Unmanned vehicle scheduling method, system, equipment and medium

Abstract

The invention discloses an unmanned vehicle scheduling method, system and device and a medium. The method comprises the following steps: determining a buffer area and a to-be-dispatched area corresponding to each task area in a target dispatching area according to site information and unmanned vehicle information of the target dispatching area; determining a first driving path from the scheduling starting point position to the task area position and a second driving path from the task area position to the scheduling ending point position based on a shortest path principle; scheduling the plurality of unmanned vehicles according to the first driving path and the second driving path, and determining a predicted driving track of each unmanned vehicle in the scheduling process; and controlling the unmanned vehicle to pass through a target driving conflict area in the target scheduling area according to the predicted driving track. According to the scheme, the corresponding buffer area and the to-be-dispatched area can be set for the task area according to the actual situation of the dispatching area, the scene applicability is enhanced, vehicle conflict control is carried out based on the predicted driving track of the unmanned vehicle, and the unmanned vehicle dispatching efficiency and robustness can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned vehicles, and in particular to an unmanned vehicle dispatching method, system, equipment and medium. Background Art

[0002] In the field of autonomous driving, orderly, efficient and stable unmanned vehicle dispatching is the core condition for the commissioning and large-scale promotion of unmanned vehicles. Due to the limited on-site environment, the routes are mostly fixed, and the most efficient parking dispatching needs to be achieved in a limited space. The core goal is to achieve the maximum number of vehicles parking in and out in the shortest time.

[0003] Existing unmanned vehicle scheduling is mainly based on a single control logic. For example, a single coordination area is used to control conflicts between vehicles parking in and out. If a vehicle fails to park and occupies the coordination area for a long time, other vehicles will be unable to park in / out. Therefore, the robustness is low. It does not support vehicles parking in and out at the same time, so the parking efficiency is low. New requirements or adjustments often require customized development, which has a long cycle and high deployment costs, so it lacks versatility. Summary of the invention

[0004] The present invention provides an unmanned vehicle scheduling method, system, device and medium, which can set corresponding buffer areas and standby areas for task areas according to the actual situation of the scheduling area, enhance the applicability of scenarios, and control vehicle conflicts based on the predicted driving trajectory of the unmanned vehicle, which helps to improve the efficiency and robustness of unmanned vehicle scheduling.

[0005] According to one aspect of the present invention, a method for dispatching an unmanned vehicle is provided, the method comprising:

[0006] Acquire site information and unmanned vehicle information of the target dispatch area; wherein the site information includes site size, site layout, dispatch starting point location, dispatch end point location, and location and number of parking spaces in the task area; and the unmanned vehicle information includes size, number, and steering characteristics of the unmanned vehicle;

[0007] Determine the buffer area and the waiting area corresponding to each task area in the target scheduling area according to the site information and the unmanned vehicle information; wherein the waiting area has the same number of parking spaces as the corresponding task area;

[0008] Determine a first driving path from the scheduling starting point to the task area and a second driving path from the task area to the scheduling end point based on the shortest path principle; wherein the first driving path passes through the buffer area and the waiting area;

[0009] Scheduling a plurality of unmanned vehicles according to the first driving path and the second driving path, and determining a predicted driving trajectory of each of the unmanned vehicles during the scheduling process;

[0010] The unmanned vehicle is controlled to pass through a target driving conflict area in the target scheduling area according to the predicted driving trajectory; wherein the driving conflict area is an area where unmanned vehicle driving conflicts are prone to occur.

[0011] According to another aspect of the present invention, there is provided an unmanned vehicle dispatching system, the system comprising:

[0012] The dispatch area information acquisition module is used to obtain the site information and unmanned vehicle information of the target dispatch area; wherein the site information includes the site size, site layout, dispatch starting point location, dispatch end point location, and the location and number of parking spaces in the task area; the unmanned vehicle information includes the size, number and steering characteristics of the unmanned vehicle;

[0013] A buffer and standby area determination module, used to determine the buffer area and standby area corresponding to each task area in the target scheduling area according to the site information and the unmanned vehicle information; wherein the number of parking spaces in the standby area is the same as that in the corresponding task area;

[0014] A driving path planning module, used to determine a first driving path from the scheduling starting point to the task area and a second driving path from the task area to the scheduling end point based on the shortest path principle; wherein the first driving path passes through the buffer area and the waiting area;

[0015] an unmanned vehicle scheduling module, configured to schedule a plurality of unmanned vehicles according to the first driving path and the second driving path, and determine a predicted driving trajectory of each of the unmanned vehicles during the scheduling process;

[0016] The conflict area scheduling module is used to control the unmanned vehicle to pass through the target driving conflict area in the target scheduling area according to the predicted driving trajectory; wherein the driving conflict area is an area where unmanned vehicle driving conflicts are prone to occur.

[0017] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0018] at least one processor; and,

[0019] a memory communicatively connected to the at least one processor; wherein,

[0020] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the unmanned vehicle scheduling method described in any embodiment of the present invention.

[0021] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the unmanned vehicle scheduling method described in any embodiment of the present invention when executed.

[0022] The technical solution of the embodiment of the present invention obtains the site information and unmanned vehicle information of the target scheduling area; wherein the site information includes the site size, site layout, scheduling starting point position, scheduling end point position, and the position and number of parking spaces of the task area, and the unmanned vehicle information includes the size, number and steering characteristics of the unmanned vehicle; the buffer area and the waiting area corresponding to each task area in the target scheduling area are determined according to the site information and the unmanned vehicle information; wherein the number of parking spaces in the waiting area is the same as that in the corresponding task area; based on the shortest path principle, a first driving path from the scheduling starting point position to the task area position and a second driving path from the task area position to the scheduling end point position are determined; wherein the first driving path passes through the buffer area and the waiting area; multiple unmanned vehicles are scheduled according to the first driving path and the second driving path, and the predicted driving trajectory of each unmanned vehicle is determined during the scheduling process; the unmanned vehicle is controlled to pass through the target driving conflict area in the target scheduling area according to the predicted driving trajectory; wherein the driving conflict area is an area where unmanned vehicle driving conflicts are prone to occur. This technical solution can set corresponding buffer areas and waiting areas for the task area according to the actual situation of the scheduling area, enhance the scene applicability, and perform vehicle conflict control based on the predicted driving trajectory of the unmanned vehicle, which helps to improve the scheduling efficiency and robustness of the unmanned vehicle.

[0023] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 is a flow chart of an unmanned vehicle dispatching method provided according to Embodiment 1 of the present invention;

[0026] Figure 2A is a schematic diagram of a buffer area and a waiting area provided according to Embodiment 1 of the present invention;

[0027] Figure 2Bis a schematic diagram of another buffer area and a waiting area provided according to the first embodiment of the present invention;

[0028] Figure 2C is a schematic diagram of another buffer area and a waiting area provided according to the first embodiment of the present invention;

[0029] Figure 3A is a schematic diagram of a buffer area in a serial mode provided according to Embodiment 1 of the present invention;

[0030] Figure 3B is a schematic diagram of a buffer area in a parallel mode provided in Embodiment 1 of the present invention;

[0031] Figure 4 is a flow chart of an unmanned vehicle dispatching method provided according to Embodiment 2 of the present invention;

[0032] Figure 5A is a schematic diagram of scheduling an unmanned vehicle to be parked provided according to Embodiment 2 of the present invention;

[0033] Figure 5B is another schematic diagram of scheduling of unmanned vehicles to be parked provided according to the second embodiment of the present invention;

[0034] Figure 6 This is a schematic diagram of unmanned vehicle dispatching in a multi-stage dispatching mode provided according to Embodiment 2 of the present invention;

[0035] Fig. 7A is a schematic diagram of scheduling an unmanned vehicle to be parked provided according to the second embodiment of the present invention;

[0036] Figure 7B is another schematic diagram of scheduling an unmanned vehicle to be parked provided according to the second embodiment of the present invention;

[0037] Figure 8 is a structural schematic diagram of an unmanned vehicle dispatching system provided according to Embodiment 3 of the present invention;

[0038] Fig. 9 It is a structural schematic diagram of an electronic device for implementing an unmanned vehicle dispatching method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0039] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0040] It should be noted that the terms "first", "second", "target", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0041] Embodiment 1

[0042] Figure 1 This is a flow chart of an unmanned vehicle dispatching method provided in Embodiment 1 of the present invention. This embodiment is applicable to the situation of efficiently and accurately dispatching unmanned vehicles. The method can be executed by an unmanned vehicle dispatching system. The unmanned vehicle dispatching system can be implemented in the form of hardware and / or software. The unmanned vehicle dispatching system can be configured in an electronic device with data processing capabilities. Figure 1 As shown, the method includes:

[0043] S110, obtaining site information and unmanned vehicle information of the target dispatching area.

