Robot search task path planning method and device, electronic equipment and storage medium

Abstract

The robot search task path planning method provided by the present disclosure comprises the following steps: S1, obtaining the probability of a target object in each room in a current environment through semantic information, and obtaining a current confidence state of a search task according to the probability; S2, designing a cost function of the search task based on a path length, the current confidence state and motion maneuverability, and taking a room corresponding to a minimum cost as a target position of the current search task; S3, moving a robot to the target position and detecting the target object, and if the target object is detected, the current search task ends; if the target object is not detected, S4 is entered; S4, reducing the probability of the target object in a current room to a first value, increasing the probability of the target object in other rooms by a second value, and updating the current confidence state, and returning to S2. The present method can effectively utilize prior knowledge of an environment, and realize a fast and efficient object search task.

Description

Technical Field

[0001] This disclosure pertains to the field of robot path planning, and specifically relates to a method, apparatus, electronic device, and storage medium for robot search task path planning based on confidence criteria. Background Technology

[0002] Mobile robots assisting humans in searching for objects in indoor environments has become one of the core tasks of robotics. Examples include searching for survivors in enclosed disaster relief environments, delivering documents in office settings, and serving drinks in homes. Currently, path planning methods for search tasks typically rely on the distance between the robot and each room in the environment or follow a fixed search strategy (traversing rooms clockwise or counterclockwise). Because the object's location is unknown, the robot's task execution time is long and the planning efficiency is low. Therefore, it is necessary to develop an effective path planning method that utilizes prior environmental knowledge to obtain the probability of objects in different rooms and makes efficient decisions, enabling robots to perform fast and accurate object search tasks. Summary of the Invention

[0003] This disclosure aims to at least partially address one of the technical problems in the related art.

[0004] Therefore, the robot search task path planning method provided in the first aspect of this disclosure can effectively utilize prior environmental knowledge to process the path planning method for indoor environment object search, thereby achieving fast and efficient object search tasks. The robot search task path planning method provided in the first aspect of this disclosure includes:

[0005] S1. Obtain the probability of the target object in each room of the current environment through semantic information, and obtain the current confidence state of the robot search task based on the probability.

[0006] S2. Design a cost function for the search task based on path length, current confidence state, and motion mobility, and take the room with the minimum cost as the target location of the current search task.

[0007] S3. The robot moves to the target position and performs target object detection. If the robot detects the target object, the current search task ends; if the robot does not detect the target object, proceed to step S4.

[0008] S4. Update the probability of the target object in each room of the current environment: reduce the probability of the target object in the current room to a first value, increase the probability of the target object in other rooms to a second value, and the total increase is equal to the change in the probability of the target object in the current room; update the current confidence state and return to step S2.

[0009] In some embodiments, in step S1, the target object is assumed to be in the i-th room R of the current environment. i The probability is p i It can be obtained according to the following formula:

[0010]

[0011]

[0012] p(R i ) = 1 / n

[0013] In the formula, p(R) i |obj) is the target object obj calculated according to Bayes' theorem, which exists in the i-th room R. i The probability, where i is 1, corresponds to the room number where the robot is currently located; p(obj|R i Let R be the i-th room. i The semantic information-based probability of the existence of the target object obj, NR i p(R) represents the total number of times the word in the i-th room appears in the corpus, which stores several statements, each containing a word related to the target object in the search task. NF is a hyperparameter representing the number of failed searches for the target object, and n is the total number of rooms in the search task environment. i Let R be the i-th room. i The probability of being searched is assumed to be that each room has been searched the same number of times before the search task is executed.

[0014] In some embodiments, in step S1, let the current confidence state be B, and the expression be:

[0015] B = [b1, ..., b i ,…,b n ],b i =p i

[0016] In the formula, b i p is the i-th element in the current confidence state B. i Let R be the target object in the i-th room of the current environment. i The probability is given by i, where i = 1 corresponds to the room number where the robot is currently located.

