CN113111296A - Vehicle path planning method and device, electronic equipment and storage medium - Google Patents
Vehicle path planning method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113111296A CN113111296A CN201911345444.8A CN201911345444A CN113111296A CN 113111296 A CN113111296 A CN 113111296A CN 201911345444 A CN201911345444 A CN 201911345444A CN 113111296 A CN113111296 A CN 113111296A
- Authority
- CN
- China
- Prior art keywords
- position area
- vehicle
- area
- passable
- value
- 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 44
- 238000012549 training Methods 0.000 claims description 23
- 230000006870 function Effects 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 3
- 230000000875 corresponding effect Effects 0.000 description 34
- 230000009471 action Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000003068 static effect Effects 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000002787 reinforcement Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
- G01C21/343—Calculating itineraries, i.e. routes leading from a starting point to a series of categorical destinations using a global route restraint, round trips, touristic trips
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Automation & Control Theory (AREA)
- Pure & Applied Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Operations Research (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Algebra (AREA)
- Mechanical Engineering (AREA)
- Transportation (AREA)
- Navigation (AREA)
Abstract
The application relates to a method, a device, electronic equipment and a storage medium for planning a path of a vehicle, wherein the method comprises the steps of determining a current position area of the vehicle; performing path planning on the current position area based on a path planning model to obtain a passable value set of a position area set to be selected corresponding to the current position area; if the position area to be selected corresponding to the passable value with the largest value in the passable value set is the feasible position area, determining the position area to be selected as a target position area; and finishing the command to the vehicle path planning until the target position area is matched with the terminal. The method provided by the application can be applied to the AGV, and if the candidate position area corresponding to the passable value with the largest numerical value is the infeasible position area, whether the candidate position area corresponding to the passable value with the second largest numerical value is the feasible position area can be determined, so that the AGV does not need to stop for waiting or restart an algorithm to calculate a new path, and can save time and save memory.
Description
Technical Field
The present disclosure relates to the field of path planning technologies, and in particular, to a method and an apparatus for path planning of a vehicle, an electronic device, and a storage medium.
Background
An Automated Guided Vehicle (AGV) is an Automated transport facility equipped with an electromagnetic or optical automatic guidance device and capable of completing a specified transport task in a given path and scene information layout.
With the increasing number of AGVs in a system, the system can plan a path with difficulty. After receiving external tasks, the system plans paths by using algorithms such as dixtera (Dijkstra), a and D. The system firstly establishes a model by using a grid method, then searches for a proper idle AGV in a grid map according to a task starting point and a task ending point, and further plans a path, so that the AGV can complete a task along the planned path. When multiple AGVs execute tasks together, different AGVs may apply for the same grid node, possibly resulting in AGV collision.
In order to prevent AGVs from colliding, the conventional multiple AGV path planning includes two ways: static path planning and dynamic path planning. Static path planning refers to: the system plans the shortest path for the AGV according to the task starting point and the task end point, does not change the path in the moving process of the AGV, and enables the AGV to stop and wait once collision is predicted. Dynamic path planning refers to: on the basis of static path planning, the system considers surrounding AGV movement paths and adjusts the static paths of the AGVs in real time, and if collision is detected to be about to occur, the system plans the AGV paths again in order to avoid the collision.
The two conventional methods have the following disadvantages: the static path planning method enables other AGVs to stop and wait, and occupies the time for other AGVs to execute tasks; in the dynamic path planning method, the algorithm is restarted when the path is re-planned, and the path from the new starting point to the task end point is calculated, so that the execution of the algorithm increases the time consumption, and the efficiency of the AGV in executing the task is affected.
Disclosure of Invention
The embodiment of the application provides a vehicle path planning method and device, electronic equipment and a storage medium, and the efficiency of AGV executing tasks can be improved in a multi-AGV environment.
In one aspect, an embodiment of the present application provides a method for planning a path of a vehicle, including: determining a current position area of the vehicle, wherein the current position area is one position area in a position area set determined based on a starting point and an end point of the vehicle; performing path planning on the current position area based on a path planning model to obtain a passable value set of a position area set to be selected corresponding to the current position area; if the position area to be selected corresponding to the passable value with the largest value in the passable value set is the feasible position area, determining the position area to be selected as a target position area; sending a driving command to the vehicle, wherein the driving command comprises the identification of the target position area, so that the vehicle drives to the target position area according to the identification of the target position area; and if the target position area is matched with the end point, finishing a command for planning the vehicle path.
