Human-machine cooperation method and related device based on human intention estimation and impedance adjustment

Abstract

The invention discloses a human-machine cooperation method based on human intention estimation and impedance adjustment and a related device. The human-machine cooperation method comprises the steps that multi-mode sensing signals of a robot tail end and human operation are acquired; inputting the multi-modal sensing signals of the robot tail end and the human operation into a human intention estimator to obtain a real-time human intention estimation result; inputting the real-time human intention estimation result into an adaptive force coupling enhanced dynamic motion primitive module to generate an expected motion track and a stiffness parameter; and the expected movement track and the rigidity parameter are input into an auxiliary impedance controller, the rigidity and the damping coefficient of the robot are adjusted through the auxiliary impedance controller, and the method and the related device can effectively improve the cooperation ability, the environment adaptability and the interaction safety of a robot system.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of robot control and human-computer interaction, and relates to a human-robot collaboration method based on human intention estimation and impedance adjustment and a related device. BACKGROUND

[0002] With the wide deployment of human-robot collaboration systems in human-robot hybrid workspaces, especially in key fields such as high-end manufacturing, medical rehabilitation, and service robots, robots not only need to have precise action execution capabilities, but also must be able to understand human intentions and carry out natural and efficient physical collaboration with humans. In practical applications, collaboration tasks often involve irregular and complex operation surfaces, such as curved surface assembly, flexible material handling, and irregular part handling, etc. These tasks put high demands on the environmental adaptability, motion flexibility, and force regulation capability of robots. Especially in unstructured environments, robots must be able to dynamically adjust their behavior strategies according to human operation feedback under unknown or changing physical interaction conditions to ensure the accuracy, stability of task completion, and safety of human-robot interaction.

[0003] However, existing human-robot collaboration methods still have significant limitations in several key technical aspects. First, traditional systems often rely on static models or fixed rules for human intention recognition, which cannot fully extract the subtle differences in human intention changes from multi-modal perception data, resulting in poor robot reaction and adaptability, making it difficult to perform collaboration tasks that require high-frequency action responses. Second, during task execution, the trajectory planning and control parameters of the robot are usually based on predefined templates, lacking the ability to generalize to dynamic environmental changes. Especially when the interaction force pattern changes or the contact condition is disturbed, the robot cannot simultaneously adjust key control dimensions such as trajectory, time, and stiffness, causing rigidity and instability in collaboration behavior. In addition, most existing impedance control strategies use fixed parameters or offline adjustment methods, lacking the ability to dynamically "assist on demand" according to changes in human intentions, which not only affects the smoothness of interaction, but also may apply excessive or insufficient assistance force at inappropriate times, reducing the naturalness and efficiency of human-robot interaction.

[0004] Furthermore, current skill learning mechanisms are mostly single-level imitation learning or strategy fitting, lacking systematic hierarchical structure and long-term experience accumulation mechanism, limiting the robot's transfer learning ability and self-adaptation level in multi-task, multi-scene environments. Therefore, in human-robot collaboration tasks involving complex irregular surfaces, it is urgent to build a unified control framework with dynamic intention perception, adaptive trajectory and impedance regulation capability, which can realize motion skill incremental learning and generalization in different interaction situations according to human guidance, thereby effectively improving the collaboration ability, environmental adaptability, and interaction safety of the robot system. SUMMARY

[0005] The present application aims to overcome the above-mentioned shortcomings of the prior art, and provides a human-robot collaboration method based on human intention estimation and impedance adjustment and a related device, which can effectively improve the collaboration ability, environmental adaptability and interaction safety of a robot system.

[0006] To achieve the above-mentioned purpose, the present application discloses a human-robot collaboration method based on human intention estimation and impedance adjustment, comprising:

[0007] obtaining multi-modal sensing signals of a robot end and human operation;

[0008] inputting the multi-modal sensing signals of the robot end and human operation into a human intention estimator to obtain real-time human intention estimation results;

[0009] inputting the real-time human intention estimation results into an adaptive force-coupled enhanced dynamic motion primitive module to generate expected motion trajectories and stiffness parameters;

[0010] inputting the expected motion trajectories and stiffness parameters into an auxiliary impedance controller to adjust the stiffness and damping coefficient of the robot through the auxiliary impedance controller.

