CN115047871A - Multi-unmanned vehicle collaborative search method, device, equipment and medium for dynamic target - Google Patents
Multi-unmanned vehicle collaborative search method, device, equipment and medium for dynamic target Download PDFInfo
- Publication number
- CN115047871A CN115047871A CN202210592312.0A CN202210592312A CN115047871A CN 115047871 A CN115047871 A CN 115047871A CN 202210592312 A CN202210592312 A CN 202210592312A CN 115047871 A CN115047871 A CN 115047871A
- Authority
- CN
- China
- Prior art keywords
- search
- information
- position information
- unmanned
- unmanned vehicle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 85
- 230000008569 process Effects 0.000 claims abstract description 27
- 230000009471 action Effects 0.000 claims abstract description 7
- 230000008859 change Effects 0.000 claims description 37
- 238000004364 calculation method Methods 0.000 claims description 20
- 238000005457 optimization Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 8
- 230000008901 benefit Effects 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 abstract description 7
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000010801 machine learning Methods 0.000 abstract description 2
- 230000036544 posture Effects 0.000 description 37
- 238000004891 communication Methods 0.000 description 13
- 238000001514 detection method Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 12
- 230000004927 fusion Effects 0.000 description 9
- 230000006870 function Effects 0.000 description 4
- 238000009792 diffusion process Methods 0.000 description 3
- 238000007499 fusion processing Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0219—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory ensuring the processing of the whole working surface
Abstract
The application relates to the technical field of artificial intelligence and machine learning, in particular to a method, a device, equipment and a medium for collaborative searching of multiple unmanned vehicles of a dynamic target, wherein the method comprises the following steps: acquiring current position information and actual posture information of a plurality of unmanned vehicles and relative position information of unmanned vehicles; calculating information entropy distribution of the dynamic target at each position in the search area according to the current position information and the actual posture information; and generating an optimal search path of each unmanned vehicle according to the information entropy distribution, the position information of the obstacles in the search area and the relative position information of the unmanned vehicles, and controlling a plurality of unmanned vehicles to execute target search actions according to the optimal search path, so that the efficient collaborative search of a multi-vehicle system on the dynamic target in a certain search area is realized. Therefore, the problems that the obstacle avoidance problem is not considered in the searching process of the related technology, the planning path is relatively simple, and the related technology is not suitable for application scenes of ground searching and the like are solved.
Description
Technical Field
The application relates to the technical field of artificial intelligence and machine learning, in particular to a method, a device, equipment and a medium for collaborative searching of multiple unmanned vehicles of a dynamic target.
Background
Collaborative search is a typical task of robot clustering in various application scenarios. On one hand, the robot cluster is adopted to execute the search task, so that the full-coverage reconnaissance of a task area can be more thoroughly realized, and the environmental information of the whole area can be obtained; on the other hand, the designated target can be searched more efficiently. Compared with the method that a single robot completes a search task, the robot cluster collaborative search is more complex, and issues which are not met in the search of a plurality of single robots are extended, wherein the problems comprise dynamic information fusion, topology control, search task allocation, collaborative path planning and the like.
The search robot which is most widely researched and relatively well-developed in application at present is an Unmanned Aerial Vehicle (UAV). However, the aerial search using UAV also has certain limitations, and the ground search using unmanned vehicles has a greater advantage than the aerial search in outdoor and most indoor search tasks with more shelter. However, the search environment faced by ground search is more complex than air search, which presents more challenges to the multi-unmanned vehicle collaborative search problem: firstly, the trafficability of a driving environment must be considered in the searching process of a vehicle, so that a large number of obstacle avoidance problems are generated; secondly, detection signals of the sensor are often shielded by surrounding obstacles in the ground searching process, and in addition, a blind area also exists in the detection of the sensor; for the vehicle with the Ackerman steering chassis structure which is most commonly used at present, the motion process of the vehicle is more limited than that of a UAV; and fourthly, the coverage area of the unmanned vehicle sensor is smaller than that of the UAV, the searching efficiency is relatively low, and therefore the movement of the target in the searching process is often not negligible.
A multi-unmanned aerial vehicle collaborative searching method under the condition of no information is provided in the related art. The method uses the unmanned aerial vehicle as an object for searching, does not consider the problem of obstacle avoidance in the searching process, is relatively simple in path planning, and is not suitable for the application scene of ground searching of multiple unmanned aerial vehicles. Although the method considers the situation that the target moves in the searching process, a specific method for predicting the target movement cannot be given, and only the performance of the proposed searching method is considered by using a dynamic target.
Disclosure of Invention
The application provides a multi-unmanned-vehicle collaborative searching method, device, equipment and medium for a dynamic target, and aims to solve the problems that the obstacle avoidance problem is not considered in the searching process of the related technology, the planned path is relatively simple, and the method is not suitable for application scenes of ground searching and the like.
The embodiment of the first aspect of the application provides a multi-unmanned vehicle collaborative search method for a dynamic target, which comprises the following steps: acquiring current position information and actual posture information of a plurality of unmanned vehicles and relative position information of unmanned vehicles; calculating information entropy distribution of the dynamic target at each position in the search area according to the current position information and the actual posture information; and generating an optimal search path of each unmanned vehicle according to the information entropy distribution, the position information of the obstacles in the search area and the relative position information of the unmanned vehicles, and controlling a plurality of unmanned vehicles to execute target search actions according to the optimal search path.
Optionally, in an embodiment of the present application, the calculating an entropy distribution of information of the dynamic object appearing at each position in the search area includes: calculating the entropy distribution change of the ideal gas in the adiabatic free expansion process in the search area; and generating information entropy distribution of the dynamic target at each position in the search area according to the entropy distribution change.
