Unmanned vehicle dispatching method, device and system

Abstract

The present invention discloses a method, device and system for dispatching unmanned vehicles. The method comprises: determining the stations within the safety distance of the target unmanned vehicle in real time based on the station where the target unmanned vehicle is currently located; constructing a safety action space model corresponding to each station for each station within the safety distance; and controlling the target unmanned vehicle to stop if the current coordinates of other unmanned vehicles are within the safety action space model. During the driving process of the unmanned vehicle, the present invention constructs a safety action space model that changes in real time with the movement of the unmanned vehicle based on the station where the unmanned vehicle is currently located and the preset safety distance. Based on the safety action space model, the unmanned vehicle can be controlled to stop in time, so that the unmanned vehicle maintains a safe distance when following a vehicle, prevents vehicles in the same direction from rear-ending, and can improve the road planning utilization rate of narrow spaces.

Description

Technical Field

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

[0002] Laser unmanned vehicles in factories are gradually becoming popular. Compared with magnetic navigation or QR code navigation unmanned vehicles, laser SLAM (Simultaneous Localization and Mapping) unmanned vehicles have the advantages of flexible routes, rich data information processing, and easy maintenance.

[0003] Automated Guided Vehicles (AGVs) can be used in factories or workshops to achieve intelligent transportation. AGVs can achieve navigation based on SLAM algorithms. When companies implement AGV scheduling solutions that use laser SLAM unmanned vehicles in conjunction with unmanned vehicles, they will encounter motion interference during vehicle driving in application scenarios with small spaces and complex routes. This will make it impossible to accurately maintain a safe distance between vehicles, which may lead to vehicle collisions and cause safety issues. Summary of the Invention

[0004] Embodiments of the present invention provide an unmanned vehicle dispatching method, device, and system to at least solve the problems of motion interference and collision that occur when multiple unmanned vehicles are traveling in the prior art.

[0005] To solve the above technical problems, an embodiment of the present invention provides an unmanned vehicle scheduling method, comprising:

[0006] Determine in real time the stations within a safe distance of the target unmanned vehicle based on the station the target unmanned vehicle is currently at;

[0007] For each station within the safety distance, a safety action space model corresponding to each station is constructed;

[0008] If the current coordinates of other unmanned vehicles are within the safe action space model, the target unmanned vehicle is controlled to stop.

[0009] Optionally, determining the stations within the safe distance of the target unmanned vehicle in real time based on the current station of the target unmanned vehicle includes:

[0010] Determine in real time the current location of the target unmanned vehicle;

[0011] Based on the coordinates of the current site, the coordinates of the site behind the current site in the set path of the target unmanned vehicle in the forward direction, and the preset safety distance between unmanned vehicles, the sites included in the safety distance of the target unmanned vehicle are determined.

[0012] Optionally, determining the current location of the target unmanned vehicle in real time includes:

[0013] Obtaining the current coordinates of the target unmanned vehicle in real time;

[0014] Calculating the distance between the current coordinates and the coordinates of each station in the set path of the target unmanned vehicle;

[0015] The station corresponding to the minimum distance is selected as the current station of the target unmanned vehicle.

[0016] Optionally, determining the stations within the safety distance of the target unmanned vehicle based on the coordinates of the current station, the coordinates of a station in the set path of the target unmanned vehicle that is behind the current station in the forward direction, and a preset safety distance between unmanned vehicles includes:

[0017] Starting from the current site, the L value is calculated by accumulating the square of the distance to each site:

[0018] When we find a solution that satisfies L≥La 2 When the minimum L value is reached, the accumulation is stopped, and the site used to calculate the minimum L value is used as the site included in the safety distance of the target unmanned vehicle;

[0019] Wherein, La represents the preset safety distance between unmanned vehicles; LMk represents the current location of the target unmanned vehicle, (X LMk , Y LMk ) represents the coordinates of the current location of the target unmanned vehicle; (X LMk+s , Y LMk+s ) represents the coordinates of the sth station after the current station in the set path of the target unmanned vehicle according to the forward direction; the value of u determines the number of stations used to calculate the L value. For each accumulated station, the value of u is increased by one. u is a positive integer, 1≤u≤ik, and i represents the total number of stations included in the set path of the target unmanned vehicle.

[0020] Optionally, for each station within the safety distance, a safety action space model corresponding to each station is constructed, including:

[0021] For each station included in the safety distance, determining a model parameter according to the vehicle action mark of the station;

[0022] A safety action space model corresponding to the site is constructed according to the model parameters.

[0023] Optionally, for each station included in the safety distance, determining model parameters according to the vehicle action mark of the station includes:

[0024] If the vehicle action mark of the station is straight, the model parameters are determined as follows: a rectangle centered on the station coordinates, wherein the side length of the rectangle in the x-axis direction is twice the sum of the x-axis laser obstacle avoidance distance and the x-axis straight-ahead safe action distance, and the side length of the rectangle in the y-axis direction is twice the sum of the y-axis laser obstacle avoidance distance and the y-axis straight-ahead safe action distance;

[0025] If the vehicle action mark of the site is rotation, the model parameters are determined as: a rectangle centered on the site coordinates, and the side lengths of the rectangle in the x-axis and y-axis directions are both twice the radius of the vehicle rotation action.

[0026] Optionally, before determining the stations within the safe distance of the target unmanned vehicle in real time based on the current station of the target unmanned vehicle, the method further includes:

[0027] Determining a set path for the target unmanned vehicle based on the starting point and the end point of the target unmanned vehicle;

[0028] Determine the sites included in the set path based on the sites planned on the map;

[0029] Vehicle action marking is performed on each station included in the set route.

[0030] Optionally, marking the vehicle action for each station included in the set route includes:

[0031] Marking the vehicle actions at the starting point and the end point in the set path as straight ahead;

[0032] Obtaining the coordinates of each site in the set path;

[0033] For each station in the set path except the starting point and the end point, determining whether the coordinates of the station are on a line connecting the previous station and the next station in the set path;

[0034] If it is on the connecting line, the vehicle action marked at the station is to go straight;

[0035] If it is not on the connecting line, the vehicle action of the station is marked as rotation.

[0036] Optionally, after constructing the safety action space model corresponding to each station within the safety distance, the method further includes:

[0037] Eliminate the sites included in the set path of the target unmanned vehicle from all sites planned on the map to obtain a first site set;

[0038] Determining sites in the first site set that are within the safe action space model to obtain a second site set;

[0039] If the current coordinates of other unmanned vehicles are within the safe action space model, and the current site of the other unmanned vehicles belongs to the second site set, the target unmanned vehicle is controlled to continue driving.

[0040] Optionally, also include:

[0041] Determine at least one pair of conflicting sites among all sites planned on the map, and store the determined at least one pair of conflicting sites, wherein each pair of conflicting sites satisfies at least one of the following conditions: a distance between the two sites is less than a preset x-axis straight-ahead safe action distance, a distance between the two sites is less than a preset y-axis straight-ahead safe action distance, and a distance between the two sites is less than a preset vehicle rotation action radius;

[0042] If the next station of the target unmanned vehicle is a conflicting station, determine whether there is another unmanned vehicle at another station in the conflicting station or heading towards another station in the conflicting station;

[0043] If so, controlling the target unmanned vehicle to stop;

[0044] If not, the target unmanned vehicle is controlled to continue driving.

