Positioning method, device and system

Abstract

The present application provides a positioning method, device and system. After the vehicle is started, sensing information of the vehicle is obtained according to a time interval. When the vehicle is positioned, sensing information corresponding to the current moment is obtained through an in-vehicle sensing device, and sensing information obtained at critical moments before is also obtained. Thus, the vehicle is positioned according to the obtained sensing information and map information of the area where the vehicle is located. Since the present application obtains sensing information from the time dimension, the process of obtaining sensing information is not affected by road congestion. Therefore, when the vehicle is traveling, the sensing information for positioning can be updated according to the time interval, improving the positioning accuracy. Moreover, by obtaining sensing information from the time dimension, when the vehicle is traveling at a low speed, environmental information around the vehicle can be collected in the gaps between vehicles. At this time, due to the low vehicle speed, the collected environmental information around the vehicle is clearer, further improving the positioning accuracy.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of intelligent driving, and in particular, to a positioning method, device and system. Background Art

[0002] As a positioning sensor for unmanned driving vehicles, lidar, together with technologies such as image recognition, realizes the perception of the surrounding environment of the vehicle and the global positioning of the vehicle. Among them, the lidar on the vehicle can be installed in two ways: the top lidar installation method and the front bumper installation method.

[0003] Among them, in the front bumper installation method, the lidar is installed at the front and both sides of the vehicle. The installation position is relatively low and is easily blocked, resulting in a small perception range, less information for positioning, and inaccurate positioning. Therefore, in order to improve the positioning accuracy, the lidar is controlled to collect the environmental information around the vehicle once every time the vehicle travels a preset distance. When the vehicle is positioned, the positioning is performed according to the environmental information around the vehicle collected multiple times, and the positioning accuracy is relatively high.

[0004] However, when the road is congested, the vehicle travels slowly and cannot collect the environmental information around the vehicle in time, resulting in that the environmental information around the vehicle collected multiple times for positioning is not updated when the vehicle is positioned, thus resulting in poor positioning accuracy. Summary of the Invention

[0005] The present application provides a positioning method, device and system, aiming to solve the problem of inaccurate vehicle positioning caused by obstacle occlusion, road congestion, etc.

[0006] In a first aspect, the present application provides a positioning method, which can be implemented by a vehicle, or by components in the vehicle, such as components such as a processing device, a circuit, a chip, etc. in the vehicle, or a cloud server communicating with the vehicle through a gateway. The method includes:

[0007] At the current moment, obtain first sensing information through an in-vehicle sensing device, where the first sensing information includes the coordinates of feature points collected by the in-vehicle sensing device at the current moment in the vehicle body coordinate system and the odometer information of the vehicle at the current moment;

[0008] Obtain second sensing information acquired by the vehicle-mounted sensing device at a critical moment, where the second sensing information includes the coordinates of feature points collected by the vehicle-mounted sensing device in the vehicle body coordinate system at the critical moment and the odometer information of the vehicle at the critical moment. Among them, the critical moment includes a first critical moment, and the first critical moment is the moment when the second sensing information is obtained according to a time interval. The time interval between the first critical moment and the current moment is less than or equal to a preset duration;

[0009] Determine the position of the vehicle at the current moment according to the map information of the vehicle driving area and the first sensing information and the second sensing information.

[0010] In a possible implementation manner, the determining the position of the vehicle at the current moment according to the map information of the vehicle driving area and the first sensing information and the second sensing information includes:

[0011] According to the odometer information in the first sensing information and the odometer information in the second sensing information, map the coordinates of the feature points collected at the critical moment to the vehicle body coordinate system at the current moment, and obtain the coordinates of the feature points collected at the critical moment in the vehicle body coordinate system at the current moment;

[0012] Determine the position of the vehicle at the current moment according to the coordinates of the feature points collected at the critical moment and the feature points collected at the current moment in the vehicle body coordinate system at the current moment and the map information.

[0013] In a possible implementation manner, the determining the position of the vehicle at the current moment according to the coordinates of the feature points collected at the critical moment and the feature points collected at the current moment in the vehicle body coordinate system at the current moment and the map information includes:

[0014] At the current moment, for each of the M particles corresponding to the vehicle, obtain the matching degree between the feature points collected at the current moment and the critical moment and the target object in the map information according to the coordinates of the feature points collected at the critical moment and the feature points collected at the current moment in the vehicle body coordinate system at the current moment and the position of each particle. Among them, the M particles are the particles used in the previous vehicle positioning, and the position of each particle is obtained according to the odometer information at the previous vehicle positioning, the odometer information at the current moment, and the position of each particle at the previous vehicle positioning. M is a positive integer;

[0015] Obtain K particles according to the matching degree of each particle among the M particles at the current moment and the M particles. K is a positive integer;

[0016] Obtain the position of the vehicle at the current moment according to the positions of the K particles corresponding to the vehicle at the current moment.

[0017] In a possible implementation manner, obtaining the matching degrees between the feature points collected at the critical moment and the feature points collected at the current moment and the target objects in the map information according to the coordinates of the feature points collected at the critical moment and the feature points collected at the current moment in the vehicle body coordinate system at the current moment and the position of each particle includes:

[0018] Map the coordinates of the feature points collected at the current moment and the critical moment in the vehicle body coordinate system at the current moment to the particle coordinate system with the particle as the origin;

[0019] Obtain the matching degrees between the target objects to be matched formed by the feature points collected at the current moment and the critical moment mapped to the particle coordinate system and the corresponding target objects in the map information.

[0020] In a possible implementation manner, obtaining K particles according to the matching degree of each of the M particles at the current moment and the M particles includes:

[0021] Obtain L particles with a matching degree greater than or equal to a preset matching degree among the M particles, where L is less than or equal to M and less than or equal to K;

[0022] Determine the L particles as the K particles; or,

[0023] Obtain at least one particle from the L particles;

[0024] Obtain the K particles according to the L particles and the at least one particle.

[0025] In a possible implementation manner, obtaining the K particles according to the L particles and the at least one particle includes:

[0026] According to the matching degree of each particle in the at least one particle, perform at least one replication on each particle;

[0027] Determine the L particles and the particles obtained after replication as the K particles.

[0028] In a possible implementation manner, obtaining the position of the vehicle at the current moment according to the positions of the K particles corresponding to the vehicle at the current moment includes:

[0029] Obtain the average position of the K particles according to the position of each particle among the K particles, and determine the average position of the K particles as the position of the vehicle at the current moment.

[0030] In a possible implementation manner, the method further includes:

[0031] Obtain an evaluation value of the position of the vehicle at the current moment according to the position of each particle among the K particles corresponding to the vehicle at the current moment and the position of the vehicle at the current moment, where the evaluation value indicates the difference between the position of the vehicle at the current moment and the true position information of the vehicle at the current moment.

[0032] In a possible implementation manner, the step of mapping the coordinates of the feature points collected at the critical moment to the vehicle body coordinate system at the current moment according to the odometer information in the second sensing information and the odometer information in the second sensing information to obtain the coordinates of the feature points collected at the critical moment in the vehicle body coordinate system at the current moment includes:

[0033] Determine the coordinate mapping relationship between the vehicle body coordinate system corresponding to the current moment and the vehicle body coordinate system corresponding to the first critical moment according to the mileage information in the first sensing information and the mileage information in the second sensing information;

[0034] Map the coordinates of the feature points collected at the first critical moment to the vehicle body coordinate system at the current moment respectively according to the coordinate mapping relationship to obtain the coordinates of the feature points collected at the first critical moment in the vehicle body coordinate system at the current moment.

[0035] In a possible implementation manner, the critical moment further includes a second critical moment, and the second critical moment is the moment when the second sensing information is obtained according to a distance interval, where the driving distance of the vehicle from the position at the second critical moment to the position corresponding to the current moment is less than or equal to a preset distance.

[0036] In a possible implementation manner, the step of determining the position of the vehicle at the current moment according to the map information of the vehicle driving area and the first sensing information and the second sensing information includes:

[0037] Determine the pose of the vehicle at the current moment according to the map information and the first sensing information and the second sensing information.

[0038] In a possible implementation manner, before obtaining the matching degrees of the feature points collected at the critical moment and the feature points collected at the current moment with the target object in the map information based on the coordinates of the feature points collected at the critical moment and the feature points collected at the current moment in the vehicle body coordinate system at the current moment and the position of each particle, the following steps are further included:

[0039] Determine the target feature points according to the feature values of the feature points collected at each critical moment and the feature points collected at the current moment.

[0040] According to the feature values of the feature points collected at each critical moment and the feature points collected at the current moment except for the feature points included in the feature point set, determine the target feature points again, where the feature points included in the feature point set are the feature points located within a preset distance range of the target feature points determined last time and the target feature points determined last time.

[0041] When the number of the target feature points meets the preset number, obtain N target feature points, where N is equal to the preset number.

[0042] The step of obtaining the matching degrees of the feature points collected at the current moment and the feature points collected at the critical moment with the target object in the map information based on the coordinates of the feature points collected at the critical moment and the feature points collected at the current moment in the vehicle body coordinate system at the current moment and the position of each particle includes:

[0043] Based on the coordinates of the N target feature points in the vehicle body coordinate system at the current moment and the position of each particle, obtain the matching degrees of the feature points collected at the current moment and the feature points collected at the critical moment with the target object in the map information of the target area.

[0044] In a possible implementation manner, the feature value of the feature point is obtained through an evaluation function, and the feature value is used to evaluate the stability of the feature point.

[0045] In a possible implementation manner, the target feature point is the feature point with the largest feature value among all feature points.

[0046] In a possible implementation manner, the origin of the vehicle body coordinate system is located at any position on the vehicle.

[0047] In a second aspect, the present application provides a positioning device, including:

[0048] An acquisition module, configured to obtain first sensing information through a vehicle-mounted sensing device at the current moment, where the first sensing information includes the coordinates of feature points collected by the vehicle-mounted sensing device in the vehicle body coordinate system at the current moment and the odometer information of the vehicle at the current moment; and is further configured to obtain second sensing information obtained through the vehicle-mounted sensing device at a critical moment, where the second sensing information includes the coordinates of feature points collected by the vehicle-mounted sensing device in the vehicle body coordinate system at the critical moment and the odometer information of the vehicle at the critical moment, where the critical moment includes a first critical moment, and the first critical moment is the moment for obtaining the second sensing information according to a time interval, and the time interval between the first critical moment and the current moment is less than or equal to a preset duration;

[0049] A positioning module, configured to determine the position of the vehicle at the current moment according to the map information of the vehicle driving area and the first sensing information and the second sensing information.

