Centralized control multi-unmanned vehicle scheduling method, system, device and storage medium

Abstract

The present application relates to the field of mobile robot intelligent control, and discloses a centralized control multi-unmanned vehicle scheduling method, system, equipment and storage medium, the method comprises the following steps: obtaining a space conflict area in unmanned vehicle scheduling; when there is no resource scheduling conflict between multiple vehicles in the space conflict area, obtaining the conflict state of the space conflict area; solving the conflict of the space conflict area according to the conflict state to obtain a conflict resolution strategy; and centrally controlling the local unmanned vehicles in the space conflict area according to the conflict resolution strategy, so that the local unmanned vehicles obtain a new scheduling plan and schedule according to the new scheduling plan. The present application can effectively detect and solve space resource conflicts and improve the collaborative scheduling efficiency of unmanned vehicles by solving the conflict resolution strategy and enabling the local unmanned vehicles in the space conflict area to obtain a new scheduling plan according to the conflict resolution strategy and schedule according to the new scheduling plan.

Description

Technical Field

[0001] This invention relates to the field of intelligent control of mobile robots, and in particular to a centralized control method, system, device and storage medium for scheduling multiple unmanned vehicles. Background Technology

[0002] With the development of intelligent control technology for mobile robots, multi-unmanned vehicle (UAV) collaboration is widely used in scheduling operations such as intelligent warehousing and logistics. Achieving multi-UAV scheduling requires ensuring that each UAV operates without conflict in its operating space. However, existing technologies mainly rely on global resource allocation and scheduling methods based on path points and path lines as atomic resources. These methods are either too complex or require very high levels of state control for synchronized UAVs. Furthermore, the uncertainties of multi-UAV systems make deadlock phenomena and collision-based spatial resource conflicts almost unavoidable and difficult to detect accurately. Therefore, resolving localized spatial resource conflicts among multi-UAVs has become an urgent problem to solve.

[0003] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] This invention provides a centralized control method, system, device, and storage medium for scheduling multiple unmanned vehicles, aiming to solve the technical problem in the prior art that it is difficult to resolve the spatial resource conflicts of multiple unmanned vehicles in a localized manner.

[0005] To achieve the above objectives, the present invention provides a centralized control method for scheduling multiple unmanned vehicles, the method comprising the following steps:

[0006] Acquire spatial conflict areas generated during autonomous vehicle scheduling;

[0007] When there is no resource scheduling conflict between multiple vehicles in the spatial conflict area, obtain the conflict status of the spatial conflict area;

[0008] Based on the conflict state, conflict resolution is performed on the spatial conflict region to obtain a conflict resolution strategy;

[0009] According to the conflict resolution strategy, the local unmanned vehicles in the spatial conflict area are centrally controlled so that the local unmanned vehicles can obtain a new scheduling plan and perform scheduling according to the new scheduling plan.

[0010] Optionally, the step of centrally controlling the local unmanned vehicles in the spatial conflict area according to the conflict resolution strategy, so that the local unmanned vehicles can obtain a new scheduling plan and perform scheduling according to the new scheduling plan, includes:

[0011] According to the conflict resolution strategy, the driving speed of the local unmanned vehicle in the spatial conflict area is calculated in real time through a centralized control function when the conflict is resolved.

[0012] The driving speed of the local unmanned vehicle is updated based on the driving speed value so that the local unmanned vehicle can be scheduled according to the new driving speed.

[0013] Optionally, before the step of obtaining the conflict status of the spatial conflict area when there is no resource scheduling conflict among multiple vehicles in the spatial conflict area, the method further includes:

[0014] The spatial conflict zone is detected, and it is determined whether a new unmanned vehicle has entered the spatial conflict zone.

[0015] If a new unmanned vehicle enters the spatial conflict area, it is determined whether there is a resource scheduling conflict between multiple vehicles in the spatial conflict area.

[0016] If there is a resource scheduling conflict between multiple vehicles in the spatial conflict area, it is determined that a deadlock loop has been generated in the spatial conflict area, and the deadlock loop is resolved by the deadlock loop resolution module.

[0017] Optionally, before the step of detecting the spatial conflict area and determining whether a new unmanned vehicle has entered the spatial conflict area, the method further includes:

[0018] Obtain the scheduling status of all unmanned vehicles in the discrete time period of the current moment, and determine whether there are unmanned vehicles with resources to be allocated based on the scheduling status of the unmanned vehicles;

[0019] If so, determine whether there is a predicted deadlock loop caused by scheduling conflicts in the unmanned vehicles with the resources to be allocated;

[0020] If no autonomous vehicle with the resource to be allocated generates a predicted deadlock loop due to scheduling conflict, then the spatial conflict area existing in the scheduling process of the autonomous vehicle with the resource to be allocated is obtained.

[0021] Optionally, before the step of obtaining all autonomous vehicle scheduling states in the discrete time period of the current moment, and determining whether there are autonomous vehicles waiting to be allocated resources based on the autonomous vehicle scheduling states, the method further includes:

[0022] The continuous scheduling time is discretized according to the preset scheduling model of the unmanned vehicle to obtain periodic discrete time with equal time.

[0023] The autonomous vehicle's driving speed and target scheduling position are planned based on the periodic discrete time, and all the autonomous vehicle scheduling states are generated.

[0024] Optionally, after the step of obtaining the spatial conflict region existing in the scheduling process of the unmanned vehicles with the resources to be allocated if no predicted deadlock loop is generated due to scheduling conflicts, the method further includes:

[0025] If a predicted deadlock loop occurs due to scheduling conflict among the unmanned vehicles with the resources to be allocated, then obtain all predicted deadlock loops that the unmanned vehicles with the resources to be allocated will form.

[0026] Based on all the predicted deadlock loops, solve for the corresponding predicted unlocking strategy;

[0027] Based on the predicted unlocking strategy, new paths are planned for all autonomous vehicles so that the autonomous vehicles can be scheduled according to the new path plans.

