A Human-Computer Interaction Control Method, Device and Apparatus with Mode Self-Switching

Abstract

The present invention provides a mode self-switching human-computer interaction control method, device and apparatus. The control method includes: obtaining the operation information of a human-computer interaction device, including force information and the current operation mode, wherein the force information includes non-interaction force information; constructing a force model based on the force information; compensating the force model based on the non-interaction force information to obtain interaction force information; processing the interaction force information through a fuzzy inference system to obtain an evaluation index; determining a target operation mode based on the current operation information and status information, where the status information includes at least one of the operation information and the evaluation index; and controlling the operation of the human-computer interaction device according to the target operation mode. By obtaining the operation information to construct a force model to obtain interaction force information, and making a judgment based on the evaluation index obtained from the fuzzy inference system to determine the target operation mode, the present invention achieves the purpose of automatically switching a reasonable operation mode as needed according to the actual situation of the user to improve the interaction effect.

Description

Technical Field

[0001] The present invention relates to the technical field of robots, and in particular, to a human-computer interaction control method, device and apparatus with self-switching modes. Background Art

[0002] With the acceleration of the aging process in China, the number of people with movement disorders is increasing continuously. Existing research shows that this kind of people can improve muscle strength and movement coordination through a large number of repeated function-oriented movement trainings. However, the effect of simple and continuous passive training therapy in improving movement function is still limited, and the active participation of users is considered to be one of the key factors promoting neuroplasticity and movement recovery. With the continuous development of robot intelligence, robot-assisted movement devices for assisting people with movement disorders in movement training have emerged as the times require.

[0003] However, most current control strategies for robot-assisted movement are relatively single. Although some movement training robots are set with active and passive modes for users to select in advance, as mentioned above, the effect of simple and continuous passive training mode in improving movement function is still limited, and it is difficult for users to adhere to the continuous active training mode in the case of movement disorders, resulting in a decline in the active participation of users and an inability to adjust a reasonable training mode according to the actual situation of users, leading to an unsatisfactory effect in the final human-computer interaction training. Summary of the Invention

[0004] The problem solved by the present invention is to provide a control method, device and apparatus that can automatically switch a reasonable operation mode according to the actual situation of users to improve the human-computer interaction effect.

[0005] To solve the above problems, the present invention provides a human-computer interaction control method with self-switching modes, including the following steps:

[0006] Obtain the operation information of the human-computer interaction device, where the operation information includes force information and the current operation mode, and the force information includes non-interaction force information;

[0007] Construct a force model of the human-computer interaction device based on the force information;

[0008] Compensate the force model based on the non-interaction force information to obtain interaction force information;

[0009] Process the interaction force information through a fuzzy inference system to obtain an evaluation index;

[0010] Determine the target operation mode based on the current operation mode and status information, where the status information includes at least one of the operation information and the evaluation index;

[0011] Control the operation of the human - machine interaction device according to the target operation mode.

[0012] Optionally, the current operation mode includes a passive training mode and an assisted training mode; determining the target operation mode based on the current operation mode and status information includes:

[0013] When the current operation mode is the passive training mode, perform a first - mode judgment based on the evaluation index and the operation information to obtain a first judgment result, and determine the target operation mode based on the first judgment result;

[0014] When the current operation mode is the assisted training mode, perform a second - mode judgment based on the operation information to obtain a second judgment result, and determine the target operation mode based on the second judgment result.

[0015] Optionally, the operation information further includes time information; when the current operation mode is the passive training mode, performing a first - mode judgment based on the evaluation index and the operation information to obtain a first judgment result, and determining the target operation mode based on the first judgment result includes:

[0016] When the current operation mode is the passive training mode, judge whether the evaluation index is greater than a preset first threshold;

[0017] If the evaluation index is greater than the first threshold, then judge whether the integral of the evaluation index with respect to the time information is greater than a preset integral threshold;

[0018] If the integral information is greater than the integral threshold, then determine the assisted training mode as the target operation mode.

[0019] Optionally, the operation information further includes speed information; when the current operation mode is the assisted training mode, performing a second - mode judgment based on the operation information to obtain a second judgment result, and determining the target operation mode based on the second judgment result includes:

[0020] When the current operation mode is the assisted training mode, judge whether the speed information is less than or equal to a preset second threshold;

[0021] If the speed information is less than or equal to the second threshold, then judge whether the time information is greater than a preset time threshold, where the time information includes the duration during which the speed information is less than or equal to the second threshold;

[0022] If the time information is greater than the time threshold, then determine the passive training mode as the target operation mode.

[0023] Optionally, before processing the interaction force information through the fuzzy inference system to obtain the evaluation index, the following steps are further included:

[0024] Obtain historical interaction force information;

[0025] Obtain the historical interaction force and the historical interaction force change rate based on the historical interaction force information;

[0026] Obtain the membership function based on the historical interaction force and the historical interaction force change rate;

[0027] Determine the fuzzy inference rules according to the preset ranges of the historical interaction force and the historical interaction force change rate;

[0028] Construct the fuzzy inference system based on the membership function and the fuzzy inference rules.

[0029] Optionally, the historical interaction force information includes:

[0030] The historical interaction force information in the no-load situation in the passive training mode;

[0031] The historical interaction force information in the situation where the load does not exert force in the passive training mode;

[0032] The historical interaction force information in the situation where the load moves along an arbitrary trajectory in the assisted training mode.

[0033] Optionally, the assisted training mode is constructed based on a potential energy field, and the potential energy at any point on the potential energy field is positively correlated with the distance between the point and a preset target motion trajectory. Among them, the target motion trajectory is a closed curve, and the potential energy on the target motion trajectory is equal everywhere.

[0034] Compared with the prior art, the present invention obtains the operation information of the human-computer interaction device, including the force information and the current operation mode. Among them, the force information includes non-interaction force information. A force model of the human-computer interaction device is constructed based on the force information to accurately describe the force condition of the human-computer interaction device. The force model is compensated based on the non-interaction force information to obtain the interaction force information, avoiding the influence of the non-interaction force caused by the factors of the human-computer interaction device itself on the accuracy of the interaction force expression. And the evaluation index is obtained by processing the interaction force information through a fuzzy inference system. The evaluation index reflects the human-computer interaction situation, such as the situation of the user's active participation degree, converting the fuzzy language of the user's active participation degree into a quantifiable parameter. Then, the target operation mode is determined based on the current operation mode and the state information, where the state information includes at least one of the operation information and the evaluation index. The operation information and the evaluation index can reflect the actual use situation and the movement training state of the user. Based on this, determining the target operation mode improves the rationality and accuracy of the mode switching. Finally, the operation of the human-computer interaction device is controlled according to the target operation mode, achieving the purpose of automatically switching to a reasonable operation mode as needed according to the actual training situation of the user to improve the human-computer interaction effect.