[0045] An embodiment of the present invention further provides an unmanned vehicle dispatching device, comprising:

[0046] A determination module is used to determine, in real time, the stations within the safe distance of the target unmanned vehicle based on the station where the target unmanned vehicle is currently located;

[0047] A construction module is used to construct a safety action space model corresponding to each station included in the safety distance;

[0048] The control module is configured to control the target unmanned vehicle to stop if the current coordinates of other unmanned vehicles are within the safe action space model.

[0049] An embodiment of the present invention further provides an unmanned vehicle dispatching system, comprising: the unmanned vehicle dispatching device described in the embodiment of the present invention and at least one unmanned vehicle.

[0050] An embodiment of the present invention further provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in the embodiment of the present invention when executing the computer program.

[0051] An embodiment of the present invention further provides a non-volatile computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method described in the embodiment of the present invention are implemented.

[0052] By applying the technical solution of the present invention, the stations within the safety distance of the target unmanned vehicle are determined in real time based on the station where the target unmanned vehicle is currently located; for each station within the safety distance, a safety action space model corresponding to each station is constructed; if the current coordinates of other unmanned vehicles are within the above-mentioned safety action space model, the target unmanned vehicle is controlled to stop. During the driving process of the unmanned vehicle, based on the station where the unmanned vehicle is currently located and the preset safety distance, a safety action space model that changes in real time with the movement of the unmanned vehicle is constructed. Based on this safety action space model, the unmanned vehicle can be controlled to stop in time, so that the unmanned vehicle maintains a safe distance when following the vehicle, avoids collisions, and prevents vehicles in the same direction from rear-ending. This solves the problem of motion interference and collision when multiple unmanned vehicles are driving. In addition, the optimized scheduling method of this embodiment can improve the utilization rate of road planning for narrow spaces, overcome the difficulties of path planning in narrow spaces, and improve site utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 This is a flow chart of the unmanned vehicle dispatching method provided in Example 1 of the present invention;

[0054] Figure 2 is a schematic diagram of an unmanned vehicle dispatching system provided by Embodiment 2 of the present invention;

[0055] Figure 3 is a schematic diagram of vehicle parameters provided by the second embodiment of the present invention;

[0056] Figure 4 This is a specific flow chart of the unmanned vehicle dispatching method provided in the second embodiment of the present invention;

[0057] Figure 5 is a schematic diagram of a cross-shaped virtual area model provided in the second embodiment of the present invention;

[0058] Figure 6 This is a specific flow chart of the unmanned vehicle dispatching method applicable to intersections provided by the second embodiment of the present invention;

[0059] Figure 7 This is a structural block diagram of the unmanned vehicle dispatching device provided in Example 3 of the present invention. DETAILED DESCRIPTION

[0060] To make the objectives, technical solutions, and advantages of the present invention more apparent, the present invention will be further described in detail below with reference to the accompanying drawings. It is apparent that the embodiments described are only some, not all, of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without creative effort are intended to fall within the scope of protection of the present invention.

[0061] It should be noted that the terms "first", "second", etc. in the description, claims, and drawings of the present invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way are interchangeable 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 apparatus that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or that are inherent to these processes, methods, products, or apparatus.

[0062] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0063] Example 1

[0064] This embodiment provides a method for dispatching an unmanned vehicle, which performs dispatch control on at least one unmanned vehicle, particularly in scenarios with confined spaces and complex routes. The unmanned vehicle may be a SLAM laser unmanned guided vehicle.

[0065] Figure 1 This is a flow chart of the unmanned vehicle dispatching method provided in the first embodiment of the present invention. Figure 1 As shown, the method includes the following steps:

[0066] S101, determining the stations within the safe distance of the target unmanned vehicle in real time based on the current station of the target unmanned vehicle.

[0067] S102: For each station included in the safety distance, a safety action space model corresponding to each station is constructed.

[0068] S103: If the current coordinates of other unmanned vehicles are within the above-mentioned safe action space model, the target unmanned vehicle is controlled to stop.

[0069] The target unmanned vehicle is any one of the at least one dispatched unmanned vehicle. The at least one unmanned vehicle is traveling within a location, and a map of the location has been mapped with numerous stations, each with corresponding coordinates. The safety distance refers to the preset safe distance between two unmanned vehicles. The safe action space model defines the safe action area for the target unmanned vehicle, and the safe action space model changes in real time as the target unmanned vehicle moves.

[0070] This embodiment determines the stations within the safety distance of the target unmanned vehicle in real time based on the station where the target unmanned vehicle is currently located; for each station within the safety distance, a safety action space model corresponding to each station is constructed; if the current coordinates of other unmanned vehicles are within the above-mentioned safety action space model, the target unmanned vehicle is controlled to stop. During the driving process of the unmanned vehicle, based on the current station where the unmanned vehicle is located and the preset safety distance, a safety action space model that changes in real time with the movement of the unmanned vehicle is constructed. Based on this safety action space model, the unmanned vehicle can be controlled to stop in time, so that the unmanned vehicle maintains a safe distance when following the vehicle, avoids collisions, and prevents vehicles traveling in the same direction from rear-ending. This solves the problem of motion interference and collision when multiple unmanned vehicles are driving. In addition, the optimized scheduling method of this embodiment is targeted at narrow spaces, which can improve the utilization rate of road planning, overcome the difficulties of path planning in narrow spaces, and improve site utilization.

[0071] In an optional embodiment, step S101 determines the stations within the safety distance of the target unmanned vehicle in real time based on the current station of the target unmanned vehicle, including: determining the current station of the target unmanned vehicle in real time; determining the stations within the safety distance of the target unmanned vehicle based on the coordinates of the current station, the coordinates of the station after the current station in the set path of the target unmanned vehicle according to the forward direction, and the preset safety distance between unmanned vehicles.

[0072] Among them, each unmanned vehicle has its own set path, which refers to the path taken by the unmanned vehicle from the starting point to the end point, and the set path includes at least two stations.

[0073] Based on the planned sites and preset safety distances, this implementation can quickly and effectively determine the sites within the safety distance of the target unmanned vehicle, providing a guarantee for the subsequent accurate construction of a safe action space model.

[0074] Furthermore, determining the current location of the target unmanned vehicle in real time includes: obtaining the current coordinates of the target unmanned vehicle in real time; calculating the distance between the current coordinates and the coordinates of each station in the target unmanned vehicle's set path; and selecting the station corresponding to the minimum distance as the current location of the target unmanned vehicle. This embodiment uses the station closest to the current location of the target unmanned vehicle as the current location of the target unmanned vehicle, and the determination method is accurate and reliable.

