Assistive movement methods, apparatuses, devices, computer-readable media, and program products

Abstract

This disclosure presents embodiments of assisted movement methods, apparatuses, devices, computer-readable media, and program products. One specific embodiment of the method includes: responding to receiving a movement instruction corresponding to a target user, moving to a user position corresponding to the target user, wherein the target user is the object to be assisted in movement; responding to the target wheeled robot moving to the user position, adaptively adjusting the height of the device corresponding to the target wheeled robot to adapt to the user's height; and assisting the target user in movement in response to detecting pressure applied in a target direction by the target user to the target wheeled robot. This embodiment relates to intelligent robots, whereby the target wheeled robot can morphologically adapt to the target user's height and movement needs, effectively and intelligently assisting the target user in movement with high balance control.

Description

Technical Field

[0001] Embodiments of this disclosure relate to the field of computer technology, and more specifically to assistive motion methods, apparatuses, devices, computer-readable media, and program products. Background Technology

[0002] Currently, with the continuous development of robots (e.g., assistive robots), more and more robots are being applied in various scenarios (e.g., assistance scenarios). For assistive robots in these scenarios, the common approach is to use wheeled or wheel-legged robots to assist users in moving. However, using wheeled or wheel-legged robots for walking assistance results in a fixed structure, making them unable to respond to complex external forces or adaptively adjust their form to achieve balance control. Summary of the Invention

[0003] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0004] Some embodiments of this disclosure provide methods, devices, electronic devices, computer-readable media, and program products for assisting motion to address the technical problems mentioned in the background section above.

[0005] In a first aspect, some embodiments of this disclosure provide an assisted movement method applied to a target wheeled-legged robot, comprising: in response to obtaining a movement instruction corresponding to a target user, moving to a user position corresponding to the target user, wherein the target user is the object to be assisted in movement; in response to the target wheeled-legged robot moving to the user position, adaptively adjusting the height of the device corresponding to the target wheeled-legged robot to adapt to the user height corresponding to the target user; and in response to detecting that the target user applies pressure in a target direction to the target wheeled-legged robot, assisting the target user in movement.

[0006] Optionally, assisting the target user in exercising includes: acquiring motion requirement information for the target wheeled robot input by the target user; and assisting the target user in exercising according to the motion requirement information.

[0007] Optionally, the exercise requirement information includes: the exercise destination; and the above-mentioned assistance to the target user in exercising based on the exercise requirement information includes: generating an initial exercise path corresponding to the exercise destination; and assisting the target user in exercising based on the initial exercise path.

[0008] Optionally, the above-mentioned movement requirement information further includes: movement gait parameter information; and the above-mentioned assisting the target user to move according to the above-mentioned initial movement path includes: generating an auxiliary movement speed according to the above-mentioned movement gait parameter information; and assisting the target user to move according to the above-mentioned auxiliary movement speed and the above-mentioned initial movement path.

[0009] Optionally, the above method further includes: in response to supporting the target wheeled robot to perform motion coordination adjustment during movement, acquiring a sequence of motion gait parameters for a target historical time period, wherein the target historical time period is a predetermined time period prior to the current movement time; adjusting the auxiliary movement speed for the current movement time in real time according to the initial movement path and the sequence of motion gait parameters to obtain a movement adjustment speed; and assisting the target user to move according to the movement adjustment speed and the initial movement path.

[0010] Optionally, the above-mentioned adaptive adjustment of the height of the corresponding device of the target wheeled robot to match the height of the target user includes: acquiring the instruction voice information and / or facial information of the target user; acquiring the height of the target user based on the instruction voice information and / or facial information; and adaptively adjusting the height of the corresponding device of the target wheeled robot based on the user's height.

[0011] Optionally, obtaining the user height corresponding to the target user based on the indicated voice information and / or the facial information includes: determining the identity information corresponding to the target user based on the indicated voice information and / or the facial information; obtaining the initial user height corresponding to the target user based on the identity information; and calibrating the initial user height using a deployed point cloud calibration device to obtain the user height.

[0012] Optionally, the above method further includes: in response to receiving external force information during movement, generating external force change trend information based on the external force information; and adjusting the corresponding force-bearing joints of the target wheeled robot based on the external force change trend information to cope with external force impact.

[0013] Optionally, the target wheeled-legged robot includes: a leg joint device; and the generation of external force change trend information based on the external force information includes: generating external force change trend information using a pre-trained reinforcement learning model based on the external force information; and the adjustment of the corresponding force-bearing joints of the target wheeled-legged robot based on the external force change trend information to cope with external force impacts includes: generating compensation action information based on the external force change trend information; generating joint adaptive adjustment information based on the compensation action information; and adjusting the leg joint device based on the joint adaptive adjustment information to cope with external force impacts.

[0014] Secondly, some embodiments of this disclosure provide an auxiliary motion device applied to a target wheeled-legged robot, comprising: a first motion unit configured to move to a user position corresponding to the target user in response to receiving a motion instruction corresponding to the target user, wherein the target user is the object to be assisted in motion; an adjustment unit configured to adaptively adjust the height of the device corresponding to the target wheeled-legged robot in response to the target wheeled-legged robot moving to the user position, so as to adapt to the user height corresponding to the target user; and a second motion unit configured to assist the target user in motion in response to detecting pressure applied by the target user to the target wheeled-legged robot in a target direction.

[0015] Optionally, the second motion unit can be configured to: acquire motion requirement information for the target wheeled robot input by the target user; and assist the target user in performing motion based on the motion requirement information.

[0016] Optionally, the above-mentioned exercise requirement information includes: the exercise destination; and the second exercise unit can be configured to: generate an initial exercise path corresponding to the exercise destination; and assist the target user in exercising according to the initial exercise path.