[0035] The present invention also provides a human-computer interaction device with automatic mode switching, which includes: a host computer, a slave computer, a transmission component, and a detection component. The host computer is applied to the automatic mode switching human-computer interaction control method as described above. The transmission component is arranged on the slave computer. The slave computer is used to control the movement of the transmission component according to the instruction sent by the host computer. The detection component is used to detect the operation information of the transmission component and send the operation information to the host computer.

[0036] Optionally, the transmission component includes a rocker and a tray, the detection component includes a force sensor. The rocker is provided with a first connection end and a second connection end. The first connection end is rotatably connected to the tray, and the second connection end is rotatably connected to the slave computer. The force sensor is fixedly connected to the rocker.

[0037] The advantages of the human-computer interaction device with automatic mode switching and the automatic mode switching human-computer interaction control method of the present invention compared with the prior art are the same, and will not be elaborated here.

[0038] The present invention also provides an automatic mode switching human-computer interaction device, including:

[0039] An acquisition module, which is used to acquire the operation information of the human-computer interaction device. The operation information includes force information and the current operation mode. Among them, the force information includes non-interaction force information;

[0040] A modeling module, which is used to construct a force model of the human-computer interaction device based on the force information;

[0041] A compensation module, which is used to compensate the force model based on the non-interactive force information to obtain interactive force information;

[0042] An inference module, which is used to process the interactive force information through a fuzzy inference system to obtain evaluation indexes;

[0043] A mode determination module, which is used to determine a target operation mode based on the current operation mode and status information, where the status information includes at least one of the operation information and the evaluation indexes;

[0044] A control module, which is used to control the operation of the human-computer interaction device according to the target operation mode.

[0045] The human-computer interaction device with automatic mode switching and the human-computer interaction control method with automatic mode switching according to the present invention have the same advantages as the prior art, which will not be elaborated here. Description of the Drawings

[0046] Figure 1 It is a flowchart of the human-computer interaction control method with automatic mode switching according to an embodiment of the present invention;

[0047] Figure 2 It is a flowchart after refining step S500 of the human-computer interaction control method with automatic mode switching according to an embodiment of the present invention;

[0048] Figure 3 It is another flowchart after refining step S500 of the human-computer interaction control method with automatic mode switching according to an embodiment of the present invention;

[0049] Figure 4 It is a flowchart after refining step S400 of the human-computer interaction control method with automatic mode switching according to an embodiment of the present invention;

[0050] Figure 5 It is a fuzzy inference rule table of the human-computer interaction control method with automatic mode switching according to an embodiment of the present invention;

[0051] Figure 6 It is a schematic diagram of the membership function of the human-computer interaction control method with automatic mode switching according to an embodiment of the present invention;

[0052] Figure 7 It is another schematic diagram of the membership function of the human-computer interaction control method with automatic mode switching according to an embodiment of the present invention;

[0053] Figure 8 It is yet another schematic diagram of the membership function of the human-computer interaction control method with automatic mode switching according to an embodiment of the present invention. Detailed Embodiments

[0054] To make the above objects, features, and advantages of the present invention more apparent and understandable, the following provides a detailed description of specific embodiments of the present invention in conjunction with the accompanying drawings. Although certain embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as limited to the embodiments described herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present invention. It should be understood that the drawings and embodiments of the present invention are only for exemplary purposes and are not used to limit the protection scope of the present invention.

[0055] It should be understood that the various steps described in the method embodiments of the present invention can be executed in different orders and / or executed in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this regard.

[0056] As used herein, the term "comprising" and its variations are open-ended, that is, "including but not limited to". The term "based on" is "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments"; the term "optionally" means "optional embodiments". The relevant definitions of other terms will be given in the following description. It should be noted that the concepts such as "first" and "second" mentioned in the present invention are only used to distinguish different devices, modules, or units, and are not used to limit the order of functions performed by these devices, modules, or units or their interdependent relationships.

[0057] It should be noted that the modifications of "one" and "multiple" mentioned in the present invention are illustrative rather than restrictive. Those skilled in the art should understand that unless clearly stated otherwise in the context, it should be understood as "one or more".

[0058] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by terms such as "upper" and "lower" is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention.

[0059] As Figure 1 shown, an embodiment of the present invention provides a mode self-switching human-computer interaction control method, including the following steps:

[0060] S100: Obtain the operation information of the human-computer interaction device. The operation information includes force information and the current operation mode, where the force information includes non-interaction force information.

[0061] Specifically, the operation information of the human-computer interaction device, including the force information, is obtained. This step can be achieved by an information collection device, such as using a force sensor, a pressure sensor, or a speed sensor to obtain the operation information of the human-computer interaction device; wherein the force information includes non-interactive force information, such as non-interactive force information caused by the weight of the device's own structure. The operation information obtained also includes the current operation mode. For example, in order to meet the needs of different users with different motor abilities, human-computer interaction devices usually design a variety of operation modes, such as a passive training mode for users with poor motor abilities or an assisted training mode for users with good motor abilities; at the same time, it should be understood that the current operation mode includes but is not limited to the initial operation mode of the human-computer interaction device. When the device is turned on, the current operation mode obtained for the first time is the initial mode, and the current operation mode obtained again after the power-on is the current actual operation mode of the device; wherein, the initial operation mode of the device can be customized according to the actual situation, or a mode can be randomly selected as the initial operation mode.

[0062] Optionally, the operation information of the human-computer interaction device can be obtained by measuring the user's force using an instrument. For example, the user's force can be obtained by measuring the user's electromyographic parameters using an instrument, which can reflect the force information of the human-computer interaction device.

[0063] In this embodiment, by obtaining the operating information of the human-computer interaction device, such as force information, a data basis is provided for subsequent analysis of the operating information and making appropriate decisions.

[0064] S200: Constructing a force model of the human-computer interaction device based on the force information.

[0065] Specifically, the force information of the human-computer interaction device mainly includes three parts: the first part is mainly the gravity generated by the interactive device due to its own structure, the second part is mainly the gravity generated by the user's own limbs, and the third part is mainly the interaction force between the user and the device. Based on this, the force model of the human-computer interaction device is constructed.

