A path planning method for unmanned vehicle and unmanned aerial vehicle cooperation

Abstract

The application discloses a path planning method for cooperation of an unmanned vehicle and an unmanned aerial vehicle. The method comprises the following steps: acquiring a set of target points to be detected of the unmanned aerial vehicle and selecting a set of candidate parking points of the unmanned vehicle; taking a set target function as an optimization target, solving a planning solution of a vehicle-aircraft cooperative inspection path planning model to determine feasible target points and parking points, wherein in the process of solving the planning solution of the vehicle-aircraft cooperative inspection path planning model, driving time of the unmanned vehicle for completing an inspection task, waiting time of the unmanned vehicle and charging time required by the unmanned aerial vehicle are considered. The application can realize cooperative planning of the unmanned vehicle and the unmanned aerial vehicle, has high solving efficiency and improves the ability of the unmanned vehicle and the unmanned aerial vehicle for cooperatively performing an inspection task in a joint dynamic mode.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of path planning, and more particularly to a path planning method for cooperation between an unmanned vehicle and an unmanned aerial vehicle. BACKGROUND

[0002] With the rapid development of urbanization, manual inspection cannot meet the needs of modern urban inspection. In recent years, with the development of unmanned technology, unmanned aerial vehicles play an increasingly important role in search and inspection. However, due to the limited battery capacity of unmanned aerial vehicles, they cannot perform inspection tasks for a long time or over a long distance, which makes it difficult to adapt to complex inspection tasks. In order to solve the problems of short endurance time and weak long-distance maneuverability of unmanned aerial vehicles, unmanned aerial vehicles and unmanned vehicles can be used to perform joint inspection tasks in a cooperative manner. For example, an unmanned vehicle can be used as a long-distance ground mobile platform to carry an unmanned aerial vehicle, and the unmanned aerial vehicle can be replaced or charged to be reused, which can effectively improve the adaptability and efficiency of the unmanned system in performing target inspection.

[0003] In order to realize the autonomous cooperation of unmanned vehicles and unmanned aerial vehicles, the running trajectories of the unmanned vehicles and the unmanned aerial vehicles need to be cooperatively planned. For example, patent publication CN113723804A discloses a vehicle-aerial vehicle cooperative distribution method and system considering multiple aerial vehicle stations. The method includes: randomly generating a vehicle-aerial vehicle cooperative distribution scheme to form a to-be-optimized scheme; taking the to-be-optimized scheme as a historical optimal scheme and a current optimal scheme; determining whether the iteration number is greater than or equal to a preset value; in the case where the iteration number is less than the preset value, performing a destruction operation and an insertion operation on the to-be-optimized scheme to form a corresponding to-be-updated scheme; determining whether the to-be-updated scheme is better than the historical optimal scheme; in the case where the to-be-updated scheme is better than the historical optimal scheme, replacing the historical optimal scheme and the current optimal scheme with the to-be-updated scheme; in the case where the to-be-updated scheme is worse than the historical optimal scheme, updating the historical optimal scheme and the current optimal scheme based on a simulated annealing criterion; in the case where the current iteration number is greater than or equal to the preset value, taking the historical optimal scheme as the final vehicle-aerial vehicle cooperative distribution scheme. The method cooperatively distributes the unmanned aerial vehicles to the customer points by using the vehicles to carry the unmanned aerial vehicles, and the unmanned aerial vehicles to distribute, without moving the vehicles, waiting for the unmanned aerial vehicles to return. This is not a real vehicle-aerial vehicle cooperative movement, and the unmanned aerial vehicles only consider one customer point. In the inspection problem, such a method increases the energy consumption and time of inspection.

[0004] Patent publication CN113705982A provides a scheduling decision method for vehicle-machine cooperative power inspection. The method includes: obtaining the device parameters of the inspection task and the executable task; job area division, using an improved K-means clustering algorithm to cluster all the to-be-inspected towers, and each cluster generated by clustering is a job area; parking point site selection of each job area; inspection vehicle driving path planning, to determine the shortest driving path of the inspection vehicle; and importing the calculated inspection vehicle parking point and driving path into the power inspection scheduling system. In this method, the unmanned aerial vehicle starts from the parking point, inspects and then returns to the same parking point, without considering the simultaneous movement of the vehicle and the machine.

[0005] Patent publication CN113985912A provides a path planning method and system for vehicle and unmanned aerial vehicle cooperative inspection. The scheme first obtains relevant parameters in the vehicle-machine cooperative inspection process; then presets the vehicle-machine cooperative inspection constraint condition, and based on the relevant parameters, constructs a vehicle-machine cooperative inspection path planning model with the shortest total time as the objective function when the unmanned aerial vehicle inspects all target points and reaches the terminal point; and uses CPLEX solver to solve the vehicle-machine cooperative inspection path planning model to obtain the optimal planning scheme of the vehicle-machine cooperative inspection path. The alternative parking point of this method is given in advance, which is not reasonable and flexible. The model is solved by CPLEX solver, which has low solving efficiency, and it is specified that the vehicle can only wait for the unmanned aerial vehicle at the parking point, thereby limiting the application scenarios.

