Wheel robot control method, system, wheel robot, and storage medium

Abstract

The application provides a wheeled robot control method, system, wheeled robot and storage medium, and relates to the technical field of robots.The method comprises the following steps: in the process of controlling the operation of a wheeled robot based on a first target process module, if a first instruction signal is acquired, first control instruction information in the first instruction signal is identified, wherein the first instruction signal comprises a first voice signal and / or a first gesture image; a second target process module is determined from the process module based on the first control instruction information; if the second target process module affects the balance state of the wheeled robot under the control of the first target process module, a target motion mode in which the wheeled robot keeps the balance state and operates is determined based on the first target process module and the second target process module; and the operation of the wheeled robot is controlled based on the target motion mode.The technical scheme provided by the application realizes the balance control of the wheeled robot and can save control resources.

Description

Technical Field

[0001] This invention relates to the field of robotics, and more particularly to a wheeled robot control method, system, wheeled robot, and storage medium. Background Technology

[0002] Wheeled robots are robots that use wheels as their locomotion device. They are characterized by high flexibility and fast movement speed, and can adapt to different terrains and environments. These robots have been widely used in industries, homes, medical care, agriculture, education and other fields.

[0003] In the control process of wheeled robots, balance control is fundamental to ensuring their normal operation, especially for two-wheeled robots, where balance control is particularly crucial. Therefore, how to achieve balance control for wheeled robots is a pressing technical problem that needs to be solved. Summary of the Invention

[0004] This invention provides a wheeled robot control method, system, wheeled robot, and storage medium to achieve balance control of the wheeled robot.

[0005] This invention provides a control method for a wheeled robot, comprising:

[0006] During the process of controlling the operation of the wheeled robot based on the first target process module, when a first command signal is acquired, the first control command information in the first command signal is identified; the first command signal includes a first voice signal and / or a first gesture image;

[0007] The second target process module is determined from the process module based on the first control instruction information;

[0008] If it is determined that the second target process module affects the balance state of the wheeled robot under the control of the first target process module, a target motion mode for the wheeled robot to maintain balance is determined based on the first target process module and the second target process module.

[0009] The wheeled robot is controlled to operate based on the target motion mode.

[0010] According to a wheeled robot control method provided by the present invention, the step of determining the target motion mode for the wheeled robot to maintain a balanced state based on the first target process module and the second target process module includes:

[0011] Determine the scene information when the wheeled robot receives the first command signal;

[0012] Based on the scene information, the first target process module and the second target process module determine the target motion mode for the wheeled robot to maintain a balanced state.

[0013] According to a wheeled robot control method provided by the present invention, the step of determining the target motion mode for the wheeled robot to maintain a balanced state based on the scene information, the first target process module, and the second target process module includes:

[0014] Based on the scenario information, the control parameters corresponding to the third target process module are adjusted to obtain the target control parameters corresponding to the third target process module; the third target process module includes the first target process module and / or the second target process module;

[0015] The third target process module and the corresponding target control parameters are determined as the target motion mode for the wheeled robot to maintain a balanced state.

[0016] According to a wheeled robot control method provided by the present invention, the step of determining the target motion mode for the wheeled robot to maintain a balanced state based on the scene information, the first target process module, and the second target process module includes:

[0017] A fourth target process module is determined based on the scenario information, and the fourth target process module includes either the first target process module or the second target process module;

[0018] The fourth target process module is defined as the target motion mode in which the wheeled robot maintains a balanced state.

[0019] Specifically, if the fourth target process module is the first target process module, the second target process module is closed; if the fourth target process module is the second target process module, the first target process module is closed.

[0020] According to a wheeled robot control method provided by the present invention, the step of determining a second target process module from the process modules based on the first control instruction information includes:

[0021] Determine the target instruction scenario type of the first control instruction information;

[0022] Based on the target instruction scenario type, a process module matching the target instruction scenario type is searched from the process module information database to obtain the second target process module; the process module information database is used to store the correspondence between instruction scenario types and process modules.

[0023] A wheeled robot control method provided by the present invention further includes:

[0024] If an anomaly is detected in the control process of the first target process module or the control process of the second target process module, the anomaly-causing control process is restarted.

[0025] The present invention also provides a wheeled robot control system, comprising:

[0026] The instruction recognition unit is used to identify the first control instruction information in the first instruction signal when a first instruction signal is acquired during the process of controlling the operation of the wheeled robot based on the first target process module; the first instruction signal includes a first voice signal and / or a first gesture image.

[0027] A process module determination unit is used to determine a second target process module from the process modules based on the first control instruction information;

[0028] The motion mode determination unit is used to determine the target motion mode for the wheeled robot to maintain its balanced state based on the first target process module and the second target process module, when it is determined that the second target process module affects the balance state of the wheeled robot under the control of the first target process module.

