Motion mode switching method and device, service robot and medium

Abstract

The invention discloses a motion mode switching method and device, a service robot and a medium, and relates to the technical field of robot control, and the disclosed motion mode switching method comprises the steps: obtaining video image data and a congestion degree natural language instruction, inputting the video image data and the congestion degree natural language instruction into a trained large visual language model to obtain a personnel congestion level; acquiring a preset target movement speed corresponding to the crowding level, and acquiring a current movement speed of the service robot; and determining a speed smooth change curve according to the current motion speed and the target motion speed, and performing motion mode switching based on the speed smooth change curve. According to the technical scheme, the technical problem of how to improve the working efficiency of the service robot is solved.

Description

Technical Field

[0001] The present application relates to the field of robot control technology, and in particular to a motion mode switching method, device, service robot and medium. Background Art

[0002] Currently, service robots have been widely integrated into the indoor spaces of people's daily lives. These spaces are often highly unstructured, that is, the environment layout, obstacle locations, and personnel flows may change frequently. In order to effectively perform tasks in these complex and changing environments, service robots traditionally rely on preset programs to guide their movement paths. However, this control method that relies on fixed programs is powerless when facing the dynamic changes of indoor environments, because it lacks sufficient flexibility and adaptability to adjust strategies in real time to deal with emergencies or environmental changes.

[0003] Therefore, although the preset program provides a certain action framework for the service robot, in practical applications, it often limits the robot's work efficiency. When the environment changes, such as changes in the flow of personnel, the service robot based on the fixed program may not be able to respond quickly, resulting in low efficiency in task execution, or even stagnation due to the inability to find a suitable path.

[0004] Therefore, how to improve the working efficiency of service robots is a technical problem that needs to be solved by technical personnel in this field. Summary of the invention

[0005] The main purpose of the present application is to provide a motion mode switching method, device, service robot and medium, aiming to solve the technical problem of how to improve the working efficiency of the service robot.

[0006] To achieve the above-mentioned purpose, the present application proposes a motion mode switching method, which is applied to a service robot and includes:

[0007] Acquire video image data and a natural language instruction of the degree of crowding, and input the video image data and the natural language instruction of the degree of crowding into a trained large visual language model to obtain a crowding level of people;

[0008] Obtaining a preset target movement speed corresponding to the crowding level of the personnel, and obtaining a current movement speed of the service robot;

[0009] A speed smooth change curve is determined according to the current movement speed and the target movement speed, and a movement mode switching is performed based on the speed smooth change curve.

[0010] In one embodiment, before the step of inputting the video image data and the natural language instruction of the crowding level into a trained large visual language model to obtain the crowding level of personnel, the method further includes:

[0011] Acquire each historical video image data, and the historical crowding degree natural language instruction corresponding to each of the historical video image data, and the historical personnel crowding level corresponding to each of the historical video image data;

[0012] The historical video image data and the natural language instructions of the historical congestion levels are used as model input data, and the historical personnel congestion levels are used as model training labels to train the preset big visual language model to obtain a trained big visual language model.

[0013] In one embodiment, the step of determining a speed smooth change curve according to the current movement speed and the target movement speed includes:

[0014] Get the speed change duration;

[0015] A speed smooth change curve is determined according to the current movement speed, the target movement speed and the speed change duration.

[0016] In one embodiment, the step of switching the motion mode based on the speed smooth change curve includes:

[0017] Obtaining the current moment, and taking the speed corresponding to the current moment in the speed smooth change curve as a reference speed;

[0018] The motor speed is determined according to the reference speed, and the motor speed is transmitted to the motor so that the motor rotates according to the motor speed.

[0019] In one embodiment, the service robot includes various environment perception sensors, and after the step of switching the motion mode based on the speed smooth change curve, the method further includes:

[0020] Acquire environmental data collected by each of the environmental perception sensors, and calculate dynamic acceleration based on the environmental data;

[0021] determining a difference between an actual speed of the service robot and the reference speed;

[0022] Building an integral sliding mode speed controller based on the environmental data and the dynamic acceleration, and processing the difference through the integral sliding mode speed controller to obtain a new motor speed;

[0023] The new motor speed is transmitted to the motor so that the motor rotates according to the new motor speed.

