Scene generation method, device and control method for vehicle automatic driving

Abstract

The present application relates to a scene generation method, device and control method for vehicle automatic driving. The method includes: planning a driving route on an electronic map according to the preset starting and ending positions of the vehicle; obtaining the full road type information corresponding to the planned driving route in sequence according to the vehicle driving order, and connecting the full road in sections according to the road type; extracting the corresponding scene according to the road type of each section of the road in the scene library in combination with real-time road condition information, and fitting to form a first driving scene; while the vehicle is moving according to the first driving scene, updating the first driving scene according to the real-time road condition information to form a second driving scene. This method takes into account the actual operating environment information during the automatic driving process, increases the safety of automatic driving, and the fitted second driving scene includes the scene in the scene library. This data-based analysis and selection method is more scientific and reasonable than the manual control method, and ensures driving safety.

Description

Technical Field

[0001] The present application relates to the technical field of scene generation for automatic vehicle driving, and in particular to a scene generation method, device and control method for automatic vehicle driving. Background Art

[0002] Self-driving vehicles rely on artificial intelligence, visual computing, radar, monitoring devices and global positioning systems to work together, allowing computers to automatically and safely operate motor vehicles without any active human intervention.

[0003] The scenario library used in the autonomous driving process is generally constructed based on a large amount of data collection, data analysis and other steps in the early stages. However, in the actual operation of autonomous driving vehicles, using only pre-built scenario libraries is difficult to meet the actual needs of vehicle autonomous driving, which will reduce the safety of autonomous driving. Summary of the invention

[0004] Based on this, it is necessary to address the above-mentioned technical problems. The embodiments of the present invention provide a scene generation method, device and control method for vehicle automatic driving. Through real-time road condition information from the outside world, timely adjustments are made and the currently applicable driving scene is generated. In the process of automatic driving, the impact of environmental changes faced in actual applications is taken into account, thereby solving the current technical problem that it is difficult to ensure the safety of automatic driving.

[0005] In one aspect, a method for generating a scene for automatic driving of a vehicle is provided, the method comprising:

[0006] Plan the driving route on the electronic map according to the preset starting and ending points of the vehicle;

[0007] According to the driving order of the vehicles, the road type information of the entire route corresponding to the planned driving route is obtained in sequence, and the entire route road is connected in sections according to the road type;

[0008] In combination with the real-time traffic information, extract corresponding scenes in the scene library according to the road type of each section of the road, and fit to form a first driving scene; and

[0009] When the vehicle is traveling according to the first driving scenario, the first driving scenario is updated according to real-time road condition information to form a second driving scenario.

[0010] In one of the embodiments, before extracting the corresponding scene according to the road type of each section of road in the scene library, it also includes: constructing a scene library, the scene library including a plurality of scenes arranged according to the road type; the road types include expressways, main roads, secondary roads, and branch roads; each road is provided with attributes, structure, geometry, road network connection and lane information; the attributes include length, height, speed limit, and height limit; the structure includes horizontal roads, uphill roads, downhill roads, and arch bridge roads; the geometry includes straight lines, curves, arcs, and spiral lines; the road network connection includes the beginning and the end of the road; the lane information includes lane type, lane attributes, lane lines, lane starting points, and pavement; the scene types include basic packages, primary packages, intermediate packages, and advanced packages; the basic package contains standard regulatory scenes; the primary package contains standard regulatory scenes and natural driving data reconstruction cases; the intermediate package contains standard regulatory scenes, natural driving data reconstruction cases, and accident scenes; the advanced package contains standard regulatory scenes, natural driving data reconstruction cases, accident scenes, and autonomous driving test failure scenes.

[0011] In one embodiment, the lane line includes the center line of the road, the lane types include left-turn lanes, right-turn lanes, straight lanes, and U-turn lanes, the lane attributes include speed limits and vehicle type restrictions, and the pavement includes lane flatness.

[0012] In one embodiment, the fitting to form a first driving scenario includes:

[0013] Divide the number of lanes of each section of the road according to the lane lines and number each divided lane, determine the number of candidate lanes on which the vehicle can travel according to the lane type, determine the available lanes corresponding to the vehicle model from the candidate lane numbers according to the lane attributes, and obtain the maximum driving speed of the vehicle on each available lane based on the lane attributes and pavement of the available lanes;

[0014] Obtain vehicle congestion and visibility range;

[0015] The actual driving speed of the vehicle on each available lane is calculated according to the vehicle congestion and the maximum driving speed on each available lane; the optimal scene corresponding to each section of the road is extracted in combination with the visible range; and all the optimal scenes are spliced ​​to form the first driving scene.