[0006] Through analysis, the existing technology mainly has the following defects:

[0007] 1) When planning the path of the unmanned aerial vehicle, the parking point of the unmanned vehicle is not flexible and reasonable. The existing technology generally uses fixed unmanned vehicle parking points or pre-defined alternative unmanned vehicle parking points. For the method of fixed unmanned vehicle parking point, if the unmanned aerial vehicle plans the path of the unmanned aerial vehicle with the fixed unmanned vehicle parking point as the return point, it will cause the unmanned aerial vehicle to return to the parking point on the original road after detecting the target point in front, increasing the inspection time. For the method of pre-defined alternative unmanned vehicle parking point, the alternative parking point of the unmanned vehicle is not flexible and reasonable, which leads to the inability to realize the efficient dynamic cooperation of the unmanned aerial vehicle and the unmanned vehicle.

[0008] 2) The existing technology uses CPLEX solver or genetic algorithm to solve the model, and the solution form of path planning and parking point planning is complicated, the solving time is long, and the speed is slow.

[0009] 3) The existing technology only considers the situation that the unmanned vehicle waits in place or arrives at the parking point in advance to wait for the unmanned aerial vehicle, which limits the application range. SUMMARY

[0010] The application aims to overcome the defects of the prior art, and provides a path planning method for unmanned vehicles in cooperation with unmanned aerial vehicles, which comprises the following steps:

[0011] Obtaining a set of target points to be inspected of the unmanned aerial vehicle and selecting a set of candidate parking points of the unmanned vehicle;

[0012] Taking a set target function as an optimization target, a planning solution of a vehicle-aerial vehicle cooperative inspection path planning model is solved to determine feasible target points and parking points.

[0013] In the process of solving the planning solution of the vehicle-aerial vehicle cooperative inspection path planning model, the driving time of the unmanned vehicle for completing the inspection task, the waiting time of the unmanned vehicle and the charging time required by the unmanned aerial vehicle are considered.

[0014] In one embodiment, the target function is expressed as:

[0015] min T=t ugv +Δt+Δt c

[0016] t ugv =d ugv / v ugv

[0017] Wherein, d ugv represents the driving distance of the unmanned vehicle from the starting point to the ending point; v ugv represents the driving speed of the unmanned vehicle; t ugv represents the driving time of the unmanned vehicle from the starting point to the ending point after inspecting all target points; Δt represents the waiting time of the unmanned vehicle at the parking point; Δt c represents the battery replacement time or charging time required by the unmanned aerial vehicle; and T represents the total time consumed by the unmanned vehicle and the unmanned aerial vehicle from the starting point to the ending point after inspecting all target points.

[0018] In one embodiment, the candidate parking points of the unmanned vehicle are selected according to the following steps:

[0019] The roads in the road network are divided into road segments with the same interval by using the equal distance scatter method, the coordinates of each discrete point are obtained and stored in a coordinate matrix set of parking points, and a first candidate parking point set is formed.

[0020] The nearest road point of each target point to the road network is added to the first candidate parking point set, and the first candidate parking point set is expanded into a second candidate parking point set, which is selected as the candidate parking point set.

[0021] In one embodiment, in the process of solving the planning solution of the vehicle-machine cooperative inspection path planning model, the target points are numbered by positive serial numbers, the alternative stopping points are numbered by negative serial numbers, the planning solution is a sequence composed of the numbers of the target points and the stopping points, and the unmanned aerial vehicle inspects the target points according to the ascending order of the serial numbers.

[0022] Compared with the prior art, the application has the advantages that when the unmanned vehicle and the unmanned aerial vehicle jointly perform a task (such as an inspection task requiring detection of a certain number of target points) in a certain area, the route of the unmanned aerial vehicle and the stopping points of the unmanned vehicle are reasonably planned, so that the unmanned vehicle and the unmanned aerial vehicle can dynamically cooperate; a consistent representation form of the planning solution of the path and the stopping point is proposed by flexibly and reasonably setting the alternative stopping points; and the designed dynamic path planning and joint planning method of the stopping point can realize the cooperative planning of the unmanned vehicle and the unmanned aerial vehicle without using a complex solver and optimization algorithm, has high solving efficiency, and improves the ability of the unmanned vehicle and the unmanned aerial vehicle to jointly and dynamically cooperate to perform an inspection task.

[0023] Other features and advantages of the present application will become apparent from the following detailed description of illustrative embodiments thereof, which proceeds with reference to the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0024] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the application and, together with the description, serve to explain the principles of the application.

