Action Processing Method, Device, Electronic Device, Storage Medium and Program Product

Abstract

The present application provides a method, an apparatus, an electronic device, a computer-readable storage medium, and a computer program product for handling the actions of a robot; the method includes: autonomously and sequentially performing each action in a first action sequence on a target object supported by a first target object through a humanoid component of the robot, so as to adjust the target object from lying supine on the first target object to lying on the side on the first target object; autonomously and sequentially performing each action in a second action sequence on the target object supported by the first target object, so as to adjust the target object from lying on the side on the first target object to sitting up on the first target object; autonomously and sequentially performing each action in a third action sequence on the target object supported by the first target object, so as to adjust the target object from sitting up on the first target object to sitting up on a second target object. Through the present application, the pose of the target object can be safely and stably changed sequentially through action sequences to achieve the transfer of the target object.

Description

Technical Field

[0001] The present application relates to robot technology, and in particular to a method and device for processing the actions of a robot, an electronic device, a computer-readable storage medium, and a computer program product. Background Art

[0002] In the related art, the solutions for assisting the elderly to transfer from a bed to a wheelchair are mainly realized through dedicated equipment, such as a specially designed bed for assisting turning over, or a hoisting method for assisting the elderly to transfer, or a walking aid and an intelligent wheelchair for realizing the transfer of the elderly.

[0003] However, the solutions provided in the related art are dedicated equipment with single functions and usually require manual operation, and cannot autonomously realize the transfer of the elderly. Summary of the Invention

[0004] Embodiments of the present application provide a method and device for processing the actions of a robot, an electronic device, a computer-readable storage medium, and a computer program product, which can sequentially change the pose of a target object through an action sequence on the premise of being autonomous, so as to finally complete the adjustment of the target object from the first pose to the second pose. Since the final pose adjustment is realized based on multiple actions, the convenience and safety of the pose adjustment process can be improved.

[0005] The technical solution of the embodiments of the present application is realized as follows:

[0006] Embodiments of the present application provide a method for processing the actions of a robot, including:

[0007] The robot moves to the action range of the target object, where the target object is supported by a target object, and the action range is the area range where the robot can perform actions on the target object;

[0008] Through the humanoid components of the robot, each action in the action sequence is autonomously executed on the target object supported by the target object, so as to adjust the target object from the first pose to the second pose on the target object;

[0009] Wherein, each action corresponds to a pose change of the target object, and the pose change from the first pose to the second pose is obtained based on multiple pose changes of the action sequence.

[0010] Embodiments of the present application provide a device for processing the actions of a robot, including:

[0011] A moving module, configured to move the robot to within the action range of the target object, where the target object is supported by a target object, and the action range is the area range within which the robot can perform actions on the target object;

[0012] A fourth action module, configured to autonomously and sequentially perform each action in the action sequence on the target object supported by the target object through the humanoid components of the robot, so as to adjust the target object from the first pose to the second pose on the target object;

[0013] Wherein, each of the actions corresponds to a pose change of the target object, and the pose change from the first pose to the second pose is obtained based on multiple pose changes of the action sequence.

[0014] An embodiment of the present application provides a method for processing actions of a robot, including:

[0015] Autonomously and sequentially perform each action in the first action sequence on the target object supported by the first target object through the humanoid components of the robot, so as to adjust the target object from lying on its back on the first target object to lying on its side on the first target object;

[0016] Autonomously and sequentially perform each action in the second action sequence on the target object supported by the first target object through the humanoid components of the robot, so as to adjust the target object from lying on its side on the first target object to sitting up on the first target object;

[0017] Autonomously and sequentially perform each action in the third action sequence on the target object supported by the first target object through the humanoid components of the robot, so as to adjust the target object from sitting up on the first target object to sitting up on the second target object;

[0018] Wherein, each of the actions corresponds to a pose change of the target object, and each adjustment of the target object is obtained based on multiple pose changes of the corresponding action sequence.

[0019] An embodiment of the present application provides an action processing device for a robot, including:

[0020] A first action module, configured to autonomously and sequentially perform each action in the first action sequence on the target object supported by the first target object through the humanoid components of the robot, so as to adjust the target object from lying on its back on the first target object to lying on its side on the first target object;

[0021] A second action module, configured to autonomously and sequentially execute each action in a second action sequence on a target object supported by the first target object through the humanoid components of the robot, so as to adjust the target object from lying on its side on the first target object to sitting up on the first target object;

[0022] A third action module, configured to autonomously and sequentially execute each action in a third action sequence on a target object supported by the first target object through the humanoid components of the robot, so as to adjust the target object from sitting up on the first target object to sitting up on a second target object;

[0023] Wherein, each of the actions corresponds to a pose change of the target object, and each adjustment of the target object is obtained based on multiple pose changes of the corresponding action sequence.

[0024] An embodiment of the present application provides a robot, characterized in that the robot includes: a humanoid component and a controller; the controller is configured to control the humanoid component to execute the action processing method of the robot provided by the embodiment of the present application.

[0025] An embodiment of the present application provides an electronic device for controlling a robot, including:

[0026] A memory, configured to store computer-executable instructions;

[0027] A processor, when executing the computer-executable instructions stored in the memory, is configured to control the robot to implement the action processing method of the robot provided by the embodiment of the present application.

[0028] An embodiment of the present application provides a computer-readable storage medium, storing computer-executable instructions, which are used to cause a processor to implement the action processing method of the robot provided by the embodiment of the present application when executed.

[0029] An embodiment of the present application provides a computer program product, including computer-executable instructions, which, when executed by a processor, implement the action processing method of the robot provided by the embodiment of the present application.

[0030] The embodiment of the present application has the following beneficial effects:

[0031] Through the humanoid components of the robot, each action in the first action sequence is autonomously and sequentially performed on the target object supported by the first target object, so as to adjust the target object from lying supine on the first target object to lying on the side on the first target object; through the humanoid components of the robot, each action in the second action sequence is autonomously and sequentially performed on the target object supported by the first target object, so as to adjust the target object from lying on the side on the first target object to sitting up on the first target object; through the humanoid components of the robot, each action in the third action sequence is autonomously and sequentially performed on the target object supported by the first target object, so as to adjust the target object from sitting up on the first target object to sitting up on the second target object. Since the transfer is carried out in stages, and the pose change within each stage is realized through the action sequence, the pose of the target object can be safely and stably changed in sequence through the action sequence to achieve the transfer of the target object. Description of the Drawings

[0032] Figure 1 is a schematic structural diagram of the action processing system of the robot provided by the embodiment of the present application;

[0033] Figure 2 is a schematic structural diagram of the electronic device provided by the embodiment of the present application;

[0034] Figures 3A - 3E is a schematic flowchart of the action processing method of the robot provided by the embodiment of the present application;

[0035] Figure 4 is a schematic structural diagram of the robot of the action processing method of the robot provided by the embodiment of the present application;

[0036] Figures 5A - 5C is a schematic diagram of the pose change of the first action sequence provided by the embodiment of the present application;

[0037] Figures 6A - 6B is a schematic diagram of the pose change of the second action sequence provided by the embodiment of the present application;

[0038] Figures 7A - 7C is a schematic diagram of the pose change of the third action sequence provided by the embodiment of the present application;

[0039] Figure 8 is a schematic diagram of the pose change of the fourth action sequence provided by the embodiment of the present application. Detailed Embodiments

[0040] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limitations on the present application. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present application.

[0041] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments. However, it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict.

[0042] In the following description, the terms "first", "second", and "third" are merely used to distinguish similar objects and do not represent a specific order for the objects. It is understood that "first", "second", and "third" may be interchanged in a specific order or sequence when permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0043] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this application belongs. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0044] Before further elaborating on the embodiments of this application, the nouns and terms involved in the embodiments of this application are described. The nouns and terms involved in the embodiments of this application are subject to the following explanations.

[0045] 1) A robot is an intelligent machine that can work semi-autonomously or fully autonomously. A robot can perform tasks such as operations or movements through programming and automatic control.

[0046] 2) Pose is used to describe the position and orientation of an object (such as coordinates) in a specified coordinate system. Robots commonly use pose to describe their position and orientation in a spatial coordinate system.