[0024] In one embodiment, before the step of calculating the dynamic acceleration according to the environmental data, the method further includes:

[0025] Filtering the environmental data by a Kalman filtering method to obtain filtered environmental data;

[0026] The step of calculating the dynamic acceleration according to the environmental data comprises:

[0027] The dynamic acceleration is calculated according to the filtered environmental data.

[0028] In one embodiment, before the step of inputting the video image data and the natural language instruction of the crowding level into a trained large visual language model to obtain the crowding level of personnel, the method further includes:

[0029] Inputting the video image data into an image decoder to obtain a video frame sequence;

[0030] Inputting the congestion degree natural language instruction into a Chinese decoder to obtain congestion instruction information;

[0031] The step of inputting the video image data and the natural language instruction of the crowding degree into the trained large visual language model to obtain the crowding level of personnel includes:

[0032] The video frame sequence and the crowding instruction information are input into a trained large visual language model to obtain a crowding level.

[0033] In addition, to achieve the above-mentioned purpose, the present application also proposes a motion mode switching device, which is applied to a service robot, and the motion mode switching device includes:

[0034] A crowding level determination module is used to obtain video image data and a natural language instruction of crowding level, and input the video image data and the natural language instruction of crowding level into a trained large visual language model to obtain a crowding level of people;

[0035] A speed acquisition module, used to acquire a preset target movement speed corresponding to the crowding level of the personnel, and to acquire a current movement speed of the service robot;

[0036] The speed change control module is used to determine a speed smooth change curve according to the current movement speed and the target movement speed, and perform movement mode switching based on the speed smooth change curve.

[0037] In addition, to achieve the above-mentioned purpose, the present application also proposes a service robot, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the motion mode switching method as described above.

[0038] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the motion mode switching method described above are implemented.

[0039] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the motion mode switching method described above are implemented.

[0040] In the present application, the present application obtains the crowding level of people by acquiring video image data and natural language instructions of crowding level, and inputs the video image data and natural language instructions of crowding level into the trained large visual language model, and can automatically judge the current crowding situation of people based on the working scene of the service robot and the natural language instructions of user level output by the central console; then obtain the preset target movement speed corresponding to the crowding level of people, and obtain the current movement speed of the service robot, and can obtain the current movement speed and the movement speed expected to be achieved after the movement mode switching is completed; then determine the speed smooth change curve according to the current movement speed and the target movement speed, and switch the movement mode based on the speed smooth change curve, and can achieve the effect of smoothly switching from the current movement speed to the target movement speed, so that the problem of rapid acceleration and rapid deceleration can be avoided under the premise of adaptively switching the movement mode. For example, when the service robot moves from an open area to an area with dense population, the present application can automatically judge that it will enter a densely populated area based on the video image data and the instructions output by the central console, so that the service robot can automatically and smoothly reduce the speed to the target movement speed. It can be seen that the present application enables the service robot to operate at a higher speed in open areas and at a lower speed in crowded areas, thereby improving the working efficiency of the service robot. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0043] Figure 1 This is a flow chart of the first embodiment of the motion mode switching method of the present application;

[0044] Figure 2 This is a flow chart of another embodiment of the motion mode switching method of the present application;

[0045] Figure 3 A schematic diagram of a congestion level determination process of an embodiment of a motion mode switching method of the present application;

[0046] Figure 4 This is a schematic diagram of the module structure of the motion mode switching device according to an embodiment of the present application;

[0047] Figure 5 Schematic diagram of the device structure of the hardware operating environment involved in the motion mode switching method in the embodiment of the present application.

[0048] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0049] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0050] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0051] The main solution of the embodiment of the present application is: obtaining video image data and natural language instructions on the degree of crowding, and inputting the video image data and the natural language instructions on the degree of crowding into a trained large visual language model to obtain the crowding level of people; obtaining a preset target motion speed corresponding to the crowding level of people, and obtaining the current motion speed of the service robot; determining a speed smooth change curve according to the current motion speed and the target motion speed, and switching the motion mode based on the speed smooth change curve.

