JP7343548B2 - Vehicle positioning methods, devices, electronic equipment and computer storage media - Google Patents

Description

TECHNICAL FIELD The present application relates to the field of computer technology, and in particular to the field of navigation positioning technology, and specifically to a vehicle positioning method, device, electronic equipment, and computer storage medium.

Positioning is a very important part of vehicle navigation, and people's demands for positioning and navigation accuracy are increasing.

However, GPS positioning information may be inaccurate or lost, such as in overpass scenes, parking lots, tunnels, etc. On underground roads, dense forests, etc., GPS positioning information may drift significantly, from several tens of meters to several hundred meters, resulting in low positioning accuracy.

The present application provides a vehicle positioning method, apparatus, electronic device, and computer storage medium.

In the first aspect of the present application, fluctuations in positioning information are prevented by predicting the road section on which the vehicle is currently traveling based on historical positioning and correcting the positioning position based on the predicted road section on which the vehicle is currently traveling. To provide a vehicle positioning method that can avoid the increase in positioning accuracy, improve positioning accuracy, and solve the problem of large positioning fluctuations when a GPS signal is interrupted in existing technology.

A second aspect of the present application provides a vehicle positioning device.

A third aspect of the present application provides an electronic device.

A fourth aspect of the present application provides a non-transitory computer-readable storage medium having computer instructions stored thereon.

In the first aspect, the embodiment of the present application includes the steps of: acquiring road network information; periodically performing vehicle positioning to obtain a position position; and based on the position position determined in each historical period. the step of determining a target road section on which the vehicle is traveling in the current cycle from a plurality of road sections indicated by the road network information; and determining the positioning position of the current cycle based on the target road section. A vehicle positioning method is provided, which includes the step of: modifying the positioning position to obtain a positioning position within the target road section.

In a second aspect, embodiments of the present application include an acquisition module configured to acquire road network information, and a positioning module configured to periodically perform vehicle positioning to acquire a positioned position. , a determination configured to determine, from a plurality of road sections indicated by the road network information, a target road section on which the vehicle is traveling in the current period, based on the measured position determined in each historical period. A vehicle positioning device comprising: a module; and a correction module configured to correct the positioning position of the current cycle based on the target road section to obtain a positioning position within the target road section. provide.

In a third aspect, embodiments of the present application include at least one processor and a memory communicatively coupled to the at least one processor, the memory including an executable by the at least one processor. Provided is an electronic device in which the at least one processor is capable of performing the method for positioning a vehicle according to the first aspect, when instructions are stored and the instructions are executed by the at least one processor.

In a fourth aspect, embodiments of the present application provide a non-transitory computer-readable storage medium having computer instructions stored thereon, the computer instructions comprising: directing a computer to a method for positioning a vehicle according to the first aspect; Provided is a non-transitory computer-readable storage medium for executing.

In a fifth aspect, embodiments of the present application provide a computer program for causing a computer to perform the vehicle positioning method according to the first aspect.

The technical solutions provided by the embodiments of the present application have the following beneficial effects.
Obtain road network information, perform vehicle positioning periodically to obtain the measured position, and based on the measured positions determined in each historical cycle, calculate the current position from multiple road sections indicated by the road network information. A target road section on which the vehicle is traveling in a period is determined, and based on the target road section, the positioning position of the current period is corrected to obtain a positioning position within the target road section. By predicting the road section you are currently driving on using historical positioning and correcting the positioning position based on the predicted road section you are currently driving on, you can avoid large fluctuations in positioning information and improve the accuracy of positioning. can be improved.

It is understood that the content contained in this summary section is not intended to identify key features or key features of the embodiments of the present application, nor is it intended to limit the scope of the present application. I want to be Other features of the present application will be readily understood from the following specification.

The drawings are used to better understand the technical solution and do not limit the present application.
1 is a schematic flowchart of a vehicle positioning method according to an embodiment of the present application. 3 is a schematic flowchart of another vehicle positioning method according to an embodiment of the present application. 2 is a schematic flowchart of another vehicle positioning method according to an embodiment of the present application. 1 is a schematic diagram of a system framework of a vehicle positioning method according to an embodiment of the present application; FIG. 1 is a schematic structural diagram of a vehicle positioning device according to an embodiment of the present application. FIG. 2 is a block diagram of an electronic device of a vehicle positioning method according to an embodiment of the present application.

Hereinafter, exemplary embodiments of the present application will be described in conjunction with the drawings, in which various details of the embodiments of the present application are included for ease of understanding, and which are merely illustrative. should be considered as such. Accordingly, those skilled in the art may make various changes and modifications to the embodiments described herein without departing from the scope and spirit of this application. Similarly, for the sake of clarity and brevity, the following description omits descriptions of well-known functions and structures.

Hereinafter, a vehicle positioning method, device, electronic device, and computer storage medium according to an embodiment of the present application will be described with reference to the drawings.

FIG. 1 is a schematic flowchart of a vehicle positioning method according to an embodiment of the present application.

As shown in FIG. 1, the method includes steps 101 to 104.

In step 101, road network information is acquired.

Here, the road network information is road data that is composed of various roads that connect with each other and are spread out in a net-like manner within a certain area.

In this embodiment, the data service engine is capable of retrieving road network information not only in good network conditions, but also in offline data packets stored in the vehicle itself, even in the absence of a network, i.e. in an offline state. can be loaded to obtain road network information.

In one embodiment, the vehicle's current positioning information is obtained, and the vehicle's positioning information is input to a data service engine and output as corresponding road network information, e.g., all discrete locations within an area of n*n meters. By inputting the discretized road data into the map data adaptation module, the discretized road data can be converted into a tree-like structure, that is, the discretized road data The relationship between the two is established and the corresponding road network information is generated.