[0025] Figure 1 is an application scenario example of the cooperation of the unmanned vehicle and the unmanned aerial vehicle according to one embodiment of the present application;

[0026] Figure 2 is a flowchart of the path planning method of the cooperation of the unmanned vehicle and the unmanned aerial vehicle according to one embodiment of the present application;

[0027] Figure 3 is a schematic diagram of the selection of the alternative stopping points of the unmanned vehicle according to one embodiment of the present application;

[0028] Figure 4 is a schematic diagram of the target points and the stopping points according to one embodiment of the present application;

[0029] Figure 5 is a schematic diagram of the cooperative movement of the unmanned vehicle and the unmanned aerial vehicle according to one embodiment of the present application;

[0030] Figure 6 is a schematic diagram of the solving process of the unmanned vehicle-machine inspection path planning model according to one embodiment of the present application;

[0031] Figure 7 is a route planning diagram of the cooperation of the unmanned aerial vehicle and the unmanned vehicle according to one embodiment of the present application. DETAILED DESCRIPTION

[0032] Various exemplary embodiments of the present application will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangements, numerical expressions, and numerical values of components and steps set forth in these embodiments are not limiting to the scope of the present application unless specifically stated otherwise.

[0033] The following description of at least one exemplary embodiment is merely exemplary in nature and is in no way intended to limit the scope of the application, its application, or uses.

[0034] Techniques, methods, and devices known to those of ordinary skill in the relevant art can not be discussed in detail herein. However, where appropriate, such techniques, methods, and devices can be viewed as part of the specification.

[0035] In all of the examples shown and discussed herein, any specific values should be interpreted as merely exemplary and not as a limitation. Thus, other examples of the exemplary embodiments can have different values.

[0036] It should be noted that like reference numerals and letters refer to like items throughout the accompanying drawings, and therefore, once an item is defined in one drawing, it need not be discussed further in subsequent drawings.

[0037] In the path planning method for cooperation between a UAV and an unmanned vehicle provided by the present application, one unmanned vehicle and one UAV are included, wherein the unmanned vehicle can carry the UAV to travel on a road network. The UAV is configured with a task carrier such as a detection device or a disinfection device according to a specific inspection task such as environmental sanitation, illegal construction, and disinfection operation.

[0038] Referring to Figure 1 In the scenario shown, a unmanned vehicle carries a UAV to visit all target points from a predefined starting point. The purpose of the cooperative path planning for the UAV and the unmanned vehicle is to find suitable paths and dynamic stopping points for the UAV and the unmanned vehicle, so that the vehicle-UAV can start from the starting point, the UAV can traverse all the target points, and in the process, when the endurance distance or time of the UAV is exhausted, the UAV can return to the unmanned vehicle for charging or battery replacement, and finally reach the end point. In the description herein, the charging operation or the battery replacement operation is collectively referred to as charging.

[0039] The UAV flies at a speed v uav The UAV flies at a speed v ugvThe unmanned vehicle can drive on the road network and continuously move for a long time (with or without the unmanned aerial vehicle). The unmanned vehicle can provide charging for the unmanned aerial vehicle or carry enough spare batteries for the unmanned aerial vehicle to replace the batteries. At the starting point of the road network, the unmanned aerial vehicle takes off from the unmanned vehicle, flies to the target point on the two sides of the road network according to the planned detection path, and directly detects and collects data from the target point as a shooting tool or a sensor. At this time, the unmanned vehicle moves to the dynamic parking point according to the planning result of the dynamic parking point. The planning path of the unmanned aerial vehicle ensures that the unmanned aerial vehicle can detect as many target points as possible under the constraint of the maximum flight range, and returns to the parking point on the road network to combine with the unmanned vehicle to replace the batteries or charge. The unmanned aerial vehicle replaces the batteries and takes off again to continue detecting the remaining target points. After all the target points in the detection area are detected, the unmanned aerial vehicle returns to the unmanned vehicle and moves to the end point.

[0040] Specifically, referring to Figure 2 The provided cooperative path planning method of the unmanned vehicle and the unmanned aerial vehicle includes the following steps:

[0041] Step S210, determining the road network and the target points of the detection task.

[0042] The road network of the detection task is obtained, and the road network is a drivable road of the unmanned vehicle, and the target points are target points located within a certain distance on both sides of the road. The certain distance refers to the maximum distance that the unmanned aerial vehicle can reach before returning to a certain point on the road network. For example, if the maximum flight distance of the unmanned aerial vehicle is 2R, the certain distance refers to R.

[0043] In an embodiment, the energy constraint of the unmanned aerial vehicle is modeled as the maximum distance R that the unmanned aerial vehicle can travel back and forth with a full battery. Because the flight radius of a small rotor unmanned aerial vehicle is several kilometers, and the road network in the city is relatively dense, it can be considered that all the target points in the city environment are within the detectable range of the unmanned vehicle-unmanned aerial vehicle.

[0044] Step S220: Discretize the path and select the alternative road network parking points.

