Training method and training system using unmanned vehicle

Abstract

The present disclosure provides a training method performed by a training system including an unmanned vehicle. The method includes: controlling movement of the unmanned vehicle along a first preset trajectory; detecting a body reaction of a user body; determining whether the body reaction matches a preset reaction corresponding to the first preset trajectory; and in a case where it is determined that the body reaction does not match the preset reaction corresponding to the first preset trajectory, controlling the unmanned vehicle to provide a perceivable prompt.

Description

Technical Field

[0001] This disclosure relates to functional training, and more specifically, to training methods and systems utilizing unmanned vehicles. Background Technology

[0002] Functional training is a rehabilitation method that focuses on restoring strength and normal function of the neuromuscular and skeletal system, with the aim of making it easier for patients to perform daily activities. In other words, functional training aims to improve activities of daily living, such as reaching, bathing, brushing teeth, and housework.

[0003] Traditionally, functional training guidance has been provided via video or audio to instruct patients on a series of movements. However, functional training should be individualized. For example, a teenager who is 180 cm tall should have a greater effective range of motion during functional training than an elderly person who is 140 cm tall. Therefore, using audio or 2D video for training guidance is insufficient. Summary of the Invention

[0004] In view of this, this disclosure provides training methods and systems for using unmanned vehicles, offering more comprehensive and effective training.

[0005] According to a first aspect of this disclosure, a training method performed by a training system including an unmanned vehicle includes: controlling the unmanned vehicle to move along a first preset trajectory; detecting a user's physical reactions; determining whether the physical reactions match a preset reaction corresponding to the first preset trajectory; and, if the physical reactions do not match the preset reaction corresponding to the first preset trajectory, controlling the unmanned vehicle to provide perceptible prompts.

[0006] In an embodiment of the first aspect of this disclosure, controlling the unmanned vehicle to provide the perceptible cues includes pausing the movement of the unmanned vehicle.

[0007] In another embodiment of the first aspect of this disclosure, if it is confirmed that the bodily response matches the preset response corresponding to the first preset trajectory, the method further includes continuing the movement of the unmanned vehicle along the first preset trajectory.

[0008] In another embodiment of the first aspect of this disclosure, controlling the unmanned vehicle to provide the perceptible cues includes controlling the unmanned vehicle to move along a second preset trajectory different from the first preset trajectory.

[0009] In another embodiment of the first aspect of this disclosure, detecting the bodily response of the user's body includes obtaining location information of a portion of the user's body.

[0010] In another embodiment of the first aspect of this disclosure, determining whether the body reaction matches the preset reaction corresponding to the first preset trajectory includes: determining whether the distance between the unmanned vehicle and the part of the user's body is within a predetermined range based on the location information; determining that the body reaction does not match the preset reaction corresponding to the first preset trajectory if the distance is outside the predetermined range; and determining that the body reaction matches the preset reaction corresponding to the first preset trajectory if the distance is within the predetermined range.

[0011] In another embodiment of the first aspect of this disclosure, determining whether the body reaction matches the preset reaction corresponding to the first preset trajectory includes: determining whether the distance between the unmanned vehicle and the part of the user's body is greater than a maximum threshold based on the location information; if the distance is greater than the maximum threshold, determining that the body reaction does not match the preset reaction corresponding to the first preset trajectory; and if the distance is not greater than the maximum threshold, determining that the body reaction matches the preset reaction corresponding to the first preset trajectory.

[0012] In another embodiment of the first aspect of this disclosure, determining whether the body reaction matches the preset reaction corresponding to the first preset trajectory includes: determining whether the distance between the unmanned vehicle and the part of the user's body is less than a minimum threshold based on the location information; if the distance is less than the minimum threshold, determining that the body reaction does not match the preset reaction corresponding to the first preset trajectory; and if the distance is not less than the minimum threshold, determining that the body reaction matches the preset reaction corresponding to the first preset trajectory.

[0013] In another embodiment of the first aspect of this disclosure, controlling the unmanned vehicle to provide the perceptible cues includes controlling the unmanned vehicle away from the portion of the user's body.

[0014] In another embodiment of the first aspect of this disclosure, detecting the bodily response of the user's body includes acquiring muscle tension information of a portion of the user's body, the muscle tension information including at least one of force magnitude and force direction.

[0015] In an embodiment of the second aspect of this disclosure, a training system is provided. The training system includes an unmanned vehicle, a sensor, a controller, and a memory. The sensor is used to detect bodily responses of a user. The controller is coupled to the unmanned vehicle and the sensor. The memory is coupled to the controller and stores a first preset trajectory. The memory also stores at least one computer-executable instruction, which, when executed by the controller, causes the controller to: control the unmanned vehicle to move along the first preset trajectory; determine whether the bodily responses match a preset response corresponding to the first preset trajectory; and, if it is confirmed that the bodily responses do not match the preset response corresponding to the first preset trajectory, control the unmanned vehicle to provide perceptible cues.

[0016] In another embodiment of the second aspect of this disclosure, controlling the unmanned vehicle to provide the perceptible cues includes pausing the movement of the unmanned vehicle.

[0017] In another embodiment of the second aspect of this disclosure, when the at least one computer-executable instruction is executed by the controller, the controller further causes the controller to: continue the movement of the unmanned vehicle along the first preset trajectory if it is confirmed that the body reaction matches the preset reaction corresponding to the first preset trajectory.

[0018] In another embodiment of the second aspect of this disclosure, the memory also stores a second preset trajectory different from the first preset trajectory, and controlling the unmanned vehicle to provide the perceptible cues includes controlling the unmanned vehicle to move along the second preset trajectory.

[0019] In another embodiment of the second aspect of this disclosure, detecting the user's bodily response includes obtaining location information of a portion of the user's body.