In step 102, positioning of the vehicle is performed periodically to obtain a measured position.

In this embodiment, vehicle positioning information is collected according to a preset positioning cycle, and a positioning position is obtained based on the positioning information. Here, the positioning position includes longitude, latitude, and course angle information of the vehicle. .

In one possible embodiment, a global positioning system (GPS) mounted on a vehicle is used to periodically acquire positioning information to obtain the position of the vehicle.

In practical applications, if the GPS signal encounters obstacles, the normal reception of the signal will be affected and positioning will not be possible. Accurate positioning becomes impossible. As another possible embodiment, when the vehicle is traveling in a scene where the GPS signal cannot be received normally due to a blockage, based on the acquired GPS signal, the traveling distance data by the vehicle speed sensor and the traveling direction data by the electronic compass are collected. By combining these and estimating the position of the vehicle, it is possible to obtain high positioning accuracy and periodically obtain the measured position of the vehicle.

As a third possible embodiment, a Dead Reckoning (DR) algorithm can estimate the vehicle's position for each period.

As a fourth possible embodiment, an inertial measurement unit (IMU) may be used to periodically position the vehicle to obtain a determined position of the vehicle.

In step 103, a target road section on which the vehicle is traveling in the current cycle is determined from a plurality of road sections indicated by the road network information, based on the measured position in each historical cycle.

In this embodiment, the positioning of the vehicle is performed periodically to obtain the measured position of the vehicle, and the time granularity of the period can be set according to the actual demand. For example, the time granularity of the period can be seconds, minutes, hours, etc. The cycle includes the current cycle and the history cycle, and the history cycle is each cycle before the current cycle. If positioning data is collected once per positioning cycle and the current time is 8:50, 8:50 corresponds to the current cycle, and each cycle from 8:00 to 8:50 corresponds to each history period.

In this embodiment, the positioning position obtained by positioning the vehicle in the historical period can indicate the traveling trajectory and future driving tendency of the vehicle, and the target road section on which the vehicle will travel in the current period and the future period. It can be used to predict. As a possible embodiment, based on the measured position determined in each historical period and each road section included in the road network information, the measured position in each historical period is set to the corresponding road section in the road network information. By mapping, a vehicle travel trajectory can be generated, and a target road section on which the vehicle will travel in the current cycle can be predicted from a plurality of road sections indicated by the road network information based on the vehicle's historical travel trajectory.

In step 104, the positioning position of the current cycle is corrected based on the target road section to obtain a positioning position within the target road section.

In one embodiment of the present application, in practical applications, GPS often encounters obstacles, which affect the normal reception of the signal and increase the fluctuation of positioning, and therefore the present invention In the embodiment, by correcting the positioning position of the current cycle based on the determined target road section, it is possible to avoid large fluctuations in positioning and improve the accuracy of positioning. Further, by acquiring a positioning position within the target road section based on the corrected positioning position and realizing road binding, it is possible to timely identify whether there is yaw in the following. In the existing technology, the navigation performs the binding of road sections based on the positioning information directly output from the GPS, and due to the large fluctuation of the positioning, the navigation cannot identify the yaw or the navigation may falsely report the yaw. The problem arises that the

In the vehicle positioning method according to the present application, road network information is acquired, vehicle positioning is performed periodically to obtain the positioning position, and the road network information is determined based on the positioning position determined in each historical cycle. From the multiple road sections shown, determine the target road section on which the vehicle is traveling in the current cycle, correct the positioning position for the current cycle based on the target road section, and calculate the positioning within the target road section. Get location. Predict the road section you are currently driving on using historical positioning, and correct the positioning position based on the predicted road section you are currently driving on, to avoid large fluctuations in positioning information and improve positioning accuracy. At the same time, the yaw of the vehicle following can be identified in a timely manner due to the road binding.

Based on the above embodiments, the embodiment of the present application provides another vehicle positioning method, and FIG. 2 is a schematic flowchart of the another vehicle positioning method according to the embodiment of the present application.

As shown in FIG. 2, the method includes steps 201-210.

In step 201, road network information is acquired.

Here, the road network information is road data that is composed of various roads that connect with each other and are spread out in a net-like manner within a certain area.

In this embodiment, the data service engine includes road network information, and the road network information in the data service engine can be obtained not only when the network condition is good, but also when there is no network, that is, offline. However, offline data packets stored on the vehicle itself can be loaded to obtain road network information.

In one embodiment, the vehicle's current positioning information is obtained, and the vehicle's positioning information is input to a data service engine and output as corresponding road network information, e.g., all discrete locations within an area of n*n meters. By inputting the discretized road data into the map data adaptation module, the discretized road data can be converted into a tree-like structure, that is, the discretized road data The relationship between the two is established and the corresponding road network information is generated.

At step 202, vehicle sensor data is obtained every cycle using the vehicle's own sensors.

In one embodiment, a vehicle is equipped with various sensors that measure vehicle running information, such as a sensor that measures acceleration, a sensor that measures angular velocity, and a sensor that measures course angle. unit, IMU) is installed. At each measurement cycle, vehicle sensor data including acceleration, angular velocity, course angle, etc. is acquired using the vehicle's own sensors, and is input to a positioning module installed in the vehicle to perform positioning processing.

In step 203, it is determined whether or not satellite positioning data has been acquired in the corresponding period. If acquired, step 204 is executed; if not, step 205 is executed.