[0011] The human-robot collaboration method based on human intention estimation and impedance adjustment of the present application is further improved in that:

[0012] Further, the multi-modal sensing signals of the robot end and human operation include the position, velocity, acceleration of the robot end effector and the end contact force information during human collaborative operation.

[0013] Further, the human intention estimator is constructed based on a Transformer architecture.

[0014] Further, the process of inputting the multi-modal sensing signals of the robot end and human operation into the human intention estimator to obtain real-time human intention estimation results is:

[0015] inputting the multi-modal sensing signals of the robot end and human operation into the human intention estimator, the human intention estimator capturing the changes and trends of human action intention through time series modeling and multi-modal feature fusion to obtain real-time human intention estimation results, the real-time human intention estimation results including expected trajectories, expected trajectory speed requirements and task stages.

[0016] Further, the process of inputting the real-time human intention estimation results into the adaptive force-coupled enhanced dynamic motion primitive module to generate expected motion trajectories and stiffness parameters is:

[0017] The real-time human intention estimation result is input into an adaptive force-coupled enhanced dynamic motion primitive module, the adaptive force-coupled enhanced dynamic motion primitive module adds a proportional gain modulation factor and a force coupling term on the basis of a dynamic motion primitive, so that the trajectory and stiffness coding respond to the change of the external interaction force, and the expected motion trajectory and stiffness parameter are obtained.

[0018] Further, the process of inputting the expected motion trajectory and stiffness parameter into the auxiliary impedance controller to adjust the stiffness and damping coefficient of the robot by the auxiliary impedance controller is as follows:

[0019] The expected motion trajectory and stiffness parameter are input into the auxiliary impedance controller, and the auxiliary impedance controller adopts an iterative optimization algorithm to combine a cost function to feedback adjust the stiffness and damping coefficient of the robot.

[0020] The application discloses a human-robot cooperation system based on human intention estimation and impedance adjustment, which comprises:

[0021] A sensing module is used to acquire multi-modal sensing signals of a robot end and human operation.

[0022] An intention estimation module is used to input the multi-modal sensing signals of the robot end and human operation into a human intention estimator to obtain a real-time human intention estimation result.

[0023] A generation module is used to input the real-time human intention estimation result into an adaptive force-coupled enhanced dynamic motion primitive module to generate an expected motion trajectory and stiffness parameter.

[0024] A control module is used to input the expected motion trajectory and stiffness parameter into an auxiliary impedance controller to adjust the stiffness and damping coefficient of the robot by the auxiliary impedance controller.

[0025] The human-robot cooperation system based on human intention estimation and impedance adjustment has the further improvement that:

[0026] Further, the multi-modal sensing signals of the robot end and human operation comprise position, velocity, acceleration of a robot end effector and end contact force information during human cooperation operation.

[0027] The application discloses a computer device, which comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the human-robot cooperation method based on human intention estimation and impedance adjustment when executing the computer program.

[0028] The application discloses a computer readable storage medium, which stores a computer program.

[0029] The application has the following beneficial effects:

[0030] The human intention estimation and impedance adjustment based man-machine cooperation method and the related device have the advantages that human intention recognition, adaptive trajectory generation and on-demand impedance adjustment are fused to improve the cooperation ability, environmental adaptability and interaction safety of a robot system, specifically, human intention is estimated first, and then expected motion trajectory and stiffness parameters are generated according to the human intention, and then the stiffness and damping coefficient of the robot are adjusted by using an auxiliary impedance controller according to the expected motion trajectory and the stiffness parameters, so that the method is simple to operate and has high practicability, and the method breaks through the multiple technical bottlenecks of a traditional man-machine cooperation system in adaptability, safety and intelligence, is particularly suitable for a robot physical interaction cooperation task in an irregular and unstructured surface scene, and has wide engineering application prospects and industrial promotion value. BRIEF DESCRIPTION OF DRAWINGS

[0031] The accompanying drawings, which form a part of the specification, are included to provide a further understanding of the application and are incorporated herein in conjunction with the description of the application. The drawings are as follows:

[0032] Figure 1 is a schematic diagram of the application;

[0033] Figure 2 is an architecture diagram of the human intention estimator;

[0034] Figure 3 is an architecture diagram of the adaptive force-coupled enhanced dynamic motion primitive module;

[0035] Figure 4 is a system structure diagram of the application. DETAILED DESCRIPTION

[0036] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are some of the embodiments of the application but not all the embodiments of the application. Based on the embodiments in the application, all the other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the application.

