Vehicle driving planning method and device and vehicle

Abstract

The invention discloses a vehicle driving planning method and device and a vehicle, and relates to the technical field of intelligent driving, and the method comprises the steps: obtaining the driving information of at least one to-be-followed object corresponding to a target vehicle under the condition that a matched lane line is not recognized in the driving process of the target vehicle; under the condition that a target following object is not selected based on the driving information, road boundary information corresponding to the target vehicle is determined, and a virtual lane line is created based on the road boundary information and an adjacent vehicle obtained through recognition; and track planning is carried out on the target vehicle based on the virtual lane line so as to control the target vehicle to drive according to the planned driving path. According to the method, potential safety hazards such as line pressing and collision generated when no lane line is used as a constraint in the automatic driving process of the vehicle are avoided, the effectiveness of vehicle path planning is achieved, and the lane-line-free safe driving efficiency in the automatic driving process of the vehicle is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving technology, and in particular to a vehicle driving planning method and device, and a vehicle. Background Art

[0002] With the rapid development of intelligent driving technology, driverless vehicles usually need to sense lane lines when driving on the road, so as to plan the path based on the lane lines so that the vehicle can plan and drive within the lane lines. At present, because the lane lines are in the external environment, in some scenarios, the lane lines may be worn or covered by snow, resulting in the inability of the perception system to accurately identify the lane lines, so that the vehicle can drive safely on the road without lane lines, which cannot meet the accuracy requirements of the vehicle driving according to the planned path. Therefore, a vehicle driving planning method is urgently needed to solve the above problems. Summary of the invention

[0003] In view of this, the present invention provides a vehicle driving planning method and device, and a vehicle, the main purpose of which is to solve the problem of poor accuracy of existing vehicle driving planning.

[0004] According to one aspect of the present invention, a vehicle driving planning method is provided, comprising:

[0005] Acquiring driving information of at least one object to be followed corresponding to the target vehicle under the condition that no matching lane line is identified during the driving process of the target vehicle;

[0006] Under the condition that no target following object is selected based on the driving information, road boundary information corresponding to the target vehicle is determined, and a virtual lane line is created based on the road boundary information and the identified adjacent vehicles;

[0007] The target vehicle is track-planned based on the virtual lane line to control the target vehicle to travel along the planned driving path.

[0008] The embodiment of the present invention obtains driving information of at least one object to be followed corresponding to the target vehicle under the condition that no matching lane line is identified during the driving process of the target vehicle; determines road boundary information corresponding to the target vehicle under the condition that no target following object is selected based on the driving information, and creates a virtual lane line based on the road boundary information and the identified adjacent vehicles; performs trajectory planning for the target vehicle based on the virtual lane line to control the target vehicle to travel according to the planned driving path, and implements vehicle trajectory planning based on the virtual lane line to avoid safety hazards such as line pressing and collision when there are no lane lines as constraints during the automatic driving of the vehicle, thereby achieving the effectiveness of vehicle path planning, improving the safe driving efficiency without lane lines during the automatic driving of the vehicle, and meeting the accuracy requirements of vehicle path planning.

[0009] Furthermore, the creating a virtual lane line based on the road boundary information and the identified adjacent vehicles includes:

[0010] Obtaining a preset lane width of the road on which the target vehicle is traveling;

[0011] Determining the number of lanes based on the road boundary information and the preset lane width;

[0012] Identify an adjacent vehicle having an adjacent relationship with the target vehicle and a driving position of the adjacent vehicle, and construct a first virtual lane line according to the driving position, the number of lanes, and the preset lane width; and / or,

[0013] A starting lane line corresponding to the preset lane width is determined according to the road boundary information, and all second virtual lane lines are constructed in sequence according to the number of lanes and the starting lane line.

[0014] Furthermore, the method further comprises:

[0015] Under the condition that the position difference value between the first virtual lane line and the second virtual lane line is greater than a preset difference threshold, the first virtual lane line is corrected based on the second virtual lane line to obtain the virtual lane line for trajectory planning.

[0016] Furthermore, the driving information includes a driving track, a driving speed, and a driving lateral displacement. Before determining the road boundary information corresponding to the target vehicle, the method further includes:

[0017] Under the condition that the driving displacement matches a preset displacement threshold, and / or the driving speed matches a preset speed threshold, an overlap matching is performed based on the driving trajectory and the planned trajectory of the target vehicle, and a target following object is selected from the objects to be followed according to the overlap matching result, wherein the overlap matching includes at least one of trajectory overlap matching and expansion profile overlap matching.

[0018] Furthermore, after selecting a target following object from the objects to be followed according to the coincidence matching result, the method further includes:

[0019] Under the condition that the target following object is selected, determining the driving direction of the target following object and the planned direction of the target vehicle;

[0020] Under the condition that the driving direction matches the planned direction, trajectory planning of the target vehicle is performed based on the driving information of the target following object, so as to control the target vehicle to travel according to the planned driving path;

[0021] Under the condition that the driving direction does not match the planned direction, a target following object is selected from the objects to be followed again according to the coincidence matching result, or it is determined that the target following object has not been selected.