[0017] Optionally, the above-mentioned motion requirement information may also include: gait parameter information; and the second motion unit may be configured to: generate an auxiliary motion speed based on the above-mentioned gait parameter information; and assist the target user in motion based on the above-mentioned auxiliary motion speed and the above-mentioned initial motion path.

[0018] Optionally, the device further includes: in response to supporting the target wheeled robot to perform motion coordination adjustment during movement, acquiring a sequence of motion gait parameters for a target historical time period, wherein the target historical time period is a predetermined time period prior to the current movement time; adjusting the auxiliary movement speed for the current movement time in real time based on the initial movement path and the sequence of motion gait parameters to obtain a movement adjustment speed; and assisting the target user to move based on the movement adjustment speed and the initial movement path.

[0019] Optionally, the adjustment unit can be configured to: acquire the instruction voice information and / or facial information corresponding to the target user; acquire the user height corresponding to the target user based on the instruction voice information and / or facial information; and adaptively adjust the height of the device corresponding to the target wheeled robot based on the user height.

[0020] Optionally, the adjustment unit can be configured to: determine the identity information corresponding to the target user based on the aforementioned voice information and / or the aforementioned facial information; obtain the initial user height corresponding to the target user based on the aforementioned identity information; and calibrate the initial user height using a deployed point cloud calibration device to obtain the user height.

[0021] Optionally, the device further includes: in response to receiving external force information during movement, generating external force change trend information based on the external force information; and adjusting the corresponding force-bearing joints of the target wheeled robot based on the external force change trend information to cope with external force impact.

[0022] Optionally, the aforementioned target wheeled robot includes: a leg joint device; and the device further includes: generating external force change trend information using a pre-trained reinforcement learning model based on the aforementioned external force information. The device also includes: generating compensation action information based on the aforementioned external force change trend information; generating joint adaptive adjustment information based on the aforementioned compensation action information; and adjusting the leg joint device based on the aforementioned joint adaptive adjustment information to cope with external force impacts.

[0023] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, such that when the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any implementation of the first aspect.

[0024] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method as described in any implementation of the first aspect.

[0025] Fifthly, some embodiments of this disclosure provide a computer program product, including a computer program that, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

[0026] The above-described embodiments of this disclosure have the following beneficial effects: Through the assisted movement methods of some embodiments of this disclosure, the target wheeled-legged robot can adaptively adjust its form according to the height and movement needs of the target user, effectively and intelligently assisting the target user in movement under high balance control. Specifically, the reason why the robot cannot adaptively adjust its form, resulting in robot imbalance, is that robots using wheeled or wheel-legged forms for assisted walking have fixed forms and structures, cannot respond to complex external force interference, and cannot adaptively adjust their form to achieve balance control capabilities. Based on this, the assisted movement method of some embodiments of this disclosure firstly, in response to obtaining the movement instruction corresponding to the target user, moves to the user position corresponding to the target user, wherein the target user is the object to be assisted in movement. Here, after obtaining the movement instruction corresponding to the target user, it can intelligently and accurately move to the user position corresponding to the target user to facilitate the target user's movement. Here, by setting the target wheeled-legged structure of the robot, it can combine the high speed and efficiency of wheeled robots with the complex terrain adaptability of legged robots. Wheel-legged robots are used in the field of assistance. When subjected to external forces, the leg structure of the wheel-legged robot can flexibly adjust its posture, changing the support angle and height of the legs to counteract the shift in the center of gravity caused by the external forces, thus preventing the robot from becoming unbalanced. Then, in response to the target wheel-legged robot moving to the user's position, the height of the corresponding device of the target wheel-legged robot is adaptively adjusted to match the user's height. Here, the shape can be adaptively adjusted according to the user's height to facilitate the user's use and improve balance control during movement. Finally, in response to detecting the pressure applied by the user to the target wheel-legged robot in a target direction, the robot assists the user in movement. Here, after sensing the pressure applied by the user in the target direction, the target wheel-legged robot can automatically start assisting the user in movement, greatly improving the convenience of movement. In summary, the target wheel-legged robot can adaptively adjust its shape according to the user's height and movement needs, and combined with its wheel-legged structure, it can ensure a high degree of balance control during user assistance. Based on this, it can effectively and intelligently assist target users in exercising. Attached Figure Description

[0027] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0028] Figure 1 This is a schematic diagram illustrating an application scenario of an assisted motion method according to some embodiments of the present disclosure; Figure 2 This is a flowchart of some embodiments of the assisted movement method according to the present disclosure; Figure 3 This is a schematic diagram illustrating the form of a wheel-legged robot in some embodiments of the assisted motion method according to the present disclosure; Figure 4 These are flowcharts of other embodiments of the assisted movement method according to this disclosure; Figure 5 This is a schematic diagram of a target wheel-legged robot according to some embodiments of the assisted motion method of this disclosure; Figure 6 These are schematic diagrams illustrating the structure of some embodiments of the assistive motion device according to this disclosure; Figure 7 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed Implementation

[0029] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0030] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0031] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0032] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0033] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0034] Before performing any of the operations involving the collection, storage, or use of user personal information (such as exercise instructions) disclosed in this disclosure, the relevant organizations or individuals shall fulfill their obligations, including conducting personal information security impact assessments, informing personal information subjects, and obtaining prior authorization and consent from personal information subjects.

[0035] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0036] Figure 1 This is a schematic diagram of an application scenario of an assisted motion method according to some embodiments of the present disclosure.