[0066] Optionally, a force model of the human-computer interaction device is established, and the part of the human-computer interaction device that cooperates with the user's limbs is defined as the human-computer interaction structure. A base coordinate system {O0} is established with the fixed point of the human-computer interaction structure as the origin, and a coordinate system {O3} is established in the force information collection device such as a force sensor as the origin. During the exercise training process, a conical surface is formed with the human-computer interaction structure body as the generatrix and O0 as the vertex. The resultant force G on the human-computer interaction device is ver The direction of is the normal direction of the tangent plane at this point, and G in the coordinate system {O3} ver The direction vector of the human-computer interaction device can be expressed as:

[0067]

[0068] Wherein:

[0069] 3 n s represents the direction vector of G in the coordinate system {O3}; ver of the direction vector; 0 P represents the expression of the direction vector of G in {O3}; ver of the direction vector in {O3}; 3 n x represents the direction vector of G in the coordinate system {O3} ver in the X-axis direction; 3 n y represents the direction vector of G in the coordinate system {O3} ver in the Y-axis direction; G d represents the total gravity obtained by the force information acquisition device; G z3 represents the resultant force in the Z-axis direction of the coordinate system {O3}; θ1 represents the angle of rotation of the human-computer interaction structure around Y0; θ2 represents the angle of rotation of the human-computer interaction structure around X0, (θ1, θ2 ∈ (0, π / 2); α represents the angle between the human-computer interaction structure and the Z0 axis, α = arccos(cosθ1cosθ2), α ∈ (0, π / 2); L represents the equivalent length of the human-computer interaction structure; R represents the perpendicular distance from point O3 to the Z-axis of the base coordinate system {O0}.

[0070] In this embodiment, based on the force information, a force model of the human-computer interaction device is constructed to accurately describe the force condition of the human-computer interaction device.

[0071] S300: Compensate the force model based on the non-interaction force information to obtain the interaction force information.

[0072] Specifically, the force information of the human-computer interaction device mainly includes three parts. The first part is mainly the gravity generated by the interaction device due to its own structure, the second part is mainly the gravity generated by the user's own limbs, and the third part is mainly the interaction force between the user and the device. Among them, the first part and the second part belong to non-interaction force information, and the third part belongs to interaction force information. Obtain the non-interaction force information, such as the self-gravity of the human-computer interaction structure, and compensate the force model to obtain the interaction force information.

[0073] Optionally, in the non-interaction force information, the first part accounts for a relatively large proportion. Due to the differences of users, the specific compensation value of the second part cannot be determined clearly, and its influence is small and can be ignored. It is also possible to compensate by manually inputting this part of the parameters into the constructed force model.

[0074] In a preferred embodiment, from the expression of the force model, G d The forces in the X, Y, and Z directions of the force information acquisition device can be expressed as:

[0075]

[0076] Among them, F GX represents the force in the X-axis direction of the coordinate system {O3}; F d represents the force in the Y-axis direction of the coordinate system {O3}; F GY represents the force in the Z-axis direction of the coordinate system {O3}. d GZ d SX SY RX

[0077] Optionally, during the human-computer interaction process, the main interaction force information is mainly reflected by the force information collected on the X-axis and Y-axis of the force acquisition device; preferably, only the force information on the XY-axis in the coordinate system {O3} is used to establish a force model, and the force model can be simplified as:

[0078]

[0079] Among them, F SX represents the force information on the X-axis of the coordinate system {O3}; F SY represents the force information on the Y-axis of the coordinate system {O3}; F RX represents the actual interaction force information on the X-axis of the coordinate system {O3}; F RY represents the actual interaction force information on the Y-axis of the coordinate system {O3}.

[0080] In this embodiment, the interaction force information is obtained by compensating the force model with the non-interaction force information, excluding interference factors, and achieving the purpose of accurately obtaining the interaction force information.

[0081] S400: Process the interaction force information through a fuzzy inference system to obtain an evaluation index.

[0082] In one embodiment, the fuzzy inference system referred to in the present invention represents a system with the ability to perform input-output mapping based on a knowledge base. Compared with traditional inference systems, the fuzzy inference system is more similar to human logic and describes attribute values as a degree of possibility. This property gives the fuzzy inference system an advantage in dealing with the fuzziness and uncertainty encountered in various fields.

[0083] Specifically, by processing the interaction force information through a fuzzy inference system, an evaluation index is obtained. For example, the interaction force information in the X-axis direction and the interaction force information in the Y-axis direction of the human-computer interaction structure obtained are input into the fuzzy inference system to obtain an evaluation index based on the interaction force information; preferably, the resultant force of the interaction force information in the X-axis direction and the interaction force in the Y-axis direction is taken as the input, and the resultant force of the interaction force can be expressed as:

[0084]

[0085] Among them, F add represents the resultant force of the interaction forces; F RX represents the actual interaction force information on the X-axis of the human-machine interaction structure; F RY represents the actual interaction force information on the Y-axis of the human-machine interaction structure.

[0086] In this embodiment, the interaction force information is processed by a fuzzy inference system to obtain evaluation indicators. Since the evaluation indicators are derived from the interaction force information, the evaluation indicators can reflect the situation of human-machine interaction, including the situation of the user's active participation during the training process. Fuzzy languages such as the user's active participation are transformed into quantifiable evaluation indicators, which is convenient for understanding the user's training participation and motor ability.

[0087] S500: Determine the target operation mode based on the current operation mode and status information, where the status information includes at least one of the operation information and the evaluation indicators; control the operation of the human-machine interaction device according to the target operation mode.

[0088] In one embodiment, the status information includes at least one of the operation information and the evaluation indicators, and the target operation mode is determined based on the current operation mode and the status information. For example, different operation modes have their own special attributes, and the strategies for determining the target operation mode are different under different current operation modes. If the same status information is used to determine the target operation mode regardless of the current mode, it is easy to introduce redundant parameters.

[0089] Optionally, the current operation mode may include an emergency protection operation mode. The target operation mode can be determined to be the emergency protection operation mode through the operation information and / or the evaluation indicators. For example, when the user has convulsions or twitches, the information contained in the operation information, such as acceleration information and electromyogram information, changes violently. When such information parameters exceed the preset values, the target operation mode is the emergency protection operation mode, and the training is terminated to prevent accidents and injuries during use.

[0090] In this embodiment, determining the target operation mode based on the operation mode and the status information can avoid inappropriate switching of the operation mode caused by a single mode determination strategy, and improve the ability to resist unstable factors such as short-term disturbances caused by the user's exertion during the confrontation training process. At the same time, it enables the interaction device to truly switch according to the actual situation of the user as needed, improving the human-machine interaction effect.

[0091] S600: Control the operation of the human-machine interaction device according to the target operation mode.