[0029] A control unit is used to control the operation of the wheeled robot based on the target motion mode.

[0030] The present invention also provides a wheeled robot, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the wheeled robot control method as described above.

[0031] The present invention also provides a wheeled robot, including a memory and a processor, and further including a voice acquisition device and / or an image acquisition device;

[0032] The voice acquisition device is used to acquire voice signals;

[0033] The image acquisition device is used to acquire gesture images;

[0034] The processor is used to execute the computer program stored in the memory to implement the wheeled robot control method as described above.

[0035] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the wheeled robot control method as described above.

[0036] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the wheeled robot control method as described above.

[0037] The wheeled robot control method, system, wheeled robot, and storage medium provided by this invention, in the process of controlling the operation of the wheeled robot based on a first target process module, when a first instruction signal is acquired, identifies the first control instruction information in the first instruction signal, and determines a second target process module from the process modules based on the first control instruction information, thus obtaining the process module to be used when controlling the wheeled robot through the first instruction signal; then it is determined whether the second target process module will affect the balance state of the wheeled robot under the control of the first target process module. If it will, a target motion mode for maintaining the balance state of the wheeled robot is determined based on the first target process module and the second target process module, and the operation of the wheeled robot is controlled based on the target motion mode. In this way, when a new instruction signal is received during the operation of the wheeled robot, it can ensure that the wheeled robot continues to operate in a motion mode that maintains the balance state, thus realizing the balance control of the wheeled robot. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0039] Figure 1 This is a flowchart illustrating the wheeled robot control method provided in an embodiment of the present invention;

[0040] Figure 2 This is a schematic diagram of the structure of the wheeled robot control system provided in an embodiment of the present invention;

[0041] Figure 3 This is one of the structural schematic diagrams of the wheeled robot provided in the embodiments of the present invention;

[0042] Figure 4 This is the second structural schematic diagram of the wheeled robot provided in the embodiment of the present invention. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0044] It should be noted that the serial numbers assigned to the objects described in this invention, such as "first" and "second", are only used to distinguish the objects being described and do not have any sequential or technical meaning.

[0045] Wheeled robots are characterized by their high flexibility and speed, enabling them to adapt to various terrains and environments and leading to their wide range of applications. In related technologies, wheeled robots are controlled via communication-connected computer equipment or wireless remote controls, employing a hardware-based approach to basic motion control, resulting in a relatively low level of intelligence. Furthermore, balance control is fundamental to the normal operation of wheeled robots, especially for two-wheeled robots, where balance control is particularly crucial.

[0046] Based on this, embodiments of the present invention provide a wheeled robot control method that can ensure the wheeled robot continues to operate in a balanced motion mode when a new command signal is received during the operation of the wheeled robot.

[0047] The following is combined Figure 1 The wheeled robot control method of the present invention is described below. This wheeled robot control method can be applied to wheeled robots or electronic devices such as mobile phones, computers, tablets, and servers that are communicatively connected to wheeled robots, and can also be applied to wheeled robot control systems installed in wheeled robots or electronic devices.

[0048] Figure 1 An exemplary flowchart of a wheeled robot control method provided in an embodiment of the present invention is shown below. Figure 1 As shown, the wheeled robot control method may include the following steps 110 to 140.

[0049] Step 110: During the process of controlling the wheeled robot to operate based on the first target process module, when the first instruction signal is obtained, the first control instruction information in the first instruction signal is identified.

[0050] The first command signal includes voice signals and / or gesture images. The first control command information can instruct the wheeled robot to perform scene functions, such as tracking, patrolling, and handling objects.

[0051] Wheeled robots may include voice acquisition devices and / or image acquisition devices. The voice acquisition devices can acquire voice signals, and the image acquisition devices can acquire gesture images. The voice acquisition devices may include microphones or microphone arrays, and the image acquisition devices include cameras.

[0052] Wheeled robots can perform a variety of functions, including patrolling, tracking, transporting goods, providing intelligent reminders, and answering questions, but are not limited to these. When a user needs the wheeled robot to perform a certain function, they can send voice signals to control it to perform the relevant actions, or they can control it to perform the relevant actions via gesture commands. The wheeled robot can collect the user's voice signals through a voice acquisition device and recognize the voice control command information in the voice signals to control the wheeled robot. Alternatively, it can collect the user's gesture images through an image acquisition device and perform gesture recognition on the gesture images to obtain the gesture control command information to control the wheeled robot.