In another aspect, an embodiment of the present application provides an electronic device, where the electronic device includes a processor and a memory, where the memory stores at least one instruction, at least one program, a code set, or a set of instructions, and the at least one instruction, the at least one program, the code set, or the set of instructions is loaded and executed by the processor to implement the path planning method for the vehicle as described above.
In another aspect, the present application provides a computer-readable storage medium, in which at least one instruction, at least one program, a code set, or a set of instructions is stored, and the at least one instruction, the at least one program, the code set, or the set of instructions is loaded and executed by a processor to implement the path planning method for the vehicle as described above.
On the other hand, the embodiment of the present application provides a path planning device for a vehicle, including: the system comprises a position determining module, a position determining module and a position determining module, wherein the position determining module is used for determining a current position area of a vehicle, and the current position area is one position area in a position area set determined based on a starting point and an end point of the vehicle; the path planning module is used for planning a path of the current position area based on the path planning model to obtain a passable value set of a position area set to be selected corresponding to the current position area; if the position area to be selected corresponding to the passable value with the largest value in the passable value set is the feasible position area, determining the position area to be selected as a target position area; the command sending module is used for sending a driving command to the vehicle, wherein the driving command comprises the identification of the target position area, so that the vehicle drives to the target position area according to the identification of the target position area; and if the target position area is matched with the end point, finishing a command for planning the vehicle path.
The method and the device for planning the vehicle path, the electronic equipment and the storage medium have the following beneficial effects that:
determining a current position area of the vehicle, wherein the current position area is one position area in a position area set determined based on a starting point and an end point of the vehicle; performing path planning on the current position area based on a path planning model to obtain a passable value set of a position area set to be selected corresponding to the current position area; if the position area to be selected corresponding to the passable value with the largest value in the passable value set is the feasible position area, determining the position area to be selected as a target position area; sending a driving command to the vehicle, wherein the driving command comprises the identification of the target position area, so that the vehicle drives to the target position area according to the identification of the target position area; and if the target position area is matched with the end point, finishing a command for planning the vehicle path. When the method provided by the application is applied to the AGV, the system does not need to plan all paths of the AGV, and determines a position area as a target position area from all the to-be-selected position areas in the process that the AGV executes a task, so that the calculation can be reduced, and the memory can be saved; in addition, if the candidate location area corresponding to the passable value with the largest numerical value is the infeasible location area, the AGV may determine whether the candidate location area corresponding to the passable value with the largest numerical value is the feasible location area, and the AGV does not need to stop waiting or restart the algorithm to calculate a new path, so that time and memory can be further saved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic diagram of an application scenario provided in an embodiment of the present application;
fig. 2 is a schematic flowchart of a method for planning a path of a vehicle according to an embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a multiple AGV application scenario according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a vehicle path planning device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. It is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic may be included in at least one implementation of the present application. In the description of the present application, it is to be understood that the terms "upper", "lower", "top", "bottom", and the like, indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, are only for convenience in describing the present application and simplifying the description, and do not indicate or imply that the referred devices or elements must have a specific orientation, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present application. 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 implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. Moreover, the terms "first," "second," and the like are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein.
Referring to fig. 1, fig. 1 is a schematic view of an application scenario provided in an embodiment of the present application, and the application scenario includes a vehicle 101 and a server 102, where the server 102 provides a path plan for the vehicle 101, and the vehicle 101 travels according to the path provided by the server 102.
The server 102 determines a current position area of the vehicle 101, wherein the current position area is one position area in a position area set determined by the server 102 based on a starting point and an end point of the vehicle 101; the server 102 performs path planning on the current position area based on the path planning model to obtain a passable value set of a to-be-selected position area set corresponding to the current position area; if the to-be-selected position area corresponding to the passable value with the largest value in the passable value set is the feasible position area, the server 102 determines that the to-be-selected position area is the target position area; the server 102 sends a driving command to the vehicle 101, wherein the driving command comprises an identifier of the target position area, so that the vehicle 101 drives to the target position area according to the identifier of the target position area; if the target location area matches the destination, the server 102 issues a path planning completion command to the vehicle 101.
Alternatively, the vehicle 101 may be an AGV, the server 102 may be a computer, and the computer sends the path and travel command to the AGV, and the AGV executes the relevant command.
