CN113724323B

CN113724323B - Map construction method, device and equipment

Info

Publication number: CN113724323B
Application number: CN202110975934.7A
Authority: CN
Inventors: 吕吉鑫; 孟超; 胡兵; 孙杰
Original assignee: Hangzhou Hikvision Digital Technology Co Ltd
Current assignee: Hangzhou Hikvision Digital Technology Co Ltd
Priority date: 2021-08-24
Filing date: 2021-08-24
Publication date: 2024-07-23
Anticipated expiration: 2041-08-24
Also published as: CN113724323A

Abstract

The application provides a map construction method, a map construction device and map construction equipment, wherein the map construction method comprises the following steps: in the process that the teaching vehicle runs to the starting point of the task area along the backtracking path, acquiring backtracking data of the backtracking path, and storing the backtracking data; when the teaching vehicle runs to the starting point of the task area, starting a map building data filling function, and filling backtracking data into map building data; collecting task data of a task path and filling the task data into map building data in the process that a teaching vehicle runs from a task area starting point to a task area ending point along the task path; and stopping the map building data filling function when the teaching vehicle runs to the end point of the working area, and building the target map based on all map building data. By the technical scheme, the map construction range of the target map is enlarged, the operation interval of initial positioning is improved, and the success rate of initial positioning is improved.

Description

Map construction method, device and equipment

Technical Field

The present application relates to the field of intelligent traffic technologies, and in particular, to a map construction method, apparatus, and device.

Background

The automatic parking refers to automatic parking of a vehicle without manual control, and can help a driver to automatically park. The automatic parking system may employ various methods for detecting an obstacle around the vehicle, for example, a sensor is disposed around the vehicle, an obstacle around the vehicle is detected by the sensor, or a camera is disposed around the vehicle, an obstacle around the vehicle is detected by the camera, or a radar is disposed around the vehicle, and an obstacle around the vehicle is detected by the radar. Based on the data detected by these devices (e.g., sensors, or cameras, or radar), the automated parking system is able to determine the location of the obstacle and then drive the vehicle into the parking space.

An AVP (Automated VALET PARKING) system is an application of automatic parking, and in a parking lot scenario, the AVP system can help a vehicle to complete automatic driving, automatic library searching and automatic parking for a certain distance. For example, after the vehicle arrives at the parking lot, the driver parks the vehicle at the start point of the task area, and starts the automatic parking operation by using an application program (such as APP located at the intelligent terminal, etc.), and after receiving the start command, the AVP system can automatically drive the vehicle into the parking lot (i.e., the end point of the task area).

In the related art, the functions of vehicle positioning and path planning of an automatic parking scheme are required to be set manually in advance, and the functions of real automatic vehicle positioning, automatic path planning, automatic bus-substituting parking and the like cannot be realized.

Disclosure of Invention

The application provides a map construction method, which comprises the following steps:

In the process that the teaching vehicle runs to the starting point of the task area along the backtracking path, acquiring backtracking data of the backtracking path, and storing the backtracking data; when the teaching vehicle runs to the starting point of the task area, starting a map building data filling function, and filling the backtracking data into map building data;

Collecting task data of a task path in the process that the teaching vehicle runs from the starting point of the task area to the end point of the task area along the task path, and filling the task data into map building data;

and stopping the map building data filling function when the teaching vehicle runs to the end point of the task area, and building a target map based on all map building data.

Illustratively, the collecting the trace-back data of the trace-back path and storing the trace-back data includes: when the data acquisition conditions are met each time, acquiring backtracking data of the current position of the teaching vehicle;

Judging whether the number of the backtracking data stored in the first-in first-out queue reaches n, wherein n is a positive integer;

If not, the backtracking data of the current position is saved as the last backtracking data of the first-in first-out queue; if yes, deleting the stored first trace data from the first-in first-out queue, and storing the trace data of the current position as the last trace data of the first-in first-out queue.

The determining process for meeting the data acquisition condition includes:

starting to store backtracking data into the first-in first-out queue, counting the running duration of the teaching vehicle, and determining that the data acquisition condition is met when the running duration is a preset duration threshold; or alternatively, the first and second heat exchangers may be,

Starting from the step of storing the backtracking data into the first-in first-out queue, counting the driving distance of the teaching vehicle, and determining that the data acquisition condition is met when the driving distance is a preset distance threshold.

Illustratively, the target map includes a backtracking path sub-map constructed based on the backtracking data and a task path sub-map constructed based on the task data;

after the target map is constructed based on all the mapping data, the method further comprises the following steps:

In the process that the target vehicle runs to the starting point of the task area along the backtracking path, positioning the target vehicle based on a backtracking path sub-map in the target map;

and if the target vehicle is positioned successfully before the target vehicle runs to the starting point of the task area, starting an automatic driving function when the target vehicle runs to the starting point of the task area, automatically driving the target vehicle based on a sub map of the task path in the target map, and running the target vehicle from the starting point of the task area to the ending point of the task area along the task path.

Illustratively, after the positioning the target vehicle based on the backtracking path sub-map in the target map, the method further includes: if the target vehicle is not positioned successfully when the target vehicle runs to the starting point of the task area, positioning the target vehicle based on the task path sub-map in the process that the target vehicle runs from the starting point of the task area to the ending point of the task area along the task path; and starting an automatic driving function when the target vehicle is successfully positioned, automatically driving the target vehicle based on the task path sub-map, and driving the target vehicle to the end point of the task area.

Illustratively, the locating the target vehicle based on the backtracking path sub-map in the target map includes: collecting pose information of the target vehicle in the running process of the target vehicle;

And if the distance between the target vehicle and the coverage area of the retrospective path sub-map is determined to be smaller than a threshold value based on the pose information, positioning the target vehicle based on the retrospective path sub-map.

When the teaching vehicle runs to the starting point of the task area, acquiring and storing the reference data characteristic of the starting point of the task area; during the running process of a target vehicle, collecting candidate data features of each position, and positioning the target vehicle based on the candidate data features; if the candidate data characteristic of a position is matched with the reference data characteristic, the position is positioned as the starting point of the task area, an automatic driving function is started, the target vehicle is automatically driven based on a task path sub-map in the target map, and the target vehicle is driven from the starting point of the task area to the end point of the task area along the task path.

In one possible embodiment, the backtracking data may include, but is not limited to, at least one of: image data, point cloud data, pose data, and motion data; the task data may include, but is not limited to, at least one of: image data, point cloud data, pose data, and motion data; the task area end point comprises a target parking place, and the target map is used for automatically parking a target vehicle to the target parking place.