[0022] Furthermore, before acquiring the driving information of at least one object to be followed corresponding to the target vehicle, the method further includes:

[0023] Scanning a moving object within a preset distance range, and determining the scanned moving object as an object to be followed;

[0024] Under the condition that the driving object is not scanned, trajectory planning information of the target vehicle is obtained, and trajectory planning is performed based on the trajectory planning information and the road boundary information.

[0025] Further, performing trajectory planning based on the trajectory planning information and the road boundary information includes:

[0026] Adjusting the planned speed in the trajectory planning information, and performing trajectory planning according to the planned speed within the constraint range of the road boundary information, so as to control the target vehicle to travel along the planned straight driving path; and / or,

[0027] A preset safety distance corresponding to the road boundary information is obtained, and planning is performed according to the preset safety distance and the adjusted planned speed to control the target vehicle to travel along the planned right driving path.

[0028] According to another aspect of the present invention, a vehicle driving planning device is provided, comprising:

[0029] An acquisition module, used for acquiring driving information of at least one object to be followed corresponding to the target vehicle under the condition that no matching lane line is identified during the driving process of the target vehicle;

[0030] A determination module, configured to determine road boundary information corresponding to the target vehicle under the condition that no target following object is selected based on the driving information, and to create a virtual lane line based on the road boundary information and the identified adjacent vehicles;

[0031] A planning module is used to plan the trajectory of the target vehicle based on the virtual lane line to control the target vehicle to travel according to the planned driving path.

[0032] Furthermore, the determining module includes:

[0033] An acquisition unit, used to acquire a preset lane width of a driving road on which the target vehicle is located;

[0034] a determining unit, configured to determine the number of lanes based on the road boundary information and the preset lane width;

[0035] a first construction unit, configured to identify an adjacent vehicle having an adjacent relationship with the target vehicle and a driving position of the adjacent vehicle, and to construct a first virtual lane line according to the driving position, the number of lanes, and the preset lane width; and / or,

[0036] The second construction unit is used to determine a starting lane line corresponding to the preset lane width according to the road boundary information, and to sequentially construct all second virtual lane lines according to the number of lanes and the starting lane line.

[0037] Furthermore, the device also includes:

[0038] A correction module is used to correct the first virtual lane line based on the second virtual lane line under the condition that the position difference value between the first virtual lane line and the second virtual lane line is greater than a preset difference threshold, so as to obtain the virtual lane line used for trajectory planning.

[0039] Furthermore, the driving information includes a driving track, a driving speed, and a driving lateral displacement, and the device further includes:

[0040] A selection module is used to perform overlap matching based on the driving trajectory and the planned trajectory of the target vehicle under the condition that the driving displacement matches a preset displacement threshold and / or the driving speed matches a preset speed threshold, and select a target following object from the objects to be followed according to the overlap matching result, wherein the overlap matching includes at least one of trajectory overlap matching and expansion profile overlap matching.

[0041] Further,

[0042] The determination module is further used to determine the driving direction of the target following object and the planned direction of the target vehicle under the condition that the target following object is selected;

[0043] The planning module is used to plan the trajectory of the target vehicle based on the driving information of the target following object under the condition that the driving direction matches the planned direction, so as to control the target vehicle to travel according to the planned driving path;

[0044] The selection module is further configured to, under the condition that the driving direction does not match the planned direction, reselect a target following object from the objects to be followed according to a coincidence matching result, or determine that the target following object has not been selected.

[0045] Further,

[0046] The determination module is further configured to scan a moving object within a preset distance range, and determine the scanned moving object as an object to be followed;

[0047] The planning module is further used to obtain the trajectory planning information of the target vehicle under the condition that the driving object is not scanned, and perform trajectory planning based on the trajectory planning information and the road boundary information.

[0048] Furthermore, the planning module is specifically used to adjust the planned speed in the trajectory planning information, and perform trajectory planning according to the planned speed within the constraint range of the road boundary information, so as to control the target vehicle to travel along the planned straight driving path; and / or, obtain a preset safety distance corresponding to the road boundary information, and perform planning according to the preset safety distance and the adjusted planned speed, so as to control the target vehicle to travel along the planned right-side driving path.

[0049] According to another aspect of the present invention, a computer device is provided, comprising at least one processor, wherein the processor is coupled to a memory, wherein the memory stores a program or instruction running on the processor, and wherein the program or instruction, when executed by the processor, implements the steps of the vehicle driving planning method as described above.

[0050] According to another aspect of the present invention, a readable storage medium is provided, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the vehicle driving planning method as described above are implemented.