The following describes an embodiment of a data transmission method of the present application, and fig. 2 is a schematic flow chart of a path planning method for a vehicle provided by the embodiment of the present application, and the present specification provides the method operation steps as in the embodiment or the flow chart, but may include more or less operation steps based on conventional or non-inventive labor. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. In practice, the system or server product may be implemented in a sequential or parallel manner (e.g., parallel processor or multi-threaded environment) according to the embodiments or methods shown in the figures. Specifically, as shown in fig. 2, the method may include:
s201: the server determines a current location area of the vehicle, the current location area being one of a set of location areas determined based on a start point and an end point of the vehicle.
In the embodiment of the application, the server determines the position area set based on the starting point and the end point of the vehicle, and the server determines one position area of the vehicle in the position area set as the current position area of the vehicle.
The above is illustrated below by a specific example, which may be a multiple AGV application scenario. Referring to fig. 3, fig. 3 is a schematic diagram of a multiple AGV application scenario provided in an embodiment of the present application, including AGVs 1, AGVs 2 and a computer (not shown in the figure). Assuming that the start point of the AGV1 is S1 and the end point is S16, the computer determines a location area set including grid nodes S1, S2, S3, S4, S5, S6, S7, S8, S9, S10, S11, S12, S13, S14, S15, and S16 of the grid map of 4x4 as shown in fig. 3 based on the start point and the end point of the AGV1, and determines that the current location area of the AGV1 is S1.
S203: and the server plans the path of the current position area based on the path planning model to obtain the passable value set of the position area set to be selected corresponding to the current position area.
In the embodiment of the application, the path planning model is a model obtained based on deep reinforcement learning training. Specifically, the step of determining the path planning model includes: acquiring a first historical position area; performing path planning on the first historical position area based on a first planning model to obtain a first passable value set of a second historical position area set corresponding to the first historical position area; a plurality of second historical position areas of the second historical position area set correspond to a plurality of first passable values of the first passable value set in a one-to-one mode; performing path planning on each second historical position area based on a second planning model to obtain a second passable value set of a third historical position area set corresponding to each second historical position area; a plurality of third history position areas of the third history position area set correspond to a plurality of second passable values of the second passable value set one by one; determining a loss function according to a first passable value corresponding to the second historical position area and a second passable value with the largest value; and training the first planning model according to the loss function to obtain a path planning model.
In the embodiment of the application, the first planning model and the second planning model are two deep neural network models with the same initial model parameters. The first planning model is used to quickly update the model parameters and periodically transmit the parameters to the second planning model, which updates the target value, i.e., the second passable value, at a slower rate. Therefore, the second passable value is kept unchanged in a period of time, and the correlation between the current value, namely the first passable value and the second passable value, is reduced, so that the deep reinforcement learning algorithm is updated stably.
Optionally, the step of determining the first planning model includes: acquiring a training data set, wherein each piece of training data in the training data set comprises a first position area, a second position area and a preset reward parameter; and training the first initial model based on the training data set to obtain a first planning model with the model parameters as first parameters. The step of determining the second planning model includes: acquiring a training data set, wherein each piece of training data in the training data set comprises a first position area, a second position area and a preset reward parameter; and training the second initial model based on the training data set to obtain a second planning model with the model parameters as second parameters. The preset reward parameter is a reward obtained when the first position area executes the action to reach the second position area.
The first passable value may be determined according to equation (1):
Q(s,a)＝Q(s,a)+α[r+γmaxa′Q(s′,a′)-Q(s,a)]… … formula (1)
Wherein s is the current state, namely the first historical position area; a is the action currently taken, i.e. the action taken from the first to the second historic location area; α is the learning rate; r is the reward earned by the system; γ is the attenuation factor; s' is the next step state, i.e. the second historical location area; a' is the action taken in the next state, i.e., the action taken from the second past location area to the third past location area.
In the embodiment of the present application, the loss function is formula (2), and the model parameters are determined according to formula (3) by using a random gradient descent method in the back propagation process:
L(ω)＝E[(r+γmaxa′Q(s′,a′,ω)-Q(s,a,ω))2]… … formula (2)
Wherein Q (s, a, ω) is a current value, i.e. an output resulting from the first location area being an input to the first planning model; r + gamma maxa′Q (s ', a', ω) is a target value, i.e. the output resulting from the above-mentioned first location area as input to the second planning model.