[0037] exist Figure 1 In this application scenario, firstly, in response to receiving the motion instruction 102 corresponding to the target user 101, the target wheeled robot can move to the user position corresponding to the target user 101. Here, the target user 101 is the object to be assisted in movement. In this application scenario, the motion instruction 102 could be "Please come to me and help me move." Then, in response to the target wheeled robot moving to the user position, the height of the corresponding device of the target wheeled robot is adaptively adjusted to match the user height 103 corresponding to the target user 101. In this application scenario, the user height 103 could be "178CM." Finally, in response to detecting that the target user applies pressure in the target direction to the target wheeled robot, the target wheeled robot can assist the target user in movement.

[0038] It should be understood that Figure 1 The number of target wheeled-legged robots 101 shown is merely illustrative. Any number of target wheeled-legged robots can be used depending on implementation requirements.

[0039] Continue to refer to Figure 2 The diagram illustrates a flow 200 of some embodiments of an assisted motion method according to the present disclosure. This assisted motion method includes the following steps: Step 201: In response to obtaining the motion instruction corresponding to the target user, move to the user location corresponding to the target user.

[0040] In some embodiments, in response to obtaining a motion instruction corresponding to the target user, the execution subject of the above-mentioned motion assistance method (e.g., Figure 1The target wheeled robot 101 shown can move to the user's location corresponding to the target user. The target user is the object to be assisted in movement. That is, in a support scenario, the target user can be the user who needs assistance. For example, the target user can be an elderly person who needs assistance. The movement instruction can be an instruction to the target wheeled robot to provide support and move. In practice, the movement instruction can be in text or audio format. For example, the movement instruction could be "The robot comes to my side and helps me to the bedroom." In practice, the user's location can be the user's real-time location. That is, the user's current location. For example, the user's location can be the coordinates determined based on a three-dimensional spatial coordinate system constructed with the target wheeled robot as the origin.

[0041] In practice, the target wheeled robot can move to the user's location by using its wheeled legs.

[0042] It should be further clarified that the target wheeled-legged robot can be a robot used to assist people with mobility impairments. A wheeled-legged robot can be a robot that combines the characteristics of both wheeled and legged robots. That is, a wheeled-legged robot is a hybrid robot that integrates wheeled and legged locomotion mechanisms, possessing both the high speed and efficiency of wheeled robots and the adaptability to complex terrain of legged robots. In the field of assistance, when subjected to external forces, the leg structure of the wheeled-legged robot can flexibly adjust its posture, changing the support angle and height of the legs to counteract the shift in the center of gravity caused by the external forces. The target wheeled-legged robot may include a sound source localization device. The sound source localization device can be a device for locating the target sound source. Here, the target sound source can be the sound source that controls the movement of the target wheeled-legged robot. In practice, for assistance scenarios, the target sound source can be the user requiring assistance who instructs the target wheeled-legged robot to move. For example, for intelligent delivery scenarios, the target sound source can be the object instructing the target wheeled-legged robot to move. For example, the sound source localization device can be a "microphone array". In scenarios requiring assistance, the user needing assistance can communicate with the assistance robot (i.e., the target wheeled robot) by uttering a voice command saying "Please move to my location." The assistance robot will then use this voice to locate the sound source and quickly move to the user's location. The sound source localization device can be positioned on the head of the target wheeled robot to facilitate sound source localization.

[0043] It should be noted that the target wheeled robot may include a wheeled mobility device. The wheeled mobility device can be a wheeled device used to support the movement of the target wheeled robot. For example, the wheeled mobility device may consist of multiple moving wheels. For example, the number of moving wheels may be four or two. The wheeled mobility device may be located at the bottom of the target wheeled robot to facilitate movement.

[0044] As an example, firstly, the aforementioned executing entity can determine the user's location using a deployed sound source localization device. Then, based on the user's location, it instructs the target wheeled robot to move to the user's location.

[0045] Optionally, in response to determining that the user has moved to the surrounding area (e.g., within 1 meter of the user's location), the PNP algorithm is used to calculate the precise relative position in order to achieve accurate determination of the relative position.

[0046] Step 202: In response to the target wheeled robot moving to the user's position, the height of the corresponding device of the target wheeled robot is adaptively adjusted to match the user's height.

[0047] In some embodiments, in response to the target wheeled robot moving to the user's position, the execution entity can adaptively adjust the height of the device corresponding to the target wheeled robot to match the user's height. The device height can be the height difference between the corresponding support component of the target wheeled robot and the ground. The support component can be the component that the target user contacts when providing support. The user's height can be the height of the target user.

[0048] As an example, first, multiply the user's height by a target ratio (e.g., 0.65) to obtain the multiplied value, which becomes the device height. This target ratio can be set based on historical experience. The target ratio represents a proportion that facilitates user movement using the target wheeled robot. A device height set at the target ratio facilitates user handling. For example, in a support scenario, a device height set at the target ratio makes it easier for the user to walk with assistance. Finally, adjust the opening and closing angles of the hip and knee motors to match the target wheeled robot's height to the device height.

[0049] In some optional implementations of certain embodiments, the execution entity may adaptively adjust the height of the device corresponding to the target wheeled robot to suit the height of the target user, including the following steps: The first step is to acquire the instruction sound information and / or facial information corresponding to the target user. The instruction sound information can be the sound of the target user instructing the user to move. Specifically, the instruction sound information can be the audio corresponding to the movement instruction. The facial information can be information related to the user's face. For example, facial information can include: a facial image and a facial description.

[0050] In practical applications, the target wheeled robot may also include a vision device. The vision device can be a device for acquiring visual images of the surrounding environment. For example, the vision device can be an "RGB-D vision module." Here, the vision device can also be a vision device used to acquire object features corresponding to a sound source object. For example, the object features can be facial features. The vision device can be located in the head of the target wheeled robot to facilitate visual content acquisition.