[0044] The target dispatch area may refer to an area where unmanned vehicles need to be dispatched. The site information includes the site size, site layout, dispatch starting point location, dispatch end point location, and the location and number of parking spaces in the task area. The unmanned vehicle information includes the size, number, and steering characteristics of the unmanned vehicles. It should be noted that the unmanned vehicle information here refers to the information of the unmanned vehicles that need to be dispatched.

[0045] Exemplarily, the size of the site can be characterized by the length and width of the target scheduling area, the size of the unmanned vehicle can be characterized by the length and width of the vehicle body, and the steering characteristics of the unmanned vehicle can be characterized by the wheelbase. The site layout can be used to describe the distribution of site buildings in the target scheduling area, such as how many factories are set up in the target scheduling area and the corresponding position of each factory building. The location information can be described in the form of coordinates (such as road coordinates or longitude and latitude coordinates). The mission area can be one or more, for example, it can include one or more of the cage loading area, unloading area and battery replacement area, which can be pre-set according to actual needs.

[0046] S120, determining a buffer area and a waiting area corresponding to each task area in the target scheduling area according to the site information and the unmanned vehicle information.

[0047] It should be noted that due to different actual dispatching needs, the site information and unmanned vehicle information of different dispatching areas are different. In order to effectively cope with the diversity of dispatching scenarios, it is necessary to provide a set of universal unmanned vehicle dispatching solutions for different dispatching areas to improve the applicability of scenarios.

[0048] In this embodiment, after obtaining the site information and unmanned vehicle information of the target scheduling area, a corresponding buffer area and waiting area can be set for each task area in the target scheduling area according to the actual situation of the site information and the unmanned vehicle information. Among them, both the waiting area and the task area are provided with parking spaces, and the waiting area and the corresponding task area have a corresponding number of parking spaces. It should be noted that the parking space here is a virtual parking space, which can be used to support unmanned vehicles to park in or out, and there is no need to actually draw parking space lines. When the unmanned vehicle is subsequently dispatched, the unmanned vehicle first starts from the scheduling starting position, passes through the buffer area, the waiting area and the task area in turn, and after completing the corresponding task in the task area, it starts from the task area and drives to the scheduling end position.

[0049] In this embodiment, there are multiple modes for setting the buffer area and the waiting area, which can be adjusted according to the changes in the site information and the unmanned vehicle information to adapt to the scheduling requirements of different scheduling areas. Optionally, the buffer area and the waiting area corresponding to each task area in the target scheduling area are determined according to the site information and the unmanned vehicle information, including the following steps A1-A4:

[0050] A1. Determine the target lane mode corresponding to each mission area according to the site information; wherein the lane mode includes a single lane mode and a dual lane mode. In the single lane mode, the same channel is used from the buffer area to the waiting area and from the waiting area to the mission area. In the dual lane mode, different channels are used from the buffer area to the waiting area and from the waiting area to the mission area.

[0051] For example, when the width of the site is sufficient, in order to improve the dispatching efficiency of the unmanned vehicle, the target lane mode can be set to a two-lane mode. In this case, different channels are used from the buffer area to the waiting area and from the waiting area to the task area. When the width of the site is insufficient, due to the size of the site, the target lane mode can be set to a single-lane mode. In this case, the same channel is used from the buffer area to the waiting area and from the waiting area to the task area.

[0052] A2. Determine the target area mode corresponding to each mission area according to the unmanned vehicle information; wherein the area mode includes a single area mode and a multi-area mode. The single area mode includes a buffer area and a standby area, and the multi-area mode includes multiple buffer areas and multiple standby areas.

[0053] For example, when the number of unmanned vehicles is large, in order to improve the efficiency of unmanned vehicle scheduling, the target area mode can be set to a multi-area mode, in which case one task area corresponds to multiple buffer areas and multiple waiting areas; when the number of unmanned vehicles is small, in order to reduce the complexity of unmanned vehicle scheduling, the target area mode can be set to a single area mode, in which case one task area corresponds only to one buffer area and one waiting area.

[0054] A3. Determine the target parking space pattern and the target number of parking spaces in the waiting area corresponding to each mission area according to the site information and the unmanned vehicle information; wherein the parking space pattern includes a vertical parking space pattern and a diagonal parking space pattern.

[0055] Exemplarily, when the width of the site is sufficient, in order to reduce the difficulty of parking the unmanned vehicle, the target parking space mode of the waiting area can be set to a vertical parking space mode. At this time, the parking spaces in the waiting area and the parking spaces in the task area are at the same angle (both are vertical), so the unmanned vehicle located in the waiting area can be vertically reversed into the task area; when the width of the site is insufficient, due to the limitation of the site size, the target parking space mode of the waiting area can be set to an oblique parking space mode. At this time, the parking spaces in the waiting area and the parking spaces in the task area are inconsistent (the parking spaces in the waiting area are oblique, and the parking spaces in the task area are vertical), so the unmanned vehicle located in the waiting area needs to be reversed into the task area based on a certain steering angle. Further, the size of the parking space can be determined based on the size of the unmanned vehicle, and the oblique angle of the parking space can be determined based on the steering characteristics of the unmanned vehicle. In addition, the number of target parking spaces in the waiting area needs to be consistent with the number of parking spaces in the corresponding task area.

[0056] A4. Determine the buffer area and waiting area corresponding to each mission area according to the target lane mode, target area mode, target parking space mode and target number of parking spaces.

[0057] Figures 2A-2C Schematic diagrams of a buffer area and a waiting area in different modes provided by the first embodiment of the present invention. Figure 2A As shown, the buffer area and the waiting area in the dual-lane mode, the single-area mode and the vertical parking space mode are displayed. The buffer area (i.e. the yellow area) and the waiting area (i.e. the red area) in the figure correspond to the buffer area and the waiting area respectively, the cage loading area (i.e. the green area) corresponds to the task area (the specific task is cage loading), 001-007 and 008-014 represent the parking spaces in the cage loading area and the waiting area respectively (both are set to the vertical direction), the small gray rectangle containing a circle represents an unmanned vehicle, the circle represents the front of the vehicle, the arrow direction represents the driving direction of the unmanned vehicle (including forward and reverse), and the two pink lanes located above and below the waiting area are used to support the unmanned vehicle to drive from the buffer area to the waiting area and from the waiting area to the cage loading area respectively.

[0058] like Figure 2B As shown, the buffer area and the waiting area in the single-lane mode, the single-area mode and the oblique parking space mode are displayed. The buffer area and the waiting area in the figure correspond to the buffer area and the waiting area respectively, the cage loading area corresponds to the task area (the specific task is cage loading), 001-004 (004 is not shown in the figure) and 005-008 (008 is not shown in the figure) represent the parking spaces in the cage loading area and the waiting area respectively (the parking spaces in the cage loading area are set to the vertical direction, and the parking spaces in the waiting area are set to the oblique direction), the small gray rectangle containing a circle represents an unmanned vehicle, the circle represents the front of the vehicle, the direction of the arrow represents the driving direction of the unmanned vehicle (including forward and reverse), and the lane between the waiting area and the cage loading area is used to support the unmanned vehicle to drive from the buffer area to the waiting area and from the waiting area to the cage loading area.