Optionally, in an embodiment of the present application, the calculating, according to the current position information and the actual posture information, an information entropy distribution of a dynamic target appearing at each position in a search area includes: calculating the change of the number of first gas molecules at each position in the search area after the gas in the last time step is freely expanded; calculating second gas molecule number changes of each position in the search area after the plurality of unmanned vehicles are searched within a time step according to the current position information and the actual posture information based on the first gas molecule number changes; and calculating the information entropy distribution of the dynamic target at each position in the search area according to the second gas molecule number and an ideal gas entropy calculation formula.
Optionally, in an embodiment of the present application, based on the change in the first number of gas molecules, calculating, according to the current position information and the actual posture information, a change in a second number of gas molecules at each position in the search area after the search of the plurality of unmanned vehicles within a time step includes: and detecting whether the allowed passing area of the search area in the last time step is in the search range of any unmanned vehicle or not according to the current position information and the actual posture information of the plurality of unmanned vehicles in the last time step, and if so, changing the number of gas molecules in the allowed passing area to zero.
Optionally, in an embodiment of the present application, generating an optimal search path for each unmanned vehicle according to the information entropy distribution, the position information of the obstacle in the search area, and the relative position information of the unmanned vehicle includes: determining a plurality of candidate search paths in the search area according to the current position information and the actual posture information of each unmanned vehicle; calculating the search yield of the unmanned vehicle after a plurality of time steps on each candidate search path according to the information entropy distribution and the position information of the obstacles in the search area; and calculating a search overlapping range of the unmanned vehicle according to the relative position information of the unmanned vehicle, and taking a candidate search path corresponding to the maximum search income as the optimal search path when the search overlapping range is less than or equal to a preset range threshold.
Optionally, in an embodiment of the present application, the calculating the search overlapping range of the unmanned vehicle according to the relative position information of the unmanned vehicle includes: and when the search overlapping range is larger than the preset range threshold value, optimizing candidate search paths of the plurality of unmanned vehicles by utilizing a multi-objective optimization algorithm with the search gain maximization as a target to generate an optimal search path of each unmanned vehicle.
The embodiment of the second aspect of the present application provides a multi-unmanned vehicle collaborative search device for a dynamic target, including: the acquisition module is used for acquiring the current position information and the actual posture information of a plurality of unmanned vehicles and the relative position information of unmanned workshops; the generating module is used for calculating information entropy distribution of the dynamic target at each position in the search area according to the current position information and the actual posture information; and the searching module is used for generating an optimal searching path of each unmanned vehicle according to the information entropy distribution, the position information of the obstacles in the searching area and the relative position information of the unmanned vehicles, and controlling the plurality of unmanned vehicles to execute target searching actions according to the optimal searching path.
Optionally, in an embodiment of the present application, the generating module is further configured to calculate an entropy distribution change during adiabatic free expansion of the ideal gas in the search area; and generating information entropy distribution of the dynamic target appearing at each position in the search area according to the entropy distribution change.
Optionally, in an embodiment of the present application, the generating module includes: the first calculation unit is used for calculating the change of the number of first gas molecules at each position in the search area after the gas in a time step is freely expanded; and the second calculation unit is used for calculating the change of the number of second gas molecules at each position in the search area after the plurality of unmanned vehicles are searched within a time step according to the current position information and the actual posture information based on the change of the number of the first gas molecules.
Optionally, in an embodiment of the present application, the second calculating unit is further configured to detect whether a permitted passage area of the search area in a last time step is within a search range of any unmanned vehicle according to current position information and actual posture information of the plurality of unmanned vehicles in the last time step, and if so, the number of gas molecules in the permitted passage area becomes zero.
Optionally, in an embodiment of the present application, the search module includes: the determining unit is used for determining a plurality of candidate search paths in the search area according to the current position information and the actual posture information of each unmanned vehicle; the third calculation unit is used for calculating the search benefits of the unmanned vehicles after a plurality of time steps on each candidate search path according to the information entropy distribution and the position information of the obstacles in the search area; and the fourth calculating unit is used for calculating the searching overlapping range of the unmanned vehicle according to the relative position information of the unmanned vehicle, and taking the candidate searching path corresponding to the maximum searching income as the optimal searching path when the searching overlapping range is smaller than or equal to a preset range threshold value.
Optionally, in an embodiment of the present application, the fourth calculating unit is further configured to optimize the candidate search paths of the multiple unmanned vehicles by using a multi-objective optimization algorithm to generate an optimal search path of each unmanned vehicle, with the search gain being maximized as a target when the search overlapping range is greater than the preset range threshold.
An embodiment of a third aspect of the present application provides an electronic device, including: the system comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to execute the multi-unmanned vehicle collaborative search method for the dynamic target according to the embodiment.
A fourth aspect of the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to execute the method for collaborative searching for multiple unmanned vehicles of a dynamic target according to the foregoing embodiment.
Therefore, the application has at least the following beneficial effects:
the information entropy distribution of the current dynamic target at each position in the whole search area is calculated and updated according to the real-time position and posture information of each unmanned vehicle, the driving path of each unmanned vehicle in the future period is calculated and planned according to the information entropy distribution of the target in the local search area around the current unmanned vehicle, the distribution condition of nearby obstacles and the positions of other nearby unmanned vehicles, and each unmanned vehicle carries out tracking driving according to the currently planned path, so that the efficient collaborative search of a multi-vehicle system on the dynamic target in a certain search area is realized. Therefore, the problems that the obstacle avoidance problem is not considered in the searching process of the related technology, the planning path is relatively simple, and the method is not suitable for application scenes of multi-ground searching and the like are solved.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The above and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flowchart of a collaborative searching method for multiple unmanned vehicles for dynamic targets according to an embodiment of the present application;
FIG. 2 is a schematic diagram illustrating the variation of the number of molecules in each cell during the expansion of a gas according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a searched vehicle with a portion of the theoretical maximum detection range being blocked according to the embodiment of the present application;
FIG. 4 is a diagram illustrating a collaborative search architecture for multiple unmanned vehicles according to an embodiment of the present application;
FIG. 5 is a schematic diagram of a search area and internal obstacle distribution according to an embodiment of the present application;
FIG. 6 is a schematic diagram of a candidate path of a searched vehicle within N time steps in the future according to an embodiment of the present application;
FIG. 7 is a schematic diagram of a two-vehicle routing result without targets with known obstacle distribution before search according to an embodiment of the present application;
fig. 8 is a schematic diagram of a two-vehicle path planning result when no target exists under the condition that the distribution of obstacles before searching is unknown according to the embodiment of the application;
FIG. 9 is a schematic diagram of a two-vehicle collaborative search process in the presence of a random moving object according to an embodiment of the present application;
FIG. 10 is an exemplary diagram of a multi-UAV collaborative search apparatus for dynamic targets in accordance with an embodiment of the present application;
fig. 11 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Description of the reference numerals: the device comprises an acquisition module-100, a generation module-200, a search module-300, a memory-1101, a processor-1102 and a communication interface-1103.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative and intended to explain the present application and should not be construed as limiting the present application.
