Intelligent robot navigation method and system

Abstract

The application discloses an intelligent robot navigation method and system, comprising the following steps: acquiring a current travel path and a travel path environment of a robot, and inputting the current travel path and the travel path environment of the robot into a robot navigation system; initializing the robot navigation system, and obtaining a quantum state space and an action space of the robot according to the travel path and the travel path environment; obtaining an optimal quantum action through selection of the quantum state space, processing the optimal quantum action by using a reward mechanism, continuously updating the quantum state, and obtaining an intelligent optimal navigation method of the robot by issuing adjustment of the current travel path and the travel path environment of the robot by the robot navigation system. The method can not only cope with complex and changeable environments and provide efficient path planning, but also avoid navigation accuracy and robustness problems caused by machine learning, improve the calculation speed through the advantage of quantum computation, and improve the performance and reliability of the robot in practical application.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent robots and quantum technology processing, and in particular to an intelligent robot navigation method and system. BACKGROUND

[0002] With the rapid development of artificial intelligence and robot technology, robot navigation systems play an increasingly important role in various application scenarios. Traditional robot navigation methods mainly rely on deterministic algorithms such as A* algorithm, Dijkstra algorithm, etc. These methods perform well in static and simple environments. With the complexity and diversification of application requirements, robots need to navigate autonomously in dynamic and complex environments, and the limitations of these methods gradually appear. In recent years, navigation algorithms based on machine learning and deep learning have gradually attracted attention. These methods train models to achieve path planning and obstacle avoidance, and have strong environmental adaptability. However, even so, these algorithms are very inefficient when faced with drastic environmental changes and high-precision path requirements, etc. The application of quantum computing solves the problem of large computational load faced by traditional robots. However, China's current application in the field of quantum computing is still in the first stage, and faces many challenges and problems.

[0003] Some experts have proposed that the integration of machine learning and quantum computing can realize intelligent robot navigation. However, subsequent research has shown that although robot navigation methods based on machine learning have certain adaptive ability, their model training requires a large amount of sample data. At this time, the domestic sample training set has not reached the scale of foreign countries, and in the training process, overfitting or underfitting problems may occur. Under this premise, the combination of quantum computing will result in insufficient navigation accuracy and robustness of robots in practical applications. In addition, existing methods generally lack environmental modeling of the path in the robot navigation planning process, and have high computational complexity. SUMMARY

[0004] The purpose of this section is to summarize some aspects of the embodiments of the present application and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract and title of the specification to avoid obscuring the purpose of this section, abstract and title, and such simplifications or omissions cannot be used to limit the scope of the present application.

[0005] In view of the above existing problems, the present application is proposed. Therefore, the present application provides an intelligent robot navigation method to solve the problems proposed in the background art.

[0006] To solve the above technical problems, the present application provides the following technical solutions:

[0007] In a first aspect, the application provides an intelligent robot navigation method, comprising:

[0008] obtaining a current travel path and a travel path environment of the robot, and inputting the current travel path and the travel path environment of the robot into a robot navigation system;

[0009] initializing the robot navigation system, and obtaining a quantum state space and an action space of the robot according to the travel path and the travel path environment;

[0010] obtaining an optimal quantum action by selecting the quantum state space, processing the optimal quantum action by using a reward mechanism, continuously updating a quantum state, issuing an adjustment of the current travel path and the travel path environment of the robot by the robot navigation system, and obtaining an intelligent optimal navigation method of the robot.

[0011] As a preferred scheme of the intelligent robot navigation method, the method comprises:

[0012] in the robot navigation system, converting the current travel path environment of the robot into a super-qubit, and deploying a super-qubit sensor network composed of the super-qubit, and perceiving, by the super-qubit sensor network, an environmental change of the robot on the current travel path.

[0013] As a preferred scheme of the intelligent robot navigation method, the method comprises:

[0014] the number of times of occurrence of an obstacle, the number of times of path inflection points, the number of times of parameter changes of environmental conditions, and the number of times of communication delays.

