Autonomous mobile device, control method thereof, control device and readable storage medium

Through the autonomous mobile device using the collaborative processing of multi-dimensional sensor modules and cloud servers, comprehensive perception and dynamic adaptation of the environment are achieved, and the problem of incomplete environmental detection in the existing technology is solved, and the autonomous decision-making and intelligence of the robot are improved. level.

CN118938895APending Publication Date: 2024-11-12MIDEA ROBOZONE TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410912473.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-09
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

Existing robots rely on preset task processes or passive trigger mechanisms in environmental detection, and cannot fully perceive environmental information and find it difficult to cope with dynamically changing environments, which limits the ability to make independent decisions and intelligence.

Method used

The autonomous mobile device uses sensor modules of multiple dimensions to obtain environmental parameter information, actively start the detection task based on this information, and update the walking path and sampling parameters during the movement, and combine the computing power of the cloud server to perform data processing and decision-making.

Benefits of technology

It has achieved comprehensive and precise perception and understanding of the environment, improved independent decision-making and execution capabilities, enhanced adaptability and flexibility to dynamic environments, and improved the intelligence level of robots.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118938895A_ABST
    Figure CN118938895A_ABST
Patent Text Reader

Abstract

The invention provides an autonomous mobile device, a control method thereof, a control device and a readable storage medium, the autonomous mobile device comprises a body and a sensor module, the control method of the autonomous mobile device comprises the following steps: acquiring environmental information detected by the sensor module, the environmental information comprising M pieces of environmental parameter information; on the basis that N pieces of environmental parameter information in the M pieces of environmental parameter information meet the corresponding triggering conditions, a detection task is started, M is larger than or equal to N, and M and N are positive integers; after the detection task is started, a walking path and sampling parameters are determined based on the environment information and the detection task; and controlling the body to move according to the walking path, and controlling the sensor module to operate according to the sampling parameters in the process that the body moves according to the walking path so as to update the environment information. In the process, the environment information can be comprehensively sensed by using the M pieces of environment parameter information, and the detection task is actively started, so that the intelligent level of the autonomous mobile device is improved while the autonomous decision-making capability is fully exerted.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of control technology, and in particular to an autonomous mobile device and a control method thereof, a control device and a readable storage medium. Background Art

[0002] In relevant technical solutions, the robot's environmental detection relies on preset task processes or passive trigger mechanisms, and the collected data is often limited to a single dimension, which cannot provide comprehensive and three-dimensional environmental information. This makes it impossible for the robot to perceive environmental information in all aspects and it is difficult to cope with dynamically changing environments, limiting the robot's autonomous decision-making ability and intelligence level. Summary of the invention

[0003] The present invention aims to solve at least one of the technical problems existing in the prior art or related art.

[0004] To this end, a first aspect of the present invention is to provide a control method for an autonomous mobile device.

[0005] A second aspect of the present invention provides a control device for an autonomous mobile device.

[0006] A third aspect of the present invention is to provide another control device for an autonomous mobile device.

[0007] A fourth aspect of the present invention provides a readable storage medium.

[0008] A fifth aspect of the present invention is to provide an autonomous mobile device.

[0009] In view of this, according to a first aspect of the present invention, the present invention provides a control method for an autonomous mobile device, the autonomous mobile device comprising a main body and a sensor module, the control method comprising: acquiring environmental information detected by the sensor module, the environmental information comprising M environmental parameter information; starting a detection task based on N environmental parameter information among the M environmental parameter information satisfying corresponding trigger conditions, M≥N, and M and N are positive integers; after starting the detection task, determining a walking path and sampling parameters based on the environmental information and the detection task; controlling the main body to move along the walking path, and in the process of the main body moving along the walking path, controlling the sensor module to operate according to the sampling parameters to update the environmental information.

[0010] The technical solution of the present invention proposes a control method for an autonomous mobile device. By running the above-mentioned control method for an autonomous mobile device, the autonomous mobile device can use a sensor module to perceive environmental information, and then obtain M environmental parameter information, wherein the environmental information can be perceived from multiple dimensions, and then when N environmental parameter information among the M environmental parameter information meet the corresponding trigger conditions, the detection task is started.

[0011] In this process, M environmental parameter information can be used to fully perceive the environmental information, and then the environment in which the autonomous mobile device is located can be fully and accurately understood and judged, and the detection task can be actively initiated, so that the autonomous mobile device can give full play to its autonomous decision-making ability. At the same time, it also improves the intelligence level of the autonomous mobile device.

[0012] In addition, in related technical solutions, robots often use specific events to start detection tasks, such as using a timer to start the detection task when the time reaches a set length of time; or starting the detection task when an alarm signal is received.

[0013] Obviously, the triggering of the detection task is too single, lacking flexibility and adaptability, and it is difficult to cope with dynamically changing environments and diverse task requirements. In the control method proposed in the present invention, the detection task can be started based on one or more of the M environmental parameter information and the corresponding trigger conditions, so that the autonomous mobile device can independently start the detection task according to the changing environmental information, so that the autonomous mobile device can cope with changing environmental parameters, thereby improving the flexibility and adaptability of the autonomous mobile device.

[0014] At the same time, after starting the detection task, the sensor module can be controlled to operate according to the sampling parameters to update the environmental information while the main body moves along the walking path. In this process, the walking path and sampling parameters can be corrected according to the updated environmental information, so that the autonomous mobile device can achieve active cruise control while giving the autonomous mobile device stronger autonomous decision-making and execution capabilities.

[0015] In addition, the control method of the autonomous mobile device proposed in this application also has the following additional technical features.

[0016] In some technical schemes, optionally, the walking path and sampling parameters are determined based on the environmental information and the detection task, specifically including: extracting features of M environmental parameter information respectively to obtain M environmental features; determining a first feature based on the M environmental features, where the first feature is a feature obtained by fusion of the M environmental features; determining a second feature based on the first feature, historical environmental information and prior knowledge of the environment; and determining the walking path and sampling parameters based on the second feature and the task requirements of the detection task.

[0017] In this technical solution, feature extraction is performed on M environmental parameter information respectively to obtain M environmental features corresponding to the M environmental parameter information one by one, wherein the M environmental features can represent the M environmental parameter information so as to convert the environmental parameter information into data that can be processed by the automatic mobile device. At the same time, feature extraction of the environmental parameter information also facilitates feature fusion of the M environmental parameter information to obtain the first feature.

[0018] In this process, the first feature can describe environmental information from multiple dimensions, so it can be combined with historical environmental information and prior knowledge of the environment to obtain the second feature. The second feature can characterize the current environment in multiple dimensions, so that the autonomous mobile device can fully and accurately understand and judge the current environment, and then plan the walking path and sampling parameters in combination with the task requirements of the detection task.

[0019] In this process, by constructing the second feature so that the second feature can be used to fully perceive the current environmental information, the defect of incomplete information perception by a single sensor in the related technical solutions is overcome. At the same time, in the process of constructing the second feature, historical environmental information is referenced so that the constructed second feature can include the changing trend of environmental information, providing a basis for fully understanding the environmental information.

[0020] In addition, the use of prior knowledge of the environment enables the autonomous mobile device to fully understand the environment in which the autonomous mobile device is located, and then plan a reasonable walking path and sampling parameters.

[0021] In some technical solutions, optionally, the control method also includes: sending the updated environmental information to a cloud server so that the cloud server determines the third feature based on the updated environmental information, historical environmental information and prior knowledge of the environment; receiving the third feature sent by the cloud server; and updating the walking path and sampling parameters based on the third feature and the task requirements of the detection task.