[0045] The road network in the actual environment is complex, and not every road is a straight line. Some roads are curved and changeable, and the selection of the parking point for the vehicle-machine cooperation is particularly important. Due to the complexity of the road network, it is difficult to use a continuous function to represent. By discretizing the path into sequentially connected points, it is easy to quickly solve the planning model subsequently, the calculation result is convenient to store, and it is easy to extend.

[0046] In one embodiment, the road is divided into road segments with the same width (i.e. interval) by equidistant discretization, and the number of road segments k can be determined according to actual conditions. Assuming that the length of each road segment after discretization is d, the coordinates of each discrete point are stored in the coordinate matrix set M' of the stop point h′×2 , where h' is the number of discrete points.

[0047] Preferably, the road point with the shortest distance from each target point to the road is further taken as an alternative road network stop point and numbered to obtain an alternative stop point set. The UAV only takes off and lands at the stop point in the road network.

[0048] Specifically, a set of stop points is added in the coordinate matrix M' of the stop point h′×2 , i.e. the nearest road point of the target point to the road network is taken as a stop point and added to the alternative stop point set of the UAV, i.e. the intersection of the target point and the perpendicular line of the road is expanded into the coordinate matrix M of the stop point h×2 , where h is the number of discrete points (including the expanded stop points). The advantage of this design is that when the distance of an individual target point v j is very close to the flight radius R of the UAV, there may be no stop point in the selected stop point set M' that the UAV can return within the limited endurance range, and the problem can be solved after a new alternative stop point set M is formed.

[0049] As shown in Figure 3 , in the case of a road network with a curved and variable road, a tangent line l1 of the road is drawn outside the road, a perpendicular line l2 of the tangent line l1 passing through the target point, and the intersection of the tangent line l1 and the perpendicular line l2 is the nearest point m of the target point to the road network of the UAV. If the road network road corresponding to the target point is a straight line, a perpendicular line l2 of the road is directly drawn through the target point, and the intersection of the road and the perpendicular line l2 is the nearest point m of the target point to the road network of the UAV. The point m is added to the alternative stop point set of the UAV to form M.

[0050] In step S230, the target points and the alternative stop points are sorted.

[0051] The target points on both sides of the road network are numbered, for example, the target points are numbered in sequence in the direction of the road from the starting point, obtaining a sequence of target points, such as V = {1, 2,..., n} representing a set of all target points, i.e. there are n target points.

[0052] The stop points in the alternative stop point set M are numbered, and in order to distinguish from the target points, the number is multiplied by -1 to obtain M = {-1, -2,..., -h}.

[0053] By this way of marking, the positive number indicates the target point on both sides of the road network, and the negative number indicates the stop point on the road, so that the target point and the stop point can be effectively distinguished. Figure 4 Fig. 1 is a schematic diagram of target points and stop points.

[0054] In step S240, a vehicle-UAV cooperative inspection path planning model is constructed, and a heuristic search method is used to obtain a planning solution of the vehicle-UAV cooperative inspection path.

[0055] In this step, according to the actual constraints of the vehicle and the UAV, a heuristic search method is used to obtain a planning solution of the vehicle-UAV cooperative inspection path. The planning solution is in the form of a sequence of numbers of target points and stop points.

[0056] In the prior art, the form of the solution is usually in the form of a matrix in terms of storage and representation. This method has a large amount of data storage, has a great influence on the speed of model solving, and also increases the requirements for model equipment and solvers. There are also methods that use the coordinates of the numbers, i.e. the numbers of each point, to represent, but the target points and the stop points are stored and represented separately. This representation is not simple and effective.

[0057] In an embodiment of the present application, a simple and effective storage and solution form is adopted, i.e. a sequence of numbers of target points and stop points. Among them, the positive sequence numbers such as 1, 2, 3... represent the inspection target points, and the negative sequence numbers such as -1, -2, -3... represent the stop points, such as Figure 5 As shown in the movement schematic diagram of the UAV and the vehicle cooperation, the storage and solution form can be represented as [-1, 1, -2, -3, 2, -3, -5, 3, 4, -7, 5, -8]. The solution form of the vehicle-UAV cooperative planning only needs a group of numbers to simply and effectively represent the planning result of the vehicle-UAV cooperative operation, which is beneficial to the judgment and calculation of the charging or battery replacement time of the UAV.

[0058] In the sequence of planning solutions, the first negative number and the last negative number are removed, and the charging or battery replacement time (or collectively referred to as charging time) of the UAV is judged and calculated between the other negative numbers. This is because the first negative number and the last negative number represent the first take-off point and the last landing point respectively. Since the UAV is in a full power state at the first take-off point, and the UAV does not need to take off after completing the inspection task at the last landing point, the charging or battery replacement time does not need to be considered at this time.

[0059] The goal of path planning is to maximize the inspection task within the UAV range and minimize the inspection task time.