[0050] In a possible implementation manner, when the positioning module determines the position of the vehicle at the current moment according to the map information of the vehicle driving area and the first sensing information and the second sensing information, it is specifically configured to:

[0051] According to the odometer information in the first sensing information and the odometer information in the second sensing information, map the coordinates of the feature points collected at the critical moment to the vehicle body coordinate system at the current moment, and obtain the coordinates of the feature points collected at the critical moment in the vehicle body coordinate system at the current moment;

[0052] Determine the position of the vehicle at the current moment according to the coordinates of the feature points collected at the critical moment and the coordinates of the feature points collected at the current moment in the vehicle body coordinate system at the current moment and the map information.

[0053] In a possible implementation manner, when the positioning module determines the position of the vehicle at the current moment according to the coordinates of the feature points collected at the critical moment and the coordinates of the feature points collected at the current moment in the vehicle body coordinate system at the current moment and the map information, it is specifically configured to:

[0054] At the current moment, for each of the M particles corresponding to the vehicle, obtain the matching degrees between the feature points collected at the critical moment and the feature points collected at the current moment and the target objects in the map information based on the coordinates of the feature points collected at the critical moment and the current moment in the vehicle body coordinate system at the current moment and the positions of each particle, where the M particles are the particles used in the previous vehicle positioning, the position of each particle is obtained based on the odometer information in the previous vehicle positioning, the odometer information at the current moment, and the positions of each particle in the previous vehicle positioning, and M is a positive integer;

[0055] Obtain K particles based on the matching degrees of each of the M particles at the current moment and the M particles, where K is a positive integer;

[0056] Obtain the position of the vehicle at the current moment based on the positions of the K particles corresponding to the vehicle at the current moment.

[0057] In a possible implementation manner, when the positioning module obtains the matching degrees between the feature points collected at the critical moment and the feature points collected at the current moment and the target objects in the map information based on the coordinates of the feature points collected at the critical moment and the current moment in the vehicle body coordinate system at the current moment and the positions of each particle, it specifically is used for:

[0058] Map the coordinates of the feature points collected at the current moment and the critical moment in the vehicle body coordinate system at the current moment to the particle coordinate system with the particle as the origin;

[0059] Obtain the matching degrees between the target object to be matched formed by the feature points collected at the current moment and the critical moment mapped to the particle coordinate system and the corresponding target objects in the map information.

[0060] In a possible implementation manner, when the positioning module obtains K particles based on the matching degrees of each of the M particles at the current moment and the M particles, it specifically is used for:

[0061] Obtain L particles with matching degrees greater than or equal to a preset matching degree among the M particles, where L is less than or equal to M and less than or equal to K;

[0062] Determine the L particles as the K particles; or,

[0063] Obtain at least one particle from the L particles;

[0064] Obtain the K particles based on the L particles and the at least one particle.

[0065] In a possible implementation manner, when the positioning module obtains the K particles based on the L particles and the at least one particle, it specifically is used for:

[0066] According to the matching degree of each particle in the at least one particle, perform at least one replication on each particle;

[0067] Determine the L particles and the particles obtained after replication as the K particles.

[0068] In a possible implementation manner, when the positioning module obtains the position of the vehicle at the current moment according to the positions of the K particles corresponding to the vehicle at the current moment, it specifically is used for:

[0069] According to the positions of each of the K particles, obtain the average position of the K particles, and determine the average position of the K particles as the position of the vehicle at the current moment.

[0070] In a possible implementation manner, the positioning module is further used for:

[0071] According to the position of each of the K particles corresponding to the vehicle at the current moment and the position of the vehicle at the current moment, obtain an evaluation value of the position of the vehicle at the current moment, where the evaluation value indicates the difference between the position of the vehicle at the current moment and the true position information of the vehicle at the current moment.

[0072] In a possible implementation manner, when the positioning module maps the coordinates of the feature points collected at the critical moment to the vehicle body coordinate system at the current moment according to the odometer information in the second sensing information and the odometer information in the second sensing information, and obtains the coordinates of the feature points collected at the critical moment in the vehicle body coordinate system at the current moment, it specifically is used for:

[0073] Determine the coordinate mapping relationship between the vehicle body coordinate system corresponding to the current moment and the vehicle body coordinate system corresponding to the first critical moment according to the mileage information in the first sensing information and the mileage information in the second sensing information;

[0074] According to the coordinate mapping relationship, map the coordinates of the feature points collected at the first critical moment to the vehicle body coordinate system at the current moment respectively, and obtain the coordinates of the feature points collected at the first critical moment in the vehicle body coordinate system at the current moment.

[0075] In a possible implementation, the critical moment further includes a second critical moment, which is the moment when second sensing information is obtained according to a distance interval, where the driving distance of the vehicle from the position at the second critical moment to the position corresponding to the current moment is less than or equal to a preset distance.

[0076] In a possible implementation, when the positioning module determines the position of the vehicle at the current moment according to the map information of the vehicle driving area and the first sensing information and the second sensing information, it is specifically configured to:

[0077] Determine the pose of the vehicle at the current moment according to the map information, the first sensing information, and the second sensing information.

[0078] In a possible implementation, before the positioning module obtains the matching degrees of the feature points collected at the current moment and the critical moment with the target object in the map information according to the coordinates of the feature points collected at the critical moment and the current moment in the vehicle body coordinate system at the current moment and the position of each particle, it is further configured to:

[0079] Determine target feature points according to the feature values of the feature points collected at each critical moment and the feature points collected at the current moment;

[0080] Determine target feature points again according to the feature values of the feature points collected at each critical moment and the feature points collected at the current moment except for the feature points included in the feature point set, where the feature points included in the feature point set are the feature points located within a preset distance range of the target feature points determined last time and the target feature points determined last time;

[0081] When the number of the target feature points meets a preset number, obtain N target feature points, where N is equal to the preset number;

[0082] When the positioning module obtains the matching degrees of the feature points collected at the current moment and the critical moment with the target object in the map information according to the coordinates of the feature points collected at the critical moment and the current moment in the vehicle body coordinate system at the current moment and the position of each particle, it is specifically configured to:

[0083] Obtain the matching degrees of the feature points collected at the current moment and the critical moment with the target object in the map information of the target area according to the coordinates of the N target feature points in the vehicle body coordinate system at the current moment and the position of each particle.

[0084] In a possible implementation, the feature value of the feature point is obtained through an evaluation function, and the feature value is used to evaluate the stability of the feature point.

[0085] In a possible implementation, the target feature point is the feature point with the largest eigenvalue among all feature points.

[0086] In a possible implementation, the origin of the vehicle body coordinate system is located at any position on the vehicle.

[0087] In a third aspect, the present application provides a positioning device, including: a memory and at least one processor;

[0088] The memory is used to store program instructions;

[0089] The processor is used to call the program instructions in the memory and execute the positioning method according to any one of the first aspect.

[0090] In a fourth aspect, the present application provides a positioning system, including a vehicle and an on-vehicle sensing device;

[0091] The on-vehicle sensing device is installed on the vehicle;

[0092] The vehicle is used to execute the positioning method according to any one of the first aspect; or,

[0093] The on-vehicle sensing device is used to execute the positioning method according to any one of the first aspect.

[0094] In a fifth aspect, the present application provides a non-transitory computer-readable storage medium storing computer instructions, and the computer instructions are used to cause the computer to execute the positioning method according to any one of the first aspect.

[0095] In a sixth aspect, the present application provides a program product, the program product includes a computer program, the computer program is stored in a readable storage medium, at least one processor of the positioning device can read the computer program from the readable storage medium, and the at least one processor executes the computer program so that the positioning device implements the positioning method according to any one of the first aspect.

[0096] The present application provides a positioning method, device and system. After the vehicle starts, sensing information of the vehicle is obtained according to a time interval. When the vehicle is positioned, first sensing information corresponding to the current moment and second sensing information corresponding to at least one critical moment are obtained, and the vehicle is positioned according to the first sensing information, at least one second sensing information and map information. Since the sensing information is obtained from the time dimension, the process of obtaining the sensing information is not affected by road congestion. Therefore, when the vehicle is traveling, the sensing information for positioning can be updated according to the time interval, improving the positioning accuracy. Moreover, when the sensing information is obtained from the time dimension, when the vehicle is traveling at a low speed, the environmental information around the vehicle can be collected in the gap between vehicles. At this time, since the vehicle speed is slow, the environmental information around the vehicle collected is clearer, further improving the positioning accuracy. Description of the Drawings

[0097] Figure 1 Schematic diagram of an application scenario provided by an embodiment of the present application;

[0098] Figure 2 Flowchart of the positioning method provided by an embodiment of the present application

[0099] Figure 3 Schematic diagram of the vehicle body coordinate system provided by an embodiment of the present application;

[0100] Figure 4 Schematic diagram of positioning the vehicle provided by an embodiment of the present application;

[0101] Figure 5 Schematic diagram of positioning the vehicle provided by another embodiment of the present application;

[0102] Figure 6 Schematic diagram of positioning the vehicle provided by another embodiment of the present application;

[0103] Figure 7a Schematic diagram of the surrounding environment information when the vehicle faces the first direction provided by an embodiment of the present application;

[0104] Figure 7b Schematic diagram of the surrounding environment information when the vehicle faces the second direction provided by an embodiment of the present application;

[0105] Figure 8 Flowchart of the positioning method provided by another embodiment of the present application;

[0106] Figure 9 Flowchart of the positioning method provided by another embodiment of the present application;

[0107] Figure 10 Schematic diagram of particle initialization provided by an embodiment of the present application;

[0108] Figure 11 Schematic diagram of the surrounding environment information in the vehicle body coordinate system and the particle coordinate system respectively provided by an embodiment of the present application;

[0109] Figure 12 Schematic diagram of the structure of the positioning device provided by an embodiment of the present application;

[0110] Figure 13 Schematic diagram of the structure of the positioning device provided by an embodiment of the present application;

[0111] Figure 14 Schematic diagram of the structure of the positioning system provided by an embodiment of the present application. Detailed implementation manners

[0112] To facilitate the understanding of the embodiments of the present application, the concepts involved in the embodiments of the present application are first introduced.

