CN115384553A - Method, device, equipment and medium for generating lane track - Google Patents

Abstract

The invention provides a method for generating a lane track, and particularly relates to the technical field of automatic driving, wherein the method comprises the following steps: acquiring upstream data, wherein the upstream data comprises map data, perception data and vehicle positioning; inputting the upstream data into a lane generation model; performing data conversion on the upstream data; performing self-checking on the map data and the perception data, judging whether the self-checking is passed or not, and if the self-checking is not passed, repairing the map data and the perception data; if the self-checking passes, dividing the map data and the perception data into different levels; and processing the data of each grade according to the vehicle positioning to generate a plurality of candidate lane sets. The invention can effectively improve the decision-making capability of the automatic driving system and realize safe forward running of the vehicle.

Description

Method, device, equipment and medium for generating lane track

Technical Field

The application relates to the technical field of automatic driving, in particular to a method, a device, equipment and a medium for generating lane tracks.

Background

The automatic driving vehicle is a comprehensive intelligent system integrating multiple functions of environment perception, planning decision, behavior control and execution and the like, and comprises multidisciplinary knowledge such as machinery, control, sensor technology, signal processing, mode recognition, artificial intelligence, computer technology and the like. The development of the intelligent vehicle with the autonomous driving capability has important practical significance for developing vehicle active safety auxiliary driving products with the independent intellectual property rights of China, improving the intelligent level of automobiles with independent brands of China, improving the road traffic safety condition and developing an intelligent traffic system.

In the automatic driving vehicle, decision planning is a key technology, and an upstream data module is processed and reconstructed through a decision module. However, frequent changes of the upstream data format bring inconvenience to the decision algorithm, and when the upstream data is wrong or defective, corresponding countermeasures are lacked to ensure that the vehicle moves ahead in a safe lane.

Disclosure of Invention

In view of the above-mentioned shortcomings of the prior art, the present invention provides a method for generating a lane track to ensure the safe forward movement of a vehicle.

The invention provides a method for generating a lane track, which comprises the following steps:

acquiring upstream data, wherein the upstream data comprises map data, perception data and vehicle positioning;

inputting the upstream data into a lane generation model;

performing data conversion on the upstream data;

performing self-checking on the map data and the perception data, judging whether the self-checking is passed or not, and if the self-checking is not passed, repairing the map data and the perception data; if the self-checking is passed, dividing the map data and the perception data into different grades; and

and processing the data of each grade according to the vehicle positioning to generate a plurality of candidate lane sets.

In an embodiment of the present invention, the map data includes dynamic map data and static map data, and the map data and the sensing data are divided into a high-precision map confidence level, a static map limping level, and a sensing lane line slow-moving level according to whether the static map data and the dynamic map data are defective.

In an embodiment of the present invention, the dynamic map data includes road object data, map coordinate data, map relationship data, and lane-level guidance data.

In an embodiment of the invention, the static map data includes road data, lane data, traffic signal data and logical relationship data.

In an embodiment of the invention, when the dynamic map data is defective, the vehicle locates a nearest road segment according to the static map lameness level matching, and selects a straight road segment to explore and move ahead.

In an embodiment of the present invention, after the vehicle locates the nearest road segment according to the static map lameness level matching, the method further includes the following steps: and matching the vehicles with all lanes under the road section, and selecting a straight lane to explore ahead.

In an embodiment of the present invention, the set of candidate lanes includes lane center lines, lane boundary lines, and lane lengths.

The present invention also provides a lane trajectory generation device, characterized in that the device includes:

the data acquisition module is used for acquiring upstream data, and the upstream data comprises map data, perception data and vehicle positioning;

the data conversion module inputs the upstream data into a lane generation model and performs data conversion on the upstream data;

the data self-checking and cognition module is used for carrying out self-checking on the map data and the perception data, judging whether the self-checking is passed or not, and repairing the map data and the perception data if the self-checking is not passed; if the self-checking passes, dividing the map data and the perception data into different levels; and

and the lane generation module is used for processing the data of each grade according to the vehicle positioning to generate a plurality of candidate lane sets.