[0020] In another embodiment of the second aspect of this disclosure, determining whether the body reaction matches the preset reaction corresponding to the first preset trajectory includes: determining whether the distance between the unmanned vehicle and the user's body part is within a predetermined range based on the location information; determining that the body reaction does not match the preset reaction corresponding to the first preset trajectory if the distance is outside the predetermined range; and determining that the body reaction matches the preset reaction corresponding to the first preset trajectory if the distance is within the predetermined range.

[0021] In another embodiment of the second aspect of this disclosure, determining whether the body reaction matches the preset reaction corresponding to the first preset trajectory includes: determining whether the distance between the unmanned vehicle and the part of the user's body is greater than a maximum threshold based on the location information; if the distance is greater than the maximum threshold, determining that the body reaction does not match the preset reaction corresponding to the first preset trajectory; and if the distance is not greater than the maximum threshold, determining that the body reaction matches the preset reaction corresponding to the first preset trajectory.

[0022] In another embodiment of the second aspect of this disclosure, determining whether the body reaction matches the preset reaction corresponding to the first preset trajectory includes: determining, based on the location information, whether the distance between the unmanned vehicle and the part of the user's body is less than a minimum threshold; if the distance is less than the minimum threshold, determining that the body reaction does not match the preset reaction corresponding to the first preset trajectory; and if the distance is not less than the minimum threshold, determining that the body reaction matches the preset reaction corresponding to the first preset trajectory.

[0023] In another embodiment of the second aspect of this disclosure, controlling the unmanned vehicle to provide the perceptible cues includes controlling the unmanned vehicle away from the portion of the user's body.

[0024] In another embodiment of the second aspect of this disclosure, detecting the bodily response of the user's body includes acquiring muscle tension information of a portion of the user's body, the muscle tension information including at least one of force magnitude and force direction.

[0025] In summary, the training method disclosed herein provides activity guidance in the three-dimensional real world, not only offering different challenges based on the needs of different users, but also incorporating visual feedback in functional training. Therefore, it achieves more comprehensive and effective training. Attached Figure Description

[0026] When with attachment Figure 1 When reading this document, the best understanding of all aspects of this disclosure can be obtained from the following detailed description. The various features are not drawn to scale. For clarity of discussion, the dimensions of the various features may be increased or decreased at will.

[0027] Figure 1 This shows a block diagram of a training system according to one embodiment of the present disclosure.

[0028] Figure 2 This diagram shows a schematic of a training system in operation according to one embodiment of the present disclosure.

[0029] Figures 3A, 3B, 3C, and 3D show block diagrams of various layouts of the training system in one embodiment of this disclosure.

[0030] Figure 4 This diagram shows a flowchart of a training method according to one embodiment of the present disclosure.

[0031] Figure 5 A timing diagram showing the distance between an unmanned vehicle and a portion of the user's body in one embodiment of this disclosure. Detailed Implementation

[0032] The following contains specific information relating to embodiments of this disclosure. The accompanying drawings and detailed disclosure are only illustrative of exemplary embodiments of this disclosure. However, this disclosure is not limited to these exemplary embodiments. Other variations and embodiments of this disclosure will occur to those skilled in the art. Unless otherwise stated, the same or corresponding elements in the drawings may be indicated by the same or corresponding reference numerals. Furthermore, the drawings and illustrations in this disclosure are generally not drawn to scale and are not intended to correspond to actual relative dimensions.

[0033] For consistency and ease of understanding, similar features (though not illustrated in some examples) are identified by numbers in the example figures. However, features in different implementations may differ in other respects and should not be narrowly limited to what is shown in the figures.

[0034] References to “one implementation,” “an implementation,” “an example implementation,” “various implementations,” “some implementations,” “implementations of this disclosure,” etc., may indicate that an implementation of this disclosure may include a particular feature, structure, or characteristic, but not every possible implementation of this disclosure must include that particular feature, structure, or characteristic. Furthermore, the repeated use of the phrases “in one implementation,” “in an example implementation,” or “an implementation” does not necessarily refer to the same implementation, although they may refer to the same implementation. Moreover, the use of any phrase related to “this disclosure,” such as “implementation,” does not imply that all implementations of this disclosure must include a particular feature, structure, or characteristic, but should be understood as meaning that “at least some implementations of this disclosure” include said particular feature, structure, or characteristic. The term “coupled” is defined as a connection, whether direct or indirect through intermediate components, and is not necessarily limited to a physical connection. The term “comprising” as used means “including but not limited to”; it particularly indicates an open inclusion or membership in a combination, group, series, or equivalent of the disclosure.

[0035] The "and / or" here refers to an association relationship used to describe the associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: A exists alone, A and B exist simultaneously, or B exists alone. "A and / or B and / or C" can mean that at least one of A, B, and C exists. The character " / " used here generally indicates that the preceding and following associated objects are in an "or" relationship.

[0036] Furthermore, for the purpose of non-limiting interpretation, specific details such as functional entities and techniques have been described to provide an understanding of the invented techniques. In other examples, detailed disclosures of well-known methods, techniques, systems, architectures, etc., have been omitted to avoid unnecessary detail from obscuring this disclosure.

[0037] Figure 1 This shows a block diagram of a training system according to one embodiment of the present disclosure.

[0038] like Figure 1 As shown, the training system 10 includes a controller 100, a sensor 110, an unmanned vehicle 120, and a memory 130, wherein the controller 100 is coupled to the sensor 110, the unmanned vehicle 120, and the memory 130 via wired and / or wireless means. The training system 10 is an interactive training system capable of guiding a user through a series of training movements using an unmanned vehicle moving in a three-dimensional (3D) real world, and providing feedback when the user does not follow the provided guidance. The series of training movements could be, for example, "Eight Pieces of Brocade," which includes eight independent exercises, each targeting a different body area, and "Qi Meridians," but is not limited to these.

[0039] It should be noted that, although the training system 10 in the following embodiments includes a controller 100, a sensor 110, an unmanned vehicle 120, and a memory 130 for illustrative purposes, this disclosure does not limit the number of controllers 100, the number of sensors 110, the number of unmanned vehicles 120, or the number of memories 130 in the training system 10. For example, the training system 10 may include multiple unmanned vehicles 120, each configured to guide a limb of a user's body.