In the embodiment of the application, the set of the position areas to be selected is obtained by executing corresponding actions on the current position area.
Continuing with the above example, in the grid map, the AGV may travel along the grid lines or along the diagonal lines of the grid. Assume in this example that the AGV can only perform four actions, up, down, left, and right, along the grid lines. The computer carries out path planning on a current position area S1 of the AGV1 based on a trained path planning model, and takes S1 as the input of the path planning model to obtain a passable value set of a position area set to be selected corresponding to S1, wherein the position area set to be selected comprises S2 and S5, and the passable value set comprises Q2 and Q5.
S205: and if the position area to be selected corresponding to the passable value with the largest value in the passable value set is the feasible position area, the server determines that the position area to be selected is the target position area.
In the embodiment of the application, if the position area to be selected corresponding to the communication value with the largest value in the passable value set is the infeasible position area, the position area to be selected corresponding to the passable value with the largest value in the passable value set is determined; and if the position area to be selected corresponding to the passable value with the largest numerical value in the passable value set is the feasible position area, determining that the position area to be selected is the target position area.
In the embodiment of the application, the candidate position area corresponding to the passable value with the largest value in the passable value set is a position area closer to the terminal point, the feasible position area is a position area not occupied by other vehicles, and the infeasible position area is a position area occupied by other vehicles. Therefore, if the to-be-selected position area corresponding to the passable value with the largest value in the passable value set is the feasible position area, the server determines that the to-be-selected position area is the target position area; and if the candidate position area corresponding to the communication value with the largest value in the passable value set is the infeasible position area, determining the candidate position area corresponding to the passable value with the largest value in the passable value set as the feasible position area.
S207: and the server sends a driving command to the vehicle, wherein the driving command comprises the identification of the target position area, so that the vehicle drives to the target position area according to the identification of the target position area.
Optionally, the identifier of the target location area may include a driving direction and a driving distance from the current location area to the target location area.
Optionally, the identification of the target location area may include a two-dimensional code identifier.
Continuing with the above example, the computer obtains the same values of Q2 and Q5 based on the path planning model, and S2 and S5 are both feasible location areas, and the computer randomly selects S2 as the target location area. The computer sends a travel command to the AGV1, which may include an S2 two-dimensional code identifier or 1 grid distance to the right, to cause the AGV1 to travel to S2. Thus, the AGVs 1 sequentially travel from S2 to S6 and S7, when the AGV1 travels to S7, the computer obtains the candidate position area set corresponding to S7 based on the path planning model, wherein the candidate position area set includes S3, S6, S8 and S11, and the passable value set includes Q3, Q6, Q8 and Q11. Where Q11 is the largest but S11 is already occupied by the AGV2 as an infeasible location area, so the computer determines S8 corresponding to Q8 with the next highest passable value as the target location area and the computer sends a travel command, which may include an S8 two-dimensional identifier or 1 grid distance to the right. Thus, the AGV1 travels from S8 to S12 and S16 in this order.
S209: and if the target position area is matched with the end point, the server sends a path planning completion command to the vehicle.
In an alternative embodiment, in which the target location area matches the end point, the location area corresponding to the end point coincides with the target location area.
In an alternative embodiment, in which the target location area matches the end point, the end point is located within the target location area.
Continuing with the above example, after the AGV1 has traveled from S12 to the target position area S16, S16 overlaps the position area corresponding to the destination, and the computer sends a path planning complete command to the AGV1 to update the AGV1 to idle to perform other tasks.
An embodiment of the present application further provides a path planning apparatus for a vehicle, and fig. 4 is a schematic structural diagram of the path planning apparatus for a vehicle provided in the embodiment of the present application, including:
a position determining module 401, configured to determine a current position area of the vehicle, where the current position area is one position area in a position area set determined based on a starting point and an ending point of the vehicle;
a path planning module 402, configured to perform path planning on the current location area based on a path planning model, to obtain a passable value set of a to-be-selected location area set corresponding to the current location area; if the position area to be selected corresponding to the passable value with the largest value in the passable value set is the feasible position area, determining the position area to be selected as a target position area;
a sending command module 403, configured to send a driving command to the vehicle, where the driving command includes an identifier of the target location area, so that the vehicle drives to the target location area according to the identifier of the target location area; and if the target position area is matched with the end point, finishing a command for planning the vehicle path.