In one embodiment, it is determined whether satellite positioning data is acquired in the corresponding period, and if the satellite positioning data is acquired, the vehicle positioning information is determined based on a Kalman filter algorithm, i.e., the subsequent step 204 is performed. If the positioning information of the vehicle is determined based on the dead reckoning algorithm DR, step 205 is executed. Even when satellite positioning data can be obtained, even when satellite positioning cannot be obtained, the vehicle can be positioned without being affected by the strength of the GPS signal, and the vehicle's position at the corresponding cycle can be obtained. I can do it.

In step 204, if satellite positioning data is acquired in the corresponding period, Kalman filtering is performed on the satellite positioning data based on the vehicle sensor data to obtain positioning update data in the corresponding period.

Here, the positioning update data indicates an update of the vehicle's positioning position compared to the immediately previous cycle, and includes a longitude difference value, a latitude difference value, and a course angle difference value.

In one embodiment, if satellite positioning data including a GPS position or a vehicle speed obtained based on a Global Navigation Satellite System (GNSS) is obtained in a corresponding period, the observation phase includes vehicle sensor data. The acceleration, angular velocity, and acquired satellite positioning data are input to a Kalman filter to obtain vehicle positioning update data. Specifically, when making predictions using a Kalman filter, the relative displacement and rotation angle are obtained by integrating the accelerometer and angular velocity meter in the inertial measurement unit, and in the error calculation stage, the vehicle speed is used to estimate the vehicle itself. The speed determined by the sensor of get.

Note that before inputting the GPS positioning information to the Kalman filter, the GPS coordinate system has been converted to a local Cartesian coordinate system (ENU).

In step 205, if no satellite positioning data is acquired in the corresponding cycle, the dead reckoning algorithm DR is used to determine positioning update data in the corresponding cycle.

In one embodiment, if no satellite positioning data is acquired in the corresponding period, that is, the vehicle may currently be in a scene where the GPS signal is blocked, such as a viaduct or a long tunnel, and this embodiment The positioning module implements the dead reckoning algorithm DR to estimate the positioning update data of the corresponding period. As a result, even if GPS positioning data cannot be acquired, positioning update data for a corresponding period can be determined based on the dead reckoning algorithm.

Note that in this embodiment, the dead reckoning algorithm DR is implemented within the DR module of the positioning module, and even if no satellite positioning data is acquired in the corresponding period, the dead reckoning algorithm DR is implemented from the DR module to the response acquired based on the DR algorithm. It is possible to obtain a positioning update position with a cycle of 1, and it is possible to avoid not being able to obtain a positioning position when a GPS signal cannot be received.

In step 206, positioning data for each historical period is determined based on the positioning update data for each historical period.

In actual application scenes, real-time positioning methods with different periods may be different, for example, they may be acquired based on GPS positioning, estimated and acquired based on DR algorithm, or GPS positioning methods may be different. Since the data, sensor data, and DR estimation algorithm may be acquired in combination, the standards of the positioning data to be output are different. In order to realize that the positioning position data determined in each cycle is determined based on a unified processing method and in the same coordinate system, the vehicle positioning data is updated in comparison with the previous cycle. After acquiring the positioning update data of the corresponding cycle to display, the positioning update data is superimposed on the positioning position acquired in the immediately previous cycle to obtain the positioning position of the corresponding cycle, and the positioning position is determined in each cycle. This makes it possible to unify the processing method and coordinate system of the measured positions.

For example, taking the course angle as an example, if the course angle of the immediately previous period is Last_Yaw and the positioning update data is Delta_Yaw, the course angle of the corresponding period is Yaw=Last_Yaw+Delta_Yaw, and similarly, the longitude of the corresponding period, Positioning position data such as latitude can be determined.

In step 207, the travel trajectory of the vehicle is determined based on the measured positions measured in each history cycle.

In one embodiment of the present application, a road section in which a vehicle has traveled in each historical period is determined from a plurality of road sections indicated by road network information based on the positioning position determined in each historical period, and A road section sequence for indicating a travel trajectory is generated based on the road sections on which the vehicle has traveled, where each element in the road section sequence indicates a road section on which the vehicle has traveled in a corresponding history period. As a result, a road section sequence indicating the historical driving trajectory of the vehicle is generated by combining the position determined in each historical period with road network information, and furthermore, based on the historical road section sequence, the road section sequence after the historical period is Predict interval sequences.

In step 208, the travel trajectory of the vehicle is input into the prediction model to obtain the travel probability that the vehicle will travel on each road section in the current cycle.

Here, the prediction model has already learned the mapping relationship between the travel trajectory and the travel probability of each road section.

In one possible embodiment, the prediction model is a hidden Markov model, specifically, inputting the road segment sequence into the hidden Markov model to obtain the output sequence and the corresponding travel probability, where the output Each element in the sequence is intended to indicate the road section on which the vehicle travels in each period after the historical period, and the hidden Markov model obtained in training is used to identify the relationship between positions determined in different historical periods. Since the characteristics can be quantified, predictions based on road sections of the entire road network can be realized, and the accuracy of road section sequence prediction of vehicle travel trajectories in each period after the historical period is improved.

In step 209, a target road section is determined from each road section based on the travel probability.

In one possible implementation, a Hidden Markov Model outputs each sequence and a corresponding trip probability, where the trip probability corresponding to each sequence is such that the vehicle travels that road segment sequence in each period after the historical period. In order to indicate the reliability of running, in this embodiment, the road section sequence with the highest probability of running is determined as the road section sequence in which the vehicle runs in each period after the history period, and based on the road section sequence, By determining the road section corresponding to the current cycle and setting this road section as the target road section on which the vehicle is traveling in the current cycle, prediction based on the road section of the entire road network is realized. By determining the road section with the highest reliability as the target road section from among each road section, the accuracy of determining the target road section on which the vehicle is currently traveling is improved.