[0113] Current moment: The moment when the vehicle is positioned after starting.

[0114] Critical moment: The moment when the vehicle scans the surrounding environment information of the vehicle through the sensor device after starting, and the scanned surrounding environment information of the vehicle is used for positioning.

[0115] Feature point: Among the point clouds corresponding to the surrounding environment of the vehicle scanned by the sensing device, the points that can reflect the characteristics of the target objects in the surrounding environment. Therefore, the target objects in the surrounding environment can be identified through the feature points.

[0116] Figure 1 Schematic diagram of the application scenario provided by an embodiment of the present application. In the intelligent driving mode of the vehicle, after the vehicle starts, for example, the vehicle is driving, or is temporarily in a parked state due to congestion, waiting for a traffic light, etc. The laser radar on the vehicle senses the surrounding environment information of the vehicle to position the vehicle. Specifically: A preset distance is set. The laser radar on the vehicle emits laser signals around the vehicle every time the vehicle travels the preset distance. After the target objects in the surrounding environment of the vehicle are scanned by the laser, they are displayed as a cloud of points. The landmark information around the vehicle is extracted through the cloud of points obtained each time of acquisition. During positioning, the landmark information around the vehicle collected multiple times is matched with the map information to achieve the positioning of the vehicle.

[0117] However, when the vehicle is driving on a congested road, the driving speed is slow, so that when the vehicle is positioning, the surrounding environment information collected cannot be updated in time, resulting in inaccurate positioning.

[0118] For example, as Figure 1As shown, when a vehicle is traveling on a congested road, environmental information around the vehicle is collected every 100 meters. For example, the vehicle collects environmental information around the vehicle at points A, B, C and D respectively. The vehicle travels to point E. Since the driving distance between points D and E is less than 100 meters, when positioning is required at point E, positioning is performed based on the environmental information around the vehicle collected at points A, B, C and D. At this time, due to the existence of errors, the vehicle is positioned near point D.

[0119] Due to road congestion, vehicles travel slowly, resulting in the vehicle traveling to point F and positioning, the distance between point D and point F is still less than 100 meters, so that the environmental information around the vehicle collected by the vehicle is still collected at points A, B, C and D. Therefore, during positioning, the environmental information around the vehicle is still collected at points A, B, C and D, resulting in a large difference between the vehicle's position obtained by positioning and the vehicle's actual position, and inaccurate positioning.

[0120] It is worth noting that the above examples are only used to illustrate the application scenarios to which the embodiments of the present application can be applied, and cannot be understood as limiting the application scenarios of the embodiments of the present application.

[0121] Therefore, in order to solve the problems existing in the prior art, the present application proposes that: the time dimension is continuous, so the vehicle-mounted device, such as a laser radar, can be controlled in the time dimension to continuously collect environmental information around the vehicle, and the vehicle's current position at the moment can be located through the continuously collected environmental information around the vehicle. Since the environmental information around the vehicle is continuously collected in the time dimension in the present application, and the time dimension is not affected by road congestion and other conditions. Therefore, after the vehicle is started, the collected environmental information around the vehicle can be updated in time, thereby improving the accuracy of positioning.

[0122] It should be understood that in practical applications, the technical solution of the present application can be applied to aircraft positioning in addition to vehicle positioning, for example, in the positioning scenario of a drone, to improve the accuracy of positioning. Among them, the present application is explained by taking vehicle positioning as an example, however, this should not be understood as limiting the scope of application of the present application.

[0123] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0124] Figure 2The flowchart of the positioning method provided by an embodiment of the present application. The execution subject of this embodiment is, for example, a vehicle, or can be implemented by components in the vehicle, such as components like a processing device, circuit, chip, etc. in the vehicle, or a cloud server communicating with the vehicle through a gateway. The present application does not limit this. As Figure 2 shown, the method of the embodiment of the present application includes:

[0125] S201. At the current moment, obtain first sensing information through an in-vehicle sensing device.

[0126] Among them, the first sensing information includes the coordinates of feature points collected by the in-vehicle sensing device at the current moment in the vehicle body coordinate system and the odometer information of the vehicle at the current moment.

[0127] In this step, optionally, the vehicle body coordinate system can be a plane coordinate system, such as a plane rectangular coordinate system, a polar coordinate system, or a space coordinate system, such as a space rectangular coordinate system, a cylindrical coordinate system, a spherical coordinate system. The present application does not limit this. In this embodiment, the space rectangular coordinate system is taken as an example for illustration.

[0128] Optionally, if the vehicle body coordinate system is a space rectangular coordinate system, the origin of the vehicle body coordinate system can be located at any position on the vehicle in question. For example, as Figure 3 shown, taking the geometric center of the vehicle as the origin, the driving direction as the X-axis, the direction perpendicular to the driving direction on the horizontal plane as the Y-axis, and the direction perpendicular to the driving direction on the vertical plane as the Z-axis.

[0129] It should be noted that the origin of the vehicle body coordinate system is determined with the vehicle as a reference object. However, during the driving process of the vehicle, the position of the vehicle changes. Therefore, the origin of the vehicle body coordinate system corresponding to different positions of the vehicle is different.

[0130] After the vehicle starts, obtain the environmental information around the vehicle and the odometer information of the vehicle through an in-vehicle sensing device. Among them, the in-vehicle sensing device is, for example, a system integrating multiple sensors (sensors), and can include, for example, a lidar and an inertial measurement unit. The lidar is used to scan the environment around the vehicle to obtain the environmental information around the vehicle, and the inertial measurement unit is used to obtain the odometer information of the vehicle.

[0131] It should be noted that in some possible designs, the point cloud of the environmental information around the vehicle can also be obtained through other sensors, such as, for example, an ultrasonic sensor, etc.

[0132] At the current moment, the lidar in the vehicle-mounted sensing device emits laser light outward to obtain the point cloud corresponding to the vehicle's surrounding environment, and the inertial detection unit obtains the odometer information at the current moment, so that the vehicle can obtain the sensing information at the current moment, that is, the first sensing information, through the point cloud corresponding to the vehicle's surrounding environment at the current moment and the odometer information. Among them, the odometer information can include, for example: the steering information of the vehicle after startup, the number of rotations of the wheels, etc.

[0133] Optionally, when the vehicle-mounted sensing device obtains the point cloud corresponding to the vehicle's surrounding environment at the current moment and the odometer information, it can directly send the obtained point cloud corresponding to the vehicle's surrounding environment and the odometer information to the vehicle processing device, and the vehicle processing device processes the point cloud corresponding to the vehicle's surrounding environment and the odometer information to obtain the first sensing information. For example, the vehicle processing device extracts at least one feature point from the point cloud corresponding to the vehicle's surrounding environment, maps the coordinates of the feature point in the vehicle-mounted sensing device coordinate system to the vehicle body coordinate system, and determines the coordinates of at least one feature point in the vehicle body coordinate system.

[0134] Or, the vehicle-mounted sensing device performs preliminary processing on the obtained point cloud corresponding to the vehicle's surrounding environment and the odometer information, such as data format conversion, extraction of feature points in the point cloud, etc., and sends the preliminarily processed point cloud corresponding to the vehicle's surrounding environment and the odometer information obtained by the inertial detection unit at the current moment to the vehicle's processing device. The vehicle processing device obtains the first sensing information according to the preliminarily processed point cloud corresponding to the vehicle's surrounding environment and the inertial detection unit.

[0135] Or, the vehicle-mounted sensing device obtains the first sensing information according to the obtained point cloud corresponding to the vehicle's surrounding environment at the current moment and the odometer information, and then sends the first sensing information to the vehicle's processing device. In this way, when the vehicle is positioning, the vehicle processing device can directly use the first sensing information, reduce the processing amount of the vehicle processing device, and speed up the positioning speed of the vehicle processing device.

[0136] S202. Obtain the second sensing information obtained by the vehicle-mounted sensing device at a critical moment.

[0137] Among them, the second sensing information includes the coordinates of the feature points collected by the vehicle-mounted sensing device at the critical moment in the vehicle body coordinate system and the odometer information of the vehicle at the critical moment.

[0138] The critical moment includes the first critical moment, and the first critical moment is the moment when the second sensing information is obtained according to the time interval. The time interval between the critical moment and the current moment is less than or equal to the preset duration.

[0139] In this step, in the prior art, by setting a preset distance, when the vehicle travels each preset distance, the on-vehicle sensing device collects the environmental information and odometer information around the vehicle, so that the vehicle processing device obtains sensing information and performs positioning based on the sensing information obtained multiple times. However, road congestion causes the vehicle to travel slowly and the sensing information to be updated slowly. Moreover, due to road congestion, the environmental information around the vehicle is blocked by obstacles such as surrounding vehicles, which itself results in a small sensing range. Furthermore, in a congested section of the road, when obtaining sensing information according to the preset distance, sensing information is obtained only once when the vehicle travels each preset distance, resulting in even less valid information in the sensing information and affecting the accuracy of positioning. Herein, the valid information is the information in the sensing information that can improve the positioning accuracy.

[0140] Therefore, in this application, after the vehicle is started, the on-vehicle sensing device continuously obtains the point cloud and odometer information corresponding to the environment around the vehicle in the time dimension. For example, a collection time period is preset in advance, and when the collection time period arrives, the on-vehicle sensing device obtains the point cloud and odometer information corresponding to the environment around the vehicle once. Alternatively, according to the traveling speed of the vehicle, the time interval between two adjacent acquisitions of the point cloud and odometer information corresponding to the environment around the vehicle by the on-vehicle sensing device is adjusted. Correspondingly, for each time the on-vehicle sensing device obtains the point cloud and odometer information corresponding to the environment around the vehicle, the vehicle processing device obtains sensing information once.

[0141] At the current moment, the vehicle processing device obtains the sensing information corresponding to at least one critical moment, that is, the second sensing information. Herein, the critical moment here is the moment when the second sensing information is obtained according to the time interval. The time interval between each critical moment and the current moment is less than or equal to a preset duration.