[0028] Optionally, the step of determining that a deadlock loop has occurred in the spatial conflict area if there is a resource scheduling conflict between multiple vehicles in the spatial conflict area, and then breaking the deadlock loop through the deadlock loop unblocking module, includes:

[0029] When it is determined that a deadlock loop exists in the spatial conflict region, it is determined whether the deadlock resolution module can generate a strategy solution to resolve the deadlock loop;

[0030] If so, the deadlock loop is untied according to the strategy described above.

[0031] Furthermore, to achieve the above objectives, the present invention also proposes a centralized control multi-unmanned vehicle dispatching system, the system comprising:

[0032] The conflict acquisition module is used to acquire spatial conflict areas generated during the scheduling of unmanned vehicles;

[0033] The status acquisition module is used to acquire the conflict status of the spatial conflict area when there is no resource scheduling conflict between multiple vehicles in the spatial conflict area.

[0034] The strategy acquisition module performs conflict resolution on the spatial conflict region based on the conflict state to obtain a conflict resolution strategy.

[0035] The centralized control module centrally controls the local unmanned vehicles in the spatial conflict area according to the conflict resolution strategy, so that the local unmanned vehicles can obtain a new scheduling plan and perform scheduling according to the new scheduling plan.

[0036] Furthermore, to achieve the above objectives, the present invention also proposes a centralized control multi-unmanned vehicle scheduling device, the device comprising: a memory, a processor, and a centralized control multi-unmanned vehicle scheduling program stored in the memory and executable on the processor, the centralized control multi-unmanned vehicle scheduling program being configured to implement the steps of the centralized control multi-unmanned vehicle scheduling method described above.

[0037] Furthermore, to achieve the above objectives, the present invention also proposes a storage medium storing a centralized control multi-unmanned vehicle scheduling program, which, when executed by a processor, implements the steps of the centralized control multi-unmanned vehicle scheduling method described above.

[0038] This invention identifies spatial conflict areas; when no resource scheduling conflicts exist between multiple vehicles in the spatial conflict area, it obtains the conflict state of the spatial conflict area; it solves the conflict in the spatial conflict area based on the conflict state to obtain a conflict resolution strategy; and it centrally controls the local unmanned vehicles in the spatial conflict area according to the conflict resolution strategy, so that the local unmanned vehicles obtain a new scheduling plan and perform scheduling according to the new scheduling plan. Compared with existing technologies, this invention effectively detects and resolves spatial resource conflicts, improving the collaborative scheduling efficiency of unmanned vehicles. Attached Figure Description

[0039] Figure 1 This is a schematic diagram of the structure of a multi-unmanned vehicle dispatching device with centralized control of the hardware operating environment involved in the embodiments of the present invention;

[0040] Figure 2 This is a flowchart illustrating the first embodiment of the centralized control method for scheduling multiple unmanned vehicles according to the present invention.

[0041] Figure 3 This is a schematic diagram of the overall process of multi-unmanned vehicle scheduling in the first embodiment of the centralized control multi-unmanned vehicle scheduling method of the present invention;

[0042] Figure 4 This is a schematic diagram of the spatial mathematical model for conflict detection in the first embodiment of the centralized control multi-unmanned vehicle scheduling method of the present invention;

[0043] Figure 5 This is a flowchart illustrating the second embodiment of the centralized control method for scheduling multiple unmanned vehicles according to the present invention.

[0044] Figure 6 This is a flowchart illustrating the third embodiment of the centralized control method for scheduling multiple unmanned vehicles according to the present invention.

[0045] Figure 7 This is a schematic diagram of the discrete-time motion control model in the third embodiment of the centralized control multi-unmanned vehicle scheduling method of the present invention;

[0046] Figure 8This is a flowchart illustrating the fourth embodiment of the centralized control method for scheduling multiple unmanned vehicles according to the present invention.

[0047] Figure 9 This is a schematic diagram illustrating the generation of a predicted deadlock loop in the fourth embodiment of the centralized control multi-unmanned vehicle scheduling method of the present invention.

[0048] Figure 10 This is a schematic diagram illustrating the generation of predicted resource conflicts in the fourth embodiment of the centralized control multi-unmanned vehicle scheduling method of the present invention.

[0049] Figure 11 This is a structural block diagram of the centralized control multi-unmanned vehicle dispatching system of the present invention.

[0050] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0051] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.

[0052] Reference Figure 1 , Figure 1 This is a schematic diagram of the structure of a multi-unmanned vehicle scheduling device for centralized control of the hardware operating environment involved in the embodiments of the present invention.

[0053] like Figure 1 As shown, the centralized control multi-unmanned vehicle scheduling device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen and an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be high-speed random access memory (RAM) or stable non-volatile memory (NVM), such as a disk storage device. The memory 1005 may also optionally be a storage system independent of the aforementioned processor 1001.

[0054] Those skilled in the art will understand that Figure 1The structure shown does not constitute a limitation on a centralized control multi-unmanned vehicle dispatching device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0055] like Figure 1 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a network communication module, a user interface module, and a centralized control multi-unmanned vehicle scheduling program.

[0056] exist Figure 1 In the centralized control multi-unmanned vehicle scheduling device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and memory 1005 in the centralized control multi-unmanned vehicle scheduling device of the present invention can be set in the centralized control multi-unmanned vehicle scheduling device. The centralized control multi-unmanned vehicle scheduling device calls the centralized control multi-unmanned vehicle scheduling program stored in the memory 1005 through the processor 1001 and executes the centralized control multi-unmanned vehicle scheduling method provided in the embodiment of the present invention.

[0057] This invention provides a centralized control method for scheduling multiple unmanned vehicles, referring to... Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the centralized control method for scheduling multiple unmanned vehicles according to the present invention.