[0017] In some embodiments, in step S2, the expression of the cost function is as follows:

[0018] Γ i =ω1·L i / p(R i |obj)+ω2·θ i

[0019] In the formula, Γ i For the i-th room R i The cost; L i Let θ be the path length from the robot's current position to the i-th room; i Let ω1 be the motion mobility of the robot moving from its current position to the i-th room; ω2 is the first weighting coefficient that measures the path length considering prior knowledge of the indoor environment, and ω1 is the second weighting coefficient that measures the motion mobility, and ω1+ω2=1.

[0020] The robot's mobility θ as it moves from its current position to the i-th room i The following steps will yield the following:

[0021] Construct a circular region centered on the robot's current position. This circular region should cover the area of ​​the current environment. Divide the circular region into m equal sectors, where m is a positive integer greater than or equal to 2. Let the i-th room be R. i The angle between the line connecting the robot's current position and its current orientation is β. i Suppose there are k levels of robot mobility, and the mobility values ​​are normalized within the range of 0 to 1. Finally, the mobility θ of the robot moving from its current position to the i-th room is obtained according to the following formula. i :

[0022]

[0023]

[0024] In the formula, α is the central angle of the sector region, α=2π / m.

[0025] In some embodiments, in step S3, the robot moves to the target position according to the motion control quantity generated using the dynamic window method.

[0026] In some embodiments, the motion control quantities include the robot's linear velocity and angular velocity.

[0027] In some embodiments, in step S4, the probability of the target object in each room of the current environment is updated according to the following formula:

[0028] p'1=ε

[0029] p' j =p j +(p1-ε) / (n-1),j=2,…,n

[0030]

[0031] In the formula, p1 is the probability that the target object is in the room where the robot is currently located before the update, p'1 is the probability that the target object is in the room where the robot is currently located after the update, and p' j ε is the updated probability of the target object being in the other rooms; ε is the first value, which is a positive number close to 0, and ε is less than or equal to the original probability of the target object being in each room.

[0032] The updated current confidence state B' is obtained according to the following formula:

[0033] B' = [b'1,…,b'] i ,…,b′ n ],b′ i =p' i

[0034] In the formula, b'1 is the i-th element in the updated current confidence state B'.

[0035] The robot search task path planning method provided in the first aspect of this disclosure has the following characteristics and beneficial effects:

[0036] (1) Integrating prior environmental knowledge—semantic information—into the path planning method can reduce the execution time of object search tasks.

[0037] (2) The target position selection of the robot at each step is obtained by calculating the cost function, which takes into account the path length, confidence state and motion mobility, and can improve the efficiency of the object search task.

[0038] (3) Establish a confidence state update mechanism so that the robot can continuously update its understanding of the current environment during the search task, which can improve the intelligence of the object search task.

[0039] The robot search task path planning apparatus provided in the second aspect embodiment of this disclosure includes:

[0040] The first module is configured to obtain the probability of the target object in each room of the current environment through semantic information, and obtain the current confidence state of the robot search task based on the probability.

[0041] The second module is configured to design a cost function for the search task based on path length, current confidence state, and motion mobility, and to take the room with the minimum cost as the target location of the current search task.

[0042] The third module is configured to control the robot to move to the target position and detect the target object. If the robot detects the target object, the current search task ends; if the robot does not detect the target object, the fourth module is invoked.

[0043] The fourth module is configured to update the probability of the target object in each room of the current environment: reduce the probability of the target object in the current room to a first value, increase the probability of the target object in other rooms by a second value, and the total increase is equal to the change in the probability of the target object in the current room; update the current confidence state, and transmit the updated confidence state to the second module.

[0044] The electronic device provided in the third aspect embodiment of this disclosure includes:

[0045] At least one processor, and a memory communicatively connected to said at least one processor;

[0046] The memory stores instructions executable by the at least one processor, the instructions being configured to perform the robot search task path planning method according to any embodiment of the first aspect of this disclosure.

