CN111998859A

CN111998859A - Path planning method and device, electronic equipment and path indicating system

Info

Publication number: CN111998859A
Application number: CN202010972422.0A
Authority: CN
Inventors: 陆健; 周建
Original assignee: Hangzhou Haikang Fire Technology Co ltd
Current assignee: Hangzhou Haikang Fire Technology Co ltd
Priority date: 2020-09-16
Filing date: 2020-09-16
Publication date: 2020-11-27
Anticipated expiration: 2040-09-16
Also published as: CN111998859B

Abstract

The embodiment of the invention provides a path planning method, a path planning device, electronic equipment and a path indicating system. Therefore, in the scheme, the path planning does not need to be carried out on the plurality of termination nodes one by one, the path planning process under the scene of the plurality of termination nodes is simplified, and the path planning efficiency under the scene of the plurality of termination nodes is improved.

Description

Path planning method and device, electronic equipment and path indicating system

Technical Field

The present invention relates to the field of computer technologies, and in particular, to a path planning method and apparatus, an electronic device, and a path indication system.

Background

The path planning is a key technology for realizing robot transportation, automatic parking, fire early warning evacuation and the like, and aims to analyze all passable paths between two nodes and plan an optimal path between the two nodes, so that a robot, a vehicle or personnel can be indicated to rapidly move from one node to another node.

At present, path planning is usually performed by using Dijkstra algorithm, a-x algorithm, ant colony algorithm, etc., where both algorithms start from an initial node, continuously search for a next neighbor node, find a node in the next neighbor node with the shortest distance to the next neighbor node, and reach a destination termination node, so as to obtain an optimal path from the initial node to the destination termination node.

However, in an actual scenario, there are often a plurality of termination nodes, and according to the path planning method, path planning needs to be performed on one of the termination nodes, and then an optimal path is determined, so that in a scenario with multiple termination nodes, the efficiency of path planning is very low.

Disclosure of Invention

The embodiment of the invention aims to provide a path planning method, a path planning device, electronic equipment and a path indicating system, so as to improve the efficiency of path planning in a multi-termination node scene. The specific technical scheme is as follows:

in a first aspect, an embodiment of the present invention provides a path planning method, where the method includes:

acquiring path information between every two adjacent nodes and path information between each termination node and a preset virtual node in a preset scene, wherein the preset scene comprises a plurality of termination nodes, and the virtual node is virtually connected with each termination node and is the same as the path information between each termination node;

determining an optimal path from each node to the virtual node in a preset scene by using a preset path planning algorithm according to the path information between every two adjacent nodes and the path information between each termination node and the virtual node;

and according to the designated optimal path from the designated node to the virtual node, starting path backtracking from the virtual node to obtain a target optimal path from the designated node to a target termination node, wherein the designated node is any node except each termination node in a preset scene, and the target termination node is the termination node on the designated optimal path.

Optionally, before the step of obtaining the path information between every two adjacent nodes in the preset scene and the path information between each termination node and the preset virtual node, the method further includes:

acquiring a scene model of a preset scene, wherein the scene model comprises a plurality of target areas containing targets;

performing expansion processing on all target areas to obtain boundary lines of every two adjacent expanded target areas and intersection points of the boundary lines;

generating a connected graph according to the boundary lines and the intersection points of the boundary lines, wherein the connected graph comprises a node identifier of each node and path information between every two adjacent nodes, each node is the intersection point of each boundary line, and the path information between every two adjacent nodes is determined according to the attribute of each boundary line;

the method for acquiring the path information between every two adjacent nodes in the preset scene comprises the following steps:

and reading path information between every two adjacent nodes from the connected graph.

Optionally, the path information includes a path length;

the method comprises the following steps of determining the optimal path from each node to the virtual node in a preset scene by using a preset path planning algorithm according to the path information between every two adjacent nodes and the path information between each termination node and the virtual node, wherein the steps comprise:

aiming at each node in a preset scene, calculating the length of each path from the node to the virtual node by utilizing a preset path planning algorithm according to the path length between every two adjacent nodes and the path length between each termination node and the virtual node; and determining the path with the shortest length in each path as the optimal path from the node to the virtual node.

Optionally, the preset scene is a building scene, and the building scene includes a plurality of floors;

according to the appointed optimal path from the appointed node to the virtual node, the step of starting path backtracking from the virtual node to obtain the target optimal path from the appointed node to the target termination node comprises the following steps:

starting from a starting floor, according to the sequence of floors from low to high, aiming at any starting node in the floors, according to the appointed optimal path from the starting node to the virtual node, starting path backtracking from the virtual node, and obtaining the target optimal path from the starting node to the target termination node in the floors; until the target optimal path from the specified node in the target floor to the target termination node in the target floor is traced back; wherein, the starting node is the termination node of the previous floor;

and determining the target optimal path from the designated node to the target termination node in the starting floor according to the backtracking target optimal path of each floor.

Optionally, after the step of starting path backtracking from the virtual node according to the designated optimal path from the designated node to the virtual node to obtain the target optimal path from the designated node to the target termination node, the method further includes:

aiming at a path between any two adjacent nodes, acquiring environment data acquired by detection equipment for detecting the environment of the path; according to the environment data, correcting the path information of the path;

updating the optimal path from each node to the virtual node in the preset scene by using a path planning algorithm according to the corrected path information between every two adjacent nodes and the path information between each termination node and the virtual node;

and according to the updated designated optimal path, starting path backtracking from the virtual node to obtain an updated target optimal path.

and sending the path information of the target optimal path to each indicator arranged on the target optimal path, so that each indicator indicates the path direction of the target optimal path according to the path information of the target optimal path.