[0053] Specifically, in one example embodiment, if the first command signal acquired by the wheeled robot includes a first voice signal, then the corresponding first control command information includes first voice control command information. Accordingly, when the first command signal is acquired, identifying the first control command information in the first command signal may include: when the first voice signal acquired by the voice acquisition device is acquired, performing voice recognition on the first voice signal, and determining the first voice control command information in the first voice signal based on the voice recognition result.

[0054] For example, after a wheeled robot acquires a first voice signal through a voice acquisition device, it can perform speech recognition on the first voice signal, convert it into text information, and then perform keyword detection on the text information to obtain the first voice control command information. Alternatively, it can perform semantic understanding on the text information obtained from speech recognition to obtain the first voice control command information.

[0055] For example, when a wheeled robot is currently performing a patrol task under the control of the first target process module, it can perform voice recognition on the voice signal "look up" when it receives the voice signal "look up". The recognition result can be used to detect the command keyword "look up". If the command keyword "look up" can be detected, then "look up" can be identified as the first voice control command information.

[0056] The first target process module can be determined based on the received second instruction signal. Specifically, before controlling the wheeled robot to operate based on the first target process module, the method further includes: acquiring the second instruction signal and identifying second control instruction information in the second instruction signal; determining the first target process module from the process modules based on the second control instruction information. The second instruction signal includes a second voice signal and / or a second gesture image.

[0057] For example, if a user needs a wheeled robot to patrol area A, they can control the robot via voice control. For instance, the user can send a second voice signal, "Start patrolling area A," to the robot. Upon receiving this signal, the robot performs voice recognition and detects the command keywords, identifying "patrol" and "area A." These keywords are then identified as the second voice control command. Based on this command, the necessary process modules for patrolling area A can be determined, including modules related to patrolling such as positioning and navigation, path planning, and motion control. These process modules constitute the corresponding first target process modules.

[0058] In one example embodiment, the first command signal acquired by the wheeled robot may include a first gesture image, and the corresponding first control command information includes first gesture control command information. Accordingly, when the first command signal is acquired, identifying the first control command information in the first command signal may include: acquiring the first gesture image captured by the image acquisition device and performing gesture recognition on the first gesture image; searching for command information that matches the gesture recognition result from the gesture command information database based on the gesture recognition result, and determining the command information as the first gesture control command information.

[0059] After the wheeled robot acquires a first gesture image through an image acquisition device, it can perform gesture recognition on the first gesture image to obtain the gesture in the first gesture image. The wheeled robot can pre-set the correspondence between gestures and command information. For example, the first gesture corresponds to patrol command information, the second gesture corresponds to tracking command information, and the third gesture corresponds to transporting goods command information, etc. After recognizing the gesture from the first gesture image, the corresponding command information can be matched from the gesture-command information correspondence. This command information is the determined first gesture control command information.

[0060] For example, if a user needs a wheeled robot to patrol area A, they can control the robot using gestures. For instance, the user makes a first gesture, and the robot captures the image of the gesture using an image acquisition device. It then recognizes the gesture as the first gesture and matches it with the pre-set gesture-command information mapping to find the corresponding command information, "patrol." At this point, a voice prompt indicating the designated patrol area can be output to the user via a voice output device. The user can then make another gesture indicating the designated patrol area. The robot captures the image of the gesture again and matches it with the command information "Area A" in the same way. The command information "patrol" and "Area A" are then identified as the first gesture control command information at this point.

[0061] In one example embodiment, the first instruction signal acquired by the wheeled robot may include a first voice signal and a first gesture image. The first voice control instruction information identified from the first voice signal and the first gesture control instruction information determined based on the gesture identified from the first gesture image are determined as the first control instruction information, which can combine voice and gesture to control the wheeled robot.

[0062] Step 120: Determine the second target process module from the process modules based on the first control instruction information.

[0063] After the wheeled robot recognizes the first control command information, it can determine from the process modules that need to be called to complete the action indicated by the first control command information, and identify these process modules as the second target process modules.

[0064] For example, in one exemplary embodiment, determining the second target process module from the process modules of a wheeled robot based on the first control command information may include: determining the target command scenario type of the first control command information; and searching for a process module that matches the target command scenario type in the process module information database to obtain the second target process module; wherein the process module information database is used to store the correspondence between command scenario types and process modules.

[0065] The instruction scenario types can include at least one of the following, but are not limited to: patrolling, tracking, transporting goods, intelligent reminders, and intelligent question answering. The process module is a functional module that controls the wheeled robot's movements. Each functional module can include multiple processes required to complete that function. These functional modules may include, for example, a positioning and navigation module, a path planning module, a motion control module, an alarm module, a face recognition module, an intelligent question answering module, an image processing module, an audio module, and a human posture detection module, but are not limited to these.