[0142] For example, if the preset duration is 5 minutes, then the moments when the sensing device collects the environmental information and odometer information around the vehicle within 5 minutes before and at the current moment are critical moments. As Figure 4 shown, after the vehicle is started, the sensing device collects the environmental information and odometer information around the vehicle every 30S. In this way, the vehicle obtains sensing information every 30S. If the current moment is 10:00, then the sensing information obtained after 9:55 and before 10:00 is the sensing information corresponding to the critical moment. Among them, the vehicle reaches Figure 4 position 1 at 9:55, and the time interval between the moment when the vehicle reaches Figure 4 position 2 and the moment when the sensing device last collected the environmental information and odometer information around the vehicle is 30s, which is the time interval between critical moments. When the vehicle is at Figure 4 position 2, the sensing device collects the environmental information and odometer information around the vehicle, and the vehicle obtains a sensing information. Therefore, when the vehicle reaches 10:00Figure 4 At position 3 in Figure 4 the moment marked with "☆" after 9:55 and before 10:00.

[0143] Optionally, after the vehicle processing device obtains sensing information each time, save the sensing information. When obtaining the second sensing information at the current moment, the environmental information and odometer information around the vehicle can be collected according to the current moment and the moment when the sensing device corresponding to the saved sensing information is used, and the second sensing information can be obtained from the saved sensing information.

[0144] Optionally, when obtaining the second sensing information at the current moment, the second sensing information corresponding to each critical moment can be obtained from the critical moment list. For example, after the vehicle processing device obtains sensing information each time, save the sensing information, and according to the critical moment corresponding to the sensing information and the critical moment corresponding to each saved sensing information, delete the sensing information in the critical list whose time interval between the critical moments corresponding to the sensing information is greater than the preset duration, and update the critical moment list.

[0145] Optionally, the critical moment further includes a second critical moment, and the second critical moment is the moment when the second sensing information is obtained according to the distance interval, where the driving distance of the vehicle from the position at the second critical moment to the position corresponding to the current moment is less than or equal to the preset distance.

[0146] After the vehicle starts, the in-vehicle sensing device can continuously obtain the point cloud and odometer information corresponding to the surrounding environment of the vehicle according to the distance interval. For example, the preset distance interval for collection is 100 meters. Every time the vehicle travels 100 meters, the in-vehicle sensing device obtains the point cloud and odometer information corresponding to the surrounding environment of the vehicle once. Correspondingly, for each time the in-vehicle sensing device obtains the point cloud and odometer information corresponding to the surrounding environment of the vehicle, the vehicle processing device obtains sensing information once.

[0147] In this way, at the current moment, the vehicle processing device obtains the second sensing information corresponding to at least one second critical moment. For example, as Figure 5 shown, after the vehicle starts, the vehicle processing device obtains sensing information once every 100 meters the vehicle travels. The positions of the vehicle when the in-vehicle sensing device obtains the point cloud and odometer information corresponding to the surrounding environment of the vehicle respectively correspond to S1 - S7 in the figure. The preset distance is 500 meters. When the vehicle travels 50 meters from S7 to Figure 5 S8 in Figure 5 and the vehicle performs positioning, then the vehicle is located at Figure 5 S8 in

[0148] After the vehicle starts, the on-vehicle sensing device can continuously obtain the point cloud and odometer information corresponding to the vehicle's surrounding environment according to time intervals and distance intervals. For example, based on Figure 4 and Figure 5 , the on-vehicle sensor collects the environmental information and odometer information around the vehicle every 30 seconds. In this way, the vehicle obtains sensing information every 30 seconds, and the preset duration is 5 minutes. Also, every time the vehicle travels 100 meters, the on-vehicle sensor collects the environmental information and odometer information around the vehicle. In this way, the vehicle obtains sensing information every 100 meters traveled, and the preset distance is 500 meters. As Figure 6 shows, "○" represents the moment when the point cloud and odometer information corresponding to the vehicle's surrounding environment are obtained according to the time interval, and "●" represents the moment when the point cloud and odometer information corresponding to the vehicle's surrounding environment are obtained according to the distance interval.

[0149] Optionally, in actual applications, the moment when the on-vehicle sensing device obtains the point cloud and odometer information corresponding to the vehicle's surrounding environment according to the time interval and the moment when the on-vehicle sensing device obtains the point cloud and odometer information corresponding to the vehicle's surrounding environment according to the distance interval may be the same moment. Figure 6 In

[0150] "□" represents the moment when the on-vehicle sensing device continuously obtains the point cloud and odometer information corresponding to the vehicle's surrounding environment according to both the time interval and the distance interval. Figure 6 Corresponding to Figure 6 , the vehicle reaches position 1 in Figure 4 (i.e., position 1 in Figure 6 ) at 9:55:00. When it reaches position 2 in Figure 4 (i.e., position 2 in Figure 4 ), the sensing device collects the environmental information and odometer information around the vehicle. When the vehicle reaches S8 (i.e., position 3 in Figure 6 ) at 10:55:00, at the current moment, the moments corresponding to the first critical moment and the second critical moment are as

[0151] shown. The critical moment is the union of the first critical moment and the second critical moment.

[0152] S203. Determine the position of the vehicle at the current moment according to the map information of the vehicle's driving area and the first sensing information and the second sensing information.

[0153] In this step, after obtaining the first sensing information and at least one second sensing information, based on the first sensing information and at least one second sensing information, obtain the landmark information of the vehicle's surrounding environment at the current setting time, compare the landmark information with the map information of the vehicle's driving area, and obtain the position of the vehicle at the current time.

[0154] Optionally, the map information of the vehicle's driving area is the map information obtained based on the position during the previous positioning. For example, the map information of the vehicle's driving area is the map information obtained based on the position during the previous positioning.

[0155] When the vehicle starts, it initializes the position of the vehicle. For example, it locates the initial position of the vehicle through GPS or inputs the initial position of the vehicle. After initializing the position of the vehicle, based on the initial position of the vehicle, obtain the map information of the current area where the vehicle is located.

[0156] After the vehicle starts, the position of the vehicle changes, and the map of the area where it is located also changes. Therefore, after positioning the vehicle, it is necessary to update the map information according to the positioned position. In this way, compared with the map information before the update, the updated map information has a higher matching degree with the area where the vehicle is located. Therefore, during the next positioning, based on the updated map information, the position of the vehicle positioning can be more accurate.

[0157] Optionally, in S203, based on the map information of the vehicle's driving area and the first sensing information and the second sensing information, determine the pose of the vehicle at the current time.

[0158] Specifically, for the same target, different poses of the vehicle at the same position, for example, different orientations of the vehicle, result in different body coordinate systems. When the vehicle uses an on-vehicle sensing device, such as a lidar, to perform a laser scan on the target, when the same laser beam is directed at the target, since the position of the target in space is fixed, the coordinates of the feature points obtained by this laser beam are different in different body coordinate systems. Therefore, based on the map information of the vehicle's driving area and the first sensing information and at least one second sensing information, not only can the position of the vehicle at the current time be determined, but also the pose of the vehicle at this position can be determined.

[0159] For example Figure 7a and Figure 7b As shown, for the same roadside billboard, the information of the billboard collected by the vehicle in different poses at the same position. When the vehicle scans the billboard through the lidar in the first direction, according to the position of at least one feature point of the billboard collected in the first body coordinate system as Figure 7a shown. When the vehicle scans the billboard through the lidar in the second direction, according to the position of at least one feature point of the billboard collected in the second body coordinate system asFigure 7b as shown

[0160] When matching the billboards in the first vehicle body coordinate system and the billboards in the second vehicle body coordinate system with the billboards in the map information respectively, the first vehicle body coordinate system and the second vehicle body coordinate system can be determined respectively, and the attitude of the vehicle at this position can be determined according to the first vehicle body coordinate system and the second vehicle body coordinate system.

[0161] In this embodiment, after the vehicle starts, the sensing information of the vehicle is obtained according to the time interval. When the vehicle is positioned, the first sensing information corresponding to the current moment and the second sensing information corresponding to at least one critical moment are obtained, and the vehicle is positioned according to the first sensing information, at least one second sensing information and the map information. Since the sensing information is obtained from the time dimension, the process of obtaining the sensing information is not affected by road congestion. Therefore, when the vehicle is driving, the sensing information for positioning can be updated according to the time interval, improving the positioning accuracy. Moreover, when obtaining the sensing information from the time dimension, when the vehicle is driving at a low speed, the environmental information around the vehicle can be collected in the gap between vehicles. At this time, since the vehicle speed is slow, the environmental information around the vehicle collected is clearer, further improving the positioning accuracy.

[0162] Figure 8 is a flowchart of a positioning method provided by another embodiment of the present application. Based on the embodiment shown in Figure 2 as shown in Figure 8 as shown, the method of the embodiment of the present application includes:

[0163] S801. At the current moment, obtain the first sensing information through the vehicle-mounted sensing device.

[0164] In this step, the implementation manner of S801 can refer to S201, which will not be elaborated here.

[0165] S802. Obtain the second sensing information obtained through the vehicle-mounted sensing device at the critical moment.

[0166] In this step, the implementation manner of S802 can refer to S202, which will not be elaborated here.

[0167] S803. According to the odometer information in the first sensing information and the odometer information in the second sensing information, map the coordinates of the feature points collected at the critical moment to the vehicle body coordinate system at the current moment respectively, and obtain the coordinates of the feature points collected at the critical moment in the vehicle body coordinate system at the current moment.

[0168] In this step, when the vehicle is powered on, obtain the position of the vehicle at startup and activate the on-vehicle sensing device, such as an inertial measurement unit. After the vehicle starts, record the odometer information during the vehicle's driving process through the inertial measurement unit. For example, the steering information after the vehicle starts, the number of rotations of the wheels, the speed of the vehicle, etc.

[0169] Therefore, based on the odometer information of the vehicle, the relative position information of the vehicle's position when the odometer information is recorded relative to the vehicle's power-on position can be determined.

[0170] Therefore, the driving distance and rotation angle of the vehicle from the position at t1 to the position at t2 can be determined through the odometer information at t1 and the odometer information at t2. That is, through the odometer information at t1 and the odometer information at t2, the relative position information of the vehicle's position at t2 relative to the vehicle's position at t1 is determined.

[0171] Therefore, by according to the odometer information in the first sensing information and the odometer information in the second sensing information, the coordinates of at least one feature point collected at a critical moment can be respectively mapped to the vehicle body coordinate system at the current moment, and the coordinates of at least one feature point collected at the critical moment in the vehicle body coordinate system at the current moment are obtained.

[0172] Optionally, a specific implementation manner of S803 is:

[0173] S8031. Determine the coordinate mapping relationship between the vehicle body coordinate system corresponding to the current moment and the vehicle body coordinate system corresponding to the critical moment according to the mileage information in the first sensing information and the mileage information in the second sensing information.