In step 210, the positioning position of the current cycle is corrected based on the target road section to obtain a positioning position within the target road section.

In one embodiment, the positioning position of the current cycle is projected onto the target road section to obtain the positioning position within the target road section, and the positioning position obtained by front-end positioning varies greatly when the GPS signal is poor. Therefore, there is a problem that positioning becomes inaccurate. By correcting the positioning position to the target road section using the target road section obtained through prediction, road binding is realized and the accuracy of positioning is improved. In the existing technology, since the measured position is not corrected, the fluctuation in the positioning may be large, and the measured position is not bound to the road, so yaw cannot be identified in a timely manner.

In the vehicle positioning method according to the embodiment of the present application, the historical travel trajectory of the vehicle is determined based on the positioning positions determined in each historical cycle, and the vehicle is By obtaining the driving probability of driving on each road section in the period, and determining the target road section to be traveled in the current period from each road section based on the driving probability, the current It is possible to predict the probability of traveling on each road section at the cycle of , and the accuracy of target road section prediction is improved.

Based on the above embodiment, the present embodiment further provides a vehicle positioning method, and FIG. 3 is a schematic flowchart of yet another vehicle positioning method according to the embodiment of the present application, as shown in FIG. After modifying the positioning position of the current period based on the target road section to obtain the positioning position within the target road section, the method further includes steps 301 to 303.

In step 301, the navigation road section currently being traveled is queried from the navigation route based on the corrected positioning position.

In one embodiment, the currently traveled navigation road segment includes the modified position from the navigation route to determine whether the vehicle has yaw. Query whether there is one.

In step 302, if the navigation road segment was not queried, the yaw of the vehicle is determined.

In one embodiment, if the navigation road segment containing the positioning position was not queried, i.e. the current road segment determined by the navigation is not the target road segment, the vehicle is driving away from the target road segment. That is, the vehicle has yaw, and timely determination of whether the vehicle has yaw is realized, and the vehicle is prevented from performing incorrect navigation.

In step 303, if the navigation road section is queried, the driving state of the vehicle on the navigation road section is determined based on the vehicle's course angle.

Here, the driving state includes entering and exiting and switching between a main road and a secondary road.

In one embodiment, when the navigation road segment that includes the positioning position is queried, it indicates that the current navigation road segment is the target road segment, and the vehicle has no yaw and is accurately traveling on the target road. can be determined. Furthermore, since the course angle indicates the running angle of the vehicle, the running state of the vehicle on the navigation road section can be determined based on the course angle of the vehicle.

In one scene, the positioning update data of each period with respect to the immediately preceding period determined in the example of FIG. It is determined that there has not been a large change in the vehicle, and it is determined that the vehicle is traveling in the navigation road section.

In another scene, the positioning update data of each period with respect to the immediately preceding period determined in the example of FIG. It is determined that the angle has changed significantly and that the vehicle has left the navigation road section.

In yet another scene, the positioning update data for each cycle with respect to the immediately preceding cycle determined in the example of FIG. and if the lateral movement distance indicated by the longitude change data is greater than the threshold, it is determined that the vehicle has switched between the main road and the secondary road.

In the vehicle positioning method according to the embodiment of the present application, the navigation road section currently traveling is queried from the navigation route based on the corrected positioning position, and if the navigation road section is not queried, the vehicle If it is determined that there is a yaw in This makes it possible to quickly and timely discover whether the vehicle has yaw, and if there is no yaw, the vehicle's driving condition can be monitored in real time to understand the vehicle's driving condition in a timely manner. to avoid yaw.

In practical application, in addition to the above embodiment, after the navigation road section is queried, the navigation road section may also belong to the road section of the bridge area, and in one embodiment of the present application, the above Fig. 2 In the embodiment, the positioning position update data of each cycle with respect to the immediately previous cycle includes slope angle change data, and when a navigation road section is queried and the navigation road section belongs to a road section in a bridge area, the vehicle It is determined whether the vehicle has entered or exited the bridge in the navigation road section based on the change data of the inclination angle of the vehicle. Here, if the inclination angle is greater than or equal to the threshold, it is determined that the vehicle has entered or exited the bridge in the navigation road section, and if the inclination angle is less than the threshold, the vehicle has not entered or exited the bridge in the navigation road section. It is decided that This ensures that after it has been determined that the vehicle is traveling on the target road section, if it is determined that the navigation road section may belong to the road section of the bridge area based on the identifier in the map data, the slope angle By identifying the movement into and out of the bridge based on the magnitude of the vehicle, the driving status of the vehicle can be identified in a timely manner and avoid yaw again.

In order to clearly explain the above embodiment, this embodiment will be explained based on the block diagram of the system of the vehicle positioning method shown in FIG.

FIG. 4 is a block schematic diagram of a vehicle positioning method system according to an embodiment of the present application. As shown in FIG. 4, the vehicle positioning method system 40 includes a positioning module 43, a road network matching module 44, A data services engine 46 and a map matching adaptation 45 are provided.

The data engine service 46 is configured to determine discretized road data from the road network information based on the current positioning.

The map matching adaptation 45 is configured to process the discretized road data to generate corresponding road network information.

The positioning module 43 is configured to acquire the measured position of the vehicle in each period.

