Vehicle positioning method and device, vehicle and storage medium

Abstract

The invention provides a vehicle positioning method and device, a vehicle and a storage medium, and relates to the technical field of automatic driving, and the method comprises the steps: obtaining environment information collected by each of a plurality of sensors on the vehicle; obtaining an actual driving track corresponding to each kind of environment information according to the various kinds of environment information; according to the preset map and various actual driving tracks, the positioning result of the vehicle is obtained, various sensors are arranged on the vehicle in a redundant mode, when the functions of part of the sensors are limited or damaged, other sensors can be continuously used for positioning, the positioning requirements in various scenes are met, and the reliability of vehicle positioning is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of autonomous driving technology, and in particular to a vehicle positioning method, device, vehicle and storage medium. Background Art

[0002] With the continuous development of my country's economy and the improvement of people's living standards, driving has become the preferred way of travel for many people. In order to alleviate the fatigue caused by long-term driving, autonomous driving technology has been widely used in vehicles in recent years. The current autonomous driving technology is mainly based on satellite positioning. However, the satellite positioning method is suitable for open scenes. For scenes with limited satellite signals, this positioning method fails and it is difficult to meet the positioning needs in this case. Summary of the invention

[0003] In order to overcome the problems existing in the related art, the present disclosure provides a vehicle positioning method, device, vehicle and storage medium.

[0004] According to a first aspect of an embodiment of the present disclosure, a vehicle positioning method is provided, which includes: obtaining environmental information collected by each of a plurality of sensors on the vehicle; obtaining an actual driving trajectory corresponding to each of the environmental information based on the plurality of environmental information; and obtaining a vehicle positioning result based on a plurality of actual driving trajectories of a preset map.

[0005] Optionally, the multiple sensors include: a camera, and obtaining environmental information collected by each of the multiple sensors on the vehicle includes: obtaining image information collected by the camera on the vehicle; obtaining an actual driving trajectory corresponding to each environmental information based on the multiple environmental information includes: generating a descriptor based on the image information; and obtaining an actual descriptor trajectory corresponding to the image information based on the descriptor.

[0006] Optionally, the multiple sensors include: a laser radar, and obtaining environmental information collected by each of the multiple sensors on the vehicle includes: obtaining radar data collected by the laser radar on the vehicle; and obtaining the actual driving trajectory corresponding to each environmental information based on the multiple environmental information includes: obtaining the actual point cloud vector trajectory corresponding to the radar data based on the radar data.

[0007] Optionally, the multiple sensors include: a wheel speed meter; obtaining environmental information collected by each of the multiple sensors on the vehicle includes: obtaining wheel speed information collected by the wheel speed meter on the wheel of the vehicle; obtaining the actual driving trajectory corresponding to each environmental information based on the multiple environmental information includes: obtaining the actual wheel trajectory corresponding to the wheel speed information based on the wheel speed information.

[0008] Optionally, the preset map includes multiple preset driving trajectories and positioning information corresponding to each preset driving trajectory, and there is a one-to-one correspondence between the multiple actual driving trajectories and the multiple preset driving trajectories. The method of obtaining the positioning result of the vehicle based on the preset map and the multiple actual driving trajectories includes: when each actual driving trajectory among the multiple actual driving trajectories is aligned with the corresponding preset driving trajectory, obtaining the positioning result of the vehicle based on the positioning information corresponding to each preset driving trajectory.

[0009] Optionally, obtaining the positioning result of the vehicle according to the positioning information corresponding to each preset driving trajectory includes: using the positioning information corresponding to each preset driving trajectory as an intermediate positioning result of each actual driving trajectory; and obtaining the positioning result of the vehicle according to the intermediate positioning result and positioning constraints.

[0010] Optionally, the preset map includes: a preset descriptor trajectory, a preset point cloud vector trajectory and a preset wheel trajectory, and the constraint conditions include at least one of the following: a constraint condition corresponding to the preset descriptor trajectory, a constraint condition corresponding to the preset point cloud vector trajectory, and a constraint condition corresponding to the preset wheel trajectory.

[0011] Optionally, before obtaining the positioning result of the vehicle according to the preset map and multiple actual driving trajectories, the method further includes: acquiring local positioning information collected by a local positioning sensor on the vehicle; and obtaining a preset map based on the local positioning information.