[0174] In this step, the vehicle turns left when driving from the position at the critical moment to the position at the current moment, and the vehicle's left turn when driving from the position at the critical moment to the position at the current moment is recorded in the vehicle's odometer information. Therefore, the turning direction of the vehicle from the position at the critical moment to the position at the current moment and the driving distance of the vehicle's left turn from the position at the critical moment to the position at the current moment can be known through the odometer information at the critical moment and the odometer information at the current moment.

[0175] Therefore, through the odometer information at the current moment and the odometer information at the critical moment, the mapping matrix of the vehicle body coordinate system at t1 and the vehicle body coordinate system at the critical moment of the vehicle can be calculated. The calculation formula is, for example, Formula 1:

[0176] T key ×T key→cur =T cur Formula 1

[0177] Among them, Tkey represents the coordinate matrix of the vehicle body coordinate system of the vehicle at any critical moment relative to the vehicle's power-on position, T cur represents the coordinate matrix of the vehicle body coordinate system of the vehicle at the current moment relative to the vehicle's power-on position, T key→cur represents the mapping matrix of the vehicle body coordinate system of the vehicle at a critical moment relative to the vehicle body coordinate system at the current moment.

[0178] Therefore, based on the odometer information at the critical moment and the odometer information at the current moment, determine the coordinate mapping relationship between the vehicle body coordinate system corresponding to the current moment and the vehicle body coordinate system corresponding to the critical moment.

[0179] S8032. According to the coordinate mapping relationship, map the coordinates of the feature points collected at the first critical moment to the vehicle body coordinate system at the current moment respectively, and obtain the coordinates of the feature points collected at the first critical moment in the vehicle body coordinate system at the current moment.

[0180] In this step, according to Formula 1, it can be known that the mapping matrix For the feature points at one of the critical moments, the coordinates mapped to the vehicle body coordinate system at the current moment are obtained through Formula 2:

[0181] P cur = T key→cur × P key Formula 2

[0182] where, P cur represents the coordinates of one of the feature points at a critical moment in the vehicle body coordinate system at the current moment, and P key represents the coordinates of one of the feature points at a critical moment in the vehicle body coordinate system at the critical moment.

[0183] S804. According to the coordinates of the feature points collected at each critical moment and the coordinates of the feature points collected at the current moment in the vehicle body coordinate system at the current moment and the map information, determine the position of the vehicle at the current moment.

[0184] In this step, for the sensing information at any critical moment, map the coordinates of at least one feature point collected at this critical moment to the vehicle body coordinate system at the current moment according to the corresponding mapping matrix, so as to determine the position of the vehicle at the current moment based on the feature points in the vehicle body coordinate system at the current moment (including the feature points obtained by mapping at least one feature point collected at each critical moment to the vehicle body coordinate system at the current moment and at least one feature point collected at the current moment) and the map information.

[0185] Among them, since the coordinates of at least one feature point collected at a critical moment are mapped to the vehicle body coordinate system at the current moment according to the corresponding mapping matrix, the number of feature points at the current moment can be increased. In this way, the contour of the target object around the vehicle extracted by the feature points is clearer and closer to its true contour. Therefore, when positioning according to the map information, the degree of fit between the contour of the target object extracted by the feature points and the contour of the target object in the map information is higher, thereby improving the positioning accuracy.

[0186] Figure 9 The flowchart of the positioning method provided by another embodiment of the present application. On the basis of Figure 8 the embodiment shown, the method of the embodiment of the present application includes:

[0187] S901. At the current moment, obtain first sensing information through an on-vehicle sensing device.

[0188] In this step, the implementation manner of S901 can refer to S201, which will not be elaborated here.

[0189] S902. Obtain second sensing information obtained through the on-vehicle sensing device at a critical moment.

[0190] In this step, the implementation manner of S902 can refer to S202, which will not be elaborated here.

[0191] S903. According to the odometer information in the second sensing information and the odometer information in the second sensing information, map the coordinates of the feature points collected at the critical moment to the vehicle body coordinate system at the current moment, and obtain the coordinates of the feature points collected at the critical moment in the vehicle body coordinate system at the current moment.

[0192] In this step, the implementation manner of S903 can refer to S803, which will not be elaborated here.

[0193] S904. At the current moment, for each of the M particles corresponding to the vehicle, obtain the matching degree between the feature points collected at the current moment and the critical moment and the target object in the map information according to the coordinates of the feature points collected at the critical moment and the current moment in the vehicle body coordinate system at the current moment and the position of each particle.

[0194] Among them, the M particles are the particles used for the previous vehicle positioning. The position of each particle is obtained according to the odometer information at the previous vehicle positioning, the odometer information at the current moment, and the position of each particle at the previous vehicle positioning. M is a positive integer.

[0195] In this step, when positioning the vehicle, the framework of particle filtering can be used. Specifically:

[0196] Such as Figure 10As shown, when the vehicle just starts, obtain the initial position of the vehicle, and arrange some particles around the vehicle, that is, initialize the particles. For example, the positions of the initialized particles satisfy a normal distribution. Among them, each particle is used to simulate the vehicle, and the position of the particle simulates the position of the vehicle, and record the position of each particle. At this time, the position of the particle is the initialized position.

[0197] After the vehicle starts, the movement process of each particle is consistent with the movement process of the vehicle. The movement information of the vehicle from one position to another can be determined through the odometer information of the vehicle. For example, the distance traveled by the vehicle, the direction of turning during the driving process, etc. Therefore, according to the odometer information of the vehicle, the movement process of the particle can be predicted, and thus the position of the particle can be predicted.

[0198] For the M particles at the current moment, where the M particles are the particles used for vehicle positioning last time, determine the position of each particle at the current moment according to the position of each particle among the M particles during the last vehicle positioning, the odometer information of the vehicle during the last positioning, and the odometer information of the current moment.

[0199] At the current moment, according to the feature points in the vehicle body coordinate system at the current moment (including the feature points obtained by mapping at least one feature point collected at each critical moment to the vehicle body coordinate system at the current moment and at least one feature point collected at the current moment), the environmental information around the vehicle at the current moment can be determined, that is, the landmark information around the vehicle can be extracted according to the feature points in the vehicle body coordinate system at the current moment. For example, the target objects to be matched around the vehicle, and the position of the target objects to be matched relative to the vehicle.

[0200] Among them, the feature points in the vehicle body coordinate system at the current moment are actually the feature points collected by the lidar when the vehicle is at the real position. Therefore, the target objects to be matched around the vehicle obtained according to the feature points in the vehicle body coordinate system at the current moment are actually the target objects to be matched viewed from the real position of the vehicle. The coordinates of the target objects to be matched in the vehicle body coordinate system are actually the relative positions of the target objects to be matched relative to the real position of the vehicle. Therefore, in the optimal case, the target objects to be matched extracted from the feature points in the vehicle body coordinate system at the current moment are completely matched with the target objects in the map information.

[0201] Therefore, since each particle simulates the real position of the vehicle, and the odometer information recorded in the vehicle cannot truthfully reflect the real movement process of the vehicle. For example, there is a certain difference between the driving distance of the vehicle obtained according to the odometer information and the actual driving distance of the vehicle. Therefore, when determining the position of the particle at the current moment according to the odometer information, there is a difference between the position of the particle and the real position of the vehicle.

[0202] Therefore, for each particle, based on the feature points in the vehicle body coordinate system at the current moment and the position of the particle at the current moment, the difference between the position of the particle and the true position of the vehicle can be determined by the matching degree between the target object to be matched extracted from the feature points in the vehicle body coordinate system at the current moment and the target object in the map information.

[0203] Optionally, a specific implementation manner of S904 is as follows:

[0204] S9041. Map the coordinates of the feature points collected at the current moment and the critical moment in the vehicle body coordinate system at the current moment to the particle coordinate system with the particle as the origin.

[0205] Specifically, select each particle one by one. For each particle, replace the vehicle body coordinate system at the current moment with the particle coordinate system with the particle as the coordinate origin, map the feature points in the vehicle body coordinate system at the current moment to the particle coordinate system, and obtain the coordinates of the feature points in the vehicle body coordinate system at the current moment mapped to the particle coordinate system.

[0206] Among them, the particle coordinate system can be a plane coordinate system, such as a plane rectangular coordinate system or a polar coordinate system, or a space coordinate system, such as a space rectangular coordinate system, a cylindrical coordinate system, or a spherical coordinate system. The present application does not limit this. Among them, this embodiment is described by taking the space rectangular coordinate system as an example.

[0207] Optionally, the vehicle body coordinate system and the particle coordinate system can be of the same type of coordinate system. For example, both the vehicle body coordinate system and the particle coordinate system are space rectangular coordinate systems. Or, the vehicle body coordinate system and the particle coordinate system can be of different types of coordinate systems. For example, the vehicle body coordinate system is a space rectangular coordinate system, and the particle coordinate system is a spherical coordinate system. The embodiments of the present application do not limit this.

[0208] S9042. Obtain the matching degree between the target object to be matched formed by the feature points collected at the current moment and the critical moment mapped to the particle coordinate system and the corresponding target object in the map information.

[0209] Specifically, according to the feature points collected at the current moment and at least one critical moment mapped to the particle coordinate system, extract the target object to be matched around the vehicle at the current moment, determine the position of the particle in the map information corresponding to the position of the particle, use the position of the particle in the map information as the coordinate origin, match the target object to be matched with the corresponding target object in the map information, and determine the matching degree between the target object to be matched and the corresponding target object in the map information according to the coincidence degree between the target object to be matched and the corresponding target object in the map information.

[0210] Since the movement of the particles is consistent with the movement of the vehicle, if the position of the particles is closer to the true position of the vehicle, the higher the matching degree between the target object to be matched formed by the feature points in the vehicle body coordinate system at the current moment mapped to the particle coordinate system and the corresponding target object in the map information.

[0211] As Figure 11 shown, the vehicle coordinate system and the particle coordinate system are spatial rectangular coordinate systems (the spatial rectangular coordinate system is not shown in Figure 11 ). In the map information, the true position of the vehicle is point O, and the position of one of the particles is point O1. For the roadside billboard, the billboard and its position formed by the feature points in the vehicle body coordinate system at the current moment are as Figure 11 shown by the solid line in. Among them, the billboard shown by the solid line coincides with the billboard in the map information.