[0052] Currently, service robots have been widely integrated into the indoor spaces of people's daily lives. These spaces are often highly unstructured, that is, the environment layout, obstacle locations, and personnel flows may change frequently. In order to effectively perform tasks in these complex and changing environments, service robots traditionally rely on preset programs to guide their movement paths. However, this control method that relies on fixed programs is powerless when facing the dynamic changes of indoor environments, because it lacks sufficient flexibility and adaptability to adjust strategies in real time to deal with emergencies or environmental changes.

[0053] Therefore, although the preset program provides a certain action framework for the service robot, in practical applications, it often limits the robot's work efficiency. When the environment changes, such as changes in the flow of personnel, the service robot based on the fixed program may not be able to respond quickly, resulting in low efficiency in task execution, or even stagnation due to the inability to find a suitable path.

[0054] Therefore, how to improve the working efficiency of service robots is a technical problem that needs to be solved by technical personnel in this field.

[0055] To solve the above problems, the present application obtains the crowding level of people by acquiring video image data and natural language instructions of crowding level, and inputs the video image data and natural language instructions of crowding level into the trained large visual language model, and can automatically judge the current crowding situation of people based on the working scene of the service robot and the natural language instructions of user level output by the central console; then obtain the preset target movement speed corresponding to the crowding level of people, and obtain the current movement speed of the service robot, and can obtain the current movement speed and the movement speed expected to be achieved after the movement mode switching is completed; then determine the speed smooth change curve according to the current movement speed and the target movement speed, and switch the movement mode based on the speed smooth change curve, and can achieve the effect of smoothly switching from the current movement speed to the target movement speed, so that the problem of rapid acceleration and rapid deceleration can be avoided under the premise of adaptively switching the movement mode. For example, when the service robot moves from an open area to an area with dense population, the present application can automatically judge that it will enter a densely populated area based on the video image data and the instructions output by the central console, so that the service robot can automatically and smoothly reduce the speed to the target movement speed. It can be seen that the present application enables the service robot to run at a higher speed in open areas and at a lower speed in crowded areas, thereby improving the working efficiency of the service robot.

[0056] It should be noted that the execution subject of the motion mode switching method of the present application can be an autonomously movable terminal device with data processing, network communication and program running functions, such as a service robot, an intelligent question-answering robot, etc. The following takes a service robot as an example to illustrate various embodiments of the motion mode switching method of the present application.

[0057] Based on this, the present application embodiment provides a motion mode switching method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the motion mode switching method of the present application.

[0058] In this embodiment, the motion mode switching method is applied to a service robot, and the motion mode switching method includes steps S10 to S30:

[0059] Step S10, obtaining video image data and a natural language instruction of the degree of crowding, and inputting the video image data and the natural language instruction of the degree of crowding into a trained large visual language model to obtain a crowding level;

[0060] It should be noted that a camera is installed on the service robot. Therefore, during the operation of the service robot, the image of the surrounding environment of the service robot can be obtained through the camera. The above-mentioned video image data is the image of the surrounding environment of the service robot when it is running, obtained by the camera. In addition, it should be noted that the above-mentioned natural language instructions for the degree of congestion refer to instructions related to the degree of congestion output by the staff in the central control room. For example, the natural language instructions for the degree of congestion can be relatively crowded, empty, etc. The crowding level of personnel is the recognition result output by the large visual language model to characterize the degree of congestion. For example, the crowding level of personnel can be: not crowded, relatively crowded, moderately crowded, severely crowded, etc. This application does not limit the specific number of levels and level names of the crowding level of personnel.