[0012] According to a second aspect of an embodiment of the present disclosure, a vehicle positioning device is provided, comprising: an environmental information acquisition module, used to acquire environmental information acquired by each of a plurality of sensors on the vehicle; a trajectory acquisition module, used to acquire, based on the plurality of environmental information, an actual driving trajectory corresponding to each of the environmental information; and a positioning module, used to acquire a vehicle positioning result based on a preset map and a plurality of actual driving trajectories.

[0013] According to a third aspect of an embodiment of the present disclosure, a vehicle is provided, comprising: a processor; and a memory for storing processor executable instructions; wherein the processor is configured to implement the steps of the method described in the first aspect when executed.

[0014] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of the method provided in the first aspect of the present disclosure are implemented.

[0015] The present disclosure provides a vehicle positioning method, device, vehicle and storage medium, which obtain environmental information collected by each of multiple sensors on the vehicle; then obtain the actual driving trajectory corresponding to each environmental information based on the multiple environmental information; obtain the vehicle positioning result based on a preset map and multiple actual driving trajectories, and redundant multiple sensors on the vehicle. When the functions of some sensors are limited or damaged, other sensors can continue to be used for positioning, thereby meeting the positioning needs in various scenarios and improving the reliability of vehicle positioning.

[0016] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0018] Figure 1 is a flow chart of a vehicle positioning method shown in an exemplary embodiment of the present disclosure;

[0019] Figure 2 is a flow chart of a vehicle positioning method shown in another exemplary embodiment of the present disclosure;

[0020] Figure 3 is a block diagram of a vehicle positioning device according to an exemplary embodiment;

[0021] Figure 4 The invention is a block diagram of a vehicle used for a vehicle positioning method according to an exemplary embodiment. DETAILED DESCRIPTION

[0022] 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 embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0023] With the continuous development of my country's economy and the improvement of people's living standards, driving has become the preferred way of travel for many people. In order to alleviate the fatigue caused by long-term driving, autonomous driving technology has been widely used in vehicles in recent years. The current autonomous driving technology is mainly based on satellite positioning. However, the satellite positioning method is suitable for open scenes. For scenes with limited satellite signals, this positioning method fails and it is difficult to meet the positioning needs in this case.

[0024] For example, Real Time Kinematic (RTK) is a technology that uses the carrier phase observation of the Global Positioning System (GPS) to perform real-time dynamic relative positioning. In existing autonomous driving technologies, RTK technology is used to provide an initial global position and load a map for positioning. Since the positioning effect of RTK is severely restricted by the environment, the stability and accuracy of this solution are not ideal in scenes with severe obstruction, such as urban canyons with tall buildings.

[0025] The existing solution also uses underground tunnels for positioning triggering and completing initial positioning. Since underground tunnel scenes are relatively simple and multiple underground tunnels in the city may be very close to each other, the mapping density of this solution is greatly restricted and the positioning accuracy is not ideal. Using this solution for automatic parking, the parking experience is average.

[0026] To solve the above problems, the present disclosure provides a vehicle positioning method, see Figure 1 , Figure 1 is a flow chart of a vehicle positioning method shown in an exemplary embodiment of the present disclosure, and the vehicle positioning method can be applied to Figure 3 The vehicle positioning device 100 shown, Figure 4 The vehicle 200 shown, Figure 4 The computing platform 250 and the computer readable storage medium in the embodiment are used in a vehicle as an example. Figure 1 The process shown is described in detail, and the vehicle positioning method can specifically include the following steps:

[0027] Step S10: Acquire environmental information collected by each of the multiple sensors on the vehicle.

[0028] The vehicle is redundantly installed with multiple sensors, each corresponding to a positioning method. Optionally, after the vehicle turns on the automatic driving mode, multiple sensors are controlled to work, and each sensor collects environmental information. For example, if the multiple sensors include a camera, the image information captured by the camera on the vehicle is obtained. For another example, if the multiple sensors include a lidar, the radar data scanned by the lidar on the vehicle is obtained. For another example, if the multiple sensors include a wheel speed meter, the wheel speed information collected by the wheel speed meter on the vehicle is obtained. The wheel speed information is the rotation speed of the wheel per unit time. For example, the wheel speed information can be 15 kilometers per hour.

[0029] It should be noted that the sensors on the vehicle are not limited to the above-mentioned cameras, lidars, and wheel speed meters. It can be fewer sensors, for example, it can include cameras and lidars, or it can be more sensors, for example, it can also include inertial measurement units (Inertial Measurement Unit, IMU), wheel speed meters (Odograph, ODO), etc.

