Ground state detection method, device, equipment and medium based on accompanying robot

Abstract

The present application discloses a ground state detection method, device, equipment and medium based on a companion robot. The method includes: obtaining a ground state image and infrared data within a preset range of the companion robot through an image acquisition device and an infrared pair tube; comparing the ground state image with a pre-stored sample image to determine a first ground state of the ground state image; filtering the infrared data to obtain ground feedback data, and identifying the difference based on the ground feedback data to determine a second ground state; determining whether the first ground state is consistent with the second ground state, and if so, determining the ground state; if not, obtaining the current motor working state of the companion robot, and determining the contact friction coefficient between the companion robot's travel device and the ground contact surface through the motor working state; determining the ground state within the preset range based on the contact friction coefficient, the first ground state and the second ground state; and determining a moving path based on the ground state.

Description

Technical Field

[0001] The present application relates to the field of data processing, and specifically to a ground state detection method, device, equipment and medium based on a companion robot. Background Art

[0002] With the development of technology, robots have gradually come into our sight. How to use the machines safely and reasonably is still an unavoidable topic. Most traditional household and commercial robots use wheeled chassis, which have great safety risks. Major news websites have reported that shopping malls have been in trouble because of robots falling down. During activities, accompanying robots may encounter problems such as robots falling down due to uneven ground.

[0003] Therefore, a method is urgently needed to solve the problem that the robot will only use the same driving method when encountering uneven ground or steps, carpets, wooden floors, tiles, and concrete floors during walking, that is, to avoid the problem that the robot will forcefully move forward regardless of the ground conditions ahead. Summary of the invention

[0004] In order to solve the above problems, the present application proposes a ground state detection method, device, equipment and medium based on a companion robot, wherein the method includes:

[0005] Through the image acquisition device and the infrared tube, the ground state image and infrared data within the preset range of the escort robot are respectively obtained; the ground state image is compared with a plurality of pre-stored ground state sample images to determine the first ground state of each area in the ground state image; the infrared data is filtered to obtain ground feedback data, and the difference is identified based on the ground feedback data to determine the second ground state of each area; it is determined whether the first ground state and the second ground state corresponding to any area are consistent, and if they are consistent, the ground state of any area is determined; if they are inconsistent, the current motor working state of the escort robot is obtained, and the contact friction coefficient between the escort robot travel device and the ground contact surface is determined through the motor working state; the ground state within the preset range is determined based on the contact friction coefficient, the first ground state and the second ground state; the moving path of the escort robot is determined based on the ground state.

[0006] In one example, comparing the ground state image with a plurality of pre-stored ground state sample images to determine the first ground state of each area in the ground state image specifically includes: obtaining ground state sample images of different types of ground as a sample set; confirming a preset initial convolutional neural network model, and training the initial convolutional neural network using a back propagation algorithm based on the sample set to obtain a ground state assessment model; and inputting the ground state image into the convolutional neural network model to determine the first ground state.

[0007] In one example, after determining the ground state, the method also includes: receiving ground detection instructions and obtaining current force information of the companion robot; determining the current motion state of the companion robot based on the current force information and the motor working state; and adjusting the current motion state of the companion robot based on the ground state.

[0008] In one example, adjusting the current motion state of the escort robot according to the ground state specifically includes: determining the ground state boundary in the moving path of the escort robot according to the ground state; determining the critical moving speed threshold of the escort robot according to the ground states on both sides of the ground state boundary; and controlling the working state of the motor of the escort robot according to the critical moving speed threshold so that the escort robot changes the driving speed in advance before reaching the boundary.

[0009] In one example, the method also includes: obtaining the historical movement trajectory of the companion robot and generating the activity range of the companion robot; storing the ground state within the activity range in a database; determining that the companion robot is within the activity range, and transmitting the ground state within the activity range to the companion robot.

[0010] In one example, determining the planned path of the escort robot according to the ground state specifically includes: determining the target location of the escort robot, and determining multiple intermediate locations according to the target location, the current position of the escort robot and the ground state; selecting any two adjacent intermediate locations from the multiple intermediate locations, and determining multiple initial planned paths between the any two adjacent intermediate locations according to the ground state; determining a preset reward function, the reward function at least including a travel reward function and a turning reward function; determining the travel path weights and the turning path weights corresponding to the multiple initial planned paths respectively according to the ground state and the reward function; and determining the planned path of the escort robot according to the travel path weights and the turning path weights.