The following describes a multi-unmanned vehicle collaborative search method, apparatus, electronic device, and storage medium for a dynamic target according to an embodiment of the present application with reference to the drawings. In order to solve the problems mentioned in the background technology center, the application provides a multi-unmanned vehicle collaborative search method for a dynamic target, in the method, information entropy distribution of the current dynamic target at each position in the whole search area is calculated and updated according to real-time position and posture information of each unmanned vehicle, each unmanned vehicle calculates and plans a running path of the own vehicle within a period of time in the future according to information entropy distribution of the target in a local search area around the current own vehicle, distribution conditions of nearby obstacles and positions of other nearby unmanned vehicles, each unmanned vehicle carries out tracking running according to the currently planned path, and efficient collaborative search of a multi-vehicle system on the dynamic target in a certain search area is achieved. Therefore, the problems that the obstacle avoidance problem is not considered in the searching process of the related technology, the planning path is relatively simple, and the method is not suitable for application scenes of multi-ground searching and the like are solved.
Fig. 1 is a schematic flow chart of a collaborative search method for multiple unmanned vehicles for a dynamic target according to an embodiment of the present application.
On the basis of the existing multi-UAV collaborative search method, aiming at the characteristics of ground search, the method for simulating and predicting the information entropy distribution of a dynamic target at each position in a search area by using the entropy distribution of the free expansion process of ideal gas is provided, and therefore, the multi-unmanned vehicle collaborative search method aiming at the dynamic target is constructed, and theoretical basis and actual reference are provided for improving the ground unmanned collaborative search efficiency.
As shown in fig. 1, the multi-unmanned vehicle collaborative search method for dynamic targets includes the following steps:
in step S101, current position information, actual posture information, and relative position information of unmanned vehicles are acquired.
In order to calculate information entropy distribution of a dynamic target appearing at each position in a search area and reasonably plan a reasonable vehicle search path, the embodiment of the application needs to acquire current position information, actual posture information and relative position information of unmanned vehicles.
In step S102, an information entropy distribution of the dynamic target appearing at each position in the search area is calculated based on the current position information and the actual posture information.
For convenience of calculation, the search area is assumed to be a two-dimensional closed area with a limited area in the embodiment of the application, and obstacles in the area are simplified into two-dimensional closed graphs. The search area needs to be subjected to discrete rasterization in advance, and the map is divided into a large number of identical square grids, so that the map boundary with a complex shape or the boundary of an obstacle can be accurately depicted. Accordingly, grids are also classified into two types: one is a grid representing an obstacle and the other is a grid representing an area where the vehicle is allowed to pass.
Discretization is also carried out on the time scale, and the minimum duration unit is considered to be one time step. In the searching process, the searching information fusion result in the past time step is updated every time a time step passes, and the searching paths in the same time length in the future are planned every time a fixed number of time steps pass until all targets are found.
Optionally, in an embodiment of the present application, calculating an entropy distribution of information of the dynamic object appearing at each position in the search area includes: calculating the entropy distribution change of the ideal gas in the adiabatic free expansion process in the search area; and generating information entropy distribution of the dynamic target appearing at each position in the search area according to the entropy distribution change.
The embodiment of the application uses the change of the entropy distribution in the ideal gas adiabatic free expansion process along with the time to calculate the change of the information entropy size of the simulated dynamic target appearing in each grid along with the time.
Optionally, in an embodiment of the present application, calculating an information entropy distribution of the dynamic target appearing at each position in the search area according to the current position information and the actual posture information includes: calculating the change of the number of first gas molecules at each position in a search area after the gas in the computational time step is freely expanded; calculating second gas molecule number changes of each position in the search area after searching of a plurality of unmanned vehicles within a time step length according to the current position information and the actual posture information based on the first gas molecule number changes; and calculating the information entropy distribution of the dynamic target at each position in the search area according to the number of the second gas molecules and an ideal gas entropy calculation formula.
Optionally, in an embodiment of the present application, calculating, based on the change in the number of first gas molecules, a change in the number of second gas molecules at each location in the search area after the search of the plurality of unmanned vehicles within a time step according to the current location information and the actual posture information, includes: and detecting whether the allowed passing area of the search area in the last time step is in the search range of any unmanned vehicle or not according to the current position information and the actual posture information of the plurality of unmanned vehicles in the last time step, and if so, changing the number of gas molecules in the allowed passing area to zero.