The application provides a map construction device, which comprises:

the acquisition module is used for acquiring the backtracking data of the backtracking path and storing the backtracking data in the process that the teaching vehicle runs to the starting point of the task area along the backtracking path;

The filling module is used for starting a map building data filling function when the teaching vehicle runs to the starting point of the task area and filling the backtracking data into the map building data;

the acquisition module is further used for acquiring task data of the task path in the process that the teaching vehicle runs from the starting point of the task area to the end point of the task area along the task path;

the filling module is also used for filling the task data into the map building data;

And the construction module is used for stopping the map construction data filling function when the teaching vehicle runs to the end point of the task area and constructing a target map based on all the map construction data.

The present application provides an intelligent driving apparatus, comprising: a processor and a machine-readable storage medium storing machine-executable instructions executable by the processor;

The processor is configured to execute machine-executable instructions to perform the steps of:

The application provides a vehicle, wherein in the process that the vehicle runs to a starting point of a task area along a backtracking path, the vehicle collects backtracking data of the backtracking path and stores the backtracking data;

When the vehicle runs to the starting point of the task area, the vehicle starts a map building data filling function, and the backtracking data is filled into map building data;

In the process that the vehicle runs from the starting point of the task area to the ending point of the task area along the task path, the vehicle collects task data of the task path and fills the task data into map building data;

and stopping the map building data filling function when the vehicle runs to the end point of the task area, and building a target map based on all map building data.

As can be seen from the above technical solution, in the embodiment of the present application, when a target map is constructed, the target map includes a trace-back path sub-map constructed based on trace-back data and a task path sub-map constructed based on task data, the task path sub-map is a map of a task path between a task area starting point and a task area ending point, the trace-back path sub-map is a map of a trace-back path before the task area starting point, when a vehicle is positioned based on the target map, the vehicle can be positioned when the vehicle travels to the trace-back path, so that when the vehicle travels to the task area starting point, the vehicle is positioned successfully (instead of starting to position the vehicle when the vehicle travels to the task area starting point), thereby reducing the waiting time for positioning the vehicle, improving the accuracy of positioning the vehicle, and enabling the vehicle to travel from the task area starting point to the task area ending point based on the target map, and realizing the automatic passenger parking function. The mode can realize the self-building map and noninductive initial positioning functions of the AVP system, and greatly improves the initial positioning success rate and the use convenience of the AVP system in a self-building map scene. When the AVP system utilizes the backtracking data and the task data to construct the target map, the map construction range of the target map is enlarged, the operation interval of initial positioning is improved, and the success rate of initial positioning is improved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following description will briefly describe the drawings required to be used in the embodiments of the present application or the description in the prior art, and it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings may be obtained according to these drawings of the embodiments of the present application for a person having ordinary skill in the art.

FIG. 1 is a flow chart of a map construction method in one embodiment of the application;

FIG. 2 is a schematic diagram of error ratios of an odometer module in one embodiment of the application;

FIG. 3 is a diagram illustrating trace-back data preservation in accordance with one embodiment of the present application;

FIG. 4A is a schematic diagram of a teaching diagramming process in one embodiment of the present application;

FIG. 4B is a flow chart of a map construction method according to an embodiment of the present application;

FIG. 4C is a schematic diagram of the composition of mapping data in an embodiment of the application;

FIG. 4D is a schematic diagram of a path of a target map in one embodiment of the application;

FIG. 5A is a schematic illustration of an automated valet parking process in one embodiment of the present application;

FIG. 5B is a flow chart of a target map-based method of parking a vehicle for a customer in accordance with one embodiment of the present application;

fig. 6 is a schematic structural view of a map construction apparatus in an embodiment of the present application;

fig. 7 is a hardware configuration diagram of an intelligent driving apparatus in an embodiment of the present application.

Detailed Description

The terminology used in the embodiments of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to any or all possible combinations including one or more of the associated listed items.

It should be understood that although the terms first, second, third, etc. may be used in embodiments of the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the application. Depending on the context, furthermore, the word "if" used may be interpreted as "at … …" or "at … …" or "in response to a determination".

The embodiment of the application provides a map construction method, which can be applied to an AVP system, and is shown in FIG. 1, and is a flow diagram of the map construction method, and the method can comprise the following steps:

Step 101, in the process that the teaching vehicle runs to the starting point of the task area along the backtracking path, backtracking data of the backtracking path are collected, and the backtracking data are stored. Illustratively, the backtracking data may include, but is not limited to, at least one of: image data, point cloud data, pose data, and motion data.

For example, in the process that the teaching vehicle runs to the starting point of the task area along the backtracking path, backtracking data of the current position of the teaching vehicle can be acquired when the data acquisition condition is met each time; after the backtracking data of the current position is obtained, judging whether the number of the backtracking data stored in the first-in first-out queue reaches n, wherein n is a positive integer; if not, the backtracking data of the current position can be saved as the last backtracking data of the first-in first-out queue; if yes, deleting the stored first trace data from the first-in first-out queue, and storing the trace data at the current position as the last trace data of the first-in first-out queue.

In one possible implementation, the determining that the data acquisition condition is met may include, but is not limited to: starting from storing backtracking data into a first-in first-out queue, counting the running duration of the teaching vehicle, and determining that the data acquisition condition is met when the running duration is a preset duration threshold (which can be configured according to experience); or starting from the step of storing the backtracking data into the first-in first-out queue, counting the driving distance of the teaching vehicle, and determining that the data acquisition condition is met when the driving distance is a preset distance threshold (which can be configured according to experience).

And 102, starting a map building data filling function when the teaching vehicle runs at the starting point of the task area, and filling the backtracking data into the map building data. For example, after the mapping data filling function is started, all the stored trace-back data (i.e., n trace-back data) may be filled into the mapping data.

Step 103, collecting task data of the task path and filling the task data into the map building data in the process that the teaching vehicle runs along the task path from the starting point of the task area to the end point of the task area.

For example, after the mapping data filling function is started, each time task data of a task path is collected, the task data needs to be filled into the mapping data. Wherein the task data may include, but is not limited to, at least one of: image data, point cloud data, pose data, and motion data.

And 104, stopping the map building data filling function when the teaching vehicle runs to the end point of the task area, and building a target map based on all map building data, wherein the target map can comprise a backtracking path sub-map built based on the backtracking data and a task path sub-map built based on the task data.