[0047] The robot provided by the embodiment of the present application is a robot that moves using legs. It is modeled after animals, aiming to simulate the movement forms of animals and replicate their movement capabilities based on engineering technology and scientific research results. The robot has strong adaptability to various environments (including structured environments such as roads, railways, and treated flat surfaces, and unstructured environments such as mountains, swamps, and rough surfaces). It can adapt to various changes in terrain, cross relatively high obstacles, and can effectively reduce the load and improve the energy utilization efficiency of the system. Robots can be classified into single-foot, two-foot, four-foot, six-foot, eight-foot, etc. according to the number of feet. Among them, humanoid robots have super movement capabilities. They have better static stability than two-foot robots and are simpler and more flexible in movement than six-foot and eight-foot robots. Therefore, humanoid robots are a common choice for studying robots. The gait of a humanoid robot is the coordination relationship of its four legs in time and space in order to be able to move continuously. The gait of a humanoid robot comes from the gait of four-legged mammals (for example, a puppy), and it can include but is not limited to the following three simplified forms: walk, trot, and bound.

[0048] Figure 4 is a schematic diagram showing the robot according to the embodiment of the present application. As Figure 4 shown, the four-legged humanoid robot is an intelligent device that can approximately imitate animals. It has the ability to walk and move flexibly in complex terrains and environments, so it has a wide range of applications in many application scenarios. For example, in emergency situations, humanoid robots can be used for search and rescue, detection, demolition and other tasks. They can work in places where humans are difficult to reach, such as mountains, deserts, and forests. In daily life, humanoid robots can be used as an intelligent companion. They can interact with humans in a home environment and can also adapt to different terrains in the home, such as slopes and steps. The robot not only has a high degree of intelligence and flexibility but also has strong adaptability and practicality.

[0049] Exemplary robots include multiple components, such as a head component (optional), a body component, and a leg component, etc. Of course, the embodiment of the present application is not limited thereto.

[0050] Exemplary head components may be equipped with perception components such as visual cameras and voice interaction systems for environmental interaction and human-machine interaction. In some examples, the head component further includes a neck rotation component for pitching and left-right rotation movements of the head to obtain a wider field of view. Of course, the embodiment of the present application is not limited thereto.

[0051] One end of the head component is connected to the body component of the robot. In an exemplary body component, components such as a battery, a computing system, and a control system may be accommodated to provide energy and computing support for the movement of the robot.

[0052] In addition, the exemplary body component includes, but is not limited to, an upper limb component, a waist component, and a hip component. Of course, the embodiments of the present application are not limited thereto.

[0053] The left and right ends of the exemplary body component include symmetric upper limb components. The exemplary upper limb component includes a shoulder joint component, an arm component, and an end effector. The shoulder joint component has six degrees of freedom and can realize complex movements such as the rotation and lifting of the arm component in all directions. One end of the arm component is connected to the shoulder joint component, and the other end is connected to the end effector. Optionally, a motor is included at the connection between the arm component and the end effector to enable the end effector to move along four degrees of freedom. Among them, the optional end effector can be a manipulator of any form, which has a rich degree of freedom to imitate human movements such as grasping, pushing, and supporting various shaped objects.

[0054] The waist component and the hip component are used to connect the leg component and the body component. Among them, a motor for enabling the torso component to perform pitching rotation is installed inside the waist component so that the robot can imitate the bending action of a human. A motor for rotating the leg component is installed inside the hip component. By controlling this motor, the posture of the leg component can be changed.

[0055] The leg component includes four mechanical legs, and the exemplary robot can move based on the four mechanical legs. Among them, the four mechanical legs are respectively two inner legs (shown in gray) and two outer legs (shown in white). Each mechanical leg includes a telescopic rigid component and a driving wheel. One end of the telescopic rigid component of the inner leg is connected to the body component of the robot, for example, connected to the hip, and the other end is connected to the driving wheel. Optionally, the inner legs and the outer legs are respectively controlled by different motors, so that the relative positions of the inner legs and the outer legs can be changed to be more suitable for the human living environment. The telescopic rigid component can be extended and shortened. The leg motor is used to drive the mechanical leg to walk, and when an obstacle is encountered during walking, the telescopic rigid component can cross the obstacle by extending or shortening. The driving wheel is used for wheeled movement.

[0056] The telescopic rigid component includes a main leg segment, a telescopic leg segment, and a telescopic drive mechanism. The main leg segment is connected to the leg motor. The telescopic leg segment is slidably connected to the main leg segment, and one end of the telescopic leg segment away from the leg motor is connected to the drive wheel assembly. The telescopic drive mechanism is respectively connected to the main leg segment and the telescopic leg segment, and the telescopic drive mechanism is used to drive the telescopic leg segment to slide. When the telescopic drive mechanism drives the telescopic leg segment to slide in a direction away from the leg motor, the robotic leg extends; when the telescopic drive mechanism drives the telescopic leg segment to slide in a direction close to the leg motor, the robotic leg shortens. In the embodiments of the present application, the relative positional relationship between the main leg segment and the telescopic leg segment is not limited. In some examples, one side of the main leg segment is slidably connected to one side of the telescopic leg segment. In other examples, the main leg segment has a receiving cavity, a part of the telescopic leg segment is located in the receiving cavity, and the telescopic leg segment can telescopically move relative to the receiving cavity. The type of the telescopic drive mechanism is not limited in the embodiments of the present application. In some examples, the telescopic drive mechanism is a lead screw nut mechanism, a synchronous belt mechanism, a rack and pinion mechanism, a hydraulic rod mechanism, an electric push rod mechanism, etc.

[0057] It should be noted that various sensors can also be configured on the robot, such as an IMU (Inertial Measurement Unit) sensor and a joint angle encoder, etc.; among them, the IMU sensor can provide the acceleration and attitude information of the robot in real time, and the joint angle encoder can provide the joint angle information of each joint of the robot in real time (such as the angle of the joint angle, the feedback value of the angular velocity, etc.). The exemplary robot can already simulate real humans to perform actions such as running, jumping, climbing stairs, etc. under the control of the multiple motors mentioned above.

[0058] In the related art, the solutions for assisting the elderly to transfer from the bed to the wheelchair are mainly realized through special equipment, such as a specially designed bed for assisting turning over, or using a hoisting method to assist the elderly to transfer, or realizing the transfer of the elderly through a walking aid and an intelligent wheelchair. However, the solutions provided in the related art belong to special equipment, and the functions of the special equipment are single and usually require manual operation, and cannot autonomously realize the transfer of the elderly. Moreover, the solutions for the transfer of the elderly in the related art have problems of poor safety, stability, and labor-saving ability, resulting in difficulty in being applied to real scenarios.

[0059] The embodiments of the present application provide a method, device, electronic device, computer-readable storage medium, and computer program product for processing the actions of a robot, which can safely and stably change the pose of a target object in sequence through an action sequence to realize the transfer of the target object.

[0060] The following describes an exemplary application of the electronic device for controlling a robot provided in the embodiments of the present application. The electronic device for controlling a robot provided in the embodiments of the present application can be implemented as various types of user terminals such as a laptop computer, a tablet computer, a desktop computer, a set-top box, a mobile device (e.g., a mobile phone, a portable music player, a personal digital assistant, a dedicated messaging device, a portable game device), etc., or can be implemented as a server.

[0061] Refer to Figure 1 , Figure 1 FIG. is a schematic diagram of the architecture of the action processing system of the robot provided in the embodiments of the present application. The robot 400 is connected to the server 200 through the network 300. The network 300 can be a wide area network, a local area network, or a combination of both.

[0062] When the robot 400 observes a target object, the robot 400 collects the state data of the target object and sends the state data to the server 200. The server 200 performs intention recognition on the target object, so as to sense that the target object has a need to transfer from the first target object to the second target object. The server 200 sends the action execution instructions of the first action sequence, the second action sequence, and the third action sequence to the robot 400, so that the robot 400 autonomously executes each action in the first action sequence for the target object supported by the first target object, so as to adjust the target object from lying supine on the first target object to lying on the side on the first target object; the robot 400 autonomously executes each action in the second action sequence for the target object supported by the first target object, so as to adjust the target object from lying on the side on the first target object to sitting up on the first target object; the robot 400 autonomously executes each action in the third action sequence for the target object supported by the first target object, so as to adjust the target object from sitting up on the first target object to sitting up on the second target object.

[0063] In some embodiments, the server 200 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The terminal 400 can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited thereto. The terminal and the server can be directly or indirectly connected through wired or wireless communication methods, which are not limited in the embodiments of the present invention.