[0212] After mapping the feature points in the vehicle body coordinate system at the current moment to the particle coordinate system, the billboard and its position formed by the feature points are as Figure 11 shown by the dotted line in.

[0213] If the position of the particle is the true position of the vehicle, then Figure 11 in, the position of the billboard shown by the solid line coincides with the position of the billboard shown by the dotted line. The matching degree of the particle is determined according to the distance between the position of the billboard shown by the solid line and the position of the billboard shown by the dotted line. The smaller the distance, the higher the matching degree.

[0214] Optionally, mapping at least one feature point collected at each critical moment to the vehicle body coordinate system at the current moment results in a large number of feature points in the vehicle body coordinate system at the current moment. Moreover, when collecting the environmental information around the vehicle at different critical moments, duplicate feature points will be collected, thus increasing the calculation amount and affecting the positioning efficiency. Therefore, before S904, it further includes:

[0215] S1001. Determine the target feature points according to the feature values of the at least one feature point collected at each critical moment and the feature points collected at the current moment.

[0216] In this step, stable and representative target feature points are selected from the feature points in the vehicle body coordinate system at the current moment (including the feature points obtained by mapping at least one feature point collected at each critical moment to the vehicle body coordinate system at the current moment and at least one feature point collected at the current moment), and the target feature points are saved. On the basis of reducing the number of feature points, the environmental information around the vehicle extracted through the target feature points is close to the environmental information around the vehicle extracted through the feature points in the vehicle body coordinate system at the current moment.

[0217] Optionally, calculate the eigenvalue of each feature point among the feature points in the vehicle body coordinate system at the current moment according to the evaluation function, and select one or more feature points as target feature points according to the eigenvalues of each feature point.

[0218] Optionally, calculate the eigenvalue of each feature point among the feature points in the vehicle body coordinate system at the current moment according to the evaluation function, and select one or more feature points with the largest eigenvalue as target feature points according to the magnitudes of the eigenvalues.

[0219] S1002. Determine the target feature points again according to the feature points collected at each critical moment and the eigenvalues of the feature points other than the feature points included in the feature point set among the feature points collected at the current moment.

[0220] Among them, the feature points included in the feature point set are the feature points located within the preset distance range of the target feature points determined last time and the target feature points determined last time.

[0221] In this step, after determining the target feature points through S1001, since the target feature points have stability and representativeness, therefore, to reduce the number of feature points, the feature points within the preset distance range of the target feature points and the target feature points can be deleted among the feature points in the vehicle body coordinate system at the current moment to obtain the feature point set.

[0222] Then, repeat S1001 and S1002 to determine the target feature points again from the feature point set, and obtain a new feature point set according to the target feature points determined again.

[0223] S1003. When the number of target feature points meets the preset number, obtain N target feature points, where N is equal to the preset number.

[0224] In this step, when the number of target feature points meets the preset number, stop obtaining new target feature points, and position the vehicle according to the currently obtained target feature points.

[0225] S905. Obtain K particles according to the matching degree of each of the M particles at the current moment and the M particles.

[0226] Among them, K is a positive integer.

[0227] In this step, although the movement process of the particles is consistent with that of the vehicle, the odometer information recorded in the vehicle cannot accurately reflect the actual movement process of the vehicle. For example, there is a certain difference between the driving distance of the vehicle obtained from the odometer information and the actual driving distance of the vehicle. Therefore, when determining the position of the particles at the current moment based on the odometer information, the position of the particles relative to the vehicle at the current moment is different from the position of the particles relative to the vehicle at the previous positioning. Therefore, the matching degree of the particles changes with the movement of the vehicle. That is to say, the particles with a high matching degree at the previous time may have a lower matching degree at the current moment.

[0228] Therefore, it is necessary to resample the particles according to the matching degree of each particle among the M particles, that is, to re-determine the K particles used for vehicle positioning.

[0229] Optionally, the matching degree of the particles represents the degree of proximity between the position of the particles and the actual position of the vehicle. The higher the matching degree, the closer the position of the particles is to the actual position of the vehicle. Therefore, select the particles with a higher matching degree among the M particles and determine them as the K particles. For example, set a preset matching degree, obtain L particles among the M particles whose matching degree is greater than or equal to the preset matching degree, and determine them as the K particles.

[0230] Optionally, after obtaining L particles among the M particles whose matching degree is greater than or equal to the preset matching degree, at least one particle can be selected from the L particles, and based on the L particles and the at least one selected particle, K particles can be obtained.

[0231] Optionally, after selecting at least one particle from the L particles, the particles can be replicated at least once according to the matching degree of each particle in the at least one particle, that is, the number of particles is increased. For example, the higher the matching degree of the particle, the more the number of the particle after the increase. Based on the L particles and the particles obtained by the increase, K particles can be obtained.

[0232] S906. Obtain the position of the vehicle at the current moment according to the positions of the K particles corresponding to the vehicle at the current moment.

[0233] In this step, since the position of each particle simulates the actual position of the vehicle, therefore, at the current moment, the position of the vehicle at the current moment can be determined according to the positions of the K particles.

[0234] Optionally, according to the positions of the K particles, obtain the average position of the K particles, and determine the average position of the K particles as the position of the vehicle at the current moment.

[0235] Optionally, according to the positions of the K particles and the matching degree of each particle, obtain the weighted average position of the K particles, and determine the weighted average position of the K particles as the position of the vehicle at the current moment.

[0236] At the next positioning of the vehicle, the K particles determined at the current moment replace the M particles in S1004, and the above steps are repeated to position the vehicle.

[0237] Optionally, based on the positions of the K particles, the position of the vehicle obtained at the current moment is not the real position of the vehicle at the current moment. Therefore, if the difference between the position of the vehicle obtained based on the positions of the K particles and the real position of the vehicle at the current moment is large, there will be potential safety hazards. Therefore, the method of the embodiment of the present application further includes:

[0238] S907. Obtain an evaluation value of the position of the vehicle at the current moment according to the position of each particle among the K particles corresponding to the vehicle at the current moment and the position of the vehicle at the current moment.

[0239] Among them, the evaluation value represents the difference between the position of the vehicle at the current moment and the real position information of the vehicle at the current moment.

[0240] In this step, calculate the distribution variance of the K particles according to the position of each particle among the K particles corresponding to the vehicle at the current moment and the position of the vehicle at the current moment, and obtain the evaluation value of the position of the vehicle at the current moment according to the distribution variance. For example, determine the distribution variance as the evaluation value of the position of the vehicle at the current moment. The larger the distribution variance, the greater the difference between the position of the vehicle at the current moment and the real position of the vehicle. Therefore, according to the evaluation value, it can be determined whether to remotely control the vehicle or activate other positioning devices to position the vehicle.

[0241] Figure 12 It is a schematic structural diagram of a positioning device provided by an embodiment of the present application. As Figure 12 shown, the positioning device can be the above vehicle, or a component of the vehicle (for example, an integrated circuit, a chip, etc.). The positioning device can also be a server, for example, a cloud server, or a component of the server (for example, an integrated circuit, a chip, etc.). The positioning device can also be other communication modules for implementing the method in the method embodiment of the present application and the above optional embodiments. The positioning device may include: an acquisition module 1201 and a positioning module 1202.

[0242] The acquisition module 1201 is used to execute:

[0243] Figure 2 S201, S202 in the embodiment shown, and any optional embodiment of S201, S202, Figure 8 S801, S802 in the embodiment shown, and any optional embodiment of S801, S802. For specific details, refer to the detailed description in the method examples, which will not be elaborated here.

[0244] The positioning module 1202 is used to execute:

[0245] Figure 2 S203 in the illustrated embodiment and any optional embodiment thereof, Figure 8 S803, S804 in the illustrated embodiment and any optional embodiment of S803, S804, Figure 9 S903 - S907 in the illustrated embodiment and any optional embodiment of S903 - S907. For specific details, refer to the detailed description in the method examples and will not be elaborated here.

[0246] Among them, the acquisition module 1201 is used to obtain first sensing information through the vehicle-mounted sensing device at the current moment. The first sensing information includes the coordinates of the feature points collected by the vehicle-mounted sensing device in the vehicle body coordinate system at the current moment and the odometer information of the vehicle at the current moment.

[0247] The acquisition module 1201 is further used to obtain second sensing information obtained through the vehicle-mounted sensing device at a critical moment. The second sensing information includes the coordinates of the feature points collected by the vehicle-mounted sensing device in the vehicle body coordinate system at the critical moment and the odometer information of the vehicle at the critical moment. Among them, the critical moment includes a first critical moment, and the first critical moment is the moment when the second sensing information is obtained according to the time interval, and the time interval between the first critical moment and the current moment is less than or equal to a preset duration.

[0248] The positioning module 1202 is used to determine the position of the vehicle at the current moment according to the map information of the vehicle driving area and the first sensing information and the second sensing information.

[0249] It should be understood that the positioning device in the embodiments of the present application can be implemented by software. For example, it can be implemented by a computer program or instruction with the above functions. The corresponding computer program or instruction can be stored in the memory inside the terminal, and the above functions can be implemented by the processor reading the corresponding computer program or instruction in the memory.

[0250] Alternatively, the positioning device in the embodiments of the present application can also be implemented by hardware. Among them, the acquisition module 1201 and the positioning module 1202 are processors (such as the processors in NPU, GPU, and system chips).

[0251] Alternatively, the positioning device in the embodiments of the present application can also be implemented by the combination of a processor and a software module.

[0252] Optionally, the positioning module 1202 is further used to map the coordinates of the feature points collected at the critical moment to the vehicle body coordinate system at the current moment according to the odometer information in the first sensing information and the odometer information in the second sensing information, and obtain the coordinates of the feature points collected at the critical moment in the vehicle body coordinate system at the current moment.

[0253] Determine the position of the vehicle at the current moment based on the coordinates of the feature points collected at the critical moment and the current moment in the vehicle body coordinate system at the current moment and the map information.

[0254] Optionally, the positioning module 1202 is further configured to, at the current moment, for each of the M particles corresponding to the vehicle, obtain the matching degree between the feature points collected at the critical moment and the current moment and the target object in the map information according to the coordinates of the feature points collected at the critical moment and the current moment in the vehicle body coordinate system at the current moment and the position of each particle, where the above M particles are the particles used for the previous vehicle positioning, and the position of each particle is obtained according to the odometer information at the previous vehicle positioning, the odometer information at the current moment, and the position of each particle at the previous vehicle positioning, and M is a positive integer;

[0255] Obtain K particles according to the matching degree of each of the M particles at the current moment and the M particles, where K is a positive integer;

[0256] Obtain the position of the vehicle at the current moment according to the positions of the K particles corresponding to the vehicle at the current moment.