[0040] The controller 100 is configured to access and execute computer-executable instructions stored in the memory 130 to perform the training method disclosed herein. In some embodiments, the controller 100 may include a central processing unit (CPU) or another programmable general-purpose or special-purpose microprocessor, digital signal processor (DSP), programmable controller, application-specific integrated circuit (ASIC), programmable logic device (PLD), or other similar components or combinations thereof.

[0041] Sensor 110 is configured to detect bodily responses of the user's body and provide information about the detected bodily responses to controller 100. Bodily responses are physiological feedback from the user in response to guidance from training system 10, such as movement of at least a part of the user's body (e.g., a limb), contraction of at least one muscle of the user, or a combination thereof. In some embodiments, sensor 110 may include, for example, one or more proximity sensors, a Loco positioning system (LPS) consisting of multiple ultra-wideband radio sensors, one or more cameras, one or more millimeter-wave radar units, one or more electromyography (EMG) detectors, one or more force sensors, and / or other similar components or combinations thereof.

[0042] In one example, a proximity sensor may be mounted on the unmanned vehicle 120 to obtain the distance between the unmanned vehicle 120 and a part of the user's body.

[0043] In one example, an LPS may include at least one anchor point and multiple tags (e.g., placed on a part of the autonomous vehicle and the user's body) to record the position of each tag in the three-dimensional (3D) space established by the LPS (e.g., relative to at least one anchor point). In an LPS, the anchor point acts as a signal transmitter and the tags act as signal receivers, but an LPS is not limited to this implementation.

[0044] In one example, a camera can be configured to acquire an image of the user, and the image can be analyzed by the controller 100 to obtain bodily responses, such as skeletal movement and facial orientation. Alternatively, more than one camera can be configured to construct a 3D space. Through image processing, the positions of the unmanned vehicle 120 and the user's body limbs in 3D space can be obtained.

[0045] Millimeter-wave radar can detect the distance, speed, and trajectory of a target. In one example, millimeter-wave radar can be mounted on an unmanned vehicle 120 and configured to detect the dynamic position and speed of a user. By analyzing the data from the millimeter-wave radar, the controller 100 can obtain the relative distance between the unmanned vehicle 120 and any part of the user's body.

[0046] In one example, each EMG detector can be mounted on a limb of the user and configured to detect muscle contractions in each limb.

[0047] In one example, at least one (e.g., six) force sensors may be placed on at least one of the user's fingers and configured to detect the force applied by the user's fingers.

[0048] It should be noted that the type of sensor 110 is not limited to the examples described above. Those skilled in the art can design sensor 110 to detect a user's bodily responses as needed.

[0049] The unmanned vehicle 120 is configured to receive commands from the controller 100 and move in the 3D real world according to the received commands to guide the user to perform a series of actions. The unmanned vehicle 120 can be, for example, an unmanned aerial vehicle (UAV, also known as a drone) or an unmanned ground vehicle.

[0050] In some implementations, an unmanned vehicle 120 can be configured to guide multiple body segments of a user. For example, the unmanned vehicle can move in the air along a 1-shaped trajectory to guide the user through the first section or first movement of the "Eight Pieces of Brocade" exercise; and move in the air along a 2-shaped trajectory to guide the user through the second section or second movement of the "Eight Pieces of Brocade" exercise, and so on.

[0051] In some embodiments, an unmanned vehicle 120 may be configured to guide a user's body segment. For example, the training system 10 may include four unmanned vehicles for guiding the user's arms and legs. However, this disclosure does not limit the number of unmanned vehicles 120 in the training system 10. In some embodiments, the training system 10 may include 10 unmanned vehicles for guiding the user's head, upper torso, left upper arm, left forearm, right upper arm, right forearm, left thigh, left calf, right thigh, and right calf, respectively.

[0052] The memory 130 is used to store at least one preset track and at least one computer-executable instruction. The memory 130 may include, for example, random access memory (RAM), read-only memory (ROM), erasable rewritable read-only memory (EPROM), electronically erasable rewritable read-only memory, flash memory, optical disc read-only memory (CD-ROM), magnetic tape cassette, magnetic tape, magnetic disk storage, or any other equivalent medium capable of storing computer-executable instructions.

[0053] Figure 2 This diagram shows a schematic of a training system in operation according to one embodiment of this disclosure. Figure 2 In one exemplary embodiment, LPS is used as an example of sensor 110, and the training system 10 includes four UAVs 122, 123, 124, and 125 to guide the user 20’s two arms and two legs, respectively.

[0054] like Figure 2As shown, in some embodiments, the sensor 110 of the training system 10 is an LPS and includes an anchor point 111 and multiple labels 112, 113, 114, 115, 112', 113', 114', and 115'. For example, the LPS system defines a 3D coordinate system 30, where the anchor point 111 is located at the origin (0, 0, 0).

[0055] Tag 112 is placed on user 20's left wrist, tag 113 on user 20's right wrist, tag 114 on user 20's left ankle, and tag 115 on user 20's right ankle. In this configuration, the LPS system can obtain the positions (Xlw, Ylw, Zlw), (Xrw, Yrw, Zrw), (Xla, Yla, Zla), and (Xra, Yra, Zra) of tags 112, 113, 114, and 115 over time in the 3D coordinate system 30, respectively. The positions (Xlw, Ylw, Zlw), (Xrw, Yrw, Zrw), (Xla, Yla, Zla), and (Xra, Yra, Zra) of tags 112, 113, 114, and 115 can represent the positions or locations of user 20's left arm, right arm, left leg, and right leg, respectively.

