Facial expression control method and bionic robot

Abstract

The application relates to the technical field of bionic robots, and particularly discloses an expression control method and a bionic robot. The expression control method comprises the following steps: receiving an expression instruction, analyzing the expression instruction and obtaining a target expression corresponding to the expression instruction; based on the target expression, obtaining target inserts in multiple inserts, and obtaining driving time sequence parameters of driving mechanisms corresponding to each target insert; wherein one of the motion starting time, the displacement peak value and the motion stopping time of at least two target inserts is different; and driving the corresponding target inserts to move according to the corresponding driving time sequence parameters. When the target expression is formed, the face skin body simulates the biomechanical principle that the subcutaneous muscle contraction drives the skin movement, so that the expression of the robot has a subtle sequence, the mechanical feeling of the face skin structure is reduced, the expression is more lively and natural, and the use performance of the bionic robot is improved.

Description

Technical Field

[0001] This invention relates to the field of bionic robot technology, and more particularly to facial expression control methods and bionic robots. Background Technology

[0002] Bionic robots are automated machines that perform tasks. They can be controlled by humans, run pre-programmed routines, or act according to principles established using artificial intelligence. Bionic robots can assist or replace humans in their work, providing convenient services such as shopping assistance, tour guiding, and information retrieval. They can also perform dangerous or difficult tasks, showing great promise for future development. While bionic robots can have the same body shape and appearance as real humans, their realism and expressive abilities directly impact the human-computer interaction experience. To achieve highly realistic facial expressions, the skin structure of a bionic robot needs excellent flexibility, fit, and motion reproduction capabilities. Traditional bionic facial expression control typically uses fixed preset expression libraries or simple parameter mapping, failing to achieve flexible and natural real-time expression replication and conversion, resulting in a strong mechanical feel to the expressions of bionic robots.

[0003] Therefore, a facial expression control method and a bionic robot are needed to solve the above problems. Summary of the Invention

[0004] The purpose of this invention is to provide an expression control method and a bionic robot to solve the problem of strong mechanical expression in the expressions of bionic humanoid robots in related technologies.

[0005] On one hand, the present invention provides an expression control method for controlling the expressions of a bionic robot. The bionic robot includes a head support, a drive mechanism, and a facial skin structure. The facial skin structure includes a connected facial skin body and multiple inserts. The drive mechanism is disposed on the head support and includes multiple drive structures. The facial skin body is connected to the drive mechanism through the multiple inserts, and each insert corresponds to at least one drive structure. The expression control method includes: S10. Receive an expression command, parse the expression command, and obtain the target expression corresponding to the expression command; S20. Based on the target expression, obtain the target embedding among the multiple embeddings, and obtain the driving timing parameters of the driving mechanism corresponding to each target embedding; wherein, at least two of the target embeddings have different motion start time, displacement peak value and motion stop time. S30. Drive the corresponding target insert to move according to the corresponding driving timing parameters.

[0006] As an optional technical solution, obtaining the driving timing parameters of the driving mechanism corresponding to each target insert specifically involves: S21. Set a preset expression, determine the position change of each target embedding executing the preset expression over time based on the motion trajectory of the actual human face at each moment of forming the preset expression, and generate theoretical driving timing parameters.

[0007] As an optional technical solution, the following is also included after S21: S22. Select the preset expression, call the theoretical driving timing parameters of the preset expression, and control the multiple driving components to drive the corresponding multiple target embeddings to execute the theoretical driving timing parameters; S23. During the process of forming the preset expression, the actual deformation data of the face body is collected, and the actual deformation data is compared with the preset standard deformation data of the actual face to obtain the offset error of the preset expression. Based on the offset error, the theoretical driving timing parameters are adjusted until the difference between the actual deformation data and the standard deformation data is less than the preset difference.

[0008] As an optional technical solution, S23 specifically includes: During the process of forming the preset expression, the actual deformation data of the face body at any time is collected, and the actual deformation data at the current time is compared with the standard deformation data of the actual face at the corresponding time to obtain the motion error of each target embedding at the current time. Based on the motion error, the theoretical timing control parameters of each target embedding are adjusted until, at any time, the difference between the actual deformation data and the standard deformation data is less than the preset difference.

