the software programs and modules stored in the memory 402.

[0158] The memory 402 may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electric erasable programmable read-only memory (EEPROM), etc. The memory 402 is used to store programs, and the processor 401 executes the programs after receiving the execution instruction. Furthermore, the software programs and modules in the above-mentioned memory 402 may also include an operating system, which may include various software components and / or drivers for managing system tasks (such as memory management, storage device control, power management, etc.), and may communicate with various hardware or software components to provide an operating environment for other software components.

[0159] The processor 401 may be an integrated circuit chip having the ability to process signals. The processor 401 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc. The methods, steps, and logic diagrams disclosed in the embodiments of the present application may be implemented or executed. The general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0160] An embodiment of the present application also provides a vehicle, such as Figure 1 As shown, the vehicle includes: a vehicle terminal T-BOX, a CAN network, and Figure 4 The vehicle-mounted computing device shown, the vehicle-mounted terminal T-BOX is connected to the vehicle-mounted computing device via a CAN network.

[0161] The vehicle terminal T-BOX is used to send the vehicle's real-time offset and ADAS map data of the location of each vehicle mark point to the vehicle's onboard computing device through the CAN network.

[0162] The vehicle-mounted computing device is used to obtain the real-time offset of the vehicle and the ADAS map data of the current marking point position of the vehicle; process the ADAS map data to obtain the target road data, the road data includes road curvature, road slope, road offset and vehicle offset; filter and cache the target road data to obtain valid road data; determine the corresponding interval road data in the valid road data according to the real-time offset of the vehicle; generate the corresponding three-dimensional road model according to the real-time offset of the vehicle and the interval road data, and output and display the three-dimensional road model.

[0163] An embodiment of the present application further provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the steps of each method embodiment of the present application.

[0164] An embodiment of the present application further provides a computer program product, including a computer program, which implements the steps of each method embodiment of the present application when executed by a processor.

[0165] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0166] It should be further noted that, although the various steps in the flowchart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0167] It should be understood that the above-mentioned device embodiments are only illustrative, and the device of the present application can also be implemented in other ways. For example, the division of units / modules in the above-mentioned embodiments is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units, modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed.

[0168] In addition, unless otherwise specified, each functional unit / module in each embodiment of the present application may be integrated into one unit / module, each unit / module may exist physically separately, or two or more units / modules may be integrated together. The above-mentioned integrated unit / module may be implemented in the form of hardware or in the form of a software program module.

[0169] In the above embodiments, the description of each embodiment has its own emphasis. For the part not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0170] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the appended claims.

[0171] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A road model generation method based on ADAS map data, characterized in that: include: Get the real-time vehicle offset and ADAS map data of the vehicle's current marker position; Processing the ADAS map data to obtain target road data, wherein the road data includes road curvature, road slope, road offset and vehicle offset; Filtering and caching the target road data to obtain valid road data; Determine the corresponding section road data in the valid road data according to the real-time vehicle offset; A corresponding three-dimensional road model is generated according to the real-time vehicle offset and the section road data, and the three-dimensional road model is output and displayed.

2. The method for generating a road model based on ADAS map data according to claim 1, characterized in that: The step of processing the ADAS map data to obtain target road data includes: Acquire initial road data in the ADAS map data, wherein the initial road data includes road curvature, road slope, road offset, and vehicle offset in an ADAS protocol format; Convert the initial road data into a JSON format. The road data in the JSON format is converted into a standard format to obtain target road data.

3. The method for generating a road model based on ADAS map data according to claim 2, characterized in that: The step of filtering and caching the target road data to obtain valid road data includes: Performing data filtering processing on the target road data to remove invalid data and erroneous data in the target road data to obtain first road data at the current marking point position; Determine the historical vehicle offset of the last marked point location cached in the storage module; determining whether a first vehicle offset in the first road data is less than the historical vehicle offset; If it is less than, clearing the historical cache data in the storage module, and caching the first road data to the storage module, and determining the valid road data according to the cached data in the storage module; If it is not less than, the first road data of the current marking point position is cached to the storage module in chronological order, and the valid road data is determined according to the cached data in the storage module.

4. The method for generating a road model based on ADAS map data according to claim 3, characterized in that: Before performing data filtering processing on the target road data, the method further includes: Determine the target distance between the current mark point position and the previous mark point position cached in the storage module; Determine whether the target distance is less than a distance threshold; If the distance is less than the distance threshold, clearing the target road data and determining valid road data based on the data cached in the storage module; If it is not less than the distance threshold, the step of performing data filtering processing on the target road data is executed.

5. The method for generating a road model based on ADAS map data according to any one of claims 1 to 4, characterized in that: The determining, according to the real-time vehicle offset, the corresponding section road data in the valid road data comprises: Determine a vehicle offset interval in which the real-time vehicle offset is located in the valid road data; Determining a road offset interval in the valid road data that matches the vehicle offset interval; According to the road offset interval, corresponding interval road data in the valid road data is determined.

6. The method for generating a road model based on ADAS map data according to claim 5, characterized in that: The generating a corresponding three-dimensional road model according to the real-time vehicle offset and the section road data includes: Determine a vehicle offset difference between an end offset and a start offset of the vehicle offset interval; A three-dimensional road model including the real-time position of the vehicle is generated according to the road curvature, road slope, road offset interval corresponding to the interval road data, the vehicle offset difference and the road generation plug-in.

7. The method for generating a road model based on ADAS map data according to claim 6, characterized in that: The method generates a three-dimensional road model including the real-time position of the vehicle according to the road curvature, road slope, road offset interval corresponding to the interval road data, the vehicle offset difference and the road generation plug-in, including: Generate an initial road model including the real-time position of the vehicle according to the road curvature, road slope, road offset interval corresponding to the interval road data, the vehicle offset difference and the road generation plug-in; Generate a corresponding road boundary line according to the preset road material parameters of the vehicle; A three-dimensional road model including the real-time position of the vehicle is generated according to the initial road model and the road boundary line.

8. A vehicle-mounted computing device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory is used to store computer-executable instructions; The processor is used to execute the computer-executable instructions stored in the memory, so that the processor executes the road model generation method based on ADAS map data according to any one of claims 1 to 7.

9. A vehicle, characterized in that: include: An in-vehicle terminal T-BOX, a CAN network, and the in-vehicle computing device according to claim 8, wherein the in-vehicle terminal T-BOX is connected to the in-vehicle computing device via the CAN network; The vehicle-mounted terminal T-BOX is used to send the vehicle real-time offset and ADAS map data of the position of each marked point of the vehicle to the vehicle-mounted computing device through the CAN network; The vehicle-mounted computing device is used to obtain the real-time offset of the vehicle and the ADAS map data of the current marked point position of the vehicle; The ADAS map data is processed to obtain target road data, wherein the road data includes road curvature, road slope, road offset and vehicle offset; the target road data is filtered and cached to obtain valid road data; corresponding interval road data in the valid road data is determined according to the real-time vehicle offset; a corresponding three-dimensional road model is generated according to the real-time vehicle offset and the interval road data, and the three-dimensional road model is output and displayed.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the road model generation method based on ADAS map data according to any one of claims 1 to 7.

Images