[0030] Optionally, positioning is performed while the vehicle is traveling. As the vehicle moves, the position of the vehicle changes. Therefore, the environmental information collected by each sensor at different times and locations may be different.

[0031] When the vehicle is not in autonomous driving mode, only some of the sensors related to manual driving can work. For example, the wheel speed meter works and the vehicle's mileage can be counted while the vehicle is driving. Sensors not related to vehicle driving can be disabled to reduce the energy consumption of the entire vehicle.

[0032] Step S20: According to the various environmental information, an actual driving trajectory corresponding to each environmental information is obtained.

[0033] During the driving process of the vehicle, multiple environmental information is collected at multiple times. It can be understood that each type of environmental information is collected at different times, and the actual driving trajectory corresponding to the environmental information can be drawn according to the order in which the environmental information is collected. In this embodiment, there are multiple types of environmental information. It should be understood that each type of environmental information draws an actual driving trajectory, and multiple types of environmental information can draw multiple actual driving trajectories. For example, the actual driving trajectory may include: an actual descriptor trajectory, an actual point cloud vector trajectory, an actual wheel trajectory, etc.

[0034] Step S30: Obtain the positioning result of the vehicle according to the preset map and multiple actual driving trajectories.

[0035] The vehicle is expected to travel according to a preset map, and the preset map includes a preset driving trajectory, which is the trajectory that the vehicle is expected to travel. In one embodiment, the preset map may be pre-planned for navigation. Exemplarily, the driver navigates on the central control screen in advance, and the vehicle plans a driving route. The vehicle turns on the automatic driving mode during driving. After the vehicle turns on the automatic driving mode, the remaining path on the driving path is used as the preset driving trajectory, and the map where the preset driving path is located is used as the preset map. For example, when navigating, the driving path is planned to be from address A to address C. When driving to address B on this section of the path, the vehicle enters the automatic driving mode and determines the remaining path, i.e., address B to address C, as the preset driving trajectory.

[0036] In another embodiment, the preset driving trajectory can also be determined from a historical path. For example, a path of the vehicle before the automatic driving mode is turned on is obtained, and a path with a high degree of overlap with the historical path is found based on the path as the preset driving trajectory, and the map where the preset driving trajectory is located is used as the preset map. In the mapping stage, the preset map can be created in combination with the Global Navigation Satellite System (GNSS) positioning technology.

[0037] The positioning result of the vehicle is obtained according to the preset map and multiple actual driving tracks. For example, the positioning result of the vehicle can be obtained by comparing multiple actual driving tracks with the preset driving tracks on the preset map.

[0038] The vehicle positioning method provided in this embodiment obtains environmental information collected by each of the multiple sensors on the vehicle; then obtains the actual driving trajectory corresponding to each of the environmental information based on the multiple environmental information; obtains the vehicle positioning result based on the preset map and the multiple actual driving trajectories, and redundant multiple sensors are provided on the vehicle. When the functions of some sensors are limited or damaged, other sensors can continue to be used for positioning, thereby meeting the positioning requirements in various scenarios and improving the reliability of vehicle positioning.

[0039] Optionally, the user operates on the central control screen of the vehicle to turn on the automatic driving mode. Alternatively, the user operates on a terminal device connected to the vehicle to turn on the automatic driving mode of the vehicle.

[0040] Optionally, the vehicle can also automatically enter the automatic driving mode. Exemplarily, the vehicle collects the driver's biometric information, and uses the biometric information to identify whether the driver is in a state of fatigue. If the driver is in a state of fatigue, the vehicle automatically turns on the automatic driving mode. For example, the camera on the vehicle collects the user's facial image, and uses image recognition technology to recognize the facial image to obtain a recognition result. If the recognition result indicates that the driver is in a state of fatigue, the vehicle automatically turns on the automatic driving mode. In the scenario of driving on a highway, due to long-term driving or the need to analyze the road conditions due to high speed, this will consume more energy from the driver. In this process, the driver usually feels tired. If the driver continues to drive in a tired state, there may be safety hazards. After recognizing that the driver is in a state of fatigue, the vehicle automatically turns on the automatic driving mode to assist driving, thereby improving driving safety.