The present invention also provides an electronic device, including:

one or more processors;

and the storage device is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the electronic equipment realizes the generation method of the algorithm model of the vehicle-mounted terminal processor.

The present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor of a computer, causes the computer to execute the method for generating an algorithm model of a vehicle-mounted terminal processor.

The invention has the beneficial effects that: the method inputs the acquired upstream data into a lane generation model to complete data conversion, performs self-checking and cognitive classification on the upstream data, processes the upstream data according to different grades, and acquires a plurality of candidate lane sets. The method solves the problem of adaptation work items brought to a decision algorithm by frequent changes of upstream data formats, and when errors and defects exist in the upstream data, corresponding countermeasures are provided for exploring and advancing the vehicle, so that the safe advancing of the vehicle is ensured.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application. It is obvious that the drawings in the following description are only some embodiments of the application, and that for a person skilled in the art, other drawings can be derived from them without inventive effort. In the drawings:

FIG. 1 is an implementation environment diagram illustrating the generation of lane tracks in an exemplary embodiment of the present application;

fig. 2 is a flowchart illustrating a method of generating a lane trajectory according to an exemplary embodiment of the present application;

FIG. 3 is a block diagram of a lane generation model shown in an exemplary embodiment of the present application;

FIG. 4 is a flow diagram illustrating a level of employing static map lameness in accordance with an exemplary embodiment of the present application;

FIG. 5 is a schematic illustration of a road segment shown in an exemplary embodiment of the present application;

FIG. 6 is a lane schematic shown in an exemplary embodiment of the present application;

FIG. 7 is a schematic diagram illustrating a specific implementation of a matching link according to an exemplary embodiment of the present application;

FIG. 8 is a schematic diagram illustrating a specific implementation of a matching lane according to an exemplary embodiment of the present application;

FIG. 9 is a schematic illustration of a overlength lane centerline reference strategy shown in an exemplary embodiment of the present application;

FIG. 10 is an ultra short lane centerline reference strategy schematic shown in an exemplary embodiment of the present application;

FIG. 11 illustrates an overall architecture diagram of a decision suitable for use in implementing embodiments of the present application;

fig. 12 is a block diagram of a lane trajectory generation apparatus shown in an exemplary embodiment of the present application;

FIG. 13 illustrates a schematic structural diagram of a computer system suitable for use in implementing the electronic device of an embodiment of the present application.

Detailed Description

Other advantages and effects of the present invention will become apparent to those skilled in the art from the disclosure of the present specification, wherein the following description is made for the embodiments of the present invention with reference to the accompanying drawings and the preferred embodiments. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention, and are not intended to limit the scope of the present invention.

It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the drawings only show the components related to the present invention rather than being drawn according to the number, shape and size of the components in actual implementation, and the type, amount and proportion of each component in actual implementation can be changed freely, and the layout of the components can be more complicated.

In the following description, numerous details are set forth to provide a more thorough explanation of embodiments of the present invention, however, it will be apparent to one skilled in the art that embodiments of the present invention may be practiced without these specific details, and in other embodiments, well-known structures and devices are shown in block diagram form, rather than in detail, in order to avoid obscuring embodiments of the present invention.

Firstly, it should be noted that decision planning is one of the key parts of automatic driving, and task decision is performed according to driving requirements by fusing multi-sensing technology. In order to enable the vehicle in automatic driving to avoid possible obstacles, a plurality of lane tracks are planned by setting constraint conditions. And the vehicle selects the optimal lane track as the vehicle running track so as to reach the final destination.

The planning of the trajectory is an important part of the automatic driving behavior, and when the road environment is complex, the problem of planning the movement trajectory of the vehicle becomes complex. Therefore, a model for improving decision-making capability is designed, the generation of the optimal lane track is realized, and various driving behaviors can be smoothly and accurately completed in the driving process of the vehicle.