The road network matching module 44 predicts each road section on which the vehicle is traveling in the current cycle from a plurality of road sections indicated by the road network information based on the position determined by the positioning module 43. configured. A target road section on which the vehicle is currently traveling is determined from each possible road section.

The positioning module 43 further modifies the positioning position based on the determined target road section to obtain a positioning position within the target road section.

As shown in FIG. 4, the positioning method according to the embodiment of the present application departs from the navigation engine, ie, the navigation engine 41 of FIG. The positioning module 43 and the road network matching module 44 are separated from the navigation engine 41 and the navigation interface layer 42, and the positioning module 43 and the road network matching module 44 of the present application are not part of the navigation, but are independent components. It operates as a module. In this way, in the present application, after the positioning module 43 determines the positioning position, the positioning position is input to the road network matching module 44, and the vehicle is selected from a plurality of routes indicated by the road network information in the current cycle. By determining the target road section where the vehicle is currently traveling and correcting the positioning position based on the determined road section that the vehicle is currently traveling on, large fluctuations in GPS positioning can be avoided and the accuracy of positioning can be improved. be able to. Then, by projecting the corrected positioning position onto the target road section and obtaining the positioning position within the target road section, road binding is realized and it is possible to timely discover whether there is yaw. can.

First, road network information is acquired, specifically, the current positioning information of the vehicle is acquired, and the vehicle positioning information is input to the data service engine and output as the corresponding road network information, for example n*n All discretized road data in the area of meters. The discretized road data can be input into the map data adaptation module and the discretized road data can be converted into a tree-like structure, that is, the relationship between the discretized road data is established and the corresponding road Network information is generated.

Next, the positioning of the vehicle is performed periodically to obtain the measured position of each historical cycle and the current cycle. Specifically, in order to perform vehicle positioning in different scenes, vehicle sensor data collected by each sensor installed on the vehicle, GPS positioning data, GNSS vehicle speed data, and inertial measurement unit are collected every cycle. 2. Receive data for determining the vehicle's measured position, including data determined by the vehicle. Positioning in the embodiment of the present application is divided into front-end positioning and back-end positioning. Front-end positioning is when satellite positioning data is acquired in the corresponding cycle, the vehicle sensor data and satellite positioning data are input to the Kalman filtering module to acquire positioning update data in the corresponding cycle, and the acquired correspondence is input to the Kalman filtering module. The positioning update data of the current cycle is superimposed on the positioning position of the immediately preceding cycle to determine the positioning position of the corresponding cycle. Back-end positioning means that if no satellite positioning data is acquired in the corresponding period, the dead reckoning module uses a dead reckoning algorithm to determine the positioning update data for the corresponding period and calculates the positioning update data for the previous period. The method is to determine the positioning position of the corresponding period by superimposing the period. In other words, in the case of back-end positioning, there is no need to perform Kalman filtering, so even if the satellite positioning signal cannot be obtained, the position of the corresponding period can be determined based on the hardware DR, and it is not necessary to perform Kalman filtering. It is realized that the positioning needs of different scenes are met.

Next, the positioning position determined in each historical period is input to the road network matching module 44, and based on the hidden Markov prediction model, the road section on which the vehicle is traveling in the current period is predicted, and By acquiring the road sections and corresponding probabilities, determining the target road section based on the predicted road sections and the corresponding probabilities, and correcting the positioning position, large fluctuations in positioning can be avoided. , improve positioning accuracy. Furthermore, by projecting the corrected positioning position onto the target road section and realizing road binding, it is possible to timely discover whether there is yaw.

Then, based on the corrected positioning position, query the current navigation road section from the navigation route to realize road binding, and timely identify whether the vehicle has yaw. and identify the driving condition of the vehicle. In the existing technology, after the positioning position is determined, the road binding is not performed and the yaw cannot be identified in a timely manner.

In order to realize the above embodiment, this embodiment provides a vehicle positioning device.

FIG. 5 is a schematic diagram of the configuration of a vehicle positioning device according to an embodiment of the present application.

As shown in FIG. 5, the vehicle positioning device includes an acquisition module 51, a positioning module 52, a determination module 53, and a correction module 54.

The acquisition module 51 is configured to acquire road network information.

The positioning module 51 is configured to periodically perform positioning of the vehicle and obtain a measured position.

The determination module 53 is configured to determine, from a plurality of road sections indicated by the road network information, a target road section on which the vehicle is traveling in the current cycle, based on the position determined in each historical cycle. Ru.

The modification module 54 is configured to modify the positioning position of the current period based on the target road segment to obtain a positioning position that is within the target road segment.

In one possible embodiment of the present example, the determination module 53 comprises a determination unit configured to determine the travel trajectory of the vehicle based on the determined positions in each historical period; A prediction unit configured to input a trajectory into a prediction model to obtain a travel probability of the vehicle traveling on each road section in a current cycle, the prediction model comprising: inputting a trajectory and a prediction model on each road section; A prediction unit that has learned a mapping relationship between the driving probability and the driving probability.

The determining unit is further configured to determine the target road segment from each road segment based on the travel probability.

As a possible embodiment of the present example, the determining unit specifically selects the information for each historical period from a plurality of road sections indicated by the road network information based on the measured position determined in each historical period. is configured to determine a road section on which the vehicle has traveled, and to generate a road section sequence for indicating a travel trajectory based on the road sections on which the vehicle has traveled in each historical period, Each element indicates a road section on which the vehicle traveled in the corresponding history cycle.

In one possible embodiment of this example, the prediction model is a hidden Markov model, and the prediction unit is configured to input the road segment sequence into the hidden Markov model to obtain an output sequence and a corresponding travel probability. Each element in the output sequence indicates a road section on which the vehicle travels in each period after the history period.