[0011] In one example, after determining the ground state, the method further includes: generating a ground state image based on the ground state within a preset range of the companion robot; confirming the presence of a special ground state in the ground state image; and issuing a ground state reminder to the user based on the ground state image and the special ground state.

[0012] The present application also provides a ground state detection device based on a companion robot, the device comprising: a sensor module, used to obtain a ground state image and infrared data within a preset range of the companion robot; a ground state determination module, used to compare the ground state image with a plurality of pre-stored ground state sample images to determine the first ground state of each area in the ground state image; filtering the infrared data to obtain ground feedback data, and identifying the difference based on the ground feedback data to determine the second ground state of each area; and also used to determine whether the first ground state and the second ground state respectively corresponding to any area are consistent, and if they are consistent, determine the ground state of any area; a friction coefficient determination module, used to obtain the current motor working state of the companion robot, and determine the contact friction coefficient between the companion robot travel device and the ground contact surface through the motor working state; the ground state determination module is also used to determine the ground state within the preset range based on the contact friction coefficient, the first ground state and the second ground state; a moving path determination module, used to determine the moving path of the companion robot based on the ground state.

[0013] The present application also provides a ground state detection device based on a companion robot, comprising: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions that can be executed 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: through an image acquisition device and an infrared pair tube, respectively obtain a ground state image and infrared data within a preset range of the companion robot; compare the ground state image with a plurality of pre-stored ground state sample images to determine a first ground state of each area in the ground state image; filter the infrared data to obtain ground feedback data, and identify the difference according to the ground feedback data to determine a second ground state of each area; determine whether the first ground state and the second ground state corresponding to any area are consistent, and if they are consistent, determine the ground state of any area; if they are inconsistent, obtain the current motor working state of the companion robot, and determine the contact friction coefficient between the companion robot travel device and the ground contact surface through the motor working state; determine the ground state within the preset range according to the contact friction coefficient, the first ground state and the second ground state; determine the moving path of the companion robot according to the ground state.

[0014] The present application also provides a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured to: obtain a ground state image and infrared data within a preset range of the escort robot through an image acquisition device and an infrared pair tube; compare the ground state image with a plurality of pre-stored ground state sample images to determine a first ground state of each area in the ground state image; filter the infrared data to obtain ground feedback data, and identify the difference based on the ground feedback data to determine a second ground state of each area; determine whether the first ground state and the second ground state corresponding to any area are consistent, and if they are consistent, determine the ground state of any area; if they are inconsistent, obtain the current motor working state of the escort robot, and determine the contact friction coefficient between the escort robot travel device and the ground contact surface through the motor working state; determine the ground state within the preset range based on the contact friction coefficient, the first ground state and the second ground state; and determine the moving path of the escort robot based on the ground state.

[0015] The method proposed in the present application can simultaneously determine the ground state in the vicinity of the escort robot through image data and infrared data, and by comparing the ground states obtained by these two methods, a more accurate ground state type or ground state data can be obtained. If the ground states obtained by these two methods are quite different, the contact friction coefficient between the escort robot's traveling device and the ground can be calculated, and the more accurate one of the two ground states can be selected through the contact friction coefficient, thereby preventing the robot from moving forward regardless of the ground state ahead. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0017] Figure 1 This is a flow chart of a ground state detection method based on a companion robot in an embodiment of the present application;

[0018] Figure 2 This is a structural schematic diagram of a ground state detection device based on a companion robot in an embodiment of the present application;

[0019] Figure 3 This is a schematic diagram of the structure of a ground state detection device based on a companion robot in an embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0021] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0022] Figure 1 A flow chart of a ground state detection method based on a companion robot provided for one or more embodiments of this specification. The method can be applied to companion robots in different fields, such as shopping mall guidance types. The process can be executed by a computing device of a corresponding type of companion robot (e.g., a computing module disposed inside the companion robot, etc.), and some input parameters or intermediate results in the process allow manual intervention and adjustment to help improve accuracy.