[0059] like Figure 2C As shown in the figure, the buffer area and waiting area in the dual-lane mode, multi-area mode and vertical parking mode are shown. The buffer area and waiting area in the figure correspond to the buffer area and the waiting area respectively, and the cage area corresponds to the task area (the specific task is cage loading). The small gray rectangle containing a circle represents an unmanned vehicle, in which the circle represents the front of the vehicle, and the arrow direction represents the driving direction of the unmanned vehicle (including forward and reverse). As can be seen from the figure, there are a total of 2 buffer zones (buffer zone 1 and buffer zone 2), 2 waiting areas (waiting area 1 and waiting area 2) and 2 cage areas (cage area 1 and cage area 2), and each cage area corresponds to 2 buffer zones and 2 waiting areas. Among them, 001-006 (003 is not shown in the figure) and 013-018 (015 is not shown in the figure) respectively represent the parking spaces in the caged area 1 and the waiting area 1 (both are set to the vertical direction), and the two lanes immediately above and below the waiting area 1 are used to support the unmanned vehicle from the buffer zone 1 or the buffer zone 2 to the waiting area 1 and from the waiting area 1 to the caged area 1; 007-012 (009 is not shown in the figure) and 019-024 (021 is not shown in the figure) respectively represent the parking spaces in the caged area 2 and the waiting area 2 (both are set to the vertical direction), and the two lanes immediately below and above the waiting area 2 are used to support the unmanned vehicle from the buffer zone 1 or the buffer zone 2 to the waiting area 2 and from the waiting area 2 to the caged area 2.

[0060] S130, determining a first driving path from the scheduling starting point position to the task area position and a second driving path from the task area position to the scheduling end point position based on the shortest path principle.

[0061] In this embodiment, in order to improve the dispatching efficiency of the unmanned vehicle, the first driving path from the dispatching starting point to the task area and the second driving path from the task area to the dispatching end point can be planned based on the shortest path principle. Among them, the first driving path passes through the buffer area and the waiting area. It can be understood that when the first driving path and the second driving path of the unmanned vehicle are planned using the shortest path principle, it can be ensured that the first driving path is the shortest path from the dispatching starting point to the task area, and the second driving path is the shortest path from the task area to the dispatching end point, thereby effectively reducing the driving time from the dispatching starting point to the task area and from the task area to the dispatching end point, thereby improving the dispatching efficiency of the unmanned vehicle.

[0062] Furthermore, considering that if the first driving path and the second driving path are planned only based on the shortest path principle, the scope of the unmanned vehicle driving conflict area may be larger. Among them, the driving conflict area can be understood as an area where unmanned vehicle driving conflicts are likely (or may) occur, but this does not mean that unmanned vehicle driving conflicts will definitely occur. Since the conflict control of unmanned vehicles also requires a certain amount of computing power, although path planning based on the shortest path principle can effectively improve the scheduling efficiency of unmanned vehicles, when the scope of the driving conflict area is large, it takes more time to control the conflict, which will affect the scheduling efficiency of unmanned vehicles. Therefore, in order to better balance the impact of driving time and conflict control time on the scheduling efficiency of unmanned vehicles, in this embodiment, the first driving path and the second driving path planned based on the shortest path principle can also be adjusted in combination with the actual situation of the scope of the driving conflict area, so as to achieve the purpose of optimizing the overall scheduling efficiency of unmanned vehicles.

[0063] For example, Figure 2C For example, if it can be determined based on the shortest path principle that the unmanned vehicle in buffer zone 2 has the shortest driving distance from the exit lane to waiting zone 2, this will seriously affect the unmanned vehicles in caged area 1 and caged area 2 from reaching the dispatching terminal position through the exit lane. At this time, the exit lane constitutes a larger driving conflict area, which will affect the dispatching efficiency of the unmanned vehicle. In order to reduce the impact of the larger driving conflict area on the dispatching efficiency of the unmanned vehicle, it can be set that the unmanned vehicle in buffer zone 2 can only drive to caged area 2 through the entry lane, thereby greatly reducing the scope of the driving conflict area on the basis of increasing the shorter driving distance, which helps to improve the overall efficiency of unmanned vehicle dispatching.

[0064] S140, scheduling a plurality of unmanned vehicles according to the first driving path and the second driving path, and determining a predicted driving trajectory of each unmanned vehicle during the scheduling process.

[0065] In this embodiment, the scheduling priority can be set in advance for the unmanned vehicle, such as parking out of the mission area > parking in the mission area > parking in the waiting area. After the first driving path and the second driving path are planned, the multiple unmanned vehicles can be scheduled according to the first driving path and the second driving path based on the preset scheduling priority. Optionally, scheduling multiple unmanned vehicles according to the first driving path and the second driving path includes the following steps B1-B3:

[0066] B1. If there is an empty parking space in the buffer area, the current unmanned vehicle is controlled to drive from the dispatch starting point to the buffer area according to the first driving path, and during the dispatch process, it is determined whether there is an empty parking space in the waiting area.

[0067] Specifically, first determine whether there is an empty space in the buffer area. If so, send instructions to the current unmanned vehicle to control the current unmanned vehicle to drive from the scheduling starting point to the buffer area according to the first driving path, and determine whether there is an empty parking space in the waiting area during the scheduling process; if not, continue to wait until there is an empty space in the buffer area.

[0068] B2. If so, the current unmanned vehicle is controlled to drive from the buffer area to the idle parking space in the waiting area, and during the scheduling process, it is determined whether there is an idle parking space in the task area corresponding to the idle parking space in the waiting area.

[0069] If there are free parking spaces in the waiting area, a command is issued to the current unmanned vehicle to control the current unmanned vehicle to back up from the buffer area to the free parking spaces in the waiting area without any gaps, and during the scheduling process, it is determined whether there are free parking spaces in the task area corresponding to the free parking spaces in the waiting area; if there are no free parking spaces in the waiting area, it continues to wait until there are vacancies in the waiting area, and the unmanned vehicle in front of the buffer area is preferentially controlled to back up to the free parking spaces in the waiting area. If there are multiple free parking spaces in the waiting area, multiple unmanned vehicles are supported to back up to multiple free parking spaces in the waiting area in batches.

[0070] B3. If it exists, control the current unmanned vehicle to drive from the idle parking space in the waiting area to the idle parking space in the corresponding mission area.

[0071] If there is an idle parking space in the mission area corresponding to the idle parking space in the waiting area, a command is issued to the current unmanned vehicle to control the current unmanned vehicle to continue to back into the corresponding idle parking space in the mission area from the idle parking space in the waiting area without stopping; if there is no idle parking space in the mission area, it continues to wait until there is an empty space in the mission area, and controls the unmanned vehicle in the idle parking space in the waiting area corresponding to the idle parking space in the mission area to back into the idle parking space in the mission area. If there are multiple idle parking spaces in the mission area, multiple unmanned vehicles are supported to back into multiple idle parking spaces in the mission area in batches.

[0072] Through such a setting, the present solution can realize efficient scheduling of multiple unmanned vehicles based on the actual idle conditions of the buffer area, the waiting area and the task area, and according to the first driving path and the second driving path.

[0073] In addition, in the process of scheduling multiple unmanned vehicles according to the first driving path and the second driving path, it is also necessary to determine the predicted driving trajectory of each unmanned vehicle. The predicted driving trajectory can be used to predict the driving trajectory of the unmanned vehicle within a preset time (such as 5 seconds), so that the unmanned vehicle scheduling in the driving conflict area can be realized based on the predicted driving trajectory of each unmanned vehicle, thereby ensuring the driving safety of the unmanned vehicle in the driving conflict area.

[0074] S150, controlling the unmanned vehicle to pass through a target driving conflict area in a target scheduling area according to the predicted driving trajectory.