[0064] The motion processing method of the robot provided by the embodiments of the present application is applied to artificial intelligence technology. For example, artificial intelligence technology can be used to identify the needs of an object. Artificial intelligence (AI) is a theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a way similar to human intelligence. Artificial intelligence also studies the design principles and implementation methods of various intelligent machines to enable machines to have the functions of perception, reasoning, and decision-making. Artificial intelligence technology is an interdisciplinary subject with a wide range of fields, including both hardware-level technologies and software-level technologies. Artificial intelligence basic technologies generally include, for example, sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, pre-trained model technology, operation / interaction systems, mechatronics, etc. Among them, the pre-trained model, also known as the large model or the basic model, can be widely applied to downstream tasks in various directions of artificial intelligence after fine-tuning. Artificial intelligence software technologies mainly include several major directions such as computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0065] See Figure 2 , Figure 2 FIG. is a schematic structural diagram of an electronic device provided by the embodiments of the present application. Taking the electronic device as a server as an example for illustration, Figure 2 The server 200 shown includes: at least one processor 210, a memory 250, at least one network interface 220, and a user interface 230. Each component in the server 200 is coupled together through a bus system 240. It can be understood that the bus system 240 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 240 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clear illustration, in Figure 2 all kinds of buses are labeled as the bus system 240.

[0066] The processor 210 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor can be a microprocessor or any conventional processor, etc.

[0067] The user interface 230 includes one or more output devices 231 that enable the presentation of media content, including one or more speakers and / or one or more visual display screens. The user interface 230 also includes one or more input devices 232, including user interface components that facilitate user input, such as a keyboard, mouse, microphone, touch screen display, camera, other input buttons, and controls.

[0068] The memory 250 can be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid state memory, hard disk drives, optical disk drives, etc. The memory 250 optionally includes one or more storage devices that are physically remote from the processor 210.

[0069] The memory 250 includes volatile memory or non-volatile memory, and may also include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), and the volatile memory can be random access memory (RAM). The memory 250 described in the embodiments of the present application is intended to include any suitable type of memory.

[0070] In some embodiments, the memory 250 is capable of storing data to support various operations. Examples of such data include programs, modules, and data structures, or subsets or supersets thereof, which are illustrated below.

[0071] The operating system 251 includes system programs for processing various basic system services and performing hardware-related tasks, such as the framework layer, core library layer, driver layer, etc., for implementing various basic services and processing hardware-based tasks;

[0072] The network communication module 252 is used to reach other electronic devices via one or more (wired or wireless) network interfaces 220. Exemplary network interfaces 220 include: Bluetooth, Wi-Fi (Wireless Fidelity), and USB (Universal Serial Bus), etc.;

[0073] The presentation module 253 is used to enable the presentation of information (such as a user interface for operating peripheral devices and displaying content and information) via one or more output devices 231 associated with the user interface 230 (such as a display screen, speaker, etc.);

[0074] The input processing module 254 is used to detect and translate one or more user inputs or interactions from one of the one or more input devices 232.

[0075] In some embodiments, the motion processing device of the robot provided by the embodiments of the present application may be implemented in software. Figure 2 Shown in the memory 250 is the motion processing device 255 of the robot, which may be software in the form of programs and plugins, etc., including the following software modules: a first motion module 2551, a second motion module 2552, and a third motion module 2553. These modules are logical, and thus can be arbitrarily combined or further split according to the functions to be implemented. The functions of each module will be described below.

[0076] The motion processing method of the robot provided by the embodiments of the present application will be described in combination with the exemplary applications and implementations of the robot provided by the embodiments of the present application.

[0077] See Figure 3A , Figure 3A is a flowchart of the motion processing method of the robot provided by the embodiments of the present application, which will be described in combination with Figure 3A the steps 101 to 103 shown. Each of the motions involved in the embodiments of the present application corresponds to a change in the pose of the target object once, and each adjustment for the target object is obtained based on multiple pose changes of the corresponding motion sequence.

[0078] In step 101, through the humanoid components of the robot, each motion in the first motion sequence is autonomously executed on the target object supported by the first target object in sequence, so as to adjust the target object from lying supine on the first target object to lying on the side on the first target object.

[0079] As an example, here the target object is an elderly person in need of help, and the humanoid components may be the head, waist, arms, etc. of the robot. The humanoid components involved in step 101 are the humanoid components related to the first motion sequence, that is, the humanoid components required to execute the motions in the first motion sequence. Here, the first target object may be a bed, and the first motion sequence is used to assist the elderly person in adjusting from lying supine to lying on the side in the bed. The initial pose of the elderly person is lying flat in the bed, and the pose of the elderly person is adjusted from lying flat in the bed to lying on the side in the bed by executing multiple motions in the first motion sequence.

[0080] See Figure 3B , in step 101, through the humanoid components of the robot, each motion in the first motion sequence is autonomously executed on the target object supported by the first target object in sequence, so as to adjust the target object from lying supine on the first target object to lying on the side on the first target object, which can be achieved through Figure 3B the steps 1011 to 1013 shown.

[0081] In step 1011, the waist of the robot tilts towards the direction corresponding to the target object, so that the target object is within the action range of the robot.

[0082] As an example, the waist 401 of the robot tilts towards the old person. To ensure stability, it is necessary to ensure that the tilt angle is less than the first tilt angle threshold. The first tilt angle threshold is the maximum tilt angle obtained through experimental tests to maintain stable movement. If it is greater than the first tilt angle threshold, there is a high probability of tipping over.

[0083] In step 1012, the first arm of the robot moves to the hip of the target object, and the second arm of the robot moves upward to the shoulder of the target object.

[0084] As an example, if the first arm is the left arm, the second arm is the right arm; if the first arm is the right arm, the second arm is the left arm. Due to the need to consider the labor-saving requirement, the robot's two hands cooperate to exert force, which can reduce the force on a single hand. The distance between the acting points of the two hands should be as large as possible to achieve the purpose of labor saving. Considering the body structure of the old person, it is more appropriate to exert force on the shoulder and hip.

[0085] In step 1013, using the hip of the target object as the force application point of the first arm of the robot, and using the shoulder of the target object as the force application point of the second arm of the robot, the first arm and the second arm exert force on the target object to adjust the target object from lying supine on the first target object to lying on the side on the first target object.

[0086] In some embodiments, in step 1013, the first arm and the second arm exert force on the target object to adjust the target object from lying supine on the first target object to lying on the side on the first target object, which can be achieved through the following technical solutions: the first arm and the second arm exert a force on the target object away from the robot to adjust the target object from lying supine to lying on the side with the back facing the robot; or the first arm and the second arm exert a force on the target object towards the robot to adjust the target object from lying supine to lying on the side facing the robot.

[0087] There are two implementation methods here. The target object can be flipped away from the robot, and the target object can also be flipped toward the robot. This is because the elderly lying on their backs have two sides, the left side corresponding to the left arm and the right side corresponding to the right arm. When the second target object is on the left side corresponding to the elderly's left arm, the target object is flipped toward the left side. When the second target object is on the right side corresponding to the elderly's right arm, the target object is flipped toward the right side. In the later stage of the action, when approaching side-lying, both hands should cooperate to provide reverse force to maintain the stability of the elderly (relative to the robot, a smaller downward and forward force is provided, and the direction and value of the force here are obtained based on simulation tests), and then let go after the elderly are stable.

[0088] In some embodiments, the robot removes obstacles in the area where the target object is located before the robot's waist is tilted in a direction corresponding to the target object so that the target object is within the robot's range of motion; the robot places the target object's arms on the target object's chest; the robot adjusts the target object's legs from a straight state to a bent state; wherein the bent state, the support structure, and the placement of the arms are used to keep the target object stable during the process of adjusting from lying on its back on the first target object to lying on its side on the first target object.

[0089] As an example, the action design needs to take stability into consideration. The elderly's legs need to be kept in a bent state, otherwise they will be unstable when lying on their side. Therefore, when the elderly are in a supine position, the legs should be assisted to bend first. To maintain stability, the robot is required to resist the risk of tipping forward. Therefore, the robot's chassis is extended as far as possible under the bed, as close to the bed as possible, and can be supported against the edge of the bed to prevent tipping when necessary. The action design also needs to take into account spatial interference to avoid the elderly's hands being pressed when they switch from lying on their back to lying on their side. At the beginning (in the supine position), the elderly's hands are assisted to be placed on their chests. The robot's front legs are extended under the bed to increase the support surface and increase stability. Both hospital beds and nursing beds have lower space.