[0016] In one embodiment, extracting the optimal scene corresponding to each road section in combination with the visible range includes:

[0017] Determining the type of selectable scene according to the size of the visible range;

[0018] The maximum value of the visible range is compared with a first threshold, a second threshold, and a third threshold that increase in sequence.

[0019] When the visible range is greater than or equal to a third threshold, selecting the basic package;

[0020] When the visible range is greater than or equal to a second threshold and less than a third threshold, selecting the primary package;

[0021] When the visible range is greater than or equal to a first threshold and less than a second threshold, selecting the intermediate package;

[0022] When the visible range is smaller than a first threshold, the advanced package is selected.

[0023] In one embodiment, when building a scene library, it includes:

[0024] Data collection steps: collecting lane information, nearby vehicle information, weather information, vehicle model information, vehicle speed information, and lane occupancy information during vehicle travel;

[0025] Data fusion step, fusing the collected data to form multiple usable scenarios;

[0026] A scene extraction step, extracting each available scene;

[0027] The scene labeling step labels the available situations of the extracted scenes one by one;

[0028] Scenario analysis step, to verify the available scenarios and analyze whether the corresponding scenarios are reasonable; and

[0029] In the scenario construction step, when the scenarios are reasonable, each scenario is classified into at least one of a basic package, a primary package, an intermediate package, and an advanced package according to the complexity of the scenario.

[0030] In one embodiment, the vehicle updates the first driving scene to form a second driving scene according to real-time road condition information during the driving process, including:

[0031] The vehicle and nearby vehicles are modularized, and the vehicle obtains the driving data of nearby vehicles in real time;

[0032] Determine whether the first driving scenario of the vehicle conflicts with the driving data of nearby vehicles. If not, maintain the speed and lane of the vehicle; if so, adjust the speed and / or lane of the vehicle and update the first driving scenario to form a second driving scenario.

[0033] In one embodiment, the driving data of the nearby vehicles include lane change trajectory data of the nearby vehicles; the lane change trajectory data of the nearby vehicles include the vehicle's current lane, the vehicle's lane after change, the vehicle's speed, the vehicle's lane change starting point and end point, the vehicle's lateral speed, and the vehicle's lane change duration.

[0034] In another aspect, a scene generation device for automatic driving of a vehicle is provided, the device comprising:

[0035] A driving route planning module is used to plan a driving route on an electronic map according to the preset starting and ending positions of the vehicle;

[0036] A road segmentation module is used to sequentially obtain the full road type information corresponding to the planned driving route according to the driving order of the vehicles, and connect the full roads in sections according to the road types;

[0037] A first driving scene module is formed, which is used to extract corresponding scenes according to the road type of each section of road in the scene library in combination with real-time road condition information, and fit to form the first driving scene;

[0038] A second driving scenario module is formed, which is used to update the first driving scenario according to real-time road condition information to form a second driving scenario when the vehicle is traveling according to the first driving scenario.

[0039] On the other hand, a method for controlling automatic driving of a vehicle is provided, characterized in that it comprises the steps of:

[0040] Acquire the first driving scene formed by the scene generation method for vehicle automatic driving described above;

[0041] According to the planned driving route of the vehicle and in combination with the real-time traffic information, the vehicle travels according to the first driving scenario and controls the speed and / or driving lane of the vehicle;

[0042] During the driving process, the vehicle updates the first driving scene according to the real-time road condition information to form a second driving scene, and controls the speed and / or driving lane of the vehicle according to the second driving scene.

[0043] The above-mentioned scene generation method, device and control method for vehicle automatic driving form a second driving scene by timely updating the first driving scene based on external real-time road condition information. The second driving scene can be updated by fine-tuning the control of the vehicle on the basis of the first driving scene. The preset scene library is corrected by continuously combining real-time road condition information during the automatic driving process, which improves the authenticity of the automatic driving scene and increases the safety of automatic driving. Moreover, the fitted second driving scene includes the scenes in the scene library. This data-based analysis and selection method is more scientific and reasonable than the manual control method, which further ensures the safety of automatic driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 A diagram of an application environment of a method for generating a scene for automatic driving of a vehicle in one embodiment;

[0045] Figure 2A schematic diagram of a flow chart of a method for generating a scene for automatic driving of a vehicle in one embodiment;

[0046] Figure 3 A schematic diagram of a process for extracting an optimal scenario in an embodiment;