[0075] Among them, the driving conflict area is an area where unmanned vehicle driving conflicts are prone to occur. For example, the target driving conflict area can be an intersection area, a parking area, and a two-way single lane area. Exemplarily, when the target driving conflict area is a two-way single lane area, the safe dispatch of unmanned vehicles in the two-way single lane area can be achieved by judging the occupation of the two-way single lane by the oncoming unmanned vehicle. Specifically, when the current unmanned vehicle is about to drive to the two-way single lane area, it can be judged whether the two-way single lane area is occupied by the opposite unmanned vehicle of the current unmanned vehicle based on the predicted driving trajectory of other unmanned vehicles. If so, it indicates that there is a trajectory conflict between the current unmanned vehicle and its opposite unmanned vehicle. At this time, in order to ensure the driving safety of the current unmanned vehicle, it is necessary to wait for the opposite unmanned vehicle to pass through the two-way single lane area (at this time, the two-way single lane area is not occupied by the opposite unmanned vehicle), and then control the current unmanned vehicle to pass in the two-way single lane area; otherwise, an instruction can be directly issued to control the current unmanned vehicle to pass through the two-way single lane area.

[0076] The technical solution of the embodiment of the present invention obtains the site information and unmanned vehicle information of the target scheduling area; wherein the site information includes the site size, site layout, scheduling starting point position, scheduling end point position, and the position and number of parking spaces of the task area, and the unmanned vehicle information includes the size, number and steering characteristics of the unmanned vehicle; the buffer area and the waiting area corresponding to each task area in the target scheduling area are determined according to the site information and the unmanned vehicle information; wherein the number of parking spaces in the waiting area is the same as that in the corresponding task area; based on the shortest path principle, a first driving path from the scheduling starting point position to the task area position and a second driving path from the task area position to the scheduling end point position are determined; wherein the first driving path passes through the buffer area and the waiting area; multiple unmanned vehicles are scheduled according to the first driving path and the second driving path, and the predicted driving trajectory of each unmanned vehicle is determined during the scheduling process; the unmanned vehicle is controlled to pass through the target driving conflict area in the target scheduling area according to the predicted driving trajectory; wherein the driving conflict area is an area where unmanned vehicle driving conflicts are prone to occur. This technical solution can set corresponding buffer areas and waiting areas for the task area according to the actual situation of the scheduling area, enhance the scene applicability, and perform vehicle conflict control based on the predicted driving trajectory of the unmanned vehicle, which helps to improve the scheduling efficiency and robustness of the unmanned vehicle.

[0077] In this embodiment, optionally, the target driving conflict area is an intersection area; accordingly, controlling the unmanned vehicle to pass through the target driving conflict area in the target scheduling area according to the predicted driving trajectory includes the following steps C1-C4:

[0078] C1. When the current unmanned vehicle travels to the target distance from the intersection, it determines whether the intersection is occupied based on the predicted driving trajectories of other unmanned vehicles.

[0079] Among them, the target distance may refer to the reference distance between the unmanned vehicle and the intersection area, which may be used as a trigger condition for determining whether the intersection area is occupied. Exemplarily, a preset duration (such as 5 seconds) may be used as the target driving time for the unmanned vehicle to reach the intersection area, and then the target distance may be determined based on the target driving time and the driving speed of the unmanned vehicle. Specifically, if the predicted driving trajectory of other unmanned vehicles is partially or completely located in the intersection area, it indicates that the intersection area is occupied by other unmanned vehicles. At this time, in order to ensure the driving safety of the current unmanned vehicle, it is necessary to wait for other unmanned vehicles to pass through the intersection area (at this time the intersection area is not occupied), and then control the current unmanned vehicle to drive in the intersection area.

[0080] Furthermore, if there are unmanned vehicles entering and exiting the same lane as other unmanned vehicles in the lane where other unmanned vehicles are located before passing through the intersection area, that is, there are unmanned vehicles entering and exiting the same lane behind other unmanned vehicles, when other unmanned vehicles occupy the intersection area, it may be necessary to wait until all other unmanned vehicles and the unmanned vehicles entering and exiting the same lane as them have passed the intersection area (the intersection area is not occupied at this time) before controlling the current unmanned vehicle to drive in the intersection area.

[0081] C2. If it is not occupied and the next target driving area of ​​the current unmanned vehicle is free, the current unmanned vehicle is controlled to drive through the intersection area to the next target driving area.

[0082] If the intersection area is not occupied according to the predicted driving trajectory of other unmanned vehicles, it is necessary to further determine whether the next target driving area of ​​the current unmanned vehicle is free. If so, the current unmanned vehicle is directly controlled to drive through the intersection area to the next target driving area; otherwise, it needs to continue waiting.

[0083] C3. Determine whether there is a candidate unmanned vehicle that enters and exits the same lane as the current unmanned vehicle before passing through the intersection area.

[0084] The candidate unmanned vehicle may refer to an unmanned vehicle that enters and exits the same lane as the current unmanned vehicle before the current unmanned vehicle passes through the intersection area. In this embodiment, when the intersection area is occupied by the current unmanned vehicle, it is also necessary to determine whether there is a candidate unmanned vehicle that enters and exits the same lane as the current unmanned vehicle before the current unmanned vehicle passes through the intersection area, that is, whether there is an unmanned vehicle behind the current unmanned vehicle that enters and exits the same lane.

[0085] C4. If it exists and the next candidate driving area of ​​the candidate unmanned vehicle is free, control the candidate unmanned vehicle to drive to the next candidate driving area through the intersection area.

[0086] If there is a candidate unmanned vehicle that enters and exits the same lane as the current unmanned vehicle before passing through the intersection, it is necessary to further determine whether the next candidate driving area of ​​the candidate unmanned vehicle is free. If so, the candidate unmanned vehicle is directly controlled to pass through the intersection and drive to the next candidate driving area, otherwise it needs to continue waiting.

[0087] Through such a setting, this scheme can control the unmanned vehicle to pass safely in the intersection area according to the predicted driving trajectory of the unmanned vehicle, and at the same time can maximize the traffic efficiency of the unmanned vehicle in the intersection area.

[0088] In this embodiment, the multi-region mode may include a serial mode and a parallel mode. In the serial mode, multiple buffer regions are arranged in series and have a sequential relationship. In the parallel mode, multiple buffer regions are arranged in parallel. Figure 3A and Figure 3BSchematic diagrams of buffer areas in a serial mode and a parallel mode provided in Embodiment 1 of the present invention. Figure 3A As shown in the figure, there are three serial buffer areas, which are buffer area 1, buffer area 2 and buffer area 3 from front to back according to the driving order of the unmanned vehicles. START represents the dispatch starting point, V1-V4 represent different unmanned vehicles, STOP1-STOP3 represent the stop points of the three buffer areas, and the no-stopping sections 1 and 2 only allow unmanned vehicles to pass but not to stop. Figure 3B As shown, there are two parallel buffer areas (i.e., the yellow areas in the figure), namely buffer area 1 and buffer area 2, and the two buffer areas can independently perform buffer area parking scheduling for unmanned vehicles without interfering with each other.

[0089] It should be noted that in this embodiment, a stop point is set for each buffer area to replace the large and small parking spaces in the buffer area in the existing solution. Specifically, the existing solution is based on the occupancy of large and small parking spaces in the buffer area, and the cloud controls the dispatch of unmanned vehicles in the buffer area from large parking spaces to small parking spaces, and the vehicles will stop in small parking spaces and need to wait for parking space allocation and scheduling tasks to be issued, so the scheduling efficiency is low. In addition, when the unmanned vehicle is not completely parked in a small parking space, it may be recognized that there is no unmanned vehicle parked in the small parking space, resulting in vehicle recognition errors, thereby affecting the normal scheduling of the unmanned vehicle. The stop point set in this embodiment can be understood as an area near the parking point, and all scheduling is directly initiated by the algorithm without waiting for parking space allocation and scheduling tasks to be issued, which simplifies the unmanned vehicle scheduling link, reduces the complexity of unmanned vehicle scheduling, improves the efficiency of unmanned vehicle scheduling, and enhances the robustness of unmanned vehicle scheduling.