[0257] Optionally, the positioning module 1202 is further configured to map the coordinates of the feature points collected at the current moment and the critical moment in the vehicle body coordinate system at the current moment to the particle coordinate systems with each particle as the origin;

[0258] Obtain the matching degree between the target object to be matched formed by the feature points collected at the current moment and the critical moment mapped to each particle coordinate system and the corresponding target object in the map information.

[0259] Optionally, the positioning module 1202 is further configured to obtain L particles among the M particles whose matching degree is greater than or equal to a preset matching degree, where L is less than or equal to M and less than or equal to K;

[0260] Determine the L particles as the K particles; or,

[0261] Obtain at least one particle from the L particles;

[0262] Obtain K particles according to the L particles and the at least one particle.

[0263] Optionally, the positioning module 1202 is further configured to perform at least one replication on each particle according to the matching degree of each particle in the at least one particle;

[0264] Determine the L particles and the particles obtained after replication as the K particles.

[0265] Optionally, the positioning module 1202 is further configured to obtain the average position of the K particles according to the positions of each of the K particles, and determine the average position of the K particles as the position of the vehicle at the current moment.

[0266] Optionally, the positioning module 1202 is further configured to obtain an evaluation value of the position of the vehicle at the current moment according to the position of each of the K particles corresponding to the vehicle at the current moment and the position of the vehicle at the current moment. The evaluation value indicates the difference between the position of the vehicle at the current moment and the true position information of the vehicle at the current moment.

[0267] Optionally, the positioning module 1202 is further configured to determine the coordinate mapping relationship between the vehicle body coordinate system corresponding to the current moment and the vehicle body coordinate system corresponding to the first critical moment according to the mileage information in the first sensing information and the mileage information in the second sensing information;

[0268] According to the coordinate mapping relationship, map the coordinates of the feature points collected at the first critical moment to the vehicle body coordinate system at the current moment respectively, and obtain the coordinates of the feature points collected at the first critical moment in the vehicle body coordinate system at the current moment.

[0269] Optionally, the critical moment further includes a second critical moment, which is the moment when the second sensing information is obtained according to the distance interval, where the driving distance of the vehicle from the position at the second critical moment to the position corresponding to the current moment is less than or equal to a preset distance.

[0270] Optionally, the positioning module 1202 is further configured to determine the pose of the vehicle at the current moment according to the map information and the first sensing information and the second sensing information.

[0271] Optionally, the positioning module 1202 is further configured to determine target feature points according to the feature values of the feature points collected at each critical moment and the feature points collected at the current moment.

[0272] According to the feature values of the feature points collected at each critical moment and the feature points other than the feature points included in the feature point set among the feature points collected at the current moment, determine the target feature points again. The feature points included in the feature point set are the feature points located within the preset distance range of the target feature point determined last time and the target feature point determined last time;

[0273] When the number of target feature points meets the preset number, obtain N target feature points, where N is equal to the preset number;

[0274] Correspondingly, the positioning module 1202 is further configured to obtain the matching degree between the feature points collected at the current moment and the critical moment and the target object in the map information of the target area according to the coordinates of the N target feature points in the vehicle body coordinate system at the current moment and the position of each particle.

[0275] Optionally, the eigenvalue of the feature point is obtained through an evaluation function, and the eigenvalue is used to evaluate the stability of the feature point.

[0276] Optionally, the target feature point is the feature point with the largest eigenvalue among all feature points.

[0277] Optionally, the origin of the vehicle body coordinate system is located at any position on the vehicle in question.

[0278] The device in this embodiment can be used to execute the technical solutions in the above method embodiments. The implementation principles and technical effects are similar, and will not be elaborated here.

[0279] Figure 13 The figure is a schematic structural diagram of a positioning device provided by an embodiment of the present application. The positioning device in this embodiment can be a vehicle as described above, or a server. The positioning device can be used to implement the method described in the above method embodiments. For details, reference can be made to the descriptions in the above method embodiments.

[0280] The positioning device may include one or more processors 1301. The processor 1301, also known as a processing unit, can implement certain control functions. The processor 1301 can be a general-purpose processor or a dedicated processor, etc.

[0281] Optionally, the processor 1301 may also store instructions and / or data 1303, and the instructions and / or data 1303 can be run by the processor, so that the positioning device executes the method described in the above method embodiments.

[0282] Optionally, the positioning device may include one or more memories 1302, on which instructions 1304 may be stored. The instructions can be run on the processor, so that the positioning device executes the method described in the above method embodiments. Optionally, data may also be stored in the memory. Optionally, instructions and / or data may also be stored in the processor. The processor and the memory can be set separately or integrated together. For example, the corresponding relationships described in the above method embodiments can be stored in the memory or in the processor.

[0283] The processor and transceiver described in this embodiment can be manufactured using various IC process technologies, such as complementary metal oxide semiconductor (CMOS), N-type metal oxide semiconductor (NMOS), P-type metal oxide semiconductor (PMOS), bipolar junction transistor (BJT), BiCMOS, silicon germanium (SiGe), gallium arsenide (GaAs), etc.

[0284] It should be understood that the processor in the embodiments of the present application can be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method embodiments can be completed by the integrated logic circuit in the hardware of the processor or instructions in software form. The above-mentioned processor can be a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0285] It can be understood that the memory in the embodiments of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0286] The scope of the positioning device described in the embodiments of the present application is not limited thereto, and the structure of the positioning device can be unrestricted Figure 13 by. The positioning device described in the embodiments of the present application can be an independent device or can be a part of a larger device.

[0287] Figure 14 It is a schematic structural diagram of a positioning system provided by an embodiment of the present application. As Figure 14 shown, the positioning system includes: a vehicle 1401 and an in-vehicle sensing device 1402.

[0288] The in-vehicle sensing device 1402 is installed on the vehicle 1401 and communicates with the vehicle 1401.

[0289] Optionally, the in-vehicle sensing device 1402 is configured to collect environmental information and odometer information around the vehicle 1401 and send the environmental information and odometer information around the vehicle 1401 to the vehicle 1401.

[0290] A vehicle 1401 configured to execute the method described in the above method embodiments.

[0291] Optionally, an on-vehicle sensing device 1402 configured to collect environmental information and odometer information around the vehicle 1401, send the environmental information and odometer information around the vehicle 1401 to the vehicle 1401, and execute the method described in the above method embodiments to perform positioning on the vehicle 1401.

[0292] The system of this embodiment can be used to execute the technical solutions in any of the above method embodiments. The implementation principles and technical effects are similar and will not be elaborated here.

[0293] This application also provides a computer-readable medium having a computer program stored thereon. When the computer program is executed by a computer, the method shown in any of the above method embodiments is implemented.

[0294] This application also provides a computer program product which, when executed by a computer, implements the method shown in any of the above method embodiments.

[0295] When implemented using software in the above embodiments, it may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, the processes or functions described in the embodiments of this application are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that includes one or more integrated available media. The available media may be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as high-density digital video discs (DVDs)), or semiconductor media (such as solid state disks (SSDs)), etc.

Claims

1. A positioning method, characterized in that, Including: At the current moment, first sensing information is obtained through an in-vehicle sensing device, where the first sensing information includes the coordinates of feature points collected by the in-vehicle sensing device at the current moment in the vehicle body coordinate system and the odometer information of the vehicle at the current moment; Second sensing information obtained through the in-vehicle sensing device at a critical moment is acquired, where the second sensing information includes the coordinates of feature points collected by the in-vehicle sensing device at the critical moment in the vehicle body coordinate system and the odometer information of the vehicle at the critical moment. Among them, the critical moment includes a first critical moment, and the first critical moment is the moment when the second sensing information is obtained according to a time interval, and the time interval between the first critical moment and the current moment is less than or equal to a preset duration; According to the odometer information in the first sensing information and the odometer information in the second sensing information, the coordinate mapping relationship between the vehicle body coordinate system corresponding to the current moment and the vehicle body coordinate system corresponding to the first critical moment is determined; According to the coordinate mapping relationship, the coordinates of the feature points collected at the first critical moment are respectively mapped to the vehicle body coordinate system at the current moment, and the coordinates of the feature points collected at the first critical moment in the vehicle body coordinate system at the current moment are obtained; According to the coordinates of the feature points collected at the critical moment and the feature points collected at the current moment in the vehicle body coordinate system at the current moment and the map information, the position of the vehicle at the current moment is determined.

2. The method according to claim 1, characterized in that, The step of determining the position of the vehicle at the current moment according to the coordinates of the feature points collected at the critical moment and the feature points collected at the current moment in the vehicle body coordinate system at the current moment and the map information includes: At the current moment, for each of the M particles corresponding to the vehicle, according to the coordinates of the feature points collected at the critical moment and the feature points collected at the current moment in the vehicle body coordinate system at the current moment and the position of each particle, the matching degree between the feature points collected at the current moment and the critical moment and the target object in the map information is obtained. Among them, the M particles are the particles used in the previous vehicle positioning, and the position of each particle is obtained according to the odometer information at the previous vehicle positioning, the odometer information at the current moment, and the position of each particle at the previous vehicle positioning. M is a positive integer; According to the matching degree of each of the M particles at the current moment and the M particles, K particles are obtained, where K is a positive integer; According to the positions of the K particles corresponding to the vehicle at the current moment, the position of the vehicle at the current moment is obtained.

3. The method according to claim 2, characterized in that, The step of obtaining the matching degree between the feature points collected at the current moment and the critical moment and the target object in the map information according to the coordinates of the feature points collected at the critical moment and the feature points collected at the current moment in the vehicle body coordinate system at the current moment and the position of each particle includes: Map the coordinates of the feature points collected at the current moment and the critical moment in the vehicle body coordinate system at the current moment to the particle coordinate system with the particle as the origin respectively; Obtain the matching degree between the target object to be matched formed by the feature points collected at the current moment and the critical moment mapped to the particle coordinate system and the corresponding target object in the map information.

4. The method according to claim 2, wherein The obtaining of the K particles according to the matching degrees of each of the M particles at the current moment and the M particles includes: Obtain L particles among the M particles whose matching degrees are greater than or equal to a preset matching degree, where L is less than or equal to M and less than or equal to K; Determine the L particles as the K particles; or, Obtain at least one particle from the L particles; Obtain the K particles according to the L particles and the at least one particle.