[0015] As a preferred scheme of the intelligent robot navigation method, the method comprises:

[0016] initializing a previously stored travel path and travel path environment in the navigation system, performing real-time analysis on the environmental change perceived by the super-qubit sensor network by using topological quantum computing, and extracting environmental change features;

[0017] creating a complex environment $CE$ and a simple environment $SE$ by using the environmental change features;

[0018] defining a quantum state space $S$ and a quantum action space $A$ of the robot, and initializing a quantum action value function $Q(s,a)$.

[0019] As a preferred scheme of the intelligent robot navigation method, wherein: the optimal quantum action is obtained by selecting a quantum state space, the optimal quantum action is processed by using a reward mechanism, the quantum state is updated, the robot navigation system is used to issue an adjustment of the current robot travel path and the travel path environment, and an intelligent optimal navigation method of the robot is obtained, comprising:

[0020] If the current is a complex environment CE, the quantum state s is placed in a quantum superposition state by using a quantum gate, and a plurality of quantum actions are obtained;

[0021] For each quantum state space time step t, a quantum action a is selected from the quantum superposition state according to the quantum action value function Q(s, a);

[0022] The selected quantum action a is returned to the robot navigation system, and the reward r and the new quantum state s' are recorded and calculated by the reward mechanism.

[0023] As a preferred scheme of the intelligent robot navigation method, wherein: further comprising:

[0024] If the current is a simple environment SE, a topological quantum superposition state is created for the quantum state s by using a topological quantum weaving operation;

[0025] A quantum action a is selected from the topological quantum superposition state, and the current quantum state and the selected quantum action are reconstructed into a new superposition state;

[0026] According to the new superposition state, the robot navigation system is returned, and the reward r and the quantum action value function Q(s, a) are recorded and calculated by the reward mechanism.

[0027] As a preferred scheme of the intelligent robot navigation method, wherein: the reward mechanism comprises:

[0028] The path efficiency reward E(t), the environment adaptability reward A(t), the resource utilization rate reward R(t), the operation stability reward S(t), and the measurement accuracy reward M(t).

[0029] In a second aspect, the present application provides an intelligent robot navigation system, comprising:

[0030] A robot path input module configured to obtain a current robot travel path and a path environment, and input the robot current travel path and the travel path environment into the robot navigation system;

[0031] The robot navigation initialization module is configured to initialize the robot navigation system, and obtain a quantum state space and an action space of the robot according to the travel path and the travel path environment.

[0032] The robot navigation optimization strategy module is configured to obtain an optimal quantum action by selecting the quantum state space, process the optimal quantum action by using a reward mechanism, continuously update the quantum state, and obtain an intelligent optimal navigation method of the robot by issuing an adjustment of the travel path and the travel path environment of the current robot by the robot navigation system.

[0033] In a third aspect, the present application provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and wherein the processor implements any step of the above method when executing the computer program.

[0034] In a fourth aspect, the present application provides a computer readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements any step of the above method.

[0035] Compared with the prior art, the present application has the following advantages: the present application inputs the current travel path and the travel path environment of the robot into the robot navigation system by obtaining the current travel path and the travel path environment of the robot; the robot navigation system is initialized, and the quantum state space and the action space of the robot are obtained according to the travel path and the travel path environment; the optimal quantum action is obtained by selecting the quantum state space, the optimal quantum action is processed by using the reward mechanism, the quantum state is continuously updated, and the intelligent optimal navigation method of the robot is obtained by issuing the adjustment of the travel path and the travel path environment of the current robot by the robot navigation system; this method not only can cope with complex and changeable environment and provide efficient path planning, but also can avoid the navigation accuracy and robustness problems caused by machine learning, improve the calculation speed by using the advantage of quantum calculation, and improve the performance and reliability of the robot in practical application. BRIEF DESCRIPTION OF DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor. Among them:

[0037] Figure 1 The overall flowchart of the intelligent robot navigation method according to an embodiment of the present application;

[0038] Figure 2Robustness comparison chart of different navigation systems of the intelligent robot navigation method described in one embodiment of the present application;

[0039] Figure 3 Performance comparison chart of different navigation systems of the intelligent robot navigation method described in one embodiment of the present application. DETAILED DESCRIPTION

[0040] In order to make the above objectives, characteristics and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application are described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should fall within the scope of protection of the present application.