[0041] Automatic driving is an assisted driving function. When the user is detected to be in a non-fatigued state, the vehicle is controlled to exit the automatic driving mode according to the user's operation on the vehicle's central control screen or the terminal device connected to the vehicle. Alternatively, the vehicle automatically exits the automatic driving mode after the user operates the vehicle's steering wheel, gear position, accelerator, etc.

[0042] In one embodiment, the multiple sensors include: a camera, and the environmental information includes: image information. Step S20 may include: generating a descriptor based on the image information, for example, performing semantic segmentation on the image information to obtain multiple semantic segmentation regions, and then generating a descriptor based on the multiple semantic segmentation regions. Based on the descriptor, an actual descriptor trajectory corresponding to the image information is obtained.

[0043] In another embodiment, the multiple sensors include: a laser radar, and the environmental information includes: radar data. Step S20 may include: obtaining, according to the radar data, an actual point cloud vector trajectory corresponding to the radar data. Exemplarily, vectorization is performed on the radar data to obtain point cloud information and vector information, and then the actual point cloud vector trajectory is generated according to the point cloud information and vector information.

[0044] In another embodiment, the multiple sensors include: a wheel speed meter; the environmental information includes wheel speed information. Step S20 may include: obtaining the actual wheel trajectory corresponding to the wheel speed information according to the wheel speed information. Exemplarily, the wheel speed meter is used to collect wheel information of the vehicle, and the wheel information is the rotation speed of the wheel. The travel distance of the wheel can be obtained according to the rotation speed of the wheel and the radius of the wheel. The travel direction of the vehicle can be known according to the rotation direction of the wheel. The actual wheel trajectory records that the vehicle moves x meters in the first direction and then moves y meters in the second direction, where x and y are both positive numbers.

[0045] In one embodiment, the preset map includes a plurality of preset driving trajectories and positioning information corresponding to each preset driving trajectory, and the plurality of actual driving trajectories correspond one to one to the plurality of preset driving trajectories. It is understandable that the preset driving trajectory in the preset map corresponds to information in a local coordinate system, and the corresponding positioning information is information in a global coordinate system. For example, the preset driving trajectory includes a preset point cloud vector trajectory, and the preset point cloud vector trajectory is obtained based on a photograph of the environment in which the vehicle is located. For example, the preset point cloud vector trajectory is obtained by photographing a certain bus stop sign, and the corresponding global coordinates may be the longitude and latitude coordinates corresponding to the bus stop sign. Step S30 may include: when each actual driving trajectory among the plurality of actual driving trajectories is aligned with the corresponding preset driving trajectory, obtaining the positioning result of the vehicle according to the positioning information corresponding to each preset driving trajectory.

[0046] As a method, when each actual driving track in a plurality of actual driving tracks is aligned with the preset driving track corresponding thereto, the positioning information corresponding to each preset driving track is obtained. It can be understood that it is equivalent to using a plurality of preset driving tracks for positioning respectively. Then, according to the plurality of positioning information, the positioning result of the vehicle is obtained. Exemplarily, the distance between each two positions represented by the plurality of positioning information is less than the first preset distance, for example, the first preset distance may be 2 meters, and any one of the plurality of positioning information is determined as the positioning result. Alternatively, in combination with the example in the above embodiment, the sensor includes a camera, a laser radar and a wheel speed meter, the preset driving track includes a preset descriptor track corresponding to the camera, a preset point cloud vector track corresponding to the laser radar and a preset wheel track corresponding to the wheel speed meter, and the positioning reliability based on the point cloud vector is higher, therefore, the position represented by the positioning information corresponding to the preset driving track is determined as the first reference position, and the position represented by the positioning information obtained by other positioning methods is determined as the second reference position, and the number of the second reference positions may be multiple. When the distance between the first reference position and all the second reference positions is less than the second preset distance, the first reference position is determined as the positioning result of the vehicle.

[0047] As another way, the positioning result of the vehicle can be obtained according to the positioning information corresponding to each preset driving trajectory, which can be as follows: the positioning information corresponding to each preset driving trajectory is used as the intermediate positioning result of each actual driving trajectory. It can be understood that the intermediate positioning result is used to perform rough positioning, and the positioning accuracy can be within 5 meters or 10 meters. The positioning result of the vehicle is obtained according to the intermediate positioning result and the positioning constraint condition. It can be understood that the positioning accuracy can be within 1 meter for fine positioning.