[0037] In the description of the present application, it is to be understood that the terms "including", "comprising", "having" and "encompassing" mean that there are additions to the described features, integers, steps, operations, elements, components, and / or groups thereof that are not specifically recited. The terms "comprising" and "including" are to be construed open-ended, in that they allow for the addition of one or more features, integers, steps, operations, elements, components, and / or groups thereof.

[0038] It should also be understood that the terms used in the present specification and claims are not to be interpreted as limiting the present application. The singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

[0039] It will be further understood that the terms "and / or", "including" and "comprising" when used in this specification, specify the presence of features, integers, steps, operations, elements, components and / or groups thereof, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0040] It should be understood that, although the terms first, second, third, etc. can be used herein to describe various ranges or elements, these ranges or elements should not be limited by these terms. These terms are only used to distinguish one range or element from another. For example, a first range could be termed a second range without departing from the scope of the example embodiments. Similarly, it will be understood that, when an element is referred to as being "on" another element, it can be directly on the element, or it can be indirectly on the element with one or more intervening elements interposed therebetween.

[0041] Depending on the context, the word "if" as used herein can be interpreted to mean "when" or "upon" or "in response to determining" or "in response to detecting." Similarly, the phrase "if it is determined" or "if [a stated condition or event] is detected" can be interpreted to mean "upon determining" or "in response to determining" or "upon detecting [the stated condition or event]" or "in response to detecting [the stated condition or event]."

[0042] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0043] Various structural schematic diagrams according to the disclosed embodiments of the present application are shown in the drawings. These diagrams are not drawn to scale, in which some details are exaggerated for the purpose of clear expression, and some details can be omitted. The shapes of various regions, layers and their relative sizes and positional relationships shown in the drawings are only exemplary, and in actuality, there can be deviations due to manufacturing tolerances or technical limitations, and regions / layers with different shapes, sizes and relative positions can be additionally designed by those skilled in the art according to actual needs.

[0044] Embodiment one

[0045] With reference to Figure 1 , Figure 2 and Figure 3 , the human-machine cooperation method based on human intention estimation and impedance adjustment disclosed in the present application comprises the following steps:

[0046] 1) System initialization and demonstration acquisition;

[0047] Before the start of the cooperation task, the robot system is first in an initialization state, and through a demonstration operation, a human operator directly guides the robot to complete a series of basic motion trajectories, and at the same time, corresponding interactive force sensing data is acquired, which includes the position, velocity, acceleration of the robot end effector and the end contact force information for human cooperation operation, and a basic motion pattern library and a stiffness adjustment model are constructed therefrom, laying a data foundation for subsequent skill learning and generalization.

[0048] During the data acquisition process, the present application uses high-precision force sensors / torque sensors and visual or inertial measurement units to synchronously record the multi-modal information of human demonstration actions, ensuring the integrity and accuracy of the acquired data. At the same time, the demonstration process can be iterated multiple times, and the action trajectory and interactive force distribution are gradually improved in combination with operator feedback.

[0049] 2) Real-time estimation of human intention;

[0050] ​The human intention estimator is constructed by using a Transformer architecture, and multi-modal sensing signals of a robot end and human operation are obtained, the multi-modal sensing signals including position, velocity, acceleration and interaction force of the robot end effector.

[0051] It should be noted that the human intention recognizer using the Transformer architecture of the application extracts time-dependent features from motion and force signals in real time, realizes dynamic prediction of human operation intention, and drives adjustment of robot behavior strategy combined with the estimation result.