[0092] In one embodiment, controlling the operation of the human-machine interaction device according to the target operation mode is mainly achieved by controlling the torque output of the interaction device motor. For example, when in the passive training mode, the motor output torque drives the user to move along a pre-planned target motion trajectory; when in the assisted training mode, when the user deviates from the pre-planned target motion trajectory, the motor input torque corrects the deviation.

[0093] Optionally, the passive training mode can be constructed based on a computed torque controller. For example, the pre-planned target motion trajectory is a circle with a radius R = 80 mm, and in the passive mode, it can slowly approach the planned circular path in a spiral manner from any position. For the passive mode, the torque output of the motor can be expressed as:

[0094]

[0095] where τ represents the motor output torque; θ d represents the target motion trajectory; θ represents the actual angle of the motor, θ e = θ d - θ; M(θ) represents the inertia matrix of the system; represents all terms that depend on the state rather than acceleration.

[0096] Preferably,

[0097] In this embodiment, controlling the operation of the human-machine interaction device according to the target operation mode achieves the purpose of automatically switching to a reasonable operation mode as needed according to the user's usage situation to improve the human-machine interaction effect.

[0098] In this embodiment, by obtaining the operation information of the human-machine interaction device, including force information and the current operation mode, where the force information includes non-interaction force information, a force model of the human-machine interaction device is constructed based on the force information to accurately describe the force situation of the human-machine interaction device; the interaction force information is obtained by compensating the force model based on the non-interaction force information to avoid the influence of non-interaction forces caused by the factors of the human-machine interaction device itself on the accuracy of the interaction force expression; and the interaction force information is processed by a fuzzy inference system to obtain an evaluation index, and the evaluation index reflects the human-machine interaction situation, such as the situation of the user's active participation, and transforms the fuzzy language of the user's active participation into a quantifiable parameter; then the target operation mode is determined based on the current operation mode and state information, where the state information includes at least one of operation information and evaluation index, and the operation information and evaluation index can reflect the user's actual usage situation and movement training state, and determining the target operation mode based on this improves the rationality and accuracy of mode switching; finally, the operation of the human-machine interaction device is controlled according to the target operation mode, achieving the purpose of automatically switching to a reasonable operation mode as needed according to the user's actual training situation to improve the human-machine interaction effect.

[0099] Optionally, the current operation mode includes a passive training mode and an assisted training mode; determining a target operation mode based on the current operation mode and status information includes:

[0100] S510: When the current operation mode is the passive training mode, perform a first mode determination based on the evaluation index and operation information to obtain a first determination result, and determine the target operation mode based on the first determination result;

[0101] S520: When the current operation mode is the assisted training mode, perform a second mode determination based on the operation information to obtain a second determination result, and determine the target operation mode based on the second determination result.

[0102] In one embodiment, the passive training mode referred to in the present invention means that the human-computer interaction device outputs a driving force and completely dominates the user to move along a pre-planned trajectory; the assisted training mode referred to in the present invention means that the user exerts force independently to move along a pre-planned trajectory, and the human-computer interaction device only provides a certain auxiliary force when deviating from the preset trajectory.

[0103] Specifically, operation modes such as the passive training mode and the assisted training mode are constructed to meet the actual needs in different situations. For example, for users with very poor autonomous movement ability, the human-computer interaction device needs to dominate the training in the passive training mode to improve the training effect of the users; for users with certain autonomous movement ability, the assisted training mode is needed to help the users complete the training of the preset trajectory and has a better training effect. However, for most users, the level of autonomous movement ability is not stable, so the two movement modes need to be switched under appropriate circumstances to maximize the movement training effect.

[0104] In one embodiment, when the current operation mode is the passive training mode, perform a first mode determination based on the evaluation index and operation information, and determine the target operation mode according to the determination result; for example, in the passive training mode, determine whether the evaluation index and / or operation information meet the mode switching conditions. Among them, the mode switching conditions can perform multi-level judgments on the evaluation index and / or operation information by setting multi-level threshold conditions to improve the rationality of the determination result; or perform a single judgment on the evaluation index and / or operation information to improve the response speed.

[0105] In one embodiment, when the current operating mode is the assisted training mode, a second mode determination is made based on the operating information. For example, in the assisted training mode, it is determined whether the operating information meets the mode switching conditions. Among them, the mode switching conditions can be used to make multi-level determinations on different parameters in the operating information by setting multiple threshold conditions to improve the rationality of the determination results; it can also be to make multiple determinations on the same parameter in the operating information to increase the accuracy of the determination results; or it can be to make a single determination on a certain parameter in the operating information to improve the response speed.

[0106] In this embodiment, according to the different characteristics of the current operating mode, different judgment objects are used for different operating modes to perform different mode determinations, ensuring the rationality and accuracy of the determination results. At the same time, the type of the judgment object is also clarified according to the characteristics of the current operating mode, avoiding the introduction of unnecessary parameters, simplifying the data processing volume, and improving the data processing speed.

[0107] Optionally, as Figure 2 shown, the operating information further includes time information; when the current operating mode is the passive training mode, a first mode determination is made based on the evaluation index and the operating information to obtain a first determination result, and the target operating mode is determined based on the first determination result, specifically including:

[0108] S510: When the current operating mode is the passive training mode, determine whether the evaluation index is greater than a preset first threshold;

[0109] S520: If the evaluation index is greater than the first threshold, then determine whether the integral of the evaluation index with respect to the time information is greater than a preset integral threshold;

[0110] S530: If the integral information is greater than the integral threshold, determine that the assisted training mode is the target operating mode.

[0111] In one embodiment, when the current operating mode is the passive training mode, after obtaining the evaluation index, it is determined whether the evaluation index is greater than a preset first threshold. Among them, the first threshold can be adjusted accordingly according to the actual situation. For example, when the user's active participation in training is 60%, the corresponding rating index is 2. If the first threshold is set to 2.5, the switching condition is not met, and the passive training mode still needs to be maintained. However, in order to allow the user to use the assisted training mode for training as much as possible and improve the training effect, the first threshold can be lowered to 1.5. At this time, as long as the evaluation index exceeds 1.5, the mode switching condition is met, and the determination of the next target mode can be carried out.

[0112] In one embodiment, if the evaluation index is greater than the first threshold, integrate the evaluation index over time, and determine whether the integral of the evaluation index with respect to time information is greater than a preset integral threshold. For example, regularly obtain the value of the evaluation index. When the evaluation index value is greater than the preset first threshold, start integrating the evaluation index over time. When the obtained evaluation index value is less than or equal to the preset first threshold, end the integration of the evaluation index with respect to time, and determine whether the integral of the evaluation index with respect to time information is greater than the preset integral threshold.