[0041] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application. However, the present application can be practiced in other ways different from those described herein without departing from the scope of the present application, and those skilled in the art can make similar extensions without departing from the scope of the present application, so the present application is not limited to the specific embodiments disclosed below.

[0042] Secondly, the "one embodiment" or "embodiment" referred to herein means that the specific features, structures or characteristics can be included in at least one implementation of the present application. "In one embodiment" appearing in different places in the specification does not mean the same embodiment, nor is it an independent or alternative embodiment that excludes other embodiments.

[0043] The present application is described in detail in conjunction with the schematic diagram. In the detailed description of the embodiments of the present application, the cross-sectional view of the device structure is locally enlarged without the general proportion for the convenience of description, and the schematic diagram is only an example, which should not limit the scope of protection of the present application herein. In addition, three-dimensional spatial dimensions including length, width and depth should be included in actual manufacture.

[0044] Meanwhile, in the description of the present application, it should be noted that the orientation or position relationship of the terms "up, down, inside and outside" is based on the orientation or position relationship shown in the drawings, and is only for the convenience of describing the present application and simplifying the description, and does not indicate or imply that the indicated device or element must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first, second or third" are only for the purpose of description, and cannot be understood as indicating or implying relative importance.

[0045] Unless otherwise defined, the terms "mounting, connecting, associating" in the present application should be interpreted broadly, for example: it can be fixed connection, detachable connection or integral connection; it can also be mechanical connection, electrical connection or direct connection, it can also be indirectly connected through intermediate medium, or it can be the internal communication of two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0046] Embodiment 1

[0047] Reference Figure 1 For the first embodiment of the present application, the embodiment provides an intelligent robot navigation method, comprising:

[0048] S1, obtaining the current travel path of the robot and the travel path environment, inputting the current travel path of the robot and the travel path environment into the robot navigation system;

[0049] Further, in the robot navigation system, the current travel path environment of the robot is converted into a super quantum bit, and a super quantum sensor network composed of super quantum bits is deployed, and the environment change of the robot on the current travel path is perceived by the super quantum sensor network;

[0050] Specifically, the current travel path environment of the robot needs to be preprocessed before being input into the robot navigation system before conversion, and is converted into a super quantum bit by quantum state encoding in the robot navigation system;

[0051] It should be noted that the data preprocessing is placed outside the robot navigation system, which can improve the processing efficiency of the navigation system;

[0052] Specifically, the super quantum sensor network includes super quantum sensor nodes, which can read super quantum bit information, and each super quantum sensor node is linked by quantum entanglement to form a super quantum sensor network;

[0053] Specifically, quantum entanglement refers to a fast synchronization of data state between sensor nodes;

[0054] Further, the environment change of the robot on the current travel path includes the number of obstacles, the number of path inflection points, the number of parameter changes of environmental conditions, and the number of communication delays;

[0055] Specifically, the parameters of the environmental conditions include environmental light change, temperature change, humidity change, sound change, vibration change, electromagnetic interference, air flow change and wind direction change; wherein the sound change simulates noise and the electromagnetic interference simulates communication interference;