[0060] For example, the inspection target points in the target point set V are sorted according to the corresponding road network segments, and the UAV inspects in ascending order of the serial number, which can ensure that the UAV detects the target points from near to far, prevents backtracking, and reduces the task time. In addition, it can also prevent the UAV path from forming a loop and prevent the UAV flight path from forming a loop.

[0061] The vehicle-machine cooperative inspection path planning model can be described as follows: considering the battery replacement or charging time of the UAV and the waiting time of the UAV or the vehicle, in a vehicle-machine cooperative manner, the total time from the start point to the end point after inspecting all the target points is as short as possible.

[0062] In one embodiment, the objective function of the vehicle-machine cooperative inspection path planning model is represented as:

[0063] min T=t ugv +Δt+Δt c (1)

[0064] t ugv =d ugv / v ugv (2)

[0065] wherein d ugv represents the driving distance of the vehicle from the start point to the end point; v ugv represents the driving speed of the vehicle; t ugv represents the driving time of the vehicle from the start point to the end point after inspecting all the target points; Δt represents the time of the vehicle waiting for the UAV at the stop point; Δt c represents the battery replacement or charging time required by the UAV; and T represents the total time of the vehicle and the UAV from the start point to the end point after inspecting all the target points.

[0066] Figure 6 is a schematic diagram of the solution process of the vehicle-UAV cooperative planning, which specifically includes the following steps:

[0067] Step S0, determine the stop point set M and the target point set V.

[0068] Step S1, take off from a stop point m i , and determine whether it can reach the next unvisited target point v j , that is:

[0069]

[0070] wherein d i represents the distance from the stop point m j to the target point v i .

[0071] If the judgment result of step S1 is yes, then go to step S2:

[0072] Step S2: The drone is at the stop point m. i Take off and visit target point v j , and then judge that the UAV is at the stop point m i Take off and visit target point v j After that, can we continue to reach the next unvisited target point v? j+1 ,Right now:

[0073]

[0074] Repeat step S2 until no more target points can be visited within the range of the UAV, and save the target points that the UAV can visit.

[0075] If the result of step S1 is not satisfied, then go to step S3:

[0076] Step S3: The unmanned vehicle carrying the drone arrives at the next stop m i+1 , return to step S1 until the drone is at the stop point m i+l Take off and reach the next unvisited target point v j , and stop point m i+l As the take-off point m i , then execute step S2.

[0077] Step S4, determine whether the drone is from the take-off point m i After taking off and visiting the target point, returning to the unmanned vehicle, the range of the drone must be less than the maximum flight distance of the drone, 2R.

[0078] Select the last destination point v of the voyage j+k The corresponding road network shortest distance stop m i+l As the landing point of the drone's flight, that is:

[0079]

[0080] If step S4 cannot be satisfied, then execute step S5:

[0081] Step S5: The target point visited by the UAV is reduced by one, and the UAV returns to the previous target point v j+k-1 As the last target point of the UAV's voyage, return to step S4.

[0082] Until there is no accessible target point in the drone's range, the unmanned vehicle will carry the drone to the next stop m i+1 , return to step S1.

[0083] If step S4 can be met, then step S6 is performed:

[0084] Step S6, select a feasible stop point;

[0085] The stop point returned by the UAV is selected one by one in the front, that is, the UAV returns to the next stop point, the next stop point m i+l+1 as the landing point of the UAV's voyage. Determine whether the UAV's voyage satisfies less than the maximum flight distance of the UAV 2R.

[0086] Repeat the above steps until the judgment condition cannot be met.

[0087] The stop point returned by the UAV is selected one by one in the back, that is, the UAV returns to the previous stop point, the previous stop point m i+l-1 as the landing point of the UAV's voyage. Determine whether the UAV's voyage satisfies less than the maximum flight distance of the UAV 2R.

[0088] Repeat the above steps until the judgment condition cannot be met.

[0089] Sort the feasible stop points in ascending order according to the front order to form a feasible stop point set M'', and select the first feasible stop point as the meeting point.

[0090] Step S7, determine whether the unmanned vehicle and the UAV can meet.

[0091] From the largest stop point as the landing point of the UAV's voyage m i+l′ , determine the time for the unmanned vehicle to reach the landing point m i+l′ and the time for the UAV to take off from the stop point m i visit all target points of the voyage and return to the stop point m i+l′ .

[0092]

[0093] t ugv = d ugv / v ugv (7)

[0094] t uav = d uav / v uav (8)

[0095] There are two cases, one is that the unmanned vehicle arrives first and waits for the UAV; the second is that the UAV arrives first and waits for the unmanned vehicle.