[0009] As an optional technical solution, the actual deformation data of the face body at any given moment is collected during the formation of the preset expression as follows: During the process of the face body forming the preset expression, at any time, the displacement of the face body surface corresponding to the multiple target inserts is collected by the displacement acquisition device to form a displacement field at any time. The displacement field at any time is the actual deformation data at the current time.

[0010] As an optional technical solution, S23 specifically includes: During the process of forming the preset expression, the actual displacement curves of each target embedding at the face body are collected. The actual displacement curves are compared with the standard displacement curves at the corresponding positions of the actual human face to obtain the displacement curve diagrams of each target embedding. Based on the displacement curve diagrams, the theoretical timing control parameters of each target embedding are adjusted until the difference between the actual displacement curves and the standard displacement curves of each target embedding is less than a set difference.

[0011] As an optional technical solution, the driving timing parameters include at least the following parameters: motion start time, motion start position, maximum displacement position time, maximum displacement position, motion stop time, and motion stop position.

[0012] As an optional technical solution, the facial expression control method further includes: When the face body is in the initial expression state, the initial position information of each of the inserts is recorded and stored; and / or, Upon receiving a reset command, the initial expression is set to the target expression.

[0013] The facial expression control method provided by this invention has at least the following beneficial effects: The facial expression control method provided by this invention includes receiving facial expression commands, parsing the facial expression commands, and obtaining the target facial expression corresponding to the facial expression commands; based on the target facial expression, obtaining target embeddings among multiple embeddings, and obtaining the driving timing parameters of the driving mechanism corresponding to each target embedding; wherein, at least two target embeddings have one different value among their motion start time, peak displacement, and stop time; and driving the corresponding target embeddings to move according to the corresponding driving timing parameters. This facial expression control method, when forming a target facial expression, by setting one different value among the motion start time, peak displacement, and stop time of any two target embeddings, allows the facial skin body to simulate the biomechanical principle of muscle contraction driving skin movement under the dermis, driven by each target embedding. When forming the target facial expression, the facial skin body has a movement sequence corresponding to the subtle sequential order of different muscle groups in a real human expression, thereby making the robot's expression more human-like, reducing the mechanical feel of the facial skin structure during the formation of the target facial expression, making the expression more vivid and natural, and thus improving the usability of the bionic robot.

[0014] On the other hand, the present invention provides a bionic robot, including a head support, a drive mechanism, and a facial skin structure. The facial skin structure includes a facial skin body connected to each other and multiple inserts. The drive mechanism is disposed on the head support and includes multiple drive structures. The facial skin body is connected to the drive mechanism through multiple inserts, and each insert corresponds to at least one drive structure, for implementing the above-mentioned expression control method.

[0015] The bionic robot provided by this invention has at least the following beneficial effects: The bionic robot provided by this invention, by implementing the above-mentioned expression control method, can reduce the mechanical feel of the facial skin structure, making it more stable during and after the formation of expressions, thereby improving the vividness and naturalness of the formed expressions, and thus improving the performance of the bionic robot. Attached Figure Description

[0016] Figure 1 This is a flowchart of the facial expression control method in an embodiment of the present invention; Figure 2 This is a schematic diagram of the facial skin structure in an embodiment of the present invention.

[0017] In the picture: 10. The face itself; 20. Inlay; 21. Left eyebrow inlay; 22. Left upper eyelid inlay; 23. Left ear inlay; 24. Nose-lower eyelid inlay; 25. Upper left mouth inlay; 26. Left corner of mouth inlay; 27. Lower left mouth inlay; 28. Lower middle lip inlay; 29. ​​Upper face positioning inlay; 210. Right eyebrow inlay; 211. Right upper eyelid inlay; 212. Right ear inlay; 213. Upper middle lip inlay; 214. Upper right mouth inlay; 215. Right corner of mouth inlay; 216. Lower right mouth inlay; 217. Mushroom screw; 218. Chin inlay. Detailed Implementation

[0018] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance. The terms "first position" and "second position" refer to two different positions. Furthermore, "above," "on top of," and "over" the first feature in relation to the second feature includes the first feature directly above and diagonally above the second feature, or simply indicates that the first feature is at a higher horizontal level than the second feature. "Below," "under," and "below" the first feature in relation to the second feature includes the first feature directly below and diagonally below the second feature, or simply indicates that the first feature is at a lower horizontal level than the second feature.