For example, after stopping the map data filling function, the target map may be constructed based on all map data, and since all map data includes the backtracking data and the task data, the target map may be constructed based on the backtracking data and the task data, and the target map construction manner is not limited. The map constructed based on the backtracking data is called a backtracking path sub-map, and the map constructed based on the task data is called a task path sub-map, i.e. the target map may comprise the backtracking path sub-map and the task path sub-map.

In one possible implementation, after the target map is constructed based on all the mapping data, the target vehicle is positioned based on the retrospective path sub-map in the target map in the process that the target vehicle travels along the retrospective path to the starting point of the task region. If the target vehicle is positioned successfully before the target vehicle runs to the starting point of the task area, starting an automatic driving function when the target vehicle runs to the starting point of the task area, automatically driving the target vehicle based on the sub-map of the task path in the target map, and running the target vehicle from the starting point of the task area to the ending point of the task area along the task path. In summary, since the target map includes the backtracking path sub-map, before the target vehicle travels to the start point of the task area, the target vehicle may be positioned based on the backtracking path sub-map, so that the positioning of the target vehicle before the target vehicle travels to the start point of the task area is successful, and when the target vehicle travels to the start point of the task area, the automatic driving function may be directly started.

By way of example, the autopilot function may include, but is not limited to, an autopilot parking function, i.e., the mission area end point may include a target parking spot for automatically parking a target vehicle to the target parking spot, for example, the autopilot parking function may be initiated when the target vehicle travels to the mission area start point, and the AVP system automatically drives the target vehicle to the target parking spot based on the target map.

The method includes the steps that after a target vehicle is positioned based on a backtracking path sub-map in the target map, if the target vehicle is not positioned successfully when the target vehicle runs to a start point of a task area, the target vehicle is positioned based on the task path sub-map in a process that the target vehicle runs from the start point of the task area to an end point of the task area along a task path. And starting an automatic driving function when the target vehicle is positioned successfully, automatically driving the target vehicle based on the task path sub-map, and driving the target vehicle to a task area end point.

Illustratively, locating the target vehicle based on the backtracking path sub-map in the target map may include, but is not limited to: in the running process of the target vehicle, the pose information of the target vehicle can be acquired; if the distance between the target vehicle and the coverage area of the retrospective path sub-map is determined to be smaller than the threshold value based on the pose information, the target vehicle can be positioned based on the retrospective path sub-map in the target map.

In one possible embodiment, the reference data characteristic of the task area starting point may be collected and saved while the teaching vehicle is traveling to the task area starting point. On the basis, candidate data features of all positions are collected in the running process of the target vehicle, and the target vehicle is positioned based on the candidate data features. In the process of positioning the target vehicle based on the candidate data features, if the candidate data features of a position are matched with the reference data features, the position can be positioned as a task area starting point (namely, the positioning of the target vehicle is completed), an automatic driving function is started, the target vehicle is automatically driven based on a task path sub-map in the target map, and the target vehicle is driven from the task area starting point to a task area end point along the task path.

The map construction method according to the embodiment of the present application will be described below with reference to specific embodiments.

Before describing the map construction method of the present application, technical terms related to the present application will be described.

AVP system: in a parking lot scene, the intelligent driving system is used for helping vehicles to complete automatic driving, automatic library searching and automatic parking at a certain distance. For example, after the vehicle arrives at the parking lot, the driver parks the vehicle at the start point of the task area, and uses the application program to start the automatic parking operation, and after the AVP system receives the start command, the vehicle can be automatically driven into the parking space (i.e., the end point of the task area). In a parking lot where a high-precision map is not provided, the AVP system can realize an automatic navigation and automatic parking function of a vehicle. In order to realize the automatic parking function, the vehicle needs to be manually driven to complete the teaching and mapping in the task area (the start point of the task area to the end point of the task area) of the parking lot. After the map is built, when the vehicle approaches to the task area, the initial positioning in the built map needs to be quickly realized, the task path and scene information are obtained, and the automatic bus-substituting parking function is realized.

GNSS (Global Navigation SATELLITE SYSTEM ): GNSS is an air-based radio navigation positioning system that utilizes satellite observations to achieve the coordinates and speed of a terrestrial receiver.

IMU (Inertial Measurement Unit ): generally refers to a measurement device comprising a gyroscope and an accelerometer, and the IMU can measure motion data such as acceleration, angular velocity, and the like.

Wheel speed Sensor (WHEEL SPEED Sensor): the sensor is used for measuring the wheel rotation speed of the vehicle, and the information such as the movement speed, the movement track and the like of the vehicle can be obtained through a vehicle kinematic model.

Odometer module (Odometer Unit): the algorithm device for estimating the motion state of the carrier and recursively estimating the motion trail by using the sensor comprises an inertial odometer based on a wheel speed sensor and an IMU, a visual odometer based on a visual sensor, a laser odometer based on a laser radar and the like, and the type of the odometer module is not limited.

Tracking and positioning module (Tracking Localizer Unit): by using the observation data (such as image data and radar point cloud data) of the sensing sensor, and the relatively accurate priori pose and the reference map, the tracking and positioning module can be matched in a smaller local range to obtain the global pose relative to the map coordinate system.

Repositioning module (ReLocalization Unit): by using the observation data of the sensing sensor, and the relatively inaccurate priori pose and the reference map, the repositioning module can be matched in a smaller local range or global range to obtain the global pose relative to the map coordinate system. The repositioning module is applied to initial positioning of the unmanned vehicle/robot when the unmanned vehicle/robot first enters the map range, and is also called an initial positioning algorithm.

Combined positioning module (INTEGRATED LOCALIZATION SYSTEM): based on motion estimation and global pose information provided by algorithm devices such as a GNSS, a repositioning module, a tracking positioning module, an odometer module and the like, the combined positioning module can finally provide robust and accurate positioning information, namely the positioning information is accurate and reliable.

In order to realize the automatic bus-substituting and parking function, a map of a parking lot scene, for example, a map between a task area starting point and a task area ending point needs to be constructed first, so that when a vehicle arrives at the task area starting point, the vehicle can be positioned based on the map first, and after the vehicle is positioned successfully, the vehicle can be driven from the task area starting point to the task area ending point based on the map, thereby realizing the automatic bus-substituting and parking function. However, if the vehicle arrives at the start point of the task area, the vehicle cannot be driven from the start point of the task area to the end point of the task area based on the map, that is, the automatic bus-substituting parking function cannot be realized.