[0022] In this technical solution, the computing power and storage resources of the autonomous mobile device itself are limited, which makes the intelligent processing and decision-making capabilities of the autonomous mobile device limited. By sending the updated environmental information to the cloud server, the powerful computing and storage capabilities of the cloud server can be utilized to process, analyze and make decisions on the environmental information, so that the autonomous mobile device and the cloud server can operate in coordination, thereby improving the autonomous intelligence level of the autonomous mobile device.

[0023] In this process, compared with autonomous mobile devices, the computing power and storage resources of cloud servers are more powerful, so that the third feature not only contains the same content as the second feature, but also represents the current environment in multiple dimensions more comprehensively and accurately than the second feature. Therefore, the walking path and sampling parameters determined according to the third feature and the task requirements of the detection task are more accurate.

[0024] In some technical solutions, optionally, the autonomous mobile device can interact with an interactive terminal, and the interactive terminal communicates with a cloud server. When the interactive terminal receives environmental information from the cloud server, it displays the environmental information and the operating information of the autonomous mobile device. The control method also includes: receiving control instructions from the interactive terminal, the control instructions are determined based on the displayed environmental information and operating information; based on the control instructions, the walking path and sampling parameters are corrected.

[0025] In this technical solution, the interactive terminal can communicate with the cloud server. Therefore, the interactive terminal can display the environmental information detected by the autonomous mobile device and the operating information of the operation read from the cloud server. The user can use the interactive terminal to view the environmental information detected by the autonomous mobile device and the operating information of the autonomous mobile device. At the same time, the user can use the interactive terminal to receive control instructions input by the user, and then control the autonomous mobile device to correct the walking path and sampling parameters according to the control instructions.

[0026] In this process, it is convenient for users to remotely monitor and control the autonomous mobile device, so as to manually correct the walking path and sampling parameters, thereby realizing the remote control of the autonomous mobile device.

[0027] In some technical schemes, optionally, the control method also includes: sending the updated environmental information to a cloud server, so that the cloud server determines the third feature based on the updated environmental information, historical environmental information and prior knowledge of the environment; and determining the updated walking path and updated sampling parameters based on the third feature and the task requirements of the detection task; receiving the updated walking path and updated sampling parameters; controlling the main body to move according to the updated walking path, and in the process of the main body moving according to the updated walking path, controlling the sensor module to operate according to the updated sampling parameters.

[0028] In this technical solution, the updated environmental information can be directly sent to the cloud server, so that while the third feature can be determined by the cloud server, the updated walking path and updated sampling parameters can be directly planned, and the updated walking path and updated sampling parameters can be sent to the autonomous mobile device, so that the autonomous mobile device can directly operate according to the updated walking path and updated sampling parameters.

[0029] In this process, the amount of data that needs to be processed by the autonomous mobile device can be reduced, and the accuracy of the walking path and sampling parameters used by the autonomous mobile device during operation can be improved.

[0030] In some technical solutions, optionally, the M environmental parameter information includes at least two of the following: environmental images, environmental sounds, environmental odors, and an air quality index in the environment.

[0031] In some technical solutions, optionally, the sensor module includes at least two of the following: a visual sensor, an auditory sensor, an olfactory sensor, and an air quality index sensor.

[0032] In some technical solutions, optionally, the main body includes a movable chassis, an actuator and a motion control unit arranged on the movable chassis. In the process of controlling the main body to move according to the walking path, the control method also includes: driving the actuator to move through the motion control unit to perform the detection task.

[0033] In this technical solution, the operation is achieved during the movement of the actuator by controlling the movement of the actuator.

[0034] According to a second aspect of the present invention, the present invention provides a control device for an autonomous mobile device, the autonomous mobile device comprising a main body and a sensor module, the control device for the autonomous mobile device comprising: an acquisition unit, for acquiring environmental information detected by the sensor module, the environmental information comprising M environmental parameter information; a trigger unit, for starting a detection task based on N environmental parameter information among the M environmental parameter information satisfying corresponding trigger conditions, M≥N, and M and N are positive integers; a determination unit, for determining a walking path and sampling parameters based on the environmental information and the detection task after starting the detection task; a processing unit, for controlling the main body to move along the walking path, and in the process of the main body moving along the walking path, controlling the sensor module to operate according to the sampling parameters to update the environmental information.

[0035] The technical solution of the present invention proposes a control device for an autonomous mobile device, which can enable the autonomous mobile device to use a sensor module to perceive environmental information, and then obtain M environmental parameter information, wherein the environmental information can be perceived from multiple dimensions, and then when N environmental parameter information among the M environmental parameter information meet the corresponding trigger conditions, the detection task is started.

[0036] In this process, M environmental parameter information can be used to fully perceive the environmental information, and then the environment in which the autonomous mobile device is located can be fully and accurately understood and judged, and the detection task can be actively initiated, so that the autonomous mobile device can give full play to its autonomous decision-making ability. At the same time, it also improves the intelligence level of the autonomous mobile device.

[0037] In addition, in related technical solutions, robots often use specific events to start detection tasks, such as using a timer to start the detection task when the time reaches a set length of time; or starting the detection task when an alarm signal is received.

[0038] Obviously, the triggering of the detection task is too single, lacking flexibility and adaptability, and it is difficult to cope with dynamically changing environments and diverse task requirements. In the present invention, the detection task can be initiated based on one or more of the M environmental parameter information and the corresponding trigger conditions, so that the autonomous mobile device can independently initiate the detection task according to the changing environmental information, so that the autonomous mobile device can cope with changing environmental parameters, thereby improving the flexibility and adaptability of the autonomous mobile device.

[0039] At the same time, after starting the detection task, the sensor module can be controlled to operate according to the sampling parameters to update the environmental information while the main body moves along the walking path. In this process, the walking path and sampling parameters can be corrected according to the updated environmental information, so that the autonomous mobile device can achieve active cruise control while giving the autonomous mobile device stronger autonomous decision-making and execution capabilities.

[0040] In addition, the control device of the autonomous mobile device proposed in this application also has the following additional technical features.

[0041] In some technical schemes, optionally, the determination unit is specifically used to: perform feature extraction on M environmental parameter information respectively to obtain M environmental features; determine a first feature based on the M environmental features, where the first feature is a feature obtained after feature fusion of the M environmental features; determine a second feature based on the first feature, historical environmental information and prior knowledge of the environment; determine a walking path and sampling parameters based on the second feature and the task requirements of the detection task.

[0042] In this technical solution, feature extraction is performed on M environmental parameter information respectively to obtain M environmental features corresponding to the M environmental parameter information one by one, wherein the M environmental features can represent the M environmental parameter information so as to convert the environmental parameter information into data that can be processed by the automatic mobile device. At the same time, feature extraction of the environmental parameter information also facilitates feature fusion of the M environmental parameter information to obtain the first feature.

[0043] In this process, the first feature can describe environmental information from multiple dimensions, so it can be combined with historical environmental information and prior knowledge of the environment to obtain the second feature. The second feature can characterize the current environment in multiple dimensions, so that the autonomous mobile device can fully and accurately understand and judge the current environment, and then plan the walking path and sampling parameters in combination with the task requirements of the detection task.

[0044] In this process, by constructing the second feature so that the second feature can be used to fully perceive the current environmental information, the defect of incomplete information perception by a single sensor in the related technical solutions is overcome. At the same time, in the process of constructing the second feature, historical environmental information is referenced so that the constructed second feature can include the changing trend of environmental information, providing a basis for fully understanding the environmental information.

[0045] In addition, the use of prior knowledge of the environment enables the autonomous mobile device to fully understand the environment in which the autonomous mobile device is located, and then plan a reasonable walking path and sampling parameters.