[0090] Accordingly, scheduling multiple unmanned vehicles according to the first driving path and the second driving path includes the following steps D1-D4:

[0091] D1. When the target area mode is serial mode, if there is a vacant space in the initial buffer area, the current unmanned vehicle is controlled to drive from the scheduling starting point to the initial buffer area according to the first driving path, and whether there is a vacant space in the subsequent buffer area is determined during the scheduling process; if there is no other unmanned vehicle in the initial buffer area, the current unmanned vehicle is controlled to drive to the stop point in the initial buffer area; if there are other unmanned vehicles in the initial buffer area, the current unmanned vehicle is controlled to drive in the direction of the stop point in the initial buffer area.

[0092] Specifically, when the target area mode is the serial mode, first determine whether there is an empty space in the initial buffer area. If so, control the current unmanned vehicle to drive from the scheduling starting point to the initial buffer area according to the first driving path, and determine whether there is an empty space in the subsequent buffer area during the scheduling process; if not, wait. Further, in the process of controlling the current unmanned vehicle to drive from the scheduling starting point to the initial buffer area, determine whether there are other unmanned vehicles in the initial buffer area. If so, control the current unmanned vehicle to drive in the direction of the stop point in the initial buffer area, so that it drives behind other unmanned vehicles in the initial buffer area; if not, the current unmanned vehicle can be controlled to drive directly to the stop point in the initial buffer area.

[0093] For example, Figure 3A As shown, there is an empty space in buffer zone 1 and no other unmanned vehicles. At this time, an instruction can be issued to control unmanned vehicle V1 to drive directly from the scheduling starting point START to the stop point STOP1 in buffer zone 1. During the scheduling process, it is found that there is an empty space in buffer zone 2 and there is an unmanned vehicle V2. At this time, instructions can continue to be issued to control unmanned vehicle V1 to drive from STOP1 without stopping to the back of unmanned vehicle V2 in buffer zone 2. During the scheduling process, it is found that there is no empty space in buffer zone 3. At this time, unmanned vehicles V2 and V1 in buffer zone 2 need to stop and wait.

[0094] D2. If it exists, the reference unmanned vehicle located at the stop point in the initial buffer area is controlled to travel from the stop point in the initial buffer area to the subsequent buffer area according to the first driving path; if there are no other unmanned vehicles in the subsequent buffer area, the reference unmanned vehicle is controlled to travel to the stop point in the subsequent buffer area; if there are other unmanned vehicles in the subsequent initial buffer area, the reference unmanned vehicle is controlled to travel in the direction of the stop point in the subsequent buffer area.

[0095] Specifically, if it is determined in the above dispatching process that there are vacancies in the subsequent buffer area, it is necessary to further determine whether there are other unmanned vehicles in the subsequent buffer area. If there are, the reference unmanned vehicle located at the stop point in the initial buffer area is controlled to drive in the direction of the stop point in the subsequent buffer area, so that it drives behind other unmanned vehicles in the subsequent buffer area; if not, the reference unmanned vehicle located at the stop point in the initial buffer area can be controlled to drive directly to the stop point in the subsequent buffer area. If it is determined in the above dispatching process that there are no vacancies in the subsequent buffer area, all unmanned vehicles located in the initial buffer area must stop and wait.

[0096] D3. When the target area mode is the parallel mode, it is determined whether there is a vacancy in each target buffer area.

[0097] Specifically, when the target area mode is the parallel mode, since each buffer area will perform buffer area parking scheduling independently, it is necessary to determine whether there is a vacancy for each target buffer area. The target buffer area may refer to any buffer area in the parallel mode.

[0098] D4. If it exists, the current unmanned vehicle is controlled to drive from the scheduling starting point to the target buffer area according to the first driving path; if there is no other unmanned vehicle in the target buffer area, the current unmanned vehicle is controlled to drive to the stop point in the target buffer area; if there is other unmanned vehicle in the target buffer area, the current unmanned vehicle is controlled to drive in the direction of the stop point in the target buffer area.

[0099] Specifically, when it is determined that there are vacancies in one or more target buffer areas, it can be further determined whether there are other unmanned vehicles in each target buffer area with vacancies. For each target buffer area with vacancies, if there are other unmanned vehicles in the target buffer area, the current unmanned vehicle can be controlled to drive toward the stop point of the target buffer area so that it drives behind the other unmanned vehicles in the target buffer area; if there are no other unmanned vehicles, the current unmanned vehicle can be controlled to drive directly to the stop point of the target buffer area.

[0100] Furthermore, whether in serial mode or parallel mode, during the unmanned vehicle dispatching process, if it is detected that the unmanned vehicle closest to the buffer area's stop point is in a stopped state, and the distance between the unmanned vehicle and the buffer area's stop point is greater than a preset distance (such as 3 meters), in order to avoid wasting the buffer area space, a command can be issued to control the unmanned vehicle to drive to the vicinity of the buffer area's stop point, so that the buffer area can support more unmanned vehicles. Figure 3A For example, assuming that the preset distance is 3 meters, if the distance between the unmanned vehicle V2 and STOP2 in the buffer zone 2 is greater than 3 meters, the unmanned vehicle V2 can be controlled to travel to the vicinity of STOP2.

[0101] Through such a setting, this scheme can reduce the complexity of unmanned vehicle scheduling based on the stop points in the buffer area and improve the efficiency and robustness of unmanned vehicle scheduling.

[0102] Embodiment 2

[0103] Figure 4A flow chart of an unmanned vehicle scheduling method provided in the second embodiment of the present invention, this embodiment is optimized based on the above embodiment. The specific optimization is: the target driving conflict area is the parking space area; accordingly, the unmanned vehicle is controlled to pass through the target driving conflict area in the target scheduling area according to the predicted driving trajectory, including: if the current unmanned vehicle is a vehicle to be parked, and there is a target unmanned vehicle that is being parked in or out, then the target parking space of the current unmanned vehicle is determined according to the predicted driving trajectory of the target unmanned vehicle and the predicted driving trajectory of the current unmanned vehicle, and the current unmanned vehicle is controlled to drive to the target parking space; if the current unmanned vehicle is a vehicle to be parked out, and there is a target unmanned vehicle that is being parked in or out, then it is determined whether there is a trajectory conflict between the predicted driving trajectory of the target unmanned vehicle and the predicted driving trajectory of the current unmanned vehicle, and the current unmanned vehicle is controlled to park out of the current parking space according to the judgment result.

[0104] like Figure 4 As shown, the method of this embodiment specifically includes the following steps:

[0105] S210, obtaining site information and unmanned vehicle information of the target dispatching area.

[0106] Among them, the site information includes the site size, site layout, scheduling starting point location, scheduling end point location, and the location of the task area and the number of parking spaces. The unmanned vehicle information includes the size, number and steering characteristics of the unmanned vehicle.

[0107] S220, determining a buffer area and a waiting area corresponding to each task area in the target scheduling area according to the site information and the unmanned vehicle information.

[0108] Among them, the number of parking spaces in the waiting area and the corresponding task area is the same.

[0109] S230: Determine a first driving path from the scheduling starting point to the task area and a second driving path from the task area to the scheduling end point based on the shortest path principle.

[0110] The first driving path passes through a buffer area and a waiting area.

[0111] S240, scheduling a plurality of unmanned vehicles according to the first driving path and the second driving path, and determining a predicted driving trajectory of each unmanned vehicle during the scheduling process.

[0112] Among them, the specific implementation method of S210-S240 can refer to the relevant description in the above-mentioned embodiment 1, and will not be repeated here.

[0113] S250, when the target driving conflict area in the target dispatching area is a parking space area, determine the dispatching type of the current unmanned vehicle; wherein the dispatching type is waiting to park in or waiting to park out.

[0114] The parking area includes the parking area corresponding to the waiting area and the task area. The waiting to park in and the waiting to park out can be understood as the unmanned vehicle waiting to park in the parking area and the unmanned vehicle waiting to park out of the parking area.