In view of the above findings, in the embodiment of the present application, a self-building diagram and a non-inductive initial positioning method applied to an AVP system are provided, and when a vehicle is driven under manual control, sensing data (such as bit data and motion data) of the vehicle is estimated in real time, and meanwhile sensing data in a last preset driving distance is saved in real time by adopting a first-in first-out method, and herein, the sensing data is recorded as backtracking data, and a corresponding path is called a backtracking path.

In this embodiment, a teaching map construction process and an automatic bus-in parking process are related, and for convenience of distinction, a vehicle in the teaching map construction process is referred to as a teaching vehicle, and a vehicle in the automatic bus-in parking process is referred to as a target vehicle.

Aiming at the teaching graph construction process, a teaching vehicle is driven to a starting point (such as an elevator opening) of a task area of a parking lot, a graph construction command is sent out, and the teaching vehicle is driven to travel to a target parking space along a task path to finish parking. After receiving the map building command, the AVP system builds a map by using the trace-back data stored before the start point of the task area and the perception data (task data) collected after the start point of the task area, so that the range of the finally built target map is the sum of the distances of the trace-back path and the task path. In the process of mapping, all the perception data are fused based on the pose provided by the combined positioning, and the self-built map is aligned with the global coordinate system adopted by the combined positioning.

In the automatic passenger-substituting parking process, after the target vehicle approaches to a certain built map (namely, a target map) range in the manual driving process, the combined positioning pose displays the target vehicle, the AVP system automatically enters a non-inductive initial positioning state, and the current perceived data and the map are matched and positioned by utilizing a repositioning algorithm. After the initial positioning is successful, the AVP system prompts that the vehicle is ready, and whether the automatic bus-in parking function is operated can be manually selected.

In summary, the self-established map and noninductive initial positioning function applied to the AVP system greatly improves the initial positioning success rate and the use convenience of the AVP system in a self-established map scene.

And a combined positioning module: the vehicle utilizes the combined positioning module to estimate global pose (such as position and pose, the position represents longitude and latitude coordinates and the like), the pose represents pitch angle, yaw angle, roll angle and the like) and motion data (which can also be called motion state (such as acceleration, angular velocity and the like) of the vehicle in real time. Under the condition of map missing, the combined positioning module can fuse the data of the GNSS signals and the odometer module in an outdoor scene to obtain accurate and continuous global pose. After the vehicle enters an indoor scene with the GNSS signals blocked, the combined positioning module can infer the global pose through the odometer module. In this case, the global pose accuracy provided by the combined positioning module gradually decreases with the increase of the driving distance, as shown in fig. 2, although the global pose accuracy gradually decreases with the increase of the driving distance, the error ratio of the odometer module is generally one percent to one thousandth, and in a scene of relatively limited driving distance such as a parking lot, the global pose error estimated based on the odometer module is limited, so that the accuracy requirement of the pose can be met. Referring to fig. 2, the combined positioning module can obtain an accurate global pose outdoors by using GNSS, and can infer the global pose indoors without a map by using the odometer module. The global pose estimation based on the odometer module will decrease with increasing distance travelled, and the trajectory of the real motion and the pose estimated by the odometer module is shown in fig. 2.

And (5) backtracking data storage: the AVP system may maintain a fifo queue that stores at most n trace data, as shown in fig. 3, each vertical line represents a location where trace data is stored once, and each rectangle represents a total travel distance for storing trace data. For example, during the driving of the teaching vehicle, a certain number n of backtracking data are stored according to a fixed driving distance interval Δd, the total driving distance of the stored data is about Δd×n, that is, one backtracking data is stored every driving distance interval Δd, when new backtracking data are stored, old backtracking data exceeding a limited number n are deleted, so that the size of the stored data is unchanged, that is, n backtracking data are stored in a common first-in first-out queue. Of course, in practical application, the method is not limited to the method of storing the fifo queue, and only n trace-back data can be stored.

For the teaching mapping process, a map construction method is provided in the embodiment of the present application, as shown in fig. 4A, for a schematic diagram of the teaching mapping process, the starting points of the task areas of the parking lot may be arbitrarily configured, and the starting points are not limited thereto, for example, the starting points of the task areas of the parking lot may be target parking spaces, i.e., the teaching vehicles need to be driven into the target parking spaces. The path between the task area start point and the task area end point is a task path. The process of teaching the vehicle to travel from the starting point to the starting point of the task area is called a backtracking path.

Referring to fig. 4B, a schematic flow chart of a map construction method may include:

Step 401, in the process that the teaching vehicle runs to the starting point of the task area along the backtracking path, backtracking data of the backtracking path are collected, and the backtracking data are stored. For example, the teaching vehicle needs to be driven from the starting point to the starting point of the task area of the parking lot, that is, the teaching vehicle needs to travel along the backtracking path to the starting point of the task area, and in this process, backtracking data of the backtracking path needs to be collected and stored.

Referring to fig. 3, when the teaching vehicle is at the starting point, the trace-back data a1 of the current position of the teaching vehicle is collected, and since the number of the trace-back data stored in the first-in first-out queue is 0, assuming that n is 3, the trace-back data a1 is stored as the last trace-back data of the first-in first-out queue. After the teaching vehicle runs Δd (i.e., a starting point+Δd) along the backtracking path, backtracking data a2 of the current position of the teaching vehicle is collected, and since the number of the backtracking data stored in the first-in first-out queue is 1, the backtracking data a2 is stored as the last backtracking data of the first-in first-out queue. After the teaching vehicle continues to travel Δd (i.e., a starting point+2Δd) along the backtracking path, backtracking data a3 of the current position of the teaching vehicle is collected, and since the number of the backtracking data stored in the first-in first-out queue is 2, the backtracking data a3 is stored as the last backtracking data of the first-in first-out queue. After the teaching vehicle continues to travel Δd (i.e., the starting point+3Δd) along the backtracking path, backtracking data a4 of the current position of the teaching vehicle is collected, and since the number of the backtracking data stored in the fifo queue is 3, it is necessary to delete the stored first backtracking data a1 from the fifo queue and store the backtracking data a4 as the last backtracking data of the fifo queue. After the teaching vehicle continues to travel Δd (i.e., the starting point+4Δd) along the backtracking path, backtracking data a5 of the current position of the teaching vehicle is collected, and since the number of the backtracking data stored in the fifo queue is 3, it is necessary to delete the stored first backtracking data a2 from the fifo queue and store the backtracking data a5 as the last backtracking data of the fifo queue. Similarly, it is apparent that up to 3 trace-back data are stored in the fifo queue.