[0046] In some technical solutions, optionally, the determination unit is also used to: send the updated environmental information to the cloud server, so that the cloud server determines the third feature based on the updated environmental information, historical environmental information and prior knowledge of the environment; receive the third feature sent by the cloud server; and update the walking path and sampling parameters based on the third feature and the task requirements of the detection task.

[0047] In this technical solution, the computing power and storage resources of the autonomous mobile device itself are limited, which makes the intelligent processing and decision-making capabilities of the autonomous mobile device limited. By sending the updated environmental information to the cloud server, the powerful computing and storage capabilities of the cloud server can be utilized to process, analyze and make decisions on the environmental information, so that the autonomous mobile device and the cloud server can operate in coordination, thereby improving the autonomous intelligence level of the autonomous mobile device.

[0048] In this process, compared with autonomous mobile devices, the computing power and storage resources of cloud servers are more powerful, so that the third feature not only contains the same content as the second feature, but also represents the current environment in multiple dimensions more comprehensively and accurately than the second feature. Therefore, the walking path and sampling parameters determined according to the third feature and the task requirements of the detection task are more accurate.

[0049] In some technical solutions, optionally, the autonomous mobile device can interact with an interactive terminal, and the interactive terminal communicates with a cloud server. When the interactive terminal receives environmental information from the cloud server, it displays the environmental information and the operating information of the autonomous mobile device. The determination unit is also used to: receive control instructions from the interactive terminal, and the control instructions are determined based on the displayed environmental information and operating information; based on the control instructions, modify the walking path and sampling parameters.

[0050] In this technical solution, the interactive terminal can communicate with the cloud server. Therefore, the interactive terminal can display the environmental information detected by the autonomous mobile device and the operating information of the operation read from the cloud server. The user can use the interactive terminal to view the environmental information detected by the autonomous mobile device and the operating information of the autonomous mobile device. At the same time, the user can use the interactive terminal to receive control instructions input by the user, and then control the autonomous mobile device to correct the walking path and sampling parameters according to the control instructions.

[0051] In this process, it is convenient for users to remotely monitor and control the autonomous mobile device, so as to manually correct the walking path and sampling parameters, thereby realizing the remote control of the autonomous mobile device.

[0052] In some technical schemes, optionally, the determination unit is also used to: send the updated environmental information to the cloud server, so that the cloud server determines the third feature based on the updated environmental information, historical environmental information and prior knowledge of the environment; and determine the updated walking path and updated sampling parameters based on the third feature and the task requirements of the detection task; receive the updated walking path and updated sampling parameters; control the main body to move according to the updated walking path, and in the process of the main body moving according to the updated walking path, control the sensor module to operate according to the updated sampling parameters.

[0053] In this technical solution, the updated environmental information can be directly sent to the cloud server, so that while the third feature can be determined by the cloud server, the updated walking path and updated sampling parameters can be directly planned, and the updated walking path and updated sampling parameters can be sent to the autonomous mobile device, so that the autonomous mobile device can directly operate according to the updated walking path and updated sampling parameters.

[0054] In this process, the amount of data that needs to be processed by the autonomous mobile device can be reduced, and the accuracy of the walking path and sampling parameters used by the autonomous mobile device during operation can be improved.

[0055] In some technical solutions, optionally, the M environmental parameter information includes at least two of the following: environmental images, environmental sounds, environmental odors, and an air quality index in the environment.

[0056] In some technical solutions, optionally, the sensor module includes at least two of the following: a visual sensor, an auditory sensor, an olfactory sensor, and an air quality index sensor.

[0057] In some technical solutions, optionally, the main body includes a movable chassis, an actuator and a motion control unit arranged on the movable chassis. In the process of controlling the movement of the main body along the walking path, the processing unit is also used to: drive the actuator to move through the motion control unit to perform the detection task.

[0058] In this technical solution, the operation is achieved during the movement of the actuator by controlling the movement of the actuator.

[0059] According to the third aspect of the present invention, the present invention provides a control device for an autonomous mobile device, comprising a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the programs or instructions are executed by the processor, the steps of any of the methods described above are implemented.

[0060] According to a fourth aspect of the present invention, the present invention provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of any one of the methods described above are implemented.

[0061] According to a fifth aspect of the present invention, the present invention provides an autonomous mobile device, comprising: a control device as any of the above autonomous mobile devices; and / or a readable storage medium as described above.

[0062] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0064] Figure 1 A schematic flow chart of a control method for an autonomous mobile device in an embodiment of the present invention is shown;

[0065] Figure 2 A schematic block diagram of an autonomous mobile device according to an embodiment of the present invention is shown;

[0066] Figure 3 A schematic diagram showing the data flow and control flow between various components in a robot according to an embodiment of the present invention;

[0067] Figure 4 A schematic block diagram of an intelligent environment detection robot according to an embodiment of the present invention is shown;

[0068] Figure 5 A schematic block diagram of a control device for an autonomous mobile device according to an embodiment of the present invention is shown;

[0069] Figure 6A schematic block diagram of another control device for an autonomous mobile device in an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0070] In order to more clearly understand the above aspects, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0071] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0072] In one embodiment of the present application, Figure 1 and Figure 2 As shown, a control method of an autonomous mobile device is provided. The autonomous mobile device 200 includes a body 202 and a sensor module 204. The control method includes:

[0073] Step 102, obtaining environmental information detected by the sensor module, the environmental information including M environmental parameter information;

[0074] Step 104, based on N environmental parameter information among the M environmental parameter information satisfying corresponding trigger conditions, starting the detection task, M ≥ N, and M and N are positive integers;

[0075] Step 106, after starting the detection task, determining the walking path and sampling parameters based on the environmental information and the detection task;

[0076] Step 108, controlling the main body to move along the walking path, and in the process of the main body moving along the walking path, controlling the sensor module to operate according to the sampling parameters to update the environmental information.

[0077] An embodiment of the present invention proposes a control method for an autonomous mobile device. By running the above-mentioned control method for an autonomous mobile device, the autonomous mobile device can use a sensor module to perceive environmental information, and then obtain M environmental parameter information, wherein the environmental information can be perceived from multiple dimensions, and then when N environmental parameter information among the M environmental parameter information meet the corresponding trigger conditions, the detection task is started.

[0078] In this process, M environmental parameter information can be used to fully perceive the environmental information, and then the environment in which the autonomous mobile device is located can be fully and accurately understood and judged, and the detection task can be actively initiated, so that the autonomous mobile device can give full play to its autonomous decision-making ability. At the same time, it also improves the intelligence level of the autonomous mobile device.

[0079] In addition, in the relevant embodiments, the robot often uses a specific event to start the detection task, such as starting the detection task when a timer reaches a set duration; or starting the detection task when an alarm signal is received.

[0080] Obviously, the triggering of the detection task is too single, lacking flexibility and adaptability, and it is difficult to cope with dynamically changing environments and diverse task requirements. In the control method proposed in the present invention, the detection task can be started based on one or more of the M environmental parameter information and the corresponding trigger conditions, so that the autonomous mobile device can independently start the detection task according to the changing environmental information, so that the autonomous mobile device can cope with changing environmental parameters, thereby improving the flexibility and adaptability of the autonomous mobile device.

[0081] At the same time, after starting the detection task, the sensor module can be controlled to operate according to the sampling parameters to update the environmental information while the main body moves along the walking path. In this process, the walking path and sampling parameters can be corrected according to the updated environmental information, so that the autonomous mobile device can achieve active cruise control while giving the autonomous mobile device stronger autonomous decision-making and execution capabilities.

[0082] Exemplarily, when it is detected that the change in ambient temperature is greater than a preset temperature value, the detection task is started.