[0020] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0021] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0022] like Figure 1 As shown, this embodiment provides an expression control method for controlling the expressions of a bionic robot. The bionic robot includes a head support, a drive mechanism, and a facial skin structure. The facial skin structure includes a connected facial skin body 10 and multiple inserts 20. The drive mechanism is disposed on the head support and includes multiple drive structures. The facial skin body 10 is connected to the drive mechanism through multiple inserts 20, and each insert 20 corresponds to at least one drive structure. The expression control method includes the following steps.

[0023] S10. Receive the emoticon command, parse the emoticon command, and obtain the target emoticon corresponding to the emoticon command.

[0024] Specifically, in this embodiment, the bionic robot also includes a controller, and each drive structure is communicatively connected to the controller. The controller can independently control the movement of each drive structure, thereby controlling the movement of each insert 20.

[0025] Specifically, after the controller receives an expression command, it will parse the expression command to obtain the target expression that the facial structure needs to form.

[0026] S20. Based on the target expression, obtain the target embeddings among multiple embeddings 20, and obtain the driving timing parameters of the driving mechanism corresponding to each target embedding; wherein, at least two target embeddings have different motion start time, displacement peak value and motion stop time.

[0027] Specifically, in this embodiment, the insert 20 that needs to move to form the target expression is called the target insert. The controller can acquire the driving timing parameters of all target inserts and control each target insert to move according to the corresponding driving timing parameters. During the movement of each target insert, at least two of the three parameters—the start time of movement, the peak displacement, and the stop time—are different. This setting makes the facial structure more consistent with the subtle sequence of the formation of the target expression on an actual human face, thereby improving the vividness and flexibility of the bionic robot's expression and enhancing the robot's performance.

[0028] Furthermore, this setup can break down complex target expressions into repeatable driving timing parameters for each target embedding, enabling the bionic robot to stably reproduce preset expressions. Moreover, when repeatedly forming the same target expression, the driving timing parameters remain consistent, preventing the same target expression from being displayed differently each time, thereby improving the performance of the bionic robot.

[0029] Optionally, in this embodiment, multiple expressions are pre-stored in the controller. The multiple expressions include an initial expression and multiple target expressions. The initial expression corresponds to the initial state of the facial skin structure. The multiple target expressions can be directly switched from the initial expression, and any two different target expressions can be directly switched.

[0030] Optionally, in this embodiment, before switching expressions, the current expression is collected, and based on the current expression and the target expression, the required driving timing parameters for the driving mechanism corresponding to each target embedding to switch from the current expression to the target expression are obtained, so that the robot can smoothly switch to the target expression regardless of its current expression.

[0031] Furthermore, the specific steps for obtaining the driving timing parameters of the driving mechanism corresponding to each target insert are as follows: S21. Set a preset expression. Based on the motion trajectory of the preset expression formed by the actual human face at each moment, determine the position change of each target embedding as the preset expression is executed over time, and generate theoretical driving timing parameters.

[0032] Specifically, in this embodiment, when forming the driving timing parameters of the preset expression, during the process of the actual face forming the preset expression, the displacement of the actual face corresponding to each target embedding point is collected to form the displacement curve of each target embedding. Based on the displacement curve of each target embedding, a table of displacement of each target embedding over time is formed, and the driving timing parameters of the driving mechanism corresponding to each target embedding are generated.

[0033] Optionally, in this embodiment, each preset expression is repeatedly set, and the above S21 operation is repeated for each preset expression, thereby forming a driving timing parameter table for the expression library of the bionic robot, which can have good smoothness when the bionic robot executes any target expression in the future.

[0034] Furthermore, the following steps are included after step S21: S22. Select a preset emoticon, call the theoretical driving timing parameters of the preset emoticon, and control multiple driving components to drive the corresponding multiple target embeddings to execute the theoretical driving timing parameters.

[0035] Specifically, in this embodiment, after generating the theoretical driving timing parameters of the preset expression, when the driving mechanism drives the target insert to move the face body 10 locally, the mutual pulling of different areas of the face body 10 causes a difference in similarity between the actual expression and the preset expression. Therefore, it is necessary to verify the theoretical driving timing parameters.