[0066] For each type of instruction scenario, there can be at least one corresponding process module. That is, the implementation of an instruction scenario type requires the invocation of at least one process module. For example, in a patrol scenario, a wheeled robot needs to move along a planned path and monitor the surrounding area during the movement. In this scenario, the wheeled robot needs to invoke patrol-related process modules such as the positioning and navigation module, the path planning module, and the motion control module to complete the patrol control of the wheeled robot. These process modules are the target process modules.

[0067] For example, communication between process modules can be achieved using the Robot Operating System (ROS) communication method.

[0068] Step 130: Given that the second target process module affects the balance state of the wheeled robot under the control of the first target process module, determine the target motion mode for the wheeled robot to maintain its balance state based on the first target process module and the second target process module.

[0069] The target motion mode may include: a mode in which the wheeled robot is controlled by a first target process module, a mode in which the wheeled robot is controlled by a second target process module, a motion mode after adjusting the control parameters corresponding to the first target process module and / or the second target process module, or a mode in which the first target process module is closed and the second target process module is started after the first target process module has finished executing its process, etc.

[0070] For example, a correspondence between a first target process module, a second target process module, and a motion mode can be pre-established. If it is determined that the second target process module affects the balance state of the wheeled robot under the control of the first target process module, then based on the first and second target process modules, the corresponding motion mode is found from the correspondence to obtain the target motion mode. The motion mode can include at least one of the following: controlling the wheeled robot's operation with the first target process module; controlling the wheeled robot's operation with the second target process module; adjusting the control parameters corresponding to the first and / or second target process modules; and closing the first target process module and starting the second target process module to control the wheeled robot's operation after the first target process module's process is completed.

[0071] For example, the target motion mode for maintaining the wheeled robot's balanced operation can be determined by combining the scene information when the wheeled robot receives the first command signal, as well as the first target process module and the second target process module. The scene information can be road condition information during the wheeled robot's operation, such as going straight, turning, going uphill, or going downhill, or it can be different task scenarios, such as intelligent question answering, tracking, or alarming. Different target motion mode determination strategies can be applied under different scene information.

[0072] Specifically, determining the target motion mode for the wheeled robot to maintain a balanced state based on the first target process module and the second target process module may include: determining the scene information when the wheeled robot receives the first command signal; and determining the target motion mode for the wheeled robot to maintain a balanced state based on the scene information, the first target process module, and the second target process module.

[0073] In one example embodiment, the scene information of the wheeled robot when it receives the first command signal can be determined based on the process modules included in the first target process module and the process position that the first target process module is running at when the first command signal is received. For example, if the first target process module is a process module related to controlling the wheeled robot to patrol, and the first command signal is received during the patrol process, the current execution stage can be determined based on the running position of the process in the first target process module. For example, if it is moving straight, the scene information can be determined to be a straight-moving scene during the patrol process.

[0074] Alternatively, the wheeled robot's image acquisition equipment can be used to capture images of the surrounding road during operation. By analyzing these images, the scene information of the current operating scenario can be determined, such as whether it is moving straight, turning, going uphill, or going downhill. Alternatively, upon receiving the first command signal, the wheeled robot's current attitude information can be acquired, and the scene information of the current operating scenario can be determined based on this attitude information. Alternatively, the scene information of the current operating scenario can be determined by combining the attitude information and the road image.

[0075] In one example embodiment, determining the target motion mode for the wheeled robot to maintain balance based on scene information, the first target process module, and the second target process module may include: adjusting the control parameters corresponding to the third target process module based on the scene information to obtain the target control parameters corresponding to the third target process module; and determining the third target process module and the corresponding target control parameters as the target motion mode for the wheeled robot to maintain balance. The third target process module includes the first target process module and / or the second target process module.

[0076] For example, a first correspondence between scene information, the third target process module, and control parameters can be established in advance. After determining the scene information when the wheeled robot receives the first command signal, the third target process module and the corresponding control parameters can be determined based on the first correspondence, and the target control parameters corresponding to the third target process module can be obtained.