In the above embodiment, the backtracking data includes, but is not limited to, at least one of: image data, point cloud data, pose data, and motion data. For example, cameras can be arranged around the teaching vehicle, and image data of the current position of the teaching vehicle can be acquired through the cameras. Radar can be deployed around the teaching vehicle, and point cloud data of the current position of the teaching vehicle is acquired through the radar. Pose data (namely global pose) of the current position of the teaching vehicle and motion data, wherein the pose data comprise longitude and latitude coordinates, pitch angle, yaw angle, roll angle and the like, and the motion data comprise acceleration, angular speed and the like, can be acquired through the combined positioning module.

And step 402, when the teaching vehicle runs to the starting point of the task area, a map building command is sent out, the map building command is used for starting a map building data filling function, and after the AVP system receives the map building command, trace back data can be filled into the map building data, namely all the stored trace back data (namely n trace back data) can be filled into the map building data. And, the AVP system may also collect reference data characteristics (i.e., observed data) of the start point of the task area after receiving the mapping command, and save the reference data characteristics of the start point of the task area, which may include, but is not limited to, image data and/or point cloud data.

For example, referring to fig. 4C, after receiving the mapping command, the AVP system fills all trace-back data into the mapping data in a first-in-first-out manner. For example, the first trace data in the fifo queue is sent to the mapping module, the mapping module uses the first trace data as mapping data (the following needs to participate in the mapping process), then the second trace data in the fifo queue is sent to the mapping module, the mapping module uses the second trace data as mapping data, and so on, the nth trace data in the fifo queue is sent to the mapping module, and the mapping module uses the nth trace data as mapping data. After all n pieces of backtracking data are used as the drawing construction data, the drawing construction initialization can be successfully performed through feedback teaching of a display interface.

For example, after receiving the map building command, the AVP system may further collect image data of the start point of the task area, and collect point cloud data of the start point of the task area, for example, a camera may be disposed around the teaching vehicle, and collect image data of the current position of the teaching vehicle through the camera. Radar can be deployed around the teaching vehicle, and point cloud data of the current position of the teaching vehicle is acquired through the radar. On this basis, the image data and the point cloud data can also be stored as reference data features.

Step 403, after the driver obtains feedback that the initialization of the teaching map of the AVP system is successful, driving the teaching vehicle to perform teaching traveling along the desired task path, that is, traveling from the start point of the task area to the end point of the task area along the task path. In the process that the teaching vehicle runs along the task path from the start point of the task area to the end point of the task area, task data of the task path are collected, and the task data are filled into the map building data, that is, the AVP system fills the task data obtained in real time into the map building data.

Referring to fig. 4C, in order to compose the mapping data and use the mapping data, after the mapping data filling function is started, the mapping module can keep the mapping task running in real time, after the AVP system collects the task data of the task path each time, the task data can be sent to the mapping module, and the mapping module uses the task data as the mapping data, so that the mapping data is filled with the task data.

In the above embodiments, the task data includes, but is not limited to, at least one of: image data, point cloud data, pose data, and motion data. For example, cameras can be arranged around the teaching vehicle, and image data of the current position of the teaching vehicle can be acquired through the cameras. Radar can be deployed around the teaching vehicle, and point cloud data of the current position of the teaching vehicle is acquired through the radar. Pose data (namely global pose) of the current position of the teaching vehicle and motion data, wherein the pose data comprise longitude and latitude coordinates, pitch angle, yaw angle, roll angle and the like, and the motion data comprise acceleration, angular speed and the like, can be acquired through the combined positioning module.

And step 404, stopping the map building data filling function when the teaching vehicle runs to the end point of the task area, and building the target map based on all map building data. For example, after the teaching vehicle is driven to a target parking space (i.e., a task area end point) and parking is completed, the teaching is clicked to finish. After the AVP system obtains the teaching end command, stopping the mapping data filling function (namely all mapping data are obtained), waiting for the mapping module to read all mapping data, and constructing a target map based on all mapping data, so as to complete the mapping process.

And step 405, storing a target map, wherein the target map comprises a backtracking path sub-map constructed based on backtracking data and a task path sub-map constructed based on task data. Obviously, after the map construction is completed by the map construction module, the scope of the target map includes the observation scope of the trace-back data (recorded as a trace-back path sub-map) and the observation scope of the task data (recorded as a task path sub-map), and as shown in fig. 4D, the path of the target map is composed of the trace-back path and the task path, and the scope of the target map is the observation scope along the trace-back path and the task path.

The AVP system may also feed back the target map to the display interface in the form of a thumbnail, manually confirm and name-save the target map, i.e., set a name for the target map, and save the target map, for example.

For the automatic bus-substituting parking process, a bus-substituting parking method based on a target map is provided in the embodiment of the present application, as shown in fig. 5A, for a schematic diagram of the automatic bus-substituting parking process, the starting point of a task area of a parking lot may be arbitrarily configured, such as an elevator opening, and the end point of the task area of the parking lot may be a target parking space, that is, a target vehicle (such as a target vehicle a, a target vehicle B, or a target vehicle C) needs to be driven into the target parking space. Referring to fig. 5B, a flow chart of a target map-based method for parking a host vehicle is shown, which includes:

Step 501, acquiring the pose of the target vehicle (such as providing the pose of the block target vehicle in real time by combining the positioning modules) during the running process of the target vehicle, and determining whether the target vehicle is close to the range of the target map based on the pose of the target vehicle. If so, step 502 is performed, if not, the pose of the target vehicle is continuously acquired, whether the target vehicle has approached the range of the target map is determined based on the pose of the target vehicle, and so on.

For example, during the driving process of the target vehicle, pose information of the target vehicle (such as the position of the target vehicle, such as longitude and latitude coordinates, etc.) may be obtained in real time, if it is determined based on the pose information that the distance between the target vehicle and the coverage area of the retrospective path sub-map in the target map is smaller than a threshold (the threshold may be empirically configured), that is, the distance between the longitude and latitude coordinates of the target vehicle and the coverage area of the retrospective path sub-map is smaller than the threshold, it is indicated that the target vehicle has approached the range of the target map, and step 502 is performed.

For example, after the target map is obtained, the target map may be stored in the server, the target map may be downloaded from the server during the traveling of the target vehicle, or the target map may be downloaded from the server before the traveling of the target vehicle, without limitation. Based on this target map, it may be determined whether the target vehicle has approached the range of the target map during the travel of the target vehicle.