[0023] like Figure 1As shown, the embodiment of the present application provides a ground state detection method based on a companion robot, comprising:

[0024] S101: Obtaining the ground state image and infrared data within a preset range of the accompanying robot through an image acquisition device and an infrared pair tube.

[0025] In order to obtain the ground state within the preset range of the accompanying robot, it is necessary to use an image acquisition device and an infrared pair of tubes to obtain the ground state image and infrared data within the preset range of the accompanying robot. It should be noted that the preset range here refers to the vicinity of the accompanying robot, and its specific range size can be set according to the type of accompanying robot and the size of computing power. In one embodiment, the infrared pair of tubes automatically obtains infrared data after the accompanying robot is powered on, and the infrared pair of tubes are evenly distributed in front, behind, left and right of the robot.

[0026] S102: Compare the ground state image with a plurality of pre-stored ground state sample images to determine a first ground state of each area in the ground state image.

[0027] After obtaining the ground state image, the ground state image is compared with a plurality of pre-stored ground state sample images to determine the first ground state of each area in the ground state image. It should be noted that the pre-stored plurality of ground state sample images can be pre-stored in the storage device of the accompanying robot. When the ground state needs to be detected, the accompanying robot can select a plurality of ground state sample images from the storage device. Of course, the computer device can also obtain the plurality of ground state sample images from other external devices. For example, a plurality of ground state sample images are stored in the cloud. When the ground state needs to be detected, the computer device can obtain a plurality of ground state sample images from the cloud. This embodiment does not limit the method for obtaining the plurality of ground state sample images. The first ground state here refers to the ground state within the preset range obtained by the accompanying robot through image data, i.e., the ground state image, through calculation.

[0028] S103: Filter the infrared data to obtain ground feedback data, and perform identification difference based on the ground feedback data to determine the second ground state of each area.

[0029] While calculating the first ground state, it is also necessary to calculate the second ground state of each area within the preset range based on the infrared data. When calculating the second ground state, the collected infrared data must first be filtered to remove the interference data to obtain ground feedback data, and then the ground feedback data is used to identify the difference. The feedback obtained from different grounds will be different. By identifying the difference and dividing the data, the second ground state corresponding to each area within the preset range can be obtained.

[0030] S104: Determine whether the first ground state and the second ground state corresponding to any area are consistent; if they are consistent, determine the ground state of any area.

[0031] After determining the first ground state and the second ground state by two kinds of data respectively, compare the first ground state and the second ground state corresponding to any area, that is, check whether the first ground state and the second ground state corresponding to this area are consistent. If they are consistent, it means that the ground states determined by these two methods are correct. At this time, any ground state can be selected as the ground state of the area. It should be noted that the area here is divided within a preset range, and there are many ways to divide it. It can be divided by a ground state image, such as dividing the ground state image within the preset range into multiple areas by edge detection.

[0032] S105: If they are inconsistent, the current motor working state of the accompanying robot is obtained, and the contact friction coefficient between the traveling device of the accompanying robot and the ground contact surface is determined according to the motor working state.

[0033] We should also consider the situation when the first ground state and the second ground state are inconsistent. In order to determine which of the first ground state and the second ground state is closer to the actual situation, we can calculate the contact friction coefficient between the traveling device of the escort robot and the ground contact surface. Due to different ground states, the contact friction coefficient between the traveling device and the ground is also different. When calculating the contact friction coefficient, it is necessary to obtain the current motor working state of the escort robot, and then determine the contact friction coefficient between the traveling device of the escort robot and the ground contact surface based on the motor working state.

[0034] S106: Determine the ground state within the preset range according to the contact friction coefficient, the first ground state, and the second ground state.

[0035] After calculating the contact friction coefficient, since the first ground state and the second ground state are different, the contact friction coefficient between the traveling device and the ground is also different. Therefore, the size of the contact friction coefficient can be used to judge whether the actual ground state is more inclined to the first ground state or the second ground state.

[0036] S107: Determine a moving path of the accompanying robot according to the ground state.