Fig. 1 is a schematic diagram of an implementation environment of lane trajectory generation according to an exemplary embodiment of the present application. As shown in fig. 1, in the vehicle driving process, navigation is implemented through navigation map software installed on the intelligent terminal 110, and the navigation map software performs lane track generation, that is, a network request is made to the navigation server 120 according to the domain name of the navigation server 120, and a feasible lane track is generated at the navigation server 120 according to the acquired upstream data. The acquisition of the upstream data is realized by the sensor 130, and the collection of a plurality of data such as vehicle detection, road detection and the like is completed.

The intelligent terminal 110 shown in fig. 1 may be any terminal device supporting installation of navigation map software, such as a smart phone, a vehicle-mounted computer, a tablet computer, a notebook computer, or a wearable device, but is not limited thereto. The navigation server 120 shown in fig. 1 is a navigation server, and may be, for example, an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a CDN (Content Delivery Network), and a big data and artificial intelligence platform, which is not limited herein. The intelligent terminal 210 may communicate with the navigation server 120 through a wireless network such as 3G (third generation mobile information technology), 4G (fourth generation mobile information technology), 5G (fifth generation mobile information technology), etc., which is not limited herein. The sensor 130 may be a lidar, a camera, a millimeter wave radar, an ultrasonic radar, a velocity and acceleration sensor, and the like, although not limited thereto.

The problems noted above have general applicability in general travel scenarios. It can be seen that, in the case of frequent change of the acquired upstream data format and data error or defect, various problems may be caused because safe vehicle movement cannot be guaranteed. To solve these problems, embodiments of the present application respectively propose a lane trajectory generation method, a lane trajectory generation apparatus, an electronic device, a computer-readable storage medium, and a computer program product, which will be described in detail below.

Referring to fig. 2, fig. 2 is a flowchart illustrating a method for generating a lane track according to an exemplary embodiment of the present application. The method may be applied to the implementation environment shown in fig. 1 and specifically executed by the intelligent terminal 110 in the implementation environment. It should be understood that the method may be applied to other exemplary implementation environments and is specifically executed by devices in other implementation environments, and the embodiment does not limit the implementation environment to which the method is applied.

As shown in fig. 2, in an exemplary embodiment, the method for generating the lane trajectory at least includes steps S210 to S250, which are described in detail as follows:

step S210, obtaining upstream data, where the upstream data includes map data, perception data, and vehicle positioning.

It should be noted that the prediction module in the decision planning of the autopilot system may be one of the direct sources of upstream data. The method carries out behavior prediction on an object perceived and identified by a vehicle, converts a predicted result into a time-space dimensional track and transmits the time-space dimensional track to a subsequent module.

In this embodiment, the map data is high-precision map data, which includes static map data and dynamic map data, and the high-precision map data has higher fineness and richness compared with a common map. The static map data includes road data, lane data, traffic signal data, and logical relationship data. Specifically, the road data includes a link number, a link length, a link type, a road grade, and the like. Among them, link types such as express way, ramp, urban road, dead road, and the like. Road grades such as national road, provincial road, primary road, secondary road, county road, rural road, county-rural interior road, dead road, and the like. The lane data includes lane attributes and lane lines. The lane attributes include, for example, lane indexes, lane types, lane speed limits, left lane line indexes, right lane line indexes, center line indexes, arrows in the lane, lane connection relations, and the like. Lane lines such as lane line index, lane line type, lane line attributes, and lane line track points, etc. The traffic signal data includes ground identification, traffic light information, and traffic sign information. The ground mark is, for example, a ground mark type, a distance from the ground mark to a link (road segment) starting point, absolute coordinates of a ground mark geometric shape, and the like. Traffic light information such as longitudinal position, lateral position, relative altitude, and absolute coordinates. The logic relation data comprises judging whether the link is a crossing link, judging whether the current link is on a navigation path, dividing and converging the current link, judging whether the link is a tunnel and judging the relative driving direction of the current link. Among them, the split and merge state is such as the type of road branch point, the road branch point, and the distance to the link start point. And judging that the current link is in other directions such as bidirectional, forward and reverse relative to the driving direction. In other embodiments, the static map data also includes other arbitrary data.