[0056] Tag 112' is placed on UAV 122, which is configured to guide user 20's left arm; tag 113' is placed on UAV 123, which is configured to guide user 20's right arm; tag 114' is placed on UAV 124, which is configured to guide user 20's left leg; and tag 115' is placed on UAV 125, which is configured to guide user 20's right leg. In this case, the LPS system can obtain the positions (Xlw', Ylw', Zlw'), (Xrw', Yrw', Zrw'), (Xla', Yla', Zla'), and (Xra', Yra', Zra') of labels 112', 113', 114', and 115' over time in the 3D coordinate system 30, respectively. The positions (Xlw', Ylw', Zlw'), (Xrw', Yrw', Zrw'), (Xla', Yla', Zla'), and (Xra', Yra', Zra') of 112', 113', 114', and 115' can represent the positions or locations of UAVs 122, 123, 124, and 125, respectively.

[0057] Figure 2 In the training system 10 shown, the sensor 110 and the unmanned vehicle 120 are separate devices, and the controller 100 (not shown) Figure 2The arrangement of components in the training system 10 can be, for example, separate from, sensor 110 and unmanned vehicle 120, integrated with sensor 110, or integrated with one or each of unmanned vehicles 120. In other words, the arrangement of components in the training system 10 is not limited to that disclosed herein. Various implementations of the layout of the training system 10 are described in the following description.

[0058] Figures 3A, 3B, 3C, and 3D show block diagrams of various layouts of the training system in one embodiment of this disclosure.

[0059] like Figure 3A As shown, in some embodiments, the controller 100 and the memory 130 may be integrated into a control device 100', and the control device 100', the sensor 110, and the unmanned vehicle 120 are independent devices.

[0060] by Figure 2 For example, sensor 110 and unmanned vehicle 120 can be independent devices, and control device 100' can also be independent of sensor 110 and unmanned vehicle 120. For example, control device 100' can be positioned at the origin (0, 0, 0), receive position information from sensor 110, and control unmanned vehicle 120.

[0061] In some examples, the control device 100' is configured to receive position information (e.g., position in 3D coordinate system 30) from the sensor 110 and control the unmanned vehicle 120.

[0062] like Figure 3B As shown, in some embodiments, the control device 100' can also be integrated into the unmanned vehicle 120 as an unmanned vehicle device 120', and the unmanned vehicle device 120' is independent of the sensor 110.

[0063] by Figure 2 For example, control device 100' (e.g., controller 100 and memory 130) can be integrated into one of unmanned vehicles 122, 123, 124 or 125 as unmanned vehicle device 120', and control device 100' in unmanned vehicle device 120' is wirelessly coupled to sensor 110 (e.g. LPS) and other unmanned vehicles 120.

[0064] In some examples, control device 100' is configured to receive position information (e.g., position in 3D coordinate system 30) from sensor 110 and control unmanned vehicle device 120' and other unmanned vehicles 120.

[0065] by Figure 2As another example, four control units 100' can be integrated into unmanned vehicles 122, 123, 124 and 125 as four unmanned vehicle units 120', and the four control units 100' and sensors 110 (e.g., LPS) are wirelessly coupled to each other.

[0066] In some examples, each control device 100' is configured to receive position information (e.g., position in 3D coordinate system 30) from sensor 110 and control the corresponding unmanned vehicle 120'.

[0067] like Figure 3C As shown, in some embodiments, the controller 100 and the memory 130 may be integrated into a control device 100', and the unmanned vehicle 120 and the sensor 110 may be integrated into an unmanned vehicle device 120''.

[0068] For example, four sensors 110 corresponding to the left arm, right arm, left leg, and right leg of user 20 can be respectively installed on the unmanned vehicle 120 guiding the left arm, the unmanned vehicle 120 guiding the right arm, the unmanned vehicle 120 guiding the left leg, and the unmanned vehicle 120 guiding the right leg. The sensor 110 installed on the unmanned vehicle 120 guiding the left arm of user 20 is used to detect the distance to the left arm of user 20, the sensor 110 installed on the unmanned vehicle 120 guiding the right arm of user 20 is used to detect the distance to the right arm of user 20, the sensor 110 installed on the unmanned vehicle 120 guiding the left leg of user 20 is used to detect the distance to the left leg of user 20, and the sensor 110 installed on the unmanned vehicle 120 guiding the right leg of user 20 is used to detect the distance to the right leg of user 20.

[0069] In some examples, the control unit 100' and the four unmanned vehicle units 120'' are independent and configured to receive position information (e.g., detected distance) from the sensor 110 and control the unmanned vehicles 120''.

[0070] However, this disclosure does not limit the implementation of the detection distance. In some examples, sensor 110 may be a proximity sensor or millimeter-wave radar mounted on each unmanned vehicle 120 to detect the distance to a corresponding part of the user's body, and sensor 110 is not limited to these embodiments disclosed herein.

[0071] As shown in Figure 3D, in some embodiments, the controller 100, sensor 110 and memory 130 can be integrated into the unmanned vehicle 120 as an unmanned vehicle device 120'''.

[0072] For example, the training system 10 may include four unmanned vehicle devices 120''', and each of the four unmanned vehicle devices 120''' may include a controller 100, a sensor 110, and a memory 130. In this case, the four unmanned vehicle devices 120''' are configured to guide four parts of the user's body respectively. The four controllers 100 are wirelessly coupled to each other for communication.

[0073] In some examples, each controller 100 is configured to receive location information from sensor 110 (e.g., Figure 3C (The distance detected in the middle) and control the corresponding unmanned vehicle device 120'''.

[0074] Although four unmanned vehicles are shown in the training system 10 in the above embodiment, it should be noted that the number of unmanned vehicles 120 is not limited to four. Alternatively, the number of unmanned vehicles 120 in the training system 10 can be 1, 2, 3 or more than 4.

[0075] Furthermore, despite Figure 3A , Figure 3B , Figure 3C ,as well as Figure 3D Four exemplary configurations of the training system 10 are shown. It should be noted that the configuration of the components in the training system 10 is not limited to the four configurations shown. Those skilled in the art can implement the training system 10 according to their needs.