In the embodiment of the application, for the case that the obstacle distribution before searching is known, it is considered that at the beginning of the search, the ideal gas is isothermally and uniformly filled in the whole passing-allowed area, and the number of gas molecules in all grids representing the passing-allowed area is N 0 . After that, information entropy distribution { S ] is distributed every time step i,j (k) The updating of all the steps comprises the following steps:
step 11: the change in the number of gas molecules in each grid due to free expansion of the gas in the past time step was calculated, and as shown in FIG. 2, the gas molecule number distribution { N } which can be obtained from the last update according to equation (1) i,j (k-1) calculating to obtain the current gas molecular number distribution { N } i,j (k) And (4) dividing. Wherein the grids representing the obstacles are not affected, they together with the boundaries of the search task area form a closed boundary for free expansion of the ideal gas, and the term of summation is removed in equation (1) if it relates to the neighboring grids representing the ideal gas boundaries. In formula (1), Diff is an adjustable parameter, andthe prior dynamic target motion capability is related;
step 12: the change in the number of gas molecules in each grid due to the detection of the vehicle in the past time step is calculated. And judging whether each grid representing the passing-allowed area is currently covered by the detection range of any vehicle in the past time step according to the position and posture information of each vehicle in the past time step transmitted by each vehicle. If the grid is covered, the grid representing the passage-allowed area is considered to be vacuumized, and the number of gas molecules becomes zero. The number of gas molecules in the grid representing the obstacle is always zero;
step 13: the number of gas molecules { N ] in each grid obtained by the above calculation formula i,j (k) Calculating the information entropy size { S ] of the current target appearing in each grid according to the calculation formula (2)) of the ideal gas entropy i,j (k) And (4) dividing. In the formula (2), s 0 Is an adjustable parameter, which is equivalent to zero molecular entropy;
S i，j ＝N i,j s 0 -N i，j lnN i，j (2)
step 14: and transmitting information entropy distribution and obstacle distribution of the nearby information of each vehicle and the number of other nearby vehicles to the corresponding vehicle.
In some embodiments, for the case where the obstacle distribution before searching is unknown, it is considered that at the beginning of the search, all grids in the search area represent the allowed-to-pass area, and the ideal gas is isothermally and uniformly filled in the whole search task area, and the number of gas molecules in each grid in the area is N 0 . The updating of the information entropy distribution after each time step comprises the following steps:
step 21: step 11, the distribution of the obstacles before searching is known;
step 22: the change in the number of gas molecules in each grid due to the detection of the vehicle in the past time step is calculated. And judging whether each grid representing the passing-allowed area is currently covered by the detection range of any vehicle in the past time step according to the position and attitude information of each vehicle in the past time step transmitted by each vehicle. If the grid is covered, the grid representing the passage-allowed area is considered to be vacuumized, and the number of gas molecules becomes zero. In addition, the search information fusion module needs to additionally obtain specific environment perception information of each vehicle, and if the grid representing the passing-allowed area is detected and judged to be an obstacle, the attribute of the grid is converted into the grid representing the obstacle. The number of gas molecules in the grid representing the obstacle is always zero;
step 23: step 13, the distribution of the obstacles before searching is known;
and step 24: as well as step 14 of searching for a known distribution of obstacles.
In step S103, an optimal search path for each unmanned vehicle is generated according to the information entropy distribution, the position information of the obstacle in the search area, and the relative position information of the unmanned vehicle, and a plurality of unmanned vehicles are controlled to execute a target search action according to the optimal search path.
It can be understood that according to the embodiment of the application, the optimal search path of each unmanned vehicle is generated according to the information entropy distribution of the dynamic target appearing at each position in the search area, the position information of the obstacle in the search area and the relative position information of the unmanned vehicles, a plurality of unmanned vehicles are controlled to search the target according to the planned optimal path, the motion of the dynamic target is effectively predicted in real time, directional guidance is provided for the vehicle search, and the search efficiency of the unmanned vehicles on the dynamic target is improved.
Optionally, in an embodiment of the present application, generating an optimal search path for each unmanned vehicle according to the information entropy distribution, the position information of the obstacle in the search area, and the relative position information of the unmanned vehicle, includes: determining a plurality of candidate search paths in a search area according to the current position information and the actual posture information of each unmanned vehicle; calculating the search income of the unmanned vehicle after a plurality of time steps on each candidate search path according to the information entropy distribution and the position information of the obstacles in the search area; and calculating a search overlapping range of the unmanned vehicle according to the relative position information of the unmanned vehicle, and taking the candidate search path corresponding to the maximum search income as an optimal search path when the search overlapping range is less than or equal to a preset range threshold.
It can be understood that in most cases, the search path planning is performed by each search vehicle independently, and only when the search tasks overlap between the vehicles, the related vehicles perform joint path planning through communication. The planned route is aimed at maximizing the search efficiency and ensuring that the vehicle can avoid the obstacles to run.
If there are n in the multi-vehicle system v Vehicles for searching, 1, 2, … …, n respectively v Numbering is performed. The whole cluster shares a uniform coordinate system, and the position coordinates (x, y) and the body attitude angle of the r-th vehicle after k time steps
Are respectively provided with
And then the position state of the whole system after k time steps is set as follows:
x(k)＝{x r (k)，r＝1，2，……，n v } (3)
specifically, in the embodiment of the present application, after every N time steps, the r-th vehicle plans the search path in the future N time steps, and first needs to set a plurality of candidate paths. When k time steps (k is divided by N) currently pass, the candidate paths in the future N time steps are represented by the combination of the position and the posture of the vehicle after every time step passes in the future:
X r (k)＝{x r (k+1)，x r (k+2)，……，x r (k+N)} (4)
second, based on the current information entropy distribution { N } i,j (k) And (4) calculating the vehicle search yield after a time step on each candidate path in the future according to the formula (5). { J (x) r (k + m)), m is 1, 2, …, N }. In the formula (5), { J (x) r (k + m)), m is 1, 2, …, N } (k) is the average information entropy currently calculated from the total number of gas molecules in the entire search task area divided by the average number of gas molecules in the total number of grids in the area, as shown in FIG. 3, E (x) is r (l) For a set of grids in the effective detection range of the vehicle after a time step, E U (x (l)) is a grid set removed due to the fact that a perception signal is shielded in the maximum detection range of the vehicle theory after l time steps, and Block is an adjustable parameter used for balancing search efficiency and effectively avoiding obstacles:
if no other search vehicles exist near the vehicle, namely the possibility of overlapping with search tasks of other vehicles within N time steps in the future is low, calculating the total search income of each candidate route, and finding the route with the maximum total search income as a route planning result
Optionally, in an embodiment of the present application, calculating the search overlap range of the unmanned vehicle according to the relative position information of the unmanned vehicle includes: and when the search overlapping range is larger than the preset range threshold value, optimizing candidate search paths of the plurality of unmanned vehicles by utilizing a multi-objective optimization algorithm with the search gain maximization as a target to generate an optimal search path of each unmanned vehicle.