As will be appreciated, the dynamic map data includes road object data, map coordinate data, map relationship data, and lane-level guidance data. Meanwhile, the search range of the dynamic map data is 0-5 km in the vehicle advancing direction. In the present embodiment, the dynamic map data is used to acquire various road-related information within a range of 2km ahead of the vehicle. Specifically, the road object data includes tunnel information, toll station information, construction area information, and ramp information. The tunnel, the toll station, the construction area and the like are special areas, and the tunnel information, the toll station information and the construction area information comprise types, lengths of the nearest special areas, types of relation between the current position and the special areas, distances between the current position and the entrances and exits of the special areas and the like. The map coordinate data includes information about map coordinate points. The map coordinate points include information related to the map coordinate points, such as the number of lanes, lane numbers, link id (road segment number) where the current position is located, a distance from the current link end position, and longitude and latitude coordinates of a currently set target point. The map relation data requests, for example, a positioning point of a map and determines whether a vehicle is within the map, etc. The lane-level guidance data includes guidance information. The guidance information includes, for example, the relationship between the navigation plan and the ramp, link id on the navigation path, and the position of the feasible lane and the ramp relative to the main road. In other embodiments, the dynamic map data also includes other arbitrary data.

The real-time positioning of the vehicle on the path can be obtained by means of the installed positioning module. In the present embodiment, the real-time position of the vehicle is acquired by, for example, an installed GNSS (Global Navigation Satellite System) positioning module. In other embodiments, the real-time position of the vehicle may be obtained by a Positioning module that uses other Positioning technologies to realize Positioning, such as a GPS (Global Positioning System), an LBS (Location Based Service), and the like.

Step 220, inputting the upstream data into a lane generation model.

Since safe operation of the vehicle is required during automatic driving, processing and reconstruction of upstream data are required. The acquired upstream data is input into a lane generation model, and the data is processed through the model, so that unified data input is provided for a decision algorithm, the decision-making capability of automatic driving is improved, a plurality of lane track routes are planned for a driving vehicle, and the safe forward of the vehicle is ensured.

Step 230, performing data conversion on the upstream data.

The sensing data of the vehicle, the positioning longitude and latitude of the vehicle, and the dynamic map data and the static map data provided by the high-precision map data have different formats and need to be converted into a uniform format. In this embodiment, for example, the vehicle position, the destination position, the link id of the vehicle, the number of lanes, the lane number, the link ending position distance of the vehicle distance, and the map data are respectively converted into formats, and different data are converted into respective preset uniform format forms, so as to analyze and process the data in the lane generation model.

Step 240, performing self-inspection on the map data and the perception data, judging whether the self-inspection is passed or not, and if the self-inspection is not passed, repairing the map data and the perception data; and if the self-checking passes, dividing the map data and the perception data into different levels.

And inputting the upstream data into the lane generation model, and performing data self-checking and cognitive grading after the data conversion process is completed. Fig. 3 is a structural diagram of a lane generation model according to an exemplary embodiment of the present application, and as shown in fig. 3, self-checking is performed on high-precision map data, for example, whether dynamic map data and static map data exist or not, whether navigation information exists and integrity is satisfied or not, checking a current road segment, a navigation path, a lane index, a lane line index, and the like. And carrying out self-checking on the sensing data, for example, judging whether a sensing lane line exists or not, judging whether the curvature of the sensing lane line meets non-integrity constraint or not, and the like. After the high-precision map data and the perception data are respectively subjected to self-checking, whether the self-checking passes or not is judged, if the self-checking does not pass, the high-precision map data and the perception data are repaired, and if the self-checking passes, the high-precision map data and the perception data are classified into different grades. In the present embodiment, three levels are divided, such as a high-precision map confidence level, a static map limping level, and a perception lane line buffer level.

