Control method, device and equipment of intelligent driving vehicle, and storage medium

Abstract

The application discloses a control method and device of an intelligent driving vehicle, equipment and a storage medium, relates to the technical field of intelligent driving, and can improve the driving safety of the intelligent driving vehicle. The specific scheme comprises the following steps: acquiring images collected in the driving process of the vehicle and radar detection results, and determining whether the vehicle is currently in a target scene according to the images and / or the radar detection results; if the vehicle is currently in the target scene, acquiring a first positioning result of the vehicle, the first positioning result being a positioning result based on a satellite positioning system, the first positioning result comprising first position data of the vehicle and a confidence level of the first position data, and the target scene being used for indicating a scene in which the positioning error of the satellite positioning system is greater than a preset error threshold; if the confidence level of the first position data is less than a first preset threshold, acquiring a region range of the target scene, and if the region range is greater than a preset region range, controlling the vehicle to switch from an intelligent driving mode to a following mode.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and in particular to a control method, device, equipment and storage medium for an intelligent driving vehicle. Background Technology

[0002] Intelligent driving refers to the ability of a car to assist the driver in controlling the vehicle, or even completely replace the driver, by being equipped with advanced sensors, controllers, actuators, communication modules, and other devices. Currently, intelligent driving levels can be divided into six levels, from L0 to L5. L0 represents driving without any driver assistance, while L1-L5 are classified according to the maturity of intelligent driving technology and the level of driver participation.

[0003] Currently, the realization of autonomous driving requires high-precision positioning data, and the higher the level of autonomous driving, the higher the accuracy requirement for positioning data. Current autonomous driving positioning data typically uses high-precision positioning modules. However, due to the complex scenarios that often occur during vehicle driving, these complex scenarios can affect the accuracy of the positioning data. Low-precision positioning data can pose significant safety hazards to advanced autonomous vehicles. Summary of the Invention

[0004] This application provides a control method, device, vehicle, and storage medium for intelligent driving vehicles, which can improve the driving safety of intelligent driving vehicles.

[0005] To achieve the above objectives, this application adopts the following technical solution:

[0006] A first aspect of this application provides a control method for an intelligent driving vehicle, the method comprising:

[0007] Acquire images and radar detection results collected during vehicle operation, and determine whether the current scene of the vehicle is the target scene based on the images and / or radar detection results;

[0008] If the current scene of the vehicle is the target scene, the first positioning result of the vehicle is obtained. The first positioning result is the positioning result based on the satellite positioning system. The first positioning result includes the current first position data of the vehicle and the confidence level of the first position data. The target scene is used to indicate the scene where the positioning error of the satellite positioning system is greater than the preset error threshold.

[0009] If the confidence level of the first location data is less than the first preset threshold, the area range of the target scene is obtained. If the area range is greater than the preset area range, the vehicle is controlled to switch from intelligent driving mode to follow mode.

[0010] In one embodiment, the radar detection results include the distance to the target object, the azimuth angle of the target object, and the point cloud data currently detected by the radar.

[0011] Determining whether the vehicle's current environment is the target environment based on image and / or radar detection results includes:

[0012] If the target object is determined to include multiple buildings based on the image, the aspect ratio of each building and the coverage of multiple buildings are determined based on the distance of the buildings, the azimuth angle of the buildings, and the point cloud data currently detected by the radar. The aspect ratio is used to indicate the ratio of the height to the width of the building, and the coverage is used to indicate the coverage range of the target object in the preset range around the vehicle.

[0013] If the height-to-width ratio of a building is greater than the second preset threshold and the building's coverage is greater than the third preset threshold, then the scene in which the vehicle is currently located is determined to be the target scene.

[0014] In one embodiment, determining the aspect ratio of each building and the coverage of multiple buildings based on the building distance, building azimuth angle, and point cloud data currently detected by radar includes:

[0015] The location of a building is determined by its distance from the building and its azimuth.

[0016] A 3D model of the vehicle's current surrounding environment is generated based on point cloud data;

[0017] The height, width, and coverage angle of the building relative to vehicles are determined from the 3D model based on the building's location.

[0018] The height-to-height ratio of a building is determined based on its height and width.

[0019] The coverage of a building is determined based on the range of its coverage angle.