[0051] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0053] Figure 1 A flow chart of a vehicle driving planning method provided by an embodiment of the present invention is shown;

[0054] Figure 2 A schematic diagram of adjacent vehicle positions in a lane-free environment provided by an embodiment of the present invention is shown;

[0055] Figure 3 A schematic diagram of creating a virtual lane line provided by an embodiment of the present invention is shown;

[0056] Figure 4 Another schematic diagram of creating a virtual lane line provided by an embodiment of the present invention is shown;

[0057] Figure 5 A schematic diagram of virtual lane line correction provided by an embodiment of the present invention is shown;

[0058] Figure 6 A schematic diagram of matching based on contour coincidence provided by an embodiment of the present invention is shown;

[0059] Figure 7 A block diagram of a vehicle driving planning device provided by an embodiment of the present invention is shown;

[0060] Figure 8 A schematic structural diagram of a computer device provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0061] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0062] The embodiment of the present invention provides a vehicle driving planning method, such as Figure 1 As shown, the method includes:

[0063] 101. Under the condition that no matching lane line is identified during the driving process of a target vehicle, obtain driving information of at least one to-be-followed object corresponding to the target vehicle.

[0064] In the embodiment of the present invention, during the trajectory planning process of the unmanned intelligent vehicle, the automatic driving processor as the current execution subject can be a processor configured on the vehicle side, or a cloud server matching the vehicle, etc. At this time, the current execution subject identifies the lane lines on both sides of the lane in real time in combination with the perception system during the target vehicle driving on the road, so as to control the driving of the target vehicle in real time in combination with the lane lines. When the matching lane line is not identified, it means that the target vehicle is in a road condition where the lane line is unclear. Therefore, in order to accurately and safely plan the vehicle driving, the current execution subject obtains the driving information of the object to be followed corresponding to the target vehicle to determine whether the vehicle can be followed based on the driving information. Among them, the driving information includes but is not limited to the driving trajectory, driving speed, driving lateral displacement, etc. of the object to be followed, so as to select the target following object based on the driving information of multiple objects to be followed. In addition, the object to be followed is other vehicles in front of the target vehicle, so that after being determined as the target following object, the path planning is performed with reference to this target following object, which is not specifically limited in the embodiment of the present invention. At this time, the driving information of the object to be followed can be determined based on the scanning of the perception system according to the time frame unit. For example, the perception system performs image scanning according to the time frame unit of 8 frames per second, and obtains 8 position points of multiple objects to be followed within 1 second, thereby calculating the corresponding driving information. The embodiment of the present invention does not make specific limitations.

[0065] It should be noted that the vehicle is a vehicle with an automatic control system in the autonomous driving scenario, including passenger cars and commercial vehicles. Common models of passenger cars include but are not limited to sedans, sport utility vehicles, multi-person commercial vehicles, etc. Common models of commercial vehicles include but are not limited to pickup trucks, microvans, self-unloading vehicles, trucks, tractors, trailers and mining vehicles, etc. At this time, the vehicle can achieve autonomous driving based on the automatic control system.

[0066] 102. Under the condition that no target following object is selected based on the driving information, determine road boundary information corresponding to the target vehicle, and create a virtual lane line based on the road boundary information and the identified adjacent vehicles.

[0067] In an embodiment of the present invention, when the current execution subject fails to select a target following object based on driving information, it means that multiple objects to be followed are not suitable as following objects for the target vehicle. Therefore, the current execution subject determines the road boundary information corresponding to the target vehicle to create a virtual lane line based on this road boundary information and the identified adjacent vehicles. The road boundary information is the edgemost boundary information corresponding to the target vehicle traveling on the lane, including the road boundary position and the road boundary distance. For example, the widest shoulder identified determines the road boundary distance. At the same time, the perception system can be used to identify vehicles that are adjacent to the target vehicle, for example, a vehicle located in the adjacent lane, which can be the front vehicle or the rear vehicle, such as Figure 2 As shown, the adjacent vehicles include a left adjacent vehicle and a right adjacent vehicle, which is not specifically limited in the embodiment of the present invention.

[0068] 103. Perform trajectory planning for the target vehicle based on the virtual lane line to control the target vehicle to travel according to the planned driving path.

[0069] In the embodiment of the present invention, since the target vehicle is on a road where no lane line is identified, at this time, other adjacent vehicles may be driven by a driver or may be automatically driven. Therefore, after creating a virtual lane line based on the outermost road boundary information and adjacent vehicles, the trajectory of the target vehicle can be planned based on the virtual lane line, so that the current execution subject controls the target vehicle to travel according to the planned driving path, so as to improve the safety and accuracy of driving.