[0048] The preset map includes: a preset descriptor trajectory, a preset point cloud vector trajectory and a preset wheel trajectory, and the constraint condition includes at least one of the following: a constraint condition corresponding to the preset descriptor trajectory, a constraint condition corresponding to the preset point cloud vector trajectory, and a constraint condition corresponding to the preset wheel trajectory.

[0049] For ease of understanding, the preset description sub-track is used as an example for description. When the actual description sub-track is aligned with the preset description sub-track, coarse positioning is first performed. When the actual description sub-track is aligned with the preset description sub-track, the positioning information corresponding to the preset description sub-track is used as the coarse positioning result. The accuracy of the positioning information can be within a range of 5*5 meters. For example, the positioning information is the range of the position where the speed bump A is located. Then, the coarse positioning result is finely aligned to construct the constraint condition corresponding to the preset description sub-track. The constraint condition can be the position range corresponding to the positioning information. For example, the constraint condition is certain areas within the position range where the speed bump A on the preset description sub-track is located. When the position collected on the actual description sub-track is within the position range specified by the constraint condition, it means that the position is in certain areas on the speed bump A. The positioning information corresponding to the position (such as longitude and latitude) is used as the positioning result. The accuracy of the positioning result can reach within 1 meter.

[0050] It should be noted that the preset driving trajectory in the preset map is not limited to the combination of the preset descriptor trajectory, the preset point cloud vector trajectory and the preset wheel trajectory, and is determined according to the actual working sensors. For example, if the camera is damaged or the camera fails due to interference, light and other factors, the preset point cloud vector trajectory corresponding to the camera is not used for positioning, that is, in this case, the preset driving trajectory is the preset descriptor trajectory and the preset wheel trajectory, and these two preset driving estimates are used for vehicle positioning.

[0051] Optionally, before step S30, the method further includes: acquiring local positioning information collected by a local positioning sensor on the vehicle; and obtaining a preset map according to the local positioning information.

[0052] In one embodiment, local positioning information in a local coordinate system collected by a local positioning sensor on a vehicle is obtained, wherein the local coordinate system is a coordinate system established with the local positioning sensor as a reference. A preset map is obtained based on the local positioning information, for example, the preset map is in a global coordinate system or a world coordinate system, and a coordinate conversion relationship is established between the global coordinate system and the local coordinate system. Based on the coordinate conversion relationship, the local positioning information in the local coordinate system is converted into global positioning information in the world coordinate system, and the map where the global positioning information is located is derived as the preset map.

[0053] Optionally, the local positioning sensor may be, but is not limited to, IMU or ODO.

[0054] Optionally, during the driving process of the vehicle, the position in the local coordinate system collected by the local positioning sensor may diverge, which means that the coordinate transformation relationship is not applicable after the divergence. In order to ensure the accuracy of subsequent positioning, the coordinate transformation relationship can be updated. The update of the coordinate transformation relationship can be performed at a preset frequency. For example, the preset frequency is 10 Hz, which can be understood as updating the coordinate transformation relationship once every 0.1 seconds.

[0055] Optionally, the world coordinate system may be a latitude and longitude coordinate system. For ease of calculation, the world coordinate system may also be a relatively simple East North Up (ENU) coordinate system. Since the surface of the earth is curved, when the ENU coordinate system is used, the origin of the coordinate system needs to be updated in real time.

[0056] Optionally, memory parking (Home-zone Parking Assistant, HPA) is an important application of autonomous driving in parking scenarios. The above embodiment can be applied to the memory parking scenario. It generates a customized parking map, i.e., the above preset map, by learning the parking routes and parking spaces of a fixed parking lot. Later, when parking is needed, the vehicle can autonomously complete the parking in and out of the parking lot according to the customized preset map. For example, the method includes: obtaining environmental information collected by each of the multiple sensors on the vehicle; then, based on the multiple environmental information, obtaining the actual driving trajectory corresponding to each environmental information; then, based on the preset map and the multiple actual driving trajectories, obtaining the positioning result of the vehicle; comparing the obtained positioning result with the end point of the memory parking in the preset map, if the positioning result is the end point of the memory parking, the parking is completed. On the contrary, if the positioning result is not the end point of the memory parking, the vehicle continues to be controlled to park.

[0057] Based on the above embodiments, the present disclosure provides a vehicle positioning method. Figure 2 , the vehicle positioning method comprises:

[0058] Coarse positioning. It includes: setting the origin of the coordinate system, initializing the rough alignment of the trajectory, and maintaining the initial positioning. It can be understood that coarse positioning refers to the above-mentioned steps of creating a coordinate transformation relationship and updating the coordinate transformation relationship.