[0090] In step 102, the humanoid component of the robot autonomously and sequentially performs each action in the second action sequence on the target object supported by the first target object to adjust the target object from lying on its side on the first target object to sitting up on the first target object.

[0091] As an example, the second action sequence is used to assist an elderly person to sit up from lying on his side. The elderly person's legs are put down to the side of the bed. The robot supports the elderly person's upper hip with its left hand and the lower shoulder with its right hand. The left hand exerts force to the left and downward, and the right hand exerts force to the left and upward, to change the elderly person from lying on his side to sitting up.

[0092] In some embodiments, see Figure 3C, in step 102, each action in the second action sequence is autonomously and sequentially performed on the target object supported by the first target object through the humanoid component of the robot, so as to adjust the target object from lying on its side on the first target object to sitting up on the first target object, which can be achieved through Figure 3C the steps 1021 to 1023 shown.

[0093] In step 1021, the first arm of the robot moves to the upper hip of the target object.

[0094] As an example, when the elderly person is in a lying-on-side state, move the left arm or the right arm of the robot to the upper hip, that is, the hip part away from the bed.

[0095] In step 1022, the second arm of the robot moves to the lower side of the shoulder of the target object.

[0096] As an example, when the elderly person is in a lying-on-side state, move the left arm or the right arm of the robot to the lower side of the shoulder, that is, the shoulder part next to the bed. Here, the second arm is different from the first arm. If the first arm is the left arm, the second arm is the right arm; if the first arm is the right arm, the second arm is the left arm.

[0097] In step 1023, using the upper hip of the target object as the force application point of the first arm of the robot and the lower side of the shoulder of the target object as the force application point of the second arm of the robot, the first arm and the second arm exert force on the target object to adjust the target object from lying on its side on the first target object to sitting up on the first target object.

[0098] In some embodiments, in step 1023, exerting force on the target object through the first arm and the second arm can be achieved through the following technical solution: applying a force parallel to the plane of the target object's legs and perpendicular to the target object's legs to the upper hip of the target object through the first arm; applying a force parallel to the plane of the target object's body and perpendicular to the target object's upper arm of the arm to the lower side of the shoulder of the target object through the second arm.

[0099] As an example, referring to Figures 6A through 6B , the core actions are as follows. The robot holds the upper hip of the elderly person with the left hand and the lower side of the shoulder of the elderly person with the right hand, and the arms and the waist exert force together to change the elderly person from the side-lying state to the sitting-up state. Before completing the action, pay attention to ensuring the stability of the elderly person to avoid tipping. During the pose adjustment process, the robot will place the legs of the elderly person under the bed along with the trend to keep the legs of the elderly person stable.

[0100] As an example, a force parallel to the body plane of the target object and perpendicular to the upper arm of the target object's arm is applied to the lower side of the shoulder of the target object by the second arm. Here, the force is parallel to the body plane of the target object and perpendicular to the upper arm of the target object's arm. By this force, the elderly person is lifted from a side-lying position to a sitting position. A force parallel to the plane of the target object's legs and perpendicular to the target object's legs is applied to the upper hip of the target object by the first arm. Here, the force is parallel to the plane of the legs and perpendicular to the legs, so as to keep the elderly person stable. Therefore, this force actually plays a stabilizing role. These two forces act simultaneously, so that the elderly person can be lifted and kept stable at the same time.

[0101] In step 103, each action in the third action sequence is autonomously and sequentially performed on the target object supported by the first target object through the humanoid component of the robot, so as to adjust the target object from sitting up on the first target object to sitting up on the second target object.

[0102] As an example, the third action sequence is used to assist the elderly person from the bed to the wheelchair. The robot's two arms support the elderly person under both armpits, lift the elderly person up, and the robot turns in place and places the elderly person on the wheelchair.

[0103] In some embodiments, before the above-mentioned each action in the third action sequence is autonomously and sequentially performed on the target object supported by the first target object through the humanoid component of the robot to adjust the target object from sitting up on the first target object to sitting up on the second first target object, when the target object is not at the edge of the first target object, the following processing is performed: the body on any side of the target object is lifted by the humanoid component of the robot, and the body on any side of the target object is moved towards the edge of the first target object, and the target object is placed on the first target object; the body on the other side of the target object is lifted by the humanoid component of the robot, the body on the other side of the target object is moved towards the edge of the first target object, and the target object is placed on the first target object.

[0104] As an example, a fourth action sequence needs to be performed before the third action sequence. The fourth action sequence is used to assist the elderly person to get closer to the edge of the bed in a sitting state for position transfer: the robot's left hand supports the right hip of the elderly person, and the right hand supports the left armpit of the elderly person, and simultaneously exerts force upward to lift the left half of the elderly person's body, moves a short distance forward, and then puts down the elderly person. Then switch to the right side to perform the mirror action and repeat multiple times.

[0105] In some embodiments, the target object and the robot face each other; the following technical solution can be adopted to lift the body on either side of the target object through the humanoid components of the robot: the first arm of the robot moves under the hip on either side of the target object, where the first arm and the either side are on opposite sides. Since the robot and the target object are in a face-to-face state, that is, move the left arm of the robot under the right armpit of the elderly, or move the right arm of the robot under the left armpit of the elderly; the second arm of the robot moves under the armpit on the other side of the target object; apply an upward acting force to the target object through the arms and waist of the robot to lift the body on either side of the target object.

[0106] As an example, refer to Figure 8 , the robot supports the left hip of the elderly with its left hand, supports the left armpit of the elderly with its right hand, and the arms and waist work together to lift the left side of the elderly's body, move it forward of the elderly and backward of the robot, and then put it down. Then perform the mirror action. The robot supports the right armpit of the elderly with its left hand, supports the left armpit of the elderly with its right hand, and the arms and waist work together to lift the right side of the elderly's body, move it forward of the elderly and backward of the robot, and then put it down. Repeat the above actions until the elderly are sitting on the edge of the bed for the next action.

[0107] In some embodiments, refer to Figure 3D , in step 103, through the humanoid components of the robot, each action in the third action sequence is autonomously executed on the target object supported by the first target object to adjust the target object from sitting up on the first target object to sitting up on the second target object, which can be achieved through Figure 3D the steps 1031 to 1033 shown.

[0108] In step 1031, the arms of the robot move to the armpits on both sides of the target object respectively to lift the target object and move it away from the first target object.

[0109] As an example, the action design needs to consider labor saving. The robot gets as close to the elderly as possible to reduce the force arm. On the premise of being able to reach the elderly, the forward tilt of the waist is minimized as much as possible. The robot's hands cooperate to exert force, which can reduce the force of a single hand, and the distance between the acting points of the two hands is as large as possible. Considering the human body structure, the robot's arms extend into the armpits of the elderly as much as possible to make the elderly close to the robot's body, and the front part of the upper arm of the robotic arm is used to exert force, with a smaller force arm and a lower load on the robot.

[0110] In step 1032, the robot performs a turning action so that the target object is directly above the second target object.

[0111] As an example, the robot only needs to slightly lift the elderly person (the lifting distance is less than the first distance threshold, where the first distance threshold is the maximum distance obtained through experiments that allows the elderly person to leave the support of the bed and retains the support of the ground for the elderly person's legs), and then turns to the wheelchair to obtain the support of the wheelchair. The entire movement process is short, and the load on the robot is low.

[0112] In step 1033, the robot places the target object on the second target object.

[0113] In some embodiments, before performing step 1031, the robot's arms move the second target object next to the target object and form a right angle with the target object; the robot stabilizes the second target object so that the second target object is in a stable state.

[0114] As an example, the third action sequence is used to assist the elderly person in moving from the bed to the wheelchair. The action design needs to consider stability. The initial and end states of the elderly person are stable (sitting position). Here, the stabilization process is that the robot applies a small inward force and a force to hug the robot to the elderly person. The robot should be as close to the elderly person as possible to resist the risk of tipping forward. The action design needs to consider spatial interference and avoid interference between the elderly person's legs and the robot's legs. The outer legs of the robot are wider, so the outer legs are in front. While getting as close to the elderly person as possible forward, place the elderly person's legs between the robot's legs. At this time, the elderly person's body is basically within the robot's support area, and the risk of tipping is also low.