The device and method embodiments in the embodiments of the present application are based on the same application concept.
Embodiments of the present application further provide an electronic device, which includes a processor and a memory, where at least one instruction, at least one program, a code set, or a set of instructions is stored in the memory, and the at least one instruction, the at least one program, the code set, or the set of instructions is loaded and executed by the processor to implement the above-mentioned path planning method for the vehicle.
Embodiments of the present application also provide a storage medium, which may be disposed in a server to store at least one instruction, at least one program, a set of codes, or a set of instructions related to implementing a method for path planning for a vehicle in the method embodiments, where the at least one instruction, the at least one program, the set of codes, or the set of instructions is loaded and executed by the processor to implement the method for path planning for a vehicle.
Alternatively, in this embodiment, the storage medium may be located in at least one network server of a plurality of network servers of a computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
As can be seen from the above embodiments of the method, the apparatus, the electronic device, or the storage medium for planning a route of a vehicle provided by the present application, in the embodiments of the present application, a current location area of the vehicle is determined, where the current location area is one location area in a set of location areas determined based on a starting point and an ending point of the vehicle; performing path planning on the current position area based on a path planning model to obtain a passable value set of a position area set to be selected corresponding to the current position area; if the position area to be selected corresponding to the passable value with the largest value in the passable value set is the feasible position area, determining the position area to be selected as a target position area; sending a driving command to the vehicle, wherein the driving command comprises the identification of the target position area, so that the vehicle drives to the target position area according to the identification of the target position area; and if the target position area is matched with the end point, finishing a command for planning the vehicle path. When the method provided by the application is applied to the AGV, the system does not need to plan all paths of the AGV, and determines a position area as a target position area from all the to-be-selected position areas in the process that the AGV executes a task, so that the calculation can be reduced, and the memory can be saved; in addition, if the candidate location area corresponding to the passable value with the largest numerical value is the infeasible location area, the AGV may determine whether the candidate location area corresponding to the passable value with the largest numerical value is the feasible location area, and the AGV does not need to stop waiting or restart the algorithm to calculate a new path, so that time and memory can be further saved.
It should be noted that: the sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (10)
1. A method of path planning for a vehicle, comprising:
determining a current location area of a vehicle, the current location area being one of a set of location areas determined based on a starting point and an ending point of the vehicle;
performing path planning on the current position area based on a path planning model to obtain a passable value set of a position area set to be selected corresponding to the current position area;
if the position area to be selected corresponding to the passable value with the largest value in the passable value set is a feasible position area, determining the position area to be selected as a target position area;
sending a driving command to the vehicle, wherein the driving command comprises the identifier of the target position area, so that the vehicle drives to the target position area according to the identifier of the target position area;
and if the target position area is matched with the end point, finishing a command for planning the vehicle path.
2. The method of claim 1, further comprising the step of determining the path planning model;
the determining the path planning model includes:
acquiring a first historical position area;
performing path planning on the first historical position area based on a first planning model to obtain a first passable value set of a second historical position area set corresponding to the first historical position area; a plurality of second historical location areas of the second set of historical location areas are in one-to-one correspondence with a plurality of first passable values of the first set of passable values;
performing path planning on each second historical position area based on a second planning model to obtain a second passable value set of a third historical position area set corresponding to each second historical position area; a plurality of third history position areas of the third history position area set correspond to a plurality of second passable values of the second passable value set in a one-to-one mode;
determining a loss function according to a first passable value corresponding to the second historical position area and a second passable value with the largest value;
and training the first planning model according to the loss function to obtain the path planning model.
3. The method of claim 2, further comprising the step of determining the first planning model and the second planning model;
the determining the first planning model includes:
acquiring a training data set, wherein each piece of training data in the training data set comprises a first position area, a second position area and a preset reward parameter;
training a first initial model based on the training data set to obtain the first planning model with model parameters as first parameters;
the determining the second planning model includes:
acquiring a training data set, wherein each piece of training data in the training data set comprises a first position area, a second position area and a preset reward parameter;
and training a second initial model based on the training data set to obtain the second planning model with model parameters as second parameters.
4. The method of claim 1, wherein the determining a current location area of the vehicle comprises:
determining a set of location regions based on a starting point and an ending point of the vehicle;
determining one location area in the set of location areas as a current location area of the vehicle.