[0056] Specifically, the path inflection point refers to the change of direction in the robot's travel process, the more the number of path inflection points, the more the number of changes of direction, which also indicates that the current travel path environment is more complex; of course, these also need to be combined with the number of times of the remaining environmental change parameters to judge; for example, assuming that the number of path inflection points is large, and the remaining environmental change parameters are few, it indicates that the current travel path environment is simple, but the robot makes too many path decisions, thereby generating unnecessary calculation amount, so it is necessary to evaluate the quantum state space and action space of the robot, thereby providing efficient path planning and improving the calculation speed;

[0057] S2, initialize the robot navigation system, and obtain the quantum state space and action space of the robot according to the travel path and travel path environment;

[0058] Further, the previously stored travel path and travel path environment in the initialization navigation system are used to analyze the environmental changes perceived by the hyperquantum sensor network in real time using topological quantum computing, and the environmental change features are extracted;

[0059] It should be noted that the initialization of the navigation system takes into account that the system will retain the previous travel path and travel path environment, which will affect the accuracy of the current navigation system;

[0060] Further, using the environmental change features, a complex environment $CE$ and a simple environment $SE$ are created;

[0061] Specifically, the judgment of complex environment and simple environment includes the keywords of environmental change parameters involved in the extraction of environmental change features, which need to be marked according to the actual application environment; for example, in a closed environment, the change of air flow and wind direction is not needed; and the judgment standard of complex environment and simple environment is also determined according to the number of obstacle appearance, the number of path inflection points and the number of parameter changes of environmental conditions; among them, the number of communication delays is affected by the environmental marker keywords;

[0062] Further, the quantum state space $S$ and the quantum action space $A$ of the robot are defined, and the quantum action value function $Q(s,a)$ is initialized;

[0063] Specifically, the quantum state space of the robot refers to the set of all possible states of the robot in its travel path and travel environment, including the current coordinates and direction of the robot, the motion speed and acceleration of the robot, the internal state of the robot (such as battery power, processor load);

[0064] Specifically, the quantum action space of the robot refers to a set of all possible actions that the robot can take in a given state, including the robot's forward, backward, turning, acceleration, and deceleration; the robot's grabbing, placing, scanning, and measuring; the robot's changing path and interacting with the environment;

[0065] S3, by selecting the quantum state space to obtain the optimal quantum action, using the reward mechanism to process the optimal quantum action, and constantly updating the quantum state, the robot navigation system issues the adjustment of the current robot's travel path and the travel path environment to obtain the intelligent best navigation method of the robot;

[0066] Further, according to the characteristics of environmental changes, a complex environment or a simple environment is selected:

[0067] S301.1, if the current is a complex environment $CE$, the quantum state $s$ is placed in a quantum superposition state using a quantum gate, and a plurality of quantum actions are obtained;

[0068] S301.2, for each quantum state space time step $t$, a quantum action $a$ is selected from the quantum superposition state according to the quantum action value function $Q(s,a)$;

[0069] S301.3, the selected quantum action $a$ is returned to the robot navigation system, and the reward $r$ and the new quantum state $s′$ are recorded and calculated through the reward mechanism;

[0070] Further, S301.1~S301.3 are iterated to obtain the optimal quantum action by constantly selecting quantum actions;

[0071] Specifically, the quantum gate can control the state space and action space of the quantum;

[0072] S302.1, if the current is a simple environment $SE$, a topological quantum superposition state is created for the quantum state $s$ using a topological quantum weaving operation;

[0073] S302.2, a quantum action $a$ is selected from the topological quantum superposition state, and the current quantum state and the selected quantum action are reconstructed into a new superposition state;

[0074] S302.3, according to the new superposition state, return to the robot navigation system, record and calculate the reward $r$ and update the quantum action value function $Q(s,a)$ through the reward mechanism;

[0075] Further, S302.1~S302.3 are iterated to obtain the optimal quantum action by constantly updating the quantum action value function;

[0076] It should be noted that the robot navigation system can obtain an optimal quantum action in either a simple environment or a complex environment

[0077] Further, the reward mechanism includes a path efficiency reward E(t), an environment adaptability reward A(t), a resource utilization rate reward R(t), an operation stability reward S(t), and a measurement accuracy reward M(t)