[0020] In one embodiment, determining whether the scene in which the vehicle is currently located is the target scene based on image and / or radar detection results includes:

[0021] If the image determines that the preset range around the vehicle includes multiple other vehicles, and the target vehicle is among those other vehicles, then the distance to the target vehicle and the coverage area of ​​the target vehicle are obtained based on the radar detection results. The target vehicle is used to indicate vehicles whose volume is greater than a preset volume threshold.

[0022] Based on the distance to the target vehicle and the coverage area of ​​the target vehicle, the coverage of the target vehicle is determined. If the coverage is greater than the fourth preset threshold, the scene in which the vehicle is currently located is determined to be the target scene.

[0023] In one embodiment, determining whether the scene in which the vehicle is currently located is the target scene based on image and / or radar detection results includes:

[0024] If the vehicle is determined to be located under an overpass, in a tunnel, or in an area with obstructions above it based on images and / or detection results, then the scene in which the vehicle is currently located is determined to be the target scene.

[0025] In one embodiment, the method further includes:

[0026] If it is determined that the vehicle is currently driving in abnormal weather conditions, the vehicle will be controlled to exit intelligent driving mode. Abnormal weather conditions include solar storms, thunderstorms, and auroras.

[0027] In one embodiment, if the vehicle is currently in the target scene, after obtaining the vehicle's current first location result, the method further includes:

[0028] Obtain the second positioning result, which is a positioning result based on a high-precision map. The second positioning result includes the vehicle's current second location data and the confidence level of the second location data.

[0029] If the confidence level of the first location data is less than that of the second location data, then the second location result is taken as the current location result of the vehicle.

[0030] A second aspect of this application provides a control device for an intelligent driving vehicle, the device comprising:

[0031] The first acquisition module is used to acquire images and radar detection results collected during vehicle operation;

[0032] The first determining module is used to determine whether the scene in which the vehicle is currently located is the target scene based on the image and / or radar detection results;

[0033] The second acquisition module is used to acquire the vehicle's current first positioning result if the current scene of the vehicle is the target scene. The first positioning result is a positioning result based on the satellite positioning system. The first positioning result includes the vehicle's current first position data and the confidence level of the first position data. The target scene is used to indicate a scene where the positioning error of the satellite positioning system is greater than a preset error threshold.

[0034] The control module is used to obtain the area range of the target scene if the confidence level of the first location data is less than the first preset threshold, and to control the vehicle to switch from intelligent driving mode to follow mode if the area range is greater than the preset area range.

[0035] A third aspect of this application provides an electronic device, including a memory and a processor. The memory stores a computer program, and when the computer program is executed by the processor, it implements the intelligent driving vehicle control method of the first aspect of this application.

[0036] A fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the intelligent driving vehicle control method of the first aspect of this application.

[0037] The beneficial effects of the technical solutions provided in this application include at least the following:

[0038] The intelligent driving vehicle control method provided in this application acquires images and radar detection results collected during vehicle operation, and determines whether the current scene of the vehicle is a target scene based on the images and / or radar detection results. If the current scene is a target scene, the method acquires the vehicle's current first positioning result, which is a positioning result based on a satellite positioning system. The first positioning result includes the vehicle's current first position data and the confidence level of the first position data. The target scene indicates a scene where the positioning error of the satellite positioning system is greater than a preset error threshold. If the confidence level of the first position data is less than the first preset threshold, the method acquires the area range of the target scene. If the area range is greater than the preset area range, the method controls the vehicle to switch from intelligent driving mode to following mode. When the intelligent driving vehicle is determined to be in a scene with a large positioning error, the method controls the switching of the vehicle's intelligent driving mode based on the confidence level of the vehicle's current positioning result and the area range of the target scene. This avoids significant safety hazards caused by positioning errors, thereby improving the safety of autonomous driving vehicles. Attached Figure Description

[0039] Figure 1 This is a schematic diagram of the internal structure of a vehicle-mounted terminal provided in an embodiment of this application;

[0040] Figure 2 A flowchart illustrating a control method for an intelligent driving vehicle provided in this application embodiment;

[0041] Figure 3 A schematic diagram of an urban canyon scene provided for an embodiment of this application;

[0042] Figure 4 A schematic diagram of building coverage in an urban canyon scene provided for an embodiment of this application;

[0043] Figure 5 This is a schematic diagram of a vehicle surround scenario provided in an embodiment of this application;

[0044] Figure 6 This is a structural diagram of a control device for an intelligent driving vehicle provided in an embodiment of this application. Detailed Implementation

[0045] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0046] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of embodiments of this disclosure, unless otherwise stated, "a plurality of" means two or more.