[0061] Please refer to Figure 2 In a feasible implementation manner, before the above step S10, the method further includes:

[0062] Step S100, acquiring each historical video image data, and the historical crowding degree natural language instruction corresponding to each historical video image data, and the historical personnel crowding level corresponding to each historical video image data;

[0063] It should be noted that historical video image data refers to video image data used to train the large visual language model, and historical congestion degree natural language instructions refer to natural language instructions output by the central control room when collecting historical video image data. The historical personnel congestion level is the personnel congestion level corresponding to the historical video image data. Among them, the historical personnel congestion level can be determined manually or by preset rules, and this application does not limit this. In this embodiment, historical video image data, historical congestion degree natural language instructions, and historical personnel congestion levels are all data for training the large visual language model.

[0064] Step S200, using each of the historical video image data and each of the historical congestion degree natural language instructions as model input data, using each of the historical personnel congestion levels as model training labels, and training the preset large visual language model to obtain a trained large visual language model.

[0065] It can be understood that through historical video image data, historical crowding natural language instructions and historical crowding levels, the model parameters of the big visual language model can be fine-tuned, so that the big visual language model has the ability to automatically identify the crowding level of people.

[0066] In a feasible implementation manner, before the above step S10, the method further includes:

[0067] Step A100, inputting the video image data into an image decoder to obtain a video frame sequence;

[0068] Step A200, inputting the natural language instruction of the degree of congestion into a Chinese decoder to obtain congestion instruction information;

[0069] It should be noted that the image decoder refers to a tool or system for encoding video image data, and the Chinese decoder refers to a tool or system for understanding and processing Chinese encoding. Therefore, the above-mentioned crowding instruction information refers to the encoding of crowding information that can be recognized by the large visual language model, and the above-mentioned video frame sequence refers to the encoding of video information that can be recognized by the large visual language model.

[0070] Based on this, the above step S10 further includes:

[0071] Step S101: input the video frame sequence and the crowding instruction information into a trained large visual language model to obtain a crowding level.

[0072] In this embodiment, the present application encodes the data that needs to be input into the model through an image decoder and a Chinese decoder, thereby increasing the probability that the large visual language model correctly recognizes the input information, thereby increasing the probability that the large visual language model correctly outputs the level of crowd congestion.

[0073] For example, please refer to Figure 3 . Figure 3 This is a schematic diagram of the congestion level determination process of an embodiment of the motion mode switching method of the present application. Figure 3 In the process, the video sequence obtained by the camera on the service robot can be input into the image decoder, and the natural language instructions of the crowding program output by the central control room can be input into the Chinese decoder. Then, the data features of the data input by the image decoder and the Chinese decoder can be extracted through the large visual language model, and then the crowding result (people crowding level) can be determined through the scene perception fuzzy measurement module. Finally, the motion mode of the service robot can be switched based on the crowding result.

[0074] It should be noted that in Figure 3 In the example, the big visual language model is only used to extract data features, and the scene-aware fuzzy metric module is used to determine the crowding result based on the data features. In a feasible implementation, the scene-aware fuzzy metric module can also be integrated into the big visual language model, so that the crowding result can be obtained based only on the big visual language model.

[0075] It is understandable that in Figure 3 In the embodiment, scene perception is implemented based on the scene recognition network of the big visual language model, and scene state measurement is implemented based on fuzzy measurement. Specifically, in this embodiment, multimodal information (natural language and video image data) can be input into the big visual language model, and then the scene corresponding to the multimodal information can be inferred based on the big visual language model to obtain the congestion result of the scene. It can be understood that in the present application, natural language is used to limit the reasoning mode of the big visual language model, so as to ensure that the big visual language model can analyze the density of people in the scene according to user needs and form a congestion result.

[0076] Step S20, obtaining a preset target movement speed corresponding to the crowding level of the personnel, and obtaining the current movement speed of the service robot;

[0077] It is understandable that the motion modes of the service robot include: walking straight, turning, steering, etc. Among them, the switching between the motion modes needs to be achieved by changing the speed of the service robot.

[0078] It is understandable that for different crowding levels, speeds corresponding to different crowding levels can be preset. For example, in densely populated areas, it runs at a lower speed, and in sparsely populated areas, it runs at a higher speed. Therefore, after obtaining the crowding level output by the large visual language model, the preset speed corresponding to the crowding level can be used as the target movement speed. In addition, in order to facilitate smooth speed switching, it is also necessary to obtain the current movement speed of the service robot.