[0078] Specifically, the path efficiency reward E(t) is expressed as:

[0079]

[0080] Specifically, the environment adaptability reward A(t) is expressed as:

[0081]

[0082] Specifically, the resource utilization rate reward R(t) is expressed as:

[0083]

[0084] Specifically, the operation stability reward S(t) is expressed as:

[0085]

[0086] Specifically, the measurement accuracy reward M(t) is expressed as:

[0087]

[0088] wherein T represents a total travel time of the robot from a starting point to an ending point, Δd i represents a distance traveled by the robot in the kth time step, Δt i represents a time traveled by the robot in the kth time step, δ j represents a number of times that the jth obstacle appears, θ k represents a direction angle of the robot in the kth time step, φ k represents a rotation angle of the robot in the kth time step, γ k is a curve shape adjustment parameter of the environment adaptability reward function, η k is a parameter for balancing the influence of the environment change feature on the environment adaptability reward, ξ k represents an environment change perceived by the robot in the kth time step, ∈ l represents an amount of the lth resource consumed by the robot when performing a complex environment task or a simple environment task, κ l represents a residual amount of the lth resource consumed by the robot, ρ lTo represent the utilization of the lth resource in the task execution process, σ is the fluctuation of resource consumption, usually taking 1 as the fluctuation and 0 as the smoothness; cosh is the hyperbolic cosine function, sinh is the hyperbolic sine function, ψ represents the stability of the robot in the walking process, ω represents the path weight generated by the robot in the walking process, τ represents a moment, and α p represents the accuracy p perceived by the robot in the measurement process, δ q represents the number of errors q occurring in the measurement process of the robot.

[0089] Further, the optimal quantum action is evaluated by a reward mechanism to obtain a reward score, and the quantum state is updated to obtain the ideal state of the quantum state space, that is, the reward score value reaches the maximum, and the robot navigation system issues an adjustment of the current robot travel path and travel path environment.

[0090] It should be noted that the quantum state is updated to obtain the ideal state of the quantum state space, which can further improve the navigation accuracy based on the operation speed advantage of quantum computing itself; and the current robot travel path and travel path environment are adjusted through the latest quantum state, which enables the navigation system to maintain stable and efficient performance in uncertain and dynamic environments, thereby improving the system robustness.

[0091] Further, the embodiment also provides an intelligent robot navigation system, comprising:

[0092] A robot path input module configured to obtain the current robot travel path and path environment, and input the robot current travel path and travel path environment to the robot navigation system.

[0093] A robot navigation initialization module configured to initialize the robot navigation system, and obtain the quantum state space and action space of the robot according to the travel path and travel path environment.

[0094] A robot navigation optimization strategy module configured to obtain the optimal quantum action by selecting the quantum state space, process the optimal quantum action by using a reward mechanism, update the quantum state, and issue an adjustment of the current robot travel path and travel path environment by the robot navigation system to obtain the intelligent best navigation method of the robot.

[0095] The embodiment also provides a computer device suitable for the intelligent robot navigation method, comprising:

[0096] A memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions to realize the intelligent robot navigation method proposed in the above embodiment.

[0097] The computer device can be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected by a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is configured to perform wired or wireless communication with an external terminal. The wireless communication can be achieved by WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0098] The embodiment also provides a storage medium having a computer program stored thereon, the program being executed by a processor to implement the intelligent robot navigation method according to the above embodiment.

[0099] The storage medium according to the embodiment belongs to the same inventive concept as the data storage method according to the above embodiment, and the technical details not described in detail in the embodiment can be referred to the above embodiment, and the embodiment has the same beneficial effects as the above embodiment.