[0096] (A) The unmanned vehicle arrives first and waits for the UAV

[0097] Need to determine whether the time for the unmanned vehicle to reach the landing point m i+l′ is less than the time for the UAV to take off from the stop point mi t i+l′ flight time of the UAV from the stop point m

[0098] t ugv flight time of the UAV from the stop point m uav (9)

[0099] t uav flight time of the UAV from the stop point m ugv (10)

[0100] (B) the UAV arrives first and waits for the UAV

[0101] In the case that the UAV arrives first, it is necessary to consider whether the UAV can arrive at the stop point to meet the UAV before the energy of the UAV is exhausted.

[0102] It is necessary to determine whether the time for the UAV to arrive at the stop point m i+l′ is less than the time for the UAV to fly from the stop point m i to visit all the target points of the route and return to the stop point m 耗 plus the hovering time of the UAV, i.e., the maximum flight time t 耗 of the UAV under the energy consumption:

[0103] t uav (11)

[0104] t ugv flight time of the UAV from the stop point m 耗 (12)

[0105] Step S8, if neither (A) nor (B) in step S7 is satisfied, i.e., the UAV and the UAV cannot meet, then a stop point m i+l′-1 is selected from the set of feasible stop points M" backward, and the above step S7 is repeated to select a stop point at which the UAV and the UAV can meet.

[0106] If there is no stop point in the set of feasible stop points M" at which the UAV and the UAV can meet, the number of target points visited by the UAV route is reduced by one, and the process returns to step S4.

[0107] If there is no target point that can be visited by the UAV route, the UAV carried by the UAV arrives at the next stop point m i+1 , and the process returns to the above step S1.

[0108] If either (A) or (B) in step S7 is satisfied, it is considered that the stop point meets the requirements, i.e., the UAV and the UAV can meet.

[0109] Step S9, it is determined whether the target points in the region have been visited.

[0110] i.e., the last target point v jwhether the subscript j of the target point is equal to n.

[0111] If the inspection is not completed, the unmanned vehicle carries the unmanned aerial vehicle to the next unmanned aerial vehicle take-off point, the unmanned aerial vehicle takes off from the next parking point in the target area, and then repeats the above steps, starting from step S1, re-visits the unvisited target points, until all target points in the region are completely inspected.

[0112] That is, the unmanned aerial vehicle travels to the last target point v j The subscript j of the target point is equal to n.

[0113] In addition, in the process of obtaining the planning solution, the judgment and calculation of the time of charging or replacing the battery of the unmanned aerial vehicle are also involved.

[0114] As shown in Fig. Figure 5 , a schematic diagram of the cooperative motion of the unmanned vehicle and the unmanned aerial vehicle. For a set of numbers containing target point and parking point numbers, it is divided into two cases, one is the charging and battery replacement time between two consecutive negative numbers, and the other is the charging and battery replacement time of a single negative number.

[0115] 1) Two consecutive negative numbers

[0116] As in solution-2, -3 or -3, -5 in Fig. Figure 5 , the general form is represented by i, i+1, and the case of two consecutive negative numbers represents that the unmanned aerial vehicle lands back to the unmanned aerial vehicle at the parking point m i , and then the unmanned vehicle carries the unmanned aerial vehicle to the parking point m i+l , and the unmanned aerial vehicle takes off from the parking point m i+l .

[0117] The time when the unmanned aerial vehicle completes the charging and battery replacement operation is considered as t c , at which time the time of the unmanned vehicle traveling from the parking point m i to the parking point m i+l is compared with the charging and battery replacement time t c , and the time of the unmanned vehicle traveling from the parking point m i to the parking point m i+l :

[0118]

[0119] When t i,i+l ≥ t c , the unmanned aerial vehicle can complete the battery replacement or charging operation during the travel of the unmanned vehicle;

[0120] When t i,i+l < t cAt this time, the unmanned aerial vehicle cannot complete the battery replacement or charging operation during the driving of the unmanned vehicle, and the unmanned aerial vehicle needs to wait for a period of time to complete the battery replacement or charging operation, that is, the time of the unmanned aerial vehicle that is truly needed for charging and replacing the battery:

[0121] Delta t c = t c -t i,i+l (14)

[0122] 2) Single negative sequence number;

[0123] As in the case of the solution-7 in the Figure 5 , the single negative sequence number indicates that the unmanned aerial vehicle lands back to the unmanned aerial vehicle after the unmanned aerial vehicle lands at the parking point m i , completes the battery replacement or charging operation, and the unmanned aerial vehicle still takes off from the parking point m i , and the time of the unmanned aerial vehicle that is truly needed for charging and replacing the battery is:

[0124] Delta t c = t c (15)

[0125] In order to further verify the effect of the present application, a simulation experiment is carried out. Under the simulation condition, it is assumed that one patrol unmanned vehicle carries one unmanned aerial vehicle to carry out patrol operation on part of the area under the jurisdiction of a city, and the coordinates of all target points and road networks to be inspected in the area are known.