[0079] Step S30, determining a speed smooth change curve according to the current movement speed and the target movement speed, and performing movement mode switching based on the speed smooth change curve.

[0080] It should be noted that the speed smooth change curve is a curve used to indicate that the speed changes smoothly from the current motion speed to the target motion speed.

[0081] In a feasible implementation, the speed smooth change curve can be determined by exponential smoothing, moving average, integral sliding film, S-type speed curve control algorithm, etc., and this application does not limit this. After obtaining the speed smooth change curve, the rotation of each wheel on the service robot can be controlled according to the speed smooth change curve, thereby realizing the motion mode switching of the service robot.

[0082] In a feasible implementation manner, the above step S30 includes:

[0083] Step S301, obtaining speed change duration;

[0084] It should be noted that the speed change duration refers to the time it takes to adjust the current motion speed to the target motion speed. Those skilled in the art can independently determine the speed change duration based on factors such as the hardware model and application scenario of the service robot, and this application does not limit this.

[0085] For example, if the current motion speed needs to be adjusted to the target motion speed within 2 seconds, the speed change duration is 2 seconds.

[0086] Step S302: determining a speed smooth change curve according to the current movement speed, the target movement speed and the speed change duration.

[0087] In this embodiment, the present application determines the speed smooth change curve by using the current movement speed, target movement speed and speed change duration, and can obtain a speed smooth change curve that is compatible with the service robot based on the application scenario and hardware model of the service robot, thereby improving the work efficiency of the service robot.

[0088] In a feasible implementation manner, the above step S30 further includes:

[0089] Step S303, obtaining the current moment, and taking the speed corresponding to the current moment in the speed smooth change curve as the reference speed;

[0090] It is understandable that the correspondence between time and speed is recorded in the speed smooth change curve. After determining the current time, the speed corresponding to the current time in the speed smooth change curve can be used as the reference speed, so as to control the service robot to achieve motion mode switching based on the reference speed.

[0091] Step S304 , determining the motor speed according to the reference speed, and transmitting the motor speed to the motor so that the motor rotates according to the motor speed.

[0092] In this embodiment, the service robot also stores the correspondence between the speed and the motor speed. Therefore, after obtaining the reference speed, the motor speed corresponding to the reference speed can be determined based on the correspondence. Then, the motor can be controlled to move according to the motor speed, thereby achieving the purpose of motion mode switching.

[0093] In this embodiment, the present application can control the service robot to smoothly switch modes based on the speed smooth change curve, ensuring smooth and stable switching of the robot's motion modes.

[0094] In the present application, the present application obtains the crowding level of people by acquiring video image data and natural language instructions of crowding level, and inputs the video image data and natural language instructions of crowding level into the trained large visual language model, and can automatically judge the current crowding situation of people based on the working scene of the service robot and the natural language instructions of user level output by the central console; then obtain the preset target movement speed corresponding to the crowding level of people, and obtain the current movement speed of the service robot, and can obtain the current movement speed and the movement speed expected to be achieved after the movement mode switching is completed; then determine the speed smooth change curve according to the current movement speed and the target movement speed, and switch the movement mode based on the speed smooth change curve, and can achieve the effect of smoothly switching from the current movement speed to the target movement speed, so that the problem of rapid acceleration and rapid deceleration can be avoided under the premise of adaptively switching the movement mode. For example, when the service robot moves from an open area to an area with dense population, the present application can automatically judge that it will enter a densely populated area based on the video image data and the instructions output by the central console, so that the service robot can automatically and smoothly reduce the speed to the target movement speed. It can be seen that the present application enables the service robot to run at a higher speed in open areas and at a lower speed in crowded areas, thereby improving the working efficiency of the service robot.

[0095] Furthermore, based on the above-mentioned first embodiment of the motion mode switching method of the present application, a second embodiment of the motion mode switching method of the present application is proposed.