5. The method according to claim 4, characterized in that The obtaining of the K particles according to the L particles and the at least one particle includes: According to the matching degree of each particle in the at least one particle, perform at least one replication on each particle; Determine the L particles and the particles obtained after replication as the K particles.

6. The method according to any one of claims 2-5, characterized in that, The obtaining of the position of the vehicle at the current moment according to the positions of the K particles corresponding to the vehicle at the current moment includes: According to the position of each of the K particles, obtain the average position of the K particles, and determine the average position of the K particles as the position of the vehicle at the current moment.

7. The method according to any one of claims 2-5, characterized in that, The method further includes: According to the position of each of the K particles corresponding to the vehicle at the current moment and the position of the vehicle at the current moment, obtain an evaluation value of the position of the vehicle at the current moment, where the evaluation value indicates the difference between the position of the vehicle at the current moment and the true position information of the vehicle at the current moment.

8. The method according to any one of claims 1-5, characterized in that The critical moment further includes a second critical moment, which is the moment for obtaining second sensing information according to a distance interval, where the driving distance of the vehicle from the position at the second critical moment to the position corresponding to the current moment is less than or equal to a preset distance.

9. The method according to any one of claims 1-5, characterized in that The determining of the position of the vehicle at the current moment according to the map information of the vehicle driving area and the first sensing information and the second sensing information includes: Determine the pose of the vehicle at the current moment according to the map information and the first sensing information and the second sensing information.

10. The method according to claim 2, wherein Before obtaining the matching degrees between the feature points collected at the current moment and the critical moment and the target object in the map information according to the coordinates of the feature points collected at the critical moment and the current moment in the vehicle body coordinate system at the current moment and the position of each particle, it further includes: Determine the target feature points according to the feature values of each feature point among the feature points collected at each critical moment and the feature points collected at the current moment. Based on the characteristic points collected at each critical moment and the characteristic values of the characteristic points other than those included in the characteristic point set among the characteristic points collected at the current moment, the target characteristic points are determined again. The characteristic points included in the characteristic point set are the characteristic points located within a preset distance range of the target characteristic points determined last time and the target characteristic points determined last time; When the number of the target characteristic points meets the preset number, N target characteristic points are obtained, and N is equal to the preset number; Obtaining the matching degrees of the characteristic points collected at the current moment and the critical moment with the target objects in the map information based on the coordinates of the characteristic points collected at the critical moment and the current moment in the vehicle body coordinate system at the current moment and the position of each particle includes: Based on the coordinates of the N target characteristic points in the vehicle body coordinate system at the current moment and the position of each particle, the matching degrees of the characteristic points collected at the current moment and the critical moment with the target objects in the map information of the target area are obtained.

11. The method according to claim 10, wherein The characteristic values of the characteristic points are obtained through an evaluation function, and the characteristic values are used to evaluate the stability of the characteristic points.

12. The method according to claim 10 or 11, characterized in that, The target characteristic points are the characteristic points with the largest characteristic values among all the characteristic points.

13. The method according to any one of claims 1-5, 10-11, characterized in that, The origin of the vehicle body coordinate system is located at any position on the vehicle.

14. A positioning device, characterized in that, Including: An acquisition module, configured to obtain first sensing information through a vehicle-mounted sensing device at the current moment. The first sensing information includes the coordinates of the characteristic points collected by the vehicle-mounted sensing device at the current moment in the vehicle body coordinate system and the odometer information of the vehicle at the current moment; The acquisition module is further configured to obtain second sensing information obtained through the vehicle-mounted sensing device at a critical moment. The second sensing information includes the coordinates of the characteristic points collected by the vehicle-mounted sensing device at the critical moment in the vehicle body coordinate system and the odometer information of the vehicle at the critical moment, where the critical moment includes a first critical moment, and the first critical moment is the moment when the second sensing information is obtained according to a time interval, and the time interval between the first critical moment and the current moment is less than or equal to a preset duration; A positioning module, configured to determine the coordinate mapping relationship between the vehicle body coordinate system corresponding to the current moment and the vehicle body coordinate system corresponding to the first critical moment according to the odometer information in the first sensing information and the odometer information in the second sensing information; According to the coordinate mapping relationship, the coordinates of the characteristic points collected at the first critical moment are respectively mapped to the vehicle body coordinate system at the current moment to obtain the coordinates of the characteristic points collected at the first critical moment in the vehicle body coordinate system at the current moment; Based on the coordinates of the characteristic points collected at the critical moment and the current moment in the vehicle body coordinate system at the current moment and the map information, determine the position of the vehicle at the current moment.

15. The device according to claim 14, wherein When the positioning module determines the position of the vehicle at the current moment based on the coordinates of the characteristic points collected at the critical moment and the current moment in the vehicle body coordinate system at the current moment and the map information, it specifically is used for: At the current moment, for each of the M particles corresponding to the vehicle, obtain the matching degrees of the feature points collected at the critical moment and the feature points collected at the current moment with the target objects in the map information based on the coordinates of the feature points collected at the critical moment and the current moment in the vehicle body coordinate system at the current moment and the position of each particle, where the M particles are the particles used in the previous vehicle positioning, the position of each particle is obtained based on the odometer information in the previous vehicle positioning, the odometer information at the current moment, and the position of each particle in the previous vehicle positioning, and M is a positive integer; Obtain K particles based on the matching degrees of each of the M particles at the current moment and the M particles, where K is a positive integer; Obtain the position of the vehicle at the current moment based on the positions of the K particles corresponding to the vehicle at the current moment.

16. The device according to claim 15, characterized in that, When the positioning module obtains the matching degrees of the feature points collected at the current moment and the critical moment with the target objects in the map information based on the coordinates of the feature points collected at the critical moment and the current moment in the vehicle body coordinate system at the current moment and the position of each particle, it specifically is used for: Map the coordinates of the feature points collected at the current moment and the critical moment in the vehicle body coordinate system at the current moment to the particle coordinate system with the particle as the origin; Obtain the matching degrees of the target object to be matched formed by the feature points collected at the current moment and the critical moment mapped to the particle coordinate system with the corresponding target objects in the map information.

17. The device according to claim 15, characterized in that, When the positioning module obtains K particles based on the matching degrees of each of the M particles at the current moment and the M particles, it specifically is used for: Obtain L particles among the M particles whose matching degrees are greater than or equal to a preset matching degree, where L is less than or equal to M and less than or equal to K; Determine the L particles as the K particles; or, Obtain at least one particle from the L particles; Obtain the K particles based on the L particles and the at least one particle.

18. The device according to claim 17, characterized in that, When the positioning module obtains the K particles based on the L particles and the at least one particle, it specifically is used for: Perform at least one replication on each particle according to the matching degree of each particle in the at least one particle; Determine the L particles and the particles obtained after replication as the K particles.

19. The device according to any one of claims 15-18, characterized in that, When obtaining the position of the vehicle at the current moment based on the positions of the K particles corresponding to the vehicle at the current moment by the positioning module, it specifically is used for: Obtain the average position of the K particles according to the position of each particle in the K particles, and determine the average position of the K particles as the position of the vehicle at the current moment.

20. The device according to any one of claims 15 - 18, characterized in that, The positioning module is further used for: Based on the positions of each of the K particles corresponding to the vehicle at the current moment and the position of the vehicle at the current moment, an evaluation value of the position of the vehicle at the current moment is obtained, and the evaluation value indicates the difference between the position of the vehicle at the current moment and the true position information of the vehicle at the current moment.

21. The device according to any one of claims 14-18, characterized in that, The critical moment further includes a second critical moment, which is the moment for obtaining second sensing information according to a distance interval, wherein the driving distance of the vehicle from the position at the second critical moment to the position corresponding to the current moment is less than or equal to a preset distance.

22. The device according to any one of claims 14-18, characterized in that, When the positioning module determines the position of the vehicle at the current moment according to the map information of the vehicle driving area and the first sensing information and the second sensing information, it is specifically used for: Determine the pose of the vehicle at the current moment according to the map information, the first sensing information, and the second sensing information.

23. The device according to claim 15, characterized in that, Before the positioning module obtains the matching degrees of the feature points collected at the current moment and the critical moment with the target object in the map information according to the coordinates of the feature points collected at the critical moment and the current moment in the vehicle body coordinate system at the current moment and the position of each particle, it is further used for: Determine target feature points according to the feature values of the feature points collected at each critical moment and the feature points collected at the current moment. Determine target feature points again according to the feature values of the feature points other than the feature points included in the feature point set among the feature points collected at each critical moment and the feature points collected at the current moment, where the feature points included in the feature point set are the feature points located within a preset distance range of the target feature point determined last time and the target feature point determined last time. When the number of the target feature points meets a preset number, N target feature points are obtained, and N is equal to the preset number. When the positioning module obtains the matching degrees of the feature points collected at the critical moment and the current moment with the target object in the map information according to the coordinates of the feature points collected at the critical moment and the current moment in the vehicle body coordinate system at the current moment and the position of each particle, it is specifically used for: Obtain the matching degrees of the feature points collected at the current moment and the critical moment with the target object in the map information of the target area according to the coordinates of the N target feature points in the vehicle body coordinate system at the current moment and the position of each particle.

24. The device according to claim 23, characterized in that, The feature value of the feature point is obtained through an evaluation function, and the feature value is used to evaluate the stability of the feature point.

25. The device according to claim 23 or 24, characterized in that The target feature point is the feature point with the largest feature value among the feature points.

26. The device according to any one of claims 14-18, 23-24, characterized in that The origin of the vehicle body coordinate system is located at any position on the vehicle.

27. A positioning device, characterized in that, Includes: A memory and at least one processor; The memory is used to store program instructions. The processor is used to call the program instructions in the memory and execute the positioning method according to any one of claims 1-13.

28. A positioning system, characterized in that, Includes: A vehicle and an in-vehicle sensing device; The in-vehicle sensing device is installed on the vehicle. The vehicle is used to execute the positioning method according to any one of claims 1-13; or, The vehicle-mounted sensing device is used to execute the positioning method according to any one of claims 1-13.

29. A readable storage medium, characterized in that, A computer program is stored on the readable storage medium; when the computer program is executed, the positioning method according to any one of claims 1-13 is implemented.

Images