[0051] As an example, the aforementioned entity can utilize a visual device to acquire facial information.

[0052] The second step is to obtain the height of the target user based on the aforementioned voice information and / or facial information.

[0053] As an example, firstly, the aforementioned executing entity can retrieve the user identity with the highest semantic similarity to the indicated voice information and / or the highest semantic similarity to the facial information from the user identity database, and use this as the target user identity. Then, the user height recorded corresponding to the target user identity is determined as the user height.

[0054] The third step is to adaptively adjust the height of the corresponding device of the target wheeled robot according to the user's height.

[0055] Specifically, such as Figure 3 The diagram shows a schematic representation of the wheeled-legged robot.

[0056] During the process of adjusting the device height according to the user's height, it can be done by folding. Figure 3 The knee joint is adjusted to further adjust the height of the hip joint from the ground, thereby adjusting the overall height of the robot. After adjusting to the appropriate height, multiple wheels can be driven to move at that height to assist the user in walking.

[0057] Addressing the issue of bipedal robots having a fixed walking height and being unable to adjust it freely during movement, wheel-legged robots, based on a wheeled chassis and foldable / extendable leg structures, can achieve efficient planar movement via the wheels and can extend their legs to overcome obstacles when needed. This design allows them to switch between different heights, adapt to complex terrain, and effectively assist users in moving with high comfort.

[0058] In some optional implementations of certain embodiments, the execution entity may obtain the user height corresponding to the target user based on the indicated voice information and / or the facial information, including the following steps: The first step is to determine the identity information of the target user based on the aforementioned voice and / or facial information. For example, the identity information could be the user ID of the target user.

[0059] As an example, the aforementioned executing entity can determine the identity information of the target user based on voice information and / or facial information, using voice semantic matching and / or facial semantic matching.

[0060] The second step is to obtain the initial user height corresponding to the target user based on the aforementioned identity information. This initial user height can be a preliminarily determined height recorded in the database corresponding to the target user. Alternatively, it can be a height to be corrected.

[0061] As an example, firstly, the aforementioned executing entity can retrieve user identity data corresponding to the identity information from the user identity database. Then, it extracts the initial user height corresponding to the target user from the aforementioned user identity data. User identity data may include: user identity, user voice, facial information, and initial user height.

[0062] The third step involves using a deployed point cloud calibration device to calibrate the initial user height, thus obtaining the user's actual height. This point cloud calibration device can be a device that calibrates the height by determining the point cloud set corresponding to the target user's surrounding environment.

[0063] As an example, firstly, the aforementioned execution entity can utilize a point cloud calibration device to construct a 3D point cloud set for the target user. Then, based on the 3D point cloud set, the initial user height is updated to obtain the user's height.

[0064] Step 203: In response to detecting that the target user applies pressure in the target direction to the target wheeled robot, assist the target user in moving.

[0065] In some embodiments, in response to detecting pressure applied by the target user in a target direction to the target wheeled robot, the aforementioned execution entity can assist the target user in movement. The target direction can be the direction in which the target user applies downward pressure to the target wheeled robot. In a specific scenario, the target user can grasp the target wheeled robot and apply downward pressure. Upon detecting pressure applied in the target direction to the target wheeled robot, the target wheeled robot can sense that the target user needs assisted movement, and thus initiates an assisted movement operation for the target user.

[0066] In some optional implementations of certain embodiments, the executing entity may assist the target user in performing movement, including the following steps: The first step is to obtain the motion requirement information for the target wheeled robot input by the target user. This motion requirement information can be the target user's requirements for the motion state of the target wheeled robot to perform assisted movements. For example, the motion requirement information could be "the path must pass through all necessary points."

[0067] The second step is to assist the target user in exercising based on the exercise requirements information.

[0068] As an example, firstly, given the exercise requirement that "the path must pass through all necessary points," a movement path can be generated that passes through all necessary points. Then, based on the movement path, the target user can be assisted in exercising.

[0069] In some optional implementations of certain embodiments, the aforementioned exercise requirement information includes: the exercise destination. The exercise destination can be the endpoint of the exercise performed by the target user. For example, the exercise destination could be a "bedroom".

[0070] Optionally, the aforementioned execution entity may assist the aforementioned target user in exercising based on the aforementioned exercise requirements information, including the following steps: The first step is to generate the initial movement path corresponding to the aforementioned movement destination. This initial movement path can be a preliminarily generated path from the user's location to the movement destination. In other words, the initial movement path can be a preliminarily generated route from the user's location to the movement destination.

[0071] For example, consider a home scenario for the target wheeled robot. The robot is currently in the living room, and the user-input destination is the location corresponding to Bathroom 1. The initial travel path can be a path starting from the current location of the target wheeled robot and ending at the destination. That is, it can characterize the robot's movement path. The initial travel path can be a preliminarily determined path. For example, the initial travel path could be path 1, moving from the living room to the location corresponding to Bathroom 1.

[0072] As an example, the aforementioned execution entity can generate a motion path from the user's location to the motion destination based on the deployed navigation system, as the initial motion path.

[0073] The second step is to assist the target user in exercising based on the initial movement path described above.

[0074] As an example, the aforementioned execution entity can use the initial motion path as the motion route to assist the target user in exercising.