[0077] For example, taking the control of a wheeled robot to patrol along a planned path based on the first target process module as an example, during the patrol, assuming a "head-up" control command is obtained, the relevant process modules controlling the wheeled robot to perform the head-up action can be determined from the process modules based on the "head-up" control command information. These process modules may affect the balance state of the wheeled robot during the current patrol. At this time, the current scene information of the wheeled robot can be obtained, such as the surrounding road image captured by the wheeled robot's image acquisition device. By analyzing this image, the current scene information can be obtained. For example, if the obtained scene information is straight-line, meaning the wheeled robot is currently patrolling in a straight line, to avoid the wheeled robot falling over due to the potential impact of head-up on its balance state, the control parameters corresponding to the first target process module can be adjusted, or the control parameters corresponding to the second target process module can be adjusted, or both the control parameters corresponding to the first and second target process modules can be adjusted simultaneously to obtain the target control parameters. By adjusting the control parameters, the posture of the wheeled robot can be corrected to ensure that the wheeled robot maintains a balanced state during operation. For example, the control parameters corresponding to the second target process module required for straight movement and head-up can be found from the pre-established first correspondence. The target control parameters corresponding to the second target process module can be obtained. These target control parameters may include the head-up angle. At this time, the second target process module can be called to control the wheeled robot to perform the head-up action based on the target control parameters, on the basis of executing the first target process module. Alternatively, the control parameters corresponding to the first target process module and the second target process module can be adjusted at the same time. For example, the speed of the wheeled robot when it moves straight under the control of the first target process module can be reduced and the head-up angle corresponding to the second target process module can be determined. The wheeled robot can then be controlled to move straight at the adjusted speed and perform the head-up action at the determined head-up angle.

[0078] For example, if the obtained scene information is uphill, the control parameters corresponding to the second target process module required for uphill movement and head-up action can be found from the pre-established first correspondence. These control parameters may include the head-up angle, which will be smaller than the head-up angle when moving straight, in order to ensure the balance of the wheeled robot.

[0079] In one example embodiment, determining the target motion mode for the wheeled robot to maintain a balanced state based on scene information, the first target process module, and the second target process module may include: determining a fourth target process module based on scene information, the fourth target process module including either the first target process module or the second target process module; determining the fourth target process module as the target motion mode for the wheeled robot to maintain a balanced state; wherein, if the fourth target process module is the first target process module, the second target process module is turned off; and if the fourth target process module is the second target process module, the first target process module is turned off.

[0080] For example, a second correspondence can be pre-established between scene information, the first target process module, the second target process module, and the fourth target process module. After determining the scene information when the wheeled robot receives the first command signal, the process module required for the next step can be determined based on this first correspondence when a new second target process module appears during the process of controlling the wheeled robot's operation based on the first target process module. For instance, the first target process module can be turned off and the second target process module can be turned on, and the wheeled robot can be controlled based on the second target process module. At this time, the wheeled robot stops the currently executing functional task and switches to executing the functional task corresponding to the second target process module. Alternatively, the wheeled robot can continue to be controlled based on the first target process module while the second target process module is turned off. At this time, the wheeled robot continues to execute the current functional task and ignores the functional task corresponding to the second target process module. Or, the first target process module can be turned off and the second target process module can be turned on after executing the functional task corresponding to the first target process module. At this time, the wheeled robot executes the functional task corresponding to the second target process module after executing the current functional task.

[0081] For example, taking the control of a wheeled robot to patrol along a planned path based on the first target process module as an example, during the patrol, assuming a "head-up" control command is obtained, a second target process module related to controlling the wheeled robot to perform the head-up action can be determined from the process module based on the "head-up" control command information. This second target process module may affect the balance state of the wheeled robot's current patrol. At this time, the current scene information of the wheeled robot can be obtained. For example, if the obtained scene information is straight-line, the wheeled robot can continue to operate based on the first target process module without activating the second target process module, or the first target process module can be turned off and the second target process module can be turned on. For example, if the obtained scene information is turning or uphill, the wheeled robot can continue to operate based on the first target process module without activating the second target process module. For example, if the obtained scene information is downhill, the first target process module can be turned off and the second target process module can be turned on.

[0082] Optionally, different scenario information can correspond to different process module selection strategies. For example, taking the detection of a "look up" command during patrol as an example, if the current scenario information is straight ahead, the first target process module can be closed and the second target process module can be opened, or both the first and second target process modules can be opened simultaneously and their corresponding control parameters can be adjusted; if the current scenario information is turning or going uphill, the first target process module can be opened and the second target process module can be closed, or both the first and second target process modules can be opened simultaneously and their corresponding control parameters can be adjusted; if the current scenario information is going downhill, the first target process module can be closed and the second target process module can be opened, or both the first and second target process modules can be opened simultaneously and their corresponding control parameters can be adjusted.

[0083] In one example embodiment, a correspondence between process modules that influence the balance state of a wheeled robot can be established in advance. During the operation of the wheeled robot under the control of the first target process module, the correspondence can be used to determine whether a newly determined second target process module will affect the balance state of the wheeled robot under the control of the first target process module.

[0084] Alternatively, after identifying the second target process module, we can first determine the adjustment information of the wheeled robot's posture relative to the first target process module when it executes the action of the second target process module. Then, we can determine whether the adjustment information will disrupt the current balance state of the wheeled robot. If it will, we can determine that the second target process module affects the balance state of the wheeled robot under the control of the first target process module.