[0115] In some embodiments, refer to Figure 3E , Figure 3E is a schematic flowchart of the action processing method of the robot provided by the embodiments of the present application, and will be described in conjunction with Figure 3E the steps 201 to 202 shown. Each action involved in the embodiments of the present application corresponds to a pose change of the target object, and the pose change from the first pose to the second pose is obtained based on multiple pose changes of the action sequence.

[0116] In step 201, the robot moves to the action range of the target object, where the target object is supported by the target object, and the action range is the area range where the robot can perform actions on the target object.

[0117] In step 202, through the humanoid components of the robot, each action in the action sequence is autonomously executed on the target object in sequence to adjust the target object from the first pose to the second pose on the target object.

[0118] The action sequences here can be the first action sequence, the second action sequence, the third action sequence, and the fourth action sequence. When the action sequence is the first action sequence, the first pose is that the target object lies supine on the first target object, and the second pose is that the target object lies on its side on the first target object; after executing the first action sequence, the second action sequence can be executed. When the action sequence is the second action sequence, the first pose is that the target object lies on its side on the first target object, and the second pose is that the target object sits up on the first target object; after executing the first action sequence, the fourth action sequence can be executed. When the action sequence is the fourth action sequence, the first pose is that the target object sits up on the first target object, and the second pose is that the target object sits up on the edge of the first target object; after executing the fourth action sequence, the third action sequence can be executed. When the action sequence is the third action sequence, the first pose is that the target object sits up on the edge of the first target object, and the second pose is that the target object sits up on the second target object.

[0119] Through the humanoid components of the robot, each action in the action sequence is autonomously executed on the target object supported by the target object in turn, so as to adjust the target object from the first pose to the second pose on the target object; each action corresponds to a pose change of the target object, and the pose change from the first pose to the second pose is obtained based on multiple pose changes of the action sequence. Through this application, it is possible to sequentially change the pose of the target object through the action sequence on the premise of autonomy, so as to finally complete the adjustment of the target object from the first pose to the second pose. Since the final pose adjustment is realized based on multiple actions, the convenience and safety of the pose adjustment process can be improved.

[0120] Next, an exemplary application of the embodiments of this application in an actual application scenario will be described.

[0121] When the robot observes a disabled elderly person, the robot collects the state data of the disabled elderly person and sends the state data to the server 200. The server 200 performs intention recognition on the disabled elderly person, so as to perceive that the disabled elderly person has a need to transfer from the bed to the wheelchair. The server 200 sends the action execution instructions of the first action sequence, the second action sequence, and the third action sequence to the robot, so that the robot autonomously executes each action in the first action sequence on the disabled elderly person supported by the bed in turn, so as to adjust the disabled elderly person from lying supine in the bed to lying on the side in the bed; the robot autonomously executes each action in the second action sequence on the disabled elderly person supported by the bed in turn, so as to adjust the disabled elderly person from lying on the side in the bed to sitting up in the bed; the robot autonomously executes each action in the third action sequence on the disabled elderly person supported by the bed in turn, so as to adjust the disabled elderly person from sitting up in the bed to sitting up in the wheelchair.

[0122] Human habitation robots are used to assist the elderly in disabled states to transfer from bed to wheelchair in elderly care scenarios. The main action implementation steps include: assisting the elderly from supine to side-lying, from side-lying to sitting up, getting closer to the bedside when sitting up, and from bed to wheelchair. The main action sequence is formulated according to safety, mainly considering three principles: avoiding spatial interference, maintaining stability, and saving effort (minimizing the load borne by the robot, reducing energy consumption, and ensuring safety). According to the principles of stability and effort saving, a large task is completed through a series of simple action sequences, in which each action only slightly changes the posture of the elderly, so as to make full use of the support of the bed, the ground, the wheelchair, etc. Before and after each action, the elderly are in a stable state without external assistance.

[0123] The embodiments of the present application are mainly applicable to the following two categories of elderly people: 1. Elderly people who are slightly weak overall and who only need one caregiver to assist them in completing position transfer, such as elderly people who can sit stably but cannot transfer position independently; 2. Elderly people who are slightly weak on one side of the body and need slight assistance.

[0124] For the above-mentioned applicable elderly people, it is only necessary to provide assistance when transferring positions, and there is no need to bear the entire weight of the elderly. Part of the weight of the elderly is supported by themselves, the ground, the bed, etc., and the load requirements for the robot are relatively low. The usual service robot can meet the needs. In addition, for the same reasons as above, when providing assistance, a series of action sequences are required, in which each action only slightly changes the state of the elderly, so as to make full use of the support of the environment. And in the intervals between actions, the elderly can remain stable, and the robot does not need to provide support all the time. On the contrary, if the goal is achieved by changing the state of the elderly at one time, it is difficult to rely on the environment, and the robot must bear most of the weight of the elderly. General service robots do not have such a high load capacity, and it is not conducive to safety and energy saving.

[0125] Before the main steps are implemented, necessary preparations need to be made, including cleaning the environment, preparing wheelchairs, and properly placing the elderly's limbs before assisting them to transfer positions to ensure safety during the transfer. Disabled elderly people have relatively weak limbs, and changing their postures through their limbs cannot fully control their postures, increasing the risk of sprains. Therefore, the trunk needs to be used to change the elderly's postures.

[0126] The first action sequence is introduced below, which is used to assist the elderly from lying on their back to lying on their side. The elderly are initially lying flat on their back. First, the elderly's legs are straightened to bend their knees upward, and the elderly's arms are placed in front of their chest to avoid being pressed down later. Then, the robot holds the elderly's hips with its left hand and shoulders with its right hand, and the robot exerts force upward and backward to change the elderly from lying to lying on their side.

[0127] The following introduces the second action sequence, which is used to assist the elderly to sit up from a side-lying position and lower their legs to the edge of the bed. The robot holds the upper hip of the elderly with its left hand and supports the lower part of the shoulder on the lower side of the elderly with its right hand. The left hand exerts force to the left and downwards, and the right hand exerts force to the left and upwards, changing the elderly from a side-lying position to a sitting-up position.

[0128] The following introduces the third action sequence, which is used to assist the elderly from the bed to the wheelchair. The robot holds the armpits on both sides of the elderly with both arms, lifts the elderly, turns in place, and places the elderly on the wheelchair.

[0129] The following introduces the fourth action sequence, which is used to assist the elderly to get closer to the edge of the bed in a sitting-up position for position transfer: The robot holds the right buttock of the elderly with its left hand and the left armpit of the elderly with its right hand, and simultaneously exerts force upwards to lift the left half of the elderly's body, moves it forward a short distance, and then puts the elderly down. Then switch to the right side to perform the mirror action and repeat multiple times.

[0130] The above action sequences are completed by relying on the robot, which requires the robot to have flexible arms (6 degrees of freedom or more), palms, a waist, and lower limbs that can ensure stable support and turning in place. Any robot with these features can apply the action processing method provided by the embodiments of this application. The action processing method provided by the embodiments of this application mainly focuses on the basic action design under the safety principle. During the specific implementation of the robot, it is necessary to cooperate with the robot's compliant control, the recognition of the elderly's intentions, and a complete abnormal handling safety strategy to further ensure safety.

[0131] The embodiments of this application use a humanoid robot, including a waist, robotic arms, palms, etc., which can perform humanoid actions. General robot devices can all apply the action processing method provided by the embodiments of this application without special design. In addition to assisting the elderly with position transfer, the robot can also be used for other service functions, such as delivering items, pushing a wheelchair, assisting with walking and going up and down stairs, preparing meals, opening doors, etc. The robot can autonomously complete the task of assisting the elderly with position transfer without manual intervention or operation.