[0113] In one embodiment, if the integral is greater than the integral threshold, determine the assisted training mode as the target operation mode. The integral threshold can be adjusted accordingly according to the actual situation. When the integral threshold is selected to be small, it is relatively easy to switch to the assisted training mode. When the integral threshold is selected to be large, it is not easy to switch to the assisted training mode.

[0114] In this embodiment, in the passive training mode, determine whether the evaluation index is greater than the preset first threshold to judge whether mode switching is required. If it is greater, then determine whether the integral of the evaluation index with respect to time information is greater than the preset integral threshold. If it is greater, determine the assisted training mode as the target operation mode. Realize determining the target operation mode according to the user's motion state. When the evaluation index does not exceed the threshold, it means that the user's own ability is not sufficient for assisted training, and the passive training mode still needs to be maintained. Only when the evaluation index exceeds the threshold and it is considered that the user's active participation degree, that is, the current motion ability, can perform assisted training, start to determine whether the integral of the evaluation index with respect to time information is greater than the preset integral threshold, which reflects the user's ability to continuously maintain this state. When the integral exceeds the preset integral threshold, it means that the user can continuously perform assisted training, and the assisted training mode is used as the target operation mode. This embodiment can determine a reasonable target operation mode according to the user's own motion ability, improving the degree of customization of motion training. When the instantaneous evaluation index value of the user is relatively high, the time to reach the integral threshold is short and the mode switching is rapid; when the evaluation index is low, it means that the user's active participation degree is low, the time to reach the integral threshold is long, and the time required to switch the mode is long, achieving the effect of mode switching on demand.

[0115] Optionally, as Figure 3 shown, the operation information further includes speed information; when the current operation mode is the assisted training mode, perform a second mode judgment based on the operation information to obtain a second judgment result, and determine the target operation mode based on the second judgment result, including:

[0116] S540: When the current operation mode is the assisted training mode, determine whether the speed information is less than or equal to a preset second threshold;

[0117] S550: If the speed information is less than or equal to the second threshold, then determine whether the time information is greater than a preset time threshold, where the time information includes the duration during which the speed information is less than or equal to the second threshold;

[0118] S560: If the time information is greater than the time threshold, then determine the passive training mode as the target operation mode.

[0119] In one embodiment, when the current operation mode is the assisted training mode, determine whether the speed information is less than or equal to a preset second threshold; where the second threshold can be adjusted according to actual requirements. For example, if the speed information in the assisted training mode is 0.01 m / s and the second threshold is 0 m / s, then the switching condition is not met and the assisted training mode is still maintained; if you want to reduce the training intensity of the user, the second threshold can be appropriately increased. For example, if the second threshold is set to 0.05 m / s, it is easier to meet the mode switching condition at this time, and the determination of the next target mode can be carried out.

[0120] In one embodiment, if the speed information is less than or equal to the second threshold, then determine whether the time information is greater than a preset time threshold, where the time information includes the duration during which the speed information is less than or equal to the second threshold; for example, when the speed information is less than or equal to the second threshold, start timing until the speed information is greater than the second threshold and then end to obtain the duration, and after obtaining the duration, determine whether the duration is greater than the preset time threshold.

[0121] Optionally, the duration is timed from 0 each time. After one duration timing is completed, the next time starts timing from 0 again.

[0122] In one embodiment, if the time information is greater than the time threshold, then determine the passive training mode as the target operation mode. For example, if the duration exceeds the time threshold, it means that the user has been in this state for a long time, indicating insufficient motor ability, then determine the target motion mode as the passive training mode.

[0123] Optionally, the time threshold can be adjusted according to actual requirements. For example, when it is desired that the user participates in the assisted training as much as possible, the time threshold can be appropriately increased, indicating that the user can enter the assisted training mode only after the time of low self - motion speed lasts for a relatively long time.

[0124] In this embodiment, in the assisted movement training mode, it is determined whether the speed information is less than or equal to a preset second threshold to judge whether mode switching is required. When the speed information is greater than the second threshold, it indicates that the user has the ability to continue participating in the assisted movement training and there is no need to switch the operation mode; when the speed information is less than or equal to the second threshold, it indicates that the user's motor ability is insufficient to support the continued assisted movement training mode. If the switching condition is met, timing starts to obtain the duration of this state, and the duration reflects the user's ability to continuously maintain this state. When the duration exceeds the time threshold, it means that the subject needs to undergo passive training, otherwise it is not necessary. This avoids the inappropriate switching of the operation mode due to the user's brief slackness, resulting in a decrease in the user's enthusiasm for active participation.

[0125] Optionally, as Figure 4 shown, before processing the operation information through the fuzzy inference system to obtain the evaluation index, it further includes:

[0126] S410: Obtain historical interaction force information;

[0127] S420: Obtain the historical interaction force and the historical interaction force change rate based on the historical interaction force information;

[0128] S430: Obtain the membership function based on the historical interaction force and the historical interaction force change rate;

[0129] S440: Determine the fuzzy inference rules according to the preset ranges of the historical interaction force and the historical interaction force change rate;

[0130] S450: Construct a fuzzy inference system based on the membership function and the fuzzy inference rules.

[0131] Specifically, the input range is determined by the historical interaction force and the historical interaction force change rate, aiming to make the user actively exert force as much as possible, and fuzzy rules and membership functions are established. For example, when the interaction force is lower than the preset interaction force threshold, but the interaction force change rate is higher than the preset change rate threshold, although the magnitude of the force exerted by the user is not significant at this time, the change rate of the force exceeds the preset change rate, so the user's participation degree is considered to have reached a certain level at this time, and the current operation mode is converted to the assisted movement training mode.

[0132] In one embodiment, historical interaction force information is obtained, and the historical interaction force and the historical interaction force change rate are obtained based on the historical interaction force information; for the convenience of description, the expression of the word "historical" is omitted in the following text of this embodiment.

[0133] Specifically, interaction force information is obtained, the interaction force is obtained according to the interaction force information and denoted as F add , according to the interaction force F add the interaction force change rate dF add / dt , for ease of description, the change rate of the interaction rate is denoted as dF add , and the change rate of the interaction force reflects the degree of change of the interaction force;

[0134] As Figure 6 , Figure 7 and Figure 8 shown, based on the interaction force F add and the change rate of the interaction force dF add , a membership function is obtained. For example, the data of the interaction force F add and the change rate of the interaction force dF add in different states are obtained, and the maximum value of the interaction force F add in different states and the closed interval of the change rate of the interaction force dF add in different states are obtained. Based on this, the membership functions of the inputs F add , dF add and the output evaluation index in the fuzzy inference system are formulated.