[0059] Load a map. For example, load a map based on a coordinate transformation relationship.

[0060] Map coarse alignment. This includes: description sub-map coarse alignment, wheel track map coarse alignment, and point cloud vector map coarse alignment.

[0061] Map alignment, after which the positioning result of the vehicle is obtained. Here, map alignment can be used to construct optimization problems and use point clouds, vectors, point cloud semantics, etc. to construct constraint conditions. For example, the constructed constraint conditions are as follows: Figure 2 Point cloud residual, vector residual and semantic point cloud residual in .

[0062] Map alignment effect verification. It is understandable that the positioning results obtained in the map alignment are verified, including the verification of the point cloud alignment effect, vector alignment effect and semantic point cloud alignment effect.

[0063] After verification, the candidate map result, that is, the final positioning result, is obtained. This positioning result can be used for navigation, autonomous driving, automatic parking, etc.

[0064] The vehicle positioning method provided in this embodiment performs positioning through multi-source information, wherein multi-source information can be understood as the diversified types of sensor devices that collect environmental information, including lidar, camera, wheel speed meter, GNSS, IMU, ODO, etc., and source information can also be understood as diversified information types, including point cloud, semantic point cloud, semantic vector and other types. The rich information types provide various types of constraints, thereby improving the accuracy of positioning. And when some of the positioning methods fail, for example, the underground tunnel where the memory parking is located causes the GNSS positioning method to be limited, and the remaining positioning methods can still continue to be used for positioning, which improves the stability of positioning. And the present disclosure has a high tolerance for the external environment, even in scenes such as urban canyons with severe obstructions and old garages with few traffic signs, it can still complete positioning stably. In addition, multiple sensors are redundant with each other and are suitable for vehicles with different sensor configurations.

[0065] To implement the above method embodiment, this embodiment proposes a vehicle positioning device, see Figure 3 , Figure 3 is a block diagram of a vehicle positioning device according to an exemplary embodiment, wherein the vehicle positioning device 100 comprises: an environment information acquisition module 110, a trajectory acquisition module 120 and a positioning module 130;

[0066] An environmental information collection module 110 is used to obtain environmental information collected by each of the multiple sensors on the vehicle;

[0067] The trajectory acquisition module 120 is used to obtain the actual driving trajectory corresponding to each environmental information according to the various environmental information;

[0068] The positioning module 130 is used to obtain the positioning result of the vehicle according to a preset map and a variety of actual driving trajectories.

[0069] Optionally, the multiple sensors include: a camera, the environment information acquisition module 110 includes: an image information acquisition module, and the trajectory acquisition module 120 includes: a descriptor generation module and an actual descriptor trajectory acquisition module;

[0070] An image information acquisition module, used to acquire image information acquired by the camera on the vehicle;

[0071] A descriptor generation module, used to generate a descriptor according to the image information;

[0072] The actual descriptor track acquisition module is used to obtain the actual descriptor track corresponding to the image information according to the descriptor.

[0073] Optionally, the multiple sensors include: a laser radar, the environment information acquisition module 110 includes: a radar data acquisition module, and the trajectory acquisition module 120 includes: a radar data acquisition module and an actual point cloud vector trajectory acquisition module;

[0074] A radar data acquisition module, used to acquire radar data collected by the laser radar on the vehicle;

[0075] The actual point cloud vector trajectory acquisition module is used to obtain the actual point cloud vector trajectory corresponding to the radar data according to the radar data.

[0076] Optionally, the multiple sensors include: a wheel speed meter, the environment information acquisition module 110 includes: a wheel speed information acquisition module, and the trajectory acquisition module 120 includes: a wheel speed information acquisition module and an actual wheel trajectory acquisition module;

[0077] A wheel speed information acquisition module, used to acquire wheel speed information acquired by the wheel speed meter on the wheel of the vehicle;

[0078] The actual wheel trajectory acquisition module is used to obtain the actual wheel trajectory corresponding to the wheel speed information according to the wheel speed information.

[0079] Optionally, the preset map includes multiple preset driving tracks and positioning information corresponding to each preset driving track, and the multiple actual driving tracks correspond to the multiple preset driving tracks one by one. The positioning module 130 includes: a positioning result acquisition module;

[0080] The positioning result acquisition module is used to obtain the positioning result of the vehicle according to the positioning information corresponding to each preset driving trajectory when each actual driving trajectory among the multiple actual driving trajectories is aligned with the corresponding preset driving trajectory.