5. The method of claim 1, further comprising:
if the position area to be selected corresponding to the communication value with the largest value in the passable value set is the position area which cannot be selected, determining the position area to be selected corresponding to the passable value with the largest value in the passable value set;
and if the position area to be selected corresponding to the passable value with the largest numerical value in the passable value set is a feasible position area, determining that the position area to be selected is the target position area.
6. The method of claim 1, wherein said determining if said target location area matches an endpoint comprises:
the position area corresponding to the end point is superposed with the target position area; or;
the end point is located within the target location area.
7. The method of claim 1, wherein the identification of the target location area comprises a travel direction and a travel distance of the current location area to the target location area.
8. A path planning apparatus for a vehicle, comprising:
a location determination module to determine a current location area of a vehicle, the current location area being one of a set of location areas determined based on a starting point and an ending point of the vehicle;
the path planning module is used for planning a path of the current position area based on a path planning model to obtain a passable value set of a position area set to be selected corresponding to the current position area; if the position area to be selected corresponding to the passable value with the largest value in the passable value set is a feasible position area, determining the position area to be selected as a target position area;
the sending command module is used for sending a driving command to the vehicle, wherein the driving command comprises the identifier of the target position area, so that the vehicle can drive to the target position area according to the identifier of the target position area; and if the target position area is matched with the end point, finishing a command for planning the vehicle path.
9. An electronic device, comprising a processor and a memory, wherein at least one instruction, at least one program, a set of codes, or a set of instructions is stored in the memory, and wherein the at least one instruction, the at least one program, the set of codes, or the set of instructions is loaded and executed by the processor to implement a path planning method for a vehicle according to any of claims 1-7.
10. A computer readable storage medium having stored therein at least one instruction, at least one program, a set of codes, or a set of instructions, which is loaded and executed by a processor to implement a method of path planning for a vehicle according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911345444.8A CN113111296A (en) | 2019-12-24 | 2019-12-24 | Vehicle path planning method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911345444.8A CN113111296A (en) | 2019-12-24 | 2019-12-24 | Vehicle path planning method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113111296A true CN113111296A (en) | 2021-07-13 |
Family
ID=76708540
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911345444.8A Pending CN113111296A (en) | 2019-12-24 | 2019-12-24 | Vehicle path planning method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113111296A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024021758A1 (en) * | 2022-07-29 | 2024-02-01 | 北京旷视机器人技术有限公司 | Robot control method, electronic device and storage medium |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102929281A (en) * | 2012-11-05 | 2013-02-13 | 西南科技大学 | Robot k-nearest-neighbor (kNN) path planning method under incomplete perception environment |
| CN105137967A (en) * | 2015-07-16 | 2015-12-09 | 北京工业大学 | Mobile robot path planning method with combination of depth automatic encoder and Q-learning algorithm |
| CN106970615A (en) * | 2017-03-21 | 2017-07-21 | 西北工业大学 | A kind of real-time online paths planning method of deeply study |
| CN108375379A (en) * | 2018-02-01 | 2018-08-07 | 上海理工大学 | The fast path planing method and mobile robot of dual DQN based on variation |
| CN108536144A (en) * | 2018-04-10 | 2018-09-14 | 上海理工大学 | A kind of paths planning method of fusion dense convolutional network and competition framework |
| CN109059931A (en) * | 2018-09-05 | 2018-12-21 | 北京航空航天大学 | A kind of paths planning method based on multiple agent intensified learning |
| CN109298712A (en) * | 2018-10-19 | 2019-02-01 | 大连海事大学 | A kind of autonomous Decision of Collision Avoidance method of unmanned ship based on the study of adaptive sailing situation |
| CN109405843A (en) * | 2018-09-21 | 2019-03-01 | 北京三快在线科技有限公司 | A kind of paths planning method and device and mobile device |
| CN109460039A (en) * | 2018-12-26 | 2019-03-12 | 芜湖哈特机器人产业技术研究院有限公司 | A kind of paths planning method of AGV |