Step 250, processing the data of each grade according to the vehicle positioning, thereby generating a plurality of candidate lane sets.

And when the information of the dynamic map data and the static map data is relatively complete and local defects can exist, the forward movement of the vehicle is realized by adopting a high-precision map confidence level. Firstly, data correction is carried out, the number of a lane where a vehicle is located and the distance between the left boundary and the right boundary of the lane where the vehicle is located are obtained, positioning correction of the vehicle is carried out according to a perception lane line, and lane boundary correction is carried out according to the perception lane line. Meanwhile, safety inspection is carried out, and navigation indexes, link indexes, feasible lane sizes and the like during safe running of the vehicle are obtained. And then establishing a mapping table, and mapping the data sensed by the vehicle into data for safe operation of the vehicle. The mapping tables include, for example, { link _ id, index }, { link _ line, index }. The vehicle utilizes the sensing data and the vehicle positioning to explore all lane serial numbers within a certain distance according to the high-precision map data, all feasible lanes in the process of reaching the destination are obtained in the process of advancing the vehicle, filling marks are carried out on the feasible lanes, and therefore a plurality of candidate lane sets are obtained.

And when the dynamic map data is defective, the vehicle moves forwards by adopting a static map lameness level. And navigating the vehicle according to the static map data and the vehicle positioning, and moving forwards until the position of the vehicle is at the tail end of the map or meets an intersection as long as a road section exists in front of the vehicle. At the moment, the dynamic map data are verified, when problems occur, the vehicle runs in a centering mode by using the static map data, meanwhile, the UDLC (Universal Digital Loop Carrier) is supported, manual lane changing of the vehicle to a ramp is supported, and the vehicle is not supported to directly go onto the ramp.

When no high-precision map data exists and no vehicle is positioned, the lane is advanced by adopting a sensing lane line slow-moving level. At the moment, the vehicle is controlled to slowly move by means of the sensing lane line, and the vehicle can safely move forwards.

Fig. 4 is a flow diagram illustrating a level of employing static map lameness in accordance with an exemplary embodiment of the present application. As shown in fig. 4, the self-vehicle position, i.e., the position of the vehicle, is first determined by positioning. And then judging whether static map data or dynamic map data exist or not, if not, ending the vehicle exploration, and if so, performing positioning matching. Specifically, the positioning matching is performed by first performing link matching, and then lane matching is performed according to the link matching, so that the vehicle can search for a front path. If the vehicle reaches the end of the map, namely no route exists in front of the search, the vehicle search is ended, and if the vehicle searches for a route in front of the search, a plurality of candidate lane sets are decided and output. As shown in fig. 5, the vehicle always searches within a range of 2km in front of the vehicle and 50 m behind the vehicle and moves forward through link matching search. The vehicle is searched for by link matching as shown in fig. 6, and the vehicle is, for example, a black arrow portion in fig. 6. A road section comprises a plurality of lanes, and the vehicle explores and selects a proper lane so as to ensure safe driving.

FIG. 7 is a schematic diagram illustrating a specific implementation of a matching link according to an exemplary embodiment of the present application. As shown in fig. 7, before the link is matched, the vehicle performs the matching search within a certain range, for example, within a dashed circle in fig. 7. And matching and positioning the link closest to the vehicle according to the driving direction and the distance of the vehicle. The static map data is used as the map basis for continuous driving, and if the dynamic map data before disappearance exists, the link id at the moment before disappearance can be acquired as the map basis for continuous driving. When link matching is completed, the vehicle is located, for example, on the L1 road segment of fig. 7, and proceeds along the road segment. And the vehicles are preferably selected to run straight according to the connection relation of each road section and the included angle of the joint of each road section. In this embodiment, the vehicle preferably selects the L2 road section to go straight according to the included angle between the connection of the road section L1 and the road section L2 and the included angle between the connection of the road section L1 and the road section L3. When the angle of the included angle is the same, the vehicle preferentially selects a road with a higher rank or a road section in accordance with the road type of the previous road section. In this embodiment, the included angle of the connection between the link L2 and the link L4 is the same with respect to the included angle of the connection between the link L2 and the link L5, and the link L4 is preferably selected. And finally, according to the connection relation of each road section, the vehicle continues to explore and go forward until the end of the map.