[0126] Figure 7 The cooperative planning route map of the unmanned aerial vehicle and the unmanned vehicle. Five target points are set, the maximum flight distance of the unmanned aerial vehicle is set to 2000 meters, the road section is set to 5000 meters, the flight speed of the unmanned aerial vehicle is set to 2 meters per second, and the speed of the unmanned vehicle is set to 1 meter per second. From the cooperative planning route map, it can be seen that the routes of the unmanned aerial vehicle and the unmanned vehicle are reasonable.

[0127] In summary, the technical effects of the present application mainly embody in the following aspects:

[0128] 1) Select the candidate parking point set in combination with the actual environment and the patrol requirements. In order to prevent the distance of individual target points from being very close to the flight radius of the unmanned aerial vehicle, the nearest point of the target point to the road network of the unmanned vehicle is added to the candidate parking point set of the unmanned vehicle, and the road section is discretized into appropriate points by using the equal distance scattering method, and the parking points are reasonably and comprehensively planned.

[0129] 2) According to the given target point position and the road network of the inspected area, the points corresponding to the shortest distance from the target point to the road are sorted according to the driving direction of the unmanned vehicle, and the parking points are also sorted. When the unmanned aerial vehicle inspects, the sequence number is ascending, which can prevent the unmanned aerial vehicle path from forming a loop, prevent the unmanned vehicle from turning around on the road to meet the unmanned aerial vehicle and affect the traffic situation on the road, reduce the energy consumption and time of the inspection, and improve the efficiency of the vehicle-machine cooperative inspection task.

[0130] 3) According to the actual constraints of the vehicle-machine cooperative inspection task, the heuristic search method is used to consider two cases of the unmanned vehicle waiting for the unmanned aerial vehicle and the unmanned aerial vehicle energy consumption constraint, and the time of the unmanned aerial vehicle charging or replacing the battery, and maximize the inspection task within the flight range of the unmanned aerial vehicle, so that the unmanned vehicle and the unmanned aerial vehicle can dynamically cooperate, reduce the task execution time, realize efficient vehicle-machine cooperative movement, and be closer to the real environment.

[0131] 4) A simple and effective storage solution is constructed, for example, using a positive sequence number to represent an inspection target point and a negative sequence number to represent a parking point, and the time of the unmanned aerial vehicle charging or replacing the battery is calculated on the storage solution, which reduces the complexity of the model, is more simple and efficient, has better calculation efficiency, and improves the efficiency of the vehicle-machine cooperative inspection task.

[0132] The present application can be a system, a method and / or a computer program product. The computer program product can include a computer readable storage medium having computer readable program instructions stored therein for causing a processor to implement various aspects of the present application.

[0133] The computer readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. The computer readable storage medium can be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the above. More specific examples (a non-exhaustive list) of the computer readable storage medium include a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punched card or a concave-convex structure in a slot, and any suitable combination of the above. The computer readable storage medium used herein is not to be interpreted as a transitory signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (for example, an optical pulse through an optical fiber cable), or an electrical signal transmitted through a wire.

[0134] Computer readable program instructions described herein can be downloaded to respective computing / processing devices from a computer readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and / or a wireless network. The network can comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and / or edge servers. A network adapter card or network interface in each computing / processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing / processing device.

[0135] Computer readable program instructions for carrying out operations of the present application can be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions can execute entirely on the user's computing device, partly on the user's computing device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device or entirely on the remote computing device or server. In the latter scenario, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computing device, for example, through the Internet using an Internet Service Provider. In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGA), or programmable logic arrays (PLA) can execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present application.

[0136] The computer readable program instructions can also be loaded onto a computing / processing device, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computing / processing device, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computing / processing device, other programmable apparatus, or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0137] These computer readable program instructions can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer readable program instructions can also be stored in a computer readable storage medium that can include a non-transitory computer readable storage medium that can be a computer- readable storage medium having no data, programs, program modules, e.g., instructions for operation, or digital content stored thereon or therein for a short time or not at all. The computer readable storage medium can also have instructions stored thereon or therein which may

[0138] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process, such that the instructions which execute on the computer, other programmable data processing apparatus, or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0139] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process, such that the instructions which execute on the computer, other programmable data processing apparatus, or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0140] Having described various embodiments of the application, it is to be understood that the above description is meant to be illustrative only and not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art, without departing from the scope and spirit of the described embodiments. The selection of terms to be used in the description is intended to best explain the principles of the embodiments, the practical application, or technical improvement over the prior art, or to enable others skilled in the art to understand the embodiments disclosed herein. The scope of the application is defined by the claims appended hereto.