[0085] Step 140: Control the operation of the wheeled robot based on the target motion mode.

[0086] Once the target motion mode is determined, the wheeled robot can be controlled to operate in a balanced state based on that target motion mode.

[0087] The wheeled robot control method provided in this invention, during the process of controlling the operation of the wheeled robot based on a first target process module, when a first command signal is acquired, identifies the first control command information in the first command signal, and determines a second target process module from the process modules based on the first control command information. This allows obtaining the process module used to control the wheeled robot through the first command signal. Then, it determines whether the second target process module will affect the balance state of the wheeled robot under the control of the first target process module. If it does, a target motion mode for maintaining the balance state of the wheeled robot is determined based on the first and second target process modules, and the operation of the wheeled robot is controlled based on the target motion mode. Thus, when a new command signal is received during the operation of the wheeled robot, it can ensure that the wheeled robot continues to operate in a motion mode that maintains its balance state, achieving balance control of the wheeled robot. Furthermore, the acquired first command signal includes a first voice signal and / or a first gesture image, enabling control of the wheeled robot using voice and / or gesture interaction, achieving intelligent control of the wheeled robot.

[0088] In one exemplary embodiment of the present invention, when the wheeled robot operates under the control of the current target process module, all other process modules are shut down. For example, during the process of controlling the wheeled robot's operation based on the first target process module, only the first target process module is enabled, while other process modules are disabled; or, during the process of controlling the wheeled robot's operation based on the first target process module and obtaining a first instruction signal, during the process of controlling the wheeled robot's operation based on the determined target motion mode, only the target process module corresponding to the target motion mode is enabled, while other process modules are disabled. This releases the resource occupation of irrelevant background processes and saves control resources.

[0089] Understandably, during the process of controlling a wheeled robot to perform related tasks using the first target process module, this module can be dynamically updated based on the actions performed. For example, when controlling a wheeled robot to perform a patrol task using the target process module in a patrol scenario, if a stranger is detected, an alarm can be triggered, and the alarm module will be additionally invoked and added to the first target process module. Alternatively, when a stranger is detected, tracking can be performed, and the tracking function module will be additionally invoked and dynamically added to the first target process module.

[0090] For example, a wheeled robot can move its body via a base driver. Specifically, this base driver can control the robot's movement under the control of application layer software and provide status feedback to the application layer software.

[0091] based on Figure 1 In one example embodiment of the wheeled robot control method corresponding to the embodiment, the method may further include: restarting the abnormal control process when an abnormality is detected in the control process of the first target process module or the control process of the second target process module.

[0092] Specifically, during the process of controlling the wheeled robot's operation based on the first target process module or the target motion mode, some or all of the control processes in the first target process module or the target process module corresponding to the target motion mode may malfunction, such as loss of motion control. The wheeled robot can detect the running status of each control process in each target process module in real time or periodically. If an abnormality is detected in a certain control process in the target process module, the abnormal control process is restarted, which can ensure the normal operation of the wheeled robot without the user's awareness.

[0093] based on Figure 1 In one example embodiment of the wheeled robot control method corresponding to the embodiments, the wheeled robot can communicate with a remote electronic device, allowing a user to remotely obtain on-site images captured by the wheeled robot through the remote electronic device. Specifically, the method may further include: upon receiving a monitoring command sent by the remote electronic device, activating the wheeled robot's monitoring device and sending the monitoring images captured by the monitoring device to the remote electronic device; receiving third control command information sent by the remote electronic device based on the monitoring images, and controlling the wheeled robot's actions based on the third control command information.

[0094] Remote electronic devices can include computers, tablets, mobile phones, servers, etc.

[0095] Specifically, when a user needs to remotely view the monitoring footage captured by the wheeled robot, they can send a monitoring command to the wheeled robot, which is connected to the remote electronic device, via a remote electronic device. Upon receiving the command, the wheeled robot activates its monitoring equipment, captures images of the monitored area, and sends the captured images to the remote electronic device. The remote electronic device then displays the images on its screen, achieving the purpose of remote monitoring. In essence, the wheeled robot can move on-site according to control commands, capturing scene images of the area it moves in. Based on this, users can remotely monitor the site.

[0096] After receiving monitoring images from the wheeled robot, users can view the situation in real time, make corresponding decisions based on the situation, and send third-party control commands to the wheeled robot to control it to perform relevant actions, thus realizing remote monitoring and control.

[0097] The wheeled robot control system provided by the present invention will be described below. The wheeled robot control system described below can be referred to in correspondence with the wheeled robot control method described above.