[0036] Specifically, when verifying the theoretical driving timing parameters, a preset expression is selected, the controller calls the theoretical driving timing parameters of the preset expression, and controls multiple target embeddings corresponding to the preset expression to execute the theoretical driving timing parameters, so that the preset expression is formed on the face body 10.

[0037] S23. During the process of forming the preset expression, the actual deformation data of the face body 10 is collected, and the actual deformation data is compared with the standard deformation data of the actual human face to obtain the offset error of the preset expression. The timing parameters are driven based on the offset error adjustment theory until the difference between the actual deformation data and the standard deformation data is less than the preset difference.

[0038] Specifically, in this embodiment, during the formation of the preset expression, the actual deformation data of the actual expression formed on the face body 10 is compared with the preset standard deformation data. This allows for the determination of the offset error at any target insert at any given time. Based on this offset error, the theoretical driving timing parameters are adjusted until the difference between the actual deformation data and the standard deformation data is less than a preset difference. The theoretical driving timing parameters at this point are then the final driving timing parameters. This verification process continuously improves the preset expression, making it more vivid and thus enhancing the performance of the bionic robot.

[0039] Optionally, in this embodiment, S23 specifically involves: during the process of forming a preset expression, collecting actual deformation data of the face body 10 at any time, comparing the actual deformation data at the current time with the preset standard deformation data corresponding to the actual face at the current time, obtaining the motion error of each target insert at the current time, and adjusting the theoretical timing control parameters of each target insert based on the motion error, until at any time, the difference between the actual deformation data and the standard deformation data is less than the preset difference.

[0040] Specifically, when collecting the actual deformation data of the face body 10, it is necessary to compare the actual deformation data of the face body 10 at any time with the preset standard deformation data of the actual human face at the current time, so that the offset error is continuous data. This ensures that the movement of the face body 10 matches the muscle movement of the actual human face throughout the process of forming the preset expression, thereby further improving the vividness of the process of forming the preset expression.

[0041] Furthermore, in the process of forming the preset expression, the actual deformation data of the face body 10 at any time is collected as follows: In the process of the face body 10 forming the preset expression, at any time, the displacement of the face body 10 surface corresponding to multiple target inserts is collected by the displacement acquisition device to form the displacement field at any time. The displacement field at any time is the actual deformation data at the current time.

[0042] Specifically, in this embodiment, the displacement acquisition device includes multiple acquisition points, which are set one-to-one with multiple target inserts. By using the displacement acquisition device, the displacement of the face body 10 surface corresponding to the multiple target inserts can be acquired in real time, ensuring the reliability of the acquired data, thereby ensuring the reliability and effectiveness of the driving timing parameters and improving the performance of the bionic robot.

[0043] Optionally, in another embodiment, S23 specifically involves: during the process of forming a preset expression, acquiring the actual displacement curves of the face body 10 where each target embedding is located, comparing each actual displacement curve with the standard displacement curve of the face body 10 at the corresponding position to obtain the displacement curve diagram of each target embedding, and adjusting the theoretical timing control parameters of each target embedding based on the displacement curve diagram until the difference between the actual displacement curve and the standard displacement curve of each target embedding is less than the set difference.

[0044] Specifically, in another embodiment, the change curve of the same target embedding over time can be continuously collected and compared with the standard displacement curve of the actual face at the corresponding point, thereby verifying the theoretical driving timing parameters of the target embedding. No specific limitations are imposed here.

[0045] Furthermore, the driving timing parameters include at least the following parameters: motion start time, motion start position, maximum displacement position time, maximum displacement position, motion stop time, and motion stop position.

[0046] Specifically, in this embodiment, the start time of movement defines the time when the insert 20 begins to move, the stop time of movement defines the time when the insert 20 stops moving, the maximum displacement position and the maximum displacement position together define the state at the peak of the movement of the insert 20, and the start position and the stop position of movement are used to define the amount of displacement of the insert 20 before and after forming the target expression. By setting different start times, start positions, maximum displacement positions, maximum displacement positions, stop times and stop positions for each insert 20, it is possible to ensure that the face body 10 is more vivid in the process of forming an expression.