[0083] In some embodiments, optionally, the walking path and sampling parameters are determined based on the environmental information and the detection task, specifically including: extracting features from M environmental parameter information respectively to obtain M environmental features; determining a first feature based on the M environmental features, where the first feature is a feature obtained by fusion of the M environmental features; determining a second feature based on the first feature, historical environmental information and prior knowledge of the environment; and determining the walking path and sampling parameters based on the second feature and the task requirements of the detection task.

[0084] In this embodiment, feature extraction is performed on M environmental parameter information respectively to obtain M environmental features corresponding to the M environmental parameter information one by one, wherein the M environmental features can represent the M environmental parameter information so as to convert the environmental parameter information into data that can be processed by the automatic moving device. At the same time, feature extraction of the environmental parameter information also facilitates feature fusion of the M environmental parameter information to obtain the first feature.

[0085] In this process, the first feature can describe environmental information from multiple dimensions, so it can be combined with historical environmental information and prior knowledge of the environment to obtain the second feature. The second feature can characterize the current environment in multiple dimensions, so that the autonomous mobile device can fully and accurately understand and judge the current environment, and then plan the walking path and sampling parameters in combination with the task requirements of the detection task.

[0086] In this process, by constructing a second feature so that the second feature can be used to fully perceive the current environmental information, the defect of incomplete information perception by a single sensor in the relevant embodiments is overcome. At the same time, in the process of constructing the second feature, historical environmental information is referenced so that the constructed second feature can include the changing trend of the environmental information, providing a basis for fully understanding the environmental information.

[0087] In addition, the use of prior knowledge of the environment enables the autonomous mobile device to fully understand the environment in which the autonomous mobile device is located, and then plan a reasonable walking path and sampling parameters.

[0088] In some embodiments, the prior knowledge of the environment, that is, the obstacle information in the environment where the autonomous mobile device is located.

[0089] For example, when the environment in which the autonomous mobile device is located is a search and rescue disaster relief environment, the obstacles may be broken tables and chairs, broken stones and broken walls, and the obstacle information may be the position coordinates and size of the tables and chairs, stones and walls.

[0090] For example, when the environment in which the autonomous mobile device is located is an environment of daily life, the obstacles may be tables, chairs, beds and sofas, and the obstacle information may be the orientation coordinates and sizes of the tables, chairs, beds and sofas.

[0091] For example, when the environment in which the autonomous mobile device is located is an industrial production environment, the obstacle may be a shelf, and the obstacle information may be the position coordinates and size of the shelf.

[0092] In some embodiments, the historical environmental information may be environmental information collected by the sensor module at the last detection moment.

[0093] In some embodiments, optionally, the control method also includes: sending the updated environmental information to a cloud server so that the cloud server determines a third feature based on the updated environmental information, historical environmental information and prior knowledge of the environment; receiving the third feature sent by the cloud server; and updating the walking path and sampling parameters based on the third feature and the task requirements of the detection task.

[0094] In this embodiment, the computing power and storage resources of the autonomous mobile device itself are limited, which makes the intelligent processing and decision-making capabilities of the autonomous mobile device limited. By sending the updated environmental information to the cloud server, the powerful computing and storage capabilities of the cloud server can be utilized to process, analyze and make decisions on the environmental information, so that the autonomous mobile device and the cloud server can operate in coordination, thereby improving the autonomous intelligence level of the autonomous mobile device.

[0095] In this process, compared with autonomous mobile devices, the computing power and storage resources of cloud servers are more powerful, so that the third feature not only contains the same content as the second feature, but also represents the current environment in multiple dimensions more comprehensively and accurately than the second feature. Therefore, the walking path and sampling parameters determined according to the third feature and the task requirements of the detection task are more accurate.

[0096] In some embodiments, optionally, the task requirement can be understood as the data to be obtained after the detection task is executed, such as drawing an information map of different directions during the detection process, wherein each point in the information map includes environmental information of the corresponding position.

[0097] In some embodiments, optionally, the autonomous mobile device can interact with an interactive terminal, the interactive terminal communicates with a cloud server, and the interactive terminal displays the environmental information and operating information of the autonomous mobile device when receiving environmental information from the cloud server. The control method also includes: receiving control instructions from the interactive terminal, the control instructions are determined based on the displayed environmental information and operating information; based on the control instructions, modifying the walking path and sampling parameters.

[0098] In this embodiment, the interactive terminal can communicate with the cloud server. Therefore, the interactive terminal can display the environmental information detected by the autonomous mobile device and the operating information of the operation read from the cloud server. The user can use the interactive terminal to view the environmental information detected by the autonomous mobile device and the operating information of the autonomous mobile device. At the same time, the user can use the interactive terminal to receive control instructions input by the user, and then control the autonomous mobile device to correct the walking path and sampling parameters according to the control instructions.

[0099] In this process, it is convenient for users to remotely monitor and control the autonomous mobile device, so as to manually correct the walking path and sampling parameters, thereby realizing the remote control of the autonomous mobile device.

[0100] In some embodiments, the control instruction may be an instruction input based on natural language processing technology, such as sending the control instruction to the interactive terminal in the form of voice and / or text.

[0101] In some embodiments, optionally, the walking path includes multiple waypoints, and the control instruction may be to adjust one or more waypoints in the walking path.

[0102] In some embodiments, optionally, the sampling parameter includes a sampling frequency, and the control instruction may be to increase or decrease the sampling frequency.

[0103] In some embodiments, optionally, the control method also includes: sending the updated environmental information to a cloud server, so that the cloud server determines a third feature based on the updated environmental information, historical environmental information and prior knowledge of the environment; and determining an updated walking path and updated sampling parameters based on the third feature and the task requirements of the detection task; receiving the updated walking path and updated sampling parameters; controlling the main body to move according to the updated walking path, and in the process of the main body moving according to the updated walking path, controlling the sensor module to operate according to the updated sampling parameters.

[0104] In this embodiment, the updated environmental information can be directly sent to the cloud server, so that while the cloud server is used to determine the third feature, an updated walking path and updated sampling parameters can be directly planned, and the updated walking path and updated sampling parameters can be sent to the autonomous mobile device, so that the autonomous mobile device can directly operate according to the updated walking path and updated sampling parameters.

[0105] In this process, the amount of data that needs to be processed by the autonomous mobile device can be reduced, and the accuracy of the walking path and sampling parameters used by the autonomous mobile device during operation can be improved.

[0106] In some embodiments, optionally, the M environmental parameter information includes at least two of the following: environmental images, environmental sounds, environmental odors, and an air quality index in the environment.

[0107] In some embodiments, optionally, the sensor module includes at least two of the following: a visual sensor, an auditory sensor, an olfactory sensor, and an air quality index sensor.

[0108] Specifically, the visual sensor includes a color camera and / or a depth camera, which is used to obtain images and visual information of the environment, such as an environmental image.

[0109] The hearing sensor includes a microphone array and / or a sound source localization module, which is used to collect ambient audio and localize the sound source as ambient sound.

[0110] Olfactory sensors use gas sensors and / or electronic noses to detect specific odors in the environment and obtain environmental odors.

[0111] The air quality index sensor, i.e., the air quality sensor, is used to detect the air quality index in the environment, wherein the air quality index includes but is not limited to temperature, humidity, and fine particulate matter.

[0112] In the above embodiments, the visual sensor, the auditory sensor, the olfactory sensor, and the air quality index sensor communicate with the main body using a standard interface to achieve data collection and transmission.

[0113] Among them, the standard interface can be 485.

[0114] In some embodiments, optionally, the main body 202 includes a movable chassis 2022, an actuator 2024 and a motion control unit 2026 arranged on the movable chassis 2022. In the process of controlling the main body to move according to the walking path, the control method also includes: driving the actuator to move through the motion control unit to perform the detection task.