[0075] Specifically, based on the coordinates of the current station, the coordinates of the station that follows the current station in the set path of the target unmanned vehicle in the forward direction, and the preset safety distance between unmanned vehicles, the stations included in the safety distance of the target unmanned vehicle are determined, including:

[0076] Starting from the current station, the L value is calculated by accumulating the square of the distance to each station:

[0077] When we find a solution that satisfies L≥La 2 When the minimum L value is reached, the accumulation is stopped, and the station used to calculate the minimum L value is used as the station included in the safe distance of the target unmanned vehicle;

[0078] Among them, La represents the preset safety distance between unmanned vehicles; LMk represents the current location of the target unmanned vehicle, (X LMk , Y LMk ) represents the coordinates of the current station where the target unmanned vehicle is located; LMk+s represents the sth station after the current station in the set path of the target unmanned vehicle according to the forward direction, (X LMk+s , Y LMk+s ) represents the coordinates of the sth station after the current station in the set path of the target unmanned vehicle according to the forward direction; the value of u determines the number of stations used to calculate the L value, and the value of u increases successively with accumulation, that is, for each accumulated station, the value of u increases by one, u is a positive integer, 1≤u≤ik, and i represents the total number of stations included in the set path of the target unmanned vehicle.

[0079] For example, when we find a solution that satisfies L≥La 2 When the minimum L value is calculated, the accumulated stations for calculating the minimum L value are LMk, LMk+1, ..., LMk+b, and the set of stations included in the target unmanned vehicle safety distance La is (LMk, LMk+1, ..., LMk+b). This can quickly and accurately determine the stations included in the target unmanned vehicle safety distance. If all stations after station LMk in the set path have participated in the calculation of L value, but L value is still less than La 2 , then all the stations after station LMk in the set path are directly regarded as the stations included in the safe distance of the target unmanned vehicle.

[0080] In an optional embodiment, step S102 constructs a safe action space model corresponding to each station included in the safe distance, including: determining model parameters for each station included in the safe distance based on the vehicle action mark of the station; and constructing a safe action space model corresponding to the station based on the model parameters.

[0081] The vehicle action marker refers to the direction of the unmanned vehicle at a station, including straight ahead and rotation. After the unmanned vehicle's set path is determined, the vehicle's actions at each station along its set path can be marked. Model parameters are used to construct the safe action space model. Model parameters include the shape of the area included in the model, the center point of the area, and the side length of the area.

[0082] This embodiment constructs a safe action space model corresponding to the vehicle action mark of the unmanned vehicle at the site, so that the safe action space model matches the driving conditions of the unmanned vehicle, and can better control the driving of the unmanned vehicle and avoid collisions.

[0083] Furthermore, for each station included in the safety distance, the model parameters are determined according to the vehicle action mark of the station, including:

[0084] (1) If the vehicle action mark of the station is straight, the model parameters are determined as follows: a rectangle centered on the coordinates of the station, and the side length of the rectangle in the x-axis direction is: twice the sum of the x-axis laser obstacle avoidance distance and the x-axis straight-ahead safety action distance, and the side length of the rectangle in the y-axis direction is: twice the sum of the y-axis laser obstacle avoidance distance and the y-axis straight-ahead safety action distance.

[0085] The x-axis laser obstacle avoidance distance, y-axis laser obstacle avoidance distance, x-axis straight-ahead safe motion distance, and y-axis straight-ahead safe motion distance are all pre-set parameters based on actual conditions (such as site size, autonomous vehicle size, and autonomous vehicle driving conditions). The laser obstacle avoidance distance is calculated from the center point of the autonomous vehicle, while the straight-ahead safe motion distance is calculated from the edge of the laser obstacle avoidance range.

[0086] Taking the station LMk+1 as an example, the vehicle action of the unmanned vehicle at this station is marked as going straight. The safe action space model constructed according to the model parameters is: (X LMk+1 , Y LMk+1 ) is the center point, and the coordinates of the four vertices are (X LMk+1 –Lx1–Lx, Y LMk+1 –Ly1–Ly), (X LMk+1 –Lx1–Lx, Y LMk+1 +Ly1+Ly), (X LMk+1 +Lx1+Lx,Y LMk+1 +Ly1+Ly), (X LMk+1 +Lx1+Lx,Y LMk+1 Here, Lx1 represents the safe straight-line action distance on the x-axis, Ly1 represents the safe straight-line action distance on the y-axis, Lx represents the laser obstacle avoidance distance on the x-axis, and Ly represents the laser obstacle avoidance distance on the y-axis.

[0087] (2) If the vehicle action at the station is marked as rotation, the model parameters are determined as follows: a rectangle centered on the station coordinates, and the side lengths of the rectangle in the x-axis and y-axis directions are both twice the radius of the vehicle rotation action.

[0088] The vehicle rotation radius is a pre-set parameter value based on actual conditions (such as the size of the venue, the size of the unmanned vehicle, the driving conditions of the unmanned vehicle, etc.). The vehicle rotation radius is measured from the center point of the unmanned vehicle.

[0089] Taking the station LMk+1 as an example, the vehicle action of the unmanned vehicle at this station is marked as rotation. The safe action space model constructed according to the model parameters is: (X LMk+1 , Y LMk+1 ) is the center point, and the coordinates of the four vertices are (X LMk+1 –LR,Y LMk+1 –LR), (X LMk+1 –LR,Y LMk+1 +LR), (X LMk+1 +LR,Y LMk+1 +LR), (X LMk+1 +LR,Y LMk+1 –LR) where LR represents the radius of the vehicle’s rotation.

[0090] This embodiment determines the corresponding model parameters for different vehicle action markers to construct the corresponding safe action space model. Through all the safe action space models corresponding to all stations included in the safe distance, the safe driving area of the target unmanned vehicle can be determined. If there are other unmanned vehicles in the safe driving area, the target unmanned vehicle is controlled to stop in time to maintain a safe distance and avoid collision.

[0091] In an optional embodiment, before determining the stations within the target unmanned vehicle's safe distance in real time based on the target unmanned vehicle's current station in step S101, the method further includes: determining the target unmanned vehicle's set path based on the target unmanned vehicle's starting and ending points; determining the stations included in the set path based on the stations planned on the map; and marking the vehicle's actions for each station included in the set path. This embodiment determines the unmanned vehicle's set path and the stations included in the set path before the unmanned vehicle begins navigation, and marks the vehicle's actions for each station included in the set path, facilitating the subsequent construction of a corresponding safe action space model based on the vehicle's action markings.

[0092] Specifically, the vehicle action is marked for each station included in the set path, including: marking the vehicle action at the starting point and the end point in the set path as straight ahead; obtaining the coordinates of each station in the set path; for each station in the set path except the starting point and the end point, determining whether the coordinates of the station are on the line connecting the previous station and the next station in the set path; if on the line, it means that the direction of the vehicle head has not changed, and the vehicle action at the station is marked as straight ahead; if not on the line, it means that the direction of the vehicle head has changed, and the vehicle action at the station is marked as rotation. For simplicity, symbols can be used to represent vehicle action marks, for example, 0 represents straight ahead and 1 represents rotation. This embodiment can quickly and accurately mark vehicle actions based on station coordinates.

[0093] When vehicles are traveling towards each other on different paths, if the distance between the vehicles and the roads is narrow, the safe action space models of the vehicles will include the coordinates of each other's vehicles, causing both vehicles to stop and not move. To solve this problem, after constructing the safe action space model corresponding to each site within the safe distance in step S102, the above method can also include: removing the sites included in the set path of the target unmanned vehicle from all sites planned on the map to obtain a first site set; determining the sites in the first site set that are within the safe action space model to obtain a second site set; if the current coordinates of other unmanned vehicles are within the safe action space model, and the current site of the other unmanned vehicles belongs to the second site set, indicating that the paths of the two unmanned vehicles are different and do not conflict, such as traveling towards each other on different paths or traveling in the same direction on different paths, then the target unmanned vehicle is controlled to continue traveling. This can avoid the situation described above where the two vehicles have different paths but both stop and do not move.