[0076] Figure 4 This diagram shows a flowchart of a training method according to one embodiment of the present disclosure. Figure 4 The training method shown can be executed by the training system 10 described above; therefore, for convenience, the same reference figures will be used to describe... Figure 4 The actions shown are those of the training method.

[0077] It should be noted that although actions S410, S430, S450, and S470 are described as separate actions representing independent blocks, these separately described actions should not be interpreted as a necessary dependency sequence. Figure 4 The order in which actions are performed is not intended to be construed as a limitation, and any number of public blocks can be combined in any order to implement the method or alternative methods.

[0078] like Figure 4 As shown, in action S410, the controller 100 can control the unmanned vehicle 120 to move along a first preset trajectory. Specifically, the first preset trajectory is designed to guide the user 20 to perform a series of training actions, and the controller 100 can be used to control the unmanned vehicle to move along the first preset trajectory.

[0079] In some implementations, the first preset trajectory may, for example, include information on position and velocity that change over time (e.g., at each time point). In some implementations, the first preset trajectory may, for example, be set based on the length of the user 20's body limbs and the expected completion time for each action. In this way, the guidance provided by the unmanned vehicle 120 traveling along the first preset trajectory can meet the needs of different users.

[0080] In some implementations, the training system 10 includes only one unmanned vehicle 120. The unmanned vehicle 120 moves along a first preset trajectory to guide the user through the intended movements of a training sequence. For example, the first preset trajectory may include a sequence of 1-shaped to 8-shaped trajectories to guide the user 20 through the eight exercises of "Eight Pieces of Brocade" in sequence. Alternatively, the first preset trajectory may repeatedly move up and down in the air, and the unmanned vehicle 120 (e.g., a UAV) may move (e.g., fly) along the first preset trajectory to guide a part of the user's body (e.g., the user 20's left hand holding a dumbbell, or the muscles controlling the user 20's fingers).

[0081] In some implementations, controller 100 controls four unmanned aerial vehicles 122, 123, 124, and 125 respectively (e.g., as shown in the figure). Figure 2 As shown, the drone 122 flies along four (different) first preset trajectories to guide user 20 in performing the "Eight Pieces of Brocade" exercise. For example, drone 122 flies along the first trajectory to guide user 20's left arm in the left arm movement of the Eight Pieces of Brocade, drone 123 flies along the second trajectory to guide user 20's right arm in the right arm movement of the Eight Pieces of Brocade, drone 124 flies along the third trajectory to guide user 20's left leg in the left leg movement of the Eight Pieces of Brocade, and drone 125 flies along the fourth trajectory to guide user 20's right leg in the right leg movement of the Eight Pieces of Brocade.

[0082] In some implementations, the training system 10 may also include a speaker. While controlling the movement of the unmanned vehicle 120, the controller 100 may synchronously play an audio track corresponding to a first preset trajectory (e.g., voice guidance or music for "Baduanjin").

[0083] like Figure 4 As shown, in action S430, sensor 110 can detect the user 20's physical response, and in action S450, controller 100 can determine whether the physical response matches a preset response corresponding to a first preset trajectory. It is worth noting that actions S430 and S450 can be executed when the training system 10 is started. That is, actions S410, S430, and S450 can, for example, be executed simultaneously.

[0084] Specifically, at least a part of the user's body can react in response to guidance provided by the autonomous vehicle 120, and the sensor 110 can detect the user 20's bodily responses to the guidance provided by the autonomous vehicle 120. These bodily responses can be, for example, associated with the user 20's muscular or nervous system.

[0085] In some implementations, each first preset trajectory may correspond to a preset response.

[0086] In some implementations, the first preset trajectory may include a sequence of 1-shaped trajectories to 8-shaped trajectories to guide the user 20 in performing the eight exercises of the Eight Pieces of Brocade sequentially. In this case, the preset response may be, for example, that the user 20 performs the eight exercises of the Eight Pieces of Brocade sequentially. For example, the user 20 should begin performing the first exercise in response to the unmanned vehicle completing the 1-shaped trajectory and complete the first exercise before the unmanned vehicle 120 begins flying along the 2-shaped trajectory; the user 20 should begin performing the second exercise in response to the unmanned vehicle completing the 2-shaped trajectory and complete the second exercise before the unmanned vehicle 120 begins flying along the 3-shaped trajectory; and so on.

[0087] In some implementations, sensor 110 can acquire an image of user 20, and controller 100 can determine whether user 20 is sequentially performing the eight exercises of "Eight Pieces of Brocade" based on guidance provided by the unmanned vehicle 120 (e.g., image processing using an artificial intelligence (AI) model, etc.). If the image processing results indicate that user 20 is sequentially performing the eight exercises of "Eight Pieces of Brocade," controller 100 can determine that the body's response matches a preset response. Otherwise, controller 100 can determine that the body's response does not match a preset response. Those skilled in the art can make the determination according to their own needs; therefore, the details of the determination are not elaborated here.

[0088] In some implementations, the first preset trajectory may repeatedly guide a part of the user's body (e.g., the left hand, but not limited thereto) up and down. In this case, the preset response may be, for example, that a part of the user's body follows the repeated raising and lowering of the unmanned vehicle 120.

[0089] In some implementations, the first preset trajectory may be a regular or irregular trajectory in the air used to guide a part of the user's body (e.g., the left hand, but not limited to this). In this case, the preset response may be, for example, a part of the user's body moving in the air along a regular or irregular trajectory according to the first preset trajectory.

[0090] In some implementations, sensor 110 can acquire an image of user 20, and controller 100 can adjust the image based on the image (e.g., using OpenCV). TMThe controller 100 uses an open-source computer vision artificial intelligence (AI) model to process images, etc., to determine whether user 20 matches a preset response. If the image processing results indicate that a part of user 20's body is indeed moving along the first preset trajectory with the unmanned vehicle 120, the controller 100 can determine that the body response matches the preset response. Otherwise, the controller 100 can determine that the body response does not match the preset response. Those skilled in the art can make the judgment according to their own needs; therefore, the details of the judgment are not elaborated here.