[0047] In addition, the use of “based on” or “according to” implies openness and inclusivity, because processes, steps, calculations or other actions “based on” or “according to” one or more conditions or values ​​can in practice be based on additional conditions or values ​​beyond those conditions.

[0048] Intelligent driving refers to the ability of a car to assist the driver in controlling the vehicle, or even completely replace the driver, by being equipped with advanced sensors, controllers, actuators, communication modules, and other devices. Currently, intelligent driving levels can be divided into six levels, from L0 to L5. L0 represents driving without any driver assistance, while L1-L5 are classified according to the maturity of intelligent driving technology and the level of driver participation.

[0049] Currently, the realization of autonomous driving requires high-precision positioning data, and the higher the level of autonomous driving, the higher the accuracy requirement for positioning data. Current autonomous driving positioning data typically uses high-precision positioning modules. However, due to the complex scenarios that often occur during vehicle driving, these complex scenarios can affect the accuracy of the positioning data. Low-precision positioning data can pose significant safety hazards to advanced autonomous vehicles.

[0050] To address the aforementioned issues, this application provides a control method for intelligent driving vehicles. This method acquires images and radar detection results collected during vehicle operation and determines whether the current scene the vehicle is in is a target scene based on the images and / or radar detection results. If the current scene is a target scene, a first positioning result is acquired. This first positioning result is based on a satellite positioning system and includes the vehicle's current first location data and a confidence level for the first location data. The target scene indicates a scene where the positioning error of the satellite positioning system exceeds a preset error threshold. If the confidence level of the first location data is less than the first preset threshold, the area range of the target scene is acquired. If the area range is larger than the preset area range, the vehicle is controlled to switch from intelligent driving mode to follow mode. The intelligent driving vehicle control method provided in this application, when determining that the intelligent driving vehicle is in a scene with a large positioning error, controls the switching of the vehicle's intelligent driving mode based on the confidence level of the vehicle's current positioning result and the area range of the target scene. This avoids significant safety hazards caused by positioning errors, thereby improving the safety of autonomous driving vehicles.

[0051] The execution subject of the intelligent driving vehicle control method provided in this application embodiment can be an electronic device, which can be a computer device, a terminal device, or a server. The terminal device can be an in-vehicle terminal, various personal computers, laptops, smartphones, tablets, and portable wearable devices, etc. This application does not make any specific limitations.

[0052] This application uses an electronic device as an example of an in-vehicle terminal. Figure 1 This is a schematic diagram of the internal structure of a vehicle-mounted terminal provided in an embodiment of this application. Figure 1 As shown, the vehicle-mounted terminal includes a processor and a memory connected via a system bus. The processor provides computing and control capabilities. The memory may include non-volatile storage media and internal memory. The non-volatile storage media stores an operating system and computer programs. These computer programs can be executed by the processor to implement the steps of the control method for an intelligent driving vehicle provided in the above embodiments. The internal memory provides a cached operating environment for the operating system and computer programs in the non-volatile storage media.

[0053] Those skilled in the art will understand that Figure 1 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0054] Based on the aforementioned execution entity, embodiments of this application provide a control method for an intelligent driving vehicle. For example... Figure 2 As shown, the method includes the following steps:

[0055] Step 201: Acquire images and radar detection results collected during vehicle operation, and determine whether the scene in which the vehicle is currently located is the target scene based on the images and / or radar detection results.

[0056] The target scenario is used to indicate a scenario where the positioning error of the satellite positioning system exceeds a preset error threshold. For example, the target scenario can be: a scenario where the vehicle is surrounded by buildings, a scenario where the vehicle is surrounded by large vehicles, a tunnel scenario, a scenario where the vehicle is under an overpass, a scenario where the vehicle is under the shade of trees, or a scenario where the vehicle is traveling in abnormal weather, such as solar storms, thunderstorms, and auroras.

[0057] Step 202: If the current scene of the vehicle is the target scene, then obtain the current first location result of the vehicle.

[0058] The first positioning result is a positioning result based on a satellite positioning system, which includes the vehicle's current first location data and the confidence level of the first location data.

[0059] It should be noted that the vehicle's intelligent driving system includes a positioning module. This module can obtain the vehicle's current initial positioning result and evaluate its accuracy, obtaining a confidence level. A higher confidence level indicates higher accuracy, while a lower confidence level indicates lower accuracy.