In one possible embodiment of this example, the device queries the currently traveled navigation road segment from the navigation route based on the modified positioning, and the navigation road segment is not queried. If so, the method further includes a query determination module configured to determine yaw of the vehicle.

In one possible embodiment, the query determination module is further configured to determine a driving state of the vehicle on the navigation road segment based on a heading angle of the vehicle when the navigation road segment is queried. The driving state includes entering and exiting and switching between a main road and a secondary road.

In a possible embodiment of the present example, the query determination module further comprises: if the navigation road segment is queried and the navigation road segment belongs to a road segment in a bridge region, the query determination module further comprises: , is configured to detect whether the vehicle enters or exits a bridge in the navigation road section.

In one possible embodiment of the present example, the modification module 54 specifically projects the positioning position of the current cycle onto the target road section to obtain the positioning position within the target road section. It is configured as follows.

As a possible embodiment of this embodiment, the positioning module 52 specifically acquires vehicle sensor data using the vehicle's own sensors in each cycle, and acquires satellite positioning data in the corresponding cycle. is configured to perform Kalman filtering on the satellite positioning data based on vehicle sensor data to obtain positioning update data for a corresponding period, and the positioning update data is configured to perform Kalman filtering on the satellite positioning data based on vehicle sensor data, and the positioning update data is configured to perform Kalman filtering on the satellite positioning data based on vehicle sensor data, and the positioning update data If the satellite positioning data is not acquired in the corresponding period, the dead reckoning algorithm DR is used to determine the positioning update data in the corresponding period.

Note that the above-mentioned interpretation and explanation of the embodiment of the vehicle positioning method can also be applied to the vehicle positioning device of the embodiment, and detailed explanation will be omitted here.

The vehicle positioning device according to the embodiment of the present application acquires road network information, periodically performs vehicle positioning, acquires the positioning position, and calculates the positioning position of the vehicle based on the positioning position determined in each historical cycle. The target road section on which the vehicle is traveling in the current cycle is determined from the multiple road sections indicated by the network information, the positioning position for the current cycle is corrected based on the target road section, and the position is within the target road section. Obtain a certain positioning position. The road section the vehicle is currently traveling on is predicted based on historical positioning, and the positioning position is corrected based on the predicted road section the vehicle is currently traveling on. Thereby, it is possible to avoid large fluctuations in positioning information and improve positioning accuracy.

In order to realize the above embodiment, an embodiment of the present application is an electronic device including at least one processor and a memory communicatively connected to the at least one processor, the memory including , instructions executable by the at least one processor are stored, the instructions being executed by the at least one processor, the at least one processor performing the vehicle positioning method described in the foregoing method embodiment. Providing electronic equipment that can run.

To implement the above-described embodiments, embodiments of the present application provide a non-transitory computer-readable storage medium having computer instructions stored thereon, the computer instructions causing the computer to perform the above-described method. A non-transitory computer-readable storage medium is provided for implementing the vehicle positioning method described in the examples.

According to embodiments of the present application, the present application further provides an electronic device and a readable storage medium.

As shown in FIG. 6, it is a block diagram of an electronic device of a vehicle positioning method according to an embodiment of the present application. Electronic equipment is intended to refer to various types of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, large format computers, and other suitable computers. Electronic equipment may also represent various forms of mobile devices such as personal digital processing, mobile phones, smart phones, wearable devices, and other similar computing devices. The components depicted herein, their connections and relationships, and their functionality are merely examples and are not intended to limit the description herein and/or the required implementation of the present application.

As shown in FIG. 6, the electronic device includes one or more processors 601, a memory 602, and an interface for connecting each component with a high-speed interface and a low-speed interface. Each component may be interconnected with a different bus, mounted on a common motherboard, or mounted in other manners as desired. The processor processes instructions executed within the electronic device, including instructions stored in memory for displaying GUI graphical information on an external input/output device (such as a display device coupled to an interface). I can do it. In other embodiments, multiple processors and/or multiple buses may be used with multiple memories, if desired. Similarly, multiple electronic devices can be connected, and each device can provide a partial required operation (eg, as a server array, blade server, or multiprocessor system). In FIG. 6, one processor 601 is taken as an example.

Memory 602 is a non-transitory computer readable storage medium provided by the present application. The memory stores instructions to be executed by at least one processor, thereby allowing the at least one processor to execute the vehicle positioning method according to the present application. The non-transitory computer-readable storage medium of the present application stores computer instructions for causing a computer to perform the vehicle positioning method of the present application.

Memory 602 stores program instructions/modules (e.g., acquisition module 51, positioning module 52, determination module shown in FIG. 53 and modification module 54). The processor 601 executes non-transitory software programs, instructions and modules stored in the memory 602 to perform various functional applications and data processing of the server, i.e. the vehicle according to the embodiments of the above method. realizes a positioning method.

Memory 602 can include a program storage area and a data storage area, where the program storage area can store an operating system, application programs necessary for at least one function, and the data storage area can store an operating system, application programs necessary for at least one function. , data created by the use of electronic equipment of vehicle positioning methods, etc. can be stored. Memory 602 can also include high-speed random access memory and can further include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state memory. It is a state storage device. In some embodiments, memory 602 may optionally include memories configured remotely to processor 601, where these remote memories are connected to vehicle positioning method electronics via a network. can be done. Examples of the above networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The electronic device for the vehicle positioning method may further include an input device 603 and an output device 604. The processor 601, memory 602, input device 603, and output device 604 can be connected via a bus or other methods, and in FIG. 6, connection via a bus is taken as an example.