[0058] In this embodiment, the centralized control method for scheduling multiple unmanned vehicles includes the following steps:

[0059] Step S100: Obtain the spatial conflict area during unmanned vehicle scheduling;

[0060] It should be noted that the executing entity of the method in this embodiment can be an electronic computing service device with data processing, network communication, and program execution functions, such as an in-vehicle embedded tablet or in-vehicle computer, or other in-vehicle electronic devices capable of achieving the same or similar functions. This embodiment does not limit this. Here, various embodiments of the centralized control multi-unmanned vehicle scheduling method of the present invention will be described using a centralized control multi-unmanned vehicle scheduling device as an example.

[0061] It should be understood that the aforementioned spatial conflict area refers to the area where multiple unmanned vehicles are scheduled at the current moment, and conflicts arise because some unmanned vehicles need to use the same spatial location at the same time.

[0062] In practical implementation, the centralized control of multi-unmanned vehicle scheduling equipment needs to obtain the spatial conflict area in order to acquire the unmanned vehicle scheduling conflict information generated in that area.

[0063] Step S200: When there is no resource scheduling conflict between multiple vehicles in the spatial conflict area, obtain the conflict status of the spatial conflict area;

[0064] It should be understood that the above-mentioned conflict state is a spatial conflict that will occur at the current moment because multiple unmanned vehicles need to pass through the same location in the path space.

[0065] It should be noted that, before the step of obtaining the conflict status of the spatial conflict area when there is no resource scheduling conflict between multiple vehicles in the spatial conflict area, the method further includes: detecting the spatial conflict area and determining whether a new unmanned vehicle enters the spatial conflict area; if the new unmanned vehicle enters the spatial conflict area, determining whether there is a resource scheduling conflict between multiple vehicles in the spatial conflict area; if there is a resource scheduling conflict between multiple vehicles in the spatial conflict area, determining that a deadlock loop has been generated in the spatial conflict area, and resolving the deadlock loop through the deadlock loop resolution module.

[0066] Furthermore, before the step of detecting the spatial conflict area and determining whether a new unmanned vehicle enters the spatial conflict area, the method further includes: obtaining the scheduling status of all unmanned vehicles in the discrete time period of the current time, and determining whether there are unmanned vehicles with resources to be allocated based on the scheduling status; if so, determining whether there is a predicted deadlock loop caused by the scheduling conflict of the unmanned vehicles with resources to be allocated; if there is no predicted deadlock loop caused by the scheduling conflict of the unmanned vehicles with resources to be allocated, then obtaining the spatial conflict area existing in the scheduling process of the unmanned vehicles with resources to be allocated.

[0067] It should be understood that the above-mentioned preset scheduling model is a directed graph G model that establishes each unmanned vehicle along a pre-planned trajectory in a two-dimensional state space where multiple unmanned vehicles work together. This model can realize the scheduling of multiple unmanned vehicles.

[0068] Furthermore, this is achieved by traversing a directed graph G along a pre-planned trajectory, where the directed graph G = (V, E) consists of a vertex set and an edge set, where the vertex set represents the set of all path nodes and the edge set... V×V is a set of path trajectories composed of any two path nodes.

[0069] It should be noted that the above resource is defined as any vertex n i ∈V or any edge e j∈E, and can be allocated for scheduling the driving of autonomous vehicles. The resource set R is the union of the edge set and the vertex set, R = VUE. From the perspective of resource allocation, the scheduling system must ensure the exclusivity of each resource to ensure that there is no collision between multiple autonomous vehicles running at the same time. That is, a resource can only be occupied by one autonomous vehicle at the same time. The authorized autonomous vehicle set A = [1, ..., K], where the authorized autonomous vehicle set A represents all the autonomous vehicles activated in the scheduling system.

[0070] It should be noted that, denoted as k, the state x of each autonomous vehicle k∈A=[1,…,K] at time t is... k (t) is defined as the geometric center position p of the unmanned vehicle k at time t. k (t) and velocity v k The combination of (t), x k (t)={p k (t), v k (t)}, the state space occupied by the autonomous vehicle k Let O be defined as the contour of the autonomous vehicle k at time t and the set of all corresponding state spaces within the contour. The resource set occupied by the autonomous vehicle k and the resource set requested are O(t). k (t) and R k (t), occupying resource set O k (t) represents the state space occupied by the unmanned vehicle k at time t. The corresponding path resource set, the resource request set Rk(t), includes not only the resources on the planned path that the autonomous vehicle k needs to request at time t, but also the state space occupied by all resources requested by the autonomous vehicle k′∈A (k′≠k) at time t. The state space occupied by the autonomous vehicle k The set of resources corresponding to non-empty intersections is the set of resources that autonomous vehicle k needs to apply for at time t, and the resources applied for by other autonomous vehicles that have contour collisions with the resources applied for by autonomous vehicle k.

[0071] In practical implementation, when the centralized control multi-vehicle scheduling equipment determines that there is no resource conflict between multiple vehicles in the spatial conflict area, it can analyze the conflict information of the conflict area in the spatial conflict area and obtain the conflict status based on the analyzed data.

[0072] Step S300: Solve the conflict in the spatial conflict region according to the conflict state to obtain a conflict resolution strategy;

[0073] Understandably, the above conflict resolution strategy is that when the centralized control multi-unmanned vehicle scheduling equipment obtains the conflict status of the spatial conflict area, it can solve the conflict and use the solution as the strategy to resolve the conflict in the above spatial conflict area.

[0074] In practical implementation, the centralized control multi-unmanned vehicle scheduling equipment can solve the unmanned vehicle scheduling conflicts generated in the conflict area based on the conflict state obtained by analysis, and then obtain the conflict resolution strategy based on the solution results.

[0075] Step S400: Centrally control the local unmanned vehicles in the spatial conflict area according to the conflict resolution strategy, so that the local unmanned vehicles can obtain a new scheduling plan and perform scheduling according to the new scheduling plan.