[0096] In this embodiment, the service robot includes various environment perception sensors. After the above step S30, the method further includes:

[0097] Step S40, acquiring environmental data collected by each of the environmental perception sensors, and calculating dynamic acceleration according to the environmental data;

[0098] It should be noted that the environment perception sensor refers to a sensor used to perceive the motion state of the service robot itself and the surrounding environment. For example, the environment perception sensor may be a gyroscope, an accelerometer, an encoder, and the like.

[0099] In addition, it should be noted that dynamic acceleration refers to the change of acceleration of an object over time and position during its motion. Dynamic acceleration is difficult to measure directly, so it can only be estimated based on environmental data. Specifically, dynamic acceleration can be estimated based on environmental data and the robot's motion model.

[0100] Step S50, determining the difference between the actual speed of the service robot and the reference speed;

[0101] Step S60, constructing an integral sliding mode speed controller based on the environmental data and the dynamic acceleration, and processing the difference through the integral sliding mode speed controller to obtain a new motor speed;

[0102] It should be noted that the integral sliding mode speed controller is used to adjust the reference speed so that the motion mode switching is smooth and stable. Among them, the method for constructing the integral sliding mode speed controller can be an integral sliding mode control algorithm, specifically, an adaptive integral sliding mode control algorithm, or a linear variable gain integral sliding mode control algorithm, or an integral sliding mode control algorithm based on an extended state observer can be adopted, and this application does not limit this.

[0103] It is understandable that the response and performance of the actuators in the service robot will affect the movement speed of the service robot. Usually, when the movement of the service robot is controlled based on the reference speed, the actual speed of the service robot is often not equal to the reference speed. Therefore, it is necessary to use an integral sliding mode speed controller to calculate the speed used to control the movement of the service robot at the next moment in real time according to the current speed difference, so as to achieve the purpose of allowing the service robot to smoothly switch the movement mode.

[0104] Step S70: transmitting the new motor speed to the motor so that the motor rotates according to the new motor speed.

[0105] In this embodiment, the present application calculates the motor speed at the next moment in real time through an integral sliding mode speed control controller, which can not only dynamically correct the speed smooth change curve, but also ensure that the service robot can smoothly switch modes.

[0106] In a feasible implementation manner, before the above step of calculating the dynamic acceleration according to the environmental data, the method further includes:

[0107] Step S80, filtering the environmental data by a Kalman filtering method to obtain filtered environmental data;

[0108] It is understandable that there are usually noise and errors in the environmental data obtained through environmental perception sensors. In order to improve the accuracy of the environmental data, it is also necessary to filter the environmental data through the Kalman filtering method, so as to obtain more accurate environmental data.

[0109] Thus, the dynamic acceleration can be calculated based on the filtered environmental data.

[0110] In this embodiment, the present application improves the accuracy of dynamic acceleration estimation by filtering environmental data using a Kalman filtering method.

[0111] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the motion mode switching method of the present application. More simple transformations based on this technical concept are all within the protection scope of the present application.

[0112] This application also provides a motion mode switching device, please refer to Figure 4 The motion mode switching device is applied to a service robot, and the motion mode switching device comprises:

[0113] The crowding level determination module 10 is used to obtain video image data and a natural language instruction of crowding level, and input the video image data and the natural language instruction of crowding level into a trained large visual language model to obtain a crowding level of people;

[0114] A speed acquisition module 20, used to acquire a preset target movement speed corresponding to the crowding level of the personnel, and to acquire a current movement speed of the service robot;

[0115] The speed change control module 30 is used to determine a speed smooth change curve according to the current movement speed and the target movement speed, and perform movement mode switching based on the speed smooth change curve.

[0116] In one embodiment, the motion mode switching device comprises:

[0117] A training set acquisition module, used to acquire each historical video image data, and a natural language instruction of a historical congestion degree corresponding to each of the historical video image data, and a historical personnel congestion level corresponding to each of the historical video image data;

[0118] The model training module is used to train the preset big visual language model with each of the historical video image data and each of the historical congestion degree natural language instructions as model input data and each of the historical personnel congestion levels as model training labels to obtain a trained big visual language model.