[0070] In another embodiment of the present invention, the step of creating a virtual lane line based on the road boundary information and the identified adjacent vehicles includes:

[0071] Obtaining a preset lane width of the road on which the target vehicle is traveling;

[0072] Determining the number of lanes based on the road boundary information and the preset lane width;

[0073] Identify an adjacent vehicle having an adjacent relationship with the target vehicle and a driving position of the adjacent vehicle, and construct a first virtual lane line according to the driving position, the number of lanes, and the preset lane width; and / or,

[0074] A starting lane line corresponding to the preset lane width is determined according to the road boundary information, and all second virtual lane lines are constructed in sequence according to the number of lanes and the starting lane line.

[0075] In order to accurately create a virtual lane line so as to perform safe automatic driving based on the virtual lane line, specifically, the current execution subject first obtains the preset lane width of the target vehicle on the driving road. The driving road is the road where the target vehicle is driving, including but not limited to any inter-city highway and expressway in the city, etc. The preset lane width is the specific width of each lane in the construction of the driving road. The preset lane width can be obtained based on the national road construction standards, the map information generated by the global satellite positioning system, etc., and is not specifically limited in the embodiment of the present invention. After the current execution subject obtains the preset lane width, the number of lanes is calculated based on the road boundary information and the preset lane width. For example, the road boundary information shows that the road boundary width is 15 meters, and the preset lane width is 4 meters. After 15 / 4=3.75, the number of lanes is 3 after rounding. At this time, the rounding process is to eliminate the residual width of the emergency lane and the edge error, so as to obtain the number of lanes that meet this driving road.

[0076] In a specific application scenario in an embodiment of the present invention, when creating a virtual lane line, the virtual lane line can be constructed by combining the driving position of the adjacent lanes, that is, the current execution subject combines the perception system to identify the adjacent vehicles with the target vehicle. At this time, the adjacent vehicles can be the left vehicle, the right vehicle, the front vehicle, and the rear vehicle. The embodiment of the present invention does not make specific limitations. After identifying the adjacent vehicle, the driving position of the adjacent vehicle is determined. Since the position of the adjacent vehicle on the driving road is likely to be characterized as the approximate position of a lane, the first virtual lane line can be directly constructed according to the driving position, the number of lanes, and the preset lane width. The more adjacent lanes are identified, the more accurate the position of the constructed first virtual lane line. For example, it is identified that an adjacent vehicle is driving on the left and right sides of the target vehicle, the number of lanes is 3, and the preset lane width is 4 meters. Then, according to the position of each vehicle, the lanes are 4 meters apart, such as Figure 3 As shown, two virtual lane lines are constructed. At the same time, in order to improve the accuracy of creating virtual lane lines, they are drawn in the blank spaces between vehicles as much as possible, that is, to avoid overlapping of the created virtual lane lines with vehicles.

[0077] In another specific application scenario of the embodiment of the present invention, when creating virtual lane lines, a starting lane line can be determined by combining road boundary information, so that all second virtual lane lines are constructed in sequence according to the preset lane width. The road boundary information includes the road boundary line position and the road boundary width. After the number of lanes is calculated based on the road boundary width, the starting lane line is first created based on the road boundary line position and the preset lane width. For example, Figure 4As shown, the preset lane width is 4 meters. After extending 4 meters in the direction of the vehicle according to the road boundary line position, the starting lane line is created. When the number of lanes is 3, the remaining virtual lane lines are created in sequence at intervals of 4 meters.

[0078] It should be noted that, on some driving roads, the width between each lane line, that is, the preset lane width is different. For example, the width of the emergency lane is 4 meters, and the width of other lanes is 3.5 meters. Therefore, when constructing virtual lane lines based on different preset lane widths, first determine whether the preset lane width is unique. If not unique, then based on the method of first creating an initial lane line in the above method, and then sequentially constructing other virtual lane lines, for example, first create a starting lane line according to the emergency lane width of 4 meters, and then create the remaining virtual lane lines at intervals of 3.5 meters to the left from the starting lane line to obtain all the virtual lane lines. The embodiment of the present invention does not make specific limitations.

[0079] In another embodiment of the present invention, the steps further include:

[0080] Under the condition that the position difference value between the first virtual lane line and the second virtual lane line is greater than a preset difference threshold, the first virtual lane line is corrected based on the second virtual lane line to obtain the virtual lane line for trajectory planning.

[0081] In order to improve the accuracy of constructing virtual lane lines and to improve the effectiveness and safety of vehicle trajectory planning, the current execution subject can simultaneously create a first virtual lane line and a second virtual lane line, so as to combine the two virtual lane lines to obtain an optimal virtual lane line to achieve the purpose of virtual lane line correction. Specifically, the current execution subject calculates the position difference value between the first virtual lane line and the second virtual lane line, that is, at the same horizontal position on the driving road, calculates the position width between the two virtual lane lines and determines it as the position difference value. When this position difference value is greater than the preset difference threshold, it means that the interval between the two virtual lane lines is too large and there is a large error. At this time, the current execution end corrects the first virtual lane line based on the second virtual lane line, that is, the position of the first virtual lane line can be brought closer according to the position of the second virtual lane line, so as to achieve the correction purpose and obtain the virtual lane line finally used for trajectory planning. For example, such as Figure 5 As shown, if the position difference between the first virtual lane line L and the second virtual lane line H is greater than a preset difference threshold of 2 meters (which can be configured based on the lane width and is not specifically limited in the embodiment of the present invention), the position of the first virtual lane line L is moved right or left by a certain distance according to the position of the second virtual lane line H, such as half a meter, 30 centimeters, etc., so as to correct the first virtual lane line and obtain the final virtual lane line.