[0115] In this embodiment, the operation is performed by controlling the movement of the actuator.

[0116] In one embodiment, the autonomous mobile device includes a main body, a multimodal sensor module, that is, a sensor module, an intelligent control module, a cloud server, and a human-computer interaction terminal.

[0117] The robot body includes a mechanical structure and a motion control unit. The mechanical structure uses a wheeled or tracked mobile chassis, equipped with a robotic arm and a pan-tilt actuator to achieve the robot's movement, detection and operation tasks. The motion control unit includes a motor, a driver, a motion controller, etc., which are used to execute the robot's motion control instructions to achieve precise movement and positioning.

[0118] The multimodal sensor module integrates multiple types of sensors such as vision, hearing, smell, and air quality to collect multi-dimensional information about the robot's environment. Visual sensors include color cameras, depth cameras, etc., which are used to obtain images and visual information of the environment; auditory sensors include microphone arrays, sound source localization modules, etc., which are used to collect environmental audio and locate sound sources; olfactory sensors use gas sensors, electronic noses, etc., which are used to detect specific odors in the environment; air quality sensors are used to detect environmental parameters such as temperature, humidity, and particles with a diameter of less than or equal to 2.5 microns. Each sensor module is connected to the intelligent control module through a standard interface to realize data collection and transmission.

[0119] The intelligent control module is the core control unit of the robot. It uses hardware such as high-performance processors and large-capacity memory, and runs the Robot Operating System (ROS) and intelligent algorithm software. This module is responsible for real-time processing and fusion of multimodal sensor data, making autonomous decisions and behavior planning based on environmental information, generating and issuing motion control instructions, and interacting with cloud servers for data and task collaboration. The intelligent control module is interconnected with other components through a variety of communication interfaces (such as mobile hotspots, the 4th generation mobile communication technology (4G) / 5th generation mobile communication technology (5G), and controller area network bus (CAN)) to ensure information interaction and collaborative work.

[0120] The cloud server provides cloud resources such as big data storage, high-performance computing, and intelligent algorithm models, and performs real-time data interaction and computing collaboration with the robot. The robot uploads the collected environmental data to the cloud, and the cloud server stores and intelligently analyzes the data, mines the data value, generates environmental models and knowledge bases, and feeds the analysis results back to the robot, giving it stronger intelligent decision-making capabilities. The cloud server also provides data support and computing services for human-computer interaction terminals to achieve remote visual monitoring and control.

[0121] The human-machine interaction terminal, or interactive terminal, adopts the form of global wide area network or World Wide Web (Web) / mobile software (Application, APP) to provide users with a friendly visual interactive interface. Users can use the human-machine interaction terminal to view the environmental data collected by the robot, monitor the robot's operating status, issue control instructions, etc. in real time. The human-machine interaction terminal supports natural language interaction functions, and users can interact and control the robot in a conversational manner through voice, text, etc. The human-machine interaction terminal is connected to the cloud server through the Internet to obtain cloud data services and computing support.

[0122] Specifically, the autonomous mobile device takes a robot as an example, and the control method of the robot includes the following steps:

[0123] Step 1: The robot autonomously navigates and moves in the environment to be detected. The multimodal sensor module continuously collects environmental data and transmits the data to the intelligent control module in real time.

[0124] Step 2: The intelligent control module preprocesses, extracts features and fuses multi-source information from multimodal sensor data, combines environmental prior knowledge and historical data, and constructs a multi-dimensional representation of the current environment.

[0125] Step 3: Based on the active cruise trigger strategy, the intelligent control module analyzes environmental data in real time and makes autonomous decisions on whether to initiate the detection mission according to trigger conditions such as image changes, abnormal sounds, and odor concentration.

[0126] Step 4: When the detection task is triggered, the intelligent control module autonomously plans the detection path and sampling strategy according to the current environmental representation and task requirements, and generates and executes the corresponding motion control and sensor acquisition instructions.

[0127] Step 5: The robot performs the detection task according to the planned path, continuously collects multimodal environmental data, and uploads the data to the cloud server in real time.

[0128] Step 6: The cloud server stores, cleans and pre-processes the massive amount of environmental data received, and uses intelligent algorithms such as data mining and machine learning to extract environmental features, build environmental models, update the knowledge base, and generate environmental analysis reports.

[0129] Step 7: The cloud server feeds back the analysis results and decision suggestions to the intelligent control module on the robot side to assist the robot in making intelligent decisions and optimizing behavior.

[0130] Step 8: The user can view environmental data, robot status and analysis reports in real time through the human-computer interaction terminal, and issue control instructions to the robot through a visual interface or natural language interaction to achieve remote supervision and human-computer collaboration.

[0131] In this embodiment, through the organic integration of key components such as the robot body, multimodal sensors, intelligent control, cloud collaboration, and human-machine interaction, the robot's autonomous detection, multi-dimensional perception, intelligent decision-making, and human-machine collaboration are realized, providing a complete set of technical solutions. In specific applications, the parameters, algorithms, and strategies of each component can be flexibly configured and optimized according to the requirements of different environments and tasks to ensure the adaptability and robustness of the system. The present invention is suitable for complex and changeable indoor and outdoor environments, and can be widely used in environmental monitoring, safety inspections, equipment maintenance, and other tasks in the fields of smart cities, smart homes, industrial Internet, emergency rescue, etc., with significant technical advantages and application value.

[0132] Specifically, by integrating multiple trigger mechanisms such as images, sounds, and smells, the robot can actively perceive and autonomously detect environmental changes, overcoming the limitations of the traditional preset path detection method. At the same time, the intelligent optimization algorithm is used to dynamically plan the detection path, and the detection strategy can be adjusted in real time according to environmental characteristics and task requirements, which improves the pertinence and coverage of detection, effectively reduces detection blind spots and redundancy, and significantly improves the robot's environmental adaptability and work efficiency, and improves the robot's environmental adaptability and detection efficiency.

[0133] It integrates multiple types of sensors such as vision, hearing, smell, and air quality, realizing multi-dimensional and all-round information collection of the environment, overcoming the defect of incomplete perception information of a single sensor. Through the intelligent fusion and semantic understanding of multimodal perception data, the robot can comprehensively analyze and accurately judge the environment from multiple dimensions, greatly improving the perception and understanding ability of complex environments, providing a reliable information basis for intelligent decision-making, and enhancing the robot's environmental perception and understanding ability.

[0134] Through real-time data interaction and computing collaboration between the robot and the cloud server, the advantages of cloud resources such as massive storage, high-performance computing, and intelligent algorithms are fully utilized. The robot can upload the perception data to the cloud for in-depth mining and analysis, and with the help of the cloud knowledge base and intelligent models, it can achieve long-term learning and cognition of the environment and continuously improve its own intelligence level. The environmental analysis results and decision-making suggestions generated in the cloud can guide the robot to perform more intelligent and accurate task planning and behavior control, giving the robot close to human wisdom and insight, and improving the robot's intelligence level and decision-making ability.

[0135] The Web / APP-based visual human-computer interaction system adopts a friendly interface design and natural language interaction method. Users can monitor environmental data and robot status in real time through a graphical interface, and conduct question-and-answer communication and command control with the robot through voice, text, etc. The visual and natural interaction method reduces the user's operating threshold, provides a convenient, efficient, and intelligent human-computer collaborative experience, enhances the ease of use and controllability of the system, is conducive to improving the user's work efficiency and decision-making level, optimizes the human-computer interaction experience, and improves the system's usability.