[0047] Figure 4 A schematic diagram of a process for building a scene library in one embodiment;

[0048] Figure 5 A schematic diagram of a flow chart of a second driving scenario in one embodiment;

[0049] Figure 6 is a structural block diagram of a scene generation device for automatic driving of a vehicle in one embodiment;

[0050] Figure 7 A schematic diagram of a flow chart of a method for controlling automatic driving of a vehicle in one embodiment;

[0051] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0053] The scene generation method for vehicle automatic driving provided in this application can be used in Figure 1 The application environment shown is implemented. Among them, the terminal 102 communicates with the server 104 through the network. The terminal 102 is a vehicle control system or a control device connected to the vehicle control system, which can control the automatic driving of the vehicle; the server 104 is a cloud service that sends control instructions to the terminal 102 to realize the automatic driving of the vehicle. Among them, the terminal 102 can be but not limited to various personal computers, laptops, smart phones, tablet computers and portable wearable devices, and the server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0054] In one embodiment, Figure 2 As shown, a method for generating a scene for vehicle automatic driving is provided, and the method is applied to Figure 1 The server 104 in the example is used for explanation, and the following steps S1-S5 are included.

[0055] Step S1, planning a driving route on an electronic map according to the preset starting and ending positions of the vehicle.

[0056] Step S2, according to the driving order of the vehicles, sequentially obtain the entire road type information corresponding to the planned driving route, and connect the entire road in sections according to the road type.

[0057] Step S3, constructing a scene library, wherein the scene library includes a plurality of scenes set according to road types.

[0058] Step S4, combining the real-time traffic information, extracting the corresponding scene according to the road type of each road section in the scene library, and fitting to form a first driving scene.

[0059] Step S5: When the vehicle is traveling according to the first driving scenario, the first driving scenario is updated according to the real-time road condition information to form a second driving scenario.

[0060] The road types include expressways, main roads, secondary roads, and branch roads; each road has attributes, structure, geometry, road network connection and lane information; the attributes include length, height, speed limit, and height limit; the structure includes horizontal roads, uphill roads, downhill roads, and arch bridge roads; the geometry includes straight lines, curves, arcs, and spiral lines; the road network connection includes the beginning and the end of the road; the lane information includes lane type, lane attributes, lane lines, lane starting points, and pavement; the scene types include basic packages, primary packages, intermediate packages, and advanced packages; the basic package only contains standard regulatory scenarios; the primary package contains standard regulatory scenarios and natural driving data reconstruction cases; the intermediate package contains standard regulatory scenarios, natural driving data reconstruction cases, and accident scenarios; the advanced package contains standard regulatory scenarios, natural driving data reconstruction cases, accident scenarios, and autonomous driving test failure scenarios.

[0061] In the above-mentioned scene generation method for vehicle autonomous driving, the lane line includes the center line of the road, the lane types include left-turn lanes, right-turn lanes, straight lanes, and U-turn lanes, the lane attributes include lane material, speed limit, and vehicle type restrictions, and the pavement includes lane flatness and other information.

[0062] In this embodiment, the fitting to form a first driving scene includes:

[0063] Step S41, dividing each road section into lanes according to the lane lines and numbering each divided lane, determining the candidate lane number on which the vehicle can travel according to the lane type, and then determining the available lane corresponding to the vehicle model from the candidate lane numbers according to the lane attributes, and obtaining the maximum driving speed of the vehicle on each available lane based on the lane attributes and pavement of the available lane.

[0064] Step S42, combining the real-time traffic information to obtain the vehicle congestion and visibility range.

[0065] Among them, the above-mentioned vehicle congestion and visible range can be obtained in real time through a perception system installed on the vehicle.

[0066] Step S43, calculating the actual driving speed of the vehicle on each available lane according to the vehicle congestion and the maximum driving speed on each available lane; extracting the optimal scene corresponding to each section of the road in combination with the visible range; and splicing all the optimal scenes to form the first driving scene.

[0067] In this embodiment, when the perception system detects that the vehicle congestion on the road section where the vehicle is currently traveling is high, the vehicle speed can be appropriately reduced to ensure safety during driving.

[0068] like Figure 3 As shown, in step S43, extracting the optimal scene corresponding to each road section in combination with the visible range includes:

[0069] Step S431, determining the type of selectable scene according to the size of the visible range.