[0060] Step 203: If the confidence level of the first location data is less than the first preset threshold, then obtain the area range of the target scene; if the area range is greater than the preset area range, then control the vehicle to switch from intelligent driving mode to follow mode.

[0061] The first preset threshold can be 80%, or it can be set according to the positioning accuracy requirements of the intelligent driving vehicle. This application embodiment does not specifically limit this. The preset area range can be 2 kilometers. Similarly, the preset area range can also be set according to the positioning accuracy requirements of the intelligent driving vehicle. This application embodiment does not specifically limit this.

[0062] Understandably, if the confidence level of the first location data of the target scene is low and the area of ​​the target scene is large, it means that the vehicle's positioning error will become larger and larger. In this case, it is necessary to control the vehicle to switch from intelligent driving mode to vehicle following mode, or to control the vehicle to perform function degradation.

[0063] In this context, controlling the vehicle to downgrade its functions can be understood as: if the vehicle is currently in a higher level of intelligent driving mode, then controlling the vehicle to switch to a lower level of intelligent driving mode.

[0064] This application provides a control method for intelligent driving vehicles. By acquiring images and radar detection results collected during vehicle operation, and determining whether the current scene the vehicle is in is a target scene based on the images and / or radar detection results, if the current scene is a target scene, the method acquires the vehicle's current first positioning result. The first positioning result is a positioning result based on a satellite positioning system, including the vehicle's current first location data and the confidence level of the first location data. The target scene indicates a scene where the positioning error of the satellite positioning system is greater than a preset error threshold. If the confidence level of the first location data is less than the first preset threshold, the method acquires the area range of the target scene. If the area range is greater than the preset area range, the method controls the vehicle to switch from intelligent driving mode to following mode. The intelligent driving vehicle control method provided in this application, when determining that the intelligent driving vehicle is in a scene with a large positioning error, controls the switching of the vehicle's intelligent driving mode based on the confidence level of the vehicle's current positioning result and the area range of the target scene. This avoids significant safety hazards caused by positioning errors, thereby improving the safety of autonomous driving vehicles.

[0065] Optionally, the radar detection results in step 201 above include the distance to the target object, the azimuth angle of the target object, and the point cloud data currently detected by the radar.

[0066] The process of determining whether the scene in which the vehicle is currently located is the target scene based on the image and / or radar detection results in step 201 above can be as follows:

[0067] If the target object is determined to include multiple buildings based on the image, then the aspect ratio of each building and the coverage of multiple buildings are determined based on the distance to the buildings, the azimuth angle of the buildings, and the point cloud data currently detected by the radar.

[0068] If the height-to-width ratio of a building is greater than the second preset threshold and the building coverage is greater than the third preset threshold, then the scene in which the vehicle is currently located is determined to be the target scene, which can be called the urban canyon scene.

[0069] The images consist of images of the vehicle's surroundings captured by image acquisition equipment installed on the vehicle, while the radar detection results are those from the radar installed on the vehicle. Target objects refer to pedestrians, other vehicles, buildings, etc., surrounding the vehicle. The radar detection results include the target object's distance, azimuth angle, and the point cloud data currently detected by the radar. The target object's distance refers to the distance from the target object to the vehicle, and the target object's azimuth angle refers to the target object's azimuth angle relative to the vehicle.

[0070] The aspect ratio indicates the ratio of a building's height to its width, while the coverage indicates the coverage area of ​​a target object within a preset range around the vehicle.

[0071] Specifically, the process of determining whether a target object includes multiple buildings based on an image can be as follows:

[0072] The intelligent driving system of a vehicle includes a perception module, which has a pre-set target detection model. By inputting real-time acquired images into the target detection model, the target objects around the vehicle can be identified.

[0073] Optionally, the process of determining the aspect ratio of each building and the coverage of multiple buildings based on the distance to the buildings, the building azimuth angle, and the point cloud data currently detected by the radar can be as follows:

[0074] The location of a building is determined based on its distance and azimuth. Then, a 3D model of the vehicle's current surrounding environment is generated based on point cloud data. The height, width, and coverage angle range of the building relative to the vehicle are determined from the 3D model based on the building's location. The height ratio of the building is determined based on its height and width. Finally, the coverage of the building is determined based on the coverage angle range.