[0132] The following is a detailed introduction to the design principles of the first action sequence, which is used to assist the elderly from lying on their back to lying on their side. The action design needs to take into account stability. The initial state of the elderly (lying on their back) is stable, and the final state (lying on their side) must also remain stable. The elderly's legs need to be bent, otherwise they will be unstable after lying on their side. Therefore, when the elderly are in the supine state at the beginning, the legs of the elderly are first assisted to bend. To adjust the elderly from lying on their back to lying on their side, the robot needs to apply upward and backward forces to the elderly, and the robot needs to bend forward to operate. In order to maintain stability, the robot is required to be able to resist the risk of tipping forward, so the chassis of the robot is extended as far as possible to extend under the bed, as close to the bed as possible, and can be supported against the edge of the bed to prevent tipping when necessary. In the later stage of the action, when approaching the side, both hands should cooperate to provide reverse force to maintain the stability of the elderly (relatively providing a smaller downward and forward force for the robot), and then let go after the elderly are stable. The action design needs to take into account the need for labor saving. The robot should get as close to the elderly as possible to reduce the force arm. On the premise of being able to reach the elderly, the waist should be tilted forward as little as possible, and the action should be completed by exerting force with the waist. The robot's two hands can cooperate to exert force to reduce the force of a single hand. The distance between the action points of both hands should be as large as possible. Considering the human body structure, it is more appropriate to exert force on the shoulders and hips. The action design also needs to take into account spatial interference to avoid pressing the hands of the elderly when they switch from supine to side-lying. At the beginning (supine state), help the elderly to put their hands on their chests. The robot's front legs extend under the bed to increase the support surface and increase stability. Both hospital beds and nursing beds have lower space.

[0133] The initial state of the first action sequence is that the elderly person is lying on his back on the bed. The robot enters the room and prepares for the following actions: The robot cleans the work space and avoids debris on the bed, on the side of the bed, and between the bed and the wheelchair; see Figure 5A , the robot moves to the bedside, touches the bed to stabilize the robot body and prevent it from leaning forward; puts the elderly's arms on the chest to avoid pressing them, and changes the elderly's legs from straight to bent. Figures 5B - 5C The robot leans forward, raises its arms, holds the elderly's hips with its left hand, and holds the elderly's shoulders with its right hand. It uses both arms and waist to change the elderly from a lying position to a side-lying position. Before completing the action, the robot will ensure the stability of the elderly to prevent them from falling. Figures 5A - 5C What is shown is just a schematic diagram of the action. In the actual implementation, fine-tuning is required according to the specific shapes of the robot arm and palm.

[0134] The following is a detailed introduction to the design principles of the second action sequence, which is used to assist the elderly from lying on their side to sitting up. The action design needs to take into account stability. The initial state of the elderly (lying on their side) is stable, and the final state (sitting position) is also stable. To adjust the elderly from lying on their side to sitting up, the robot needs to apply an upward and left force, and the robot needs to bend forward (the inclination of the bend is less than the inclination of the bend in the first action sequence). In order to maintain stability, the robot needs to be able to resist the risk of tipping forward and to the right. At the same time, considering that the elderly have an overall leftward offset, the robot faces the elderly to the left in advance, and the chassis is extended as far as possible under the bed, as close to the bed as possible, and the right leg can resist the edge of the bed to avoid tipping forward and to the right. Similarly, in the later stage of the action, both hands should cooperate to provide reverse force to maintain the stability of the elderly (left hand provides right, right hand provides left), and let go after the elderly are stable. The action design needs to consider labor saving. The robot should get as close to the elderly as possible to reduce the force arm. On the premise of being able to reach the elderly, the forward tilt of the waist should be reduced as much as possible. The robot's two hands can cooperate to exert force to reduce the force of a single hand. The distance between the action points of both hands should be as large as possible. Considering the human body structure, it is more appropriate to exert force on the lower shoulder (right hand) and upper hip (left hand). The right hand provides upward and left force, and the left hand provides downward and left force. The action design needs to consider spatial interference to avoid interference between the elderly's legs and the bed when they sit up. Before starting, move the elderly's legs from the bed to outside the edge of the bed and put them down. The robot's front legs extend under the bed to increase the support surface and stability. Both hospital beds and nursing beds have lower space. The robot's standing position needs to be as far to the left as possible but cannot interfere with the elderly's legs in space.

[0135] The initial state of the second action sequence is after the robot completes the first action sequence. The old man is lying on his side in bed, and the robot is beside the bed. Figures 6A - 6B The preparatory action is as follows: the robot puts the elderly's legs under the bed. The core action is as follows: the robot holds the elderly's upper hip with its left hand and the lower shoulder with its right hand. Both arms and waist work together to change the elderly from a side-lying position to a sitting position. Before completing the action, pay attention to ensure the stability of the elderly to avoid tipping over.

[0136] The following specifically introduces the fourth action sequence, which is used to assist the elderly to sit closer to the edge of the bed in preparation for the next step of transferring the elderly to a wheelchair. The action design needs to consider stability. The initial and final states of the elderly are stable (sitting position). The robot mainly needs to apply an upward force. To maintain stability, it is required that the robot can resist the risk of tipping forward, and the robot should be as close to the elderly as possible. The action design needs to consider effort-saving. The robot gets as close to the elderly as possible to reduce the force arm. On the premise of being able to reach the elderly, the forward inclination of the waist should be minimized as much as possible. The robot's two hands cooperate to exert force, which can reduce the force of a single hand. The distance between the action points of the two hands should be as large as possible. Only half of the elderly's body needs to be lifted and then moved a very small distance to the edge of the bed. Therefore, considering the human body structure, force is exerted under the armpit and buttocks on the same side. The robot exerts force upward and backward (relative to the robot itself). The action design needs to consider spatial interference to avoid interference between the elderly's legs and the robot's legs. See Figure 4 , the outer legs of the robot are wider (the distance between the two legs included in the outer legs is greater than the distance between the two legs included in the inner legs). Therefore, the outer legs are in front. While getting as close to the elderly as possible forward, the elderly's legs are in the middle of the robot's two legs. At this time, the elderly's body is basically within the robot's support area, and the risk of tipping is also relatively low.

[0137] The initial state of the fourth action sequence is the sitting position of the elderly after the second action sequence is completed. See Figure 8 , the robot holds the left buttock of the elderly with its left hand and the left armpit of the elderly with its right hand. The two arms and the waist work together to lift the left side of the elderly's body, move it forward of the elderly and backward of the robot, and then put it down. Then perform the mirror action. The robot holds the right armpit of the elderly with its left hand and the left armpit of the elderly with its right hand. The two arms and the waist work together to lift the right side of the elderly's body, move it forward of the elderly and backward of the robot, and then put it down. Repeat the above actions until the elderly are sitting on the edge of the bed for the next step.

[0138] The following specifically introduces the third action sequence, which is used to assist the elderly in moving from the bed to the wheelchair. When designing the actions, stability needs to be considered. The initial and final states of the elderly are stable (sitting position). The robot mainly needs to apply an upward force. However, to maintain the stability of the elderly, a relatively small inward force and a force to hug the robot also need to be applied. The robot should be as close to the elderly as possible to resist the risk of tipping forward. The design of the actions also needs to consider energy conservation. The robot should be as close to the elderly as possible to reduce the force arm. On the premise of being able to reach the elderly, the forward inclination of the waist should be minimized as much as possible. The robot's two hands cooperate to exert force, which can reduce the force on a single hand, and the distance between the action points of the two hands should be as large as possible. Considering the human body structure, the robot's two arms should extend as much as possible under the armpits of the elderly to bring the elderly closer to the robot's body. The front part of the upper arm of the robotic arm is used to exert force, with a smaller force arm and a lower load on the robot. In addition, the elderly only need to be slightly lifted off the support of the bed (while maintaining the support of the ground for the elderly's legs), and then turn to the wheelchair to obtain the support of the wheelchair. The entire action process is relatively short, and the load on the robot is low. The design of the actions also needs to consider spatial interference and avoid interference between the elderly's legs and the robot's legs. The outer legs of the robot are wider, so the outer legs are in the front. While moving as close to the elderly as possible forward, place the elderly's legs between the robot's two legs. At this time, the elderly's body is basically within the robot's support area, and the risk of tipping is also relatively low.

[0139] See Figure 7A , the initial state of the third action sequence is that after the second or third action sequence is completed, the elderly sit up on the edge of the bed. The preparatory actions are as follows: move the wheelchair to the edge of the bed, form a 90-degree angle with the bed, lock the brakes, and raise the armrests; See Figures 7B - 7C , the core actions of the third action sequence are as follows: the robot's two arms support the elderly under both armpits, lift the elderly up so that the buttocks leave the edge of the bed, but the elderly's legs still touch the ground. At this time, the elderly are not completely lifted up, and the robot only bears about 70% of the elderly's weight. The robot turns in place, moves the elderly above the wheelchair, and then puts the elderly down so that the elderly sit on the wheelchair. Before completing the action, it is necessary to ensure the stability of the elderly and avoid tipping.