[0037] After determining the ground conditions in the area, the moving path of the accompanying robot can be further determined based on the ground conditions to avoid the situation where the robot has to move forward regardless of the ground conditions ahead.

[0038] In one embodiment, when comparing a ground state image with a plurality of pre-stored ground state sample images to determine the first ground state of each area in the ground state image, it is first necessary to pre-acquire ground state sample images of the escort robot on different types of ground as a sample set, and then confirm the preset initial convolutional neural network model, and input the sample set into the initial convolutional neural network model, and use the back propagation algorithm to train the initial convolutional neural network. When the set training precision and accuracy are reached, it is determined that the training of the currently trained model is completed to obtain a ground state assessment model; when determining the first ground state of each area in the ground state image, the ground state image can be directly input into the convolutional neural network model to determine the first ground state.

[0039] In one embodiment, after the ground state is determined, in order to ensure that the escort robot can maintain smooth driving in any ground state, the motor working state of the escort robot should be changed according to the different ground states. Therefore, it is necessary to first obtain the motion state of the escort robot. After the escort robot receives the ground detection instruction, the current force information of the escort robot can be obtained, and then the current motion state of the escort robot can be determined based on the force information and the current motor working state, and then the current motion state of the escort robot can be adjusted according to the ground state. It should be noted that the current force information of the escort robot can be obtained by sensors set in various areas of the escort robot's travel device.

[0040] Furthermore, when adjusting the current motion state of the escort robot according to the ground state, it is first necessary to determine the ground state boundary in the moving path of the escort robot according to the ground state within the preset range. The ground state boundary here refers to the ground state of the escort robot and the boundary of the next ground state in the moving path. According to the ground states corresponding to both sides of the ground state boundary, the critical moving speed threshold of the escort robot is determined. The critical moving speed threshold here refers to the upper limit of the moving speed of the escort robot when it is close to the boundary. If the speed is too fast, it may roll over, slip, etc. when entering the area of ​​the next ground state. Then, according to the critical moving speed threshold, the working state of the motor of the escort robot is controlled so that the escort robot changes the driving speed in advance before reaching the boundary, so that the driving speed drops below the critical moving speed threshold.

[0041] Since most escort robots have a fixed range of activity, and within a fixed range of activity, the ground state does not change too frequently. Therefore, the historical movement trajectory of the escort robot can be obtained to generate the range of activity of the escort robot; the ground state within the range of activity is stored in the database; when the escort robot is determined to be within the range of activity, the ground state within the range of activity is transmitted to the escort robot. This can avoid the escort robot from constantly calculating the ground state, thereby wasting a lot of computing resources. The escort robot can be set to collect the ground state once at a preset interval, thereby preventing the ground state from suddenly changing, which may lead to unexpected situations.

[0042] In one embodiment, when determining the planned path of the accompanying robot according to the ground state, the target location of the accompanying robot must first be determined, and multiple intermediate locations must be determined according to the target location, the current location of the accompanying robot, and the ground state; the intermediate location here refers to a location between the target location and the current location, and the ground state is in a location where the accompanying robot can travel. Select any two adjacent intermediate locations from the multiple intermediate locations, and determine multiple initial planned paths between the two adjacent intermediate locations according to the ground state. It should be noted that there are multiple initial planned paths between the two adjacent intermediate locations. Then determine the preset reward function, where the reward function at least includes a travel reward function and a turning reward function. The travel reward function refers to the reward function of the accompanying robot during the travel process, and the driving time from the first intermediate location to the second intermediate location, the length of the path, and other factors can be used as reference items. The turning reward function refers to the reward function when the accompanying robot is at the intermediate location and needs to turn, and the turning angle, time spent, and other factors can be used as reference items. According to the ground state and the reward function, the travel path weights and the turning path weights corresponding to the multiple initial planned paths are determined, so as to determine the planned path of the accompanying robot according to the travel path weights and the turning path weights.

[0043] In one embodiment, since the main purpose of the accompanying robot is to accompany the user, when the accompanying robot finds that there is a special ground state within the preset range, it should promptly issue a reminder to the user. Therefore, the accompanying robot should be able to generate a ground state image based on the ground state within the preset range of the accompanying robot. When it is confirmed that there are special ground states such as steps and depressions in the ground state image, the corresponding ground state reminder should be issued to the user based on the ground state image and the special ground state.