[0094] Considering that the distances between individual stations are relatively close, that is, the distance between two stations is less than the vehicle safe action distance (for example, Lx1, Ly1, or LR), when multiple vehicles are running, the above-mentioned stations with relatively close distances may not belong to the conflict points determined according to the model, which will cause vehicle movement interference. This embodiment solves this problem by artificially constructing a conflict relationship. Specifically, the above method may further include: determining at least one pair of conflicting sites among all sites planned on the map, and storing the determined at least one pair of conflicting sites, wherein each pair of conflicting sites satisfies at least one of the following conditions: the distance between the two sites is less than a preset x-axis straight-line safe action distance (Lx1), the distance between the two sites is less than a preset y-axis straight-line safe action distance (Ly1), and the distance between the two sites is less than a preset vehicle rotation action radius (LR); if the next site of the target unmanned vehicle is a conflicting site, then determining whether there are other unmanned vehicles at another site in the conflicting site or heading towards another site in the conflicting site; if so, then controlling the target unmanned vehicle to stop; if not, indicating that there are neither other unmanned vehicles at another site in the conflicting site nor other unmanned vehicles heading towards another site in the conflicting site, then controlling the target unmanned vehicle to continue driving. In this embodiment, for the case where the distance between individual sites is close, by artificially setting conflict points, it is possible to predict whether the next action of the unmanned vehicle will interfere. If so, the unmanned vehicle is controlled to stop and wait in advance to avoid a collision.

[0095] Unmanned vehicles often travel at intersections, where multiple vehicles are prone to collision. To address this issue, this embodiment provides a method for dispatching unmanned vehicles at intersections, including: determining an intersection based on the set paths of at least two unmanned vehicles; constructing a virtual area model centered around the coordinates of the intersection; and, if the next intersection of an unmanned vehicle is within the virtual area model and the current coordinates of another unmanned vehicle are within the virtual area model, causing the unmanned vehicle about to enter the virtual area model to stop.

[0096] The intersection can be a T-junction, a Y-junction, a crossroads, or other intersections. Of course, there can be more forks. The virtual area model defines the conflict area at the intersection. The virtual area model has a similar shape to the intersection, for example, a T-shaped, Y-shaped, cross-shaped, etc.

[0097] This embodiment is based on the path set by the unmanned vehicle and can determine the location of the intersection, and construct a virtual area model for the intersection. During the driving process of the unmanned vehicle, based on the virtual area model, the unmanned vehicle can be controlled to stop in time to prevent motion interference when passing through the intersection, so that the unmanned vehicles can pass through the intersection in an orderly manner to avoid collisions, and solve the problem that multiple unmanned vehicles are prone to collision when driving at the intersection. In addition, the optimized scheduling method of this embodiment is targeted at narrow spaces, which can improve the utilization rate of road planning, overcome the difficulties of path planning in narrow spaces, and improve the utilization rate of the site.

[0098] In one embodiment, determining an intersection site based on the set paths of at least two unmanned vehicles includes: obtaining the set paths of each unmanned vehicle; determining the sites included in each set path based on the sites planned on a map; and determining that a site is an intersection site if a site is included in at least two set paths and the previous site of the site in the at least two set paths is different. All intersection sites constitute an intersection site set. This embodiment can accurately and reliably determine intersection sites.

[0099] In one embodiment, a virtual area model is constructed with the coordinates of the intersection as the center, including: for each intersection, determining the intersection type corresponding to the intersection and determining the preset model parameters corresponding to the intersection type; with the coordinates of the intersection as the center, constructing the virtual area model according to the above preset model parameters.

[0100] The intersection type corresponding to an intersection can be determined based on the intersection's coordinates and a map. For example, the intersection's coordinates can be mapped to a map to determine the intersection type. Intersection types include T-junctions, Y-junctions, and crossroads. Preset model parameters are set for each intersection type, and these parameters are used to determine the boundaries of the intersection's virtual area model. This embodiment enables efficient and rapid construction of a virtual area model for an intersection.

[0101] Taking into account that sometimes multiple unmanned vehicles are in the virtual area model, causing all unmanned vehicles within the model to be inactive, in order to solve this problem, after constructing the virtual area model with the coordinates of the intersection site as the center, it also includes: when an unmanned vehicle enters the virtual area model, the entry time is recorded; if there are at least two unmanned vehicles in the virtual area model at the same time, at least two unmanned vehicles are controlled to drive according to the first-in-first-out principle based on their respective entry times. Specifically, the unmanned vehicles in the virtual area model can be sorted according to the entry time, and each unmanned vehicle can be controlled to exit the intersection in order from early to late entry time, that is, the unmanned vehicle with the earlier entry time has priority to exit. This avoids the problem of multiple unmanned vehicles inactive in the virtual area model.

[0102] Example 2

[0103] This embodiment illustrates the above-mentioned unmanned vehicle dispatching method with reference to a specific example. However, it should be noted that this specific embodiment is only for the purpose of better illustrating the present application and does not constitute an undue limitation on the present application. Explanations of terms that are the same or corresponding to those in the above-mentioned embodiment will not be repeated in this embodiment.

[0104] like Figure 2 As shown, the unmanned vehicle dispatching system includes: at least one SLAM laser unmanned guided vehicle 10 (referred to as SLAM vehicle) and a dispatching management system 20 (equivalent to the unmanned vehicle dispatching device described in the embodiments of this application). This unmanned vehicle dispatching system can be applied to factory workshops. The SLAM laser unmanned guided vehicle 10 is the execution unit, and the upper layer uses the dispatching management system 20 as the core platform to mobilize the SLAM laser unmanned guided vehicles 10 to perform transportation tasks.

[0105] The SLAM laser automated guided vehicle (AGV) 10 is a standalone system consisting of a core controller, laser rangefinder, motor, and mechanical chassis. The SLAM vehicle is responsible for material handling. The dispatch management system 20 communicates with the SLAM laser AGV 10 via the TCP / IP protocol (i.e., a TCP / IP local area network 30). The dispatch management system 20 is responsible for intervening in multiple SLAM laser AGVs, issuing commands to obtain the vehicle's location coordinates and stations in real time, making decisions, and issuing commands to direct the transport. When multiple vehicles are dispatched, traffic control is required to prevent collisions.

[0106] 1. Same-direction control method

[0107] The same-direction control method is used to solve the problem of vehicle rear-end collisions, so that the vehicle can stay within the set safety range. The same-direction control method includes the following steps:

[0108] (1) Set the following parameters: vehicle x-axis laser obstacle avoidance distance Lx, vehicle y-axis laser obstacle avoidance distance Ly, vehicle front and rear safety distance La (i.e., the safety distance between two unmanned vehicles), vehicle rotation radius LR, vehicle x-axis straight-line safety action distance Lx1, vehicle y-axis straight-line safety action distance Ly1, all in meters. For example, Lx = 0.8m, Ly = 0.4m, La = 2m, Lx1 = 0.1m, Ly1 = 0.1m, Vehicle parameters such as Figure 3 As shown in FIG, the virtual straight action range is the area range determined by the safe action space model.