Fig. 8 is a schematic diagram illustrating a specific implementation of the matching lane according to an exemplary embodiment of the present application. As shown in FIG. 8, before the lane is matched, the vehicle has completed the link match. According to the driving direction and distance of the vehicle and the mapping relation between the link and the lane, namely the lane attribute set, the vehicle is matched with all lanes under the link. When lane matching is completed, the vehicle is located, for example, in lane A1 of fig. 8, and explores to proceed along this lane. According to the connection relation of each lane and the vector included angle of the center line of the lane, the vehicle selects the lane with a small included angle with the current lane to run, and can also preferentially select the straight running according to the type attribute of the arrow in the lane. In this embodiment, the vector angle between the center line of the lane A1 and the center line of the lane A2 is small, and the vehicle preferentially selects the lane A2 to go straight. And when the angles of the vector included angles are the same or the types of the arrows in the lane are the same, calculating the distance between the endpoints of the center line of the lane, and preferentially selecting the lane with the small distance for driving by the vehicle. In the present embodiment, the distance between the center line of the lane A2 and the end point of the center line of the lane A3 is small, and the lane A3 is preferentially selected. And finally, according to the continuing relation of each lane, the vehicle continues to explore and go forward to the end of the map. The acquired specific lane information may be used as a reference for the path information, or the dynamic distance information may be calculated twice.

In the process of searching and advancing the vehicle, in order to keep the searching efficiency and prevent the GNSS signal from bouncing, the searching range of the vehicle is kept 2 kilometers ahead of the vehicle, and the vehicle is searched and advanced in the range of 50 meters behind the vehicle. Fig. 9 is a schematic diagram of a superlength lane centerline reference strategy shown in an exemplary embodiment of the present application. As shown in fig. 9, the distance between both ends indicates the length of the lane, and the length of the extra-long lane is much longer than the vehicle search range, and the vehicle searches for and advances while keeping the search range. Fig. 10 is an ultra short lane centerline reference strategy schematic shown in an exemplary embodiment of the present application. As shown in fig. 10, the plurality of end points are connected to indicate a plurality of lanes, the length of the plurality of ultra-short lanes is much shorter than the vehicle search range, and the vehicle searches for and advances while keeping the search range.

In the embodiment, a plurality of candidate lane sets are acquired by advancing the lane exploration, thereby helping to realize the planning of the lane track. In the present embodiment, the set of candidate lanes includes information such as lane center lines, lane boundary lines, and lane lengths. Specifically, in the process of obtaining the candidate lane set, query, self-check and repair are realized through a tool method. And acquiring information such as road section numbers and lane numbers of the junction points and the junction points, front traffic lights, pedestrian crossings, stop lines, traffic signs and the like, and performing reasonableness inspection and restoration. In which lane boundary lines are subjected to plausibility checks and repairs, such as a Z-shape, intersection of center lines with boundary lines, and the like. And (4) carrying out reasonableness check and restoration on the lane center line, such as overlarge curvature, too narrow distance between the center line and the boundary and the like. Through inspection and restoration, the accuracy of data of the lane is further improved, and the safe operation of the vehicle is ensured.