[0044] like Figure 2 As shown, the embodiment of the present application also provides a structural schematic diagram of a ground state detection device based on a companion robot, and the ground state detection device includes:

[0045] The sensor module 201 is used to obtain ground status images and infrared data within a preset range of the accompanying robot.

[0046] The ground state determination module 202 is used to compare the ground state image with a plurality of pre-stored ground state sample images to determine the first ground state of each area in the ground state image; to filter the infrared data to obtain ground feedback data, and to identify the difference based on the ground feedback data to determine the second ground state of each area; and to determine whether the first ground state corresponding to any area is consistent with the second ground state. If they are consistent, the ground state of any area is determined.

[0047] The friction coefficient determination module 203 is used to obtain the current motor working state of the accompanying robot, and determine the contact friction coefficient between the accompanying robot's traveling device and the ground contact surface according to the motor working state.

[0048] The ground state determination module 202 is further configured to determine the ground state within the preset range according to the contact friction coefficient, the first ground state, and the second ground state.

[0049] The moving path determination module 204 is used to determine the moving path of the accompanying robot according to the ground state.

[0050] like Figure 3 As shown, the embodiment of the present application also provides a ground state detection device based on a companion robot, including:

[0051] at least one processor; and,

[0052] a memory communicatively connected to the at least one processor; wherein,

[0053] The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to:

[0054] Through the image acquisition device and the infrared tube, the ground state image and infrared data within the preset range of the escort robot are respectively obtained; the ground state image is compared with a plurality of pre-stored ground state sample images to determine the first ground state of each area in the ground state image; the infrared data is filtered to obtain ground feedback data, and the difference is identified based on the ground feedback data to determine the second ground state of each area; it is determined whether the first ground state and the second ground state corresponding to any area are consistent, and if they are consistent, the ground state of any area is determined; if they are inconsistent, the current motor working state of the escort robot is obtained, and the contact friction coefficient between the escort robot travel device and the ground contact surface is determined through the motor working state; the ground state within the preset range is determined based on the contact friction coefficient, the first ground state and the second ground state; the moving path of the escort robot is determined based on the ground state.

[0055] The embodiment of the present application further provides a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured as follows:

[0056] Through the image acquisition device and the infrared tube, the ground state image and infrared data within the preset range of the escort robot are respectively obtained; the ground state image is compared with a plurality of pre-stored ground state sample images to determine the first ground state of each area in the ground state image; the infrared data is filtered to obtain ground feedback data, and the difference is identified based on the ground feedback data to determine the second ground state of each area; it is determined whether the first ground state and the second ground state corresponding to any area are consistent, and if they are consistent, the ground state of any area is determined; if they are inconsistent, the current motor working state of the escort robot is obtained, and the contact friction coefficient between the escort robot travel device and the ground contact surface is determined through the motor working state; the ground state within the preset range is determined based on the contact friction coefficient, the first ground state and the second ground state; the moving path of the escort robot is determined based on the ground state.

[0057] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0058] The devices and media provided in the embodiments of the present application correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0059] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0060] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0061] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0062] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0063] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0064] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0065] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0066] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0067] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A ground state detection method based on a companion robot, applied to a companion robot, characterized in that: include: Through the image acquisition device and the infrared tube, the ground state image and infrared data within the preset range of the accompanying robot are respectively obtained; Comparing the ground state image with a plurality of pre-stored ground state sample images to determine a first ground state of each area in the ground state image; Performing data filtering on the infrared data to obtain ground feedback data, and performing identification difference according to the ground feedback data to determine the second ground state of each area; Determine whether the first ground state and the second ground state respectively corresponding to any area are consistent, and if they are consistent, determine the ground state of any area; If they are inconsistent, obtaining the current motor working state of the accompanying robot, and determining the contact friction coefficient between the accompanying robot traveling device and the ground contact surface according to the motor working state; Determining a ground state within the preset range according to the contact friction coefficient, the first ground state, and the second ground state; Determining a moving path of the accompanying robot according to the ground state; After determining the ground state, the method further includes: Receive ground detection instructions and obtain current force information of the accompanying robot; Determining a current motion state of the accompanying robot according to the current force information and the working state of the motor; According to the ground state, adjusting the current motion state of the accompanying robot; The step of adjusting the current motion state of the accompanying robot according to the ground state specifically includes: According to the ground state, determining a ground state boundary in the moving path of the accompanying robot; Determining a critical moving speed threshold of the accompanying robot according to ground conditions on both sides of the ground condition boundary; According to the critical moving speed threshold, the working state of the motor of the accompanying robot is controlled so that the accompanying robot changes the driving speed in advance before reaching the boundary.