[0075] In actual implementation, Figure 3 This is a schematic diagram of an urban canyon scene provided in an embodiment of this application, such as... Figure 3 As shown, among the target objects around the vehicle are buildings, Figure 3 In the diagram, R1 represents the distance between the building and the vehicle, and A1 represents the azimuth angle of the building relative to the vehicle. Specifically, this azimuth angle is the angle between the building and the vehicle's direction of travel. The vehicle's position can be determined based on R1 and A1. A point cloud model of the surrounding environment can be generated from the point cloud data detected by radar. Then, based on the determined vehicle position, the corresponding model of the building is determined within the point cloud model. This allows us to obtain the building's height, width, and coverage angle range relative to the vehicle. Finally, the building's height ratio can be obtained by dividing its height by its width, and the building's coverage angle range (within 360°) can be used to calculate its coverage.

[0076] in, Figure 4 This is a schematic diagram of building coverage provided in an embodiment of this application, such as... Figure 4 As shown, the angle occupied by a building in a 360° radius around a vehicle can be determined based on the radar detection results. Then, the coverage of the building can be obtained by using the angle occupied by the building in a 360° radius.

[0077] Understandably, in urban canyon scenarios, where vehicles are surrounded by multiple buildings, satellite positioning may suffer from multipath effects or excessive obstruction. When a vehicle stops and starts, positioning may fail to converge, preventing some advanced autonomous driving functions from being activated. However, users may not understand the situation and misjudge whether there is a problem with the vehicle or the function. At this point, the vehicle will provide a scene prompt indicating that it has entered an urban canyon scenario, helping users understand the scenario and use the autonomous driving functions correctly.

[0078] Optionally, after determining that the current scene is an urban canyon scene based on the image and radar detection results, the coverage area of ​​the current urban canyon scene can be further obtained based on the current high-precision map. If the coverage area is greater than the preset range, it means that the vehicle is indeed in an urban canyon scene. This can avoid the situation where the urban canyon scene determined based on the image and radar detection results is incorrect.

[0079] Optionally, the process in step 201 above, which determines whether the scene the vehicle is currently in is the target scene based on the image and / or radar detection results, can also be:

[0080] If the image determines that the vehicle's surrounding preset range includes multiple other vehicles, and the target vehicle is among these other vehicles, then the distance to the target vehicle and its coverage area are obtained based on the radar detection results. The target vehicle is used to indicate vehicles whose volume is greater than a preset volume threshold. Then, based on the distance to the target vehicle and its coverage area, the target vehicle's coverage is determined. If the coverage is greater than a fourth preset threshold, then the scene in which the vehicle is currently located is determined to be the target scene.

[0081] The aforementioned target scenario can be referred to as a vehicle-surrounded scenario. Figure 5 This is a schematic diagram of a vehicle-surrounded scenario provided in an embodiment of this application. The target vehicle can be a large vehicle such as a truck, van, bus, or coach. The fourth preset threshold can be 40%, or it can be set according to the positioning accuracy requirements of the intelligent driving vehicle; this embodiment of the application does not specifically limit this.

[0082] In actual operation, if image recognition determines that multiple vehicles surround the vehicle, including larger vehicles, the distance between the vehicle and the larger vehicles, as well as the coverage area of ​​the larger vehicles, are obtained based on radar detection results. Based on the distance to and coverage area of ​​the target vehicle, the coverage of the target vehicle within a preset range around the vehicle can be determined. If the coverage is greater than 40%, the vehicle is determined to be in a vehicle-surrounded scenario.

[0083] Understandably, when an autonomous vehicle is surrounded by other vehicles, the positioning may be inaccurate due to obstruction from other vehicles. Simultaneously, the vehicle's visual perception and laser detection systems may also be obstructed, making it impossible to accurately determine its self-measured position. Therefore, if such a scenario is detected, the system can determine whether to switch the vehicle from autonomous driving mode to vehicle-based mode, or to degrade functionality, based on the confidence level of the positioning result and the area of ​​the scenario. Simultaneously, a prompt message can be generated to alert the driver of the positioning error in the current area, allowing the driver to take over the vehicle at any time.

[0084] Optionally, the process in step 201 above, which determines whether the scene the vehicle is currently in is the target scene based on the image and / or radar detection results, can also be:

[0085] If the vehicle is determined to be located under an overpass, in a tunnel, or in an area with obstructions above it based on images and / or detection results, then the scene in which the vehicle is currently located is determined to be the target scene.