[0109] (2) Before navigating, the vehicle performs path planning, takes the optimal path as the vehicle's set path, and obtains a set of path sites (LM1, LM2, LM3, ..., LMi), where LM1 represents the starting point and LMi represents the end point, with a total of i sites.

[0110] (3) Determine the direction of the vehicle at each station in the path station set and mark the action. If the vehicle goes straight at the station, it is marked as 0; if the vehicle rotates at the station, it is marked as 1.

[0111] Specifically, by using the site name, the two-dimensional coordinates (X LM1 , Y LM1 ), (X LM2 , Y LM2 ),…,(X LMi , Y LMi ). The starting point LM1 and the end point LMi are both marked as straight (0). Starting from the second station, the functional relationship is obtained by connecting the previous station and the next station. If the coordinates of the station do not satisfy the functional relationship, it is marked as rotation (1). If the coordinates of the station satisfy the functional relationship, it is marked as straight (0). For example, if you want to determine the vehicle action mark of station LM2, if LM2 is on the line connecting LM1 and LM3, it means that the direction of the vehicle head has not changed, and LM2 is marked as straight. If LM2 is not on the line connecting LM1 and LM3, it means that the direction of the vehicle head has changed, and LM2 is marked as rotation.

[0112] (4) The dispatch management system 20 sends a real-time instruction to the vehicle to obtain the current two-dimensional coordinates (X, Y) of the vehicle, and calculates the square of the distance between the current coordinates of the vehicle and each station in the path station set by the formula: L LMp 2 =(XX LMp ) 2 +(YY LMp ) 2 , 1≤p≤i, get the distance square set (L) of each site in the current coordinate distance path site set (LM1, LM2, LM3, ..., LMi) LM1 2 , L LM2 2 ,…,L LMp 2 ,…,L LMi 2 ), sort the distance square set (such as bubble sort), and find the minimum distance square value L LMk 2 , 1≤k≤i, the station corresponding to this value is the station where the vehicle is currently located. For example, if L LM2 2If the square of the minimum distance is reached, the vehicle is determined to be at station LM2. This step is a real-time calculation that continuously updates the vehicle's current station information.

[0113] (5) Obtain the current station LMk of the vehicle through step (4), and its coordinates are (X LMk , Y LMk ).

[0114] Starting from the current site LMk, the distance squared is accumulated to calculate the L value: L = (X LMk+1 –X LMk ) 2 +(Y LMk+1 –Y LMk ) 2 +(X LMk+2 –X LMk+1 ) 2 +(Y LMk+2 –Y LMk+1 ) 2 +…, the stations used to calculate L are the stations in the vehicle's set path, specifically the current station LMk and the stations after it. Find the station that satisfies L≥La 2 The minimum L value is calculated, and the site used to calculate the minimum L value is used as the site included in the vehicle safety distance.

[0115] For example, when L≥La 2 When L is minimum, the accumulation stops. At this time, the sites accumulated by L include LMk, LMk+1, ..., LMk+b, that is, the set of sites within the vehicle safety distance is (LMk, LMk+1, ..., LMk+b).

[0116] (6) Obtain the two-dimensional coordinates of the site set (LMk, LMk+1, ..., LMk+b): (X LMk , Y LMk ), (X LMk+1 , Y LMk+1 ),…,(X LMk+b , Y LMk+b ). Combined with step (1) and step (3), according to the coordinates of each site in the site set (LMk, LMk+1, ..., LMk+b) and the vehicle action mark, a vehicle safety action space model corresponding to each site is established.

[0117] For example, when the station LMk+1 is the straight mark 0, the establishment of (X LMk+1 , Y LMk+1 ) is the center point, and the coordinates of the four vertices are (X LMk+1 –Lx1–Lx, Y LMk+1 –Ly1–Ly), (X LMk+1 –Lx1–Lx, YLMk+1 +Ly1+Ly), (X LMk+1 +Lx1+Lx,Y LMk+1 +Ly1+Ly), (X LMk+1 +Lx1+Lx,Y LMk+1 When the site LMk+1 is the rotation mark 1, the rectangular model with (X LMk+1 , Y LMk+1 ) is the center point, and the coordinates of the four vertices are (X LMk+1 –LR,Y LMk+1 –LR), (X LMk+1 –LR,Y LMk+1 +LR), (X LMk+1 +LR,Y LMk+1 +LR), (X LMk+1 +LR,Y LMk+1 Thus, we can obtain the corresponding safety action space model for each site in the site set (LMk, LMk+1, ..., LMk+b).

[0118] (7) Based on the safe action space model obtained in step (6), the following judgment is made in real time: when there are other vehicles in the safe action space model of the vehicle, the vehicle stops. For example, the vertex coordinates of the safe action space model of the vehicle are: (X1, Y1), (X1, Y2), (X2, Y2) and (X2, Y1). If the current coordinates of the other vehicles (X0, Y0) satisfy X1≤X0≤X2 and Y1≤Y0≤Y2, the vehicle stops; otherwise, the vehicle drives normally. It should be noted that all safe action space models corresponding to all sites in the site set (LMk, LMk+1, ..., LMk+b) are judged.

[0119] Using the same-direction control method described above, when vehicles are traveling toward each other on different paths, if the distance between the vehicles and the road is narrow, the vehicle safety action space model will include the coordinates of each other's vehicles, causing both vehicles to stop and not move. This anomaly can be resolved by following the steps below.

[0120] 1) Determine the vehicle's path site set (LM1, LM2, LM3, ..., LMi). Remove the path site set (LM1, LM2, LM3, ..., LMi) from all sites on the map to obtain site set A, and obtain the site coordinate set B corresponding to site set A.

[0121] 2) All sites corresponding to the coordinates in coordinate set B that are within the vehicle safety action space model constitute site set C. Specifically, the vertex coordinates of the vehicle safety action space model are: (X1, Y1), (X1, Y2), (X2, Y2), and (X2, Y1). When the site coordinates (X', Y') in coordinate set B satisfy X1≤X'≤X2 and Y1≤Y'≤Y2, the site corresponding to (X', Y') is added to site set C.

[0122] 3) Perform the following real-time judgment: Determine whether the current coordinates of other vehicles are within the safe action space model of the vehicle. If so, continue to determine whether the current station of the other vehicle belongs to the station set C. If so, it means that the two unmanned vehicles have different paths and do not conflict. For example, if they are traveling in opposite directions on different paths or traveling in the same direction on different paths, the vehicle will not stop and will be controlled to continue driving. This step is an optimization of the above step (7), adding the judgment about the station set C.

[0123] like Figure 4 As shown in FIG, a specific flow chart of the unmanned vehicle scheduling method includes the following steps:

[0124] S401, load parameters Lx, Ly, Lx1, Ly1, La and LR.

[0125] S402: Acquire a set route of the vehicle and the stations included in the set route.

[0126] S403: Determine the vehicle's movements at each station and mark them.

[0127] In step S404, if the action mark of the vehicle's current station is rotation, an equilateral rectangular area with the coordinates of the current station as the center and the lengths of the sides in the x-axis and y-axis directions are both 2×LR is constructed as a safe action space model.