[0136] A complete system solution is proposed for typical application scenarios such as smart cities, smart homes, industrial Internet, emergency rescue, etc., covering common task requirements such as environmental monitoring, safety inspections, and equipment maintenance. Through methods such as environmental characteristics analysis, task model construction, and multi-robot collaboration, the adaptation and optimization of intelligent environmental detection robots in different scenarios are realized, improving the actual application effect. The present invention provides industry users with intelligent tools that can be used out of the box, accelerates the implementation of intelligent robots in various fields, contributes important forces to the construction of smart cities and the promotion of intelligent changes in production and life, and promotes the popularization of intelligent environmental detection robots in multiple scenarios.

[0137] The multi-dimensional, spatiotemporal and continuous environmental data collected by intelligent environmental detection robots can not only be used to support the real-time decision-making of robots, but also serve as a valuable data resource for a variety of applications such as environmental monitoring, resource management, and emergency command. The dynamic environmental model and knowledge base built based on environmental perception data can provide important references for urban planning, ecological protection, and disaster warning. The integrated application of robot perception data with city information modeling (CIM) and geographic information system (GIS) will give birth to a series of data-driven innovative application models, bringing new development opportunities for smart city construction and digital twins, enriching robot perception data, and giving birth to new application models.

[0138] Figure 3 A schematic diagram showing the data flow and control flow between the various components in the robot is shown in FIG. Figure 3 As shown in the figure, the robot body is equipped with a multimodal sensor module to collect multi-dimensional environmental data such as vision, hearing, smell and air quality. The intelligent control module preprocesses and fuses the sensor data, analyzes it based on the active cruise trigger strategy, and autonomously starts the detection task according to trigger conditions such as image changes, abnormal sounds, and odor concentration. After the detection task is started, the intelligent control module autonomously plans the detection path, the robot performs the detection task, continuously collects multimodal environmental data and uploads it to the cloud server in real time. The cloud server stores, preprocesses and analyzes the environmental data with intelligent algorithms, extracts environmental features, builds environmental models, updates the knowledge base, and generates environmental analysis reports. The cloud server feeds back decision suggestions to the robot's intelligent control module to guide the robot to perform intelligent decision-making and behavior optimization. The human-computer interaction terminal provides a visual interface, and users can monitor environmental data and robot status, and send control instructions to the robot through natural language interaction. The intelligent control module optimizes the robot's behavioral decisions based on cloud feedback and user instructions, and controls the robot body to perform corresponding actions.

[0139] In this embodiment, the role and integration of key technologies such as multimodal perception, active detection, cloud collaboration, and human-computer interaction in the system are reflected, and the overall architecture and working principles are intuitively reflected.

[0140] In one embodiment, if Figure 4 As shown, the autonomous mobile device is an intelligent environment detection robot, and the intelligent environment detection robot includes a robot body 402, a multimodal sensor module 404, that is, a sensor module, an intelligent control module 406, a cloud server 408, and a human-computer interaction terminal 410.

[0141] The robot body 402 uses a wheeled mobile chassis 4022, equipped with a mechanical arm 4024 and a gimbal 4026, for performing movement, detection and operation tasks. The multimodal sensor module 404 integrates a color camera 4042, a depth camera 4044, a microphone array 4046, a gas sensor 4048 and a temperature and humidity sensor 4050, for collecting multi-dimensional information of the environment.

[0142] The intelligent control module 406 adopts a high-performance embedded engineering machine 4062, runs a ROS operating system 4064 and an intelligent algorithm software 4066, and is responsible for real-time processing and fusion of data from the multimodal sensor module 404, autonomously starting detection tasks according to active cruise trigger strategies, and controlling the robot to perform tasks.

[0143] The cloud server 408 provides massive data storage, high-performance computing and intelligent algorithm model resources, and performs real-time data interaction and collaborative computing with the robot. The human-computer interaction terminal 410 adopts the Web / APP method, provides a friendly visual interface, and supports users to interact with the robot through natural language.

[0144] The workflow of the intelligent environment detection robot includes:

[0145] 1. The robot body 402 autonomously navigates and moves in the environment to be detected, and the multimodal sensor module 404 continuously collects environmental data and transmits it to the intelligent control module 406 in real time.

[0146] 2. The intelligent control module 406 pre-processes and fuses the sensor data, and builds a multi-dimensional representation of the current environment (i.e., the third feature in this application) by combining prior knowledge of the environment. When trigger conditions such as image changes and abnormal sounds are met, the detection task is started.

[0147] 3. The intelligent control module 406 autonomously plans the detection path, controls the robot body 402 to perform the detection task, continuously collects multimodal environmental data and uploads it to the cloud server 408.

[0148] 4. The cloud server 408 stores, analyzes and mines the environmental data, extracts features, builds models, updates the knowledge base, generates environmental analysis reports, and feeds back decision recommendations to the robot.

[0149] 5. The user can view the environmental data, robot status and analysis report in real time through the human-machine interaction terminal 410, and issue control instructions to the robot through natural language.

[0150] In one embodiment, the multimodal sensor module 404 may also integrate an infrared thermal imager and a laser radar to collect thermal radiation information and three-dimensional spatial information of the environment, thereby further enriching the perception dimension of the robot.

[0151] The intelligent control module 406 adopts a heterogeneous computing architecture, integrating processors such as a central processing unit (CPU), a graphics processing unit (GPU), and a field programmable gate array (FPGA). It uses FPGA to realize real-time preprocessing of sensor data and uses GPU to accelerate deep learning algorithms, thereby improving the computing efficiency and real-time performance of the system.

[0152] Cloud server 408 adopts a distributed cloud computing architecture and uses Docker container technology to achieve flexible deployment and dynamic scheduling of intelligent algorithm models, support concurrent access and collaborative computing of multiple robots, and improve the scalability and robustness of the system. Docker is an open source application container engine.

[0153] The human-computer interaction terminal 410 adds augmented reality (AR) / virtual reality (VR) technology functions. Users can immersively view the environmental information collected by the robot through AR glasses or VR helmets, and interact with the robot through gestures, eye tracking, etc., to achieve more intuitive and natural human-computer collaboration.

[0154] In one embodiment, multiple robots communicate wirelessly with a central dispatch node as multiple robot nodes.

[0155] Among them, the central scheduling node performs task allocation and path planning for multiple robot nodes according to task requirements and environmental characteristics, coordinates the detection behavior of each robot, and realizes parallel execution and load balancing of detection tasks.

[0156] Each robot node exchanges detection data and status information through point-to-point communication to achieve distributed environmental perception and collaborative decision-making. The robot node uses multi-agent reinforcement learning algorithms to autonomously learn collaborative strategies and continuously improve the efficiency and quality of multi-robot collaborative detection.

[0157] The cloud server 408 provides distributed data storage and parallel computing services for multi-robot collaborative scenarios, supports data sharing and knowledge migration of robot nodes, and realizes cluster intelligence and incremental learning.

[0158] The human-machine interaction terminal 410 provides a multi-perspective, multi-scale environment monitoring interface, and the user can view the detection data and status of multiple robot nodes at the same time, and perform overall scheduling and control of the multi-robot system.

[0159] This embodiment takes advantage of the collaboration of multiple robots to improve the coverage, efficiency, and robustness of environmental detection. At the same time, it combines distributed computing and cluster intelligence technology to further enhance the system's perception capability, decision-making level, and scalability, providing strong support for large-scale, long-term environmental detection tasks.