[0070] Step S432, compare the maximum value of the visible range with the first threshold, the second threshold, and the third threshold which increase in sequence. When the visible range is greater than or equal to the third threshold, select the basic package; when the visible range is greater than or equal to the second threshold and less than the third threshold, select the primary package; when the visible range is greater than or equal to the first threshold and less than the second threshold, select the intermediate package; when the visible range is less than the first threshold, select the advanced package.

[0071] In this embodiment, the visible range in the actual driving environment is taken into consideration when selecting the complexity of the autonomous driving scene. This method further ensures the safety during the autonomous driving process.

[0072] like Figure 4 As shown, in step S3 of this embodiment, when building a scene library, it includes:

[0073] Step S31, data collection step, collects lane information, nearby vehicle information, weather information, vehicle model information, vehicle speed information, lane occupancy information during the vehicle journey; the lane occupancy information includes lane occupancy conditions such as broken-down vehicles, maintenance areas, and traffic jam parking.

[0074] Step S32, a data fusion step, fuses the collected data to form a plurality of usable scenes.

[0075] Step S33, scene extraction step, extracts each available scene.

[0076] Step S34, a scene labeling step, labels the available situations of the extracted scenes one by one.

[0077] Step S35, a scenario analysis step, verifies the available scenarios and analyzes whether the corresponding scenarios are reasonable.

[0078] Step S36, a scene construction step, when the scene is reasonable, each scene is classified into at least one of a basic package, a primary package, an intermediate package and an advanced package according to the complexity of the scene.

[0079] like Figure 5 As shown, in step S5 of this embodiment, the vehicle updates the first driving scene to form a second driving scene according to real-time road condition information during the driving process, including:

[0080] Step S51, modularize the vehicle and nearby vehicles, and obtain the driving data of nearby vehicles in real time;

[0081] Step S52, determine whether the first driving scenario of the vehicle conflicts with the driving data of nearby vehicles. If not, maintain the speed and lane of the vehicle; if so, adjust the speed and / or lane of the vehicle and update the first driving scenario to form a second driving scenario.

[0082] In this embodiment, the driving data of the nearby vehicles include the lane change trajectory data of the nearby vehicles (also known as the cut-in scene); the lane change trajectory data of the nearby vehicles include the vehicle's current lane, the vehicle's changed lane, the vehicle's speed, the vehicle's lane change starting point and end point, the vehicle's lateral speed, and the vehicle's lane change duration.

[0083] It should be understood that although Figure 2-5 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2-5 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0084] In one embodiment, Figure 6 As shown, a scene generation device 10 for vehicle automatic driving is provided, including a driving route planning module 1, a road segmentation module 2, a first driving scene forming module 3 and a second driving scene forming module 4.

[0085] The driving route planning module 1 is used to plan a driving route on an electronic map according to the preset starting and ending positions of the vehicle.

[0086] The road segmentation module 2 is used to sequentially obtain the entire road type information corresponding to the planned driving route according to the vehicle driving order, and connect the entire road in sections according to the road type.

[0087] The first driving scene forming module 3 is used to extract the corresponding scene according to the road type of each section of road in the scene library in combination with the real-time road condition information, and fit to form the first driving scene;

[0088] The second driving scenario forming module 4 is used to update the first driving scenario according to real-time road condition information to form a second driving scenario when the vehicle is traveling according to the first driving scenario.

[0089] For the specific definition of the scene generation device for vehicle automatic driving, please refer to the definition of the scene generation method for vehicle automatic driving above, which will not be repeated here. Each module in the above-mentioned scene generation device for vehicle automatic driving can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0090] like Figure 7 As shown, in one embodiment, a method for controlling automatic driving of a vehicle is provided, characterized in that it includes the steps of:

[0091] Step S11, obtaining the first driving scene formed by the scene generation method for automatic driving of a vehicle as described above;

[0092] Step S12, driving according to the first driving scenario based on the planned driving route of the vehicle and in combination with real-time road condition information, and controlling the speed and / or driving lane of the vehicle; and

[0093] Step S13: During the driving process, the vehicle updates the first driving scenario according to the real-time road condition information to form a second driving scenario, and controls the speed and / or driving lane of the vehicle according to the second driving scenario.

[0094] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 8As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store scene generation data for automatic driving of the vehicle. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a scene generation method for automatic driving of the vehicle is implemented.

[0095] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0096] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0097] Plan the driving route on the electronic map according to the preset starting and ending points of the vehicle;

[0098] According to the driving order of the vehicles, the road type information of the entire route corresponding to the planned driving route is obtained in sequence, and the entire route road is connected in sections according to the road type;

[0099] In combination with the real-time traffic information, the corresponding scene is extracted in the scene library according to the road type of each section of the road, and a first driving scene is formed by fitting;

[0100] When the vehicle is traveling according to the first driving scenario, the first driving scenario is updated according to real-time road condition information to form a second driving scenario.