[0091] In some implementations, sensor 110 may, for example, acquire the distance between the autonomous vehicle 120 and a portion of the user's body to determine whether the user 20 matches a preset response. For example, the distance may be the difference in position between the autonomous vehicle 120 and a portion of the user's body in an established 3D coordinate system 30 (e.g., the distance between two positions: (Xlw, Ylw, Zlw) and (Xlw', Ylw', Zlw')). In another example, the distance may be a relative distance directly obtained by sensor 110 mounted on the autonomous vehicle 120.

[0092] In some implementations, if the distance between the unmanned vehicle 120 and the user's body does not exceed a maximum threshold, the controller 100 can determine that the body's reaction matches a preset reaction; if the distance between the unmanned vehicle 120 and the user's body exceeds the maximum threshold, the controller 100 can determine that the body's reaction does not match a preset reaction.

[0093] In some implementations, if the distance between the unmanned vehicle 120 and the user's body is not less than a minimum threshold, the controller 100 can determine that the body response matches a preset response; in some implementations, if the distance between the unmanned vehicle 120 and the user's body is less than a minimum threshold, the controller 100 can determine that the body response does not match a preset response.

[0094] In some implementations, when the distance between the autonomous vehicle 120 and the user's body is within a predetermined range, the controller 100 can determine that the body's response matches a preset response; in other implementations, when the distance between the autonomous vehicle 120 and the user's body is outside the predetermined range, the controller 100 can determine that the body's response does not match a preset response. The predetermined range may be defined, for example, by the maximum and minimum thresholds, but is not limited thereto.

[0095] In some implementations, each autonomous vehicle 120 guides a corresponding part of the user's body along a different first preset trajectory. The controller 100 can determine whether each part of the user's body follows the corresponding autonomous vehicle 120. If one of the autonomous vehicles 120 does not follow (e.g., the distance between said autonomous vehicle 120 and the corresponding part of the user's body is greater than a maximum threshold, less than a minimum threshold, or outside a predetermined range), the controller 100 can determine that the user 20's physical response does not match a preset response. Otherwise, the controller 100 can determine that the user 20's physical response matches a preset response.

[0096] In some implementations, the first preset trajectory can be repeatedly moved left and right to guide parts of the user's body (e.g., the face, but not limited to this). In this case, the preset response could be, for example, the direction of the user's face following the repeated left and right rotations of the unmanned vehicle 120.

[0097] In some implementations, sensor 110 can acquire an image of user 20, and controller 100 can base its image on the data (e.g., using OpenCV). TM (Image processing, etc.) determines whether the user 20's physical response matches a preset response. If the image processing results indicate that the user 20's facial orientation indeed follows the unmanned vehicle 120 along a first preset trajectory, the controller 100 can determine that the physical response matches the preset response. Otherwise, the controller 100 can determine that the physical response does not match the preset response. Those skilled in the art can make the determination according to their own needs; therefore, the details of the determination will not be elaborated here.

[0098] In some implementations, the first preset trajectory may be used to guide a part of the user 20's body (e.g., specific muscles controlling the user 20's fingers, but not limited thereto) along a regular or irregular trajectory in the air. In this case, the preset response may be, for example, that a part of the user 20's body (e.g., specific muscles controlling the user 20's fingers, but not limited thereto) contracts in response to the direction and velocity of the first preset trajectory. For example, when the unmanned vehicle 120 rises, the specific muscles controlling the user 20's fingers may contract to lift the fingers or apply an upward force, and when the unmanned vehicle 120 descends, the specific muscles controlling the user 20's fingers may contract to bend the fingers downward or apply a downward force. Furthermore, the intensity of the contraction may be, for example, positively correlated with the velocity of the unmanned vehicle 120.

[0099] In some implementations, sensor 110 may be an EMG detector or at least one (e.g., 6) force sensor capable of detecting bodily responses, such as muscle contraction or force exertion in a finger, even if the finger is not actually bent outwards. Based on the muscle contraction and / or applied force detected by sensor 110, controller 100 may determine whether the bodily response matches a preset response.

[0100] As shown in Figure 4, if the controller 100 confirms that the user 20's physical response matches the preset response, the process returns to action S410, indicating that the unmanned vehicle 120 continues to move along the first preset trajectory unaffected by actions S430 and S450. If the controller 100 confirms that the user 20's physical response does not match the preset response, the process proceeds to action S470, where the controller 100 can control the unmanned vehicle 120 to provide a perceptible cues, and then the process proceeds to action S430. It is worth noting that actions S430 and S450 can be executed while providing perceptible cues. That is, actions S430, S430, and S450 can, for example, be executed simultaneously.

[0101] Specifically, the perceptible prompt can be feedback used to notify the user 20 that at least a part of their body is not following the guidance of the autonomous vehicle 120.

[0102] In some implementations, the perceptible prompt may include audio feedback. For example, audio feedback may include alarms, preset audio tracks and / or paused audio tracks (e.g., voice guidance or music for "Baduanjin"), etc., and this disclosure is not limited to these forms.

[0103] In some implementations, the perceptible cues may include visual feedback. For example, visual feedback may include lighting effects, and / or the movement of the unmanned vehicle 120 deviating from a first preset trajectory, etc., but this disclosure is not limited to these forms.

[0104] In some implementations, the perceptible prompt may include pausing the movement of the autonomous vehicle 120. For example, the autonomous vehicle 120 may move along a first preset trajectory in action S410 to guide the user 20. If the controller 100 determines that the physical response does not match the preset response, the movement of the autonomous vehicle 120 (e.g., along the first preset trajectory) may be paused until the controller 100 determines in action S450 that the physical response matches the preset response. Once the controller 100 determines that the physical response matches the preset response in action S450, the autonomous vehicle 120 may continue moving along the first preset trajectory to continue guiding the user 20.