[0086] It is understandable that satellite positioning errors can occur when a vehicle is under an overpass, in a tunnel, or in an area with obstructed overhead views. Therefore, if a vehicle is detected in such a scenario, the system can determine whether to switch the vehicle from intelligent driving mode to vehicle-based mode, or to downgrade its functions, based on the confidence level of the positioning result and the geographical extent of the scenario. Simultaneously, a prompt message can be generated to alert the driver of the positioning error in the current area, allowing the driver to take over the vehicle at any time.

[0087] Meanwhile, in tunnel scenarios, the inertial navigation calculations used in the positioning system accumulate, leading to inaccurate positioning when the tunnel is too long. Furthermore, for complex elevated roads with two or more levels, positioning errors at each level are prone to occur. Therefore, for such complex elevated roads, height detection, visual perception, and LiDAR can be used for target identification to determine the vehicle's location and level, reducing the risk of lane recognition errors.

[0088] Optionally, the method also includes: if it is determined that the vehicle is currently driving in abnormal weather conditions, then controlling the vehicle to exit the intelligent driving mode, where abnormal weather conditions include solar storms, thunderstorms, and auroras.

[0089] Similarly, when driving in abnormal weather conditions, such as solar storms, thunderstorms, and auroras, network and satellite data will be severely interfered with, and positioning accuracy will drop significantly. In such cases, it is necessary to control the vehicle to exit intelligent driving mode. Before exiting intelligent driving mode, a prompt message will be generated to remind the driver to take over the vehicle at any time.

[0090] Optionally, if the vehicle is currently in the target scene, after obtaining the vehicle's current first location result, the method further includes:

[0091] Obtain a second positioning result, which is a positioning result based on a high-precision map. The second positioning result includes the vehicle's current second location data and the confidence level of the second location data. If the confidence level of the first location data is less than the confidence level of the second location data, then the second positioning result is taken as the vehicle's current positioning result.

[0092] In practice, vehicle cameras can identify lane features, traffic lights, and signs to determine the approximate location of the vehicle. Lane lines confirm the vehicle's position, and landmark signs confirm its lane, ultimately determining the vehicle's location. The identified vehicle position is then matched with a high-precision map to obtain a second positioning result and its confidence level. The priority between the high-precision map positioning and the positioning system positioning is determined based on the confidence levels of the first and second positioning results. If the confidence level of the first location data is lower than that of the second location data, the second positioning result is adopted as the vehicle's current location. This allows the high-precision map positioning to compensate for positioning system errors, improving the accuracy of the positioning results.

[0093] like Figure 6 As shown in the figure, this application embodiment also provides a control device for an intelligent driving vehicle, the device comprising:

[0094] The first acquisition module 11 is used to acquire images and radar detection results collected during vehicle operation;

[0095] The first determining module 12 is used to determine whether the scene in which the vehicle is currently located is the target scene based on the image and / or radar detection results;

[0096] The second acquisition module 13 is used to acquire the vehicle's current first positioning result if the current scene of the vehicle is the target scene. The first positioning result is a positioning result based on the satellite positioning system. The first positioning result includes the vehicle's current first position data and the confidence level of the first position data. The target scene is used to indicate a scene where the positioning error of the satellite positioning system is greater than a preset error threshold.

[0097] The control module 14 is used to obtain the area range of the target scene if the confidence level of the first location data is less than the first preset threshold, and to control the vehicle to switch from intelligent driving mode to follow mode if the area range is greater than the preset area range.

[0098] In one embodiment, the radar detection result includes the distance to the target object, the azimuth angle of the target object, and the point cloud data currently detected by the radar; the first determining module 12 is specifically used for:

[0099] If the target object is determined to include multiple buildings based on the image, the aspect ratio of each building and the coverage of multiple buildings are determined based on the distance of the buildings, the azimuth angle of the buildings, and the point cloud data currently detected by the radar. The aspect ratio is used to indicate the ratio of the height to the width of the building, and the coverage is used to indicate the coverage range of the target object in the preset range around the vehicle.

[0100] If the height-to-width ratio of a building is greater than the second preset threshold and the building's coverage is greater than the third preset threshold, then the scene in which the vehicle is currently located is determined to be the target scene.