[0076] It should be noted that the above-mentioned new scheduling plan is a scheduling plan for rescheduling unmanned vehicles in the above-mentioned spatial conflict area after the centralized control multi-unmanned vehicle scheduling equipment resolves the conflict according to the above-mentioned conflict resolution strategy. This allows the unmanned vehicles in the spatial conflict area to continue operating according to the scheduling plan.

[0077] In practice, the centralized control multi-unmanned vehicle scheduling equipment centrally controls the local unmanned vehicles in the spatial conflict area according to the conflict resolution strategy, so that the local unmanned vehicles can obtain a new scheduling plan and continue to operate according to the new scheduling plan.

[0078] Furthermore, such as Figure 3 As shown, Figure 3 This is a schematic diagram of the overall process of multi-unmanned vehicle scheduling in the first embodiment of the centralized control multi-unmanned vehicle scheduling method of the present invention.

[0079] In the diagram, step (1) establishes a mathematical model corresponding to the AGV status and resources; step (2) establishes a spatial mathematical model for conflict detection based on the spatial structure of the map established in step (1); step (3) discretizes the time of the scheduling system into equal discrete time periods, plans the speed and position status of the AGVs that are assigned tasks to the scheduling system, and maps them to discrete time periods; step (4) obtains the AGV status and the status of the corresponding resources occupied in the discrete time period at the current moment, as well as the status of the AGV requesting resources; step (5) determines whether there are AGVs waiting to be allocated resources based on the AGV status fed back by the scheduling system. If there are no AGVs waiting to be allocated resources, step (6) continues to detect the AGV's request for resources and returns to step (4); if there are AGVs waiting to be allocated resources, step (7) detects whether there are other running vehicles forming a predicted deadlock loop with this AGV on the remaining path. If a predicted deadlock loop is determined to exist, step (8) obtains the resource occupation and request relationships of all AGVs involved in all deadlock loops in which this AGV participates, replans the path, and returns to step (3) to reallocate the AGVs on the path. If the AGV is not detected to have entered the spatial conflict zone, the AGV continues to run at the planned speed and returns to step (2) so that the system can obtain the AGV's status and resource occupancy relationship over the discrete time period. Otherwise, if step (9) detects that the AGV has entered the spatial conflict zone, step (10) is triggered to detect whether there is a deadlock loop in the corresponding spatial conflict zone. The difference from step (7) is that step (10) detects all AGVs in the physical area of ​​the spatial conflict. Does the resource occupation and request relationship exist in deadlock loop? If step (10) detects a deadlock loop in the corresponding spatial conflict area, the scheduling system obtains the resource occupation and request relationship of all AGVs involved in the deadlock loop and executes the local deadlock loop resolution procedure in step (13). Based on the deadlock loop resolution result in step (13), step (14) determines whether to resolve the current deadlock loop. If there is no solution to the deadlock loop, step (15) returns that there is no solution to the deadlock loop. If a deadlock loop resolution strategy solution is obtained, step (16) controls the AGVs involved in the deadlock loop to execute the strategy according to the deadlock loop resolution strategy solution.

[0080] It should be noted that, in Figure 3In this process, deadlock handling takes precedence over local conflict optimization and control. That is, once a deadlock occurs in a spatial conflict region, deadlock resolution must be completed first, and non-deadlock conflicts are handled based on a first-come, first-served principle. Conflict optimization and control are then performed for the spatial conflict region only after no deadlock exists in the scheduling system. Therefore, if step (10) detects that there is no deadlock loop in the corresponding spatial conflict region, step (11) is executed to perform local cooperative game centralized control conflict resolution to optimize and control the scheduling variables of the AGVs with spatial conflicts.

[0081] It should be noted that, Figure 3 The AGVs mentioned herein all refer to unmanned vehicles.

[0082] It should also be noted that, according to Figure 3 The directed graph G model shown establishes a spatial mathematical model for conflict detection, such as... Figure 4 As shown, Figure 4 This is a schematic diagram of the spatial mathematical model for conflict detection in the first embodiment of the centralized control multi-unmanned vehicle scheduling method of the present invention.

[0083] Figure 4 In the spatial conflict detection resource set, a recursive search is performed for sufficiently long adjacent nodes in space. Make Spatial location satisfies the following Within a space with a center and radius B, the set This is defined as a spatial conflict detection label set. Parameter A is set long enough that when an autonomous vehicle detects entering the conflict detection label set, it can optimize its state by detecting a cooperative game among autonomous vehicles. At a relatively far location near the intersection, the state of its cooperating autonomous vehicles is predicted through a cooperative game, allowing it to adjust its own state accordingly. Based on the spatial mathematical model of conflict detection, collision-free scheduling of detected conflicts can be achieved through a collision-free motion model under non-deadlock conditions.

[0084] It should be explained that the collision-free motion model in the non-deadlock state is defined as follows: Let n be a path node of the planned path corresponding to the autonomous vehicle k. k，i The collision region is defined by path node n. k，i Let the circular position state space be defined with center radius r. If the distance between all edges is greater than or equal to 2r, then the autonomous vehicle k is defined as entering or leaving a certain path node n of the corresponding planned path. k，i The time of the collision zone are respectively Define the autonomous vehicle k as reaching a certain path node n of the corresponding planned path. k，i The time is The scheduling planning variable is defined as the combination of the times when all autonomous vehicles enter the collision area corresponding to a certain path node, arrive at the corresponding path node, and leave the collision area corresponding to that path node. Based on the current state parameters of all driverless vehicles with timestamps, and the planned state variables of the autonomous vehicle The predicted scheduling planning variables are expressed as follows:

[0085] It should be understood that the above cooperative game can be defined as follows: the action space of each autonomous vehicle is deceleration and acceleration along the planned path trajectory, and the average speed motion can be regarded as motion with deceleration and acceleration of . At the beginning and end of each discrete time period, the autonomous vehicle has a maximum speed, and the average speed of the autonomous vehicle is required to be any value within the interval, representing the maximum average speed adjustment offset.