In a second aspect, an embodiment of the present invention provides a path planning apparatus, where the apparatus includes:

the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring path information between every two adjacent nodes and path information between each termination node and a preset virtual node in a preset scene, the preset scene comprises a plurality of termination nodes, and the virtual node is virtually connected with each termination node and is the same as the path information between each termination node;

the path calculation module is used for determining an optimal path from each node to the virtual node in a preset scene by using a preset path planning algorithm according to the path information between every two adjacent nodes and the path information between each termination node and the virtual node;

and the backtracking module is used for starting path backtracking from the virtual node according to the designated optimal path from the designated node to the virtual node to obtain a target optimal path from the designated node to a target termination node, wherein the designated node is any node except each termination node in a preset scene, and the target termination node is a termination node on the designated optimal path.

Optionally, the apparatus further comprises: the system comprises a connected graph generating module, a target area generating module and a target area generating module, wherein the connected graph generating module is used for acquiring a scene model of a preset scene, and the scene model comprises a plurality of target areas containing targets; performing expansion processing on all target areas to obtain boundary lines of every two adjacent expanded target areas and intersection points of the boundary lines; generating a connected graph according to the boundary lines and the intersection points of the boundary lines, wherein the connected graph comprises a node identifier of each node and path information between every two adjacent nodes, each node is the intersection point of each boundary line, and the path information between every two adjacent nodes is determined according to the attribute of each boundary line;

the obtaining module is specifically configured to read path information between every two adjacent nodes from the connected graph.

Optionally, the path information includes a path length;

the path calculation module is specifically used for calculating the length of each path from each node to each virtual node by using a preset path planning algorithm according to the path length between every two adjacent nodes and the path length between each termination node and each virtual node aiming at each node in a preset scene; and determining the path with the shortest length in each path as the optimal path from the node to the virtual node.

the backtracking module is specifically used for starting path backtracking from the virtual node to obtain a target optimal path from the starting node to a target termination node in the floor according to the designated optimal path from the starting node to the virtual node aiming at any starting node in the floors from low to high; until the target optimal path from the specified node in the target floor to the target termination node in the target floor is traced back; wherein, the starting node is the termination node of the previous floor; and determining the target optimal path from the designated node to the target termination node in the starting floor according to the backtracking target optimal path of each floor.

Optionally, the apparatus further comprises: the path updating module is used for acquiring environment data acquired by detection equipment for detecting the environment of a path aiming at the path between any two adjacent nodes; according to the environment data, correcting the path information of the path; updating the optimal path from each node to the virtual node in the preset scene by using a path planning algorithm according to the corrected path information between every two adjacent nodes and the path information between each termination node and the virtual node; and according to the updated designated optimal path, starting path backtracking from the virtual node to obtain an updated target optimal path.

Optionally, the apparatus further comprises: and the output module is used for sending the path information of the target optimal path to each indicator arranged on the target optimal path, so that each indicator indicates the path direction of the target optimal path according to the path information of the target optimal path.

In a third aspect, an embodiment of the present invention provides an electronic device, including a processor and a machine-readable storage medium, the machine-readable storage medium storing machine-executable instructions executable by the processor, the processor being caused by the machine-executable instructions to: the method provided by the first aspect of the embodiment of the invention is realized.

In a fourth aspect, an embodiment of the present invention provides a machine-readable storage medium, in which machine-executable instructions are stored, and when the machine-executable instructions are loaded and executed by a processor, the method provided in the first aspect of the embodiment of the present invention is implemented.

In a fifth aspect, an embodiment of the present invention provides a path indicating system, including an electronic device and a plurality of indicators, where the plurality of indicators are distributed in a preset scene;

the electronic equipment is used for acquiring path information between every two adjacent nodes and path information between each termination node and a preset virtual node in a preset scene, wherein the preset scene comprises a plurality of termination nodes, and the virtual node is virtually connected with each termination node and is the same as the path information between each termination node; determining an optimal path from each node to the virtual node in a preset scene by using a preset path planning algorithm according to the path information between every two adjacent nodes and the path information between each termination node and the virtual node; according to the designated optimal path from the designated node to the virtual node, starting path backtracking from the virtual node to obtain a target optimal path from the designated node to a target termination node, wherein the designated node is any node except each termination node in a preset scene, and the target termination node is a termination node on the designated optimal path; sending the path information of the target optimal path to each indicator arranged on the target optimal path;

and each indicator is used for indicating the path direction of the target optimal path according to the path information of the target optimal path.

Optionally, the path indicating system further includes: the system comprises a plurality of detection devices, a plurality of detection device and a plurality of communication devices, wherein the detection devices are arranged between every two adjacent nodes in a preset scene;

the detection equipment is used for detecting the environment of a path between two adjacent nodes to obtain environment data and sending the environment data to the electronic equipment;

the electronic equipment is also used for acquiring environment data acquired by detection equipment for detecting the environment of a path aiming at the path between any two adjacent nodes; according to the environment data, correcting the path information of the path; updating the optimal path from each node to the virtual node in the preset scene by using a path planning algorithm according to the corrected path information between every two adjacent nodes and the path information between each termination node and the virtual node; and according to the updated designated optimal path, starting path backtracking from the virtual node to obtain an updated target optimal path.

The embodiment of the invention provides a path planning method, a path planning device, electronic equipment and a path indicating system, wherein the path planning method comprises the following steps: the method comprises the steps of obtaining path information between every two adjacent nodes and path information between each termination node and a preset virtual node in a preset scene, determining an optimal path from each node to the virtual node in the preset scene by using a preset path planning algorithm according to the path information between every two adjacent nodes and the path information between each termination node and the virtual node, and backtracking from the virtual node according to an appointed optimal path from an appointed node to the virtual node to obtain a target optimal path from the appointed node to a target termination node.