[0128] S405: If the action mark of the vehicle's current station is straight ahead, a rectangular area with the coordinates of the current station as the center, with a side length of 2×(Lx+Lx1) in the x-axis direction and a side length of 2×(Ly+Ly1) in the y-axis direction, is constructed as a safe action space model.

[0129] S406 , the vehicle's safety action space model changes as the vehicle moves.

[0130] S407, determine whether there are other vehicles located in the safe action space model of the vehicle, if so, proceed to S408, if not, proceed to S409.

[0131] S408, controlling the vehicle to stop.

[0132] S409, control the vehicle to move forward.

[0133] 2. Intersection Control Methods

[0134] The intersection control method is used to solve the problem of vehicle collision at the intersection and ensure that vehicles pass through the intersection in an orderly manner. The intersection control method includes the following steps:

[0135] (1) Set the model parameters of the intersection involved in the map. Taking the cross intersection as an example, set the model parameters L1 and L2 in meters. For example, L1 = 0.6m, L2 = 1.8m. The cross virtual area model is a symmetrical structure. The coordinates of the 12 contour points can be obtained according to the values of L1 and L2. For details about L1 and L2, see Figure 5 .

[0136] (2) According to the road planner, obtain the set paths of n vehicles and the stations included in the set paths. For example, the set of stations on the path of the first vehicle is (LM11, LM12, LM13, ..., LM1j), where LM11 represents the starting point of the first vehicle, LM1j represents the end point of the first vehicle, and the set path of the first vehicle contains a total of j stations.

[0137] (3) Determine the cross site by traversal. Specifically, if there is a site included in at least two set paths, and the previous site of the site in the at least two set paths is different, then the site is determined to be a cross site and is placed in the cross site set D.

[0138] (4) For each intersection site in the intersection site set D, take the coordinates (X0, Y0) of the intersection site as the center and construct the following Figure 5 The cross-shaped virtual area model shown, wherein X1 = X0-L1; X2 = X0+L1; X3 = X0+L2; X4 = X0-L2; Y1 = Y0+L1; Y2 = Y0+L2; Y3 = Y0-L1; Y4 = Y0-L2.

[0139] (5) Using the map information, obtain all site sets E planned on the map, obtain the coordinates of all sites in the site set E, find sites within the virtual area model from the site set E, and form a site set F. Specifically, if the coordinates (X, Y) of a site satisfy X1≤X≤X2 and Y3≤Y≤Y1, or satisfy X4≤X≤X1 and Y3≤Y≤Y1, or satisfy X2≤X≤X3 and Y3≤Y≤Y1, or satisfy X1≤X≤X2 and Y4≤Y≤Y3, or satisfy X1≤X≤X2 and Y1≤Y≤Y2, then it is determined that the site falls within the virtual area model constructed in step (4).

[0140] (6) Real-time detection: When the next stop of a vehicle belongs to the stop set F, a command is sent to other vehicles to obtain the current coordinates (X5, Y5) of the other vehicles. According to the previously constructed virtual area model, if the current coordinates of other vehicles satisfy X1≤X5≤X2 and Y3≤Y5≤Y1, or X4≤X5≤X1 and Y3≤Y5≤Y1, or X2≤X5≤X3 and Y3≤Y5≤Y1, or X1≤X5≤X2 and Y4≤Y5≤Y3, or X1≤X5≤X2 and Y1≤Y5≤Y2, it means that other vehicles are within the range of the virtual area model. A command is issued to the vehicle that is about to enter the virtual area model to stop. If no other vehicles are within the range of the virtual area model, a command is issued to allow the vehicle that is about to enter the virtual area model to pass.

[0141] Using the above-mentioned intersection control method, multiple vehicles may sometimes be located within the virtual area model, resulting in no vehicles within the model being able to move. This issue can be addressed through the following exception handling process. Specifically, when a vehicle enters the virtual area model, the dispatch management system 20 obtains the current time as the vehicle's entry time and stores it. If at least two vehicles are simultaneously within the virtual area model, the entry times of all vehicles within the virtual area model are sorted, with the vehicle that entered the virtual area model first passing first. Following the first-in, first-out principle, instructions are issued to each vehicle to ensure they pass through the intersection in sequence, avoiding collisions.

[0142] like Figure 6 FIG. 1 is a flow chart of a method for dispatching unmanned vehicles at intersections, including the following steps:

[0143] S601, obtaining the route sites of n vehicles.

[0144] S602: Perform traversal detection to determine all cross-sites.

[0145] S603: For each intersection site, a cross-shaped virtual area model is constructed with the coordinates of the intersection site as the center.

[0146] S604, determine whether there are other vehicles in the virtual area model, if so, proceed to S605, if not, proceed to S606.

[0147] S605 , controlling a vehicle that is about to enter the virtual area model to stop, and controlling vehicles in the virtual area model to exit in sequence according to the entry time.

[0148] S606: Control the vehicle that is about to enter the virtual area model to continue moving forward.

[0149] 3. Artificially setting conflict points

[0150] Considering that the distance between individual stations is relatively short, that is, the distance between two stations is less than the vehicle safety operation distance (such as Lx1, Ly1 or LR), during the operation of multiple vehicles, the stations with relatively short distances may not belong to the conflict points determined according to the model, which may cause vehicle movement interference. In this embodiment, the problem is solved by artificially constructing a conflict relationship.

[0151] Establish a data table. Specifically, among all the stations planned on the map, the stations whose distance h between stations satisfies the following conditions are taken as a pair of conflict stations: h < Lx1 or h < Ly1 or h < LR. Store all the conflict stations to obtain the data table. In the data table, Am represents the mth pair of conflict stations.

[0152] For example, if a certain station LMr ∈ Am in the set of path stations (LM1, LM2, LM3,..., LMi) of vehicle Q, when the next station of vehicle Q is LMr, determine whether there is another vehicle at another station in Am or moving towards another station in Am. If so, control vehicle Q to stop. If there is no other vehicle at another station in Am and no other vehicle is moving towards another station in Am, control vehicle Q to pass.

[0153] This embodiment provides an optimization control for unmanned vehicle scheduling, which is applied to the traffic control scheduling of laser SLAM unmanned transport vehicles, solves the problem of vehicle movement interference, and maintains a safe distance. Centered on the vehicle, a linear dynamic model (i.e., a safe operation space model) is established when the vehicle is driving, so that the vehicle maintains a safe fixed distance when driving, preventing rear-end collisions of vehicles in the same direction. For intersections, based on the set path of the vehicle, a virtual area model is constructed to prevent movement interference when the vehicle passes through the intersection, enabling the vehicles to pass in an orderly manner. Based on the straight-ahead and rotation models, predict whether the next action of the vehicle will cause interference and stop in advance to wait, avoiding collisions during vehicle movement. It avoids the problems of interference and collision when the vehicle is driving on a complex route planned to save road space, and also overcomes the difficulties of path planning in narrow spaces, improving the utilization rate of the workshop site and the road planning utilization rate.