[0086] The state parameters and optimized state variables of the cooperative autonomous vehicles are uniformly managed, planned, and controlled by the scheduling server. Within each spatial conflict region and each discrete time period, based on the state parameters of each autonomous vehicle, an optimization problem is established for all autonomous vehicles in this region in a cooperative manner. The payoff function of the cooperative game reflects the quality of the execution strategies of all cooperative autonomous vehicles. Therefore, the objective is to minimize the sum of deviations of the cooperative autonomous vehicles from their optimal position states achieved in the previous discrete time period, and each autonomous vehicle is required to meet the collision-free scheduling constraints at each spatial conflict resource point and maintain a collision-free safe distance at any given time.

[0087] This embodiment identifies spatial conflict areas; when no resource scheduling conflicts exist between multiple vehicles in the spatial conflict area, it acquires the conflict state of the spatial conflict area; it solves the conflict in the spatial conflict area based on the conflict state to obtain a conflict resolution strategy; and it centrally controls the local unmanned vehicles in the spatial conflict area according to the conflict resolution strategy, so that the local unmanned vehicles obtain a new scheduling plan and perform scheduling according to the new scheduling plan. This invention solves the conflicts generated in local spatial areas during the scheduling process of unmanned vehicles to obtain a conflict resolution strategy, enabling the local unmanned vehicles in the spatial conflict area to obtain a new scheduling plan based on the conflict resolution strategy and perform scheduling according to the new scheduling plan. Compared with existing technologies, this invention can effectively detect and resolve spatial resource conflicts, improving the collaborative scheduling efficiency of unmanned vehicles.

[0088] refer to Figure 5 , Figure 5 This is a flowchart illustrating the second embodiment of the centralized control method for scheduling multiple unmanned vehicles according to the present invention.

[0089] Based on the first embodiment described above, in this embodiment, in order to detect whether a deadlock loop is generated in the spatial conflict region and to unlock the generated deadlock loop, the method further includes the following step before step S200:

[0090] Step S110: Detect the spatial conflict area and determine whether a new unmanned vehicle has entered the spatial conflict area;

[0091] Understandably, the centralized control of the multi-vehicle scheduling equipment detects spatial conflict areas to determine whether a new unmanned vehicle has entered the spatial conflict area. If a new unmanned vehicle enters the spatial conflict area, it may cause the existing unmanned vehicle scheduling spatial conflict to fall into a deadlock state, thus making all unmanned vehicles in that space unable to operate due to the deadlock.

[0092] Step S120: If a new unmanned vehicle enters the spatial conflict area, determine whether there is a resource scheduling conflict between multiple vehicles in the spatial conflict area.

[0093] It should be understood that the above-mentioned resource scheduling conflict refers to the conflict between multiple unmanned vehicles when they apply for or occupy resources.

[0094] Step S130: If there is a resource scheduling conflict between multiple vehicles in the spatial conflict area, it is determined that a deadlock loop has been generated in the spatial conflict area, and the deadlock loop is resolved by the deadlock loop resolution module.

[0095] It should be understood that a deadlock loop under multi-vehicle scheduling is defined as follows: at any given time there are at least two or more unmanned vehicles waiting to be allocated resources, and the intersection of the resource request set of each unmanned vehicle and the resource set occupied by the other unmanned vehicle is not empty.

[0096] Furthermore, the mathematical definition of the condition for detecting a deadlock loop involving multiple autonomous vehicles is: if there exists an autonomous vehicle m∈A W (t), the resource set O occupied by the unmanned vehicle m. m (t), there exists at least one other driverless car n∈A W The resource set R of (t) n (t), m≠n, such that O m (t)∩R n (t)≠φ, conversely O n (t)∩R m (t)≠φ must also hold true. At time t, the set of autonomous vehicles forming a deadlock loop and the set of all autonomous vehicles blocked by this deadlock loop are defined as the set of rescheduled autonomous vehicles ARE(t)=[1,...,D], and the set of other non-deadlocked running autonomous vehicles. Therefore, from the perspective of resource allocation, the deadlock problem in multi-autonomous vehicle collaborative operation can be equivalent to rescheduling the set of autonomous vehicles A when a condition involving a multi-autonomous vehicle deadlock loop is detected at time t. RE All unmanned vehicles within (t) are in a state of stagnation due to the inability to obtain resources.

[0097] Furthermore, if at any time t1 a deadlock loop condition involving multiple autonomous vehicles is detected, the corresponding set of rescheduled autonomous vehicles A is re-scheduled. RE (t1), at time t2, t2>t1, another deadlock loop involving multiple unmanned vehicles and the corresponding rescheduled set of unmanned vehicles A is detected. RE (t2), if A RE (t2)∩A RE If (t1) = φ, meaning there exists an independent multi-vehicle deadlock loop, then the corresponding deadlock loops are processed sequentially according to time order; if Then the current deadlock loop resolution procedure is stopped and re-triggered, thereby ensuring the exclusivity of resources and achieving collision-free scheduling to detect whether a deadlock loop has occurred.

[0098] In this embodiment, the centralized control multi-unmanned vehicle scheduling device detects the spatial conflict area and determines whether a new unmanned vehicle has entered the spatial conflict area. If a new unmanned vehicle enters the spatial conflict area, it determines whether there is a resource scheduling conflict between multiple vehicles in the spatial conflict area. If there is a resource scheduling conflict between multiple vehicles in the spatial conflict area, it determines that a deadlock loop has occurred in the spatial conflict area, and the deadlock loop is unlocked by a deadlock loop unblocking module. This achieves the detection of deadlock loops in spatial conflict areas and the unlocking of detected deadlock loops.