[0082] In another embodiment of the present invention, before the step of determining the road boundary information corresponding to the target vehicle, the method further includes:

[0083] Under the condition that the driving displacement matches a preset displacement threshold, and / or the driving speed matches a preset speed threshold, a coincidence match is performed based on the driving trajectory and the planned trajectory of the target vehicle, and a target following object is selected from the objects to be followed according to the coincidence matching result.

[0084] In order to achieve the purpose of automatic driving control of the target vehicle based on the vehicle following mode when there is no lane line, and because the current execution subject selects the target following object according to the driving information of the object to be followed, at this time, the driving information includes the driving trajectory, driving speed, driving lateral displacement, etc. Therefore, the current execution subject can first determine the driving trajectory, driving speed, and driving lateral displacement of the object to be followed through the perception system. Among them, since the object to be followed can include other vehicles in any direction such as the front, rear, left, and right of the target vehicle, after searching for at least one object to be followed through the perception system, further judgment and selection are made based on the driving position and / or driving speed of the object to be followed. At this time, the current execution subject is pre-configured with a preset displacement threshold and a preset speed threshold for screening, so as to judge the driving displacement and driving speed of the object to be followed. The preset displacement threshold and the preset speed threshold can be configured according to the offset distance of the target vehicle, a specific multiple of the speed, etc., and the embodiment of the present invention does not make specific limitations. When the driving displacement matches the preset displacement threshold and / or the driving speed matches the preset speed threshold, it means that the speed and displacement of the object to be followed meet the driving plan of the target vehicle. Therefore, the current execution subject further matches the driving trajectory with the planned trajectory of the target vehicle for overlap. The overlap matching includes at least one of trajectory overlap matching and expansion profile overlap matching. Specifically, the driving trajectory is first matched with the planned trajectory for overlap. At this time, it can be judged according to the 100% overlap. For example, within a time frame unit, the driving trajectory overlaps with the planned trajectory by 60%, and it is determined that the driving trajectory matches the planned trajectory. The embodiment of the present invention does not make specific limitations. At the same time, in order to avoid a collision between the object to be followed and the target vehicle, the selected object to be followed needs to have a certain safety distance from the target vehicle. At this time, the expansion profile overlap of the driving trajectory and the planned trajectory can be matched to determine whether a collision is expected based on the overlap. For example, in the lateral and longitudinal directions of the driving plan and the planned trajectory, the vehicle contours of the target vehicle and the object to be tracked are expanded at the same time, such as Figure 6As shown, if the overlap between the expanded contours is less than 10%, the overlap matching result is determined to be non-overlapping, and the object to be followed can be selected as the target following object. The embodiment of the present invention is not specifically limited. In addition, the expansion method of the vehicle contour in the embodiment of the present invention can be horizontal, vertical, or horizontal and vertical expansion at the same time, which is not specifically limited.

[0085] In another embodiment of the present invention, after the step of selecting a target following object from the to-be-followed objects according to the coincidence matching result, the method further comprises:

[0086] Under the condition that the target following object is selected, determining the driving direction of the target following object and the planned direction of the target vehicle;

[0087] Under the condition that the driving direction matches the planned direction, trajectory planning of the target vehicle is performed based on the driving information of the target following object, so as to control the target vehicle to travel according to the planned driving path;

[0088] Under the condition that the driving direction does not match the planned direction, a target following object is selected from the objects to be followed again according to the coincidence matching result, or it is determined that the target following object has not been selected.

[0089] In order to achieve safe driving of the vehicle in a following manner when there is no lane line, avoid entering the wrong operation error of following, or enter the wrong route, the current execution subject determines the driving direction of the target following object and the planned direction of the target vehicle after selecting the target following object, so as to determine whether the driving direction is consistent with the planned direction. Among them, the current execution subject can judge whether the driving direction is consistent with the planned direction based on the direction angle difference, for example, if the driving direction is perceived to be angle a and the planned direction is angle b, then a difference comparison is performed; it can also judge whether the driving direction is consistent with the planned direction based on the direction displacement difference, for example, if the lateral displacement of the driving direction is n meters and the lateral displacement of the planned direction is m meters, then a difference comparison is performed, and the embodiment of the present invention does not make specific restrictions. At this time, when the driving direction matches the planned direction, it means that the target following object is used as the following basis for the target vehicle to perform path planning. Therefore, the current execution subject can perform trajectory planning of the target vehicle based on the driving information of the target following object to control the target vehicle to travel according to the planned driving path. When the driving direction does not match the planned direction, it means that the target following object cannot be used as the following basis for the target vehicle path planning. Therefore, the current execution subject reselects the target following object from the objects to be followed according to the coincidence matching result, or determines that the target following object is not selected.