[0119] In one embodiment, the speed change control module 30 is further used to:

[0120] Get the speed change duration;

[0121] A speed smooth change curve is determined according to the current movement speed, the target movement speed and the speed change duration.

[0122] In one embodiment, the speed change control module 30 is further used to:

[0123] Obtaining the current moment, and taking the speed corresponding to the current moment in the speed smooth change curve as a reference speed;

[0124] The motor speed is determined according to the reference speed, and the motor speed is transmitted to the motor so that the motor rotates according to the motor speed.

[0125] In one embodiment, the service robot includes various environment perception sensors, and the motion mode switching device includes:

[0126] A dynamic acceleration estimation module, used to obtain the environmental data collected by each of the environmental perception sensors, and calculate the dynamic acceleration based on the environmental data;

[0127] a system error determination module, configured to determine a difference between an actual speed of the service robot and the reference speed;

[0128] A speed update module, used for constructing an integral sliding mode speed controller based on the environmental data and the dynamic acceleration, and processing the difference through the integral sliding mode speed controller to obtain a new motor speed;

[0129] The speed update module is used to transmit the new motor speed to the motor so that the motor rotates according to the new motor speed.

[0130] In one embodiment, the motion mode switching device comprises:

[0131] A filtering module, used for filtering the environmental data by a Kalman filtering method to obtain filtered environmental data;

[0132] Based on this, the above dynamic acceleration estimation module is also used for:

[0133] The dynamic acceleration is calculated according to the filtered environmental data.

[0134] In one embodiment, the motion mode switching device comprises:

[0135] An image decoding module, used for inputting the video image data into an image decoder to obtain a video frame sequence;

[0136] A language decoding module, used for inputting the natural language instruction of the congestion degree into a Chinese decoder to obtain congestion instruction information;

[0137] Based on this, the above-mentioned congestion level determination module 10 is also used for:

[0138] The video frame sequence and the crowding instruction information are input into a trained large visual language model to obtain a crowding level.

[0139] The motion mode switching device provided by the present application adopts the motion mode switching method in the above embodiment, which can solve the technical problem of how to improve the working efficiency of the service robot. Compared with the prior art, the beneficial effects of the motion mode switching device provided by the present application are the same as the beneficial effects of the motion mode switching method provided by the above embodiment, and the other technical features in the motion mode switching device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0140] The present application provides a service robot, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the motion mode switching method in the above-mentioned embodiment one.

[0141] Reference below Figure 5 , which shows a schematic structural diagram of a service robot suitable for implementing an embodiment of the present application. Figure 5 The service robot shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0142] like Figure 5As shown, the service robot may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the service robot are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the service robot to communicate with other devices wirelessly or wired to exchange data. Although the service robot with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0143] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0144] The service robot provided by the present application adopts the motion mode switching method in the above embodiment, which can solve the technical problem of how to improve the working efficiency of the service robot. Compared with the prior art, the beneficial effects of the service robot provided by the present application are the same as the beneficial effects of the motion mode switching method provided by the above embodiment, and the other technical features of the service robot are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0145] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0146] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0147] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the motion mode switching method in the above-mentioned embodiment.

[0148] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0149] The computer-readable storage medium may be included in the service robot; or it may exist independently without being assembled into the service robot.

[0150] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the service robot, the service robot: obtains video image data and natural language instructions on the degree of crowding, and inputs the video image data and the natural language instructions on the degree of crowding into a trained large visual language model to obtain a crowding level; obtains a preset target motion speed corresponding to the crowding level, and obtains the current motion speed of the service robot; determines a speed smooth change curve according to the current motion speed and the target motion speed, and switches motion modes based on the speed smooth change curve.

[0151] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0152] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0153] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0154] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned motion mode switching method, and can solve the technical problem of how to improve the working efficiency of the service robot. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the motion mode switching method provided by the above-mentioned embodiment, and will not be repeated here.

[0155] The present application also provides a computer program product, including a computer program, which implements the steps of the motion mode switching method as described above when executed by a processor.

[0156] The computer program product provided by this application can solve the technical problem of how to improve the working efficiency of the service robot. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the motion mode switching method provided by the above embodiment, which will not be repeated here.