[0081] Optionally, the positioning result acquisition module includes: a coarse positioning module and a fine positioning module;

[0082] A coarse positioning module, used to use the positioning information corresponding to each preset driving trajectory as an intermediate positioning result of each actual driving trajectory;

[0083] The precise positioning module is used to obtain the positioning result of the vehicle according to the intermediate positioning result and the positioning constraint condition.

[0084] Optionally, the preset map includes: a preset descriptor trajectory, a preset point cloud vector trajectory and a preset wheel trajectory, and the constraint conditions include at least one of the following: a constraint condition corresponding to the preset descriptor trajectory, a constraint condition corresponding to the preset point cloud vector trajectory, and a constraint condition corresponding to the preset wheel trajectory.

[0085] Optionally, the vehicle positioning device 100 includes: a local positioning information acquisition module and a preset map acquisition module;

[0086] A local positioning information acquisition module is used to acquire local positioning information collected by a local positioning sensor on a vehicle;

[0087] The preset map acquisition module is used to obtain the preset map based on the local positioning information.

[0088] Regarding the vehicle positioning device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0089] The present disclosure also provides a computer-readable storage medium having computer program instructions stored thereon, and the program instructions, when executed by a processor, implement the steps of the vehicle positioning method provided by the present disclosure.

[0090] Figure 4 is a block diagram of a vehicle for a vehicle positioning method according to an exemplary embodiment. For example, Figure 4 The vehicle 200 in the embodiment may be a hybrid vehicle, a non-hybrid vehicle, an electric vehicle, a fuel cell vehicle, or other types of vehicles. The vehicle 200 may be an autonomous vehicle or a semi-autonomous vehicle.

[0091] Please refer to Figure 4 , the vehicle 200 may include various subsystems, such as an infotainment system 210, a perception system 220, a decision control system 230, a drive system 240, and a computing platform 250. The vehicle 200 may also include more or fewer subsystems, and each subsystem may include multiple components. In addition, each subsystem and each component of the vehicle 200 may be interconnected by wire or wireless means.

[0092] In some embodiments, the infotainment system 210 may include a communication system, an entertainment system, and a navigation system, among others.

[0093] The perception system 220 may include several sensors for sensing information about the environment around the vehicle 200. For example, the perception system 220 may include a global positioning system (the global positioning system may be a GPS system, a Beidou system, or other positioning systems) and an inertial measurement unit (IMU).

[0094] The decision control system 230 may include a computing system, a vehicle controller, a steering system, a throttle, and a braking system.

[0095] The drive system 240 may include components that provide power movement for the vehicle 200. In one embodiment, the drive system 240 may include an engine, an energy source, a transmission system, and wheels. The engine may be one or a combination of an internal combustion engine, an electric motor, and an air compression engine. The engine can convert energy provided by the energy source into mechanical energy.

[0096] Some or all functions of the vehicle 200 are controlled by a computing platform 250. The computing platform 250 may include at least one processor 251 and a memory 252, and the processor 251 may execute instructions 253 stored in the memory 252.

[0097] The processor 251 may be any conventional processor, such as a commercially available CPU. The processor may also include a graphics processor (Graphic Process Unit, GPU), a field programmable gate array (Field Programmable Gate Array, FPGA), a system on chip (System on Chip, SOC), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC) or a combination thereof.

[0098] The memory 252 may be implemented by any type of volatile or nonvolatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0099] In addition to instructions 253 , memory 252 may also store data, such as road maps, route information, and data such as the location, direction, and speed of the vehicle. The data stored in memory 252 may be used by computing platform 250 .

[0100] In the embodiment of the present disclosure, the processor 251 may execute the instruction 253 to complete all or part of the steps of the above-mentioned vehicle positioning method.

[0101] In another exemplary embodiment, a computer program product is also provided. The computer program product includes a computer program executable by a programmable device. The computer program has a code portion for executing the above-mentioned vehicle positioning method when executed by the programmable device.

[0102] In summary, the vehicle positioning method, device, vehicle and storage medium provided by the present invention obtain environmental information collected by each of the multiple sensors on the vehicle; then obtain the actual driving trajectory corresponding to each environmental information based on the multiple environmental information; obtain the vehicle positioning result based on the preset map and multiple actual driving trajectories, and redundant multiple sensors on the vehicle. When the functions of some sensors are limited or damaged, other sensors can still continue to be used for positioning, thereby meeting the positioning needs in various scenarios and improving the reliability of vehicle positioning.