[0047] Optionally, in some embodiments, during the process of switching from the current expression to the target expression, the displacement of some inserts 20 first increases and then decreases, so that the maximum displacement position will appear between the start time of the movement and the stop time of the movement.

[0048] Optionally, in some embodiments, during the process of switching from the current expression to the target expression, the displacement of some embeddings 20 gradually increases, so that the maximum displacement position is at the same time as the movement stops, and the displacement of the maximum displacement position and the movement stops are the same. In other embodiments, during the process of switching from the current expression to the target expression, the displacement of some embeddings 20 gradually decreases, so that the maximum displacement position is at the same time as the movement starts, and the displacement of the maximum displacement position and the movement starts are the same. These will not be elaborated further here.

[0049] Furthermore, the expression control method also includes: when the face body 10 is in the initial expression state, recording and storing the initial position information of each embedding 20.

[0050] Specifically, in this embodiment, storing the initial position information of each of the embeddings 20 of the face body 10 in the initial expression makes it easier to judge the target expression based on the initial expression.

[0051] Optionally, in some embodiments, when the controller receives a reset command, the initial expression is set to the target expression for switching.

[0052] S30. Drive the corresponding target insert to move according to the corresponding driving timing parameters.

[0053] Specifically, in this embodiment, each target insert is driven to move according to the corresponding driving timing parameters, thereby ensuring that the face body 10 can conform to the vividness of the target expression formed by the actual human face during the formation of the target expression, thereby improving the performance of the bionic robot.

[0054] Furthermore, the following steps are included after S30: S40. After all target inserts have stopped moving, control all target inserts to maintain their current positions and hold them for a preset time.

[0055] Specifically, in this embodiment, after all the target inserts have stopped moving, the target expression is formed, and all the target inserts are controlled to maintain their current position for a preset time, so that the target expression can be clearly perceived by the observer, avoiding it from flashing by and improving the user experience.

[0056] Optionally, in this embodiment, the preset time ranges from 0.5s to 2s, and no specific limitation is made here.

[0057] like Figure 2 As shown, this embodiment also provides a bionic robot, including a head support, a drive mechanism, and a facial skin structure. The facial skin structure includes a connected facial skin body 10 and multiple inserts 20. The drive mechanism is disposed on the head support and includes multiple drive structures. The facial skin body 10 is connected to the drive mechanism through multiple inserts 20, and each insert 20 corresponds to at least one drive structure for implementing the aforementioned expression control method. By implementing the aforementioned expression control method, the bionic robot in this embodiment can reduce the mechanical feel of the facial skin structure, making it more stable during and after the formation of expressions, thereby improving the vividness and naturalness of the formed expressions, and thus improving the usability of the bionic robot.

[0058] Furthermore, in this embodiment, the multiple inserts 20 include partial contouring inserts, including a left eyebrow contouring insert 21, a nose-lower eyelid contouring insert 24, a right eyebrow contouring insert 210, and a chin contouring insert 218. The left eyebrow contouring insert 21 and the right eyebrow contouring insert 210 are respectively provided with a left eyebrow contouring surface and a right eyebrow contouring surface that match the frontal bone of the human face structure; the nose-lower eyelid contouring insert 24 is provided with a nose-lower eyelid contouring surface that matches the nasal bone, infraorbital margin, and nasal cartilage of the human face structure; the chin contouring insert 218 is provided with a chin contouring surface that matches the mandible of the human face structure. This arrangement allows the static facial skin structure to approximate the actual facial structure, enhancing the realism of the facial skin structure.

[0059] In this embodiment, as Figure 1 As shown, the face structure also includes an upper eyelid left insert 22, an ear left insert 23, a mouth upper left insert 25, a left corner of the mouth insert 26, a mouth lower left insert 27, a lip lower middle insert 28, an upper face positioning insert 29, an upper eyelid right insert 211, an ear right insert 212, a lip upper middle insert 213, a mouth upper right insert 214, a mouth corner right insert 215, and a mouth lower right insert 216, which are used to support the face body and form related target expressions.

[0060] Obviously, the above description is merely a preferred embodiment of the present invention and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure involved in this invention is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in this invention.