The input device 603 can receive input numerical or textual information and generate key signal inputs for user configuration and function control of the electronics of the vehicle positioning method, such as a touch screen, keypad, mouse, etc. An input device such as a trackpad, touchpad, pointing stick, one or more mouse buttons, trackball, joystick, etc. Output devices 604 can include display devices, supplemental lighting devices (eg, LEDs), haptic feedback devices (eg, vibration motors), and the like. Such display devices can include, but are not limited to, liquid crystal displays (LCDs), light emitting diode (LED) displays, and plasma displays. In some embodiments, the display device may be a touch screen.

Various embodiments of the systems and techniques described herein include digital electronic circuit systems, integrated circuit systems, application specific integrated circuits (ASICs), computer hardware, firmware, software, and/or the like. This can be achieved by a combination of These various embodiments may be implemented in one or more computer programs that can be executed and/or interpreted on a programmable system that includes at least one programmable processor. The programmable processor may be a special purpose or general purpose programmable processor, and receives data and instructions from a storage system, at least one input device, and at least one output device, and transmits data and instructions to the storage system. and the at least one output device.

These computing programs (also referred to as programs, software, software applications, or code) may include machine instructions for programmable processors, high-level process and/or object-oriented programming languages, and/or assembly/machine languages. can implement these computing programs. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, device for providing machine instructions and/or data to a programmable processor. , and/or apparatus (e.g., magnetic disk, optical disk, memory, programmable logic device (PLD)), including a machine-readable medium that receives machine instructions that are machine-readable signals. The term "machine readable signal" refers to any signal for providing machine instructions and/or data to a programmable processor.

The systems and techniques described herein may be implemented on a computer to provide interaction with a user, and the computer may include a display device (e.g., a CRT) for displaying information to the user. computer (e.g., a mouse or trackball), and a keyboard and pointing device (e.g., a mouse or trackball) through which a user can provide input to the computer. Other types of devices may also provide interaction with the user, for example, the feedback provided to the user may be any form of sensing feedback (e.g., visual feedback, auditory feedback, or haptic feedback). Input from the user may be received in any form, including acoustic input, audio input, and tactile input.

The systems and techniques described herein may be used in computing systems with back-end components (e.g., data servers), or with middleware components (e.g., application servers), or with front-end components. A system (e.g., a user computer having a graphical user interface or web browser by which the user interacts with embodiments of the systems and techniques described herein), or such a computer); It can be implemented in a computing system that includes any combination of end components, middleware components, and front-end components. The components of the system may be interconnected by any form or medium of digital data communication (eg, a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

A computer system can include a client and a server. Clients and servers are generally remote from each other and typically interact via a communications network. A client-server relationship is created by computer programs running on corresponding computers and having a client-server relationship with each other.

According to the technical solution of the embodiment of the present application, road network information is acquired, vehicle positioning is performed periodically to obtain a positioning position, and based on the positioning position determined in each historical period, The target road section on which the vehicle is traveling in the current cycle is determined from the multiple road sections indicated by the road network information, the positioning position of the current cycle is corrected based on the target road section, and the target road section is determined. Obtain the position within the range. The road section the vehicle is currently traveling on is predicted based on historical positioning, and the positioning position is corrected based on the predicted road section the vehicle is currently traveling on. Thereby, it is possible to avoid large fluctuations in positioning information and improve positioning accuracy.

Steps can be reordered, added, or deleted using the various forms of flow shown above. For example, each step described in this application may be performed in parallel, sequentially, or in a different order, but the techniques disclosed in this application may A proposal is not limited herein as long as it can achieve the desired results.

The above specific implementation modes do not limit the protection scope of the present application. Various modifications, combinations, subcombinations, and substitutions may be made by those skilled in the art based on design requirements and other factors. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of this application shall be included within the protection scope of this application.

Claims (19)