[0154] Embodiment III

[0155] Based on the same inventive concept, this embodiment provides an unmanned vehicle scheduling device, which can be used to implement the unmanned vehicle scheduling method described in the above embodiment. The unmanned vehicle scheduling device can be implemented by software and / or hardware, and the unmanned vehicle scheduling device is generally integrated into a terminal, such as a computer.

[0156] Figure 7 is the structural block diagram of the unmanned vehicle scheduling device provided in Embodiment III of the present invention, as Figure 7 shown, the unmanned vehicle scheduling device includes:

[0157] A determination module 71 is configured to determine, in real time, the stations within a safe distance of the target unmanned vehicle based on the station the target unmanned vehicle is currently located at;

[0158] A construction module 72 is configured to construct a safety action space model corresponding to each station within the safety distance;

[0159] The control module 73 is configured to control the target unmanned vehicle to stop if the current coordinates of other unmanned vehicles are within the safe action space model.

[0160] Optionally, the determining module 71 includes:

[0161] A first determining unit, configured to determine in real time the current location of the target unmanned vehicle;

[0162] The second determination unit is used to determine the stations included in the safety distance of the target unmanned vehicle based on the coordinates of the current station, the coordinates of the station after the current station in the set path of the target unmanned vehicle according to the forward direction, and the preset safety distance between unmanned vehicles.

[0163] Optionally, the first determining unit includes:

[0164] An acquisition subunit, configured to acquire the current coordinates of the target unmanned vehicle in real time;

[0165] a calculation subunit, configured to respectively calculate the distance between the current coordinates and the coordinates of each station in the set path of the target unmanned vehicle;

[0166] The determination subunit is used to select the site corresponding to the minimum distance as the current site of the target unmanned vehicle.

[0167] Optionally, the second determining unit is specifically configured to:

[0168] Starting from the current site, the L value is calculated by accumulating the square of the distance to each site:

[0169] When we find a solution that satisfies L≥La 2 When the minimum L value is reached, the accumulation is stopped, and the site used to calculate the minimum L value is used as the site included in the safety distance of the target unmanned vehicle;

[0170] Wherein, La represents the preset safety distance between unmanned vehicles; LMk represents the current location of the target unmanned vehicle, (X LMk , Y LMk ) represents the coordinates of the current location of the target unmanned vehicle; (X LMk+s , YLMk+s ) represents the coordinates of the sth station after the current station in the set path of the target unmanned vehicle according to the forward direction; the value of u determines the number of stations used to calculate the L value. For each accumulated station, the value of u is increased by one. u is a positive integer, 1≤u≤ik, and i represents the total number of stations included in the set path of the target unmanned vehicle.

[0171] Optionally, the building block 72 includes:

[0172] a third determining unit, configured to determine, for each station included in the safety distance, a model parameter according to the vehicle action mark of the station;

[0173] The construction unit is used to construct a safety action space model corresponding to the site according to the model parameters.

[0174] Optionally, the third determining unit is specifically configured to:

[0175] If the vehicle action mark of the station is straight, the model parameters are determined as follows: a rectangle centered on the station coordinates, wherein the side length of the rectangle in the x-axis direction is twice the sum of the x-axis laser obstacle avoidance distance and the x-axis straight-ahead safe action distance, and the side length of the rectangle in the y-axis direction is twice the sum of the y-axis laser obstacle avoidance distance and the y-axis straight-ahead safe action distance;

[0176] If the vehicle action mark of the site is rotation, the model parameters are determined as: a rectangle centered on the site coordinates, and the side lengths of the rectangle in the x-axis and y-axis directions are both twice the radius of the vehicle rotation action.

[0177] Optionally, the unmanned vehicle dispatching device further includes:

[0178] A path determination module, configured to determine a set path for the target unmanned vehicle based on the starting and ending points of the target unmanned vehicle before the determination module 71 determines the sites within the safety distance of the target unmanned vehicle in real time based on the current site of the target unmanned vehicle;

[0179] A site determination module, configured to determine the sites included in the set path based on the sites planned on the map;

[0180] The marking module is used to mark the vehicle action of each station included in the set path.

[0181] Optionally, the tagging module includes:

[0182] a first marking unit, configured to mark the vehicle motion at the starting point and the end point in the set path as straight ahead;

[0183] An acquisition unit, configured to acquire the coordinates of each station in the set path;

[0184] a determination unit configured to determine, for each station in the set path except the starting point and the end point, whether the coordinates of the station are located on a line connecting a previous station and a next station in the set path;

[0185] a second marking unit, for marking the vehicle movement at the station as going straight if the vehicle is on the connecting line;

[0186] The third marking unit is used to mark the vehicle action of the station as rotation if the vehicle is not on the connecting line.

[0187] Optionally, the unmanned vehicle dispatching device further includes:

[0188] a removal module configured to, after the construction module 72 constructs a safe action space model corresponding to each station within the safety distance, remove the stations included in the set path of the target unmanned vehicle from all stations planned on the map to obtain a first station set;

[0189] a set determining module, configured to determine sites in the first site set that are within the safe action space model, to obtain a second site set;

[0190] The first control module is used to control the target unmanned vehicle to continue driving if the current coordinates of other unmanned vehicles are within the safe action space model and the current site of the other unmanned vehicles belongs to the second site set.

[0191] Optionally, the unmanned vehicle dispatching device further includes:

[0192] a conflict site determination module, configured to determine at least one pair of conflict sites among all sites planned on the map, and store the determined at least one pair of conflict sites, wherein each pair of conflict sites satisfies at least one of the following conditions: a distance between the two sites is less than a preset x-axis straight-ahead safe action distance, a distance between the two sites is less than a preset y-axis straight-ahead safe action distance, or a distance between the two sites is less than a preset vehicle rotation action radius;

[0193] a judgment module, configured to, if the next station of the target unmanned vehicle is a conflicting station, determine whether another unmanned vehicle is at another station within the conflicting station or is heading towards another station within the conflicting station;

[0194] The second control module is configured to control the target unmanned vehicle to stop if yes; and to control the target unmanned vehicle to continue driving if no.

[0195] Optionally, the unmanned vehicle dispatching device may further include:

[0196] An intersection site determination module, configured to determine an intersection site based on set paths of at least two unmanned vehicles;

[0197] A model building module, configured to build a virtual area model with the coordinates of the intersection site as the center;

[0198] The third control module is used to control the unmanned vehicle that is about to enter the virtual area model to stop if the next stop of the unmanned vehicle is within the virtual area model and the current coordinates of other unmanned vehicles are within the virtual area model.

[0199] Optionally, the cross-site determination module includes:

[0200] A path acquisition unit, used to respectively acquire the set path of each unmanned vehicle;

[0201] a fourth determining unit, configured to determine the sites included in each set path according to the sites planned on the map;

[0202] The fifth determining unit is configured to determine that a site is a cross site if there is a site included in at least two set paths and the previous site of the site in the at least two set paths is different.

[0203] Optionally, model building modules include:

[0204] a sixth determining unit, configured to determine, for each intersection, a type of intersection corresponding to the intersection, and determine preset model parameters corresponding to the intersection type;

[0205] The model building unit is used to build the virtual area model according to the preset model parameters with the coordinates of the intersection site as the center.

[0206] Optionally, the shape of the virtual area model is T-shaped, Y-shaped or cross-shaped.