[0115] S260: If the dispatch type of the current unmanned vehicle is waiting to be parked, and there is a target unmanned vehicle that is parking in or out, the target parking space of the current unmanned vehicle is determined according to the predicted driving trajectory of the target unmanned vehicle and the predicted driving trajectory of the current unmanned vehicle, and the current unmanned vehicle is controlled to drive to the target parking space.

[0116] In this embodiment, for unmanned vehicles to be parked, suitable target parking spaces can be flexibly allocated to them based on the predicted driving trajectories of other unmanned vehicles, and flexible scheduling of unmanned vehicles to park in / out at the same time can be achieved. Compared with the prior art method of scheduling unmanned vehicles strictly according to the parking interval, this solution can maximize the scheduling efficiency of unmanned vehicles while avoiding driving conflicts among multiple unmanned vehicles.

[0117] Specifically, if the dispatch type of the current unmanned vehicle is to be parked, and there is a target unmanned vehicle that is parking in or out, then based on the principle that the predicted driving trajectories do not conflict, one is selected from multiple free parking spaces in the parking area as the target parking space for the current unmanned vehicle according to the predicted driving trajectory of the target unmanned vehicle and the predicted driving trajectory of the current unmanned vehicle, so as to ensure that there is no conflict between the predicted driving trajectory of the current unmanned vehicle corresponding to the target parking space and the predicted driving trajectory of the target unmanned vehicle. At this time, the current unmanned vehicle can be controlled to drive directly to the target parking space. If there are multiple parking spaces that meet the above conditions, one of them can be selected randomly.

[0118] For example, Figure 5A As shown, V1 is parking in parking space 006, V2 is waiting to park, and there are two free parking spaces in the parking area (i.e., 009 and 010). Since the predicted driving trajectory of V2 corresponding to 009 conflicts with the predicted driving trajectory of V1, and the predicted driving trajectory of V2 corresponding to 010 does not conflict with the predicted driving trajectory of V1, parking space 010 can be used as the target parking space for V2, and V2 can be controlled to park in parking space 010.

[0119] For example, Figure 5B As shown, V1 is parking out, V2 is waiting to park in, and there are two vacant parking spaces in the parking area (i.e., 007 and 012). Since the predicted driving trajectory of V2 corresponding to 007 conflicts with the predicted driving trajectory of V1, and the predicted driving trajectory of V2 corresponding to 012 does not conflict with the predicted driving trajectory of V1, parking space 012 can be used as the target parking space for V2, and V2 can be controlled to park in parking space 012.

[0120] It should be noted that, in special cases, the predicted driving trajectory of the current unmanned vehicle corresponding to each parking space in the parking area conflicts with the predicted driving trajectory of the target unmanned vehicle. At this time, the target parking space can be determined according to the number of free parking spaces in the parking area. If there is one free parking space in the parking area, the free parking space is directly determined as the target parking space; if there are multiple free parking spaces in the parking area, one can be randomly selected as the target parking space. In view of the above situation, in order to ensure the driving safety of the current unmanned vehicle, it is necessary to wait for the target unmanned vehicle to complete parking in or out before controlling the current unmanned vehicle to drive to the target parking space.

[0121] In this embodiment, optionally, controlling the current unmanned vehicle to drive to the target parking space includes: if the predicted driving trajectory of the current unmanned vehicle corresponding to the target parking space conflicts with the predicted driving trajectory of the target unmanned vehicle, then after the target unmanned vehicle completes parking in or out, controlling the current unmanned vehicle to drive directly to the target parking space; or, controlling the current unmanned vehicle to arrive at a temporary parking position, and after the target unmanned vehicle completes parking in or out, controlling the current unmanned vehicle to drive from the temporary parking position to the target parking space.

[0122] In this embodiment, in case that the predicted driving trajectory of the current unmanned vehicle corresponding to the target parking space conflicts with the predicted driving trajectory of the target unmanned vehicle, two optional scheduling methods are provided for the current unmanned vehicle, which can be flexibly selected according to actual needs (such as the principle of optimal scheduling efficiency). One is a single-stage scheduling method, which controls the current unmanned vehicle to drive directly to the target parking space after waiting for the target unmanned vehicle to complete parking or parking out; the other is a multi-stage scheduling method, which sets a temporary stop position for the current unmanned vehicle based on the principle that some predicted driving trajectories do not conflict, first controls the current unmanned vehicle to arrive at the temporary stop position, and after the target unmanned vehicle completes parking or parking out, controls the current unmanned vehicle to drive from the temporary stop position to the target parking space.

[0123] For example, Figure 6 As shown in the figure, V1 is parking in parking space 009, and V2 is waiting to park in parking space 010. At this time, it is found that the predicted driving trajectories of V1 and V2 conflict. In this case, V2 can be controlled to drive to temporary stop position STOP2 first, and V2 will not affect the normal driving of V1 during this process; then wait for V1 to park in parking space 009, and then control V2 to start from temporary stop position STOP2 and park in parking space 010.

[0124] S270: If the dispatch type of the current unmanned vehicle is to be parked out, and there is a target unmanned vehicle that is parking in or out, determine whether there is a trajectory conflict between the predicted driving trajectory of the target unmanned vehicle and the predicted driving trajectory of the current unmanned vehicle, and control the current unmanned vehicle to park out of the current parking space based on the determination result.

[0125] In this embodiment, if the dispatch type of the current unmanned vehicle is to be parked out, and there is a target unmanned vehicle that is parking in or out, it is necessary to determine whether there is a trajectory conflict between the predicted driving trajectory of the target unmanned vehicle and the predicted driving trajectory of the current unmanned vehicle. If there is no conflict, an instruction can be directly issued to control the current unmanned vehicle to park out from the current parking space; if there is a conflict, it is necessary to wait for the target unmanned vehicle to complete parking in or out before issuing an instruction to control the current unmanned vehicle to park out from the current parking space, thereby ensuring the driving safety of the current unmanned vehicle and the target unmanned vehicle.

[0126] For example, Fig. 7A As shown, V2 and V3 are parking out, and V1 is waiting to park out. As can be seen from the figure, there is a conflict between the predicted driving trajectories of V1 and V2. At this time, it is necessary to wait for V2 to complete parking out before judging whether there is a conflict between the predicted driving trajectories of V1 and V3. If there is no conflict, a command can be directly issued to control V1 to park out from parking space 003; if there is still a conflict, it is necessary to wait for V3 to complete parking out before issuing a command to control V1 to park out from parking space 003.

[0127] For example, Figure 7B As shown in the figure, V3 is parking in parking space 008, while V1 and V2 are waiting to park out. As can be seen from the figure, there is no conflict between the predicted driving trajectories of V1 and V3, but there is a conflict between the predicted driving trajectories of V2 and V3. Therefore, an instruction can be issued to control V1 to park out, and after V3 has finished parking, an instruction can be issued to control V2 to park out.

[0128] The technical solution of the embodiment of the present invention is that when the target driving conflict area is a parking area, if the current unmanned vehicle is a vehicle to be parked, and there is a target unmanned vehicle that is being parked in or out, the target parking space of the current unmanned vehicle is determined according to the predicted driving trajectory of the target unmanned vehicle and the predicted driving trajectory of the current unmanned vehicle, and the current unmanned vehicle is controlled to drive to the target parking space; if the current unmanned vehicle is a vehicle to be parked out, and there is a target unmanned vehicle that is being parked in or out, it is determined whether there is a trajectory conflict between the predicted driving trajectory of the target unmanned vehicle and the predicted driving trajectory of the current unmanned vehicle, and the current unmanned vehicle is controlled to park out of the current parking space according to the judgment result. This technical solution can coordinate the safe passage of unmanned vehicles in the parking area by predicting the driving trajectory of unmanned vehicles in real time, and can optimize the passage efficiency while ensuring that multiple unmanned vehicles pass without conflict, thereby improving the overall task completion efficiency.