[0100] Embodiment 2

[0101] Reference Figure 2 and Figure 3 As a second embodiment of the present application, the embodiment provides an intelligent robot navigation method, including: in order to verify the effectiveness of the intelligent robot navigation method, four different navigation systems are selected for comparison test: a traditional A* algorithm navigation system, a navigation system based on machine learning, a navigation system based on quantum computing, and the method of the present application (an intelligent robot navigation system); the experimental site is set in a dynamic environment, including multiple obstacles and complex path inflection points, simulating the complex environment in actual application, and the experimental robots are all of the same model and are equipped with the same sensors and computing resources to ensure the fairness of the experiment.

[0102] The experimental preparation is as follows: different types of obstacles are arranged in the experimental site, including movable obstacles, fixed obstacles, randomly appearing obstacles and complex path inflection points; different environmental parameter change points are set, including light, temperature, humidity, noise and electromagnetic interference;

[0103] The navigation system is initialized:

[0104] Traditional A* algorithm navigation system: preset static map, define obstacle position and path node;

[0105] Machine learning-based navigation system initialization: load pre-trained navigation model, model trained based on a large amount of path data;

[0106] Quantum computing-based navigation system initialization: set qubit state and quantum gate operation, load environment change data;

[0107] Intelligent robot navigation system initialization: obtain the current path and environment of the robot, convert the path and environment data into super qubits, deploy a super quantum sensor network, and initialize the navigation system;

[0108] Experimental process:

[0109] The robot navigates from the starting point to the ending point under the guidance of the above four navigation systems respectively; the number of obstacles encountered by the robot, the number of path inflection points, the number of environmental parameter changes and the number of communication delays in each navigation process are recorded; the performances of the four navigation systems in dynamic environment are compared, and the path planning time, path efficiency, environmental adaptability, resource utilization rate, operation stability and measurement accuracy are focused on;

[0110] Among them, the path efficiency reward score = path efficiency * 0.4; the resource utilization rate reward score = resource utilization rate * 0.3; the measurement accuracy reward score = measurement accuracy * 0.3; the comprehensive reward score = path efficiency reward score + resource utilization rate reward score + measurement accuracy reward score;

[0111] Experimental results: as shown in Table 1;

[0112] Table 1

[0113]

[0114]

[0115] From Table 1, it can be known that the traditional A* algorithm navigation system performs worst when encountering obstacles, and the number of obstacles is as high as 15, while the intelligent robot navigation system is only 5, which shows that the intelligent system can better identify and avoid obstacles, and the intelligent robot navigation system keeps the lowest in the number of path inflection points, the number of environmental parameter changes and the number of communication delays, which shows that the intelligent robot navigation system is more efficient in planning path on the basis of environmental adaptability and environmental response speed, and can find the optimal path;

[0116] And through the measurement accuracy, it can be found that the intelligent robot navigation system is 5%-15% higher than the other navigation systems in navigation accuracy; thus it is shown that the navigation accuracy of the present application is more optimal; and throughFigure 2 and Figure 3 It can be seen that the system of the present application has also improved in robustness and performance, fully demonstrating the practicability and reliability of the method of the present application.

[0117] Those skilled in the art will understand that the embodiments of the present application can be provided as methods, systems or computer program products. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) containing computer usable program code. The solutions in the embodiments of the present application can be implemented in various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript, etc.

[0118] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device that implements the flow Figure 1 one or more flows and / or blocks Figure 1 an apparatus that implements the functions specified in the flow

[0119] These computer program instructions can also be stored in a computer readable memory that can direct the computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including instruction apparatus that implements the flow Figure 1 one or more flows and / or blocks Figure 1 an apparatus that implements the functions specified in the flow

[0120] These computer program instructions can also be loaded onto a computer or other programmable data processing device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide a process for implementing the flow Figure 1 one or more flows and / or blocks Figure 1 an apparatus that implements the functions specified in the flow

[0121] While the preferred embodiments of the application have been described, additional variations and modifications can be made to these embodiments by those skilled in the art once they have the benefit of the present disclosure without departing from the spirit and scope of the application. Accordingly, it is intended that such additions and modifications be included within the scope of the application. It is the following claims, including any amendments thereto, which define the scope of the application.