The embodiment of the invention is provided with the virtual node which is virtually connected with each termination node and has the same path information with each termination node, so that the optimal path from each real node to the virtual node in the preset scene can be determined by utilizing a preset path planning algorithm, and finally, a target optimal path from any real node to the target termination node in the preset scene can be obtained through path backtracking. Therefore, in the embodiment of the invention, path planning does not need to be carried out on a plurality of termination nodes one by one, the path planning process under the scene of the plurality of termination nodes is simplified, and the path planning efficiency under the scene of the plurality of termination nodes is further improved.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other embodiments can be obtained by using the drawings without creative efforts.

Fig. 1 is a schematic flow chart of a path planning method according to an embodiment of the present invention;

fig. 2 is another schematic flow chart of a path planning method according to an embodiment of the present invention;

FIG. 3 is a flow chart illustrating a prior art image dilation process;

FIG. 4 is a connectivity graph generated by the dilation process performed on a target region in accordance with an embodiment of the present invention;

fig. 5 is a schematic flow chart of a path planning method according to another embodiment of the present invention;

fig. 6 is a schematic flow chart of a path planning method according to an embodiment of the present invention;

FIG. 7 is a flow chart of a method for intelligently evacuating a building during a fire according to an embodiment of the present invention;

FIG. 8 is a flow chart illustrating a path planning process according to an embodiment of the present invention;

fig. 9 is a schematic structural diagram of a path planning apparatus according to an embodiment of the present invention;

FIG. 10 is a schematic structural diagram of an electronic device according to an embodiment of the invention;

fig. 11 is a schematic structural diagram of a path indicating system according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the 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 invention.

In order to improve the efficiency of path planning in a multi-termination node scenario, embodiments of the present invention provide a path planning method, an apparatus, an electronic device, and a path indication system. Next, a path planning method provided in an embodiment of the present invention is first described.

The application scenario of the path planning method provided by the embodiment of the present invention may be robot transportation, automatic parking, fire early warning and evacuation, urban traffic management, and the like, and therefore, an execution main body of the path planning method provided by the embodiment of the present invention may be a robot, a vehicle, a background server, and the like, which are hereinafter collectively referred to as electronic devices.

As shown in fig. 1, a process of the path planning method according to the embodiment of the present invention may include the following steps.

S101, acquiring path information between every two adjacent nodes and path information between each termination node and a preset virtual node in a preset scene, wherein the preset scene comprises a plurality of termination nodes, and the virtual node is virtually connected with each termination node and is the same as the path information between each termination node.

And S102, determining the optimal path from each node to the virtual node in the preset scene by using a preset path planning algorithm according to the path information between every two adjacent nodes and the path information between each termination node and the virtual node.

S103, according to the designated optimal path from the designated node to the virtual node, starting path backtracking from the virtual node to obtain a target optimal path from the designated node to a target termination node, wherein the designated node is any node except each termination node in a preset scene, and the target termination node is a termination node on the designated optimal path.

By applying the embodiment of the invention, a virtual node is set, the virtual node is virtually connected with each termination node, and the path information between the virtual node and each termination node is the same, so that the optimal path from each real node to the virtual node in the preset scene can be determined by using a preset path planning algorithm, and finally, a target optimal path from any real node to a target termination node in the preset scene can be obtained by path backtracking. Therefore, path planning does not need to be carried out on the plurality of termination nodes one by one, the path planning process under the multi-termination-node scene is simplified, and the path planning efficiency under the multi-termination-node scene is further improved.

The preset scene can be a scene such as a factory, a building, an urban road, a parking lot and the like, the preset scene comprises a plurality of nodes, and the nodes refer to intersections of passable paths in the preset scene, such as crossroads, corridor corners and the like; the preset scene of the embodiment of the invention comprises a plurality of termination nodes, wherein the termination nodes refer to the end points of the path, such as a safety exit, a transportation destination and the like; the preset scene of the embodiment of the invention comprises at least one starting node, wherein the starting node refers to a starting point of path planning, such as a position where a target such as a vehicle and a person is located, a building entrance and the like.

In a preset scene, a passable path is formed between every two adjacent nodes, and the path information of the passable path formed between every two adjacent nodes can be acquired through means such as image analysis and actual measurement. The route information of one route affects the trafficability of the route, and for example, the route information may be the length, width, congestion degree, etc. of the route, and the shorter the route, the wider the route, or the lower the congestion degree of the route, the better the trafficability of the route. In a specific implementation, the route information may be a weighted value set by integrating the length, width, congestion degree, and the like of the route, where the weighted value represents the feasibility of the route, that is, the higher the weighted value is, the better the feasibility of the route is.

In the embodiment of the invention, a virtual node is set, and the virtual node is virtually connected with each termination node in a preset scene, and the path information between the virtual node and each termination node is the same. The virtual node is different from a node which actually exists in a preset scene, the virtual node is only fictionally constructed when path planning is needed, and the virtual node is supposed to be connected with each termination node in the preset scene, and path information such as path length, width, congestion degree and the like between the virtual node and each termination node are the same. A virtual node is a virtual end point, i.e. a node after the assumed termination node or a node next to the termination node.

Since a plurality of termination nodes are virtually connected to one virtual node, the path plan of the plurality of termination nodes can be converted into the path plan of a single termination node when the path plan is performed. Specifically, according to the path information between every two adjacent nodes and the path information between each termination node and the virtual node, a preset path planning algorithm is used to determine the optimal path from each node to the virtual node in a preset scene. The preset path planning algorithm may be a traditional Dijkstra algorithm, an a-x algorithm, an ant colony algorithm, or the like.

Optionally, the path information includes a path length; correspondingly, S102 may specifically be: aiming at each node in a preset scene, calculating the length of each path from the node to the virtual node by utilizing a preset path planning algorithm according to the path length between every two adjacent nodes and the path length between each termination node and the virtual node; and determining the path with the shortest length in each path as the optimal path from the node to the virtual node.