[0098] Figure 2 An exemplary schematic diagram of the structure of the wheeled robot control system provided in an embodiment of the present invention is shown, with reference to... Figure 2 As shown, the wheeled robot control system may include: an instruction recognition unit 210, used to identify first control instruction information in a first instruction signal when a first instruction signal is acquired during the process of controlling the operation of the wheeled robot based on a first target process module, wherein the first instruction signal includes a first voice signal and / or a first gesture image; a process module determination unit 220, used to determine a second target process module from the process modules based on the first control instruction information; a motion mode determination unit 230, used to determine a target motion mode for the wheeled robot to maintain its balanced state based on the first target process module and the second target process module when it is determined that the second target process module affects the balance state of the wheeled robot under the control of the first target process module; and a control unit 240, used to control the operation of the wheeled robot based on the target motion mode.

[0099] In one example embodiment, the motion mode determination unit 230 includes: a first determination subunit, used to determine scene information when the wheeled robot receives a first instruction signal; and a second determination subunit, used to determine the target motion mode for the wheeled robot to maintain a balanced state based on the scene information, the first target process module, and the second target process module.

[0100] In one example embodiment, the second determining subunit is specifically used to: adjust the control parameters corresponding to the third target process module based on scene information to obtain the target control parameters corresponding to the third target process module; the third target process module includes the first target process module and / or the second target process module; and determine the third target process module and the corresponding target control parameters as the target motion mode for the wheeled robot to maintain a balanced state.

[0101] In one example embodiment, the second determining subunit is specifically used to: determine a fourth target process module based on scene information, the fourth target process module including a first target process module or a second target process module; determine the fourth target process module as the target motion mode for the wheeled robot to maintain a balanced state; wherein, if the fourth target process module is the first target process module, the second target process module is turned off; if the fourth target process module is the second target process module, the first target process module is turned off.

[0102] In one example embodiment, the process module determination unit 220 includes: a third determination subunit, used to determine the target instruction scenario type of the first control instruction information; and a search subunit, used to search for a process module that matches the target instruction scenario type from the process module information database based on the target instruction scenario type, to obtain a second target process module; wherein the process module information database is used to store the correspondence between instruction scenario types and process modules.

[0103] In one example embodiment, the wheeled robot control system may further include: an exception handling unit, used to restart the control process that has encountered an exception when an exception is detected in the control process of the first target process module or the control process of the second target process module.

[0104] In one example embodiment, the wheeled robot control system may further include: a monitoring unit, configured to activate the monitoring device of the wheeled robot upon receiving a monitoring instruction sent by a remote electronic device, and to send the monitoring images collected by the monitoring device to the remote electronic device; the control unit 240 is further configured to receive third control instruction information sent by the remote electronic device based on the monitoring images, and to control the wheeled robot's actions based on the third control instruction information.

[0105] Figure 3 One example is a schematic diagram of the structure of a wheeled robot, such as... Figure 3As shown, the wheeled robot may include a processor 310, a communication interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 can call logical instructions in the memory 330 to execute the wheeled robot method provided in any of the above method embodiments. This method may include, for example, the following: during the process of controlling the operation of the wheeled robot based on a first target process module, upon obtaining a first instruction signal, identifying first control instruction information in the first instruction signal, wherein the first instruction signal includes a first voice signal and / or a first gesture image; determining a second target process module from the process modules based on the first control instruction information; if it is determined that the second target process module affects the balance state of the wheeled robot under the control of the first target process module, determining a target motion mode for the wheeled robot to maintain its balance state based on the first target process module and the second target process module; and controlling the operation of the wheeled robot based on the target motion mode.

[0106] Figure 4 Example 2: A schematic diagram of a wheeled robot, as shown below. Figure 4 As shown, the wheeled robot may include a memory 410 and a processor 420, and may also include a voice acquisition device 430 and / or an image acquisition device 440.

[0107] The voice acquisition device 430 is used to acquire voice signals, and the voice acquisition device 430 can be a microphone or a microphone array. The image acquisition device 440 is used to acquire gesture images, and the image acquisition device 440 includes a camera.

[0108] The wheeled robot also includes a communication interface 450 and a communication bus 460, wherein the processor 420, the communication interface 450, and the memory 410 can communicate with each other through the communication bus 460. The processor 420 can call logical instructions in the memory 410 to execute the wheeled robot method provided in any of the above method embodiments. The method may include, for example, the following: during the process of controlling the operation of the wheeled robot based on a first target process module, upon obtaining a first instruction signal, identifying first control instruction information in the first instruction signal, wherein the first instruction signal includes a first voice signal and / or a first gesture image; determining a second target process module from the process modules based on the first control instruction information; if it is determined that the second target process module affects the balance state of the wheeled robot under the control of the first target process module, determining a target motion mode for the wheeled robot to maintain its balance state based on the first target process module and the second target process module; and controlling the operation of the wheeled robot based on the target motion mode.