Claims

1. An expression control method for controlling the expression of a bionic robot, the bionic robot comprising a head support, a drive mechanism, and a facial skin structure, the facial skin structure comprising a connected facial skin body (10) and multiple inserts (20), the drive mechanism being disposed on the head support, the drive mechanism comprising multiple drive structures, the facial skin body (10) being connected to the drive mechanism via multiple inserts (20), and each insert (20) corresponding to at least one drive structure, characterized in that, The facial expression control method includes: S10. Receive an expression command, parse the expression command, and obtain the target expression corresponding to the expression command; S20. Based on the target expression, obtain the target embeddings among the multiple embeddings (20), and obtain the driving timing parameters of the driving mechanism corresponding to each target embedding; wherein, at least two of the target embeddings have different motion start time, displacement peak value and motion stop time. S30. Drive the corresponding target insert to move according to the corresponding driving timing parameters.

2. The facial expression control method according to claim 1, characterized in that, Following S30, the following is also included: S40. After all the target inserts have stopped moving, control all the target inserts to maintain their current positions for a preset time.

3. The facial expression control method according to claim 1, characterized in that, The specific steps for obtaining the driving timing parameters of the driving mechanism corresponding to each target insert are as follows: S21. Set a preset expression, determine the position change of each target embedding executing the preset expression over time based on the motion trajectory of the actual human face at each moment of forming the preset expression, and generate theoretical driving timing parameters.

4. The facial expression control method according to claim 3, characterized in that, Following S21, the following is also included: S22. Select the preset expression, call the theoretical driving timing parameters of the preset expression, and control the multiple driving components to drive the corresponding multiple target embeddings to execute the theoretical driving timing parameters; S23. During the process of forming the preset expression, the actual deformation data of the face body (10) is collected, the actual deformation data is compared with the preset standard deformation data of the actual face, the offset error of the preset expression is obtained, and the theoretical driving timing parameters are adjusted based on the offset error until the difference between the actual deformation data and the standard deformation data is less than the preset difference.

5. The facial expression control method according to claim 4, characterized in that, Specifically, S23 is: During the process of forming the preset expression, the actual deformation data of the face body (10) at any time is collected, and the actual deformation data at the current time is compared with the standard deformation data of the actual face at the corresponding time to obtain the motion error of each target insert at the current time. Based on the motion error, the theoretical timing control parameters of each target insert are adjusted until at any time, the difference between the actual deformation data and the standard deformation data is less than the preset difference.

6. The facial expression control method according to claim 5, characterized in that, In the process of forming the preset expression, the actual deformation data of the face body (10) at any given time is collected as follows: During the process of the face body (10) forming the preset expression, at any time, the displacement of the face body (10) surface corresponding to the multiple target inserts is collected by the displacement acquisition device to form the displacement field at any time. The displacement field at any time is the actual deformation data at the current time.

7. The facial expression control method according to claim 4, characterized in that, Specifically, S23 is: During the process of forming the preset expression, the actual displacement curves of each target embedding at the face body are collected. The actual displacement curves are compared with the standard displacement curves at the corresponding positions of the actual human face to obtain the displacement curve diagrams of each target embedding. Based on the displacement curve diagrams, the theoretical timing control parameters of each target embedding are adjusted until the difference between the actual displacement curves and the standard displacement curves of each target embedding is less than a set difference.

8. The facial expression control method according to any one of claims 1-7, characterized in that, The driving timing parameters include at least the following parameters: motion start time, motion start position, maximum displacement position time, maximum displacement position, motion stop time, and motion stop position.

9. The facial expression control method according to claim 8, characterized in that, The facial expression control method also includes: When the face body (10) is in the initial expression state, the initial position of each of the inserts (20) is recorded and stored; and / or, Upon receiving a reset command, the initial expression is set to the target expression.

10. A biomimetic robot, comprising a head support, a drive mechanism, and a facial skin structure, wherein the facial skin structure comprises a connected facial skin body (10) and a plurality of inserts (20), the drive mechanism is disposed on the head support, the drive mechanism comprises a plurality of drive structures, the facial skin body (10) is connected to the drive mechanism through the plurality of inserts (20), and each insert (20) corresponds to at least one drive structure, characterized in that, Used to implement the facial expression control method according to any one of claims 1-9.

Images