It can be understood that, if there are other search vehicles near the current vehicle, that is, there is a possibility that the search tasks of other vehicles overlap greatly in N time steps in the future, the related vehicles find a combination with the largest total search yield among combinations of respective candidate paths through communication as a result of path planning for multiple vehicles, and the method can be implemented by using an existing multi-objective optimization method. And tracking driving is carried out according to the planned path within N time steps, and the real-time position and posture information of the vehicle is sent.
It should be noted that, the specific optimization method adopted in the embodiment of the present application is a nash optimal iterative method, a certain time is required for an iterative calculation process of searching for a path plan, and if the calculation is started until the starting time of the planned path, the planned calculation process will tend to cause a delay of receiving the planned path by the vehicle path tracking module. Therefore, in the embodiment, the path planning is started one to two time steps ahead, and the position of each vehicle and the information entropy distribution of the search area at the starting time of the path planning must be predicted each time.
As shown in fig. 4, a framework of the collaborative searching method for multiple unmanned vehicles for dynamic targets according to the embodiment of the present application is shown, and the execution steps according to the embodiment of the present application can be implemented by multiple modules, which specifically include a search information fusion module, multiple path planning modules and a tracking driving module, where the number of the path planning modules is the same as that of the unmanned vehicles.
The search information fusion process is completed in a unique information fusion module in the multi-vehicle system, information entropy density distribution of targets appearing at all positions in a search area is maintained in a unified mode through information fusion, and the information entropy density distribution is the information entropy size in all grids after discretization of the search area. The path planning is independently completed by each search vehicle in most cases, and the related vehicles carry out joint path planning through communication only when search tasks between the vehicles are overlapped. The planned route is aimed at maximizing the search efficiency and ensuring that the vehicle can avoid the obstacles to run. The tracking driving is that a plurality of unmanned vehicles carry out tracking driving according to a planned path and send real-time position and posture information of the unmanned vehicles.
The following describes in detail a multi-unmanned vehicle collaborative search method for a dynamic target according to the present application with reference to the accompanying drawings and specific embodiments, and for convenience of understanding, the embodiments of the present application classify a search path planning and a tracking driving into one stage.
In the embodiment of the present application, the search area is a square area of 300 m × 300 m, as shown in fig. 5. The system is divided into 300 multiplied by 300 grids of 1 multiplied by 1 meter, a right-handed system plane rectangular coordinate system is established by taking the center of the grid at the leftmost lower part of a square area as the origin and taking the positive direction parallel to the lower bottom edge of the square as the right direction as the x axis, the unit is meter, and the vehicle attitude angle is considered to be 0 degree when the vehicle head points to the positive direction of the x axis. The obstacle distribution is considered to be completely known before the search is started, the specific distribution is shown as a black part in fig. 5, and the rest passable parts are shown as gray parts in fig. 5. The number n of identical unmanned search vehicles in the search area v And 2, the two chassis are in a front wheel Ackerman steering structure. When the zero time k is 0, the two vehicles start from the state coordinates (0,0,60 °) and (10,0,30 °), respectively. As shown in fig. 4, the detection range of each vehicle when no obstacle blocks the detection signal is a sector having an included angle of 60 ° and a radius of 30 m directly in front of the vehicle.
1) Search information fusion phase
The search information fusion process is completed in a unique information fusion module in the multi-vehicle system. When k is equal to 0 at the beginning of the search, the ideal gas is isothermally and uniformly filled in the whole passage-allowed area, and the number of gas molecules in all grids representing the passage-allowed area is N 0 . After that, information entropy distribution { S ] is distributed every time step i,j The updating of all the steps comprises the following steps:
inputting: position and posture of two vehicles at current time (k)
And (3) outputting: information entropy distribution and obstacle distribution near the two vehicles and whether another vehicle exists within 30 meters of straight-line distance.
The method comprises the following steps: referring to FIG. 2, the number distribution of gas molecules { N ] obtained by the previous update is shown by the following formula i,j (k-1) calculating to obtain the current gas molecular number distribution { N } i,j (k) And (4) dividing. Wherein the summed terms are removed if it relates to an adjacent grid representing an obstacle or search area boundary;
step two: according to the current respective positions and postures sent by the two vehicles
Changing the number of gas molecules of the grid in the detection range of each searched vehicle at the current moment into zero;
step three: from the number distribution of gas molecules { N }according to the formula i,j (k) Calculating the information entropy distribution (S) of the current target appearing in each grid i,j (k)}；
S i，j ＝N i，j s 0 -N i，j ln N i，j
Step four: and sending information of information entropy distribution and obstacle distribution near the two vehicles and information of whether another vehicle exists within 30 meters of the straight-line distance to the corresponding vehicle.
Empirical studies have shown that the entire simulation process is difficult to converge when the coefficient Diff exceeds about 0.1, and to further increase the diffusion rate, equation (1) can only be iteratively performed a number of times between each time step interval, which can result in a doubling of the computational time cost. Especially when the search area is divided finely, the updating calculation of the whole gas free expansion process is very slow. In order to increase the diffusion rate under the premise of reasonable calculation cost, in the embodiment, adjacent 3 × 3 grids are taken as a finite element unit, and all 3 grids in the unit are considered 2 The number of molecules within each grid is the same. And the embodiment adopts a strategy that the gas diffusion rate is gradually increased from zero.