[0109] For example, processors 310 and 420 may include a central processing unit (CPU), a microprocessor, a network processor (NP), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0110] For example, communication bus 340 and communication bus 460 can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc.

[0111] Furthermore, the logical instructions in the aforementioned memories 330 and 410 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0112] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the wheeled robot control method provided in the above-described method embodiments. This method may include, for example, the following: during the process of controlling the operation of the wheeled robot based on a first target process module, upon obtaining a first command signal, identifying first control command information in the first command signal, wherein the first command signal includes a first voice signal and / or a first gesture image; determining a second target process module from the process modules based on the first control command information; if it is determined that the second target process module affects the balance state of the wheeled robot under the control of the first target process module, determining a target motion mode for the wheeled robot to maintain its balance state based on the first target process module and the second target process module; and controlling the operation of the wheeled robot based on the target motion mode.

[0113] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program is implemented to perform the wheeled robot control method provided in the above-described method embodiments. This method may include, for example, the following: during the process of controlling the operation of the wheeled robot based on a first target process module, upon receiving a first command signal, identifying first control command information in the first command signal, wherein the first command signal includes a first voice signal and / or a first gesture image; determining a second target process module from the process modules based on the first control command information; if it is determined that the second target process module affects the balance state of the wheeled robot under the control of the first target process module, determining a target motion mode for the wheeled robot to maintain its balance state based on the first target process module and the second target process module; and controlling the operation of the wheeled robot based on the target motion mode.

[0114] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0115] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0116] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A control method for a wheeled robot, characterized in that, include: During the process of controlling the operation of the wheeled robot based on the first target process module, when a first command signal is acquired, the first control command information in the first command signal is identified; the first command signal includes a first voice signal and / or a first gesture image; The second target process module is determined from the process module based on the first control instruction information; If it is determined that the second target process module affects the balance state of the wheeled robot under the control of the first target process module, the scene information of the wheeled robot when it receives the first instruction signal is determined, and the target motion mode of the wheeled robot to maintain balance is determined based on the scene information, the first target process module and the second target process module. The wheeled robot is controlled to operate based on the target motion mode; The method for determining the target motion mode includes: Based on the scenario information, the control parameters corresponding to the third target process module are adjusted to obtain the target control parameters corresponding to the third target process module; the third target process module includes the first target process module and / or the second target process module; The third target process module and the corresponding target control parameters are determined as the target motion mode for the wheeled robot to maintain a balanced state. A fourth target process module is determined based on the scenario information, and the fourth target process module includes the first target process module or the second target process module; The fourth target process module is defined as the target motion mode in which the wheeled robot maintains a balanced state. Specifically, if the fourth target process module is the first target process module, the second target process module is closed; if the fourth target process module is the second target process module, the first target process module is closed.

2. The wheeled robot control method according to claim 1, characterized in that, The step of determining the second target process module from the process modules based on the first control instruction information includes: Determine the target instruction scenario type of the first control instruction information; Based on the target instruction scenario type, a process module matching the target instruction scenario type is searched from the process module information database to obtain the second target process module; the process module information database is used to store the correspondence between instruction scenario types and process modules.

3. The wheeled robot control method according to any one of claims 1 to 2, characterized in that, Also includes: If an anomaly is detected in the control process of the first target process module or the control process of the second target process module, the anomaly-causing control process is restarted.

4. A control system for a wheeled robot, characterized in that, The wheeled robot control method according to claim 1 includes: The instruction recognition unit is used to identify the first control instruction information in the first instruction signal when a first instruction signal is acquired during the process of controlling the operation of the wheeled robot based on the first target process module; the first instruction signal includes a first voice signal and / or a first gesture image. A process module determination unit is used to determine a second target process module from the process modules based on the first control instruction information; The motion mode determination unit is used to determine the target motion mode for the wheeled robot to maintain its balanced state based on the first target process module and the second target process module, when it is determined that the second target process module affects the balance state of the wheeled robot under the control of the first target process module. A control unit is used to control the operation of the wheeled robot based on the target motion mode.

5. A wheeled robot, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the wheeled robot control method as described in any one of claims 1 to 3.

6. A wheeled robot, comprising a memory and a processor, characterized in that, It also includes voice acquisition devices and / or image acquisition devices; The voice acquisition device is used to acquire voice signals; The image acquisition device is used to acquire gesture images; When the processor executes the computer program stored in the memory, it implements the wheeled robot control method as described in any one of claims 1 to 3.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the wheeled robot control method as described in any one of claims 1 to 3.

Images