[0160] In one embodiment, if Figure 5 As shown, the present invention provides a control device 500 for an autonomous mobile device, the autonomous mobile device includes a main body and a sensor module, the control device 500 for the autonomous mobile device includes: an acquisition unit 502, used to acquire environmental information detected by the sensor module, the environmental information includes M environmental parameter information; a trigger unit 504, used to start a detection task based on N environmental parameter information among the M environmental parameter information satisfying corresponding trigger conditions, M≥N, and M and N are positive integers; a determination unit 506, used to determine a walking path and sampling parameters based on the environmental information and the detection task after starting the detection task; a processing unit 508, used to control the main body to move along the walking path, and in the process of the main body moving along the walking path, control the sensor module to operate according to the sampling parameters to update the environmental information.

[0161] An embodiment of the present invention proposes a control device 500 for an autonomous mobile device, which can enable the autonomous mobile device to use a sensor module to perceive environmental information, and then obtain M environmental parameter information, wherein the environmental information can be perceived from multiple dimensions, and then when N environmental parameter information among the M environmental parameter information meet corresponding trigger conditions, a detection task is started.

[0162] In this process, M environmental parameter information can be used to fully perceive the environmental information, and then the environment in which the autonomous mobile device is located can be fully and accurately understood and judged, and the detection task can be actively initiated, so that the autonomous mobile device can give full play to its autonomous decision-making ability. At the same time, it also improves the intelligence level of the autonomous mobile device.

[0163] In addition, in the relevant embodiments, the robot often uses a specific event to start the detection task, such as starting the detection task when a timer reaches a set duration; or starting the detection task when an alarm signal is received.

[0164] Obviously, the triggering of the detection task is too single, lacking flexibility and adaptability, and it is difficult to cope with dynamically changing environments and diverse task requirements. In the present invention, the detection task can be initiated based on one or more of the M environmental parameter information and the corresponding trigger conditions, so that the autonomous mobile device can independently initiate the detection task according to the changing environmental information, so that the autonomous mobile device can cope with changing environmental parameters, thereby improving the flexibility and adaptability of the autonomous mobile device.

[0165] At the same time, after starting the detection task, the sensor module can be controlled to operate according to the sampling parameters to update the environmental information while the main body moves along the walking path. In this process, the walking path and sampling parameters can be corrected according to the updated environmental information, so that the autonomous mobile device can achieve active cruise control while giving the autonomous mobile device stronger autonomous decision-making and execution capabilities.

[0166] In some embodiments, optionally, the determination unit 506 is specifically used to: perform feature extraction on M environmental parameter information respectively to obtain M environmental features; determine a first feature based on the M environmental features, where the first feature is a feature obtained after feature fusion of the M environmental features; determine a second feature based on the first feature, historical environmental information and prior knowledge of the environment; determine a walking path and sampling parameters based on the second feature and the task requirements of the detection task.

[0167] In this embodiment, feature extraction is performed on M environmental parameter information respectively to obtain M environmental features corresponding to the M environmental parameter information one by one, wherein the M environmental features can represent the M environmental parameter information so as to convert the environmental parameter information into data that can be processed by the automatic moving device. At the same time, feature extraction of the environmental parameter information also facilitates feature fusion of the M environmental parameter information to obtain the first feature.

[0168] In this process, the first feature can describe environmental information from multiple dimensions, so it can be combined with historical environmental information and prior knowledge of the environment to obtain the second feature. The second feature can characterize the current environment in multiple dimensions, so that the autonomous mobile device can fully and accurately understand and judge the current environment, and then plan the walking path and sampling parameters in combination with the task requirements of the detection task.

[0169] In this process, by constructing a second feature so that the second feature can be used to fully perceive the current environmental information, the defect of incomplete information perception by a single sensor in the relevant embodiments is overcome. At the same time, in the process of constructing the second feature, historical environmental information is referenced so that the constructed second feature can include the changing trend of the environmental information, providing a basis for fully understanding the environmental information.

[0170] In addition, the use of prior knowledge of the environment enables the autonomous mobile device to fully understand the environment in which the autonomous mobile device is located, and then plan a reasonable walking path and sampling parameters.

[0171] In some embodiments, the prior knowledge of the environment, that is, the obstacle information in the environment where the autonomous mobile device is located.

[0172] For example, when the environment in which the autonomous mobile device is located is a search and rescue disaster relief environment, the obstacles may be broken tables and chairs, broken stones and broken walls, and the obstacle information may be the position coordinates and size of the tables and chairs, stones and walls.

[0173] For example, when the environment in which the autonomous mobile device is located is an environment of daily life, the obstacles may be tables, chairs, beds and sofas, and the obstacle information may be the orientation coordinates and sizes of the tables, chairs, beds and sofas.

[0174] For example, when the environment in which the autonomous mobile device is located is an industrial production environment, the obstacle may be a shelf, and the obstacle information may be the position coordinates and size of the shelf.

[0175] In some embodiments, the historical environmental information may be environmental information collected by the sensor module at the last detection moment.

[0176] In some embodiments, optionally, the determination unit 506 is also used to: send the updated environmental information to the cloud server, so that the cloud server determines the third feature based on the updated environmental information, historical environmental information and prior knowledge of the environment; receive the third feature sent by the cloud server; and update the walking path and sampling parameters based on the third feature and the task requirements of the detection task.

[0177] In this embodiment, the computing power and storage resources of the autonomous mobile device itself are limited, which makes the intelligent processing and decision-making capabilities of the autonomous mobile device limited. By sending the updated environmental information to the cloud server, the powerful computing and storage capabilities of the cloud server can be utilized to process, analyze and make decisions on the environmental information, so that the autonomous mobile device and the cloud server can operate in coordination, thereby improving the autonomous intelligence level of the autonomous mobile device.

[0178] In this process, compared with autonomous mobile devices, the computing power and storage resources of cloud servers are more powerful, so that the third feature not only contains the same content as the second feature, but also represents the current environment in multiple dimensions more comprehensively and accurately than the second feature. Therefore, the walking path and sampling parameters determined according to the third feature and the task requirements of the detection task are more accurate.

[0179] In some embodiments, optionally, the autonomous mobile device can interact with an interactive terminal, and the interactive terminal communicates with a cloud server. When receiving environmental information from the cloud server, the interactive terminal displays the environmental information and the operating information of the autonomous mobile device. The determination unit 506 is also used to: receive control instructions from the interactive terminal, and the control instructions are determined based on the displayed environmental information and operating information; based on the control instructions, modify the walking path and sampling parameters.

[0180] In this embodiment, the interactive terminal can communicate with the cloud server. Therefore, the interactive terminal can display the environmental information detected by the autonomous mobile device and the operating information of the operation read from the cloud server. The user can use the interactive terminal to view the environmental information detected by the autonomous mobile device and the operating information of the autonomous mobile device. At the same time, the user can use the interactive terminal to receive control instructions input by the user, and then control the autonomous mobile device to correct the walking path and sampling parameters according to the control instructions.

[0181] In this process, it is convenient for users to remotely monitor and control the autonomous mobile device, so as to manually correct the walking path and sampling parameters, thereby realizing the remote control of the autonomous mobile device.

[0182] In some embodiments, the control instruction may be an instruction input based on natural language processing technology, such as sending the control instruction to the interactive terminal in the form of voice and / or text.

[0183] In some embodiments, optionally, the walking path includes multiple waypoints, and the control instruction may be to adjust one or more waypoints in the walking path.

[0184] In some embodiments, optionally, the sampling parameter includes a sampling frequency, and the control instruction may be to increase or decrease the sampling frequency.

[0185] In some embodiments, optionally, the determination unit 506 is also used to: send the updated environmental information to the cloud server, so that the cloud server determines the third feature based on the updated environmental information, historical environmental information and prior knowledge of the environment; and determine the updated walking path and updated sampling parameters based on the third feature and the task requirements of the detection task; receive the updated walking path and updated sampling parameters; control the main body to move according to the updated walking path, and in the process of the main body moving according to the updated walking path, control the sensor module to operate according to the updated sampling parameters.