[0099] refer to Figure 6 , Figure 6 This is a flowchart illustrating the third embodiment of the centralized control method for scheduling multiple unmanned vehicles according to the present invention.

[0100] Based on the first embodiment described above, in this embodiment, in order to obtain the predicted deadlock loop and unlock the predicted deadlock loop, before step S110, the method further includes:

[0101] Step S101: Discretize the continuous scheduling time according to the preset scheduling model of the unmanned vehicle to obtain periodic discrete time with equal time.

[0102] It should be understood that, based on periodic discrete time, all autonomous vehicles in each spatial conflict area are defined as a set of cooperative game participants. Based on the solution to the conflict resolution optimization problem of the cooperative game, the state of each autonomous vehicle in the cooperative autonomous vehicle set in the next periodic discrete time is determined, and the speed state of each vehicle in this cooperative game participant set is controlled by the scheduling system.

[0103] Step S102: Plan the driving speed and target scheduling position of the unmanned vehicle according to the periodic discrete time, and generate all the scheduling states of the unmanned vehicle.

[0104] Understandably, the target scheduling location mentioned above is the location where the unmanned vehicle will be scheduled.

[0105] It should be understood that the above scheduling state is a current operating state of the unmanned vehicle when it is scheduled.

[0106] It should be noted that after step S102, the following steps are also included:

[0107] Step S103: Obtain the scheduling status of all unmanned vehicles in the discrete time period of the current time, and determine whether there are unmanned vehicles with resources to be allocated based on the scheduling status of the unmanned vehicles;

[0108] It should be noted that, as Figure 7 As shown, Figure 7 This is a schematic diagram of the discrete-time motion control model in the third embodiment of the centralized control multi-unmanned vehicle scheduling method of the present invention.

[0109] Figure 7 In this context, by dividing continuous time into finite discrete time periods, the state variable x... h (0≤h≤T) from x 0 Initially, the constant acceleration u is measured during the h-th time period. h (0≤h≤T) is applied in the h-th time period to map the state variables of each driverless vehicle k∈A to all discrete time periods.

[0110] Step S104: If yes, determine whether there is a predicted deadlock loop caused by scheduling conflict for the unmanned vehicle with the resource to be allocated;

[0111] It should be understood that the aforementioned resources to be allocated are the resources that the currently scheduled driverless car will allocate to the driverless car in order to enable the driverless car to continue running, so that the driverless car has resources to be allocated and forms a total set.

[0112] Step S105: If no unmanned vehicle with the resource to be allocated generates a predicted deadlock loop due to scheduling conflict, then obtain the spatial conflict area that exists in the scheduling process of the unmanned vehicle with the resource to be allocated.

[0113] In this embodiment, the centrally controlled multi-unmanned vehicle scheduling device discretizes the continuous scheduling time according to the preset scheduling model of the unmanned vehicles to obtain periodic discrete time with equal time intervals; it plans the driving speed and target scheduling position of the unmanned vehicles according to the periodic discrete time intervals and generates all the scheduling states of the unmanned vehicles; it obtains all the scheduling states of the unmanned vehicles in the periodic discrete time interval at the current moment, and determines whether there are unmanned vehicles waiting to be allocated resources based on the scheduling states; if so, it determines whether there is a predicted deadlock loop caused by scheduling conflicts for the unmanned vehicles waiting to be allocated resources; step S105: if there is no predicted deadlock loop caused by scheduling conflicts for the unmanned vehicles waiting to be allocated resources, it obtains the spatial conflict area existing in the scheduling process of the unmanned vehicles waiting to be allocated resources. This realizes the acquisition of predicted deadlock loops and the unlocking of predicted deadlock loops.

[0114] refer to Figure 8 , Figure 8 This is a flowchart illustrating the fourth embodiment of the centralized control method for scheduling multiple unmanned vehicles according to the present invention.

[0115] Based on the third embodiment described above, in this embodiment, in order to unlock the detected predicted deadlock loop, after step S105, the method further includes:

[0116] Step S106: If there is a predicted deadlock loop caused by scheduling conflict in the unmanned vehicle with the resource to be allocated, then obtain the spatial conflict area in the scheduling process of the unmanned vehicle with the resource to be allocated.

[0117] It should be understood that the aforementioned predicted deadlock loop refers to the deadlock prediction and unlocking device for multi-autonomous vehicle (MAV) collaboration, which pre-detects potential deadlock loops during the collaborative scheduling process of multiple MAVs. The predicted deadlock loop is defined as: at time t+Δt, based on the predicted state... For each driverless car m∈A predicted W The set of resources to be requested for (t+Δt) The corresponding set of resources that will be used There exists another one or more autonomous vehicles such that each of these autonomous vehicles n∈A W (t+Δt), n≠m, the set of resources that will be occupied at time t+Δt. With driverless car m∈A W The set of resources to be requested for (t+Δt) The intersection of them is not empty, that is... Conversely, the same applies. Here, Δt is the estimated deadlock loop time interval parameter. Due to the uncertainty of the multi-vehicle system, the larger Δt is, the lower the accuracy of the deadlock loop prediction will be.

[0118] It should be understood that, as Figure 9 As shown, Figure 9 This diagram illustrates the prediction of deadlock loops in a centralized multi-unmanned vehicle scheduling method. Assuming the current time is t1, the resources occupied by AGV1 at time t1+Δt are... And AGV1 will request resources at time t1+Δt. AGV2 will request resources at time t1+Δt. The resources that AGV2 will occupy at time t1+Δt are when and At that time, the estimated set of AGV resources to be rescheduled. This is equivalent to AGV1 and AGV2 forming a predicted deadlock loop in terms of the resources they will request and the resources they will occupy.

[0119] It should be noted that, for ease of understanding, Figure 9 The AGV1 and AGV2 used in this context refer to two unmanned vehicles.