[0122] Obviously, numerous modifications and variations of the present application are possible in light of the above teachings. It is therefore to be understood that within the scope of the appended claims and their equivalents, the application can be practiced otherwise than as specifically described.

Claims

1. An intelligent robot navigation method, characterized in that, include: Obtain the robot's current travel path and travel path environment, and input the robot's current travel path and travel path environment into the robot navigation system; The robot navigation system is initialized, and the robot's quantum state space and action space are obtained based on the travel path and the travel path environment. The optimal quantum action is obtained by selecting a quantum state space. The optimal quantum action is processed by a reward mechanism, and the quantum state is continuously updated. The robot navigation system then issues adjustments to the current robot's travel path and travel path environment to obtain the robot's intelligent optimal navigation method. The method involves selecting the optimal quantum action from the quantum state space, processing the optimal quantum action using a reward mechanism, continuously updating the quantum state, and then having the robot navigation system issue adjustments to the current robot's path and the path environment to obtain the robot's intelligent optimal navigation method, including: If the current environment is complex Then, quantum gates are used to encode quantum states. By placing it in a quantum superposition state, multiple quantum actions are obtained; For each time step of the quantum state space According to the quantum action value function Selecting a quantum action from a quantum superposition state ; Selected quantum action Returning to the robot navigation system, the reward is recorded and calculated using a reward mechanism. and new quantum states ; If the current environment is simple Then, topological quantum weaving operations are used to manipulate the quantum state. Creating topological quantum superposition states; Select a quantum action from the topological quantum superposition state. This reconstructs the current quantum state and the chosen quantum action into a new superposition state. The robot navigation system is returned based on the new superposition state, and the result is recorded and calculated using a reward mechanism. and updating quantum action value function .

2. The intelligent robot navigation method as described in claim 1, characterized in that, Obtaining the robot's current travel path and its surrounding environment, and inputting the current travel path and its surrounding environment into the robot navigation system, includes: In the robot navigation system, the robot's current path environment is converted into super qubits, and a super quantum sensor network composed of super qubits is deployed to sense environmental changes on the robot's current path.

3. The intelligent robot navigation method as described in claim 2, characterized in that, The super quantum sensor network senses environmental changes on the robot's current path, including: The number of times obstacles appeared, the number of path inflection points, the number of times environmental condition parameters changed, and the number of communication delays.

4. The intelligent robot navigation method as described in claim 3, characterized in that, The robot navigation system is initialized, and the robot's quantum state space and action space are obtained based on the travel path and the travel path environment, including: Initialize the previously stored travel path and travel path environment in the navigation system, and use topological quantum computing to analyze the environmental changes sensed by the super quantum sensor network in real time and extract the characteristics of the environmental changes; Create complex environments by utilizing the aforementioned environmental change characteristics. and simple environment ; Define the quantum state space of a robot and quantum action space Initialize the quantum action value function .

5. The intelligent robot navigation method as described in claim 1, characterized in that, The reward mechanism includes: Path efficiency reward Environmental adaptability reward Resource utilization rate reward Operational stability reward And measurement accuracy rewards .

6. An intelligent robot navigation system, based on the intelligent robot navigation method according to any one of claims 1 to 5, characterized in that, include: The robot path input module is configured to acquire the robot's current travel path and path environment, and input the robot's current travel path and path environment into the robot navigation system; The robot navigation initialization module is configured to initialize the robot navigation system and obtain the robot's quantum state space and action space based on the travel path and the travel path environment. The robot navigation optimization strategy module is configured to obtain the optimal quantum action by selecting the quantum state space, process the optimal quantum action using a reward mechanism, continuously update the quantum state, and issue adjustments to the current robot's travel path and travel path environment through the robot navigation system to obtain the robot's intelligent optimal navigation method.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images