[0101] In one embodiment, the first determining module 12 is specifically used to: determine the location of the building based on the distance to the building and the azimuth of the building;

[0102] A 3D model of the vehicle's current surrounding environment is generated based on point cloud data;

[0103] The height, width, and coverage angle of the building relative to vehicles are determined from the 3D model based on the building's location.

[0104] The height-to-height ratio of a building is determined based on its height and width.

[0105] The coverage of a building is determined based on the range of its coverage angle.

[0106] In one embodiment, the first determining module 12 is specifically used to: if it is determined from the image that the preset range around the vehicle includes multiple other vehicles, and the target vehicle is among the other vehicles, then the distance to the target vehicle and the coverage area of ​​the target vehicle are obtained from the radar detection results, and the target vehicle is used to indicate vehicles whose volume is greater than a preset volume threshold.

[0107] Based on the distance to the target vehicle and the coverage area of ​​the target vehicle, the coverage of the target vehicle is determined. If the coverage is greater than the fourth preset threshold, the scene in which the vehicle is currently located is determined to be the target scene.

[0108] In one embodiment, the first determining module 12 is specifically used to: if it is determined from the image and / or from the detection results that the vehicle is located in an area under an overpass, in a tunnel, or in an area with obstructions above the vehicle, then determine the scene in which the vehicle is currently located as the target scene.

[0109] In one embodiment, the control module 14 is further configured to:

[0110] If it is determined that the vehicle is currently driving in abnormal weather conditions, the vehicle will be controlled to exit intelligent driving mode. Abnormal weather conditions include solar storms, thunderstorms, and auroras.

[0111] In one embodiment, the second acquisition module 13 is further configured to acquire a second positioning result, which is a positioning result based on a high-precision map. The second positioning result includes the vehicle's current second location data and the confidence level of the second location data. If the confidence level of the first location data is less than the confidence level of the second location data, the second positioning result is used as the vehicle's current positioning result.

[0112] The control device for the intelligent driving vehicle provided in this embodiment can execute the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0113] Specific limitations regarding the control devices for intelligent driving vehicles can be found in the limitations on the control methods for intelligent driving vehicles described above, and will not be repeated here. Each module in the aforementioned control device for intelligent driving vehicles can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in hardware or independently of the processor in the vehicle terminal, or stored in software in the memory of the vehicle terminal, so that the processor can call and execute the corresponding operations of each module.

[0114] In another embodiment of this application, a vehicle is also provided, including a memory and a processor. The memory stores a computer program, which, when executed by the processor, implements the steps of the control method for an intelligent driving vehicle as described in the embodiments of this application.

[0115] In another embodiment of this application, a computer-readable storage medium is also provided, on which a computer program is stored, wherein when the computer program is executed by a processor, the steps of the control method for an intelligent driving vehicle as described in the embodiments of this application are implemented.

[0116] In another embodiment of this application, a computer program product is also provided, which includes computer instructions that, when executed on the control device of an intelligent driving vehicle, cause the control device of the intelligent driving vehicle to perform each step of the control method of the intelligent driving vehicle in the method flow shown in the above method embodiment.

[0117] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software programs, implementation can be, in whole or in part, in the form of a computer program product. This computer program product includes one or more computer instructions. When these computer instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device containing one or more servers, data centers, etc., that can be integrated with the medium. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state disks, SSDs).

[0118] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are 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.

[0119] The above embodiments merely illustrate several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A control method for an intelligent driving vehicle, characterized in that, The method includes: Acquire images and radar detection results collected during vehicle operation, and determine whether the scene in which the vehicle is currently located is the target scene based on the images and / or the radar detection results; If the current scene of the vehicle is the target scene, then the current first positioning result of the vehicle is obtained. The first positioning result is a positioning result based on the satellite positioning system. The first positioning result includes the current first location data of the vehicle and the confidence level of the first location data. The target scene is used to indicate a scene where the positioning error of the satellite positioning system is greater than a preset error threshold. If the confidence level of the first location data is less than the first preset threshold, the area range of the target scene is obtained; if the area range is greater than the preset area range, the vehicle is controlled to switch from intelligent driving mode to follow mode. The radar detection results include the distance to the target object, the azimuth angle of the target object, and the point cloud data currently detected by the radar. Determining whether the scene in which the vehicle is currently located is the target scene based on the image and / or the radar detection results includes: If the target object is determined to include multiple buildings based on the image, then the aspect ratio of each building and the coverage of multiple buildings are determined based on the distance of the buildings, the azimuth angle of the buildings, and the point cloud data currently detected by the radar. The aspect ratio is used to indicate the ratio of the height to the width of the building, and the coverage is used to indicate the coverage range of the target object within a preset range around the vehicle. If the height-to-width ratio of the building is greater than a second preset threshold and the coverage of the building is greater than a third preset threshold, then the scene in which the vehicle is currently located is determined to be the target scene.