[0135] Based on the preset ranges of the interaction force F add and the change rate of the interaction force dF add , the fuzzy inference rules are determined. The fuzzy inference rules are the core elements of the fuzzy inference system and also the hub for the correct interpretation of knowledge and experience and the formation of an appropriate rule set. Preferably, when the user's motor ability is satisfied, the preset ranges of F add and dF add are determined with the goal of enabling the user to perform assisted movement training as much as possible, and then the fuzzy inference rules are determined.

[0136] In one embodiment, the setting of the membership function may cause the rule with the maximum membership degree to contribute to the accurate output value and ignore the rules with lower membership functions, resulting in a larger weight being assigned to unimportant rules. To avoid the above phenomenon, through the sum of centroids defuzzification method, it is ensured that as F add and dF add increase, the active participation degree σ also increases.

[0137] Specifically, as Figure 6 shown, membership functions regarding Z, PS, and PL are established for F add . Among them, the membership function regarding Z is a trapezoidal function; the membership function of PS is a triangular function; the membership function of PL is a trapezoidal function. As Figure 7 shown, Gaussian membership functions regarding NL, NS, Z, PS, and PL are established for dF add . As Figure 8 shown, Gaussian membership functions regarding Z, PS, and PL are established for σ.

[0138] The mode is switched through the following switching strategy:

[0139]

[0140]

[0141] Among them, ITH represents the threshold of active participation, μ represents the switching parameter, Assist represents the assisted movement training mode, Passive represents the passive training mode, and STH represents the switching threshold of the training mode.

[0142] Optionally, as Figure 5 shown, in the fuzzy inference rule table, Z represents a value of 0, PS represents a positive value and the value is less than the first threshold; PL represents a positive value and the value is greater than the second threshold; NS represents a negative value and the value is less than the third threshold, and NL represents a negative value and the value is less than the fourth threshold.

[0143] For example, obtain the data set in the passive training mode as a fuzzy set, dF add The maximum closed interval of the fuzzy set is [-6.1, 4.9]. When formulating the fuzzy inference rules, with the goal of enabling the user to perform assisted movement training as much as possible, taking Figure 7 as an example, dF add The membership functions between NL, NS, Z, PS, and PL are Gaussian functions, where the parameters of the Gaussian functions are determined according to the actual situation. In this embodiment, when the value of dF add is in the interval [1.8, 4.8], the membership corresponding to the curve of the membership function PS is greater than the memberships corresponding to Z and PL, then it is considered that the membership of PS is larger in the current data, and in the subsequent calculation, the weight ratio of the rule corresponding to PS is also correspondingly larger. In other embodiments, the size membership relationship of the current data is determined through the intersection points between the membership functions.

[0144] Among them, the first threshold is greater than or equal to 0 and less than or equal to the second threshold, and the third threshold is less than or equal to 0 and greater than or equal to the fourth threshold.

[0145] Optionally, product implication is adopted to prevent only the rule corresponding to the maximum membership function from contributing to the exact output value and ignoring the rules of lower membership functions, resulting in a large weight being assigned to unimportant rules. Preferably, the sum of centroids defuzzification method is used for defuzzification.

[0146] In one embodiment, based on the membership function and the fuzzy inference rules, a fuzzy inference system is constructed to realize the input interaction force and the change rate of the interaction force, and an evaluation index is obtained through the fuzzy inference system.

[0147] In this embodiment, when constructing the fuzzy inference system, in addition to the interaction force, the change rate of the interaction force is also introduced to describe the human-machine interaction situation in multiple dimensions. Compared with the single use of interaction force information for different mode switching and the recognition of the user's motion intention, under the corresponding switching conditions, using the interaction force and the change rate of the interaction force for mode switching in this embodiment can improve the response speed. Based on this, the membership function and the fuzzy inference rule are obtained. The evaluation index obtained is closely related to the user's active participation in the human-machine interaction, reflects the user's active participation degree during the training process, realizes the transformation of the fuzzy language of the user's active participation degree into a quantifiable parameter, and more intuitively reflects the user's active participation situation.

[0148] Optionally, the operation information further includes:

[0149] In the passive training mode, the historical interaction force information under the no-load condition;

[0150] In the passive training mode, the historical interaction force information when the load does not exert force;

[0151] In the assisted training mode, the historical interaction force information when the load moves along an arbitrary trajectory.

[0152] In one embodiment, obtaining the historical interaction force in different states includes:

[0153] The historical interaction force information under the no-load condition in the passive training mode. For example, in the case where there is no user participation, the interaction force information when the human-machine interaction device operates alone according to the pre-planned target trajectory;

[0154] The historical interaction force information when the load does not exert force in the passive training mode. For example, in the passive training mode, when the user does not exert force independently and is completely driven by the human-machine interaction device to operate according to the pre-planned target trajectory, the active participation degree of the user can be regarded as 0%, corresponding to the lowest evaluation index value;

[0155] The historical interaction force information when the load moves along an arbitrary trajectory in the assisted training mode. For example, in the assisted training mode, without pre-planning the target trajectory, the interaction force information when the user exerts force independently along an arbitrary trajectory. At this time, the active participation degree of the user can be regarded as 100%, corresponding to the highest evaluation index value.

[0156] In this embodiment, by obtaining the historical interaction force information in the no-load condition of the passive training mode as a reference control, using the no-force condition of the load in the passive training mode to reflect the historical interaction force information when the user's active participation is at the lowest level, and using the condition where the load moves along an arbitrary trajectory in the assisted training mode to reflect the historical interaction force information when the user's active participation is at the highest level, a basis is provided for establishing the membership function and fuzzy inference rules in the fuzzy inference system.

[0157] Optionally, the assisted training mode is constructed based on a potential energy field, and the potential energy at any point on the potential energy field is positively correlated with the distance between any point and a preset target motion trajectory. Here, the target motion trajectory is a closed curve, and the potential energy is equal everywhere on the target motion trajectory.

[0158] Specifically, the part of the human-machine interaction device that cooperates with the user's limb is defined as the human-machine interaction structure, and the center point of the contact part between the human-machine interaction structure and the user's limb is defined as the calibration point. N points are uniformly sampled from the preset target motion trajectory to construct the data set of the potential energy field. The data set can be expressed as:

[0159]

[0160] where, P represents the data set of the target motion trajectory; ξ i represents the position information of the i-th point of the calibration point in the Cartesian space, ξ i ∈R n ; represents the velocity information of the i-th point of the calibration point in the Cartesian space,

[0161] In one embodiment, under the assisted training mode, the motor input torque can be expressed as:

[0162]

[0163] where, M(θ) represents the inertia matrix; represents the centripetal force and Coriolis matrix; G(θ) represents the gravity matrix; represents the system friction torque; J represents the Jacobian matrix; represents the gradient of the potential energy field; represents the damping force.