[0052] 3) generating a desired motion trajectory and stiffness parameter;

[0053] The real-time human intention estimation result is input into the adaptive force-coupled enhanced dynamic motion primitive module to dynamically generate a desired motion trajectory and stiffness parameter.

[0054] It should be noted that the adaptive force-coupled enhanced dynamic motion primitive module adds a proportional gain modulation factor and a force coupling term on the basis of a dynamic motion primitive, so that the trajectory and stiffness code can respond to changes in external interaction force, realizing synchronous generalization of position, time and stiffness. The adaptive force-coupled enhanced dynamic motion primitive module uses a generalized learning system to realize efficient generalization, can autonomously adjust the motion mode according to different task environments and interaction conditions, and adapt to diversified operation requirements. The adaptive force-coupled enhanced dynamic motion primitive module ensures that the robot can stably and smoothly complete the specified action on a complex curved surface and a non-structural target.

[0055] It should be noted that the adaptive force-coupled enhanced dynamic motion primitive module realizes robustness enhancement of interaction force disturbance by introducing a proportional gain modulation term and a force coupling term, and uses a generalized learning system to improve generalization speed and accuracy, so that synchronous generalization can be realized under different surface morphologies and interaction conditions.

[0056] 4) real-time adjustment of the stiffness and damping coefficient of the robot;

[0057] The desired motion trajectory and stiffness parameter are input into the auxiliary impedance controller, and the stiffness and damping coefficient of the robot are adjusted by the auxiliary impedance controller.

[0058] The auxiliary impedance controller adopts an iterative optimization algorithm, combines a cost function, adjusts the stiffness and damping coefficient of the robot through feedback, ensures sensitive response of the robot to human actions, avoids discomfort and safety hazards caused by excessive rigidity, and enables the robot to automatically adjust the assisting degree in different task stages, so that more natural and intelligent collaborative behaviors are realized.

[0059] Compared with the traditional static impedance control, the auxiliary impedance controller adopts a target function and an iterative updating mechanism, supports dynamic adjustment of the assisting degree of the robot to human operations according to actual interaction requirements, realizes collaborative behaviors that neither excessively intervene nor are delayed in response, and further enables the impedance controller to be deeply integrated with the adaptive force-coupled enhanced dynamic motion primitive module, so that the system can realize rapid adaptation to external disturbances and task changes in three dimensions of posture, time and stiffness.

[0060] It should be noted that the present application supports a 'teaching-learning' mode, and the robot continuously updates its skill library through continuous teaching guidance of humans. The incremental learning mechanism allows the system to realize progressive adjustment and optimization of trajectories and stiffness parameters on the basis of existing data, combined with new demonstration data, and improves the adaptability to new tasks and complex environments. This mechanism promotes continuous accumulation and migration of robot skills, so that the robot can still quickly generalize existing skills when facing unseeable non-structured surfaces or sudden environmental changes, and ensures stable execution of collaborative tasks.

[0061] The present application can dynamically adjust the motion trajectory according to the real-time estimated human intention, realize high-softness physical interaction, the impedance controller effectively avoids task failure or safety hazards caused by excessive rigidity, and the adaptive force-coupled enhanced dynamic motion primitive module can ensure the stability and continuity of motion, so that the overall collaborative efficiency, operation precision and safety are significantly better than those of the traditional fixed impedance and non-adaptive control scheme.

[0062] Embodiment two

[0063] Reference Figure 4 The human-machine collaborative system based on human intention estimation and impedance adjustment provided by the present application comprises:

[0064] A sensing module is configured to acquire multi-modal sensing signals of a robot end and human operation.

[0065] An intention estimation module is configured to input the multi-modal sensing signals of the robot end and human operation into a human intention estimator to obtain a real-time human intention estimation result.

[0066] A generation module is configured to input the real-time human intention estimation result into an adaptive force-coupled enhanced dynamic motion primitive module to generate a desired motion trajectory and stiffness parameter.

[0067] A control module is configured to input the expected motion trajectory and the stiffness parameter into an auxiliary impedance controller, and adjust the stiffness and damping coefficient of the robot through the auxiliary impedance controller.