2. The method according to claim 1, characterized in that The step of comparing the ground state image with a plurality of pre-stored ground state sample images to determine the first ground state of each area in the ground state image specifically includes: Acquire ground state sample images of different types of ground as a sample set; Confirming a preset initial convolutional neural network model, and training the initial convolutional neural network using a back propagation algorithm based on the sample set to obtain a ground condition assessment model; The ground state image is input into the convolutional neural network model to determine the first ground state.

3. The method according to claim 1, characterized in that The method further comprises: Acquire the historical movement trajectory of the accompanying robot and generate the activity range of the accompanying robot; Storing the ground state within the activity range in a database; It is determined that the accompanying robot is within the activity range, and the ground state within the activity range is transmitted to the accompanying robot.

4. The method according to claim 1, characterized in that: Determining the planned path of the accompanying robot according to the ground state specifically includes: Determine a target location of the accompanying robot, and determine a plurality of intermediate locations according to the target location, the current location of the accompanying robot and the ground state; Selecting any two adjacent intermediate locations from the plurality of intermediate locations, and determining a plurality of initial planned paths between the arbitrary two adjacent intermediate locations according to the ground state; Determine a preset reward function, wherein the reward function at least includes a moving reward function and a turning reward function; Determining the travel path weights and the turning path weights respectively corresponding to the multiple initial planned paths according to the ground state and the reward function; The planned path of the accompanying robot is determined according to the traveling path weight and the turning path weight.

5. The method according to claim 1, characterized in that After determining the ground state, the method further includes: Generate a ground state image according to the ground state within a preset range of the accompanying robot; confirming that a special ground state exists in the ground state image; A ground state reminder is issued to the user according to the ground state image and the special ground state.

6. The ground state detection device based on the accompanying robot is characterized in that: The device comprises: A sensor module, used to obtain ground state images and infrared data within a preset range of the accompanying robot; A ground state determination module is used to compare the ground state image with a plurality of pre-stored ground state sample images to determine a first ground state of each area in the ground state image; to filter the infrared data to obtain ground feedback data, and to identify differences based on the ground feedback data to determine a second ground state of each area; and to determine whether the first ground state and the second ground state respectively corresponding to any area are consistent, and if they are consistent, to determine the ground state of any area; A friction coefficient determination module, used for obtaining the current motor working state of the accompanying robot, and determining the contact friction coefficient between the accompanying robot traveling device and the ground contact surface according to the motor working state; The ground state determination module is further used to determine the ground state within the preset range according to the contact friction coefficient, the first ground state and the second ground state; A moving path determination module, used to determine the moving path of the accompanying robot according to the ground state; After determining the ground state, receiving a ground detection instruction and obtaining current force information of the accompanying robot; Determining a current motion state of the accompanying robot according to the current force information and the working state of the motor; According to the ground state, adjusting the current motion state of the accompanying robot; The step of adjusting the current motion state of the accompanying robot according to the ground state specifically includes: According to the ground state, determining a ground state boundary in the moving path of the accompanying robot; Determining a critical moving speed threshold of the accompanying robot according to ground conditions on both sides of the ground condition boundary; According to the critical moving speed threshold, the working state of the motor of the accompanying robot is controlled so that the accompanying robot changes the driving speed in advance before reaching the boundary.

7. The ground state detection device based on the accompanying robot is characterized in that: include: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 5.

8. A non-volatile computer storage medium storing computer executable instructions, characterized in that: The computer executable instructions are configured to execute the method according to any one of claims 1 to 5.

Images