Step 502, when the target vehicle has approached the range of the target map, the target vehicle may be positioned based on the retrospective path sub-map in the target map, that is, in the process that the target vehicle travels along the retrospective path to the start point of the task area, the target vehicle is positioned based on the retrospective path sub-map in the target map.

Referring to fig. 5A, for the target vehicle a, the target vehicle a travels along the trace-back path to the task area start point, and in the process that the target vehicle a travels along the trace-back path to the task area start point, since the target map includes the trace-back path sub map corresponding to the trace-back path, the target vehicle a can be positioned based on the trace-back path sub map. And because the coverage area of the retrospective route sub-map is larger, the target vehicle A can finish initial positioning between the starting points of the task areas with high probability.

In step 503, if the target vehicle is positioned successfully before the target vehicle travels to the start point of the task area, the automatic driving function (i.e., the automatic passenger parking function) is started when the target vehicle travels to the start point of the task area. Or if the target vehicle is positioned successfully only when the target vehicle runs to the starting point of the task area, the automatic driving function can be started when the target vehicle runs to the starting point of the task area. Or if the target vehicle is not positioned successfully when the target vehicle runs to the starting point of the task area, continuously positioning the target vehicle based on the task path sub-map in the target map in the process that the target vehicle runs from the starting point of the task area to the ending point of the task area along the task path, and starting an automatic driving function when the target vehicle is positioned successfully.

For example, referring to fig. 5A, for the target vehicle a, in the process that the target vehicle a travels along the backtracking path to the start point of the task area, the target vehicle a may be positioned based on the backtracking path sub-map, and if the target vehicle a has been positioned successfully before the target vehicle a travels to the start point of the task area, the automatic driving function may be started for the target vehicle a when the target vehicle a travels to the start point of the task area.

Or if the target vehicle a is not positioned successfully when running to the starting point of the task area, after the target vehicle a runs to the starting point of the task area, the target vehicle a needs to run to the ending point of the task area from the starting point of the task area along the task path, and in the process that the target vehicle a runs to the ending point of the task area from the starting point of the task area along the task path, the positioning of the target vehicle a based on the task path sub map is continued until the positioning of the target vehicle a is successful, and the automatic driving function is started for the target vehicle a.

For another example, since the target vehicle B is not traveling along the retrospective route to the start point of the task area, the target vehicle B cannot be positioned based on the retrospective route sub-map, that is, the noninductive initial positioning is completed only with a small probability before the start point of the task area. Obviously, if the target vehicle B is not positioned successfully (the noninductive initial positioning is not successful) when the target vehicle B is driven to the vicinity of the start point of the task area, the positioning of the target vehicle B is completed in the following manner:

during traveling of the target vehicle B, candidate data features (such as image data and/or point cloud data) of each position of the target vehicle B (i.e., each position during traveling) are collected, and the target vehicle B is positioned based on the candidate data features. For example, if the candidate data feature of a location (i.e., the start point of the task area) matches the reference data feature (e.g., the image data and/or the point cloud data) of the start point of the task area, i.e., the similarity between the candidate data feature and the reference data feature is greater than a similarity threshold (configured empirically), the location may be located as the start point of the task area, completing the location of the target vehicle B, and starting the autopilot function.

In summary, the target vehicle B may be located based on the candidate data features of each position during the driving of the target vehicle B, that is, the target vehicle B may be successfully located at the start point of the task area.

Or if the target vehicle B is not positioned successfully when running to the starting point of the task area, after the target vehicle B runs to the starting point of the task area, the target vehicle B needs to run from the starting point of the task area to the ending point of the task area along the task path, and in the process that the target vehicle B runs to the ending point of the task area from the starting point of the task area along the task path, the positioning of the target vehicle B based on the task path sub map is continued until the positioning of the target vehicle B is successful, and the automatic driving function is started for the target vehicle B.

For another example, in the case of the target vehicle C, the target vehicle C cannot be positioned based on the backtracking path sub-map without passing through the task area start point, the target vehicle C needs to travel along the task path from the task area start point to the task area end point, the target vehicle C is positioned based on the task path sub-map in the process of traveling along the task path from the task area start point to the task area end point until the positioning of the target vehicle C is successful, the automatic driving function is started for the target vehicle C, and the probability of the initial positioning success of the target vehicle C increases as the travel distance of the target vehicle C in the task path increases.

Step 504, after the automatic driving function (i.e. the automatic bus parking function) is started, the target vehicle is automatically driven based on the task path sub-map in the target map, and the target vehicle is driven from the start point of the task area to the end point of the task area along the task path. For example, after the target vehicle is successfully positioned, the AVP system prompts that the automatic valet parking function is ready, the driver confirms that the automatic valet parking function is started manually, after the driver confirms that the automatic valet parking function is started manually, the driver can leave the target vehicle, the AVP system automatically drives the target vehicle based on the task path sub-map, and the target vehicle is driven from the starting point of the task area to the ending point of the task area along the task path, so that automatic navigation and automatic parking are realized.

In one possible implementation manner, when the target vehicle runs to the starting point of the task area, if the target vehicle does not have the initial positioning success, the AVP system does not prompt the user that the positioning is successful, and can start the AVP function. If the initial positioning of the starting point is unsuccessful, the user is instructed to drive the target vehicle to continue running, and the task path positioning is performed until the positioning is successful.

As can be seen from the above technical solutions, in the embodiments of the present application, the target map includes a trace-back path sub-map and a task path sub-map, where the task path sub-map is a map of a task path between a task area start point and a task area end point, and the trace-back path sub-map is a map of a trace-back path before the task area start point, when the vehicle is positioned based on the target map, the vehicle can be positioned when the vehicle travels to the trace-back path, so that when the vehicle travels to the task area start point, the vehicle is already positioned successfully, and thus the vehicle can travel from the task area start point to the task area end point based on the target map, and an automatic passenger parking function is implemented. The mode can realize the self-building map and noninductive initial positioning functions of the AVP system, and greatly improves the initial positioning success rate and the use convenience of the AVP system in a self-building map scene. When the AVP system utilizes the backtracking data and the task data to construct the target map, the map construction range of the target map is enlarged, the operation interval of initial positioning is improved, and the success rate of initial positioning is improved. In the mode, the backtracking data and the task data are utilized to build the map together, so that the map range is wider, and early positioning success is facilitated. The combined positioning information displays the vehicle approaching the map range, then the positioning function is triggered, the vehicle is supported to approach the starting point of the task area from different paths, and when the running path before the starting point of the task area is overlapped with the backtracking path when the map is built, the vehicle has a longer initial positioning interval, and the initial positioning success rate is higher. The AVP system maintains the trace-back data with fixed storage size in real time, and uses the trace-back data and task data to build the graph after obtaining the graph building command, so as to ensure the sufficiency of the graph building scope.