[0101] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0102] Plan the driving route on the electronic map according to the preset starting and ending points of the vehicle;

[0103] According to the driving order of the vehicles, the road type information of the entire route corresponding to the planned driving route is obtained in sequence, and the entire route road is connected in sections according to the road type;

[0104] In combination with the real-time traffic information, the corresponding scene is extracted in the scene library according to the road type of each section of the road, and a first driving scene is formed by fitting;

[0105] When the vehicle is traveling according to the first driving scenario, the first driving scenario is updated according to real-time road condition information to form a second driving scenario.

[0106] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0107] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0108] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for generating a scene for automatic vehicle driving, characterized in that: Includes steps: Plan the driving route on the electronic map according to the preset starting and ending points of the vehicle; According to the driving order of the vehicles, the road type information of the entire route corresponding to the planned driving route is obtained in sequence, and the entire route road is connected in sections according to the road type; In combination with the real-time traffic information, the corresponding scene is extracted in the scene library according to the road type of each section of the road, and a first driving scene is formed by fitting; as well as When the vehicle is traveling according to the first driving scenario, the first driving scenario is updated according to the real-time road condition information to form a second driving scenario; The types of scenarios in the scenario library include basic package, primary package, intermediate package and advanced package; the basic package contains standard regulatory scenarios; the primary package contains standard regulatory scenarios and natural driving data reconstruction cases; the intermediate package contains standard regulatory scenarios, natural driving data reconstruction cases and accident scenarios; the advanced package contains standard regulatory scenarios, natural driving data reconstruction cases, accident scenarios and autonomous driving test failure scenarios; Building a scene library, wherein the scene library includes a plurality of scenes set according to road types; The road types include expressways, trunk roads, secondary trunk roads, and branch roads; each road is provided with attributes, structure, geometry, road network connection, and lane information; the attributes include length, height, speed limit, and height limit; the structure includes horizontal road, uphill road, downhill road, and arch bridge road; the geometry includes straight line, curve, arc, and spiral line; the road network connection includes the beginning and the end of the road; the lane information includes lane type, lane attributes, lane line, lane starting point, and pavement; The lane line includes the center line of the road, the lane type includes a left-turn lane, a right-turn lane, a straight lane, and a U-turn lane, the lane attributes include speed limit and vehicle type limit, and the pavement includes lane flatness; The fitting to form a first driving scenario includes: Divide the number of lanes of each section of the road according to the lane lines and number each divided lane, determine the number of candidate lanes on which the vehicle can travel according to the lane type, determine the available lanes corresponding to the vehicle model from the candidate lane numbers according to the lane attributes, and obtain the maximum driving speed of the vehicle on each available lane based on the lane attributes and pavement of the available lanes; Obtain vehicle congestion and visibility range; Calculating the actual driving speed of the vehicle on each available lane according to the vehicle congestion and the maximum driving speed on each available lane; extracting the optimal scene corresponding to each section of the road in combination with the visible range; and splicing all the optimal scenes to form the first driving scene; The extracting the optimal scene corresponding to each section of the road in combination with the visible range includes: Determining the type of selectable scene according to the size of the visible range; The maximum value of the visible range is compared with a first threshold, a second threshold, and a third threshold that increase in sequence. When the visible range is greater than or equal to a third threshold, selecting the basic package; When the visible range is greater than or equal to a second threshold and less than a third threshold, selecting the primary package; When the visible range is greater than or equal to a first threshold and less than a second threshold, selecting the intermediate package; When the visible range is smaller than a first threshold, the advanced package is selected.

2. The method for generating a scene for automatic vehicle driving according to claim 1, characterized in that: When building a scene library, include: Data collection steps: collecting lane information, nearby vehicle information, weather information, vehicle model information, vehicle speed information, and lane occupancy information during vehicle travel; Data fusion step, fusing the collected data to form multiple usable scenarios; A scene extraction step, extracting each available scene; The scene labeling step labels the available situations of the extracted scenes one by one; Scenario analysis step, to verify the available scenarios and analyze whether the corresponding scenarios are reasonable; and In the scenario construction step, when the scenarios are reasonable, each scenario is classified into at least one of a basic package, a primary package, an intermediate package, and an advanced package according to the complexity of the scenario.