[0047] A computer-readable storage medium is provided in a fourth aspect embodiment of this disclosure, the computer-readable storage medium storing computer instructions for causing the computer to perform the robot search task path planning method according to any embodiment of the first aspect of this disclosure. Attached Figure Description

[0048] Figure 1 A flowchart of a robot search task path planning method provided in the first aspect of this disclosure.

[0049] Figure 2 This is a schematic diagram illustrating the motion mobility set in the path planning method provided in the first aspect of this disclosure.

[0050] Figure 3 A schematic diagram of the structure of an electronic device provided in a third aspect embodiment of this disclosure. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of this application clearer, the application will be described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely for explaining this application and are not intended to limit this application.

[0052] Conversely, this application covers any alternatives, modifications, equivalent methods, and schemes made within the spirit and scope of this application as defined by the claims. Furthermore, to provide the public with a better understanding of this application, certain specific details are described in detail below. However, this application can be fully understood by those skilled in the art even without these detailed descriptions.

[0053] See Figure 1The first aspect of this disclosure provides a robot search task path planning method based on confidence criterion decision-making, comprising:

[0054] S1. Obtain the probability of the target object in each room of the current environment through semantic information, and obtain the current confidence state of the robot search task based on the probability. The current confidence state is used to characterize the probability of the target object existing in each room.

[0055] S2. Design a cost function for the search task based on three factors: path length, current confidence state, and mobility. The room with the minimum cost is taken as the target location for the current search task.

[0056] S3. The robot uses a dynamic time window method to generate motion control quantities, thereby driving the robot to move to the target position of the current search task and perform target object detection. If the robot detects the target object, the current search task ends; if the robot does not detect the target object, proceed to step S4.

[0057] S4. Update the probability of the target object in each room of the current environment: reduce the probability of the target object in the current room (i.e., the target location of the current search task determined in step S2) to a first value (the first value is a decimal close to zero), increase the probability of the target object in other rooms by a second value, and the total increase is equal to the change in the probability of the target object in the current room, update the current confidence state, and return to step S2.

[0058] In some embodiments, step S1 specifically includes the following steps:

[0059] Semantic information allows for the establishment of probabilistic models of the relationships between objects within rooms. Natural Language Processing (NLP) techniques have been extensively studied in word representation, which can measure semantic similarity. A total corpus is constructed, storing several statements (command-based or dialogue-based object search statements collected from the robot's working environment). Statements containing words related to the target object in the search task are selected from this corpus to form a corpus for that target object search task. By selecting the target object as a keyword, the frequency of nouns related to each room in the current environment appearing around the keyword is counted within the defined context of the corpus. This is then analyzed using Natural Language Processing (NLP). i Let R represent the total number of times the word in the i-th room appears in the corpus. In reality, the target object may not be in any room but in a corridor, the indoor environment may be empty, or it may have been discarded. Therefore, we consider a hyperparameter NF to represent the number of times the target object search fails. The target object in the i-th room is obtained by the following formula: i Probability based on semantic information:

[0060]

[0061] In the formula, p(obj|R) i ) represents the i-th room R i The probability of the existence of the target object obj based on semantic information, where n represents the total number of rooms in the search task environment, and i is 1 when it corresponds to the number of the room where the robot is currently located.

[0062] If each room has been searched the same number of times before the search task is executed, then the probability p(R) of each room being searched at this time is... i )as follows:

[0063] p(R i )=1 / n (2)

[0064] The probability p of the target object being in the i-th room of the current environment is obtained using the following formula. i as follows:

[0065]

[0066] In the formula, p(R) i |obj) represents the target object obj, calculated according to Bayes' theorem, which exists in the i-th room R. i The probability of.

[0067] The current confidence state B can be represented as:

[0068] B = [b1, ..., b i ,…,b n ],b i =p i (4)

[0069] In the formula, b i It is the i-th element in the current confidence state B.

[0070] In other embodiments, the total corpus uses a publicly available dataset, such as Wikipedia 2014+Gigaword 5 (https: / / www.kaggle.com / datasets / gerwynng / glove-wikipedia-2014-gigaword-5).