| CN110378439A (en) * | 2019-08-09 | 2019-10-25 | 重庆理工大学 | Single robot path planning method based on Q-Learning algorithm |
| CN110443412A (en) * | 2019-07-18 | 2019-11-12 | 华中科技大学 | The intensified learning method of Logistic Scheduling and path planning in dynamic optimization process |
| CN110597261A (en) * | 2019-09-24 | 2019-12-20 | 浙江大华技术股份有限公司 | Method and device for preventing collision conflict |
-
2019
- 2019-12-24 CN CN201911345444.8A patent/CN113111296A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102929281A (en) * | 2012-11-05 | 2013-02-13 | 西南科技大学 | Robot k-nearest-neighbor (kNN) path planning method under incomplete perception environment |
| CN105137967A (en) * | 2015-07-16 | 2015-12-09 | 北京工业大学 | Mobile robot path planning method with combination of depth automatic encoder and Q-learning algorithm |
| CN106970615A (en) * | 2017-03-21 | 2017-07-21 | 西北工业大学 | A kind of real-time online paths planning method of deeply study |
| CN108375379A (en) * | 2018-02-01 | 2018-08-07 | 上海理工大学 | The fast path planing method and mobile robot of dual DQN based on variation |
| CN108536144A (en) * | 2018-04-10 | 2018-09-14 | 上海理工大学 | A kind of paths planning method of fusion dense convolutional network and competition framework |
| CN109059931A (en) * | 2018-09-05 | 2018-12-21 | 北京航空航天大学 | A kind of paths planning method based on multiple agent intensified learning |
| CN109405843A (en) * | 2018-09-21 | 2019-03-01 | 北京三快在线科技有限公司 | A kind of paths planning method and device and mobile device |
| CN109298712A (en) * | 2018-10-19 | 2019-02-01 | 大连海事大学 | A kind of autonomous Decision of Collision Avoidance method of unmanned ship based on the study of adaptive sailing situation |
| CN109460039A (en) * | 2018-12-26 | 2019-03-12 | 芜湖哈特机器人产业技术研究院有限公司 | A kind of paths planning method of AGV |
| CN110443412A (en) * | 2019-07-18 | 2019-11-12 | 华中科技大学 | The intensified learning method of Logistic Scheduling and path planning in dynamic optimization process |
| CN110378439A (en) * | 2019-08-09 | 2019-10-25 | 重庆理工大学 | Single robot path planning method based on Q-Learning algorithm |
| CN110597261A (en) * | 2019-09-24 | 2019-12-20 | 浙江大华技术股份有限公司 | Method and device for preventing collision conflict |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024021758A1 (en) * | 2022-07-29 | 2024-02-01 | 北京旷视机器人技术有限公司 | Robot control method, electronic device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11928644B2 (en) | Articles picking method, control system and articles picking system | |
| CN114581180B (en) | Charging station recommendation method, charging pile state determination method and device | |
| CN112461256A (en) | Path planning method and device | |
| US10343280B1 (en) | Method and system for robotic surface coverage | |
| CN106066180A (en) | Identify parking spot with regard to destination | |
| CN111483345B (en) | Charging control method and device for unmanned aerial vehicle, storage medium and electronic equipment | |
| CN108229864A (en) | Distribution method, device and the electronic equipment of order | |
| US20230063370A1 (en) | Multi-robot route planning | |
| CN108073727A (en) | The data processing method and device of place search | |
| CN115410410B (en) | Parking space recommendation method, device, equipment and storage medium | |
| CN112966806A (en) | Processing device, processing method, and recording medium | |
| CN114527751A (en) | Robot path planning method and device and electronic equipment | |
| CN113111296A (en) | Vehicle path planning method and device, electronic equipment and storage medium | |
| CN114564026A (en) | Path planning method and device for multiple distribution points, robot and storage medium | |
| CN114862209A (en) | Transport capacity scheduling method and device, electronic equipment and storage medium | |
| CN111722629B (en) | Path planning method and device, storage medium and electronic device | |
| JP7248008B2 (en) | AREA RATING SYSTEMS, METHODS AND PROGRAMS | |
| JP7481903B2 (en) | Information processing device, information processing method, information processing system, and computer program | |
| KR101877767B1 (en) | Method for providing route information for performing missions, and recording medium for performing the method | |
| KR20220095452A (en) | Computer system of providing service consumption plan for efficient service migration in mobile edge computing environments, and method thereof | |
| CN117148838A (en) | Robot movement control method and device and readable storage medium | |
| CN113137972A (en) | Path planning method and device | |
| CN115759491A (en) | Scenic spot travel planning method and device, electronic equipment and computer medium | |
| CN112197763B (en) | Map construction method, device, equipment and storage medium | |
| Petersen et al. | Fast task-sequence allocation for heterogeneous robot teams with a human in the loop |
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 |