[0068] In the embodiment, the multimodal sensing signals of the robot end and the human operation include position, velocity, acceleration of the robot end effector, and end contact force information of the human collaborative operation.

[0069] The division of the modules in the embodiments of the present application is illustrative, and is merely a logical function division. In actual implementation, another division manner can be used. In addition, each function module in each embodiment of the present application can be integrated in one processor, or can be physically separated, or two or more modules can be integrated in one module. The integrated module can be implemented in the form of hardware or in the form of a software function module.

[0070] Embodiment three

[0071] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the human-intention-estimation-based and impedance-adjustment-based human-robot collaborative method are implemented, for example, including: acquiring multimodal sensing signals of a robot end and human operation; inputting the multimodal sensing signals of the robot end and human operation into a human-intention estimator to obtain real-time human-intention estimation results; inputting the real-time human-intention estimation results into a self-adaptive force-coupling-enhanced dynamic motion primitive module to generate an expected motion trajectory and a stiffness parameter; and inputting the expected motion trajectory and the stiffness parameter into an auxiliary impedance controller to adjust the stiffness and damping coefficient of the robot through the auxiliary impedance controller. The memory can include an internal memory, for example, a high-speed random access memory, and can also include a non-volatile memory, for example, at least one disk memory. The processor, network interface, and memory are connected to each other through an internal bus, which can be an industry standard architecture bus, a peripheral component interconnect standard bus, an extended industry standard architecture bus, etc. The bus can be divided into an address bus, a data bus, and a control bus. The memory is used to store programs, and specifically, the programs can include program codes, and the program codes include computer operation instructions. The memory can include an internal memory and a non-volatile memory, and provide instructions and data to the processor.

[0072] Embodiment four

[0073] A computer readable storage medium stores a computer program, the computer program is executed by a processor to implement steps of the human intention estimation based impedance adjustment human-robot cooperation method, for example, including: acquiring a robot end and a human operation multi-modal sensing signal; inputting the robot end and the human operation multi-modal sensing signal into a human intention estimator to obtain a real-time human intention estimation result; inputting the real-time human intention estimation result into an adaptive force-coupled enhanced dynamic motion primitive module to generate a desired motion trajectory and a stiffness parameter; and inputting the desired motion trajectory and the stiffness parameter into an auxiliary impedance controller to adjust a stiffness and a damping coefficient of the robot by the auxiliary impedance controller. Specifically, the computer readable storage medium includes, but is not limited to, for example, a volatile memory and / or a non-volatile memory. The volatile memory can include a random access memory (RAM) and / or a cache memory, etc. The non-volatile memory can include a read-only memory (ROM), a hard disk, a flash memory, an optical disc, a magnetic disc, etc.

[0074] Those skilled in the art will appreciate that embodiments of the application can be supplied as a method, a system, or a computer program product. Accordingly, the application can be embodied in the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the application can be embodied in the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk memory, CD-ROMs, optical storage media, etc.) having computer usable program code embodied therein.

[0075] The application is described with reference to the flowcharts and / or block diagrams of the methods, apparatus (systems), and computer program products according to embodiments of the application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions, which are executed via the processor of the computer or other programmable data processing apparatus, generate a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in a flow or multiple flows and / or blocks Figure 1 The apparatus that implements the functions specified in a flow or multiple flows and / or blocks.

[0076] These computer program instructions can also be stored in a computer readable storage medium that can direct a computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer readable storage medium produce a product including an instruction apparatus, which implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in a flow or multiple flows and / or blocks Figure 1the function specified in one or more blocks.

[0077] These computer program instructions can also be loaded into computer or other programmable data processing devices, so that a series of operation steps are performed on the computer or other programmable data processing devices to generate computer-implemented processes, thus the instructions executed on the computer or other programmable data processing devices provide processes for implementing the flows Figure 1 one or more flows and / or blocks Figure 1 the function specified in one or more blocks.

[0078] Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. It is intended that the present application cover any and all variations of the application that come within the scope of the present application. The specification and examples given are intended as illustrative only and not in a limiting sense, as the true scope of the present application is indicated by the following claims.