[0071] In some embodiments, in step S2, the expression for the cost function is as follows:

[0072] Γ i =ω1·L i / p(R i |obj)+ω2·θ i (5)

[0073] In the formula, Γi For the i-th room R i The cost; L i Let L be the path length from the robot's current position to the i-th room (the center of the i-th room can be chosen to represent the room). i / p(R i |obj) represents the path length considering prior knowledge of the indoor environment, reflecting the impact of confidence state on decision-making; θ i Let θ represent the robot's motion mobility from its current position to the i-th room, characterizing its tendency to choose a motion direction similar to its previous direction. ω1 is a first weighting coefficient that measures the path length considering prior knowledge of the indoor environment, and ω2 is a second weighting coefficient that measures motion mobility, satisfying ω1 + ω2 = 1. Here, θ represents the robot's motion mobility from its current position to the i-th room. i The following steps will yield the following:

[0074] Construct a circular region centered on the robot's current position. This circular region should cover the area of ​​the current environment. Divide the circular region into m equal sectors, where m is a positive integer greater than or equal to 2. Let the i-th room be R. i The angle between the line connecting the robot's current position and its current orientation is β. i Suppose there are k levels of robot mobility, and the mobility values ​​are normalized within the range of 0 to 1. Finally, the mobility θ of the robot moving from its current position to the i-th room is obtained according to the following formula. i :

[0075]

[0076]

[0077] In the formula, α is the central angle of each sector region, α=2π / m.

[0078] In one embodiment, suppose there are m = 8 sector regions within a circular region, and the central angle of each sector region is π / 4. Then, the robot's mobility levels are k = 5, with values ​​of 1 / 15, 2 / 15, 1 / 5, 4 / 15, and 1 / 3, respectively. The distribution of robot mobility values ​​corresponding to each sector region within the circular region is as follows: Figure 2 As shown. Figure 2In the diagram, the black center represents the robot's current position, and the arrowed line segments represent the robot's current orientation. Adjacent dashed lines intersect at the center to form corresponding fan-shaped regions. The robot's mobility is equal when moving from its current position to any position within the same fan-shaped region. The value of mobility is positively correlated with cost; that is, the lower the mobility, the lower the cost, and the lower the mobility value, the closer the robot is to its previous direction of movement.

[0079] Since a good decision-making strategy determines the quality of path planning, the shortest path length strategy is the most commonly used method in robot navigation without considering any prior knowledge of the working environment, but this is clearly not the optimal solution. This disclosure incorporates the confidence state of the object's location within the room into the decision-making strategy and considers path length and motion mobility, proposing a path planning method based on confidence criteria. This method can utilize prior environmental knowledge and weigh the impact of path length and motion mobility on the cost of path planning, thereby improving the efficiency of path planning execution and the success rate of the task.

[0080] In some embodiments, the motion control quantities generated by the robot in step S3 using the Dynamic Window Approach (DWA) include the robot's linear velocity and angular velocity.

[0081] In some embodiments, step S4 specifically includes the following steps:

[0082] As the search task is executed, the robot's confidence state regarding the target object changes. If the target object is successfully found, the search task ends; otherwise, if the previous confidence state does not meet expectations, it is updated as follows: P'={p'1,…,p' i ,…,p' n ,ε}, where p'1=ε, p' j =p j +(p1-ε) / (n-1),j=2,…,n, It is a very small positive number, and satisfies ε≤p i ,i=1,…,n. Finally, the current confidence state of the target object is updated using equation (4), and the process returns to step S2. The robot continues to plan its path using the current confidence state until the target object is found, at which point the search task ends.

[0083] The robot search task path planning apparatus provided in the second aspect embodiment of this disclosure includes:

[0084] The first module is configured to obtain the probability of the target object in each room of the current environment through semantic information, and obtain the current confidence state of the robot search task based on the probability.