FIG. 11 illustrates an overall architecture diagram of a decision that is suitable for use in implementing embodiments of the present application. In the decision overall architecture diagram shown in fig. 11, prediction data generated based on an algorithm model or the like, high-precision map data, vehicle positioning, and vehicle chassis information are first subjected to data preprocessing, and the processed data is checked and dumped. And (4) inputting the high-precision map data, the perception data and the vehicle positioning into a decision-making environment model for data processing. The environment model for decision making comprises a lane generation model and a crowdsourcing map and perception combined model. In the present embodiment, lane exploration is mainly performed by a lane generation model, and a plurality of candidate lanes are acquired. And evaluating the obtained multiple candidate lanes, grading the candidate lanes, and selecting a suboptimal candidate lane set. And establishing a Frenet coordinate system for expressing the relative relation between the candidate lane and the vehicle so as to describe the motion state of the vehicle. And (4) performing intersection and obstacle decision, wherein decision scenes such as lane following, intersection, garage driving, garage parking, vehicle head dropping and the like are determined. And performing corresponding task planning according to the scene, the phase and the task list, and performing trajectory planning of the vehicle according to the path boundary and the speed boundary constraint under the Frenet coordinate system. And finally, extracting the characteristics of the plurality of tracks, performing multi-track evaluation by using expert or terminal data drive, and finishing safety inspection and functional data filling so as to select the optimal track and ensure that the vehicle moves forwards normally and safely.

Fig. 12 is a block diagram of a lane trajectory generation device shown in an exemplary embodiment of the present application. The apparatus can be applied to the implementation environment shown in fig. 2, and is specifically configured in the intelligent terminal 210. The apparatus may also be applied to other exemplary implementation environments, and is specifically configured in other devices, and the embodiment does not limit the implementation environment to which the apparatus is applied.

As shown in fig. 12, the exemplary lane trajectory generation device includes:

the data acquisition module 1210 acquires upstream data, wherein the upstream data includes high-precision map data, perception data and vehicle positioning. The data conversion module 1220 inputs the upstream data into the lane generation model, and performs data conversion on the upstream data. The data self-checking and recognizing module 1230 performs self-checking on the map data and the sensing data, judges whether the self-checking is passed or not, and restores the map data and the sensing data if the self-checking is not passed; and if the self-check passes, dividing the map data and the perception data into different levels. And a lane generation module 1240 for processing the data for each level according to the vehicle position, thereby generating a plurality of candidate lane sets.

It should be noted that the lane trajectory generation apparatus provided in the foregoing embodiment and the lane trajectory generation method provided in the foregoing embodiment belong to the same concept, and specific ways for the modules and units to perform operations have been described in detail in the method embodiment, and are not described again here. In practical applications, the lane trajectory generation device provided in the above embodiment may distribute the above functions by different functional modules according to needs, that is, divide the internal structure of the device into different functional modules to complete all or part of the above described functions, which is not limited herein.

An embodiment of the present application further provides an electronic device, including: one or more processors; a storage device for storing one or more programs, which when executed by the one or more processors, cause the electronic apparatus to implement the lane trajectory generation method provided in the above-described embodiments.

FIG. 13 illustrates a schematic structural diagram of a computer system suitable for use in implementing the electronic device of an embodiment of the present application. It should be noted that the computer system 1300 of the electronic device shown in fig. 13 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.

As shown in fig. 13, the computer system 1300 includes a Central Processing Unit (CPU) 1301, which can perform various appropriate actions and processes, such as performing the methods described in the above embodiments, according to a program stored in a Read-Only Memory (ROM) 1302 or a program loaded from a storage portion 1308 into a Random Access Memory (RAM) 1303. In the RAM 1303, various programs and data necessary for system operation are also stored. The CPU 1301, the ROM 1302, and the RAM 1303 are connected to each other via a bus 1304. An Input/Output (I/O) interface 1305 is also connected to bus 1304.

The following components are connected to the I/O interface 1305: an input portion 1306 including a keyboard, a mouse, and the like; an output section 1307 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, a speaker, and the like; a storage portion 1308 including a hard disk and the like; and a communication section 1309 including a Network interface card such as a LAN (Local Area Network) card, a modem, or the like. The communication section 1309 performs communication processing via a network such as the internet. A drive 1310 is also connected to the I/O interface 1305 as needed. A removable medium 1311 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 1310 as needed, so that the computer program read out therefrom is mounted in the storage section 1308 as needed.