In an implementation manner of the embodiment of the present invention, the path information specifically refers to a path length. In general, the path length is a determining factor that affects the path trafficability, and the shorter the path length, the better the trafficability of the path, and the more likely it is to be the better path. When path planning is carried out, the length of each path from any node to a virtual node can be calculated according to the path length between every two adjacent nodes and the path length between each termination node and the virtual node, multiple passable paths are possible between the node and the virtual node, each passable path is composed of multiple sub-paths between every two adjacent nodes, the path length between every two adjacent nodes is known, the length of each path from the node to the virtual node can be obtained through path superposition, and the path with the shortest length is selected from the paths and can be used as the optimal path from the node to the virtual node.

After the optimal path from each node to the virtual node in the preset scene is obtained, the optimal path from a designated node to the virtual node in the preset scene except the termination node can be found, and according to the designated optimal path, the path can be traced back from the virtual node to obtain the target optimal path from the designated node to the target termination node. The backtracking process is as follows: and (4) tracing back from the virtual node along the appointed optimal path in the reverse direction until the appointed node is traced back, namely obtaining the target optimal path from the appointed node to the target termination node.

Optionally, the preset scene is a building scene, and the building scene includes a plurality of floors. Correspondingly, S103 may specifically be: starting from a starting floor, according to the sequence of floors from low to high, aiming at any starting node in the floors, according to the appointed optimal path from the starting node to the virtual node, starting path backtracking from the virtual node, and obtaining the target optimal path from the starting node to the target termination node in the floors; until the target optimal path from the specified node in the target floor to the target termination node in the target floor is traced back; wherein, the starting node is the termination node of the previous floor; and determining the target optimal path from the designated node to the target termination node in the starting floor according to the backtracking target optimal path of each floor.

In the specific implementation, the target optimal paths of each floor obtained by backtracking are sequentially connected, so that the target optimal path from the designated node to the target termination node in the starting floor can be obtained.

In an application scenario of fire early warning and evacuation, a preset scenario is a building scenario, and the building scenario includes a plurality of floors, in path planning in a conventional building scenario, a building is generally modeled into a complete building model, or each floor plan of the building is spread out to form a complete building plan, and then path planning is performed based on the building model or the building plan. In the embodiment of the present invention, a layer-by-layer progressive idea is adopted for layer-by-layer planning, that is, from an initial floor (i.e., a first layer), path planning is performed by using the steps shown in fig. 1, so as to obtain a target optimal path from all nodes of the first layer to a target termination node (generally, a building exit) of the first layer; then, taking a starting node of the first floor (generally, a first landing from the first floor to the second floor) as a terminating node of the second floor, performing path planning by using the steps shown in fig. 1 to obtain a target optimal path from all nodes of the second floor to the target terminating node of the second floor, and so on until a target floor (for example, the fifth floor) where the designated node is located, performing path planning by using the steps shown in fig. 1 to obtain a target optimal path from the designated node of the fifth floor (generally, where the target such as a person is located) to the target terminating node of the fifth floor (a landing from the fifth floor to the fourth floor). The optimal target paths from the first floor to the fifth floor are connected in sequence, so that the optimal path from the designated node to the building exit can be obtained, and therefore, the method does not need to perform complicated modeling and drawing processes, path planning of each floor is similar, complicated path planning does not need to be performed from the designated node backwards, and the calculation amount of path planning of all floors can be reduced.

Based on the embodiment shown in fig. 1, another flow of the path planning method is further provided in the embodiment of the present invention, as shown in fig. 2, which may include the following steps.

S201, a scene model of a preset scene is obtained, wherein the scene model comprises a plurality of target areas containing targets.

S202, performing expansion processing on all target areas to obtain the boundary lines of every two adjacent expanded target areas and the intersection points of the boundary lines.

S203, generating a connected graph according to the boundary lines and the intersection points of the boundary lines, wherein the connected graph comprises node identification of each node and path information between every two adjacent nodes, each node is the intersection point of each boundary line, and the path information between every two adjacent nodes is determined according to the attribute of each boundary line.

And S204, reading path information between every two adjacent nodes from the connected graph, and acquiring path information between each termination node and a preset virtual node, wherein the preset scene comprises a plurality of termination nodes, the virtual node is virtually connected with each termination node, and the path information between the virtual node and each termination node is the same.

S205, determining the optimal path from each node to the virtual node in the preset scene by using a preset path planning algorithm according to the path information between every two adjacent nodes and the path information between each termination node and the virtual node.

And S206, according to the designated optimal path from the designated node to the virtual node, starting path backtracking from the virtual node to obtain a target optimal path from the designated node to a target termination node, wherein the designated node is any node except each termination node in a preset scene, and the target termination node is a termination node on the designated optimal path.

In an implementation manner of the embodiment of the present invention, path information between every two adjacent nodes in a preset scene is read from a connected graph by establishing the connected graph. The connected graph refers to a graph used for describing free space and obstacles in the environment in path planning, and can be simplified into a connected graph G (V, E) consisting of nodes V and paths E.

The process of establishing the connectivity graph comprises the following steps: firstly, a scene model of a preset scene is obtained, wherein the scene model comprises a plurality of target areas containing targets. The scene model of the preset scene is established in advance according to the actual situation of the preset scene, and may be a three-dimensional model or a two-dimensional model, and each target in the actual scene, such as an obstacle, a pedestrian, a door, a wall, and the like, can be represented in the scene model, and occupies a certain area in the scene model, which is called as a target area. The further connected graph can be generated by a manual labeling method and by adopting the idea of image expansion. The manual labeling is to manually move the traversable paths in the graph according to the traversable paths in the scene model and the distribution of the targets, and set path information according to the attributes of the length, the width and the like of each path. The specific manual labeling method is not described in detail here.

Compared with manual labeling, the method of image expansion is more rapid and convenient. The idea is as shown in fig. 3, a V-graph (Voronoi, Voronoi diagram) is used to process spatial position information in a scene model to generate a grid diagram, for a plurality of discrete points in the scene model, a Delaunay triangulation network (a triangular network which is full of space but not intersected) is formed, then the center of a circumscribed circle of each triangle of the triangulation network is found, and finally the centers of circumscribed circles of adjacent triangles are connected to form a polygonal network using each triangle vertex as a generator, where the polygonal network is a connected graph.

By taking this idea as a reference, the target area in the actual scene is not a point, and the target area can be expanded for each target area to form boundary lines, such boundary lines represent a traversable route E in space, the intersection points of the boundary lines are nodes V, and route information of each route is determined based on the attributes of each boundary line, so that the connected graph G (V, E) is obtained. As shown in fig. 4, the connected graph is generated by performing the expansion process on the target region.

Based on the embodiment shown in fig. 1, another flow of the path planning method is further provided in the embodiment of the present invention, as shown in fig. 5, which may include the following steps.

S501, acquiring path information between every two adjacent nodes and path information between each termination node and a preset virtual node in a preset scene, wherein the preset scene comprises a plurality of termination nodes, the virtual node is virtually connected with each termination node, and the path information between the virtual node and each termination node is the same.

And S502, determining the optimal path from each node to the virtual node in the preset scene by using a preset path planning algorithm according to the path information between every two adjacent nodes and the path information between each termination node and the virtual node.

And S503, according to the designated optimal path from the designated node to the virtual node, starting path backtracking from the virtual node to obtain a target optimal path from the designated node to a target termination node, wherein the designated node is any node except each termination node in a preset scene, and the target termination node is a termination node on the designated optimal path.

S504, aiming at a path between any two adjacent nodes, acquiring environment data acquired by detection equipment for detecting the environment of the path; and correcting the path information of the path according to the environment data.

And S505, updating the optimal path from each node to the virtual node in the preset scene by using a path planning algorithm according to the corrected path information between every two adjacent nodes and the path information between each termination node and the virtual node.

And S506, according to the updated designated optimal path, starting path backtracking from the virtual node to obtain an updated target optimal path.

In an implementation manner of the embodiment of the present invention, for a special scene such as a fire, the feasibility of the path is also influenced by the impression of factors such as smoke, flame, and people stream, and in consideration of the personnel safety and the evacuation efficiency, the planned route needs to be iteratively optimized according to the factors.

After a target optimal path from a designated node to a target termination node is planned and obtained, environment data acquired by detection equipment for detecting the environment of the path is acquired for the path between any two adjacent nodes, wherein the detection equipment can be a smoke detector, a flame detector, a temperature sensor, a camera, a velometer and the like, and different detection equipment can detect different environment data, such as smoke concentration detected by the smoke detector, flame temperature detected by the flame detector and the temperature sensor, crowd density detected by the camera and crowd passing speed detected by the velometer. Among these pieces of environment data, there are those in which the environment data is positively correlated with the route information, for example, the smoke concentration, the flame temperature, the crowd density, and the like are positively correlated with the route length, and those in which the environment data is negatively correlated with the route information, for example, the crowd passing speed is negatively correlated with the route length, and therefore, the route information of the route can be corrected based on the environment data and the known correlation.

Taking the influence of the flame temperature on the path information as an example, the path information is the path equivalent length, and the corrected equivalent path length can be calculated according to the formula (1).

Wherein L (t) represents the corrected equivalent path length, L represents the original path length, t represents the flame temperature, t represents₀Denotes the unaffected temperature in the path, t₁Indicating the maximum tolerated temperature of the population. It can be seen from equation (1) that the higher the flame temperature is, the longer the path becomes, the less suitable it is for traffic.

Taking the influence of the crowd on the path blockage as an example, considering two influence factors of the crowd density and the crowd passing speed on one path, the corrected equivalent path length can be calculated according to the formula (2).

Wherein f (ρ) represents the crowd density, and f (v) represents the crowd passing speed. Then it can be seen from equation (2) that the equivalent path length is proportional to the crowd density and inversely proportional to the crowd passing speed.

Except for flame temperature, crowd density and crowd passing speed, the smoke concentration in the path, the damage degree of the path and the like can be quantitatively converted into the equivalent path length. The above formulas (1) and (2) can be modified to some extent for different scenarios, and the quantitative relationship expressed by the formulas can be derived through experiments or simulations, which are not illustrated here.

After the path information is corrected, path planning can be performed again by using a path planning algorithm according to the corrected path information and the path information between each termination node and the virtual node, the optimal path from each node to the virtual node in the preset scene is updated, and the updated target optimal path is obtained through further path backtracking.

In order to ensure real-time update, in an implementation manner of the embodiment of the present invention, the environmental data collected by the detection devices on each path should be acquired at intervals, so as to implement real-time update of the optimal path.

According to the embodiment of the invention, the environmental change condition under the whole preset scene can be monitored in real time, the optimal path from the designated node to each termination node is updated in time according to the acquired environmental data, and the accuracy and the real-time property of the output of the optimal path are ensured.

Based on the embodiment shown in fig. 1, another flow of the path planning method is further provided in the embodiment of the present invention, as shown in fig. 6, which may include the following steps.

S601, acquiring path information between every two adjacent nodes and path information between each termination node and a preset virtual node in a preset scene, wherein the preset scene comprises a plurality of termination nodes, and the virtual node is virtually connected with each termination node and is the same as the path information between each termination node.

S602, determining the optimal path from each node to the virtual node in the preset scene by using a preset path planning algorithm according to the path information between every two adjacent nodes and the path information between each termination node and the virtual node.

And S603, according to the designated optimal path from the designated node to the virtual node, starting path backtracking from the virtual node to obtain a target optimal path from the designated node to a target termination node, wherein the designated node is any node except each termination node in a preset scene, and the target termination node is a termination node on the designated optimal path.

S604, the path information of the target optimal path is sent to each indicator arranged on the target optimal path, so that each indicator indicates the path direction of the target optimal path according to the path information of the target optimal path.

In an implementation manner of the embodiment of the present invention, after a target optimal path from a designated node to a target terminating node is determined, path information of the path needs to be output, in a specific scene such as fire early warning and evacuation, the output manner is to send the path information of the target optimal path to each indicator arranged on the target optimal path, and after receiving the path information of the path, each indicator can indicate the path direction of the path according to the path information. The indicator can be arranged between every two nodes, and the indication mode of the specific indicator can be arrow indication or text indication and the like.

The target optimal path from the designated node to the target termination node is output to the indicators distributed on the path, and the indicators can clearly indicate the path direction of the path, so that the crowd evacuation efficiency under specific scenes such as fire early warning evacuation and the like is improved, and the crowd safety is ensured.

For convenience of understanding, the path planning method provided by the embodiment of the invention is described in detail below with reference to a specific scene of building fire early warning evacuation. As shown in fig. 7, the method for intelligently evacuating a building fire may include the following steps.

And S701, acquiring a three-dimensional model of the building.

S702, generating a path planning connected graph G (V, E).

The three-dimensional model of the building is converted into a path planning connected graph G (V, E) with weights, which is used for subsequent path planning, as described in the embodiment shown in fig. 2, a manual labeling method or an "image expansion" method may be adopted to generate the path planning connected graph, and details are not repeated here. The weight carried by the path planning connected graph is set according to the path length of each path, and the weight is inversely proportional to the path length.

And S703, planning the optimal path with multiple starting points and multiple end points.

The multi-starting-point and multi-end-point path planning means that for a plurality of starting points, one path with the shortest path to a plurality of end points is planned for each starting point. In the embodiment of the present invention, the traditional Dijkstra algorithm is improved by using an equivalent idea, and a specific path planning process is shown in fig. 8, and includes: s801, initializing a weighted path planning connection graph G (V, E), and determining that a plurality of end points S1, S2 and S3 … … exist. S802, setting virtual endpoints S ', S' to be virtually connected with all endpoints, and setting the weight to be W0. And S803, with the S 'as an end point, planning the shortest path from all points in the connected graph to the S' by referring to a single-source Dijkstra algorithm. S804, backtracking the shortest path and outputting each node from the last but one point.

In addition, in the process of planning the multi-start multi-end optimal path, influencing factors such as flame and people stream need to be acquired, the weight of each path is adjusted according to the influencing factors, and the multi-start multi-end optimal path planning result is updated. Specifically, the influence of the influencing factor on the optimal path planning is shown in the embodiment shown in fig. 5, and is not described herein again.

S704, outputting the direction of each node.

After the optimal path from each node to all the terminals is planned, the path information (namely the directions of all the nodes on the path) of the optimal path is issued to the evacuation indicator lamps on each path in the building, and the evacuation indicator lamps point to the direction of the optimal path so as to indicate the crowd to safely and quickly escape from the fire scene.

Corresponding to the above method embodiment, an embodiment of the present invention provides a path planning apparatus, and as shown in fig. 9, the apparatus may include:

an obtaining module 910, configured to obtain path information between every two adjacent nodes and path information between each termination node and a preset virtual node in a preset scenario, where the preset scenario includes multiple termination nodes, and the virtual node is virtually connected to each termination node and has the same path information as the path information between each termination node;

a path calculation module 920, configured to determine, according to path information between every two adjacent nodes and path information between each termination node and a virtual node, an optimal path from each node to the virtual node in a preset scenario by using a preset path planning algorithm;

a backtracking module 930, configured to perform path backtracking from a virtual node according to an assigned optimal path from an assigned node to the virtual node, and obtain a target optimal path from the assigned node to a target termination node, where the assigned node is any node in a preset scene except for each termination node, and the target termination node is a termination node on the assigned optimal path.

Optionally, the apparatus may further include: the system comprises a connected graph generating module, a target area generating module and a target area generating module, wherein the connected graph generating module is used for acquiring a scene model of a preset scene, and the scene model comprises a plurality of target areas containing targets; performing expansion processing on all target areas to obtain boundary lines of every two adjacent expanded target areas and intersection points of the boundary lines; generating a connected graph according to the boundary lines and the intersection points of the boundary lines, wherein the connected graph comprises a node identifier of each node and path information between every two adjacent nodes, each node is the intersection point of each boundary line, and the path information between every two adjacent nodes is determined according to the attribute of each boundary line;

the obtaining module 910 may be specifically configured to read path information between every two adjacent nodes from the connected graph.

Optionally, the path information includes a path length;

the path calculation module 920 may be specifically configured to calculate, for each node in a preset scene, a length of each path from the node to a virtual node by using a preset path planning algorithm according to a path length between each two adjacent nodes and a path length between each termination node and the virtual node; and determining the path with the shortest length in each path as the optimal path from the node to the virtual node.

the backtracking module 930 may be specifically configured to start path backtracking from a virtual node to obtain a target optimal path from a start node to a target end node in a floor according to a designated optimal path from the start node to the virtual node for any start node in the floors in a sequence from a low floor to a high floor; until the target optimal path from the specified node in the target floor to the target termination node in the target floor is traced back; wherein, the starting node is the termination node of the previous floor; and determining the target optimal path from the designated node to the target termination node in the starting floor according to the backtracking target optimal path of each floor.

Optionally, the apparatus may further include: the path updating module is used for acquiring environment data acquired by detection equipment for detecting the environment of a path aiming at the path between any two adjacent nodes; according to the environment data, correcting the path information of the path; updating the optimal path from each node to the virtual node in the preset scene by using a path planning algorithm according to the corrected path information between every two adjacent nodes and the path information between each termination node and the virtual node; and according to the updated designated optimal path, starting path backtracking from the virtual node to obtain an updated target optimal path.

Optionally, the apparatus may further include: and the output module is used for sending the path information of the target optimal path to each indicator arranged on the target optimal path, so that each indicator indicates the path direction of the target optimal path according to the path information of the target optimal path.

An embodiment of the present invention further provides an electronic device, as shown in fig. 10, including a processor 1001 and a machine-readable storage medium 1002, where the machine-readable storage medium 1002 stores machine-executable instructions capable of being executed by the processor 1001, and the processor 1001 is caused by the machine-executable instructions to: implementing any of the above path planning methods.

The machine-readable storage medium may include a RAM (Random Access Memory) and a NVM (Non-volatile Memory), such as at least one disk Memory. Alternatively, the machine-readable storage medium may be at least one memory device located remotely from the processor.

The Processor may be a general-purpose Processor including a CPU, an NP (Network Processor), and the like; but also a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component.

Data transmission between the processor 1001 and the machine-readable storage medium 1002 may be performed by a wired connection or a wireless connection, and communication between the electronic device and another device may be performed by a wired communication interface or a wireless communication interface. Fig. 10 is a diagram illustrating an example of data transmission via a bus, and is not limited to a specific connection manner.

In the embodiment of the present invention, the processor can realize that: by setting a virtual node which is virtually connected with each termination node and has the same path information with each termination node, the optimal path from each real node to the virtual node in the preset scene can be determined by using a preset path planning algorithm, and finally, a target optimal path from any real node to the target termination node in the preset scene can be obtained by path backtracking. Therefore, path planning does not need to be carried out on the plurality of termination nodes one by one, the path planning process under the multi-termination-node scene is simplified, and the path planning efficiency under the multi-termination-node scene is further improved.

In addition, an embodiment of the present invention provides a machine-readable storage medium, where machine-executable instructions are stored in the machine-readable storage medium, and when the machine-executable instructions are loaded and executed by a processor, the method for planning a path according to any one of the foregoing embodiments is implemented.

In the embodiment of the present invention, the machine-readable storage medium stores machine-executable instructions for executing the path planning method provided in the embodiment of the present invention when running, so that the following can be implemented: by setting a virtual node which is virtually connected with each termination node and has the same path information with each termination node, the optimal path from each real node to the virtual node in the preset scene can be determined by using a preset path planning algorithm, and finally, the target optimal path from any real node to the target termination node in the preset scene can be obtained by path backtracking. Therefore, path planning does not need to be carried out on the plurality of termination nodes one by one, the path planning process under the multi-termination-node scene is simplified, and the path planning efficiency under the multi-termination-node scene is further improved.

In a further embodiment provided by the present invention, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to perform any of the path planning methods of the above embodiments.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored on a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website, computer, server, or data center to another website, computer, server, or data center via wire (e.g., coaxial cable, fiber, DSL (Digital Subscriber Line)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., a floppy Disk, a hard Disk, a magnetic tape), an optical medium (e.g., a DVD (Digital Versatile Disk)), or a semiconductor medium (e.g., a SSD (Solid State Disk)), etc.

An embodiment of the present invention further provides a path indicating system, as shown in fig. 11, including an electronic device 1101 and a plurality of indicators 1102, where the plurality of indicators are dispersedly disposed in a preset scene;

the electronic device 1101 is configured to acquire path information between every two adjacent nodes and path information between each termination node and a preset virtual node in a preset scene, where the preset scene includes a plurality of termination nodes, and the virtual node is virtually connected to each termination node and has the same path information as the path information between each termination node; determining an optimal path from each node to the virtual node in a preset scene by using a preset path planning algorithm according to the path information between every two adjacent nodes and the path information between each termination node and the virtual node; according to the designated optimal path from the designated node to the virtual node, starting path backtracking from the virtual node to obtain a target optimal path from the designated node to a target termination node, wherein the designated node is any node except each termination node in a preset scene, and the target termination node is a termination node on the designated optimal path; the path information of the target optimal path is sent to each indicator 1102 arranged on the target optimal path;

each indicator 1102 is configured to indicate a path direction of the target optimal path according to the path information of the target optimal path.

Optionally, the path indicating system may further include: a plurality of detection devices (not shown in the figure), wherein the detection devices are arranged between every two adjacent nodes in a preset scene;

the electronic device can also be used for acquiring environment data acquired by a detection device for detecting the environment of a path according to the path between any two adjacent nodes; according to the environment data, correcting the path information of the path; updating the optimal path from each node to the virtual node in the preset scene by using a path planning algorithm according to the corrected path information between every two adjacent nodes and the path information between each termination node and the virtual node; and according to the updated designated optimal path, starting path backtracking from the virtual node to obtain an updated target optimal path.

By applying the embodiment of the invention, a virtual node is set, the virtual node is virtually connected with each termination node, and the path information between the virtual node and each termination node is the same, so that the optimal path from each real node to the virtual node in the preset scene can be determined by using a preset path planning algorithm, and finally, a target optimal path from any real node to a target termination node in the preset scene can be obtained by path backtracking. Therefore, path planning does not need to be carried out on the plurality of termination nodes one by one, the path planning process under the multi-termination-node scene is simplified, and the path planning efficiency under the multi-termination-node scene is further improved. And the optimal path from the designated node to all the termination nodes is output to each indicator arranged on the path, and the indicators can clearly indicate the path direction of the path, so that the crowd evacuation efficiency under specific scenes such as fire early warning evacuation and the like is improved, and the crowd safety is ensured.

It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the embodiments of the path planning apparatus, the electronic device, the machine-readable storage medium, the computer program product and the monitoring system, since they are substantially similar to the embodiments of the method, the description is relatively simple, and it is sufficient to refer to the partial description of the embodiments of the method for relevant points.

The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.

Claims

1. A method of path planning, the method comprising:

determining an optimal path from each node to the virtual node in the preset scene by using a preset path planning algorithm according to the path information between each two adjacent nodes and the path information between each termination node and the virtual node;

and according to the appointed optimal path from the appointed node to the virtual node, starting path backtracking from the virtual node to obtain a target optimal path from the appointed node to a target termination node, wherein the appointed node is any node except each termination node in the preset scene, and the target termination node is the termination node on the appointed optimal path.

2. The method according to claim 1, wherein before the step of obtaining the path information between each two adjacent nodes and the path information between each terminating node and the preset virtual node in the preset scenario, the method further comprises:

generating a connected graph according to the boundary lines and the intersection points of the boundary lines, wherein the connected graph comprises a node identifier of each node and path information between every two adjacent nodes, each node is the intersection point of the boundary lines, and the path information between every two adjacent nodes is determined according to the attribute of each boundary line;

the step of obtaining the path information between every two adjacent nodes in the preset scene includes:

and reading the path information between every two adjacent nodes from the connected graph.

3. The method of claim 1, wherein the path information comprises a path length;

the step of determining an optimal path from each node to the virtual node in the preset scene by using a preset path planning algorithm according to the path information between each two adjacent nodes and the path information between each termination node and the virtual node includes:

for each node in the preset scene, calculating the length of each path from the node to the virtual node by using a preset path planning algorithm according to the path length between each two adjacent nodes and the path length between each termination node and the virtual node; and determining the path with the shortest length in each path as the optimal path from the node to the virtual node.

4. The method of claim 1, wherein the preset scene is a building scene, the building scene comprising a plurality of floors;

the step of obtaining the target optimal path from the designated node to the target termination node by starting path backtracking from the virtual node according to the designated optimal path from the designated node to the virtual node comprises the following steps:

starting from a starting floor, according to the sequence of floors from low to high, aiming at any starting node in the floors, according to the appointed optimal path from the starting node to the virtual node, starting path backtracking from the virtual node to obtain the target optimal path from the starting node to the target termination node in the floor; until a target optimal path from a designated node in a target floor to a target termination node in the target floor is traced back; wherein the starting node is a termination node of the previous floor;

and determining the optimal target path from the designated node to the target termination node in the starting floor according to the optimal target path of each floor obtained by backtracking.

5. The method according to claim 1, wherein after the step of starting path backtracking from the virtual node according to the designated optimal path from the designated node to the virtual node to obtain the target optimal path from the designated node to the target termination node, the method further comprises:

updating the optimal path from each node to the virtual node in the preset scene by using the path planning algorithm according to the modified path information between each two adjacent nodes and the path information between each termination node and the virtual node;

and according to the updated designated optimal path, starting path backtracking from the virtual node to obtain the updated target optimal path.

6. The method according to claim 1, wherein after the step of starting path backtracking from the virtual node according to the designated optimal path from the designated node to the virtual node to obtain the target optimal path from the designated node to the target termination node, the method further comprises:

7. A path planning apparatus, the apparatus comprising:

a path calculation module, configured to determine, according to the path information between each two adjacent nodes and the path information between each termination node and the virtual node, an optimal path from each node to the virtual node in the preset scenario by using a preset path planning algorithm;

and the backtracking module is used for starting path backtracking from the virtual node according to the designated optimal path from the designated node to the virtual node to obtain a target optimal path from the designated node to a target termination node, wherein the designated node is any node except each termination node in the preset scene, and the target termination node is a termination node on the designated optimal path.

8. An electronic device comprising a processor and a machine-readable storage medium storing machine-executable instructions executable by the processor, the processor being caused by the machine-executable instructions to: carrying out the method of any one of claims 1 to 6.

9. A path indicating system is characterized by comprising electronic equipment and a plurality of indicators, wherein the indicators are distributed in a preset scene;

the electronic device is configured to acquire path information between every two adjacent nodes and path information between each termination node and a preset virtual node in the preset scene, where the preset scene includes a plurality of termination nodes, and the virtual node is virtually connected to each termination node and has the same path information as the path information between each termination node; determining an optimal path from each node to the virtual node in the preset scene by using a preset path planning algorithm according to the path information between each two adjacent nodes and the path information between each termination node and the virtual node; according to an appointed optimal path from an appointed node to the virtual node, starting path backtracking from the virtual node to obtain a target optimal path from the appointed node to a target termination node, wherein the appointed node is any node except each termination node in the preset scene, and the target termination node is the termination node on the appointed optimal path; sending the path information of the target optimal path to each indicator arranged on the target optimal path;

and the indicators are used for indicating the path direction of the target optimal path according to the path information of the target optimal path.

10. The path indicating system according to claim 9, further comprising: the detection devices are arranged between every two adjacent nodes in the preset scene;

the electronic equipment is also used for acquiring environment data acquired by detection equipment for detecting the environment of a path aiming at the path between any two adjacent nodes; according to the environment data, correcting the path information of the path; updating the optimal path from each node to the virtual node in the preset scene by using the path planning algorithm according to the modified path information between each two adjacent nodes and the path information between each termination node and the virtual node; and according to the updated designated optimal path, starting path backtracking from the virtual node to obtain the updated target optimal path.