[0164] In order to enable the user to move along the preset target motion trajectory in the assisted motion training mode, when the user moves along the preset target motion trajectory, the human-machine interaction device does not generate an auxiliary force. When deviating from the preset target motion trajectory, the motor outputs torque to provide a corrective force. It can be seen from the above formula that the corrective force is related to the potential field gradient. The larger the gradient, that is, the farther the point on the motion trajectory is from the target motion trajectory, the greater the corrective force, indicating that the potential energy at this point is higher. That is, the potential energy at any point on the potential energy field is positively correlated with the distance between any point and the preset target motion trajectory.

[0165] In one embodiment, the target motion trajectory is a closed curve, and the potential energy on the target motion trajectory is equal everywhere. Compared with the situation where there is also potential energy change on the target motion trajectory, this embodiment cancels the potential energy change on the target motion trajectory. Preferably, the potential energy at any point on the target motion trajectory is 0.

[0166] In this embodiment, the assisted motion training mode is constructed based on the potential energy field, and the potential energy at any point on the potential energy field is positively correlated with the distance between any point and the preset target motion trajectory, which is convenient to achieve the purpose of the human-machine interaction device assisting the user to move along the preset target motion trajectory in the assisted motion training mode. At the same time, since the target motion trajectory is a closed curve and the potential energy on the target motion trajectory is equal everywhere, a closed-loop trajectory planning is realized, overcoming the defect that the target motion trajectory cannot be closed-loop due to the potential energy change on the target motion trajectory.

[0167] Another embodiment of the present invention provides a human-machine interaction device with mode self-switching. The human-machine interaction device with mode self-switching includes: a host computer, a slave computer, a transmission component, and a detection component. The transmission component is applied to the mode self-switching human-machine interaction control method as described above. The transmission component is arranged on the slave computer, and the slave computer is used to control the movement of the transmission component according to the instructions issued by the host computer. The detection component is used to detect the operation information of the transmission component and send the operation information to the host computer.

[0168] In one embodiment, the host computer referred to in the present invention represents a device for issuing instructions to the rest according to the control method logic based on the acquired data; the slave computer represents a device for receiving the instructions issued by the host computer and performing corresponding actions.

[0169] Specifically, the human-machine interaction device includes: a host computer, a slave computer, a transmission component, and a detection component. The transmission component is arranged on the slave computer, and the slave computer is used to control the movement of the transmission component according to the instructions issued by the host computer to meet the training requirements in different operation modes; the detection component is used to detect the operation information of the transmission component, such as force information, time information, etc., and send the operation information to the host computer. The host computer processes the information according to the control method of the human-machine interaction device and obtains corresponding action instructions.

[0170] In this embodiment, a man-machine interaction device with mode self-switching is composed of a host computer, a slave computer, a transmission component, and a detection component. The slave computer is provided with a transmission component for controlling the movement of the transmission component according to an instruction issued by the host computer. The detection component is used to detect the operation information of the transmission component and send the operation information to the host computer. The host computer processes the information according to the control method of the man-machine interaction device and obtains corresponding action instructions to realize the control of the man-machine interaction device.

[0171] Optionally, the transmission component includes a rocker and a tray, and the detection component includes a force sensor. The rocker is provided with a first connection end and a second connection end. The first connection end is rotatably connected to the tray, and the second connection end is rotatably connected to the slave computer. The force sensor is fixedly connected to the rocker.

[0172] In one embodiment, the force sensor referred to in the present invention includes a two-dimensional force sensor and a three-dimensional force sensor. Since the interaction force between the man-machine interaction device and the user is mainly reflected by the X-axis and Y-axis of the force sensor, and the cost of the two-dimensional force sensor is lower than that of the three-dimensional force sensor, preferably, a two-dimensional force sensor is used as the force sensor.

[0173] Specifically, the transmission component includes a rocker and a tray, and the detection component includes a force sensor. The force sensor is fixedly connected to the rocker and is used to measure the force condition of the rocker of the man-machine interaction device. The rocker is provided with a first connection end and a second connection end. The first connection end is rotatably connected to the tray for accommodating the user's limb, and the second connection end is rotatably connected to the slave computer to control the movement of the rocker through the slave computer.

[0174] In this embodiment, the force sensor is fixedly connected to the rocker, which is convenient for measuring the force condition of the rocker of the man-machine interaction device. The first connection end of the rocker is rotatably connected to the tray, which is convenient for the user's limb movement to complete the trajectory movement training. The second connection end of the rocker is rotatably connected to the slave computer, and the movement of the rocker is controlled through the slave computer to support the user's movement training in different modes.

[0175] The other advantages of the man-machine interaction device with mode self-switching provided in this embodiment compared with the prior art are the same as those of the man-machine interaction control method with mode self-switching, which will not be elaborated here.

[0176] Another embodiment of the present invention provides a man-machine interaction device with mode self-switching, including:

[0177] An acquisition module for acquiring the operation information of the man-machine interaction device. The operation information includes force information and the current operation mode, where the force information includes non-interaction force information;

[0178] A modeling module for constructing a force model of the man-machine interaction device based on the force information;

[0179] A compensation module, which is used to compensate the force model based on the non-interactive force information to obtain the interactive force information;

[0180] An inference module, which is used to process the interactive force information through a fuzzy inference system to obtain an evaluation index;

[0181] A mode determination module, which is used to determine the target operation mode based on the current operation mode and status information, and the status information includes at least one of the operation information and the evaluation index;

[0182] A control module, which is used to control the operation of the human-computer interaction device according to the target operation mode.

[0183] In an embodiment, the acquisition module of the human-computer interaction device with mode self-switching acquires the operation information and the current operation mode. The modeling module establishes a force model based on the operation information. The compensation module compensates the force model based on the non-interactive force information to obtain the interactive force information. The inference module processes the interactive force information through a fuzzy inference system to obtain an evaluation index. The mode determination module determines the target operation mode based on the current operation mode and status information, and then the control module controls the operation of the human-computer interaction device according to the target operation mode.