[0105] In some implementations, the perceptible cues may also include the autonomous vehicle 120 moving along a second preset trajectory. For example, if movement along the first preset trajectory is paused, the autonomous vehicle 120 may not need to remain stationary. Instead, the controller 100 may control the autonomous vehicle 120 to move along a second preset trajectory different from the first preset trajectory to provide visual feedback to the user 20. The second preset trajectory may be, for example, but not limited to, a circular trajectory or an octagonal trajectory. Once the controller 100 determines in action S450 that the body response matches a preset response, the autonomous vehicle 120 may continue moving along the first preset trajectory to continue guiding the user 20. It is important to note that in this case, the controller 100 determines whether the body response matches the preset response by comparing the distance between a part of the user's body and the pause point of the autonomous vehicle 120, rather than by comparing the distance between a part of the user's body and the current position of the autonomous vehicle 120. The distance between a part of the user's body and the current position of the autonomous vehicle 120 is used because the autonomous vehicle 120 is moving to provide perceptible cues (e.g., visual feedback) rather than training guidance.

[0106] In some implementations, the perceptible cue may include a part of the user's body that is away from the user's body. In some cases, the controller 100 may determine that the body response does not match a preset response based on the distance between the autonomous vehicle 120 and the user's body part being less than a minimum threshold. Therefore, the controller 100 may control the part of the autonomous vehicle 120 that is away from the user's body (e.g., moving in the opposite direction to the movement of the user's body part) to avoid a collision. It is worth noting that actions S430 and S450 may be executed when the perceptible cue is provided. Once the controller 100 determines in action S450 that the body response matches a preset response (e.g., the distance between the autonomous vehicle 120 and the user's body part is not less than a minimum threshold), the autonomous vehicle 120 may continue to move along the first preset trajectory to continue guiding the user 20.

[0107] In some implementations, different perceptible cues (e.g., different colors of light flashing on the autonomous vehicle 120, different alarms, or different second preset trajectories, etc.) can send different messages to the user. For example, a first perceptible cue can send a message to the user 20 to notify that a part of the user's body is too far from the autonomous vehicle 120, and a second perceptible cue can send a message to the user 20 to notify that a part of the user's body is too close to the autonomous vehicle. However, the design of perceptible cues is not limited to this disclosure, and those skilled in the art can have different implementations as needed.

[0108] Figure 5This diagram shows a timeline of the distance between an unmanned vehicle and a portion of the user's body in one embodiment of this disclosure.

[0109] like Figure 5 As shown, the distance between the unmanned vehicle 120 and a part of the user's body is depicted over time.

[0110] In some implementations, at time point t0, when the distance between the unmanned vehicle 120 and the user's body part is within a predetermined range [Dmin, Dmax], the unmanned vehicle 120 begins to move along a first preset trajectory, and the user's body part follows the unmanned vehicle 120.

[0111] During the time period t0 to t1, a part of the user's body follows the autonomous vehicle 120 very well (e.g., the user's physical reaction matches the preset reaction corresponding to the first preset trajectory).

[0112] In some implementations, at time point t1, the controller 100 may determine that the user 20's physical response does not match the preset response corresponding to the first preset trajectory because the distance between the autonomous vehicle 120 and a part of the user's body is less than a minimum threshold Dmin. In this case, the controller 100 may control the autonomous vehicle 120 to move away from the user's body part until the controller 100 detects that the distance between the autonomous vehicle 120 and the user's body part is not less than (i.e., greater than or equal to) the minimum threshold Dmin (e.g., at time point t2).

[0113] During the time period t1 to t2, the user's physical reaction does not match the preset reaction corresponding to the first preset trajectory, and the unmanned vehicle 120 moves away from the part of the user's body to eliminate the mismatch.

[0114] In some implementations, at time point t2, the controller 100 can control the unmanned vehicle 120 to continue moving along the first preset trajectory, so that parts of the user's body can continue to follow the unmanned vehicle 120 for training.

[0115] During the time period t2 to t3, a part of the user's body followed the autonomous vehicle 120 very well. (For example, the user's physical reactions matched the preset reactions corresponding to the first preset trajectory).

[0116] In some implementations, at time point t3, the controller 100 may determine that the user 20's physical response does not match the preset response corresponding to the first preset trajectory because the distance between the autonomous vehicle 120 and a part of the user's body is greater than a maximum threshold Dmax. In this case, the controller 100 may control the autonomous vehicle 120 to provide perceptible cues, including pausing movement along the first preset trajectory, until the controller 100 detects that the distance between the autonomous vehicle 120 and the user's body part is not greater than (i.e., less than or equal to) the maximum threshold Dmax (e.g., at time point t4).

[0117] During time intervals t3 and t4, the user's physical response does not match the preset response corresponding to the first preset trajectory, and the training system 10 waits for parts of the user's body to catch up with the autonomous vehicle 120. In other words, the mismatch between time intervals t3 and t4 is eliminated by the user 20, not by the training system 10.

[0118] In some implementations, at time point t4, the controller 100 can control the unmanned vehicle 120 to continue moving along the first preset trajectory, so that the user's body can continue to follow the unmanned vehicle 120 for training.

[0119] During time intervals t4 to t5, a part of the user's body follows the autonomous vehicle 120 very well. (For example, the user's physical responses match the preset responses corresponding to a first preset trajectory). Training can, for example, end at time point t5.