[0090] It should be noted that after all the objects to be followed are selected in turn, the target following object still cannot be selected. In order to ensure the normal driving of the target vehicle and meet the driving planning requirements, the current execution end can control the target vehicle to continue to drive stably according to the current driving speed and driving direction, so as to re-search for the object to be followed or re-identify the lane line after driving for a period of time. The embodiment of the present invention does not make specific limitations.

[0091] In another embodiment of the present invention, before the step of acquiring the driving information of at least one object to be followed corresponding to the target vehicle, the method further includes:

[0092] Scanning a moving object within a preset distance range, and determining the scanned moving object as an object to be followed;

[0093] Under the condition that the driving object is not scanned, trajectory planning information of the target vehicle is obtained, and trajectory planning is performed based on the trajectory planning information and the road boundary information.

[0094] In order to select the target follow-up object from the objects to be tracked so as to follow the vehicle, the current execution subject scans the driving objects within the preset distance range through the perception system. At this time, the preset distance range can be 50 meters, 100 meters, etc., so as to scan all the driving objects as the objects to be followed, and further determine the driving information of each object to be followed to select the target follow-up object. At the same time, if the current execution subject does not scan the driving object within the preset distance range through the perception system, it means that there is no vehicle available for following around the target vehicle, so the trajectory planning information of the target vehicle is directly obtained. Among them, the trajectory planning information may include the trajectory route, planning speed, trajectory curvature, etc., so that the target vehicle continues to control driving according to the original planning of the trajectory route, planning speed, trajectory curvature, etc. in the trajectory planning information within the constraint range of the road boundary information to ensure the safe driving of the target vehicle.

[0095] In another embodiment of the present invention, the step of performing trajectory planning based on the trajectory planning information and the road boundary information includes:

[0096] Adjusting the planned speed in the trajectory planning information, and performing trajectory planning according to the planned speed within the constraint range of the road boundary information, so as to control the target vehicle to travel along the planned straight driving path; and / or,

[0097] A preset safety distance corresponding to the road boundary information is obtained, and planning is performed according to the preset safety distance and the adjusted planned speed to control the target vehicle to travel along the planned right driving path.

[0098] In order to accurately make the target vehicle follow the trajectory planning information and road boundary information, in a specific implementation scenario, the current execution subject can adjust the planning speed, such as slowing down, to control the vehicle to slowly pass through the lane-free area within the constraint range of the road boundary information, and complete the trajectory planning at a low speed to control the target vehicle to travel along the planned straight driving path. In another specific implementation scenario, the current execution subject can adjust the distance from the road boundary line, such as driving close to the road boundary to the right. At this time, first obtain the preset safety distance between the road boundary line, such as 2 meters, 1 meter, etc., which is not specifically limited in the embodiment of the present invention. At the same time, the current execution subject performs trajectory planning according to this expected safety distance and the adjusted planning speed (such as deceleration) so as to control the target vehicle to travel along the planned deceleration path close to the road boundary line, which is not specifically limited in the embodiment of the present invention.

[0099] The embodiment of the present invention obtains driving information of at least one object to be followed corresponding to the target vehicle under the condition that no matching lane line is identified during the driving process of the target vehicle; determines road boundary information corresponding to the target vehicle under the condition that no target following object is selected based on the driving information, and creates a virtual lane line based on the road boundary information and the identified adjacent vehicles; performs trajectory planning for the target vehicle based on the virtual lane line to control the target vehicle to travel according to the planned driving path, and implements vehicle trajectory planning based on the virtual lane line to avoid safety hazards such as line pressing and collision when there are no lane lines as constraints during the automatic driving of the vehicle, thereby achieving the effectiveness of vehicle path planning, improving the safe driving efficiency without lane lines during the automatic driving of the vehicle, and meeting the accuracy requirements of vehicle path planning.

[0100] Furthermore, as a response to the above Figure 1 The implementation of the method shown in the figure, the embodiment of the present invention provides a vehicle driving planning device, such as Figure 7 As shown, the device comprises:

[0101] An acquisition module 21 is used to acquire driving information of at least one object to be followed corresponding to the target vehicle under the condition that no matching lane line is identified during the driving process of the target vehicle;

[0102] A determination module 22, configured to determine road boundary information corresponding to the target vehicle under the condition that no target following object is selected based on the driving information, and to create a virtual lane line based on the road boundary information and the identified adjacent vehicles;

[0103] The planning module 23 is used to plan the trajectory of the target vehicle based on the virtual lane line to control the target vehicle to travel according to the planned driving path.