[0075] In some optional implementations of certain embodiments, the aforementioned movement requirement information further includes: gait parameter information. This gait parameter information characterizes the gait of the target user during movement. In practice, gait parameter information may include: movement speed, movement mode, stride length, and cadence. Movement speed can be the speed at which the target user requires assisted movement. Movement mode can be the movement pattern at which the target user requires assisted movement. For example, movement mode may include: slow walking mode and normal walking mode. It should be noted that the gait parameter information here can be set by the target user based on their own movement state. When the target user has not set gait parameter information, i.e., when the corresponding gait parameter information is empty, the gait parameter information can be determined based on the target user's historical movement data. Historical movement data can be the target user's movement status at a historical time.

[0076] Optionally, the aforementioned execution entity may assist the aforementioned target user in exercising based on the aforementioned initial motion path, including the following steps: The first step is to generate an auxiliary motion speed based on the aforementioned gait parameters. This auxiliary motion speed can be the speed at which the target wheeled robot assists the target user in movement. In other words, the auxiliary motion speed characterizes the speed at which the target wheeled robot assists the target user in movement.

[0077] As an example, the robot's movement speed is matched based on the movement speed, movement mode, stride length, and cadence in the gait parameters, serving as an auxiliary movement speed.

[0078] The second step is to assist the target user in exercising based on the aforementioned auxiliary movement speed and initial movement path.

[0079] As an example, the aforementioned execution entity can move at an assisted movement speed and use the movement path as a movement route to assist the target user in exercising.

[0080] Optionally, after "Step Two", the steps may also include: The first step involves, in response to the target wheeled-legged robot's need for motion coordination adjustment during movement, acquiring a sequence of motion gait parameters within a target historical time period. This target historical time period is a predetermined time period preceding the current movement time. The current movement time can be the time the target wheeled-legged robot assists the target user in movement. The sequence of motion gait parameters represents the gait patterns observed during the target movement time period. Each motion gait parameter corresponds to a specific historical movement time within the target movement time period. Motion coordination adjustment allows for real-time adjustment of the motion gait parameters during the process of assisting the target user in movement. Specifically, the adjustment functions for motion coordination adjustment can be configured by the user according to their needs.

[0081] The second step involves adjusting the assisted movement speed in real time based on the initial movement path and the sequence of gait parameters, thus obtaining the adjusted movement speed. This adjusted movement speed characterizes the movement speed at which the target user is assisted in movement over a future time period.

[0082] As an example, the aforementioned execution entity can utilize a reinforcement learning model to generate a motion adjustment speed to assist the target user in moving in the future time period, based on the motion path state of the initial motion path in the future time period and the sequence of motion gait parameter information information of the target user in the target historical time period.

[0083] The third step involves adjusting the speed and initial movement path based on the aforementioned movements to assist the target user in their exercise. Further details will not be elaborated upon.

[0084] The above-described embodiments of this disclosure have the following beneficial effects: Through the assisted movement methods of some embodiments of this disclosure, the target wheeled-legged robot can adaptively adjust its form according to the height and movement needs of the target user, effectively and intelligently assisting the target user in movement under high balance control. Specifically, the reason why the robot cannot adaptively adjust its form, resulting in robot imbalance, is that robots using wheeled or wheel-legged forms for assisted walking have fixed forms and structures, cannot respond to complex external force interference, and cannot adaptively adjust their form to achieve balance control capabilities. Based on this, the assisted movement method of some embodiments of this disclosure firstly, in response to obtaining the movement instruction corresponding to the target user, moves to the user position corresponding to the target user, wherein the target user is the object to be assisted in movement. Here, after obtaining the movement instruction corresponding to the target user, it can intelligently and accurately move to the user position corresponding to the target user to facilitate the target user's movement. Here, by setting the target wheeled-legged structure of the robot, it can combine the high speed and efficiency of wheeled robots with the complex terrain adaptability of legged robots. Wheel-legged robots are used in the field of assistance. When subjected to external forces, the leg structure of the wheel-legged robot can flexibly adjust its posture, changing the support angle and height of the legs to counteract the shift in the center of gravity caused by the external forces, thus preventing the robot from becoming unbalanced. Then, in response to the target wheel-legged robot moving to the user's position, the height of the corresponding device of the target wheel-legged robot is adaptively adjusted to match the user's height. Here, the shape can be adaptively adjusted according to the user's height to facilitate the user's use and improve balance control during movement. Finally, in response to detecting the pressure applied by the user to the target wheel-legged robot in a target direction, the robot assists the user in movement. Here, after sensing the pressure applied by the user in the target direction, the target wheel-legged robot can automatically start assisting the user in movement, greatly improving the convenience of movement. In summary, the target wheel-legged robot can adaptively adjust its shape according to the user's height and movement needs, and combined with its wheel-legged structure, it can ensure a high degree of balance control during user assistance. Based on this, it can effectively and intelligently assist target users in exercising.

[0085] Further reference Figure 4 The diagram illustrates a flow 400 of another embodiment of the motion-assisted method according to the present disclosure. This motion-assisted method includes the following steps: Step 401: In response to obtaining the motion instruction corresponding to the target user, move to the user location corresponding to the target user.

[0086] Step 402: In response to the target wheeled robot moving to the user's position, the height of the device corresponding to the target wheeled robot is adaptively adjusted to match the user's height.

[0087] Step 403: In response to detecting that the target user applies pressure in the target direction to the target wheeled robot, assist the target user in moving.

[0088] Step 404: In response to receiving external force information during the motion, generate external force change trend information based on the external force information.