[0157] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A motion mode switching method, It is characterized in that The motion mode switching method is applied to a service robot, and the motion mode switching method comprises: Acquire video image data and a natural language instruction of the degree of crowding, and input the video image data and the natural language instruction of the degree of crowding into a trained large visual language model to obtain a crowding level of people; Obtaining a preset target movement speed corresponding to the crowding level of the personnel, and obtaining a current movement speed of the service robot; A speed smooth change curve is determined according to the current movement speed and the target movement speed, and a movement mode switching is performed based on the speed smooth change curve.

2. The motion mode switching method according to claim 1, It is characterized in that Before the step of inputting the video image data and the natural language instruction of the degree of crowding into the trained large visual language model to obtain the crowding level of personnel, the method further includes: Acquire each historical video image data, and the historical crowding degree natural language instruction corresponding to each of the historical video image data, and the historical personnel crowding level corresponding to each of the historical video image data; The historical video image data and the natural language instructions of the historical congestion levels are used as model input data, and the historical personnel congestion levels are used as model training labels to train the preset big visual language model to obtain a trained big visual language model.

3. The motion mode switching method according to claim 1, It is characterized in that The step of determining a speed smooth change curve according to the current movement speed and the target movement speed comprises: Get the speed change duration; A speed smooth change curve is determined according to the current movement speed, the target movement speed and the speed change duration.

4. The motion mode switching method according to claim 3, It is characterized in that The step of switching the motion mode based on the speed smooth change curve includes: Obtaining the current moment, and taking the speed corresponding to the current moment in the speed smooth change curve as a reference speed; The motor speed is determined according to the reference speed, and the motor speed is transmitted to the motor so that the motor rotates according to the motor speed.

5. The motion mode switching method according to claim 4, It is characterized in that The service robot includes various environment perception sensors. After the step of switching the motion mode based on the speed smooth change curve, the method further includes: Acquire environmental data collected by each of the environmental perception sensors, and calculate dynamic acceleration based on the environmental data; determining a difference between an actual speed of the service robot and the reference speed; Building an integral sliding mode speed controller based on the environmental data and the dynamic acceleration, and processing the difference through the integral sliding mode speed controller to obtain a new motor speed; The new motor speed is transmitted to the motor so that the motor rotates according to the new motor speed.

6. The motion mode switching method according to claim 5, It is characterized in that Before the step of calculating the dynamic acceleration according to the environmental data, the method further includes: Filtering the environmental data by a Kalman filtering method to obtain filtered environmental data; The step of calculating the dynamic acceleration according to the environmental data comprises: The dynamic acceleration is calculated according to the filtered environmental data.

7. The motion mode switching method according to claim 1, It is characterized in that Before the step of inputting the video image data and the natural language instruction of the degree of crowding into the trained large visual language model to obtain the crowding level of personnel, the method further includes: Inputting the video image data into an image decoder to obtain a video frame sequence; Inputting the congestion degree natural language instruction into a Chinese decoder to obtain congestion instruction information; The step of inputting the video image data and the natural language instruction of the crowding degree into the trained large visual language model to obtain the crowding level of personnel includes: The video frame sequence and the crowding instruction information are input into a trained large visual language model to obtain a crowding level.

8. A motion mode switching device, It is characterized in that The motion mode switching device is applied to a service robot, and the motion mode switching device comprises: A crowding level determination module is used to obtain video image data and a natural language instruction of crowding level, and input the video image data and the natural language instruction of crowding level into a trained large visual language model to obtain a crowding level of people; A speed acquisition module, used to acquire a preset target movement speed corresponding to the crowding level of the personnel, and to acquire a current movement speed of the service robot; The speed change control module is used to determine a speed smooth change curve according to the current movement speed and the target movement speed, and perform movement mode switching based on the speed smooth change curve.

9. A service robot, It is characterized in that The service robot comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the motion mode switching method as described in any one of claims 1 to 7.

10. A storage medium, It is characterized in that The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the motion mode switching method according to any one of claims 1 to 7 are implemented.

Images