In particular, according to embodiments of the application, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising a computer program for performing the method illustrated by the flow chart. In such embodiments, the computer program may be downloaded and installed from a network via communications component 1309 and/or installed from removable media 1311. When the computer program is executed by a Central Processing Unit (CPU) 1301, various functions defined in the system of the present application are executed.

It should be noted that the computer readable media shown in the embodiments of the present application may be computer readable signal media or computer readable storage media or any combination of the two. The computer readable storage medium may be, for example, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a Read-Only Memory (ROM), an Erasable Programmable Read-Only Memory (EPROM), a flash Memory, an optical fiber, a portable Compact Disc Read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer-readable signal medium may comprise a propagated data signal with a computer-readable computer program embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. Each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in the embodiments of the present application may be implemented by software or hardware, and the described units may also be disposed in a processor. Wherein the names of the elements do not in some way constitute a limitation on the elements themselves.

Another aspect of the present application also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor of a computer, causes the computer to execute the method of generating a lane trajectory as described above. The computer-readable storage medium may be included in the electronic device described in the above embodiment, or may exist separately without being incorporated in the electronic device.

Another aspect of the application also provides a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the lane trajectory generation method provided in the above-described embodiments.

The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.

Claims (10)

1. A method of generating a lane trajectory, the method comprising:

acquiring upstream data, wherein the upstream data comprises map data, perception data and vehicle positioning;

inputting the upstream data into a lane generation model;

performing data conversion on the upstream data;

self-checking the map data and the perception data, judging whether the self-checking is passed or not, and if not, repairing the map data and the perception data; if the self-checking is passed, dividing the map data and the perception data into different grades; and

and processing the data of each grade according to the vehicle positioning to generate a plurality of candidate lane sets.

2. The method of claim 1, wherein the map data comprises dynamic map data and static map data, and the map data and the perception data are divided into a high-precision map confidence level, a static map limping level and a perception lane line slowing level according to whether the static map data and the dynamic map data are defective or not.

3. The method of claim 2, wherein the dynamic map data includes road object data, map coordinate data, map relationship data, and lane-level guidance data.

4. The method of claim 2, wherein the static map data comprises road data, lane data, traffic signal data, and logical relationship data.

5. The method as claimed in claim 2, wherein when the dynamic map data is missing, the vehicle locates the nearest road segment according to the static map lameness level matching, and selects a straight road segment to explore ahead.

6. The method for generating a lane track according to claim 5, wherein after the vehicle locates the nearest road segment according to the static map lameness level matching, the method further comprises the following steps: and matching all lanes under the road section by the vehicle, and selecting a straight lane to explore for advancing.

7. The method of claim 1, wherein the set of candidate lanes comprises lane center lines, lane boundary lines, and lane lengths.

8. A lane trajectory generation apparatus, characterized in that the apparatus comprises:

the data acquisition module is used for acquiring upstream data, and the upstream data comprises map data, perception data and vehicle positioning;

the data conversion module inputs the upstream data into a lane generation model and performs data conversion on the upstream data;

the data self-checking and cognition module is used for carrying out self-checking on the map data and the perception data, judging whether the self-checking is passed or not, and repairing the map data and the perception data if the self-checking is not passed; if the self-checking passes, dividing the map data and the perception data into different levels; and

and the lane generation module is used for processing the data of each grade according to the vehicle positioning to generate a plurality of candidate lane sets.

9. An electronic device, characterized in that the electronic device comprises:

one or more processors;

storage means for storing one or more programs that, when executed by the one or more processors, cause the electronic device to implement the method of generating a lane trajectory according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that a computer program is stored thereon, which, when executed by a processor of a computer, causes the computer to execute the method of generating a lane trajectory according to any one of claims 1 to 7.

Images