[0089] In some embodiments, in response to receiving external force information during motion, the executing entity (e.g. Figure 1 The target wheeled robot shown can generate external force change trend information based on the aforementioned external force information. The external force information can be the external force received by the target wheeled robot. In practice, external force information can include: the direction and magnitude of the external force. For example, the direction of the external force can be the side of the target wheeled robot. That is, a sudden force is applied to the target wheeled robot from its side. The magnitude of the external force can be the magnitude of the received force. For example, the magnitude of the external force can be 30N. The external force change trend information can be the change in external force that may be received within a certain time period after the current time. The duration of this certain time period can be preset. In scenarios where external forces are suddenly applied, such as in support or transport scenarios, the sudden application of the external force leads to a large change in the external force; therefore, the duration of this certain time period is relatively short. For example, the duration of this certain time period can be 3 seconds. The external force change trend information can characterize the changes in the direction and magnitude of the external force within a certain time period. For example, information on the trend of external force changes could be "An estimated external force of approximately 30N-100N is expected to be applied from left to right within 3 seconds."

[0090] Specifically, the aforementioned wheeled robot also includes a force sensor. This force sensor can be a sensor that senses force information. In practice, the force sensor is a six-dimensional force sensor. A six-dimensional force sensor is a precision sensor capable of simultaneously measuring three forces (Fx, Fy, Fz) and three torques (Mx, My, Mz) acting on an object in three-dimensional space.

[0091] In practice, the force sensing sensor can be located at the top of the target wheeled robot.

[0092] As an example, the aforementioned execution entity can utilize the force sensing sensors in the target wheeled robot to obtain in real time the direction and magnitude of the external forces received by the target wheeled robot during its movement.

[0093] As an example, the aforementioned execution entity can utilize the vision device configured on the target wheeled robot to acquire in real time the motion speed and object category of the object applying the aforementioned external force information. Then, based on the motion speed, object category, and the sequence of external force information within the historical time period corresponding to the current time, it determines the applied external force change information corresponding to the aforementioned object by querying an external force change mapping table, which serves as the external force change trend information. The external force change mapping table can represent the external force change formula or external force change rule for applying external force under a corresponding object category. In practice, each external force change formula or rule in the external force change mapping table is generated based on historical experience.

[0094] In some alternative implementations of certain embodiments, the aforementioned target wheeled robot further includes a leg joint device. The leg joint device can be a joint device capable of flexible posture adjustment, which can counteract the shift in the center of gravity caused by external forces by changing the support angle and height of the legs.

[0095] Optionally, the above-mentioned generation of external force change trend information based on the external force information includes: The aforementioned execution entity can generate information on the changing trends of external forces using a pre-trained reinforcement learning model based on the external force information. This reinforcement learning model can be a deep learning model specifically designed to predict these trends. Here, reinforcement learning is used to "predict" or, more accurately, "adapt and control" the dynamic changes of the target wheeled robot during force application. The core idea is to enable the target wheeled robot to learn how to make optimal decisions based on the current force state through continuous interaction with the environment to achieve task objectives (e.g., maintaining stability, completing assembly, etc.). For example, the reinforcement learning model can employ an Actor-Critic framework or its variants (e.g., DDPG, TD3, SAC), combining policy learning and value function learning, demonstrating excellent performance in continuous control tasks. In practice, the training of reinforcement learning models typically begins in a simulation environment to ensure safety and efficiency, with subsequent migration from simulation to reality or online fine-tuning possible. The reward functions corresponding to the reinforcement learning model can include: force constraint reward functions, stability reward functions, and efficiency reward functions. Force constraint reward functions can be functions that encourage contact forces to remain within safe limits. A stability reward function can be one that penalizes drastic force fluctuations or robot jitter. An efficiency reward function can be one that encourages completing a task in fewer steps.

[0096] As an example, the aforementioned executing entity can directly input external force information into the reinforcement learning model to obtain information on the changing trends of external forces.

[0097] Step 405: Based on the above information on the trend of external force changes, adjust the corresponding force-bearing joints of the target wheeled robot to cope with the impact of external forces.

[0098] In some embodiments, the aforementioned execution entity can adjust the corresponding force-bearing joints of the target wheeled robot based on the aforementioned external force change trend information to cope with external force impacts. The force-bearing joints of the robot can be key mechanical connection parts in the robot structure specifically designed to bear and transmit external loads (e.g., gravity, impact force, operational reaction force) and internal driving forces (e.g., motor torque). For example, the force-bearing joints can be the leg joints of the target wheeled robot.

[0099] As an example, firstly, based on the aforementioned external force change trend information, corresponding external force response change information is generated. This external force response change information can be force response information for responding to external forces and the external force impact corresponding to the external force change trend. Here, forces can be applied to the force-bearing joints corresponding to the target wheeled robot to achieve force response. Then, force application commands corresponding to the external force response change information are generated. Finally, based on the aforementioned force application commands, the force-bearing joints are instructed to perform force processing to respond to the external force impact.

[0100] Optionally, the aforementioned execution entity can adjust the corresponding force-bearing joints of the target wheeled robot based on the aforementioned external force change trend information to cope with external force impacts, including the following steps: The first step is to generate compensation action information based on the aforementioned external force change trend information. This compensation action information can be the action content of the target wheeled robot to compensate for the impact of the external force. For example, the compensation action information could be "applying a force of 30N-40N-50N gradually from right to left".

[0101] As an example, the aforementioned executing entity can input information on the changing trend of external forces into a reinforcement learning model to obtain information on compensating actions.

[0102] The second step is to generate joint adaptive adjustment information based on the aforementioned compensation action information. This information can be the adjustments performed by the stressed joint. For example, the adjustments could be the angular changes corresponding to the support angle of the stressed joint. In practice, joint adaptive adjustment information may include: angle, angular velocity, and applied torque.

[0103] As an example, the aforementioned executing entity can query the joint adjustment content corresponding to the compensating action information from the action mapping table, which serves as joint adaptive adjustment information. The action mapping table can represent the mapping relationship between the joint adjustment content and the corresponding action content of the compensating action.