[0207] Optionally, the unmanned vehicle dispatching device further includes:

[0208] a recording module for recording the entry time when the unmanned vehicle enters the virtual area model after constructing the virtual area model with the coordinates of the intersection site as the center;

[0209] The fourth control module is used to control the at least two unmanned vehicles to travel according to the first-in-first-out principle based on their respective entry times if there are at least two unmanned vehicles in the virtual area model at the same time.

[0210] The above-mentioned unmanned vehicle dispatching device can execute the unmanned vehicle dispatching method provided by the embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method. For technical details not fully described in this embodiment, please refer to the unmanned vehicle dispatching method provided by the embodiment of the present invention.

[0211] Example 4

[0212] This embodiment provides an unmanned vehicle dispatching system, comprising: the unmanned vehicle dispatching device described in the above embodiment and at least one unmanned vehicle.

[0213] Example 5

[0214] This embodiment provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the unmanned vehicle dispatching method described in the above embodiment are implemented.

[0215] Example 6

[0216] This embodiment provides a non-volatile computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the unmanned vehicle scheduling method described in the above embodiment are implemented.

[0217] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0218] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0219] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for dispatching an unmanned vehicle, characterized in that: include: Determine in real time the stations within a safe distance of the target unmanned vehicle based on the station the target unmanned vehicle is currently at; For each station within the safety distance, a safety action space model corresponding to each station is constructed, and a safe driving area of the target unmanned vehicle is determined by using all safety action space models corresponding to all stations within the safety distance; If the current coordinates of other unmanned vehicles are within the safe driving area, the target unmanned vehicle is controlled to stop.

2. The method according to claim 1, characterized in that Determine the stations within the safe distance of the target unmanned vehicle in real time based on the current station of the target unmanned vehicle, including: Determine in real time the current location of the target unmanned vehicle; Based on the coordinates of the current site, the coordinates of the site behind the current site in the set path of the target unmanned vehicle in the forward direction, and the preset safety distance between unmanned vehicles, the sites included in the safety distance of the target unmanned vehicle are determined.

3. The method according to claim 2, characterized in that Determine the current location of the target unmanned vehicle in real time, including: Obtaining the current coordinates of the target unmanned vehicle in real time; Calculating the distance between the current coordinates and the coordinates of each station in the set path of the target unmanned vehicle; The station corresponding to the minimum distance is selected as the current station of the target unmanned vehicle.

4. The method according to claim 2, characterized in that Determining the stations within the safety distance of the target unmanned vehicle based on the coordinates of the current station, the coordinates of stations in the set path of the target unmanned vehicle that are behind the current station in the forward direction, and the preset safety distance between unmanned vehicles includes: Starting from the current site, the L value is calculated by accumulating the square of the distance to each site: When we find a solution that satisfies L≥La 2 When the minimum L value is reached, the accumulation is stopped, and the site used to calculate the minimum L value is used as the site included in the safety distance of the target unmanned vehicle; Wherein, La represents the preset safety distance between unmanned vehicles; LMk represents the current location of the target unmanned vehicle, (X LMk , Y LMk ) represents the coordinates of the current location of the target unmanned vehicle; (X LMk+s , Y LMk+s ) represents the coordinates of the sth station after the current station in the set path of the target unmanned vehicle according to the forward direction; the value of u determines the number of stations used to calculate the L value. For each accumulated station, the value of u is increased by one. u is a positive integer, 1≤u≤ik, and i represents the total number of stations included in the set path of the target unmanned vehicle.

5. The method according to claim 1, wherein For each station within the safety distance, a safety action space model corresponding to each station is constructed, including: For each station included in the safety distance, determining a model parameter according to the vehicle action mark of the station; A safety action space model corresponding to the site is constructed according to the model parameters.

6. The method according to claim 5, characterized in that For each station within the safety distance, model parameters are determined based on the vehicle action mark of the station, including: If the vehicle action mark of the station is straight, the model parameters are determined as follows: a rectangle centered on the station coordinates, wherein the side length of the rectangle in the x-axis direction is twice the sum of the x-axis laser obstacle avoidance distance and the x-axis straight-ahead safe action distance, and the side length of the rectangle in the y-axis direction is twice the sum of the y-axis laser obstacle avoidance distance and the y-axis straight-ahead safe action distance; If the vehicle action mark of the site is rotation, the model parameters are determined as: a rectangle centered on the site coordinates, and the side lengths of the rectangle in the x-axis and y-axis directions are both twice the radius of the vehicle rotation action.

7. The method according to claim 1, characterized in that Before determining the stations within the safe distance of the target unmanned vehicle in real time based on the current station of the target unmanned vehicle, the method further includes: Determining a set path for the target unmanned vehicle based on the starting point and the end point of the target unmanned vehicle; Determine the sites included in the set path based on the sites planned on the map; Vehicle action marking is performed on each station included in the set route.

8. The method according to claim 7, characterized in that Marking the vehicle actions for each station included in the set route includes: Marking the vehicle actions at the starting point and the end point in the set path as straight ahead; Obtaining the coordinates of each site in the set path; For each station in the set path except the starting point and the end point, determining whether the coordinates of the station are on a line connecting the previous station and the next station in the set path; If it is on the connecting line, the vehicle action marked at the station is to go straight; If it is not on the connecting line, the vehicle action of the station is marked as rotation.

9. The method according to any one of claims 1 to 8, characterized in that After constructing a safety action space model corresponding to each station within the safety distance, the method further includes: Eliminate the sites included in the set path of the target unmanned vehicle from all sites planned on the map to obtain a first site set; Determining sites in the first site set that are within the safe action space model to obtain a second site set; If the current coordinates of other unmanned vehicles are within the safe action space model, and the current site of the other unmanned vehicles belongs to the second site set, the target unmanned vehicle is controlled to continue driving.

10. The method according to any one of claims 1 to 8, characterized in that Also includes: Determine at least one pair of conflicting sites among all sites planned on the map, and store the determined at least one pair of conflicting sites, wherein each pair of conflicting sites satisfies at least one of the following conditions: a distance between the two sites is less than a preset x-axis straight-ahead safe action distance, a distance between the two sites is less than a preset y-axis straight-ahead safe action distance, and a distance between the two sites is less than a preset vehicle rotation action radius; If the next station of the target unmanned vehicle is a conflicting station, determine whether there is another unmanned vehicle at another station in the conflicting station or heading towards another station in the conflicting station; If so, controlling the target unmanned vehicle to stop; If not, the target unmanned vehicle is controlled to continue driving.

11. An unmanned vehicle dispatching device, characterized in that: include: A determination module is used to determine, in real time, the stations within the safe distance of the target unmanned vehicle based on the station where the target unmanned vehicle is currently located; A construction module is used to construct a safe action space model corresponding to each station included in the safe distance, and determine the safe driving area of the target unmanned vehicle through all safe action space models corresponding to all stations included in the safe distance; The control module is used to control the target unmanned vehicle to stop if the current coordinates of other unmanned vehicles are within the safe driving area.

12. An unmanned vehicle dispatching system, characterized in that: include: The unmanned vehicle dispatching device according to claim 11 and at least one unmanned vehicle.

13. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 10 when executing the computer program.

14. A non-volatile computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 10 are implemented.

Images