3. The method for generating a scene for automatic vehicle driving according to claim 1, wherein: The vehicle updates the first driving scene to form a second driving scene according to real-time road condition information during the driving process, including: The vehicle and nearby vehicles are modularized, and the vehicle obtains the driving data of nearby vehicles in real time; Determine whether the first driving scenario of the vehicle conflicts with the driving data of nearby vehicles. If not, maintain the speed and lane of the vehicle; if so, adjust the speed and / or lane of the vehicle and update the first driving scenario to form a second driving scenario.

4. The method for generating a scene for automatic vehicle driving according to claim 3, characterized in that: The driving data of the nearby vehicles includes lane change trajectory data of the nearby vehicles; The lane change trajectory data of the nearby vehicles includes the current lane of the vehicle, the lane after the vehicle changes, the vehicle speed, the starting and ending points of the vehicle lane change, the lateral speed of the vehicle, and the duration of the vehicle lane change.

5. A scene generation device for automatic vehicle driving, characterized in that: The device comprises: A driving route planning module is used to plan a driving route on an electronic map according to the preset starting and ending positions of the vehicle; A road segmentation module is used to sequentially obtain the full road type information corresponding to the planned driving route according to the driving order of the vehicles, and connect the full roads in sections according to the road types; A first driving scene module is formed, which is used to extract corresponding scenes according to the road type of each section of road in the scene library in combination with real-time road condition information, and fit to form the first driving scene; A second driving scenario module is formed, which is used to update the first driving scenario according to the real-time road condition information to form a second driving scenario when the vehicle is traveling according to the first driving scenario; The types of scenarios in the scenario library include basic package, primary package, intermediate package and advanced package; the basic package contains standard regulatory scenarios; the primary package contains standard regulatory scenarios and natural driving data reconstruction cases; the intermediate package contains standard regulatory scenarios, natural driving data reconstruction cases and accident scenarios; the advanced package contains standard regulatory scenarios, natural driving data reconstruction cases, accident scenarios and autonomous driving test failure scenarios; A scenario library construction module, wherein the scenario library includes a plurality of scenarios set according to road types; The road types include expressways, trunk roads, secondary trunk roads, and branch roads; each road is provided with attributes, structure, geometry, road network connection, and lane information; the attributes include length, height, speed limit, and height limit; the structure includes horizontal road, uphill road, downhill road, and arch bridge road; the geometry includes straight line, curve, arc, and spiral line; the road network connection includes the beginning and the end of the road; the lane information includes lane type, lane attributes, lane line, lane starting point, and pavement; The lane line includes the center line of the road, the lane type includes a left-turn lane, a right-turn lane, a straight lane, and a U-turn lane, the lane attributes include speed limit and vehicle type limit, and the pavement includes lane flatness; The fitting to form a first driving scenario includes: Divide the number of lanes of each section of the road according to the lane lines and number each divided lane, determine the number of candidate lanes on which the vehicle can travel according to the lane type, determine the available lanes corresponding to the vehicle model from the candidate lane numbers according to the lane attributes, and obtain the maximum driving speed of the vehicle on each available lane based on the lane attributes and pavement of the available lanes; Obtain vehicle congestion and visibility range; Calculating the actual driving speed of the vehicle on each available lane according to the vehicle congestion and the maximum driving speed on each available lane; extracting the optimal scene corresponding to each section of the road in combination with the visible range; and splicing all the optimal scenes to form the first driving scene; The extracting the optimal scene corresponding to each section of the road in combination with the visible range includes: Determining the type of selectable scene according to the size of the visible range; The maximum value of the visible range is compared with a first threshold, a second threshold, and a third threshold that increase in sequence. When the visible range is greater than or equal to a third threshold, selecting the basic package; When the visible range is greater than or equal to a second threshold and less than a third threshold, selecting the primary package; When the visible range is greater than or equal to a first threshold and less than a second threshold, selecting the intermediate package; When the visible range is smaller than a first threshold, the advanced package is selected.

6. A method for controlling automatic driving of a vehicle, characterized in that: Includes steps: Obtain the first driving scene formed by the scene generation method for automatic driving of a vehicle according to any one of claims 1 to 4; According to the planned driving route of the vehicle and in combination with the real-time traffic information, the vehicle travels according to the first driving scenario and controls the speed and / or driving lane of the vehicle; as well as During the driving process, the vehicle updates the first driving scene according to the real-time road condition information to form a second driving scene, and controls the speed and / or driving lane of the vehicle according to the second driving scene.

Images