[0129] Embodiment 3

[0130] Figure 8This is a schematic diagram of the structure of an unmanned vehicle dispatching system provided in the third embodiment of the present invention. The system can execute the unmanned vehicle dispatching method provided in any embodiment of the present invention and has the corresponding functional modules and beneficial effects of the execution method. Figure 8 As shown, the system includes:

[0131] The dispatch area information acquisition module 310 is used to obtain the site information and unmanned vehicle information of the target dispatch area; wherein the site information includes the site size, site layout, dispatch starting point location, dispatch end point location, and the location and number of parking spaces in the task area; the unmanned vehicle information includes the size, number and steering characteristics of the unmanned vehicle;

[0132] A buffer and waiting area determination module 320 is used to determine a buffer area and a waiting area corresponding to each task area in the target scheduling area according to the site information and the unmanned vehicle information; wherein the waiting area has the same number of parking spaces as the corresponding task area;

[0133] A driving path planning module 330 is used to determine a first driving path from the scheduling starting point to the task area and a second driving path from the task area to the scheduling end point based on the shortest path principle; wherein the first driving path passes through the buffer area and the waiting area;

[0134] An unmanned vehicle scheduling module 340, configured to schedule a plurality of unmanned vehicles according to the first driving path and the second driving path, and determine a predicted driving trajectory of each of the unmanned vehicles during the scheduling process;

[0135] The conflict area scheduling module 350 is used to control the unmanned vehicle to pass through the target driving conflict area in the target scheduling area according to the predicted driving trajectory; wherein the driving conflict area is an area where unmanned vehicle driving conflicts are likely to occur.

[0136] Optionally, the buffer and waiting area determination module 320 is specifically configured to:

[0137] Determine the target lane mode corresponding to each task area according to the site information; wherein the lane mode includes a single lane mode and a double lane mode, in which the same channel is used from the buffer area to the waiting area and from the waiting area to the task area in the single lane mode, and different channels are used from the buffer area to the waiting area and from the waiting area to the task area in the double lane mode;

[0138] Determine a target area mode corresponding to each of the mission areas according to the unmanned vehicle information; wherein the area mode includes a single area mode and a multi-area mode, the single area mode includes a buffer area and a waiting area, and the multi-area mode includes multiple buffer areas and multiple waiting areas;

[0139] Determine the target parking space mode and the target parking space quantity of the waiting area corresponding to each mission area according to the site information and the unmanned vehicle information; wherein the parking space mode includes a vertical parking space mode and a diagonal parking space mode;

[0140] According to the target lane mode, the target area mode, the target parking space mode and the target number of parking spaces, a buffer area and a waiting area corresponding to each of the task areas are determined.

[0141] Optionally, the multi-region mode includes a serial mode and a parallel mode. In the serial mode, a plurality of buffer regions are arranged in series and have a sequential relationship. In the parallel mode, a plurality of buffer regions are arranged in parallel.

[0142] Accordingly, the unmanned vehicle dispatching module 340 is used to:

[0143] When the target area mode is the serial mode, if there is a vacant space in the initial buffer area, the current unmanned vehicle is controlled to drive from the scheduling starting point to the initial buffer area according to the first driving path, and whether there is a vacant space in the subsequent buffer area is determined during the scheduling process; wherein, if there is no other unmanned vehicle in the initial buffer area, the current unmanned vehicle is controlled to drive to the stop point in the initial buffer area; if there is other unmanned vehicle in the initial buffer area, the current unmanned vehicle is controlled to drive in the direction of the stop point in the initial buffer area;

[0144] If so, the reference unmanned vehicle located at the stop point in the initial buffer area is controlled to travel from the stop point in the initial buffer area to the subsequent buffer area according to the first driving path; wherein, if there are no other unmanned vehicles in the subsequent buffer area, the reference unmanned vehicle is controlled to travel to the stop point in the subsequent buffer area; if there are other unmanned vehicles in the subsequent initial buffer area, the reference unmanned vehicle is controlled to travel in the direction of the stop point in the subsequent buffer area;

[0145] When the target area mode is the parallel mode, it is determined whether there is a vacancy in each target buffer area;

[0146] If so, the current unmanned vehicle is controlled to drive from the scheduling starting point to the target buffer area according to the first driving path; if there are no other unmanned vehicles in the target buffer area, the current unmanned vehicle is controlled to drive to the stop point in the target buffer area; if there are other unmanned vehicles in the target buffer area, the current unmanned vehicle is controlled to drive in the direction of the stop point in the target buffer area.

[0147] Optionally, the unmanned vehicle dispatching module 340 is used to:

[0148] If there is an empty parking space in the buffer area, control the current unmanned vehicle to drive from the dispatch starting point to the buffer area according to the first driving path, and determine whether there is an empty parking space in the waiting area during the dispatch process;

[0149] If so, the current unmanned vehicle is controlled to travel from the buffer area to the idle parking space in the waiting area, and during the scheduling process, it is determined whether there is an idle parking space in the mission area corresponding to the idle parking space in the waiting area;

[0150] If so, the current unmanned vehicle is controlled to travel from the idle parking space in the waiting area to the idle parking space in the corresponding task area.

[0151] Optionally, the target driving conflict area is an intersection area;

[0152] Accordingly, the conflict area scheduling module 350 is used to:

[0153] When the current unmanned vehicle travels to a target distance from the intersection area, determining whether the intersection area is occupied according to the predicted driving trajectory of other unmanned vehicles;

[0154] If it is not occupied and the next target driving area of ​​the current unmanned vehicle is free, control the current unmanned vehicle to drive to the next target driving area through the intersection area;

[0155] Determine whether there is a candidate unmanned vehicle that enters and exits the same lane as the current unmanned vehicle on the lane where the current unmanned vehicle was located before passing through the intersection area;

[0156] If so, and the next candidate driving area of ​​the candidate unmanned vehicle is vacant, the candidate unmanned vehicle is controlled to drive through the intersection area to the next candidate driving area.

[0157] Optionally, the target driving conflict area is a parking area;

[0158] Accordingly, the conflict area scheduling module 350 is used to:

[0159] If the current unmanned vehicle is a vehicle to be parked, and there is a target unmanned vehicle that is parking in or out, the target parking space of the current unmanned vehicle is determined according to the predicted driving trajectory of the target unmanned vehicle and the predicted driving trajectory of the current unmanned vehicle, and the current unmanned vehicle is controlled to drive to the target parking space;

[0160] If the current unmanned vehicle is a vehicle to be parked out, and there is a target unmanned vehicle that is parking in or out, it is determined whether there is a trajectory conflict between the predicted driving trajectory of the target unmanned vehicle and the predicted driving trajectory of the current unmanned vehicle, and the current unmanned vehicle is controlled to park out of the current parking space based on the determination result.

[0161] Optionally, the conflict area scheduling module 350 is further used to:

[0162] If the predicted driving trajectory of the current unmanned vehicle corresponding to the target parking space conflicts with the predicted driving trajectory of the target unmanned vehicle, then after the target unmanned vehicle completes parking in or out, the current unmanned vehicle is controlled to directly drive to the target parking space; or

[0163] The current unmanned vehicle is controlled to arrive at a temporary parking position, and after the target unmanned vehicle completes parking in or out, the current unmanned vehicle is controlled to travel from the temporary parking position to the target parking space.

[0164] An unmanned vehicle dispatching system provided by an embodiment of the present invention can execute an unmanned vehicle dispatching method provided by any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0165] Embodiment 4

[0166] Fig. 9 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0167] like Fig. 9 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0168] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0169] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the unmanned vehicle dispatching method.

[0170] In some embodiments, the unmanned vehicle dispatch method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the unmanned vehicle dispatch method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the unmanned vehicle dispatch method in any other appropriate manner (e.g., by means of firmware).