[0085] The second module is configured to design a cost function for the search task based on path length, current confidence state, and motion mobility, and to take the room with the minimum cost as the target location of the current search task.

[0086] The third module is configured to control the robot to move to the target position and detect the target object. If the robot detects the target object, the current search task ends; if the robot does not detect the target object, the fourth module is invoked.

[0087] The fourth module is configured to update the probability of the target object in each room of the current environment: reduce the probability of the target object in the current room to a first value, increase the probability of the target object in other rooms by a second value, and the total increase is equal to the change in the probability of the target object in the current room; update the current confidence state, and transmit the updated confidence state to the second module.

[0088] To implement the above embodiments, this disclosure also proposes a computer-readable storage medium storing a computer program thereon, which is executed by a processor to perform the robot search task path planning method provided in the first aspect of this disclosure.

[0089] The following is for reference. Figure 3 The diagram illustrates a structural schematic suitable for implementing the electronic device provided in the third aspect of the present disclosure. The electronic device in the embodiments of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs, desktop computers, and servers. Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0090] like Figure 3 As shown, the electronic device may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 101, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 102 or a program loaded from a storage device 108 into a random access memory (RAM) 103. The RAM 103 also stores various programs and data required for the operation of the electronic device. The processing unit 101, ROM 102, and RAM 103 are interconnected via a bus 104. An input / output (I / O) interface 105 is also connected to the bus 104.

[0091] Typically, the following devices can be connected to I / O interface 105: input devices 106 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, etc.; output devices 107 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 108 including, for example, magnetic tapes, hard disks, etc.; and communication devices 109. Communication device 109 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 3 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown. More or fewer devices may be implemented or have alternatively.

[0092] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, this embodiment includes a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network via communication device 109, or installed from storage device 108, or installed from ROM 102. When the computer program is executed by processing device 101, it performs the functions defined above in the methods of embodiments of this disclosure.

[0093] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0094] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0095] The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to:

[0096] S1. Obtain the probability of the target object in each room of the current environment through semantic information, and obtain the current confidence state of the robot search task based on the probability.

[0097] S2. Design a cost function for the search task based on path length, current confidence state, and motion mobility, and take the room with the minimum cost as the target location of the current search task.

[0098] S3. The robot moves to the target position and performs target object detection. If the robot detects the target object, the current search task ends; if the robot does not detect the target object, proceed to step S4.

[0099] S4. Update the probability of the target object in each room of the current environment: reduce the probability of the target object in the current room to a first value, increase the probability of the target object in other rooms to a second value, and the total increase is equal to the change in the probability of the target object in the current room; update the current confidence state and return to step S2.

[0100] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and Python, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0101] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0102] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0103] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the function involved, as will be understood by those skilled in the art to which embodiments of this application pertain.

[0104] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0105] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0106] Those skilled in the art will understand that implementing all or part of the steps of the methods in the above embodiments can be accomplished by instructing related hardware through a program. The developed program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0107] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0108] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A path planning method for a robot search task, characterized in that, include: S1. Obtain the probability of the target object in each room of the current environment through semantic information, and obtain the current confidence state of the robot search task based on the probability. S2. Design a cost function for the search task based on path length, current confidence state, and motion mobility, and take the room with the minimum cost as the target location of the current search task. S3. The robot moves to the target position and performs target object detection. If the robot detects the target object, the current search task ends. If the robot does not detect the target object, proceed to step S4; S4. Update the probability of the target object in each room of the current environment: reduce the probability of the target object in the current room to a first value, increase the probability of the target object in other rooms to a second value, and the total increase is equal to the change in the probability of the target object in the current room; update the current confidence state and return to step S2. In step S1, let the target object be in the current environment at the th Room The probability is It can be obtained according to the following formula: In the formula, For the target object calculated according to Bayes' theorem Existing in the Room The probability, When the value is 1, it corresponds to the room number where the robot is currently located; For the first Room There is a target object Probability based on semantic information Indicates the first The total number of times the words for each room appear in the corpus, which stores several sentences, each containing a word related to the target object corresponding to the search task. This is a hyperparameter used to represent the number of times the target object search failed. The total number of rooms in the search task environment; For the first Room The probability of being searched is assumed to be that each room has been searched the same number of times before the search task is executed.