2. The method according to claim 1, characterized in that, The step of determining the aspect ratio of each building and the coverage of multiple buildings based on the distance to the buildings, the azimuth angle of the buildings, and the point cloud data currently detected by the radar includes: The location of the building is determined based on the distance to the building and the azimuth angle of the building; A 3D model of the vehicle's current surrounding environment is generated based on the point cloud data; The height, width, and coverage angle range of the building relative to the vehicle are determined from the three-dimensional model based on the building's location. The height ratio of the building is determined based on the building's height and the building's width; The coverage of the building is determined based on the coverage angle range.

3. The method according to claim 1, characterized in that, Determining whether the scene in which the vehicle is currently located is the target scene based on the image and / or the radar detection results includes: If the image determines that the preset range around the vehicle includes multiple other vehicles, and the target vehicle is among the other vehicles, then the distance to the target vehicle and the coverage area of ​​the target vehicle are obtained based on the radar detection results. The target vehicle is used to indicate vehicles whose volume is greater than a preset volume threshold. The coverage of the target vehicle is determined based on the distance to the target vehicle and the coverage area of ​​the target vehicle. If the coverage is greater than a fourth preset threshold, the scene in which the vehicle is currently located is determined to be the target scene.

4. The method according to claim 1, characterized in that, Determining whether the scene in which the vehicle is currently located is the target scene based on the image and / or the radar detection results includes: If, based on the image and / or the detection results, it is determined that the vehicle is located under an overpass, in a tunnel, or in an area with obstructions above the vehicle, then the scene in which the vehicle is currently located is determined to be the target scene.

5. The method according to claim 1, characterized in that, The method further includes: If it is determined that the vehicle is currently driving in abnormal weather conditions, the vehicle is controlled to exit the intelligent driving mode. The abnormal weather conditions include solar storms, thunderstorms, and auroras.

6. The method according to any one of claims 1-5, characterized in that, If the scene in which the vehicle is currently located is the target scene, then after obtaining the vehicle's current first location result, the method further includes: Obtain a second positioning result, which is a positioning result based on a high-precision map. The second positioning result includes the vehicle's current second location data and the confidence level of the second location data. If the confidence level of the first location data is less than the confidence level of the second location data, then the second location result is taken as the current location result of the vehicle.

7. A control device for an intelligent driving vehicle, characterized in that, The device includes: The first acquisition module is used to acquire images and radar detection results collected during vehicle operation; The first determining module is used to determine whether the scene in which the vehicle is currently located is the target scene based on the image and / or the radar detection result; The second acquisition module is used to acquire the vehicle's current first positioning result if the vehicle is currently in a target scene. The first positioning result is a positioning result based on a satellite positioning system. The first positioning result includes the vehicle's current first location data and the confidence level of the first location data. The target scene is used to indicate a scene where the positioning error of the satellite positioning system is greater than a preset error threshold. The control module is used to obtain the area range of the target scene if the confidence level of the first location data is less than a first preset threshold, and to control the vehicle to switch from intelligent driving mode to follow mode if the area range is greater than the preset area range. The radar detection results include the target object's distance, azimuth angle, and point cloud data currently detected by the radar; the first determining module is specifically used for: If the target object is determined to include multiple buildings based on the image, the aspect ratio of each building and the coverage of multiple buildings are determined based on the distance of the buildings, the azimuth angle of the buildings, and the point cloud data currently detected by the radar. The aspect ratio is used to indicate the ratio of the height to the width of the building, and the coverage is used to indicate the coverage range of the target object in the preset range around the vehicle. If the height-to-width ratio of a building is greater than the second preset threshold and the building's coverage is greater than the third preset threshold, then the scene in which the vehicle is currently located is determined to be the target scene.

8. An electronic device, characterized in that, It includes a memory and a processor, the memory storing a computer program that, when executed by the processor, implements the control method for the intelligent driving vehicle according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, It stores a computer program, which, when executed by a processor, implements the control method for the intelligent driving vehicle according to any one of claims 1-6.

Images