[0103] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the present disclosure. This application is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and examples are to be considered as exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0104] It should be understood that the present disclosure is not limited to the exact 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 disclosure is limited only by the appended claims.

Claims

1. A vehicle positioning method, characterized in that: The vehicle positioning method comprises: Obtaining environmental information collected by each of multiple sensors on the vehicle; According to various environmental information, the actual driving trajectory corresponding to each environmental information is obtained; The vehicle positioning results are obtained based on the preset map and multiple actual driving trajectories.

2. The vehicle positioning method according to claim 1, characterized in that: The multiple sensors include: cameras, and the step of obtaining environmental information collected by each of the multiple sensors on the vehicle includes: Acquire image information collected by the camera on the vehicle; The method of obtaining the actual driving trajectory corresponding to each environmental information according to the multiple environmental information includes: Generate a descriptor according to the image information; According to the descriptor, an actual descriptor trajectory corresponding to the image information is obtained.

3. The vehicle positioning method according to claim 1, characterized in that: The multiple sensors include: a laser radar, and the step of obtaining environmental information collected by each of the multiple sensors on the vehicle includes: Acquire radar data collected by the laser radar on the vehicle; The method of obtaining the actual driving trajectory corresponding to each environmental information according to the multiple environmental information includes: According to the radar data, an actual point cloud vector trajectory corresponding to the radar data is obtained.

4. The vehicle positioning method according to claim 1, characterized in that: The multiple sensors include: a wheel speed meter, and the step of obtaining environmental information collected by each of the multiple sensors on the vehicle includes: Obtaining wheel speed information collected by the wheel speed meter on the wheel of the vehicle; The method of obtaining the actual driving trajectory corresponding to each environmental information according to the multiple environmental information includes: According to the wheel speed information, an actual wheel trajectory corresponding to the wheel speed information is obtained.

5. The vehicle positioning method according to any one of claims 1 to 4, characterized in that: The preset map includes multiple preset driving tracks and positioning information corresponding to each preset driving track, the multiple actual driving tracks correspond to the multiple preset driving tracks one by one, and obtaining the positioning result of the vehicle according to the preset map and the multiple actual driving tracks includes: When each actual driving trajectory among the multiple actual driving trajectories is aligned with the preset driving trajectory corresponding thereto, a positioning result of the vehicle is obtained according to the positioning information corresponding to each preset driving trajectory.

6. The vehicle positioning method according to claim 5, characterized in that: The obtaining of the positioning result of the vehicle according to the positioning information corresponding to each preset driving trajectory includes: Using the positioning information corresponding to each preset driving trajectory as the intermediate positioning result of each actual driving trajectory; The positioning result of the vehicle is obtained according to the intermediate positioning result and the positioning constraint condition.

7. The vehicle positioning method according to claim 6, characterized in that: The preset map includes: a preset descriptor trajectory, a preset point cloud vector trajectory and a preset wheel trajectory, and the constraint condition includes at least one of the following: a constraint condition corresponding to the preset descriptor trajectory, a constraint condition corresponding to the preset point cloud vector trajectory, and a constraint condition corresponding to the preset wheel trajectory.

8. The vehicle positioning method according to claim 1, characterized in that: Before obtaining the positioning result of the vehicle according to the preset map and the multiple actual driving trajectories, the method further includes: Obtaining local positioning information collected by a local positioning sensor on the vehicle; A preset map is obtained according to the local positioning information.

9. A vehicle positioning device, characterized in that: The vehicle positioning device comprises: An environmental information acquisition module, used to acquire environmental information collected by each of the multiple sensors on the vehicle; A trajectory acquisition module is used to obtain the actual driving trajectory corresponding to each environmental information according to a variety of environmental information; The positioning module is used to obtain the vehicle positioning results based on the preset map and multiple actual driving trajectories.

10. A vehicle, characterized in that: The vehicle comprises: processor; a memory for storing processor-executable instructions; The processor is configured to implement the steps of the vehicle positioning method according to any one of claims 1 to 8 when executing.

11. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the program instructions are executed by a processor, the steps of the vehicle positioning method described in any one of claims 1 to 8 are implemented.

Images