Claims

1. A method for path planning of unmanned vehicle and unmanned aerial vehicle, comprising the following steps: obtaining a set of target points to be inspected by the unmanned aerial vehicle and selecting a set of candidate parking points of the unmanned vehicle; solving a planning solution of a vehicle-aerial vehicle cooperative inspection path planning model with a set target function as an optimization target to determine feasible target points and parking points; wherein, in the process of solving the planning solution of the vehicle-aerial vehicle cooperative inspection path planning model, the driving time of the unmanned vehicle for completing the inspection task, the waiting time of the unmanned vehicle and the charging time required by the unmanned aerial vehicle are considered; wherein, the candidate parking points of the unmanned vehicle are selected according to the following steps: discretizing the roads in the road network into road segments with the same interval by using the equal distance scatter method, obtaining the coordinates of each discrete point and storing them in a coordinate matrix set of parking points to form a first set of candidate parking points; adding the nearest road points of each target point to the road network to the first set of candidate parking points to expand into a second set of candidate parking points, which is the selected set of candidate parking points; wherein, the nearest road points of each target point to the road network are determined according to the following steps: for the case of road bending, drawing a tangent line l1 of the road outside the road, drawing a perpendicular line l2 of the tangent line l1 through the corresponding target point, and taking the intersection point of l1 and l2 as the nearest road point of the target point to the road network; for the case of straight road, drawing a perpendicular line l2 of the road through the target point, and taking the intersection point of the road and the perpendicular line l2 as the nearest road point of the target point to the road network.

2. The method of claim 1, wherein, The target function is expressed as: minT = t ugv +△t+△t c t ugv = d ugv / v ugv Wherein, d ugv represents the driving distance of the unmanned vehicle from the starting point to the ending point; v ugv represents the driving speed of the unmanned vehicle; t ugv represents the driving time of the unmanned vehicle from the starting point to the ending point after inspecting all target points; Δt represents the time of the unmanned vehicle waiting for the unmanned aerial vehicle at the stop point; Δt c represents the battery replacement time or charging time required by the unmanned aerial vehicle; T represents the total time consumed by the unmanned vehicle and the unmanned aerial vehicle from the starting point to the ending point after inspecting all target points.

3. The method of claim 1, wherein, in the process of solving the planning solution of the vehicle-aerial vehicle cooperative inspection path planning model, the target points are numbered with positive serial numbers and the candidate parking points are numbered with negative serial numbers, the planning solution is a sequence composed of the numbers of the target points and the parking points, and the unmanned aerial vehicle inspects the target points in ascending order of serial numbers.

4. The method of claim 3, wherein, in the process of solving the planning solution of the vehicle-aerial vehicle cooperative inspection path planning model, the feasible parking points are determined by judging whether the unmanned vehicle and the unmanned aerial vehicle can converge, comprising the following steps: for the case that the unmanned vehicle arrives at the parking point first and waits for the unmanned aerial vehicle: determining whether the time for the unmanned vehicle to reach the stop point m i+l′ is less than the time for the unmanned aerial vehicle to visit all the target points from the stop point m i and return to the stop point m i+l′ ; for the case that the unmanned aerial vehicle arrives at the parking point first and waits for the unmanned vehicle: determining whether the unmanned vehicle arrives at the stop point m i+l′ in a time less than the maximum flight time of the unmanned aerial vehicle under energy consumption when the unmanned aerial vehicle takes off from the stop point m i ; wherein, i and i+l' represent the index of the parking point, when neither of the two cases is satisfied, it means that the unmanned vehicle and the unmanned aerial vehicle cannot converge, and when one of the two cases is satisfied, it means that the unmanned vehicle and the unmanned aerial vehicle can converge, and the corresponding parking point is taken as a feasible parking point.

5. The method of claim 3, wherein, The charging time required by the unmanned aerial vehicle is calculated according to the following steps: For the UAV to land back at the docking point m i After landing back, the unmanned vehicle carries the UAV to the docking point m i+l The UAV takes off from the docking point m i+l The case: Comparing the unmanned vehicle from the stop point m i travel to the stop point m + The time t of the l i,i+l And the charging time t c When t i,i+l ≥t c , it is judged that the unmanned aerial vehicle can complete the charging operation during the driving process of the unmanned vehicle, when t i,i+l <t c , the charging time △tc required by the unmanned aerial vehicle is: Δt c = t c - t i,i+l For the UAV to be landed at the docking point m i After landing back to the UAV, the charging operation is completed, and the UAV still needs to take off from the docking point m i The charging time △t required by the UAV in the case of taking off is: c ​ Δt c = t c wherein, i and i+l represent the index.

6. The method of claim 4, wherein, The maximum flight time of the unmanned aerial vehicle under energy consumption is expressed as: t 耗 = 2R / v uav wherein R represents the farthest flight distance of the UAV, v uav represents the flight speed of the UAV.

7. A computer readable storage medium having stored thereon a computer program, wherein, The computer program is executed by the processor to realize the steps of the method according to any one of claims 1 to 6.

8. A computer device comprising a memory and a processor, having stored on the memory a computer program capable of running on the processor, characterized in that, The processor executes the computer program to realize the steps of the method according to any one of claims 1 to 6.

Images