2. The robot search task path planning method according to claim 1, characterized in that, In step S1, let the current confidence state be... The expression is: In the formula, Current confidence state The first in One element, For the target object in the current environment Room The probability, When the value is 1, it corresponds to the room number where the robot is currently located.

3. The robot search task path planning method according to claim 1, characterized in that, In step S2, the expression for the cost function is as follows: In the formula, For the first Room The cost; For the robot's current position to the th The path length to each room; For the robot to move from its current position to the next position The mobility of movement within each room; The first weighting coefficient is used to measure the path length considering prior knowledge of the indoor environment. The second weighting coefficient for measuring motion mobility, and satisfying ; The robot moves from its current position to the [missing position]. Mobility of each room The following steps will yield the following: Using the robot's current position as the center, construct a circular region that covers the area of ​​the current environment. Divide the circular region into equal parts. A fan-shaped area, Let be a positive integer greater than or equal to 2, and let the th... Room The angle between the line connecting the robot's current position and its current orientation is... Let the robot's mobility be classified into several levels. The values ​​of the motion mobility are normalized within the range of 0 to 1, and the final value of the robot's movement from the current position to the next position is obtained according to the following formula. Mobility of each room : In the formula, The central angle of the sector region is... .

4. The robot search task path planning method according to claim 1, characterized in that, In step S3, the robot moves to the target position according to the motion control quantity generated using the dynamic window method.

5. The robot search task path planning method according to claim 4, characterized in that, The motion control quantities include the robot's linear velocity and angular velocity.

6. The robot search task path planning method according to claim 1, characterized in that, In step S4, the probability of the target object in each room of the current environment is updated according to the following formula: In the formula, This represents the probability of the target object being in the room where the robot is currently located before the update. This represents the updated probability of the target object being in the room where the robot is currently located. The updated probability of the target object being in the remaining rooms; The first value is a positive number close to 0, and The probability of the target object in each room being less than or equal to the probability before the update; The updated current confidence state is obtained according to the following formula. : In the formula, The updated current confidence state The first in Each element.

7. A path planning device for a robot search task, characterized in that, include: The first module is configured to obtain the probability of the target object in each room of the current environment through semantic information, and obtain the current confidence state of the robot search task based on the probability. Let the target object be in the current environment. Room The probability is It can be obtained according to the following formula: In the formula, For the target object calculated according to Bayes' theorem Existing in the Room The probability, When the value is 1, it corresponds to the room number where the robot is currently located; For the first Room There is a target object Probability based on semantic information Indicates the first The total number of times the words for each room appear in the corpus, which stores several sentences, each containing a word related to the target object corresponding to the search task. This is a hyperparameter used to represent the number of times the target object search failed. The total number of rooms in the search task environment; For the first Room The probability of being searched is assumed to be that each room has been searched the same number of times before the search task is executed. The second module is configured to design a cost function for the search task based on path length, current confidence state, and motion mobility, and to take the room with the minimum cost as the target location of the current search task. The third module is configured to control the robot to move to the target position and detect the target object. If the robot detects the target object, the current search task ends. If the robot fails to detect the target object, the fourth module is invoked; The fourth module is configured to update the probability of the target object in each room of the current environment: reduce the probability of the target object in the current room to a first value, increase the probability of the target object in other rooms by a second value, and the total increase is equal to the change in the probability of the target object in the current room; update the current confidence state, and transmit the updated confidence state to the second module.

8. An electronic device, characterized in that, include: At least one processor, and a memory communicatively connected to said at least one processor; The memory stores instructions executable by the at least one processor, the instructions being configured to perform the robot search task path planning method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the robot search task path planning method according to any one of claims 1 to 6.

Images