[0104] Furthermore, the determining module includes:

[0105] An acquisition unit, used to acquire a preset lane width of a driving road on which the target vehicle is located;

[0106] a determining unit, configured to determine the number of lanes based on the road boundary information and the preset lane width;

[0107] a first construction unit, configured to identify an adjacent vehicle having an adjacent relationship with the target vehicle and a driving position of the adjacent vehicle, and to construct a first virtual lane line according to the driving position, the number of lanes, and the preset lane width; and / or,

[0108] The second construction unit is used to determine a starting lane line corresponding to the preset lane width according to the road boundary information, and to sequentially construct all second virtual lane lines according to the number of lanes and the starting lane line.

[0109] Furthermore, the device also includes:

[0110] A correction module is used to correct the first virtual lane line based on the second virtual lane line under the condition that the position difference value between the first virtual lane line and the second virtual lane line is greater than a preset difference threshold, so as to obtain the virtual lane line used for trajectory planning.

[0111] Furthermore, the driving information includes driving track, driving speed, and driving lateral displacement. The device further includes: a selection module,

[0112] The determination module is further used to determine the driving track, driving speed, and driving lateral displacement of at least one of the objects to be followed;

[0113] The selection module is used to perform overlap matching between the driving trajectory and the planned trajectory of the target vehicle under the condition that the driving displacement matches a preset displacement threshold and / or the driving speed matches a preset speed threshold, and select a target following object from the objects to be followed according to the overlap matching result, wherein the overlap matching includes at least one of trajectory overlap matching and expansion profile overlap matching.

[0114] Further,

[0115] The determination module is further used to determine the driving direction of the target following object and the planned direction of the target vehicle under the condition that the target following object is selected;

[0116] The planning module is used to plan the trajectory of the target vehicle based on the driving information of the target following object under the condition that the driving direction matches the planned direction, so as to control the target vehicle to travel according to the planned driving path;

[0117] The selection module is further configured to, under the condition that the driving direction does not match the planned direction, reselect a target following object from the objects to be followed according to a coincidence matching result, or determine that the target following object has not been selected.

[0118] Further,

[0119] The determination module is used to scan a moving object within a preset distance range, and determine the scanned moving object as an object to be followed;

[0120] The planning module is further used to obtain the trajectory planning information of the target vehicle under the condition that the driving object is not scanned, and perform trajectory planning based on the trajectory planning information and the road boundary information.

[0121] Furthermore, the planning module is specifically used to adjust the planned speed in the trajectory planning information, and perform trajectory planning according to the planned speed within the constraint range of the road boundary information, so as to control the target vehicle to travel along the planned straight driving path; and / or, obtain a preset safety distance corresponding to the road boundary information, and perform planning according to the preset safety distance and the adjusted planned speed, so as to control the target vehicle to travel along the planned right-side driving path.

[0122] The embodiment of the present invention obtains driving information of at least one object to be followed corresponding to the target vehicle under the condition that no matching lane line is identified during the driving process of the target vehicle; determines road boundary information corresponding to the target vehicle under the condition that no target following object is selected based on the driving information, and creates a virtual lane line based on the road boundary information and the identified adjacent vehicles; performs trajectory planning for the target vehicle based on the virtual lane line to control the target vehicle to travel according to the planned driving path, and implements vehicle trajectory planning based on the virtual lane line to avoid safety hazards such as line pressing and collision when there are no lane lines as constraints during the automatic driving of the vehicle, thereby achieving the effectiveness of vehicle path planning, improving the safe driving efficiency without lane lines during the automatic driving of the vehicle, and meeting the accuracy requirements of vehicle path planning.

[0123] According to one embodiment of the present invention, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the vehicle driving planning method as described above are implemented.

[0124] Figure 8 A schematic diagram of the structure of a computer device provided according to an embodiment of the present invention is shown, comprising at least one processor, the processor is coupled to a memory, the memory stores a program or instruction running on the processor, and the program or instruction is executed by the processor to implement the steps of the above-mentioned method for generating a vehicle lane change instruction. The specific embodiment of the present invention does not limit the specific implementation of the computer device.

[0125] like Figure 8 As shown, the computer device may include: a processor (processor) 302 , a communication interface (Communications Interface) 304 , a memory (memory) 306 , and a communication bus 308 .

[0126] The processor 302 , the communication interface 304 , and the memory 306 communicate with each other via the communication bus 308 .

[0127] The communication interface 304 is used to communicate with other devices such as clients or other servers.

[0128] The processor 302 is used to execute the program 310, and specifically can execute the relevant steps in the above-mentioned vehicle driving planning method embodiment.

[0129] Specifically, the program 310 may include program codes, which include computer operation instructions.