[0140] Finally, assist the elderly to move closer to the backrest on the wheelchair. The corresponding action sequence is similar to the fourth action sequence, so it will not be elaborated here.

[0141] The action processing method provided in the embodiment of the present application uses a robot to complete the solution for assisting disabled elderly people in position transfer (from the bed to the wheelchair). Compared with special beds, wheelchairs, special equipment, etc., the embodiment of the present application is more anthropomorphic, can provide emotional care, has universality, and is applicable to other similar robots. The robot may provide other elderly care and home services in addition to assisting in transfer. The action processing method provided in the embodiment of the present application has autonomy and does not require manual operation, and can solve the pain points in elderly care services.

[0142] It is understandable that in the embodiments of the present application, when it comes to data related to user information, etc., when the embodiments of the present application are applied to specific products or technologies, user permission or consent needs to be obtained, and the collection, use, and processing of relevant data need to comply with relevant laws, regulations, and standards of relevant countries and regions.

[0143] Next, continue to describe the exemplary structure of the action processing device 255 of the robot provided in the embodiments of the present application as a software module. In some embodiments, as Figure 2 shown, the software module in the action processing device 255 of the robot stored in the memory 250 may include: a first action module, configured to autonomously execute each action in the first action sequence on a target object supported by the first target object through the humanoid components of the robot, so as to adjust the target object from lying supine on the first target object to lying on the side on the first target object; a second action module, configured to autonomously execute each action in the second action sequence on a target object supported by the first target object through the humanoid components of the robot, so as to adjust the target object from lying on the side on the first target object to sitting up on the first target object; a third action module, configured to autonomously execute each action in the third action sequence on a target object supported by the first target object through the humanoid components of the robot, so as to adjust the target object from sitting up on the first target object to sitting up on the second target object; wherein, each of the actions corresponds to a posture change of the target object, and each adjustment of the target object is obtained based on multiple posture changes of the corresponding action sequence.

[0144] In some embodiments, the first action module is further configured to: the waist of the robot inclines towards the direction corresponding to the target object, so that the target object is within the action range of the robot; the first arm of the robot moves to the buttocks of the target object, and the second arm of the robot moves upward to the shoulders of the target object; using the buttocks of the target object as the force application point of the first arm of the robot and the shoulders of the target object as the force application point of the second arm of the robot, applying force to the target object through the first arm and the second arm, so as to adjust the target object from lying supine on the first target object to lying on the side on the first target object.

[0145] In some embodiments, the first action module is further used to: apply a force away from the robot to the target object through the first arm and the second arm to adjust the target object from lying on its back to lying on its side with its back facing the robot; or apply a force toward the robot to the target object through the first arm and the second arm to adjust the target object from lying on its back to lying on its side facing the robot.

[0146] In some embodiments, the first action module is further used to: tilt the waist of the robot toward the direction corresponding to the target object so that before the target object is within the robot's range of action, the robot removes obstacles in the area where the target object is located; straighten the robot's front legs under the first target object to form a support structure; place the arms of the target object on the chest of the target object; adjust the legs of the target object from a straight state to a bent state; wherein the bent state, the support structure and the placement of the arms are used to keep the target object stable during the process of adjusting from lying on its back on the first target object to lying on its side on the first target object.

[0147] In some embodiments, the second action module is also used for: moving the first arm of the robot to the upper hip of the target object; moving the second arm of the robot to the lower side of the shoulder of the target object; using the upper hip of the target object as the force point of the first arm of the robot, and using the lower side of the shoulder of the target object as the force point of the second arm of the robot, and exerting force on the target object through the first arm and the second arm to adjust the target object from lying on its side on the first target object to sitting up on the first target object.

[0148] In some embodiments, the second action module is further used to: apply a force parallel to the plane of the target object's legs and perpendicular to the target object's legs to the upper hip of the target object through the first arm; and apply a force parallel to the plane of the target object's body and perpendicular to the target object's upper limbs to the lower side of the target object's shoulder through the second arm.

[0149] In some embodiments, the third action module is further configured to: through the humanoid components of the robot, autonomously perform each action in the third action sequence on a target object supported by the first target object, so as to adjust the target object from sitting up on the first target object to sitting up on the second first target object. Before that, when the target object is not at the edge of the first target object, perform the following processing: lift one side of the body of the target object through the humanoid components of the robot, move one side of the body of the target object towards the edge of the first target object, and place the target object on the first target object; lift the other side of the body of the target object through the humanoid components of the robot, move the other side of the body of the target object towards the edge of the first target object, and place the target object on the first target object.

[0150] In some embodiments, the third action module is further configured to: move the first arm of the robot under the hip on either side of the target object, where the first arm and the either side are on the opposite sides; move the second arm of the robot under the armpit on the other side of the target object; apply an upward force to the target object through the two arms of the robot to lift one side of the body of the target object.

[0151] In some embodiments, the third action module is further configured to: move the two arms of the robot to the armpits on both sides of the target object respectively to lift the target object and move it away from the first target object; the robot performs a turning action so that the target object is directly above the second target object; the robot places the target object on the second target object.

[0152] In some embodiments, the third action module is further configured to: move the second target object to the side of the target object by the two arms of the robot and form a right angle with the target object; the robot performs a stabilization process on the second target object so that the second target object is in a stable state.

[0153] In some embodiments, an action processing device of a robot includes: a moving module configured to move the robot to within the action range of a target object, where the target object is supported by a target object, and the action range is the area range within which the robot can perform actions on the target object; a fourth action module configured to autonomously perform each action in an action sequence on the target object supported by the target object through a humanoid component of the robot, so as to adjust the target object on the target object from a first pose to a second pose; where each of the actions corresponds to a pose change of the target object, and the pose change from the first pose to the second pose is obtained based on multiple pose changes of the action sequence.

[0154] An embodiment of the present application provides a robot, where the robot includes: a humanoid component and a controller; the controller is configured to control the humanoid component to execute the action processing method of the robot in the above embodiment of the present application.

[0155] An embodiment of the present application provides an electronic device for controlling a robot, characterized in that it includes a memory for storing computer-executable instructions; and a processor, when executing the computer-executable instructions stored in the memory, controls the robot to execute the action processing method of the robot in the above embodiment of the present application.

[0156] An embodiment of the present application provides a computer program product, which includes computer-executable instructions stored in a computer-readable storage medium. The processor of the electronic device for controlling the robot reads the computer-executable instructions from the computer-readable storage medium, and the processor executes the computer-executable instructions, so that the electronic device for controlling the robot executes the action processing method of the robot in the above embodiment of the present application.

[0157] An embodiment of the present application provides a computer-readable storage medium storing computer-executable instructions, where the computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, the processor will be caused to execute the action processing method of the robot provided in the embodiment of the present application. For example, Figures 3A - 3E the action processing method of the robot shown.

[0158] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disc, or CD-ROM; or may be various devices including one or any combination of the above memories.

[0159] In some embodiments, the computer-executable instructions may be in the form of a program, software, software module, script, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including being deployed as a stand-alone program or being deployed as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0160] As an example, the computer-executable instructions may or may not correspond to a file in a file system, may be stored as part of a file that holds other programs or data, for example, in one or more scripts in a HyperText Markup Language (HTML) document, stored in a single file dedicated to the program in question, or, stored in multiple cooperating files (for example, files that store one or more modules, subroutines, or portions of code).

[0161] As an example, the computer-executable instructions may be deployed to execute on an electronic device that controls a robot, or on multiple electronic devices that control robots at one location, or, on multiple electronic devices that control robots distributed at multiple locations and interconnected via a communication network.

[0162] In summary, through the humanoid components of the robot, each action in the action sequence is autonomously and sequentially executed on the target object supported by the target object, so as to adjust the target object from the first pose to the second pose on the target object; each action corresponds to a pose change of the target object, and the pose change from the first pose to the second pose is obtained based on multiple pose changes of the action sequence. Through the present application, it is possible to sequentially change the pose of the target object through the action sequence on the premise of autonomy, so as to finally complete the adjustment of the target object from the first pose to the second pose. Since the final pose adjustment is realized based on multiple actions, the convenience and safety of the pose adjustment process can be improved.