2) Search path planning and tracking phase
The search path planning process is independently completed by two vehicles under most conditions, and the two vehicles carry out combined path planning through communication only when the straight-line distance between the two vehicles is less than 30 meters. As shown in fig. 6, it is considered that the motion of the searched vehicle in each time step may be three cases of uniform left turn, uniform right turn or uniform straight running at a 25-wheel turning angle, and the running speed is always 4 m/s. The planning of the search path in the future 3 time steps of the two vehicles after every time step of N-3 time steps comprises the following steps:
inputting: information entropy distribution and obstacle distribution near the current time (k) of the two vehicles and whether another vehicle exists within 30 meters of the straight line distance;
and (3) outputting: searching paths of the two vehicles within 3 time steps in the future and real-time positions and postures of the two vehicles in the actual tracking driving process in corresponding time.
The method comprises the following steps: enumerating possible 3 time steps of two vehicles in future respectively 3 Candidate paths, e.g. X r (k)＝{x r (k+1)，x r (k+2)，x r (k+3)}；
Step two: based on the current information entropy distribution { Ni, J (k) } and the distribution situation of the obstacles, the search income { J (x) of the vehicle after each time step in the future 3 time steps on each candidate path is calculated according to the following formula r (k+m))，m＝1，2，3}；
Step three: if the straight-line distance between the two vehicles is larger than 30 meters, the two vehicles respectively calculate the total search income of each candidate path according to the following formula, and find the path with the maximum total search income as a path planning result
Step four: if the linear distance between the two vehicles is less than 30 meters, finding a combination with the largest total search yield in the combinations of the respective candidate paths as a multi-vehicle path planning result through communication, wherein the specific optimization method adopted in the embodiment is a Nash optimal iterative method;
step five: and tracking driving is carried out by the tracking driving modules of the two vehicles within 3 time steps later according to the planned path, and the real-time position and posture information of the two vehicles is sent to the search information fusion module.
Fig. 7 and 8 show the case where there is no target in the search area, and the currently planned complete search paths of the two vehicles are obtained every 50 time steps, where the gray background in the figure reflects the distribution of the ideal gas molecule number density in the search area at that time, and darker colors represent higher molecule number densities.
Fig. 9 shows a case where a randomly moving target exists in the area, and the currently planned complete search path of two vehicles is obtained every 50 time steps until the target is found.
According to the collaborative searching method for the multiple unmanned vehicles of the dynamic target, provided by the embodiment of the application, the information entropy distribution of the current dynamic target at each position in the whole searching area is calculated and updated according to the real-time position and posture information of each unmanned vehicle, each unmanned vehicle calculates and plans the driving path of the self vehicle in a future period of time according to the information entropy distribution of the target in the local searching area around the current self vehicle, the distribution condition of nearby obstacles and the positions of other nearby unmanned vehicles, and each unmanned vehicle carries out tracking driving according to the currently planned path, so that the efficient collaborative searching of the dynamic target by a multiple vehicle system in a certain searching area is realized. Therefore, the problems that the obstacle avoidance problem is not considered in the searching process of the related technology, the planning path is relatively simple, and the method is not suitable for application scenes of multi-ground searching and the like are solved.
Next, a multi-unmanned vehicle collaborative search apparatus for a dynamic target according to an embodiment of the present application will be described with reference to the drawings.
Fig. 10 is a block diagram schematically illustrating a multi-unmanned vehicle cooperative search apparatus for dynamic targets according to an embodiment of the present application.
As shown in fig. 10, the multi-unmanned vehicle cooperative search device 10 for a dynamic target includes: an acquisition module 100, a generation module 200 and a search module 300.
The acquiring module 100 is configured to acquire current position information and actual posture information of a plurality of unmanned vehicles and relative position information of unmanned vehicles. And the generating module 200 is configured to calculate information entropy distribution of the dynamic target appearing at each position in the search area according to the current position information and the actual posture information. And the searching module 300 is configured to generate an optimal searching path for each unmanned vehicle according to the information entropy distribution, the position information of the obstacles in the searching area, and the relative position information of the unmanned vehicle, and control a plurality of unmanned vehicles to execute the target searching action according to the optimal searching path.
Optionally, in an embodiment of the present application, the generating module 200 is further configured to calculate an entropy distribution change during the adiabatic free expansion of the ideal gas in the search area; and generating information entropy distribution of the dynamic target at each position in the search area according to the entropy distribution change.
Optionally, in an embodiment of the present application, the generating module 200 includes: the first calculation unit is used for calculating the change of the number of first gas molecules at each position in the search area after the gas in the first time step expands freely; and the second calculation unit is used for calculating the second gas molecule number change of each position in the search area after the search of the plurality of unmanned vehicles within a time step length according to the current position information and the actual posture information based on the first gas molecule number change.
Optionally, in an embodiment of the present application, the second calculating unit is further configured to detect whether a passage-allowed area of the search area in the last time step is within a search range of any one unmanned vehicle according to current position information and actual posture information of multiple unmanned vehicles in the last time step, and if so, the number of gas molecules in the passage-allowed area becomes zero.
Optionally, in an embodiment of the present application, the search module 300 includes: the determining unit is used for determining a plurality of candidate search paths in the search area according to the current position information and the actual posture information of each unmanned vehicle; the third calculation unit is used for calculating the search benefits of the unmanned vehicle after a plurality of time steps on each candidate search path according to the information entropy distribution and the position information of the obstacles in the search area; and the fourth calculating unit is used for calculating the searching overlapping range of the unmanned vehicle according to the relative position information of the unmanned vehicle, and taking the candidate searching path corresponding to the maximum searching income as the optimal searching path when the searching overlapping range is less than or equal to the preset range threshold.
Optionally, in an embodiment of the present application, the fourth calculating unit is further configured to optimize the candidate search paths of the multiple unmanned vehicles by using a multi-objective optimization algorithm to generate an optimal search path for each unmanned vehicle, with a goal of maximizing the search yield when the search overlap range is greater than the preset range threshold.