a step of obtaining road network information;
a step of periodically performing vehicle positioning to obtain a positioning position;
determining a travel trajectory of the vehicle based on the position determined in each historical cycle;
determining a target road section on which the vehicle is traveling in the current cycle from a plurality of road sections indicated by the road network information based on the travel trajectory of the vehicle;
projecting the positioning position of the current period onto the target road section based on the target road section, correcting the positioning position of the current period, and obtaining a positioning position within the target road section;
including;
The step of periodically performing vehicle positioning and acquiring the positioning position is
acquiring vehicle sensor data using the vehicle's own sensors every cycle;
If satellite positioning data is acquired in a corresponding cycle, performing Kalman filtering on the satellite positioning data based on vehicle sensor data to obtain positioning update data in the corresponding cycle, the positioning update data being , indicating an update of the measured position of the vehicle compared to a previous period;
If no satellite positioning data is acquired in the corresponding period, determining the positioning update data in the corresponding period using a dead reckoning algorithm DR;
vehicle positioning methods, including a step of determining a target road section on which the vehicle is traveling in the current cycle from a plurality of road sections indicated by the road network information based on the travel trajectory of the vehicle;
Determining a travel trajectory of the vehicle based on the determined position in each history cycle;
A step of inputting the travel trajectory of the vehicle into a prediction model to obtain a travel probability that the vehicle travels on each road section in the current cycle, the prediction model inputting the travel trajectory and the travel probability of each road section. a step that has learned a mapping relationship between
determining the target road section from each road section based on the travel probability;
The vehicle positioning method according to claim 1, comprising: The step of determining a travel trajectory of the vehicle based on the measured positions determined in each history cycle,
determining a road section on which the vehicle traveled in each historical period from among a plurality of road sections indicated by the road network information, based on the position determined in each historical period;
generating a road segment sequence indicative of a travel trajectory based on road segments traveled by the vehicle in each historical period, wherein each element in the road segment sequence represents a road segment traveled by the vehicle in a corresponding historical period; a step indicating a road section;
The vehicle positioning method according to claim 2, comprising: The prediction model is a hidden Markov model, and the step of inputting the travel trajectory of the vehicle into the prediction model to obtain the travel probability that the vehicle travels on each road section in the current cycle,
inputting the road segment sequence into the hidden Markov model to obtain an output sequence and a corresponding travel probability, wherein each element in the output sequence indicates that the vehicle has 4. The vehicle positioning method according to claim 3, further comprising the step of indicating a road section on which the vehicle is traveling. After the step of modifying the positioning position of the current cycle based on the target road section to obtain a positioning position within the target road section,
searching for a currently traveling navigation road section from the navigation route based on the corrected positioning position;
if the navigation road segment is not retrieved, determining a yaw of the vehicle;
The vehicle positioning method according to any one of claims 1 to 4, comprising: After the step of searching for the navigation road section you are currently traveling on,
If the navigation road section is retrieved, the step of determining the driving state of the vehicle on the navigation road section based on the course angle of the vehicle, the driving state being whether the driving state is in/out, main road and auxiliary road. 6. The vehicle positioning method according to claim 5, further comprising a step of switching to a road. After the step of searching for the navigation road section you are currently traveling on,
When the navigation road section is searched and the navigation road section belongs to a road section in a bridge area, whether the vehicle enters or exits the bridge in the navigation road section based on the inclination angle of the vehicle. The vehicle positioning method according to claim 5, comprising the step of detecting. a step of correcting the positioning position of the current cycle based on the target road section to obtain a positioning position within the target road section;
5. The vehicle positioning method according to claim 1, further comprising the step of projecting the positioning position of the current cycle onto the target road section to obtain the positioning position within the target road section. an acquisition module configured to acquire road network information;
a positioning module configured to periodically perform positioning of a vehicle and obtain a positioning position;
A travel trajectory of the vehicle is determined based on the positioning position determined in each historical cycle, and based on the travel trajectory of the vehicle, the vehicle is selected from a plurality of road sections indicated by the road network information in the current cycle. a determination module comprising a determination unit configured to determine a target road section on which the vehicle is traveling;
Based on the target road section, the positioning position of the current cycle is projected onto the target road section, the positioning position of the current cycle is corrected, and the positioning position within the target road section is obtained. a modification module,
Equipped with
The positioning module
At each cycle, vehicle sensor data is acquired using the vehicle's own sensors,
When satellite positioning data is acquired in a corresponding cycle, Kalman filtering is performed on the satellite positioning data based on vehicle sensor data to obtain positioning update data in the corresponding cycle, and the positioning update data is indicating an update of the positioning position of the vehicle compared to a previous period;
A vehicle positioning device configured to use a dead reckoning algorithm DR to determine the positioning update data in a corresponding period when satellite positioning data is not acquired in the corresponding period. A prediction unit , wherein the determination module is configured to input a travel trajectory of the vehicle into a prediction model to obtain a travel probability that the vehicle travels on each road section in the current period, The unit includes a prediction unit that has learned a mapping relationship between a travel trajectory and a travel probability of each road section,
The vehicle positioning device according to claim 9, wherein the determining unit is configured to determine the target road section from each road section based on the travel probability. The determining unit is
Determining a road section in which the vehicle traveled in each historical period from a plurality of road sections indicated by the road network information based on the positioning position determined in each historical period,
The vehicle is configured to generate a road segment sequence for indicating a travel trajectory based on road segments traveled by the vehicle in each historical period, and each element in the road segment sequence is configured to generate a road segment sequence in which the vehicle travels in a corresponding historical period. The vehicle positioning device according to claim 10, which indicates a road section traveled. The prediction model is a hidden Markov model, and the prediction unit is configured to input the road segment sequence into the hidden Markov model to obtain an output sequence and a corresponding travel probability; 12. The vehicle positioning device according to claim 11, wherein each element indicates a road section on which the vehicle travels in each period after the history period. a search configured to search for a currently traveling navigation road section from a navigation route based on the revised positioning position, and to determine a yaw of the vehicle if the navigation road section is not searched; The vehicle positioning device according to any one of claims 9 to 12, comprising a determination module. The search determination module includes:
When the navigation road section is retrieved, the vehicle is configured to determine a driving condition of the vehicle on the navigation road section based on a course angle of the vehicle, and the driving condition is determined whether the driving condition is an ingress/egress, a main road and an auxiliary road. The vehicle positioning device according to claim 13, which includes switching with a road. The search determination module includes:
When the navigation road section is searched and the navigation road section belongs to a road section in a bridge area, whether the vehicle enters or exits the bridge in the navigation road section based on the inclination angle of the vehicle. The vehicle positioning device according to claim 13, configured to detect. The modification module includes:
The vehicle positioning device according to any one of claims 9 to 12, configured to project the positioning position of the current cycle onto the target road section to obtain the positioning position within the target road section. . at least one processor;
a memory communicatively connected to the at least one processor;
Equipped with
The memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor An electronic device that can perform the vehicle positioning method described. 9. A non-transitory computer-readable storage medium having computer instructions stored thereon, said computer instructions causing a computer to perform a method for positioning a vehicle according to any one of claims 1 to 8. computer-readable storage medium. A computer program that causes a computer to execute the vehicle positioning method according to any one of claims 1 to 8.