Based on the same application concept as the above method, a map construction device is provided in an embodiment of the present application, and referring to fig. 6, the map construction device is a schematic structural diagram of the map construction device, and the device may include:

The acquisition module 61 is configured to acquire trace-back data of a trace-back path and store the trace-back data in a process that a teaching vehicle travels along the trace-back path to a start point of a task area;

The filling module 62 is configured to start a mapping data filling function when the teaching vehicle travels to the start point of the task area, and fill the backtracking data into mapping data;

The collecting module 61 is further configured to collect task data of the task path during a process that the teaching vehicle travels along the task path from the task area start point to the task area end point;

The filling module 62 is further configured to fill the task data into mapping data;

and a construction module 63, configured to stop the map building data filling function when the teaching vehicle travels to the end point of the task area, and construct the target map based on all the map building data.

Illustratively, the collecting module 61 collects trace-back data of the trace-back path, and is specifically configured to: when the data acquisition conditions are met each time, acquiring backtracking data of the current position of the teaching vehicle; judging whether the number of the backtracking data stored in the first-in first-out queue reaches n, wherein n is a positive integer; if not, the backtracking data of the current position is saved as the last backtracking data of the first-in first-out queue; if yes, deleting the stored first trace data from the first-in first-out queue, and storing the trace data of the current position as the last trace data of the first-in first-out queue.

Illustratively, the acquisition module 61 is specifically configured to, when the data acquisition condition is satisfied:

In a possible implementation, the target map includes a backtracking path sub-map constructed based on the backtracking data and a task path sub-map constructed based on the task data, and the apparatus further includes (not shown in fig. 6): the positioning module is used for positioning the target vehicle based on a retrospective path sub-map in the target map in the process that the target vehicle runs to the starting point of the task area along the retrospective path; and the automatic driving module is used for starting an automatic driving function when the target vehicle runs to the task area starting point if the target vehicle is positioned successfully before the target vehicle runs to the task area starting point, automatically driving the target vehicle based on a task path sub-map in the target map, and running the target vehicle from the task area starting point to the task area ending point along the task path.

The positioning module is further configured to, if the target vehicle is not positioned successfully when the target vehicle travels to the task area starting point, position the target vehicle based on the task path sub-map in a process that the target vehicle travels from the task area starting point to the task area ending point along the task path; and the automatic driving module is also used for starting an automatic driving function when the target vehicle is positioned successfully, automatically driving the target vehicle based on the task path sub-map and driving the target vehicle to the task area terminal point.

The positioning module is specifically configured to, when positioning the target vehicle based on a backtracking path sub-map in the target map: collecting pose information of a target vehicle in the running process of the target vehicle; and if the distance between the target vehicle and the coverage area of the retrospective path sub-map is determined to be smaller than a threshold value based on the pose information, positioning the target vehicle based on the retrospective path sub-map.

Illustratively, the collecting module 61 is further configured to collect and store a reference data feature of the task area starting point when the teaching vehicle travels to the task area starting point;

the positioning module is further used for collecting candidate data characteristics of each position in the running process of the target vehicle and positioning the target vehicle based on the candidate data characteristics;

and the automatic driving module is further used for positioning a position as the starting point of the task area if the candidate data characteristic of the position is matched with the reference data characteristic, starting an automatic driving function, automatically driving the target vehicle based on a task path sub-map in the target map, and driving the target vehicle from the starting point of the task area to the ending point of the task area along the task path.

Based on the same application concept as the above method, an intelligent driving device is provided in an embodiment of the present application, and as shown in fig. 7, the intelligent driving device may include: a processor 71 and a machine-readable storage medium 72, the machine-readable storage medium 72 storing machine-executable instructions executable by the processor 71; the processor 71 is configured to execute machine executable instructions to implement the steps of:

And stopping the map building data filling function when the teaching vehicle runs to the end point of the task area, and building a target map based on all map building data. Optionally, the target map includes a backtracking path sub-map constructed based on the backtracking data and a task path sub-map constructed based on the task data.

Based on the same application conception as the method, the embodiment of the application also provides a vehicle, wherein in the process that the vehicle runs to the starting point of a task area along a backtracking path, the vehicle collects backtracking data of the backtracking path and stores the backtracking data;

And stopping the map building data filling function when the vehicle runs to the end point of the task area, and building a target map based on all map building data. Optionally, the target map includes a backtracking path sub-map constructed based on the backtracking data and a task path sub-map constructed based on the task data.

Based on the same application concept as the above method, the embodiment of the present application further provides a machine-readable storage medium, where a number of computer instructions are stored, where the computer instructions can implement the map construction method disclosed in the above example of the present application when executed by a processor.

Wherein the machine-readable storage medium may be any electronic, magnetic, optical, or other physical storage device that can contain or store information, such as executable instructions, data, or the like. For example, a machine-readable storage medium may be: RAM (Radom Access Memory, random access memory), volatile memory, non-volatile memory, flash memory, a storage drive (e.g., hard drive), a solid state disk, any type of storage disk (e.g., optical disk, dvd, etc.), or a similar storage medium, or a combination thereof.

The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. A typical implementation device is a computer, which may be in the form of a personal computer, laptop computer, cellular telephone, camera phone, smart phone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or a combination of any of these devices.

For convenience of description, the above devices are described as being functionally divided into various units, respectively. Of course, the functions of each element may be implemented in the same piece or pieces of software and/or hardware when implementing the present application.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the application may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

Moreover, these computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.