It should be noted that the foregoing explanation of the embodiment of the cooperative multi-unmanned vehicle search method for a dynamic target is also applicable to the apparatus of the cooperative multi-unmanned vehicle search method for a dynamic target in this embodiment, and details are not repeated here.
According to the collaborative searching method and device for the multiple unmanned vehicles of the dynamic target, provided by the embodiment of the application, the information entropy distribution of the current dynamic target at each position in the whole searching area is calculated and updated according to the real-time position and posture information of each unmanned vehicle, each unmanned vehicle calculates and plans the driving path of the self vehicle within a period of time in the future according to the information entropy distribution of the target in the local searching area around the current self vehicle, the distribution condition of nearby obstacles and the positions of other nearby unmanned vehicles, and each unmanned vehicle carries out tracking driving according to the currently planned path, so that the efficient collaborative searching of the dynamic target by a multiple vehicle system in a certain searching area is realized. Therefore, the problems that the obstacle avoidance problem is not considered in the searching process of the related technology, the planning path is relatively simple, and the method is not suitable for application scenes of multi-ground searching and the like are solved.
Fig. 11 is a schematic structural diagram of an electronic device according to an embodiment of the present application. The electronic device may include:
a memory 1101, a processor 1102, and a computer program stored on the memory 1101 and executable on the processor 1102.
The processor 1102, when executing the program, implements the multi-unmanned vehicle collaborative search method for dynamic targets provided in the above-described embodiments.
Further, the electronic device further includes:
a communication interface 1103 for communicating between the memory 1101 and the processor 1102.
A memory 1101 for storing computer programs that are executable on the processor 1102.
The memory 1101 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
If the memory 1101, the processor 1102 and the communication interface 1103 are implemented independently, the communication interface 1103, the memory 1101 and the processor 1102 may be connected to each other through a bus and perform communication with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 11, but this is not intended to represent only one bus or type of bus.
Optionally, in a specific implementation, if the memory 1101, the processor 1102 and the communication interface 1103 are integrated on one chip, the memory 1101, the processor 1102 and the communication interface 1103 may complete communication with each other through an internal interface.
The processor 1102 may be a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement embodiments of the present Application.
The present embodiment also provides a computer-readable storage medium having stored thereon a computer program, wherein the program is configured to implement the above multi-unmanned vehicle collaborative search method for a dynamic object when executed by a processor.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or N embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or to implicitly indicate the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "N" means at least two, e.g., two, three, etc., unless explicitly defined otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more N executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present application.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
Claims (14)
1. A multi-unmanned vehicle collaborative search method for dynamic targets is characterized by comprising the following steps:
acquiring current position information and actual posture information of a plurality of unmanned vehicles and relative position information of unmanned vehicles;
calculating information entropy distribution of the dynamic target at each position in the search area according to the current position information and the actual posture information;
and generating an optimal search path of each unmanned vehicle according to the information entropy distribution, the position information of the obstacles in the search area and the relative position information of the unmanned vehicles, and controlling the plurality of unmanned vehicles to execute target search actions according to the optimal search path.
2. The method of claim 1, wherein calculating the entropy distribution of information about the occurrence of the dynamic object at each location within the search area comprises:
calculating the entropy distribution change of the ideal gas in the adiabatic free expansion process in the search area;
and generating information entropy distribution of the dynamic target at each position in the search area according to the entropy distribution change.
3. The method of claim 1, wherein calculating an information entropy distribution of occurrences of dynamic objects at locations within a search area based on the current location information and the actual pose information comprises:
calculating the change of the number of first gas molecules at each position in the search area after the gas in the last time step is freely expanded;
calculating the change of the number of second gas molecules at each position in the search area after the plurality of unmanned vehicles are searched within a time step according to the current position information and the actual posture information based on the change of the number of the first gas molecules;
and calculating the information entropy distribution of the dynamic target at each position in the search area according to the second gas molecule number and an ideal gas entropy calculation formula.
4. The method of claim 3, wherein calculating a second change in the number of gas molecules for each location within the search area after the search of the plurality of unmanned vehicles within a computational time step based on the first change in the number of gas molecules based on the current location information and the actual pose information comprises:
and detecting whether the passing-allowed area of the search area in the last time step is within the search range of any unmanned vehicle or not according to the current position information and the actual posture information of the plurality of unmanned vehicles in the last time step, and if so, changing the number of gas molecules in the passing-allowed area to zero.
5. The method according to claim 1, wherein generating an optimal search path for each unmanned vehicle according to the information entropy distribution, the position information of the obstacles in the search area, and the relative position information of the unmanned vehicles comprises:
determining a plurality of candidate search paths in the search area according to the current position information and the actual posture information of each unmanned vehicle;
calculating the search income of the unmanned vehicle after a plurality of time steps on each candidate search path according to the information entropy distribution and the position information of the obstacles in the search area;
and calculating a search overlapping range of the unmanned vehicle according to the relative position information of the unmanned vehicle, and taking a candidate search path corresponding to the maximum search income as the optimal search path when the search overlapping range is less than or equal to a preset range threshold.
6. The method of claim 5, wherein the calculating the search overlap range of the unmanned vehicle from the relative position information of the unmanned vehicle comprises:
and when the search overlapping range is larger than the preset range threshold value, optimizing candidate search paths of the plurality of unmanned vehicles by utilizing a multi-objective optimization algorithm with the search gain maximization as a target to generate an optimal search path of each unmanned vehicle.
7. A multi-unmanned vehicle collaborative search device for dynamic targets is characterized by comprising:
the acquisition module is used for acquiring the current position information and the actual posture information of a plurality of unmanned vehicles and the relative position information of unmanned workshops;
the generating module is used for calculating information entropy distribution of the dynamic target at each position in the search area according to the current position information and the actual posture information;
and the searching module is used for generating an optimal searching path of each unmanned vehicle according to the information entropy distribution, the position information of the obstacles in the searching area and the relative position information of the unmanned vehicles, and controlling the plurality of unmanned vehicles to execute target searching actions according to the optimal searching path.