[0104] The third step involves adjusting the leg joint device based on the aforementioned joint adaptability adjustment information to cope with external impacts. The leg joint device in the target wheeled robot is the movable connection between the various components of the robot's legs, and it is the core structure that enables the robot to perform complex movements such as walking, running, and jumping.

[0105] As an example, the aforementioned execution entity can execute joint execution commands corresponding to the joint adaptive adjustment information for the leg joint device in order to cope with external impacts.

[0106] like Figure 5 As shown, the robot architecture of the target wheeled-legged robot is illustrated.

[0107] like Figure 5 As shown, the head of the target wheeled robot is equipped with a six-dimensional force sensor (i.e., a force sensing sensor) and a microphone array (i.e., a sound source localization device). Below the microphone array is an RGBD module (i.e., a vision device). Joint motors serve as leg joint devices, and movement is achieved through moving wheels (i.e., wheeled mobility devices).

[0108] from Figure 4 It can be seen from this that, with Figure 2 Compared to the description of some corresponding embodiments, Figure 4 In some corresponding embodiments, the process 400 of the assisted motion method can summarize the external force information during the motion process to accurately predict the external force change trend information, so as to make timely adjustments to the force-bearing joints based on the external force change trend information, so as to cope with the external force impact and ensure the stability of the motion process.

[0109] Further reference Figure 6 As an implementation of the methods shown in the above figures, this disclosure provides some embodiments of an auxiliary motion device, which are similar to... Figure 2 Corresponding to the method embodiments shown, this assistive motion device can be specifically applied to various electronic devices.

[0110] like Figure 6As shown, an auxiliary motion device 600 includes: a first motion unit 601, an adjustment unit 602, and a second motion unit 603. The first motion unit 601 is configured to move to the user position corresponding to the target user in response to receiving a motion instruction from the target user, wherein the target user is the object to be assisted in motion. The adjustment unit 602 is configured to adaptively adjust the height of the target wheeled robot corresponding to the user position in response to the target wheeled robot moving to match the user's height. The second motion unit 603 is configured to assist the target user in motion in response to detecting pressure applied in a target direction by the target user to the target wheeled robot.

[0111] In some optional implementations of certain embodiments, the second motion unit 603 may be further configured to: acquire motion requirement information for the target wheeled robot input by the target user; and assist the target user in performing motion based on the motion requirement information.

[0112] In some optional implementations of some embodiments, the above-mentioned motion requirement information includes: a motion destination; and the second motion unit 603 may be further configured to: generate an initial motion path corresponding to the above-mentioned motion destination; and assist the target user in exercising according to the above-mentioned initial motion path.

[0113] In some optional implementations of some embodiments, the motion requirement information further includes: gait parameter information; and the second motion unit 603 may be further configured to: generate an auxiliary motion speed based on the above gait parameter information; and assist the target user in motion based on the above auxiliary motion speed and the above initial motion path.

[0114] In some optional implementations of certain embodiments, the second motion unit 603 may be further configured to: in response to supporting the target wheeled robot in motion coordination adjustment during motion, acquire a sequence of motion gait parameters for a target historical time period, wherein the target historical time period is a predetermined time period prior to the current motion time; adjust the auxiliary motion speed for the current motion time in real time based on the initial motion path and the sequence of motion gait parameters to obtain a motion adjustment speed; and assist the target user in motion based on the motion adjustment speed and the initial motion path.

[0115] In some optional implementations of some embodiments, the adjustment unit 602 may be further configured to: acquire the instruction voice information and facial information corresponding to the target user; acquire the user height corresponding to the target user based on the instruction voice information and facial information; and adaptively adjust the height of the device corresponding to the target wheeled robot based on the user height.

[0116] In some optional implementations of some embodiments, the adjustment unit 602 may be further configured to: determine the identity information corresponding to the target user based on the above-mentioned instruction voice information and / or the above-mentioned facial information; obtain the initial user height corresponding to the target user based on the above-mentioned identity information; and calibrate the initial user height using the deployed point cloud calibration device to obtain the user height.

[0117] In some optional implementations of certain embodiments, the device 600 further includes a generation unit and a joint adjustment unit (not shown in the figure). The generation unit can be configured to generate external force change trend information based on external force information received during movement. The joint adjustment unit can be configured to adjust the corresponding force-bearing joints of the target wheeled robot according to the external force change trend information to cope with external force impacts.

[0118] In some alternative implementations of certain embodiments, the target wheeled robot includes: a leg joint device; and a generation unit configured to: generate external force change trend information using a pre-trained reinforcement learning model based on the external force information. A joint adjustment unit configured to: generate compensation action information based on the external force change trend information; generate joint adaptive adjustment information based on the compensation action information; and adjust the leg joint device based on the joint adaptive adjustment information to cope with external force impacts.

[0119] It is understandable that the units described in the assistive motion device 600 are similar to those in the reference device. Figure 2 The steps in the described method correspond to each other. Therefore, the operations, features, and beneficial effects described above for the method also apply to the assistive motion device 600 and the units contained therein, and will not be repeated here.

[0120] The following is for reference. Figure 7 It shows a schematic diagram of the structure of an electronic device 700 suitable for implementing some embodiments of the present disclosure. Figure 7 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0121] like Figure 7As shown, the electronic device 700 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory 702 or a program loaded from a storage device 708 into a random access memory 703. The random access memory 703 also stores various programs and data required for the operation of the electronic device 700. The processing unit 701, the read-only memory 702, and the random access memory 703 are interconnected via a bus 704. An input / output interface 705 is also connected to the bus 704.