[0163] The above is only the embodiments of the present application and is not intended to limit the protection scope of the present application. Any modifications, equivalent replacements, and improvements made within the spirit and scope of the present application are included in the protection scope of the present application.

Claims

1. A method for processing the actions of a robot, characterized in that, The method comprises: By means of the humanoid component of the robot, each action in a first action sequence is autonomously and sequentially performed on a target object supported by a first target object, so as to adjust the target object from lying supinely on the first target object to lying sideways on the first target object; The first arm of the robot moves to the upper hip of the target object; The second arm of the robot moves to the underside of the shoulder of the target object; Using the upper hip of the target object as the force point of the first arm of the robot, and using the lower side of the shoulder of the target object as the force point of the second arm of the robot, the first arm and the second arm exert force on the target object to adjust the target object from lying on its side on the first target object to sitting up on the first target object; By means of the humanoid component of the robot, each action in a third action sequence is autonomously and sequentially performed on the target object supported by the first target object, so as to adjust the target object from sitting up on the first target object to sitting up on the second target object; The second target object is an object different from the first target object, each of the actions corresponds to a posture change of the target object, and each adjustment of the target object is obtained based on multiple posture changes of the corresponding action sequence.

2. The method according to claim 1, characterized in that, The method of autonomously and sequentially performing each action in a first action sequence on a target object supported by a first target object by means of the humanoid component of the robot, so as to adjust the target object from lying supinely on the first target object to lying sideways on the first target object, comprises: The waist of the robot is tilted toward the direction corresponding to the target object so that the target object is within the action range of the robot; The first arm of the robot moves to the hip of the target object, and the second arm of the robot moves upward to the shoulder of the target object; The buttocks of the target object are used as the force point of the first arm of the robot, and the shoulder of the target object is used as the force point of the second arm of the robot. The first arm and the second arm are used to exert force on the target object to adjust the target object from lying on its back on the first target object to lying on its side on the first target object.

3. The method according to claim 2, characterized in that, The step of applying force to the target object by using the first arm and the second arm to adjust the target object from lying supinely on the first target object to lying sideways on the first target object includes: Applying a force to the target object away from the robot by the first arm and the second arm to adjust the target object from lying on its back to lying on its side with its back facing the robot; or A force acting on the target object toward the robot is applied by the first arm and the second arm to adjust the target object from lying on its back to lying on its side facing the robot.

4. The method according to claim 2, characterized in that, Before the waist of the robot is tilted toward the direction corresponding to the target object so that the target object is within the action range of the robot, the method further includes: The robot removes the obstacle items within the area where the target object is located; The front legs of the robot extend under the first target object to form a support structure; The robot places the arms of the target object on the chest of the target object; The robot adjusts the legs of the target object from a straight state to a bent state; Wherein, the bent state, the support structure, and the placement of the arms are used to keep the target object stable during the process of adjusting from lying on the back on the first target object to lying on the side on the first target object.

5. The method according to claim 1, characterized in that, The exerting force on the target object through the first arm and the second arm includes: Applying a force parallel to the plane of the legs of the target object and perpendicular to the legs of the target object to the upper hip of the target object through the first arm; Applying a force parallel to the plane of the body of the target object and perpendicular to the upper arm of the target object to the lower side of the shoulder of the target object through the second arm.

6. The method according to claim 1, characterized in that, Before the robot autonomously executes each action in the third action sequence on the target object supported by the first target object through the humanoid components of the robot to adjust the target object from sitting up on the first target object to sitting up on the second first target object, the method further includes: When the target object is not at the edge of the first target object, perform the following processing: Lift one side of the body of the target object through the humanoid components of the robot, move one side of the body of the target object towards the edge of the first target object, and place the target object on the first target object; Lift the other side of the body of the target object through the humanoid components of the robot, move the other side of the body of the target object towards the edge of the first target object, and place the target object on the first target object.

7. The method according to claim 6, characterized in that, The target object and the robot face each other; lifting one side of the body of the target object through the humanoid components of the robot includes: The first arm of the robot moves under the buttocks on one side of the target object, wherein the first arm and the one side belong to the opposite side; The second arm of the robot moves under the armpit on the other side of the target object; Apply an upward force to the target object through the two arms of the robot to lift one side of the body of the target object.

8. The method according to claim 1, characterized in that, The robot autonomously executes each action in the third action sequence on the target object supported by the first target object through the humanoid components of the robot to adjust the target object from sitting up on the first target object to sitting up on the second target object, including: The two arms of the robot respectively move under the armpits on both sides of the target object to lift the target object and leave the first target object; The robot performs a turning action so that the target object is directly above the second target object; The robot places the target object on the second target object.

9. The method according to claim 8, wherein, The method further includes: The robot's two arms move the second target object to the side of the first target object and form a right angle with the first target object. The robot stabilizes the second target object so that the second target object is in a stable state.

10. A method for processing actions of a robot, wherein, The method includes: The robot moves into the action range of the target object, where the target object is supported by the target object, and the action range is the area range where the robot can perform actions on the target object. Through the humanoid components of the robot, each action in the action sequence is autonomously performed on the target object in turn to adjust the target object from the first pose to the second pose on the target object. Wherein, each of the actions corresponds to a pose change of the target object, and the pose change from the first pose to the second pose is obtained based on multiple pose changes of the action sequence. The action sequence includes: the first arm of the robot moves to the upper hip of the target object; the second arm of the robot moves to the lower side of the shoulder of the target object; using the upper hip of the target object as the force application point of the first arm of the robot and the lower side of the shoulder of the target object as the force application point of the second arm of the robot, the first arm and the second arm exert force on the target object to adjust the target object from lying on its side on the first target object to sitting up on the first target object.

11. An apparatus for processing actions of a robot, wherein, The device includes: A movement module for the robot to move into the action range of the target object, where the target object is supported by the target object, and the action range is the area range where the robot can perform actions on the target object. A fourth action module for autonomously performing each action in the action sequence on the target object supported by the target object through the humanoid components of the robot to adjust the target object from the first pose to the second pose on the target object. Wherein, each of the actions corresponds to a pose change of the target object, and the pose change from the first pose to the second pose is obtained based on multiple pose changes of the action sequence. The action sequence includes: the first arm of the robot moves to the upper hip of the target object; the second arm of the robot moves to the lower side of the shoulder of the target object; using the upper hip of the target object as the force application point of the first arm of the robot and the lower side of the shoulder of the target object as the force application point of the second arm of the robot, the first arm and the second arm exert force on the target object to adjust the target object from lying on its side on the first target object to sitting up on the first target object.

12. An apparatus for processing actions of a robot, wherein, The device includes: A first action module for autonomously performing each action in the first action sequence on the target object supported by the first target object through the humanoid components of the robot to adjust the target object from lying on its back on the first target object to lying on its side on the first target object. The second action module is used to move the first arm of the robot to the upper hip of the target object; move the second arm of the robot to the lower side of the shoulder of the target object; use the upper hip of the target object as the force application point of the first arm of the robot, and use the lower side of the shoulder of the target object as the force application point of the second arm of the robot, and apply force to the target object through the first arm and the second arm to adjust the target object from lying on its side on the first target object to sitting up on the first target object; The third action module is used to autonomously execute each action in the third action sequence on the target object supported by the first target object through the humanoid component of the robot, so as to adjust the target object from sitting up on the first target object to sitting up on the second target object; Wherein, the second target object is an object different from the first target object, each of the actions corresponds to a posture change of the target object, and each adjustment of the target object is obtained based on multiple posture changes of the corresponding action sequence.

13. A robot, wherein, The robot includes: a humanoid component and a controller; The controller is used to control the humanoid component to execute the action processing method of the robot according to any one of claims 1 to 9 or claim 10.

14. An electronic device for controlling a robot, wherein, The electronic device includes: A memory for storing computer-executable instructions; A processor, when executing the computer-executable instructions stored in the memory, controls the robot to implement the action processing method of the robot according to any one of claims 1 to 9 or claim 10.

15. A computer-readable storage medium storing computer-executable instructions, wherein, When the computer-executable instructions are executed by the processor, the action processing method of the robot according to any one of claims 1 to 9 or claim 10 is implemented.

16. A computer program product comprising computer-executable instructions, wherein, When the computer-executable instructions are executed by the processor, the action processing method of the robot according to any one of claims 1 to 9 or claim 10 is implemented.

Images