[0186] In this embodiment, the updated environmental information can be directly sent to the cloud server, so that while the cloud server is used to determine the third feature, an updated walking path and updated sampling parameters can be directly planned, and the updated walking path and updated sampling parameters can be sent to the autonomous mobile device, so that the autonomous mobile device can directly operate according to the updated walking path and updated sampling parameters.

[0187] In this process, the amount of data that needs to be processed by the autonomous mobile device can be reduced, and the accuracy of the walking path and sampling parameters used by the autonomous mobile device during operation can be improved.

[0188] In some embodiments, optionally, the M environmental parameter information includes at least two of the following: environmental images, environmental sounds, environmental odors, and an air quality index in the environment.

[0189] In some embodiments, optionally, the sensor module includes at least two of the following: a visual sensor, an auditory sensor, an olfactory sensor, and an air quality index sensor.

[0190] In some embodiments, optionally, the main body includes a movable chassis, an actuator and a motion control unit arranged on the movable chassis. In the process of controlling the main body to move along the walking path, the processing unit 508 is also used to: drive the actuator to move through the motion control unit to perform the detection task.

[0191] In this embodiment, the operation is performed by controlling the movement of the actuator.

[0192] In one embodiment, if Figure 6 As shown, the present invention provides a control device 600 for an autonomous mobile device, including a processor 602 and a memory 604. The memory 604 stores programs or instructions that can be run on the processor 602. When the programs or instructions are executed by the processor, the steps of any of the above methods are implemented.

[0193] Among them, the memory 604 can be used to store software programs and various data. The memory 604 mainly includes a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area can store an operating system, an application program or instruction required for at least one function (such as a sound playback function, an image playback function, etc.), etc. In addition, the memory 604 may include a volatile memory or a non-volatile memory, or the memory may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM) and a direct memory bus random access memory (DRRAM). The memory in the embodiments of the present application includes but is not limited to these and any other suitable types of memory.

[0194] In one embodiment, the present invention provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of any of the above methods are implemented.

[0195] In one embodiment, the present invention provides an autonomous mobile device, including: a control device as any of the above autonomous mobile devices; and / or a readable storage medium as described above.

[0196] In one embodiment, the autonomous mobile device is a walking robot.

[0197] The term "first" or "second" in the specification and claims of the present application may include one or more of the features explicitly or implicitly. In the textual description of the present invention, unless otherwise specified, "plurality" means two or more. In addition, "and / or" in the specification and claims means at least one of the connected objects, and the character " / " generally means that the objects connected before and after are in an "or" relationship.

[0198] In the text description of the present invention, it is understood that, except for explicit provisions and limitations, the terms "installation", "connection" and "connection" should be understood in a broad sense. For example, it can be fixed connection, detachable connection, or integral connection; it can be mechanical structure connection or electrical connection; it can be direct connection between the two, or indirect connection between the two through an intermediate medium, or it can be internal communication between two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0199] In the claims, specification and drawings of the present invention, the description of the terms "one embodiment", "some embodiments", "specific embodiments" and the like means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In the claims, specification and drawings of the present invention, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0200] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, 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 control method for an autonomous mobile device, characterized in that: The autonomous mobile device includes a body and a sensor module, and the control method includes: Acquire environmental information detected by the sensor module, wherein the environmental information includes M environmental parameter information; Based on N pieces of the environmental parameter information among the M pieces of the environmental parameter information satisfying corresponding trigger conditions, starting a detection task, M ≥ N, and M and N are positive integers; After starting the detection task, determining a walking path and sampling parameters based on the environmental information and the detection task; The main body is controlled to move along the walking path, and in the process of the main body moving along the walking path, the sensor module is controlled to operate according to the sampling parameters to update the environmental information.

2. The control method of the autonomous mobile device according to claim 1, characterized in that: The determining of the walking path and sampling parameters based on the environmental information and the detection task specifically includes: Extracting features from the M pieces of environmental parameter information respectively to obtain M environmental features; Determine a first feature based on the M environmental features, where the first feature is a feature obtained by fusing the M environmental features; determining a second feature based on the first feature, historical environmental information, and prior knowledge of the environment; A walking path and sampling parameters are determined based on the second feature and the task requirements of the detection task.

3. The control method of the autonomous mobile device according to claim 1, characterized in that: The control method further comprises: sending the updated environmental information to a cloud server so that the cloud server determines a third feature based on the updated environmental information, historical environmental information, and prior knowledge of the environment; receiving a third feature sent by the cloud server; The walking path and the sampling parameters are updated based on the third feature and the task requirements of the detection task.

4. The control method of the autonomous mobile device according to claim 3, characterized in that: The autonomous mobile device can interact with an interactive terminal, the interactive terminal communicates with the cloud server, and the interactive terminal displays the environmental information and the operation information of the autonomous mobile device when receiving the environmental information from the cloud server. The control method further includes: receiving a control instruction from the interactive terminal, wherein the control instruction is determined based on the displayed environment information and the operation information; Based on the control instruction, the walking path and the sampling parameters are modified.

5. The control method of the autonomous mobile device according to claim 1, characterized in that: The control method further comprises: sending the updated environmental information to a cloud server so that the cloud server determines a third feature based on the updated environmental information, historical environmental information, and prior knowledge of the environment; and Determine the updated walking path and the updated sampling parameters based on the third feature and the task requirements of the detection task; Receiving the updated walking path and the updated sampling parameters; The main body is controlled to move according to the updated walking path, and in the process of the main body moving according to the updated walking path, the sensor module is controlled to operate according to the updated sampling parameters.

6. The control method of an autonomous mobile device according to any one of claims 1 to 5, characterized in that: The M pieces of environmental parameter information include at least two of the following: Environmental images, environmental sounds, environmental smells, and air quality index within the environment.

7. The control method of an autonomous mobile device according to any one of claims 1 to 5, characterized in that: The sensor module includes at least two of the following: Visual sensors, auditory sensors, olfactory sensors, air quality index sensors.

8. The control method of an autonomous mobile device according to any one of claims 1 to 5, characterized in that: The main body includes a movable chassis, an actuator and a motion control unit arranged on the movable chassis. In the process of controlling the main body to move according to the walking path, the control method further includes: The motion control unit drives the actuator to move so as to perform the detection task.

9. A control device for an autonomous mobile device, characterized in that: The autonomous mobile device comprises a body and a sensor module, and the control device of the autonomous mobile device comprises: An acquisition unit, used to acquire environmental information detected by the sensor module, wherein the environmental information includes M environmental parameter information; A trigger unit, configured to start a detection task based on N pieces of the environmental parameter information among the M pieces of the environmental parameter information satisfying corresponding trigger conditions, where M ≥ N, and M and N are positive integers; A determination unit, configured to determine a walking path and sampling parameters based on the environmental information and the detection task after starting the detection task; The processing unit is used to control the main body to move along the walking path, and in the process of the main body moving along the walking path, control the sensor module to operate according to the sampling parameters to update the environmental information.

10. A control device for an autonomous mobile device, characterized in that: The device comprises a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the control method of the autonomous mobile device according to any one of claims 1 to 8 are implemented.

11. A readable storage medium, characterized in that: The readable storage medium stores a program or an instruction, and when the program or the instruction is executed by a processor, the steps of the control method of the autonomous mobile device according to any one of claims 1 to 8 are implemented.

12. An autonomous mobile device, characterized in that: include: A control device for an autonomous mobile device as claimed in claim 9 or 10; and / or The readable storage medium as claimed in claim 11.