[0130] The processor 302 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention. The one or more processors included in the computer device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0131] The memory 306 is used to store the program 310. The memory 306 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0132] The program 310 may be specifically configured to enable the processor 302 to perform the following operations:

[0133] Acquiring driving information of at least one object to be followed corresponding to the target vehicle under the condition that no matching lane line is identified during the driving process of the target vehicle;

[0134] Under the condition that no target following object is selected based on the driving information, road boundary information corresponding to the target vehicle is determined, and a virtual lane line is created based on the road boundary information and the identified adjacent vehicles;

[0135] The target vehicle is track-planned based on the virtual lane line to control the target vehicle to travel along the planned driving path.

[0136] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0137] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A vehicle driving planning method, characterized in that: include: Acquiring driving information of at least one object to be followed corresponding to the target vehicle under the condition that no matching lane line is identified during the driving process of the target vehicle; Under the condition that no target following object is selected based on the driving information, road boundary information corresponding to the target vehicle is determined, and a virtual lane line is created based on the road boundary information and the identified adjacent vehicles; The target vehicle is track-planned based on the virtual lane line to control the target vehicle to travel along the planned driving path.

2. The method according to claim 1, characterized in that: The creating of a virtual lane line based on the road boundary information and the identified adjacent vehicles comprises: Obtaining a preset lane width of the road on which the target vehicle is traveling; Determining the number of lanes based on the road boundary information and the preset lane width; Identify an adjacent vehicle having an adjacent relationship with the target vehicle and a driving position of the adjacent vehicle, and construct a first virtual lane line according to the driving position, the number of lanes, and the preset lane width; and / or, A starting lane line corresponding to the preset lane width is determined according to the road boundary information, and all second virtual lane lines are constructed in sequence according to the number of lanes and the starting lane line.

3. The method according to claim 2, characterized in that The method further comprises: Under the condition that the position difference value between the first virtual lane line and the second virtual lane line is greater than a preset difference threshold, the first virtual lane line is corrected based on the second virtual lane line to obtain the virtual lane line for trajectory planning.

4. The method according to claim 1, characterized in that: The driving information includes a driving track, a driving speed, and a driving lateral displacement. Before determining the road boundary information corresponding to the target vehicle, the method further includes: Under the condition that the driving displacement matches a preset displacement threshold, and / or the driving speed matches a preset speed threshold, an overlap matching is performed based on the driving trajectory and the planned trajectory of the target vehicle, and a target following object is selected from the objects to be followed according to the overlap matching result, wherein the overlap matching includes at least one of trajectory overlap matching and expansion profile overlap matching.

5. The method according to claim 4, characterized in that After selecting a target following object from the to-be-followed objects according to the coincidence matching result, the method further includes: Under the condition that the target following object is selected, determining the driving direction of the target following object and the planned direction of the target vehicle; Under the condition that the driving direction matches the planned direction, trajectory planning of the target vehicle is performed based on the driving information of the target following object, so as to control the target vehicle to travel according to the planned driving path; Under the condition that the driving direction does not match the planned direction, a target following object is selected from the objects to be followed again according to the coincidence matching result, or it is determined that the target following object has not been selected.

6. The method according to claim 1, characterized in that Before acquiring the driving information of at least one object to be followed corresponding to the target vehicle, the method further includes: Scanning a moving object within a preset distance range, and determining the scanned moving object as an object to be followed; Under the condition that the driving object is not scanned, trajectory planning information of the target vehicle is obtained, and trajectory planning is performed based on the trajectory planning information and the road boundary information.

7. The method according to claim 6, characterized in that The performing trajectory planning based on the trajectory planning information and the road boundary information includes: Adjusting the planned speed in the trajectory planning information, and performing trajectory planning according to the planned speed within the constraint range of the road boundary information, so as to control the target vehicle to travel along the planned straight driving path; and / or, A preset safety distance corresponding to the road boundary information is obtained, and planning is performed according to the preset safety distance and the adjusted planned speed to control the target vehicle to travel along the planned right driving path.

8. A vehicle driving planning device, characterized in that: include: An acquisition module, used for acquiring driving information of at least one object to be followed corresponding to the target vehicle under the condition that no matching lane line is identified during the driving process of the target vehicle; A determination module, configured to determine road boundary information corresponding to the target vehicle under the condition that no target following object is selected based on the driving information, and to create a virtual lane line based on the road boundary information and the identified adjacent vehicles; A planning module is used to plan the trajectory of the target vehicle based on the virtual lane line to control the target vehicle to travel according to the planned driving path.

9. A vehicle, characterized in that: Including the vehicle driving planning device as described in claim 8.

10. A computer device, characterized in that: It includes at least one processor, which is coupled to a memory, and the memory stores a program or instruction running on the processor, and when the program or instruction is executed by the processor, the steps of the vehicle driving planning method as described in any one of claims 1 to 7 are implemented.

11. A readable storage medium having a program or instruction stored thereon, characterized in that: When the program or instruction is executed by a processor, the steps of the vehicle driving planning method as described in any one of claims 1 to 7 are implemented.

Images