[0079] It is to be understood that the application is not limited to the precise construction described and as shown in the attached drawings, and that various modifications and changes can be made by those skilled in the art without departing from the scope of the present application. The scope of the application is limited only by the claims that follow.

[0080] The above description is only preferred embodiments of the present application, not any limitation thereto, any simple modification, change and equivalent structural change made according to the technical essence of the present application to the above embodiments are still within the protection scope of the technical solution of the present application.

Claims

1. A human-machine collaboration method based on human intention estimation and impedance adjustment, characterized in that: include: Acquire multimodal sensor signals from the robot end and human operation; Inputting multimodal sensor signals of the robot end and human operation into a human intention estimator to obtain real-time human intention estimation results; Inputting the real-time human intention estimation result into the adaptive force coupling enhanced dynamic motion primitive module to generate the desired motion trajectory and stiffness parameters; The desired motion trajectory and stiffness parameters are input into the auxiliary impedance controller, and the stiffness and damping coefficient of the robot are adjusted by the auxiliary impedance controller.

2. The human-machine collaboration method based on human intention estimation and impedance adjustment according to claim 1, characterized in that: The multimodal sensing signals of the robot end and human operation include the position, velocity, acceleration of the robot end effector and the end contact force information of the collaborative operation with the human.

3. The human-machine collaboration method based on human intention estimation and impedance adjustment according to claim 1, characterized in that: The human intention estimator is built on the Transformer architecture.

4. The human-machine collaboration method based on human intention estimation and impedance adjustment according to claim 1, characterized in that: The multimodal sensor signals of the robot end and human operation are input into the human intention estimator to obtain the real-time human intention estimation result as follows: The multimodal sensor signals of the robot end and human operation are input into the human intention estimator. The human intention estimator captures the changes and trends of human action intentions through time series modeling and multimodal feature fusion, and obtains real-time human intention estimation results. The real-time human intention estimation results include the expected trajectory, the expected trajectory speed requirement and the task stage.

5. The human-machine collaboration method based on human intention estimation and impedance adjustment according to claim 1, characterized in that: The process of inputting the real-time human intention estimation result into the adaptive force coupling enhanced dynamic motion primitive module to generate the desired motion trajectory and stiffness parameters is as follows: The real-time human intention estimation result is input into the adaptive force coupling enhanced dynamic motion primitive module. Based on the dynamic motion primitive, the adaptive force coupling enhanced dynamic motion primitive module adds a proportional gain modulation factor and a force coupling term, so that the trajectory and stiffness encoding respond to changes in external interaction forces, thereby obtaining the desired motion trajectory and stiffness parameters.

6. The human-machine collaboration method based on human intention estimation and impedance adjustment according to claim 1, characterized in that: The process of inputting the desired motion trajectory and stiffness parameters into the auxiliary impedance controller and adjusting the stiffness and damping coefficient of the robot by the auxiliary impedance controller is as follows: The desired motion trajectory and stiffness parameters are input into the auxiliary impedance controller, which uses an iterative optimization algorithm combined with a cost function to feedback-adjust the stiffness and damping coefficient of the robot.

7. A human-machine collaboration system based on human intention estimation and impedance adjustment, characterized in that: include: The sensing module is used to obtain multimodal sensing signals from the robot end and human operation; An intention estimation module is used to input the multimodal sensor signals of the robot end and human operation into a human intention estimator to obtain real-time human intention estimation results; A generation module, configured to input the real-time human intention estimation result into an adaptive force coupling enhanced dynamic motion primitive module to generate a desired motion trajectory and stiffness parameters; The control module is used to input the desired motion trajectory and stiffness parameters into the auxiliary impedance controller, and adjust the stiffness and damping coefficient of the robot through the auxiliary impedance controller.

8. The human-machine collaboration system based on human intention estimation and impedance adjustment according to claim 7, characterized in that: The multimodal sensing signals of the robot end and human operation include the position, velocity, acceleration of the robot end effector and the end contact force information of the collaborative operation with the human.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the human-machine collaboration method based on human intention estimation and impedance adjustment as described in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the human-machine collaboration method based on human intention estimation and impedance adjustment as described in any one of claims 1 to 6 are implemented.

Images