[0171] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0172] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0173] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0174] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0175] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0176] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0177] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0178] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for dispatching an unmanned vehicle, characterized in that: The method comprises: Acquire site information and unmanned vehicle information of the target dispatch area; wherein the site information includes site size, site layout, dispatch starting point location, dispatch end point location, and location and number of parking spaces in the task area; and the unmanned vehicle information includes size, number, and steering characteristics of the unmanned vehicle; Determine the buffer area and the waiting area corresponding to each task area in the target scheduling area according to the site information and the unmanned vehicle information; wherein the waiting area has the same number of parking spaces as the corresponding task area; Determine a first driving path from the scheduling starting point to the task area and a second driving path from the task area to the scheduling end point based on the shortest path principle; wherein the first driving path passes through the buffer area and the waiting area; Scheduling a plurality of unmanned vehicles according to the first driving path and the second driving path, and determining a predicted driving trajectory of each of the unmanned vehicles during the scheduling process; The unmanned vehicle is controlled to pass through a target driving conflict area in the target scheduling area according to the predicted driving trajectory; wherein the driving conflict area is an area where unmanned vehicle driving conflicts are prone to occur.

2. The method according to claim 1, characterized in that Determining the buffer area and the waiting area corresponding to each task area in the target scheduling area according to the site information and the unmanned vehicle information includes: Determine the target lane mode corresponding to each task area according to the site information; wherein the lane mode includes a single lane mode and a double lane mode, in which the same channel is used from the buffer area to the waiting area and from the waiting area to the task area in the single lane mode, and different channels are used from the buffer area to the waiting area and from the waiting area to the task area in the double lane mode; Determine a target area mode corresponding to each of the mission areas according to the unmanned vehicle information; wherein the area mode includes a single area mode and a multi-area mode, the single area mode includes a buffer area and a waiting area, and the multi-area mode includes multiple buffer areas and multiple waiting areas; Determine the target parking space mode and the target parking space quantity of the waiting area corresponding to each mission area according to the site information and the unmanned vehicle information; wherein the parking space mode includes a vertical parking space mode and a diagonal parking space mode; According to the target lane mode, the target area mode, the target parking space mode and the target number of parking spaces, a buffer area and a waiting area corresponding to each of the task areas are determined.

3. The method according to claim 2, characterized in that The multi-region mode includes a serial mode and a parallel mode. In the serial mode, a plurality of buffer regions are arranged in series and have a sequential relationship. In the parallel mode, a plurality of buffer regions are arranged in parallel. Accordingly, scheduling a plurality of unmanned vehicles according to the first driving path and the second driving path includes: When the target area mode is the serial mode, if there is a vacant space in the initial buffer area, the current unmanned vehicle is controlled to drive from the scheduling starting point to the initial buffer area according to the first driving path, and whether there is a vacant space in the subsequent buffer area is determined during the scheduling process; wherein, if there is no other unmanned vehicle in the initial buffer area, the current unmanned vehicle is controlled to drive to the stop point in the initial buffer area; if there is other unmanned vehicle in the initial buffer area, the current unmanned vehicle is controlled to drive in the direction of the stop point in the initial buffer area; If so, the reference unmanned vehicle located at the stop point in the initial buffer area is controlled to travel from the stop point in the initial buffer area to the subsequent buffer area according to the first driving path; wherein, if there are no other unmanned vehicles in the subsequent buffer area, the reference unmanned vehicle is controlled to travel to the stop point in the subsequent buffer area; if there are other unmanned vehicles in the subsequent initial buffer area, the reference unmanned vehicle is controlled to travel in the direction of the stop point in the subsequent buffer area; When the target area mode is the parallel mode, it is determined whether there is a vacancy in each target buffer area; If so, the current unmanned vehicle is controlled to drive from the scheduling starting point to the target buffer area according to the first driving path; if there are no other unmanned vehicles in the target buffer area, the current unmanned vehicle is controlled to drive to the stop point in the target buffer area; if there are other unmanned vehicles in the target buffer area, the current unmanned vehicle is controlled to drive in the direction of the stop point in the target buffer area.

4. The method according to claim 1, characterized in that: Scheduling a plurality of unmanned vehicles according to the first driving path and the second driving path includes: If there is an empty parking space in the buffer area, control the current unmanned vehicle to drive from the dispatch starting point to the buffer area according to the first driving path, and determine whether there is an empty parking space in the waiting area during the dispatch process; If so, the current unmanned vehicle is controlled to travel from the buffer area to the idle parking space in the waiting area, and during the scheduling process, it is determined whether there is an idle parking space in the mission area corresponding to the idle parking space in the waiting area; If so, the current unmanned vehicle is controlled to travel from the idle parking space in the waiting area to the idle parking space in the corresponding task area.

5. The method according to claim 1, characterized in that The target driving conflict area is an intersection area; Accordingly, controlling the unmanned vehicle to pass through the target driving conflict area in the target scheduling area according to the predicted driving trajectory includes: When the current unmanned vehicle travels to a target distance from the intersection area, determining whether the intersection area is occupied according to the predicted driving trajectory of other unmanned vehicles; If it is not occupied and the next target driving area of ​​the current unmanned vehicle is free, control the current unmanned vehicle to drive to the next target driving area through the intersection area; Determine whether there is a candidate unmanned vehicle that enters and exits the same lane as the current unmanned vehicle on the lane where the current unmanned vehicle was located before passing through the intersection area; If so, and the next candidate driving area of ​​the candidate unmanned vehicle is vacant, the candidate unmanned vehicle is controlled to drive through the intersection area to the next candidate driving area.

6. The method according to claim 1, characterized in that The target driving conflict area is a parking space area; Accordingly, controlling the unmanned vehicle to pass through the target driving conflict area in the target scheduling area according to the predicted driving trajectory includes: If the current unmanned vehicle is a vehicle to be parked, and there is a target unmanned vehicle that is parking in or out, the target parking space of the current unmanned vehicle is determined according to the predicted driving trajectory of the target unmanned vehicle and the predicted driving trajectory of the current unmanned vehicle, and the current unmanned vehicle is controlled to drive to the target parking space; If the current unmanned vehicle is a vehicle to be parked out, and there is a target unmanned vehicle that is parking in or out, it is determined whether there is a trajectory conflict between the predicted driving trajectory of the target unmanned vehicle and the predicted driving trajectory of the current unmanned vehicle, and the current unmanned vehicle is controlled to park out of the current parking space based on the determination result.

7. The method according to claim 6, characterized in that Controlling the current unmanned vehicle to drive to the target parking space includes: If the predicted driving trajectory of the current unmanned vehicle corresponding to the target parking space conflicts with the predicted driving trajectory of the target unmanned vehicle, then after the target unmanned vehicle completes parking in or out, the current unmanned vehicle is controlled to directly drive to the target parking space; or The current unmanned vehicle is controlled to arrive at a temporary parking position, and after the target unmanned vehicle completes parking in or out, the current unmanned vehicle is controlled to travel from the temporary parking position to the target parking space.

8. An unmanned vehicle dispatching system, characterized in that: The system comprises: The dispatch area information acquisition module is used to obtain the site information and unmanned vehicle information of the target dispatch area; wherein the site information includes the site size, site layout, dispatch starting point location, dispatch end point location, and the location and number of parking spaces in the task area; the unmanned vehicle information includes the size, number and steering characteristics of the unmanned vehicle; A buffer and standby area determination module, used to determine the buffer area and standby area corresponding to each task area in the target scheduling area according to the site information and the unmanned vehicle information; wherein the number of parking spaces in the standby area is the same as that in the corresponding task area; A driving path planning module, used to determine a first driving path from the scheduling starting point to the task area and a second driving path from the task area to the scheduling end point based on the shortest path principle; wherein the first driving path passes through the buffer area and the waiting area; an unmanned vehicle scheduling module, configured to schedule a plurality of unmanned vehicles according to the first driving path and the second driving path, and determine a predicted driving trajectory of each of the unmanned vehicles during the scheduling process; The conflict area scheduling module is used to control the unmanned vehicle to pass through the target driving conflict area in the target scheduling area according to the predicted driving trajectory; wherein the driving conflict area is an area where unmanned vehicle driving conflicts are prone to occur.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the unmanned vehicle scheduling method described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the unmanned vehicle scheduling method according to any one of claims 1 to 7 when executed.

Images