[0122] Typically, the following devices can be connected to the input / output interface 705: input devices 706 including, for example, a touchscreen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 707 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 708 including, for example, magnetic tape, hard disk, etc.; and communication devices 709. Communication device 709 allows electronic device 700 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 7 An electronic device 700 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 7 Each box shown can represent a device or multiple devices as needed.

[0123] In particular, according to some embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 709, or installed from a storage device 708, or installed from a read-only memory 702. When the computer program is executed by the processing device 701, it performs the functions defined in the methods of some embodiments of this disclosure.

[0124] It should be noted that, in some embodiments of this disclosure, the computer-readable medium described above may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In some embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0125] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0126] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: move to the user position corresponding to the target user in response to receiving a motion instruction corresponding to the target user, wherein the target user is the object to be assisted in motion; adaptively adjust the height of the corresponding device of the target wheeled robot to match the user's height in response to the target wheeled robot moving to the user position; and assist the target user in motion in response to detecting pressure applied in a target direction by the target user to the target wheeled robot.

[0127] Computer program code for performing operations of some embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0128] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0129] The units described in some embodiments of this disclosure can be implemented in software or in hardware. The described units can also be housed in a processor; for example, a processor may be described as including a first motion unit, an adjustment unit, and a second motion unit. The names of these units do not necessarily limit the specific unit; for example, the first motion unit may also be described as "a unit that moves to the user position corresponding to the target user in response to receiving a motion instruction from the target user."

[0130] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0131] Some embodiments of this disclosure also provide a computer program product, including a computer program that, when executed by a processor, implements any of the above-described auxiliary motion methods.

[0132] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. An assisted motion method applied to a target wheeled-legged robot, comprising: In response to receiving a motion instruction corresponding to a target user, the device moves to the user position corresponding to the target user, wherein the target user is the object to be assisted in motion. In response to the target wheeled robot moving to the user's position, the height of the corresponding device of the target wheeled robot is adaptively adjusted to match the user's height. In response to detecting that the target user applies pressure in the target direction to the target wheeled robot, the robot assists the target user in moving.

2. The method according to claim 1, wherein, The method of assisting the target user in exercising includes: Obtain the motion requirement information for the target wheeled robot input by the target user; Based on the exercise requirements information, assist the target user in exercising.

3. The method according to claim 2, wherein, The exercise requirements information includes: the exercise destination; and The step of assisting the target user in exercising based on the exercise requirement information includes: Generate the initial motion path corresponding to the stated motion destination; Based on the initial movement path, assist the target user in exercising.

4. The method according to claim 3, wherein, The exercise requirement information also includes: gait parameter information; and The step of assisting the target user in exercising based on the initial movement path includes: Based on the aforementioned gait parameter information, an auxiliary movement speed is generated; The target user is assisted in exercising based on the assisted movement speed and the initial movement path.

5. The method according to claim 4, wherein, The method further includes: In response to the motion coordination adjustment of the target wheeled robot during the motion process, the sequence of motion gait parameter information under the target historical time period is obtained, wherein the target historical time period is a predetermined time period before the current motion time; Based on the initial movement path and the sequence of movement gait parameters, the auxiliary movement speed at the current movement time is adjusted in real time to obtain the movement adjustment speed. The target user is assisted in exercising by adjusting the speed based on the movement and the initial movement path.

6. The method according to claim 1, wherein, The adaptive adjustment of the height of the corresponding device of the target wheeled robot to suit the height of the target user includes: Obtain the instruction voice information and / or facial information corresponding to the target user; Based on the indicated voice information and / or the facial information, obtain the user height corresponding to the target user; The height of the corresponding device of the target wheeled robot is adaptively adjusted according to the user's height.

7. The method according to claim 6, wherein, The step of obtaining the user height corresponding to the target user based on the indicated voice information and / or the facial information includes: Based on the indicated voice information and / or the facial information, determine the identity information corresponding to the target user; Based on the identity information, obtain the initial user height corresponding to the target user; The initial user height is calibrated using a deployed point cloud calibration device to obtain the user's height.

8. The method according to claim 1, wherein, The method further includes: In response to receiving external force information during motion, external force change trend information is generated based on the external force information; Based on the information on the changing trend of external forces, the target wheeled robot is adjusted according to the corresponding force-bearing joints to cope with the impact of external forces.

9. The method according to claim 8, wherein, The target wheeled-legged robot includes: a leg joint device; and The step of generating external force change trend information based on the external force information includes: Based on the external force information, a pre-trained reinforcement learning model is used to generate information on the trend of external force changes; and The step of adjusting the corresponding force-bearing joints of the target wheeled robot according to the external force change trend information to cope with external force impact includes: Based on the external force change trend information, compensation action information is generated; Based on the compensation action information, joint adaptive adjustment information is generated; Based on the joint adaptive adjustment information, the leg joint device is adjusted to cope with external impacts.

10. An auxiliary motion device applied to a target wheeled-legged robot, comprising: The first motion unit is configured to move to the user position corresponding to the target user in response to receiving a motion instruction corresponding to the target user, wherein the target user is the object to be assisted in motion. The adjustment unit is configured to adaptively adjust the height of the corresponding device of the target wheeled robot in response to the target wheeled robot moving to the user position, so as to adapt to the user height corresponding to the target user. The second motion unit is configured to assist the target user in moving in response to detecting pressure applied in a target direction by the target user to the target wheeled robot.

11. An electronic device, comprising: One or more processors; Storage device, on which one or more programs are stored, When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-9.

12. A computer-readable medium having a computer program stored thereon, wherein, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-9.

13. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-9.

Images