Claims

1. A method of map construction, the method comprising:

In the process that the teaching vehicle runs to the starting point of the task area along the backtracking path, acquiring backtracking data of the backtracking path, and storing the backtracking data; when the teaching vehicle runs to the starting point of the task area, if the AVP system receives a map building command, a map building data filling function is started, and the backtracking data is filled into map building data; after the AVP system receives the drawing building command, acquiring reference data characteristics of a starting point of a task area, wherein the reference data characteristics comprise image data and/or point cloud data; the reference data features are used for positioning the position in the driving process as a task area starting point;

Stopping the map building data filling function when the teaching vehicle runs to the end point of the task area, and building a target map based on all map building data; the target map comprises a backtracking path sub-map constructed based on the backtracking data and a task path sub-map constructed based on the task data;

If the target vehicle is successfully positioned before the target vehicle runs to the starting point of the task area, starting an automatic driving function when the target vehicle runs to the starting point of the task area, automatically driving the target vehicle based on a task path sub-map in the target map, and running the target vehicle from the starting point of the task area to the ending point of the task area along the task path;

If the target vehicle is not positioned successfully when the target vehicle runs to the starting point of the task area, positioning the target vehicle based on the task path sub-map in the process that the target vehicle runs from the starting point of the task area to the ending point of the task area along the task path; starting an automatic driving function when the target vehicle is successfully positioned, automatically driving the target vehicle based on the task path sub-map, and driving the target vehicle to the task area end point;

When a target vehicle does not travel to the starting point of the task area along the backtracking path, collecting candidate data features of each position in the traveling process of the target vehicle, and positioning the target vehicle based on the candidate data features; if the candidate data characteristic of a position is matched with the reference data characteristic, the position is positioned as the starting point of the task area, an automatic driving function is started, the target vehicle is automatically driven based on a task path sub-map in the target map, and the target vehicle is driven from the starting point of the task area to the end point of the task area along the task path.

2. The method of claim 1, wherein the step of determining the position of the substrate comprises,

The collecting the backtracking data of the backtracking path and storing the backtracking data comprises the following steps:

When the data acquisition conditions are met each time, acquiring backtracking data of the current position of the teaching vehicle;

3. The method of claim 2, wherein the step of determining the position of the substrate comprises,

The determining process for meeting the data acquisition condition comprises the following steps:

4. The method of claim 1, wherein the locating the target vehicle based on a backtracking path sub-map in the target map comprises:

collecting pose information of the target vehicle in the running process of the target vehicle;

5. The method of any of claims 1-4, wherein the backtracking data comprises at least one of: image data, point cloud data, pose data, and motion data; the task data includes at least one of: image data, point cloud data, pose data, and motion data; the task area end point comprises a target parking place, and the target map is used for automatically parking a target vehicle to the target parking place.

6. A map construction apparatus, characterized in that the apparatus comprises:

The filling module is used for starting a graph building data filling function and filling the backtracking data into the graph building data if the AVP system receives a graph building command when the teaching vehicle runs to the starting point of the task area;

The acquisition module is also used for acquiring reference data characteristics of a starting point of the task area after the AVP system receives the drawing building command, wherein the reference data characteristics comprise image data and/or point cloud data; the reference data features are used for positioning the position in the driving process as a task area starting point;

And collecting task data of the task path in the process that the teaching vehicle runs from the starting point of the task area to the end point of the task area along the task path;

The construction module is used for stopping the map building data filling function when the teaching vehicle runs to the end point of the task area and constructing a target map based on all map building data; the target map comprises a backtracking path sub-map constructed based on the backtracking data and a task path sub-map constructed based on the task data;

The positioning module is used for positioning the target vehicle based on a retrospective path sub-map in the target map in the process that the target vehicle runs to the starting point of the task area along the retrospective path;

The automatic driving module is used for starting an automatic driving function when the target vehicle runs to the task area starting point if the target vehicle is positioned successfully before the target vehicle runs to the task area starting point, automatically driving the target vehicle based on a task path sub-map in the target map, and running the target vehicle from the task area starting point to the task area ending point along the task path;

The positioning module is further configured to, if the target vehicle is not positioned successfully when the target vehicle travels to the task area starting point, position the target vehicle based on the task path sub-map in a process that the target vehicle travels from the task area starting point to the task area ending point along the task path; the automatic driving module is further used for starting an automatic driving function when the target vehicle is successfully positioned, automatically driving the target vehicle based on the task path sub-map and driving the target vehicle to the task area terminal;

the positioning module is further configured to collect candidate data features of each position during a driving process of the target vehicle when the target vehicle does not travel to the task area starting point along the backtracking path, and position the target vehicle based on the candidate data features; and the automatic driving module is further used for positioning a position as the starting point of the task area if the candidate data characteristic of the position is matched with the reference data characteristic, starting an automatic driving function, automatically driving the target vehicle based on a task path sub-map in the target map, and driving the target vehicle from the starting point of the task area to the ending point of the task area along the task path.

7. An intelligent driving apparatus, comprising: a processor and a machine-readable storage medium storing machine-executable instructions executable by the processor;

8. A vehicle is characterized in that,

In the process that the vehicle runs to the starting point of a task area along a backtracking path, the vehicle collects backtracking data of the backtracking path and stores the backtracking data;

When the vehicle runs to the starting point of the task area, if the AVP system of the vehicle receives a map building command, a map building data filling function is started, and the backtracking data is filled into map building data; after the AVP system receives the drawing building command, acquiring reference data characteristics of a starting point of a task area, wherein the reference data characteristics comprise image data and/or point cloud data; the reference data features are used for positioning the position in the driving process as a task area starting point;

When the vehicle runs to the end point of the task area, stopping the map building data filling function by the vehicle, and building a target map based on all map building data; the target map comprises a backtracking path sub-map constructed based on the backtracking data and a task path sub-map constructed based on the task data;

Positioning the vehicle based on a retrospective path sub-map in the target map in the process that the vehicle runs to the starting point of the task area along the retrospective path;

If the vehicle is positioned successfully before the vehicle runs to the starting point of the task area, starting an automatic driving function when the vehicle runs to the starting point of the task area, automatically driving the vehicle based on a sub map of the task path in the target map, and running the vehicle from the starting point of the task area to the ending point of the task area along the task path;

If the vehicle is not positioned successfully when the vehicle runs to the starting point of the task area, positioning the vehicle based on the task path sub-map in the process that the vehicle runs from the starting point of the task area to the ending point of the task area along the task path; starting an automatic driving function when the vehicle is positioned successfully, automatically driving the vehicle based on the task path sub-map, and driving the vehicle to the end point of the task area;

When the vehicle does not travel to the starting point of the task area along the backtracking path, collecting candidate data features of each position in the traveling process of the vehicle, and positioning the vehicle based on the candidate data features; if the candidate data characteristic of a position is matched with the reference data characteristic, the position is positioned as the starting point of the task area, an automatic driving function is started, the vehicle is automatically driven based on a task path sub-map in the target map, and the vehicle is driven from the starting point of the task area to the end point of the task area along the task path.