[0184] In this embodiment, the acquisition module acquires the operation information of the human-computer interaction device, including the force information and the current operation mode. Among them, the force information includes the non-interactive force information. The modeling module constructs a force model of the human-computer interaction device based on the force information to accurately describe the force condition of the human-computer interaction device. The compensation module compensates the force model based on the non-interactive force information to obtain the interactive force information, avoiding the influence of the non-interactive force caused by the factors of the human-computer interaction device itself on the accuracy of the interactive force expression. And the fuzzy inference system of the inference module processes the interactive force information to obtain an evaluation index. The evaluation index reflects the human-computer interaction situation, such as the situation of the user's active participation. The fuzzy language of the user's active participation is transformed into a quantifiable parameter. The mode determination module determines the target operation mode based on the current operation mode and status information, where the status information includes at least one of the operation information and the evaluation index. The operation information and the evaluation index can reflect the actual use situation and the movement training status of the user. Based on this, determining the target operation mode improves the rationality and accuracy of the mode switching. Finally, the control module controls the operation of the human-computer interaction device according to the target operation mode, achieving the purpose of automatically switching a reasonable operation mode as needed according to the actual training situation of the user to improve the human-computer interaction effect.

[0185] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM), etc. In this application, the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiments of the present invention. In addition, the functional units in each embodiment of the present invention can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0186] Although the present disclosure is disclosed as above, the scope of protection of the present disclosure is not limited thereto. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the present disclosure, and these changes and modifications will all fall within the protection scope of the present invention.

Claims

1. A human-computer interaction control method with automatic mode switching, characterized in that, Including the following steps: Obtain the operation information of the human-computer interaction device, where the operation information includes time information, speed information, force information, and the current operation mode, and the force information includes non-interaction force information; Construct a force model of the human-computer interaction device based on the force information; Compensate the force model based on the non-interaction force information to obtain interaction force information; Process the interaction force information through a fuzzy inference system to obtain an evaluation index; Determine the target operation mode based on the current operation mode and status information, where the status information includes at least one of the operation information and the evaluation index, and the current operation mode includes an assisted training mode and a passive training mode; When the current operation mode is the assisted training mode, perform a second mode determination based on the operation information to obtain a second determination result, and determine the target operation mode based on the second determination result, including: when the current operation mode is the assisted training mode, determine whether the speed information is less than or equal to a preset second threshold; if the speed information is less than or equal to the second threshold, then determine whether the time information is greater than a preset time threshold, where the time information includes the duration when the speed information is less than or equal to the second threshold; if the time information is greater than the time threshold, then determine the passive training mode as the target operation mode; Control the operation of the human-computer interaction device according to the target operation mode.

2. The method for controlling human-computer interaction with self-switching mode according to claim 1, wherein The determining the target operation mode based on the current operation mode and status information includes: When the current operation mode is the passive training mode, perform a first mode determination based on the evaluation index and the operation information to obtain a first determination result, and determine the target operation mode based on the first determination result.

3. The mode self-switching human-computer interaction control method according to claim 2, characterized in that When the current operation mode is the passive training mode, perform a first mode determination based on the evaluation index and the operation information to obtain a first determination result, and determine the target operation mode based on the first determination result, including: When the current operation mode is the passive training mode, determine whether the evaluation index is greater than a preset first threshold; If the evaluation index is greater than the first threshold, then determine whether the integral of the evaluation index with respect to the time information is greater than a preset integral threshold; If the integral information is greater than the integral threshold, then determine the assisted training mode as the target operation mode.

4. The mode self-switching human-computer interaction control method according to claim 3, characterized in that, Before processing the operation information through the fuzzy inference system to obtain an evaluation index, it further includes: Obtain historical interaction force information; Obtain the historical interaction force and the historical interaction force change rate according to the historical interaction force information; Obtain a membership function based on the historical interaction force and the historical interaction force change rate; Determine fuzzy inference rules according to the preset ranges of the historical interaction force and the historical interaction force change rate; Construct the fuzzy inference system based on the membership function and the fuzzy inference rules.

5. The mode self-switching human-computer interaction control method according to claim 4, characterized in that, The historical interaction force information includes: Under the passive training mode, the historical interaction force information in the no-load situation; Under the passive training mode, the historical interaction force information when the load does not generate force; Under the assisted training mode, the historical interaction force information of the load moving along any trajectory.

6. The method for controlling human-computer interaction with mode self-switching according to claim 5, characterized in that The assisted training mode is constructed based on a potential energy field. The potential energy at any point on the potential energy field is positively correlated with the distance between the point and a preset target motion trajectory. The target motion trajectory is a closed curve, and the potential energy on the target motion trajectory is equal everywhere.

7. A human-computer interaction device with self-switching mode, characterized in that, The mode self-switching human-computer interaction device includes: a host computer, a slave computer, a transmission component, and a detection component. The host computer is used to implement the mode self-switching human-computer interaction control method according to any one of claims 1-6. The transmission component is arranged on the slave computer. The slave computer is used to control the movement of the transmission component according to the instruction sent by the host computer. The detection component is used to detect the operation information of the transmission component and send the operation information to the host computer.

8. The mode self-switching human-computer interaction device according to claim 7, wherein The transmission component includes a rocker and a tray. The detection component includes a force sensor. The rocker is provided with a first connection end and a second connection end. The first connection end is rotatably connected to the tray, and the second connection end is rotatably connected to the slave computer. The force sensor is fixedly connected to the rocker.

9. A human-computer interaction device with self-switching mode, characterized in that, Including: An acquisition module, which is used to acquire the operation information of the human-computer interaction device. The operation information includes time information, speed information, force information, and the current operation mode. The force information includes non-interaction force information. A modeling module, which is used to construct a force model of the human-computer interaction device based on the force information. A compensation module, which is used to compensate the force model based on the non-interaction force information to obtain interaction force information. An inference module, which is used to process the interaction force information through a fuzzy inference system to obtain an evaluation index. A mode determination module, which is used to determine a target operation mode based on the current operation mode and status information. The status information includes at least one of the operation information and the evaluation index. The current operation mode includes an assisted training mode and a passive training mode. When the current operation mode is the assisted training mode, a second mode judgment is performed based on the operation information to obtain a second judgment result, and the target operation mode is determined based on the second judgment result, including: when the current operation mode is the assisted training mode, it is judged whether the speed information is less than or equal to a preset second threshold; if the speed information is less than or equal to the second threshold, it is judged whether the time information is greater than a preset time threshold. The time information includes the duration when the speed information is less than or equal to the second threshold; if the time information is greater than the time threshold, the passive training mode is determined as the target operation mode. A control module, which is used to control the operation of the human-computer interaction device according to the target operation mode.

Images