8. The apparatus of claim 7, wherein the generating module is further configured to calculate a change in entropy distribution during adiabatic free expansion of the ideal gas in the search area; and generating information entropy distribution of the dynamic target appearing at each position in the search area according to the entropy distribution change.
9. The apparatus of claim 7, wherein the generating module comprises:
the first calculation unit is used for calculating the change of the number of first gas molecules at each position in the search area after the gas in a time step is freely expanded;
and a second calculation unit which calculates a second gas molecule number change of each position in the search area after the plurality of unmanned vehicles search within a time step according to the current position information and the actual posture information based on the first gas molecule number change.
10. The apparatus according to claim 9, wherein the second computing unit is further configured to detect whether a traffic-allowed area of the search area in a previous time step is within a search range of any one unmanned vehicle according to current position information and actual attitude information of the plurality of unmanned vehicles in the previous time step, and if so, the number of gas molecules in the traffic-allowed area becomes zero.
11. The apparatus of claim 7, wherein the search module comprises:
the determining unit is used for determining a plurality of candidate search paths in the search area according to the current position information and the actual posture information of each unmanned vehicle;
the third calculation unit is used for calculating the search benefits of the unmanned vehicles after a plurality of time steps on each candidate search path according to the information entropy distribution and the position information of the obstacles in the search area;
and the fourth calculating unit is used for calculating the searching overlapping range of the unmanned vehicle according to the relative position information of the unmanned vehicle, and taking the candidate searching path corresponding to the maximum searching income as the optimal searching path when the searching overlapping range is smaller than or equal to a preset range threshold value.
12. The apparatus according to claim 11, wherein the fourth computing unit is further configured to optimize the candidate search paths of the plurality of unmanned vehicles by using a multi-objective optimization algorithm with the search gain maximized as a target when the search overlap range is greater than the preset range threshold, so as to generate an optimal search path for each unmanned vehicle.
13. An electronic device, comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the method of multi-unmanned vehicle collaborative search of dynamic targets according to any of claims 1-6.
14. A computer-readable storage medium, on which a computer program is stored, the program being executed by a processor for implementing a multi-unmanned vehicle collaborative search method for dynamic targets according to any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210592312.0A CN115047871A (en) | 2022-05-27 | 2022-05-27 | Multi-unmanned vehicle collaborative search method, device, equipment and medium for dynamic target |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210592312.0A CN115047871A (en) | 2022-05-27 | 2022-05-27 | Multi-unmanned vehicle collaborative search method, device, equipment and medium for dynamic target |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115047871A true CN115047871A (en) | 2022-09-13 |
Family
ID=83159680
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210592312.0A Pending CN115047871A (en) | 2022-05-27 | 2022-05-27 | Multi-unmanned vehicle collaborative search method, device, equipment and medium for dynamic target |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115047871A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117519213A (en) * | 2024-01-04 | 2024-02-06 | 上海仙工智能科技有限公司 | Multi-robot collaborative freight control method and system and storage medium |
-
2022
- 2022-05-27 CN CN202210592312.0A patent/CN115047871A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117519213A (en) * | 2024-01-04 | 2024-02-06 | 上海仙工智能科技有限公司 | Multi-robot collaborative freight control method and system and storage medium |
| CN117519213B (en) * | 2024-01-04 | 2024-04-09 | 上海仙工智能科技有限公司 | Multi-robot collaborative freight control method and system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107168305B (en) | Bezier and VFH-based unmanned vehicle track planning method under intersection scene | |
| CN113110457B (en) | Autonomous coverage inspection method for intelligent robot in indoor complex dynamic environment | |
| Sudhakara et al. | Trajectory planning of a mobile robot using enhanced A-star algorithm | |
| Saulnier et al. | Information theoretic active exploration in signed distance fields | |
| Jian et al. | Putn: A plane-fitting based uneven terrain navigation framework | |
| CN114913386A (en) | Training method of multi-target tracking model and multi-target tracking method | |
| CN108387240B (en) | Construction method of multilayer hexagonal grid map | |
| Bandeira et al. | Analysis of path planning algorithms based on travelling salesman problem embedded in UAVs | |
| CN112857370A (en) | Robot map-free navigation method based on time sequence information modeling | |
| Macharet et al. | Data gathering tour optimization for Dubins' vehicles | |
| CN110705385A (en) | Method, device, equipment and medium for detecting angle of obstacle | |
| Huang et al. | A novel particle swarm optimization algorithm based on reinforcement learning mechanism for AUV path planning | |
| Meng et al. | UAV 3-dimension flight path planning based on improved rapidly-exploring random tree | |
| CN115047871A (en) | Multi-unmanned vehicle collaborative search method, device, equipment and medium for dynamic target | |
| Gimenez et al. | Optimization methodology to fruit grove mapping in precision agriculture | |
| Lei et al. | A bio-inspired neural network approach to robot navigation and mapping with nature-inspired algorithms | |
| Belavadi et al. | Frontier exploration technique for 3d autonomous slam using k-means based divisive clustering | |
| Wang et al. | Research on autonomous planning method based on improved quantum Particle Swarm Optimization for Autonomous Underwater Vehicle | |
| CN117389305A (en) | Unmanned aerial vehicle inspection path planning method, system, equipment and medium | |
| Chen et al. | A real-time multi-constraints obstacle avoidance method using LiDAR | |
| CN109977455B (en) | Ant colony optimization path construction method suitable for three-dimensional space with terrain obstacles | |
| Han et al. | Research on UAV indoor path planning algorithm based on global subdivision grids | |
| CN114815899A (en) | Unmanned aerial vehicle three-dimensional space path planning method based on 3D laser radar sensor | |
| Xue et al. | Real-time 3D grid map building for autonomous driving in dynamic environment | |
| Kalaivanan et al. | Coverage path planning for an autonomous robot specific to agricultural operations |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |