Rapid search path planning method and device in search and rescue environment

Abstract

The invention provides a rapid search path planning method and device in a search and rescue environment, and the method comprises the steps: determining a search and rescue region, dividing the search and rescue region into a plurality of grids, constructing POMDP seven-tuple information corresponding to each grid, and storing the POMDP seven-tuple information in the search and rescue region; the POMDP seven-tuple information comprises a finite state set, a finite action set, a state transition matrix, an award, a finite observation set, an observation probability and a discount coefficient; acquiring current position information of the search and rescue robot and surrounding map environment information of the search and rescue robot in real time, determining a grid where the search and rescue robot is located currently based on the current position information, and determining a next target grid of the search and rescue robot through a partially observable Markov decision algorithm based on POMDP seven-tuple information corresponding to the grid where the search and rescue robot is located currently; and determining a search path of the search and rescue robot based on the target grid and the surrounding map environment information. According to the invention, the robot can complete the searching work of fully autonomous searching and mapping at the same time under the condition that the environment map is unknown, and the adaptability of the robot to the search and rescue environment is improved.

Description

Technical Field

[0001] The present invention relates to the field of robotics technology, and in particular to a method and device for rapid search path planning in a search and rescue environment. Background Art

[0002] With the development of artificial intelligence and robotics, the application areas of unmanned vehicles and drones are becoming more and more extensive, and they are beginning to replace people to complete some complex tasks in harsh environments. The use of unmanned vehicles, drones, etc. for post-disaster search and rescue has been a hot topic of research at home and abroad in recent years.

[0003] Unmanned vehicles are also called robots. When performing search and rescue missions, robots need to plan paths. Traditional path planning algorithms include search-based (such as A, A*) methods and sampling-based (RRT, PRM) methods, which can plan collision-free paths from the starting point to the end point; however, such algorithms cannot fully consider environmental information. In order for robots to perform complex tasks better, they must be made smarter and better able to imitate human behavior. Reinforcement learning is a machine learning method. In reinforcement learning, the agent selects actions based on the state of the environment and obtains rewards or penalties from the environment. It improves its decision-making strategy through continuous trial and error learning to obtain better long-term returns; by modeling states, rewards, actions, etc., robots can be trained to perform complex tasks; however, this method also has great disadvantages, such as the need for interactive learning between the agent and the environment, which requires a large amount of interactive data, which is very expensive and time-consuming in some tasks.

[0004] Although existing robots can plan paths in search and rescue missions, existing path planning algorithms require robots to work in a known environment map or be familiar with the working environment, which limits their ability to work in unknown and unfamiliar environments. As a result, existing robots cannot complete search and rescue work in unknown environments. Therefore, how to enable robots to complete fully autonomous search work while exploring and mapping in unknown environments and improve their adaptability in search and rescue environments are technical issues that need to be solved urgently. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides a method and device for rapid search path planning in a search and rescue environment to eliminate or improve one or more defects existing in the prior art.

[0006] One aspect of the present invention provides a method for rapid search path planning in a search and rescue environment, the method comprising: Determine a search and rescue area, divide the search and rescue area into a plurality of grids, and construct POMDP seven-tuple information corresponding to each grid, wherein the POMDP seven-tuple information includes a finite state set, a finite action set, a state transition matrix, a reward, a finite observation set, an observation probability, and a discount factor; Acquire the current position information of the search and rescue robot and the surrounding map environment information of the search and rescue robot in real time, determine the current grid of the search and rescue robot based on the current position information of the search and rescue robot, and determine the next target grid of the search and rescue robot through a partially observable Markov decision algorithm based on the POMDP seven-tuple information corresponding to the current grid; The search path of the search and rescue robot is determined based on the target grid of the search and rescue robot for the next step and the surrounding map environment information of the search and rescue robot.

[0007] In some embodiments of the present invention, constructing POMDP seven-tuple information corresponding to each grid includes: Determine the search and rescue priority corresponding to each of the grids, and determine the state set based on the search and rescue priority corresponding to the grid; Determine adjacent grids of the grid, and determine the limited action set based on the adjacent grids; A limited observation set corresponding to the grid is determined based on whether there is a trapped person in the grid.

[0008] In some embodiments of the present invention, determining the next target grid of the search and rescue robot through a partially observable Markov decision algorithm based on the POMDP seven-tuple information corresponding to the current grid includes: Determining a traversable area based on the acquired surrounding map environment information of the search and rescue robot; The next target grid of the search and rescue robot is determined by a partially observable Markov decision algorithm based on the POMDP seven-tuple information corresponding to the current grid and the traversable area.

[0009] In some embodiments of the present invention, determining a traversable area based on the acquired surrounding map environment information of the search and rescue robot includes: Obtain the center point of each grid, and use each center point as each boundary point; Determine a connection relationship between boundary points based on the surrounding map environment information, where the connection relationship is connected, disconnected or unknown; A passable area is determined based on the connection relationship between the boundary points.

[0010] In some embodiments of the present invention, obtaining the current position information of the search and rescue robot and the surrounding map environment information of the search and rescue robot in real time includes: Based on the instant positioning and map building method, the current position information of the search and rescue robot and the surrounding map environment information of the search and rescue robot are obtained in real time.

[0011] In some embodiments of the present invention, determining the search path of the search and rescue robot based on the target grid of the next step of the search and rescue robot and the surrounding map environment information of the search and rescue robot includes: The search path of the search and rescue robot is determined by a robot autonomous navigation algorithm based on the target grid of the search and rescue robot's next step and the surrounding map environment information of the search and rescue robot.

[0012] In some embodiments of the present invention, there are multiple search and rescue robots, and the multiple search and rescue robots all communicate with a common information processing node, and the multiple search and rescue robots share current location information, surrounding map environment information, and search paths.

[0013] In some embodiments of the present invention, multiple search and rescue robots share current location information, surrounding map environment information, and search paths, including: Obtaining current location information, surrounding map environment information, and search paths corresponding to each of the search and rescue robots; The current position information, surrounding map environment information and search path corresponding to each of the search and rescue robots are integrated based on the common information processing node to obtain integrated information; The fused information is sent to each of the search and rescue robots.

[0014] According to another aspect of the present invention, a rapid search path planning system in a search and rescue environment is also disclosed, the system comprising a processor, a memory and a computer program stored in the memory, the processor is used to execute the computer program, and when the computer program is executed, the system implements the steps of the method described in any of the above embodiments.

[0015] According to yet another aspect of the present invention, there is provided a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described in any of the above embodiments are implemented.

[0016] The method and device for rapid search path planning in a search and rescue environment disclosed in the above embodiment of the present invention first divides the search and rescue environment into grids, and then constructs POMDP seven-tuple information for each grid, thereby calculating the next action with the maximum reward for the search and rescue robot based on the partially observable Markov decision algorithm; and in the search and rescue process, the method of exploring while mapping is adopted to complete the planning of the search path. This method can realize a fully autonomous search operation of exploring while mapping when the environment is partially known and the map is unknown, thereby improving the robot's adaptability in the search and rescue environment.

[0017] In addition, the rapid search path planning method in the present application can use multiple search and rescue robots to work together, and multiple search and rescue robots share current location information, surrounding map environment information and search paths. This method further improves the search and rescue efficiency and reduces the search and rescue time.

[0018] Additional advantages, purposes, and features of the present invention will be described in part in the following description, and will become apparent to those skilled in the art after studying the following, or may be learned from the practice of the present invention. The purposes and other advantages of the present invention may be achieved and obtained by the structures specifically indicated in the specification and the accompanying drawings.

[0019] Those skilled in the art will appreciate that the objectives and advantages that can be achieved with the present invention are not limited to the above specific description, and the above and other objectives that can be achieved by the present invention will be more clearly understood from the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings described herein are used to provide a further understanding of the present invention, constitute a part of this application, and do not constitute a limitation of the present invention. The components in the drawings are not drawn to scale, but are only for illustrating the principles of the present invention. In order to facilitate the illustration and description of some parts of the present invention, the corresponding parts in the drawings may be enlarged, that is, they may become larger relative to other components in the exemplary device actually manufactured according to the present invention. In the drawings: Figure 1 Schematic diagram of a flow chart of a method for rapid search path planning in a search and rescue environment according to an embodiment of the present application.

[0021] Figure 2a A schematic diagram of a search and rescue area for a fast search path planning method according to an embodiment of the present application.

[0022] Figure 2b A schematic diagram of a grid map of a fast search path planning method according to an embodiment of the present application.

[0023] Figure 3a The moving direction of the search and rescue robot according to an embodiment of the present application is shown in FIG. Figure 1 .

[0024] Figure 3b Schematic diagram 2 of the moving direction of the search and rescue robot according to an embodiment of the present application.

[0025] Figure 4a This is a map diagram used in the simulation experiment. Figure 1 .

[0026] Figure 4b This is the second diagram of the map used in the simulation experiment.

[0027] Figure 5a Schematic diagram of the rescue process of the search and rescue robot during the simulation experiment Figure 1 .

[0028] Figure 5b This is the second schematic diagram of the search and rescue process of the search and rescue robot during the simulation experiment.

[0029] Figure 5c Schematic diagram 3 of the search and rescue process of the search and rescue robot during the simulation experiment.

[0030] Figure 5d Schematic diagram 4 of the search and rescue process of the search and rescue robot during the simulation experiment.

[0031] Figure 6 This is a schematic diagram of the communication structure of multiple search and rescue robots according to an embodiment of the present application. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments and the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0033] It should also be noted that, in order to avoid obscuring the present invention due to unnecessary details, only structures and / or processing steps closely related to the solutions according to the present invention are shown in the accompanying drawings, while other details that are not closely related to the present invention are omitted.

[0034] It should be emphasized that the term “include / comprises” when used herein refers to the presence of features, elements, steps or components, but does not exclude the presence or addition of one or more other features, elements, steps or components.

[0035] It should also be noted here that, unless otherwise specified, the term "connection" in this article can refer not only to a direct connection, but also to an indirect connection with an intermediary, not only to a wired connection, but also to a wireless connection, and the specific connection can be changed based on the actual application scenario.

[0036] Simulating a real search and rescue scenario, using a search and rescue robot for search and rescue, searching every part of the scene in the shortest time, so as to search for all trapped persons, this process can be modeled as full coverage path planning. The full coverage path planning algorithm is a path planning algorithm used in automation systems, which aims to ensure that the search and rescue robot can cover all points or areas in a given environment. Its goal is to find a path that allows the search and rescue robot to pass through every point or area on the path, thereby achieving full coverage of the entire environment.

[0037] The rapid search path planning method in the search and rescue environment of the present application applies decision-making planning to the search and rescue scenario, and at the same time combines the autonomous detection algorithm to enable the robot to patrol every part of the environment without a map and partial knowledge of the environmental conditions. The present application can enable the robot to realize fully autonomous search operations while exploring and building maps in an unknown environment, so as to pass all grid nodes on the path as quickly as possible, and can improve the search and rescue efficiency by the collaborative work of multiple search and rescue robots.

[0038] In order to better understand the present invention, the following are explanations of relevant terms: Partially observable Markov decision process (POMDP) ​​is an extension of Markov decision process (MDP) and is used to solve decision problems in partially observable environment states.<S,A,T,R,Ω,O,λ> Modeling can well simulate the uncertainty in the environment. In POMDP, the environment faced by the decision maker is random and cannot be fully observed. It can only be inferred through a series of observed variables. At each moment, the system generates an observed variable based on the current state and the action performed. The observed variable provides partial information about the state of the system. The decision maker then updates its belief state based on the observed variable. The belief state is the probability value of each state. Then POMDP is solved and the next action is selected. The decision maker's goal is to find an optimal strategy to maximize the long-term cumulative reward.

[0039] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. In the accompanying drawings, the same reference numerals represent the same or similar components, or the same or similar steps.

[0040] Figure 1 This is a flowchart of a method for rapid search path planning in a search and rescue environment according to an embodiment of the present application. As shown in the figure, the method for rapid search path planning includes at least steps S10 to S30.

[0041] Step S10: Determine a search and rescue area, divide the search and rescue area into multiple grids, and construct POMDP seven-tuple information corresponding to each grid, wherein the POMDP seven-tuple information includes a finite state set, a finite action set, a state transition matrix, a reward, a finite observation set, an observation probability, and a discount factor.

[0042] In this step, the search and rescue environment is divided into grids to generate a grid map. Each grid represents an area in the environment and serves as a state of the POMDP, that is, each grid is modeled using the POMDP. The modeling information includes the robot's possible actions, observation results, and state transition probabilities. Figure 2aThe figure shows a schematic diagram of the search and rescue area. The search and rescue map can be established based on gazebo. The map size can be 20m*20m, and obstacles are randomly placed in the map. The search and rescue map can be further converted into a 10*10 grid map, where the size of each grid is 2m*2m. The corresponding grid map schematic diagram is shown in Figure 2b As shown, in Figure 2b In the figure, the solid lines in the two grids are obstacles, the solid lines indicate that they are impassable, and the dotted lines indicate that they are passable. In this step, the grid map is modeled according to the POMDP seven-tuple to simulate the real search and rescue environment, so that the robot continuously plans the path at the starting point to travel through all the grids in the shortest possible time.

[0043] In real search and rescue scenarios, the probability of trapped people in each place is different. For example, during an earthquake, the probability of people under a collapsed building is higher than in the wild, so the priority of collapsed buildings is higher during search and rescue. This application draws on actual search and rescue scenarios to assign a priority to each grid in the grid map, representing its importance. The higher the reward obtained when passing through a grid with a high priority, the probability of things observed in grids of different priorities is also different. Each grid will be assigned an observation variable, which is an element in the observation space set.

[0044] In the process of POMDP seven-tuple modeling, the probability of the location distribution of the rescued personnel is taken into account, and the grid is divided into different priorities to represent the urgency of the grid. The higher the priority, the greater the probability of the trapped personnel, and the greater the reward. Set two types of observation information (o1, o2) and assign different observation functions; set different values ​​for the observation information according to the specific situation, and o1 is more associated with high priority, that is, the higher the priority grid, the greater the probability of observing o1, and the lower the priority grid, the greater the probability of observing 02.

[0045] Exemplarily, constructing the POMDP seven-tuple information corresponding to each of the grids includes: determining the search and rescue priority corresponding to each of the grids, determining the state set based on the search and rescue priority corresponding to the grid; determining the adjacent grids of the grid, determining the limited action set based on the adjacent grids; and determining the limited observation set corresponding to the grid based on whether there are trapped persons in the grid. In this embodiment, the search and rescue priority corresponding to each grid can be determined based on the terrain distribution of the search and rescue area; exemplarily, the search and rescue priority can be divided into S1, S2 and S3 levels, and the search and rescue priority is the urgency of the search and rescue site. The higher the search and rescue priority, the greater the probability of the existence of trapped persons, the more urgent the terrain is, and the more it should be searched first; and the distribution of terrains with different priorities will also be different, and the specific priority of each grid can be determined according to actual conditions.

[0046] Specifically, in the POMDP seven-tuple<S,A,T,R,Ω,O,λ> In the finite state set S=<S1,S2,S3> Represents the probability that the grid belongs to each level of priority; the finite action set A=<a1,a2,a3,a4,a5,a6,a7,a8> Represents the eight neighboring grids around a grid. When the robot moves to a grid, its next step can be to move from the grid to the next grid in the eight directions around it. State transfer matrix Indicates that in state s, take action a to reach the next state The probability of moving from one priority level to another priority level via a certain direction is related to the priority allocation of the environment. represents the reward for taking action a to reach state s; because the priorities of S1, S2, and S3 gradually decrease, the rewards for moving to S1, S2, and S3 also gradually decrease. Finite observation set Ω =<o1,o2> It indicates whether there are trapped persons in the observed grid, that is, the set of phenomena observed by the robot during its movement. It can be the images captured by the camera or the data collected by the sensor. When the robot moves to a grid, it will obtain an observation variable. When it passes through a grid repeatedly, the observation variable obtained remains unchanged, that is, the data collected by the sensor at the same location will not change. The observation function O=pr(o|s,a) represents the probability of observing the observation variable o when taking action a to reach state s. The distribution of the finite observation set is related to the setting of the observation function and the environment.

[0047] Step S20: Acquire the current position information of the search and rescue robot and the surrounding map environment information of the search and rescue robot in real time, determine the current grid of the search and rescue robot based on the current position information of the search and rescue robot, and determine the next target grid of the search and rescue robot through a partially observable Markov decision algorithm based on the POMDP seven-tuple information corresponding to the current grid.

[0048] In this step, the robot's current position, state, and map information are constructed in real time through the lidar, and the POMDP model is used to calculate the next action with the maximum reward; after executing this action, the robot's state is updated based on the acquired environmental information to quickly traverse and search every corner of the environment. In this step, the robot's decision for each step in an unknown environment is determined based on the partially observable Markov decision algorithm (POMDP algorithm).

[0049] In some embodiments of the present invention, the next target grid of the search and rescue robot is determined through a partially observable Markov decision algorithm based on the POMDP seven-tuple information corresponding to the current grid, including: determining a traversable area based on the acquired surrounding map environment information of the search and rescue robot; determining the next target grid of the search and rescue robot through a partially observable Markov decision algorithm based on the POMDP seven-tuple information corresponding to the current grid and the traversable area.

[0050] Furthermore, determining the traversable area based on the acquired surrounding map environment information of the search and rescue robot includes the following steps: obtaining the center point of each grid, and using each center point as each boundary point; determining the connection relationship between the boundary points based on the surrounding map environment information, wherein the connection relationship is connected, disconnected or unknown; and determining the traversable area based on the connection relationship between the boundary points.

[0051] When a search and rescue robot performs a task in an unknown environment map, it first needs to obtain information such as a map of the environment as soon as possible. However, the main way to build a map in the prior art is to manually control the robot's movement, that is, to traverse all unknown environments, collect environmental feature information through sensors, and then build a global map based on the environmental feature information collected by the sensors. This method requires human control throughout the process, which is impossible to achieve in a search and rescue scenario. In order to further improve the intelligence of the search and rescue robot, the present application is based on the robot's autonomous exploration technology to allow the search and rescue robot to obtain the most complete and accurate environmental map in a limited time and without human intervention. Many existing map exploration strategies are based on boundaries, and boundaries are defined as the dividing line between unknown space and known space; the idea of ​​the boundary-based exploration strategy is to guide the robot to an unknown area to complete the exploration task, so the autonomous exploration task is generally divided into three steps: generating boundary points, selecting the boundary points with the highest evaluation value, and planning the path to the selected boundary points. The selection of the target boundary point is the key to effective exploration. The boundary-based exploration algorithm detects the boundary points between the explored area and the unknown area, processes and filters the boundary points, and continuously explores the boundary points with the largest comprehensive benefits as the target points until the exploration is completed when there are no boundary points.

[0052] In the above embodiment, the fast search path planning method obtains the current position information of the search and rescue robot and the surrounding map environment information of the search and rescue robot in real time based on the instant positioning and map construction method. Furthermore, the traversable area is determined based on the acquired surrounding map environment information of the search and rescue robot. The selection of boundary points must comprehensively consider information gain, navigation cost and robot positioning accuracy. This process consumes certain resources. When determining the traversable area, the present application can first select the center point of each grid in the grid map as the boundary point. The boundary points of each map are determined. Figure 2bThere are 100 grids in the grid map shown, so there are 100 boundary points; the connection between boundary points is connected (no obstacles between two boundary points), disconnected (there are obstacles between two boundary points) or unknown (not scanned by radar); during the exploration process, the search and rescue robot continuously scans all boundary points for connectivity through the laser radar, and constructs a traversable area. The robot can plan the path and perform tasks in this traversable area. At the beginning, the traversable area is very small. As the robot continues to move, the range scanned by the radar becomes larger and larger, and the traversable area gradually becomes larger.

[0053] In the process of searching, the search and rescue robot in the above embodiment obtains environmental information through sensors such as radar or camera, and constructs an environmental map in real time; this step adopts SLAM technology to achieve simultaneous positioning and map construction of the robot in an unknown environment. In addition, the present application can use the open source framework gmapping for environmental modeling, build a map while the robot is constantly moving, and construct a traversable area. The traversable area is as follows: Figure 3a and Figure 3b shown in Figure 3a In the figure, the gray lines connect all the known areas to form a traversable area, based on which the path navigation of the search and rescue robot is realized. Thus, the robot can move freely in the traversable area, and each decision will move to the next open grid. As the robot continues to perform tasks and build maps, the traversable area will continue to increase, such as Figure 5a , Figure 5b , Figure 5c , Figure 5d shown, since Figure 5a to Figure 5d , the traversable area gradually increases. It can be seen that the grid scanning algorithm can ensure that the robot uses the map information constructed in real time to complete navigation in each step, that is, it ensures that the search and rescue robot can build a map while exploring without an environmental map, and each decision makes full use of the known partial environment and map information, while ensuring that the rapid search path planning is completed independently by the search and rescue robot without manual navigation.

[0054] Step S30: determining a search path of the search and rescue robot based on the target grid of the next step of the search and rescue robot and the surrounding map environment information of the search and rescue robot.

[0055] In this step, a specific search path is determined, which enables the robot to walk toward the specified target point without colliding with obstacles, and when the search and rescue robot performs a search and rescue mission, it ensures that the grids with high priority are searched first and all grids are searched as quickly as possible. In one embodiment, the search path of the search and rescue robot is determined by a robot autonomous navigation algorithm based on the target grid of the search and rescue robot in the next step and the surrounding map environment information of the search and rescue robot; the purpose of the autonomous navigation algorithm is to enable the robot to effectively explore and navigate in an unknown environment.

[0056] For example, after obtaining the optimal action of the search and rescue robot, the navigation of the search and rescue robot can be further realized through the ROS system, specifically using the amcl and move_base function packages in the ROS system. The amcl function package will perform real-time positioning of the robot based on the sensor data carried by the robot (such as lidar scanning data); while the move_base function package is responsible for planning a collision-free path from the current position to the target position, and publishing the cmd_vel speed control topic to drive the movement of the robot.

[0057] In some embodiments of the present invention, there are multiple search and rescue robots, and the multiple search and rescue robots all communicate with a common information processing node, and the multiple search and rescue robots share current location information, surrounding map environment information, and search paths. In this embodiment, the search and rescue efficiency is further improved and the search and rescue time is reduced by the collaborative work of multiple search and rescue robots; and the multiple search and rescue robots all use the fast search path planning method disclosed in any of the above embodiments to implement path planning.

[0058] Furthermore, multiple search and rescue robots share current position information, surrounding map environment information and search paths, which may specifically include: obtaining the current position information, surrounding map environment information and search path corresponding to each of the search and rescue robots; fusing the current position information, surrounding map environment information and search path corresponding to each of the search and rescue robots based on the common information processing node to obtain fused information; and sending the fused information to each of the search and rescue robots.

[0059] In addition, in order to further improve the search and rescue efficiency of multiple search and rescue robots, it is also necessary to improve the communication efficiency between multiple search and rescue robots. In this application, each search and rescue robot needs to know the information of other robots in the process of performing tasks. If every two robots need to establish a connection, the entire communication system will be very complicated and inflexible when adding or reducing robots; therefore, this application adopts a communication method similar to a bus to realize the communication of multiple search and rescue robots. The robots exchange information by publishing topics or service communications. The communication structure diagram is shown in Figure 5; at this time, each robot publishes its own map construction, exploration results and other information to the public information processing node. After the public information processing node fuses this information, it sends the fused information to each robot in the form of topics or service communications, so that each robot has the field of view of all robots. Based on this method, we can flexibly add any number of search and rescue robots.

[0060] Through the above embodiments, it can be found that the fast search path planning method of the present application adopts a partially observable Markov decision method to determine the decision of the robot at each step in an unknown environment, and adopts simultaneous positioning and map construction technology to build a map, that is, in an unknown map environment, based on the robot's fully autonomous exploration and mapping algorithm, according to partial information of the environment, every place in the environment is quickly searched to determine whether there are people who need to be rescued.

[0061] In order to verify the effectiveness of the fast search path planning method of the present application, the present application further adopts the Robot Operating System (ROS) as the software framework, models the robot and the search and rescue environment in gazebo and conducts simulation experiments, and observes the experimental results through the rviz plug-in; the map schematic diagram used in the simulation experiment is as follows Figure 4a and Figure 4b As shown, based on the simulation results, it is found that the fast search path planning method of the present application can enable the robot to complete the search work of fully autonomous exploration and mapping in an unknown environment, thereby improving the robot's adaptability in the search and rescue environment.

[0062] Correspondingly, the present invention also provides a rapid search path planning system in a search and rescue environment, the system comprising a processor, a memory and a computer program stored in the memory, the processor is used to execute the computer program, and when the computer program is executed, the system implements the steps of the method described in any of the above embodiments.

[0063] Exemplarily, the rapid search path planning system may further include a path planning module, a robot navigation module, a simultaneous localization and mapping (SLAM) module, a multi-robot collaboration module, and a simulation experiment module. The functions of each module are as follows: Path planning module: divides the map into grid maps, and uses the partially observable Markov decision process (POMDP) ​​to model each grid into seven tuples, and finally solves to determine the robot's decision for each step in an unknown environment. This module calculates the optimal next action based on the robot's current position, state, and partial information about the environment, so as to quickly traverse and search every corner of the environment.

[0064] Robot navigation module: The robot navigation is realized by using the amcl, move_base and other function packages in the ros system. amcl can realize the positioning of the robot, move_base can plan a collision-free path from the starting point to the end point, and publish the speed topic to control the movement of the robot.

[0065] Simultaneous Localization and Mapping (SLAM) module: During the robot's search, it obtains environmental information through sensors such as radar or cameras, and builds an environmental map in real time. This module uses SLAM technology to achieve simultaneous localization and mapping of the robot in an unknown environment. This application uses the open source framework gmapping for environmental modeling. The grid scanning algorithm proposed based on the above content ensures that the robot uses the map information constructed in real time every time.

[0066] Multi-robot collaboration module: By adding multiple robots, the search and rescue efficiency is improved. When multiple robots perform tasks, bus communication is used. Robots use topic or service communication to publish their information to information processing nodes. After the information processing nodes are integrated and processed, they are sent to each robot in the form of topic or service communication to ensure that the robots can effectively exchange information and work together. Moreover, this communication method can flexibly add and cancel any number of robots.

[0067] Simulation experiment module: Using the Robot Operating System (ROS) as the software framework, the robot and the search and rescue environment were modeled in gazebo and simulation experiments were conducted, and the experimental results were observed through the rviz plug-in. This module simulated the search and rescue environment and verified the effectiveness and performance of the fast search path planning method of this application.

[0068] In addition, the rapid search path planning system may also include a user interface and a visualization interface. The user interface is used to accept search and rescue instructions input by the user, and the visualization interface is used to display the robot's actions and planning results at each step in real time.

[0069] Through the above embodiments, it can be found that the method and device for rapid search path planning in the search and rescue environment of the present application, when performing path planning, constructs a priority map, simulates the real search and rescue environment as much as possible, models the POMDP seven-tuple, and realizes dynamic and efficient solution based on the POMDP solution method, so that the robot can continuously solve in the process of performing tasks, that is, when the robot moves to a certain grid, observes an observation variable, updates its confidence state according to the observation function, and then solves the POMDP, that is, selects the action with the largest long-term reward, and finally moves to the next grid according to its action. In addition, the present application also realizes the robot's autonomous exploration in the case of unknown maps, generates a passable area while building the map, ensures that the robot makes decisions in the passable area, and realizes the robot's fully autonomous path planning. The proof ensures that the robot performs the search and rescue task in the shortest possible time and minimizes the backtracking phenomenon, that is, the robot can not only quickly search the entire map, but also search each grid as few times as possible.

[0070] Specifically, the fast search path planning method of the present application applies the POMDP decision-making planning algorithm model to robots to realize intelligent search and rescue. The idea of ​​priority in search and rescue scenarios is proposed, that is, the higher the priority, the more it should be searched first. By setting the reward function in the seven-tuple, it can ensure that the robot pays attention to the grids with high priority first, but the influence of distance must also be considered, that is, when the robot is far away from the grid with high priority, the travel consumption of moving there will be considered. Therefore, when the robot is performing a search and rescue task, it will take into account both mobile consumption and search and rescue efficiency when choosing the next grid to move. At the same time, the POMDP model is very good at simulating the uncertainty that may occur in the real environment.

[0071] The embodiments of the present invention also provide a computer-readable storage medium and a computer program product, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method described in any of the above embodiments are implemented. The computer-readable storage medium can be a tangible storage medium, such as a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a floppy disk, a hard disk, a removable storage disk, a CD-ROM, or any other form of storage medium known in the technical field.

[0072] It should be understood by those skilled in the art that the exemplary components, systems and methods described in conjunction with the embodiments disclosed herein can be implemented in hardware, software or a combination of the two. Whether it is performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention. When implemented in hardware, it can be, for example, an electronic circuit, an application-specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present invention are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link via a data signal carried in a carrier.

[0073] It should be clear that the present invention is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present invention.

[0074] In the present invention, features described and / or illustrated for one embodiment may be used in the same or similar manner in one or more other embodiments, and / or combined with features of other embodiments or replace features of other embodiments.

[0075] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the embodiments of the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for rapid search path planning in a search and rescue environment, characterized in that: The method comprises: Determine a search and rescue area, divide the search and rescue area into a plurality of grids, and construct POMDP seven-tuple information corresponding to each grid, wherein the POMDP seven-tuple information includes a finite state set, a finite action set, a state transition matrix, a reward, a finite observation set, an observation probability, and a discount factor; Acquire the current position information of the search and rescue robot and the surrounding map environment information of the search and rescue robot in real time, determine the current grid of the search and rescue robot based on the current position information of the search and rescue robot, and determine the next target grid of the search and rescue robot through a partially observable Markov decision algorithm based on the POMDP seven-tuple information corresponding to the current grid; The search path of the search and rescue robot is determined based on the target grid of the search and rescue robot for the next step and the surrounding map environment information of the search and rescue robot.

2. The method for rapid search path planning in a search and rescue environment according to claim 1, characterized in that: Construct the POMDP seven-tuple information corresponding to each grid, including: Determine the search and rescue priority corresponding to each of the grids, and determine the state set based on the search and rescue priority corresponding to the grid; Determine adjacent grids of the grid, and determine the limited action set based on the adjacent grids; A limited observation set corresponding to the grid is determined based on whether there is a trapped person in the grid.

3. The method for rapid search path planning in a search and rescue environment according to claim 1, characterized in that: Determining the next target grid of the search and rescue robot through a partially observable Markov decision algorithm based on the POMDP seven-tuple information corresponding to the current grid, including: Determining a traversable area based on the acquired surrounding map environment information of the search and rescue robot; The next target grid of the search and rescue robot is determined by a partially observable Markov decision algorithm based on the POMDP seven-tuple information corresponding to the current grid and the traversable area.

4. The method for rapid search path planning in a search and rescue environment according to claim 3, characterized in that: Determining a traversable area based on the acquired surrounding map environment information of the search and rescue robot includes: Obtain the center point of each grid, and use each center point as each boundary point; Determine a connection relationship between boundary points based on the surrounding map environment information, where the connection relationship is connected, disconnected or unknown; A passable area is determined based on the connection relationship between the boundary points.

5. The method for rapid search path planning in a search and rescue environment according to claim 1, characterized in that: Real-time acquisition of the current location information of the search and rescue robot and the surrounding map environment information of the search and rescue robot includes: Based on the instant positioning and map building method, the current position information of the search and rescue robot and the surrounding map environment information of the search and rescue robot are obtained in real time.

6. The method for rapid search path planning in a search and rescue environment according to claim 1, characterized in that: Determining a search path of the search and rescue robot based on the next target grid of the search and rescue robot and surrounding map environment information of the search and rescue robot includes: The search path of the search and rescue robot is determined by a robot autonomous navigation algorithm based on the target grid of the search and rescue robot's next step and the surrounding map environment information of the search and rescue robot.

7. The method for rapid search path planning in a search and rescue environment according to any one of claims 1 to 6, characterized in that: There are multiple search and rescue robots, and the multiple search and rescue robots all communicate with a common information processing node, and the multiple search and rescue robots share current location information, surrounding map environment information and search paths.

8. The method for rapid search path planning in a search and rescue environment according to claim 7, characterized in that: The multiple search and rescue robots share current location information, surrounding map environment information and search paths, including: Obtaining current location information, surrounding map environment information, and search paths corresponding to each of the search and rescue robots; The current position information, surrounding map environment information and search path corresponding to each of the search and rescue robots are integrated based on the common information processing node to obtain integrated information; The fused information is sent to each of the search and rescue robots.

9. A fast search path planning system in a search and rescue environment, the system comprising a processor, a memory and a computer program stored in the memory, characterized in that: The processor is used to execute the computer program. When the computer program is executed, the system implements the steps of the method according to any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images