[0120] It should be noted that the estimated rescheduling set is a set formed by integrating the results of the pre-estimated rescheduling of various possible scheduling resources by the centralized control multi-unmanned vehicle scheduling equipment for possible deadlock loops.

[0121] It should be explained that before detecting whether a predicted deadlock loop has occurred, the centralized control multi-vehicle scheduling equipment still needs to predict the resulting resource conflicts, referring to... Figure 10 , Figure 10 This is a schematic diagram illustrating the generation of predicted resource conflicts in the fourth embodiment of the centralized control multi-unmanned vehicle scheduling method of the present invention.

[0122] Figure 10 In the example, assuming the current time is t2, the resources occupied by AGV1 at time t2+Δt will be... And AGV1 will request resources at time t2+Δt. AGV2 will request resources at time t2+Δt. The resources that AGV2 will occupy at time t2+Δt are when hour, That is, AGV1 and AGV2 constitute a predicted resource conflict.

[0123] It should be explained that the above predicted resource conflict can be defined as: at time t+Δt, based on the predicted state... For each driverless car m∈A predicted W The set of resources to be requested for (t+Δt) There exists another one or more autonomous vehicles such that each of these autonomous vehicles n∈A W (t+Δt), n≠m, the set of resources to be requested at time t+Δt. With driverless car m∈A W The set of resources to be requested for (t+Δt) The intersection of them is not empty, that is... At that time, it is determined that a resource conflict has occurred.

[0124] It should be noted that, Figure 10 The meanings of AGV1 and AGV2 mentioned above are the same as those in the previous text. Figure 9 The consistency between the two is not repeated here.

[0125] It should also be noted that, based on the above definition of predicted deadlock loops and the mapping relationship between autonomous vehicle states and resources, the remaining paths of other operating vehicles are detected to form a predicted deadlock loop with the remaining path of the current autonomous vehicle. Here, the remaining path is defined as: the ordered set of path resources from the current state of the autonomous vehicle to its task's endpoint. This is achieved by examining each autonomous vehicle... At time t+T n The set of resources to be occupied The set of resources that driverless car m will apply for The intersection of them is not empty, that is... Among them, T m and T n Let be the times when driverless car m and driverless car n arrive at their respective destinations at time t. Furthermore, in the predicted deadlock loop, there exists at least one driverless car whose remaining path resource set is completely contained within the remaining path resources of other driverless cars in the same or opposite direction.

[0126] Step S107: Solve for the corresponding predictive unlocking strategy based on all predicted deadlock loops;

[0127] It should be understood that, for the predicted deadlock loop, the solution to the predicted deadlock loop is obtained by rescheduling all autonomous vehicles in the set of autonomous vehicles at a relatively low cost, using the heuristic function value corresponding to the deadlock loop unlocking strategy, and using the sum of all heuristic function values ​​as the objective function.

[0128] It should be noted that the heuristic function value can be used to solve for the predicted unlocking strategy.

[0129] Step S108: Perform new path planning for all unmanned vehicles according to the predicted unlocking strategy, so that the unmanned vehicles can be scheduled according to the new path planning.

[0130] This embodiment obtains the scheduling status of all autonomous vehicles (RVs) in the discrete time period of the current moment. Based on the scheduling status, it determines whether there are RVs awaiting resource allocation. If so, it determines whether any RVs awaiting resource allocation have a predicted deadlock loop due to scheduling conflicts. If no RVs awaiting resource allocation have a predicted deadlock loop due to scheduling conflicts, it obtains the spatial conflict regions existing in the scheduling process of the RVs awaiting resource allocation. If RVs awaiting resource allocation have a predicted deadlock loop due to scheduling conflicts, it obtains all predicted deadlock loops that the RVs awaiting resource allocation will form. It then solves for the corresponding predicted unlocking strategies based on all predicted deadlock loops. Finally, it performs new path planning for all RVs based on the predicted unlocking strategies, enabling the RVs to be scheduled according to the new path plans. This achieves the goal of obtaining predicted unlocking strategies by solving for predicted deadlock loops and performing new path planning for RVs based on the predicted unlocking strategies, thereby enabling the RVs to be scheduled according to the new path plans.

[0131] refer to Figure 11 , Figure 11 This is a structural block diagram of the centralized control multi-unmanned vehicle dispatching system of the present invention.

[0132] The conflict acquisition module 801 is used to acquire spatial conflict areas generated during the scheduling of unmanned vehicles.

[0133] The status acquisition module 802 is used to acquire the conflict status of the spatial conflict area when there is no resource scheduling conflict between multiple vehicles in the spatial conflict area.

[0134] The strategy acquisition module 803 performs conflict resolution on the spatial conflict region based on the conflict state to obtain a conflict resolution strategy.

[0135] The centralized control module 804 centrally controls the local unmanned vehicles in the spatial conflict area according to the conflict resolution strategy, so that the local unmanned vehicles can obtain a new scheduling plan and perform scheduling according to the new scheduling plan.

[0136] This embodiment identifies spatial conflict areas; when no resource scheduling conflicts exist between multiple vehicles in the spatial conflict area, it acquires the conflict state of the spatial conflict area; it solves the conflict in the spatial conflict area based on the conflict state to obtain a conflict resolution strategy; and it centrally controls the local unmanned vehicles in the spatial conflict area according to the conflict resolution strategy, so that the local unmanned vehicles obtain a new scheduling plan and perform scheduling according to the new scheduling plan. This invention solves the conflicts generated in local spatial areas during the scheduling process of unmanned vehicles to obtain a conflict resolution strategy, enabling the local unmanned vehicles in the spatial conflict area to obtain a new scheduling plan based on the conflict resolution strategy and perform scheduling according to the new scheduling plan. Compared with existing technologies, this invention can effectively detect and resolve spatial resource conflicts, improving the collaborative scheduling efficiency of unmanned vehicles.