[0120] In addition to being guided by the training system 10, in some implementations, user 20 can also control the unmanned vehicle 120 with parts of their body, such as contracting specific muscles or applying force to parts of their body. For example, user 20 can control the unmanned vehicle (e.g., UAV) to move towards user 20 by waving their hand, and can control the unmanned vehicle to move away from user 20 by waving their hand. As another example, user 20 can control the unmanned vehicle (e.g., UAV) to move upward (e.g., fly) by applying an upward force with their finger, and can control the unmanned vehicle (e.g., UAV) to move downward (e.g., fly) by applying a downward force with their finger. As yet another example, user 20 can control the unmanned vehicle (e.g., UAV) to move upward (e.g., fly) by contracting muscles to lift their finger, and can control the unmanned vehicle (e.g., UAV) to move downward (e.g., fly) by contracting muscles to lower their finger. Therefore, not only can the unmanned vehicle 120 guide the user, but user 20 can also control the unmanned vehicle 120 to move along any desired trajectory.

[0121] Compared to traditional video or audio guidance, the guidance provided by the unmanned vehicle disclosed herein may result in a larger center of pressure (COP) range, less stable COP progression, and reduced limb movement fluidity.

[0122] In summary, the training method and system disclosed herein, utilizing unmanned vehicles for motion guidance in a three-dimensional real world, not only present challenges to the needs of different users but also involve visual feedback in functional training. Therefore, it achieves more comprehensive and effective training.

[0123] According to this disclosure, various techniques can be used to implement the concepts described in this application without departing from the scope of these concepts. Furthermore, while these concepts have been described with specific reference to certain embodiments, those skilled in the art will understand that changes in form and detail can be made without departing from the scope of these concepts. Therefore, the described embodiments are to be considered illustrative rather than restrictive in all respects. It should also be understood that this disclosure is not limited to the specific embodiments described above. Therefore, many rearrangements, modifications, and substitutions are possible without departing from the scope of this disclosure.

Claims

1. A training method performed by a training system comprising a plurality of unmanned vehicles, the method comprising: The method comprises: ​ controlling movement of the plurality of unmanned vehicles along a plurality of first predetermined trajectories, respectively; detecting a plurality of body responses of a plurality of body parts of a user, each of the plurality of body parts corresponding to one of the plurality of unmanned vehicles; determining whether each of the plurality of body responses matches a predetermined response corresponding to the first predetermined trajectory corresponding thereto; and in a case where it is determined that one of the plurality of body responses does not match the predetermined response corresponding to the first predetermined trajectory corresponding thereto, controlling the corresponding unmanned vehicle to provide a perceptible cue, wherein at least two of the plurality of first predetermined trajectories are different from each other.

2. The training method of claim 1, wherein, Controlling the corresponding unmanned vehicle to provide the perceptible cue comprises: suspending the movement of the corresponding unmanned vehicle.

3. The training method of claim 2, wherein, In a case where it is determined that one of the plurality of body responses matches the predetermined response corresponding to the first predetermined trajectory corresponding thereto, the method further comprises: continuing the movement of the corresponding unmanned vehicle along the first predetermined trajectory corresponding thereto.

4. The training method of claim 1, wherein, Controlling the corresponding unmanned vehicle to provide the perceptible cue comprises: controlling the corresponding unmanned vehicle to move along a second predetermined trajectory different from the first predetermined trajectory corresponding thereto.

5. The training method of claim 1, wherein, Detecting the plurality of body responses of the plurality of body parts of the user comprises obtaining position information of each of the plurality of body parts.

6. The training method of claim 5, wherein, Determining whether each of the plurality of body responses matches the predetermined response corresponding to the first predetermined trajectory corresponding thereto comprises: determining, according to the position information, whether a first unmanned vehicle of the plurality of unmanned vehicles is within a predetermined range of the corresponding body part; in a case where the first unmanned vehicle is outside the predetermined range, determining that the body response of the corresponding body part does not match the predetermined response corresponding to the first predetermined trajectory of the first unmanned vehicle; and in a case where the first unmanned vehicle is within the predetermined range, determining that the body response of the corresponding body part matches the predetermined response corresponding to the first predetermined trajectory of the first unmanned vehicle.

7. The training method of claim 5, wherein, Determining whether each of the plurality of body responses matches the predetermined response corresponding to the first predetermined trajectory corresponding thereto comprises: determining, according to the position information, whether a first unmanned vehicle of the plurality of unmanned vehicles is greater than a maximum threshold value from the corresponding body part; in a case where the first unmanned vehicle is greater than the maximum threshold value, determining that the body response of the corresponding body part does not match the predetermined response corresponding to the first predetermined trajectory of the first unmanned vehicle; and in a case where the first unmanned vehicle is not greater than the maximum threshold value, determining that the body response of the corresponding body part matches the predetermined response corresponding to the first predetermined trajectory of the first unmanned vehicle.

8. The training method of claim 5, wherein, Determining whether each of the plurality of body responses matches the predetermined response corresponding to the first predetermined trajectory corresponding thereto comprises: determining, according to the position information, whether a distance between a first unmanned vehicle of the plurality of unmanned vehicles and the corresponding body part is less than a minimum threshold; determining, in the case that the distance is less than the minimum threshold, that the body reaction of the corresponding body part does not match a preset reaction corresponding to the first preset trajectory of the first unmanned vehicle; and determining, in the case that the distance is not less than the minimum threshold, that the body reaction of the corresponding body part matches the preset reaction corresponding to the first preset trajectory of the first unmanned vehicle.

9. The training method of claim 8, wherein, controlling the perceivable cues provided by the corresponding unmanned vehicle comprises: controlling the first unmanned vehicle to move away from the corresponding body part.

10. The training method of claim 1, wherein, detecting the plurality of body reactions of the plurality of body parts of the user respectively comprises obtaining muscle tension information of one of the plurality of body parts, the muscle tension information comprising at least one of a force magnitude and a force direction.

11. A training system comprising: a plurality of unmanned vehicles; a sensor configured to detect a plurality of body reactions of a plurality of body parts of a user; a controller coupled to the plurality of unmanned vehicles and the sensor; and a memory coupled to the controller and storing a plurality of first preset trajectories corresponding to the plurality of unmanned vehicles, wherein the memory further stores at least one computer-executable instruction that, when executed by the controller, causes the controller to perform the training method of any one of claims 1-10. ​

Images