[0137] The various embodiments or specific implementations of the centralized control multi-unmanned vehicle dispatching system of the present invention can be referred to the above-mentioned method embodiments, and will not be repeated here.

[0138] Furthermore, this embodiment of the invention also proposes a storage medium storing a centralized control multi-unmanned vehicle scheduling program, which, when executed by a processor, implements the steps of the centralized control multi-unmanned vehicle scheduling method described above.

[0139] It should be noted that, in this document, the terms "comprising," "including," or any other variations are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0140] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0141] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention can essentially be said to contribute to the prior art in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory / random access memory, magnetic disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0142] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for centralized control of multi-unmanned vehicle scheduling, characterized in that, The method comprises the following steps: acquiring a space conflict area generated during unmanned vehicle scheduling; when there is no resource scheduling conflict between multiple vehicles in the space conflict area, acquiring a conflict state of the space conflict area; solving the conflict of the space conflict area according to the conflict state to obtain a conflict resolution strategy; controlling the local unmanned vehicles in the space conflict area according to the conflict resolution strategy, so that the local unmanned vehicles acquire a new scheduling plan and schedule according to the new scheduling plan; before the step of acquiring the conflict state of the space conflict area when there is no resource scheduling conflict between multiple vehicles in the space conflict area, the method further comprises the following steps: detecting the space conflict area and determining whether there is a new unmanned vehicle entering the space conflict area; if there is a new unmanned vehicle entering the space conflict area, determining whether there is a resource scheduling conflict between multiple vehicles in the space conflict area; if there is a resource scheduling conflict between multiple vehicles in the space conflict area, determining that the space conflict area generates a deadlock ring, and breaking the deadlock ring through a deadlock ring resolution module; before the step of detecting the space conflict area and determining whether there is a new unmanned vehicle entering the space conflict area, the method further comprises the following steps: acquiring all unmanned vehicle scheduling states on a discrete time in a current period, and determining whether there is an unmanned vehicle with to-be-allocated resources according to the unmanned vehicle scheduling states; if yes, determining whether a predicted deadlock ring is generated due to scheduling conflict for the unmanned vehicle with to-be-allocated resources; if no predicted deadlock ring is generated due to scheduling conflict for the unmanned vehicle with to-be-allocated resources, acquiring a space conflict area existing in a scheduling process of the unmanned vehicle with to-be-allocated resources.

2. The method of claim 1, wherein, The step of controlling the local unmanned vehicles in the space conflict area according to the conflict resolution strategy, so that the local unmanned vehicles acquire a new scheduling plan and schedule according to the new scheduling plan, comprises the following steps: according to the conflict resolution strategy, calculating a driving speed value of the local unmanned vehicles in the space conflict area when the conflict is resolved through a centralized control function in real time; updating the driving speed of the local unmanned vehicles according to the driving speed value, so that the local unmanned vehicles schedule according to a new driving speed.

3. The method of claim 1, wherein, Before the step of acquiring all unmanned vehicle scheduling states on a discrete time in a current period, and determining whether there is an unmanned vehicle with to-be-allocated resources according to the unmanned vehicle scheduling states, the method further comprises the following steps: discretizing continuous scheduling time according to a preset scheduling model of an unmanned vehicle, to acquire a periodical discrete time with equal time; planning the driving speed and target scheduling position of the unmanned vehicle according to the periodical discrete time, and generating all the unmanned vehicle scheduling states.

4. The method of claim 1, wherein, After the step of acquiring a space conflict area existing in a scheduling process of the unmanned vehicle with to-be-allocated resources when no predicted deadlock ring is generated due to scheduling conflict for the unmanned vehicle with to-be-allocated resources, the method further comprises the following steps: If the unmanned vehicles of the to-be-allocated resources generate a predicted deadlock ring due to scheduling conflicts, all predicted deadlock rings to be formed by the unmanned vehicles of the to-be-allocated resources are obtained; A corresponding predicted unlocking strategy is solved according to the all predicted deadlock rings; New path planning is performed on all unmanned vehicles according to the predicted unlocking strategy, so that the unmanned vehicles are scheduled according to the new path planning.

5. The method of claim 1, wherein, If the space conflict region has resource scheduling conflicts among multiple vehicles, the step of determining that the space conflict region generates a deadlock ring and resolving the deadlock ring by a deadlock ring resolution module, comprises: When it is determined that the space conflict region has a deadlock ring, it is determined whether the deadlock resolution module can generate a strategy solution for resolving the deadlock ring; If yes, the deadlock ring is resolved according to the strategy solution.

6. A centralized multi-unmanned vehicle dispatching system, characterized in that, The system is used to implement the centralized control multi-unmanned vehicle scheduling method of any one of claims 1-5, and the system comprises: A conflict acquisition module is configured to acquire a space conflict region generated when unmanned vehicles are scheduled; A state acquisition module is configured to acquire a conflict state of the space conflict region when the space conflict region does not have resource scheduling conflicts among multiple vehicles; A strategy acquisition module is configured to perform conflict solving on the space conflict region according to the conflict state to obtain a conflict resolution strategy; A centralized control module is configured to perform centralized control on local unmanned vehicles of the space conflict region according to the conflict resolution strategy, so that the local unmanned vehicles obtain new scheduling planning and are scheduled according to the new scheduling planning.

7. A centralized multi-unmanned vehicle dispatching device, characterized by, The device comprises a memory, a processor, and a centralized control multi-unmanned vehicle scheduling program stored on the memory and executable on the processor, and the centralized control multi-unmanned vehicle scheduling program is configured to implement the steps of the centralized control multi-unmanned vehicle scheduling method of any one of claims 1-5.

8. A storage medium, characterized by The storage medium stores a centralized control multi-unmanned vehicle scheduling program, and the centralized control multi-unmanned vehicle scheduling program is executed by the processor to implement the steps of the centralized control multi-unmanned vehicle scheduling method of any one of claims 1-5.

Images