Multi-part expression cooperative control method, device, system, equipment and product of anthropomorphic robot

Abstract

The invention discloses an anthropomorphic robot multi-part expression cooperative control method, device, system, equipment and product, and relates to the technical field of anthropomorphic humans. The method comprises the steps of firstly obtaining a target expression control signal, then responding to the signal to obtain one-to-one corresponding and mutually independent silence delay parameters for at least two expression execution mechanisms, then synchronously starting a plurality of silence delays based on the parameters, and finally respectively driving the corresponding execution mechanisms when the delays are finished. Therefore, by introducing independent and adjustable silent delay parameters and synchronously starting, the problems of'programmed sequence sense 'and'mechanical cooperation' caused by asynchronous distribution of multi-part action starting instructions in the prior art are solved, and the biological characteristics of'synchronous response and asynchronous execution 'of human facial neural signals are effectively simulated; therefore, the naturalness and life feeling of robot expressions are remarkably improved, and practical application and popularization are facilitated.

Description

Technical Field

[0001] This invention belongs to the field of bionic human technology, specifically relating to a method, device, system, equipment, and product for coordinated control of multiple facial expressions of an anthropomorphic robot. Background Technology

[0002] With the rapid development of humanoid and social robot technologies, the naturalness and anthropomorphism of their facial expressions have become crucial for enhancing human-computer interaction and establishing emotional connections. However, current technological approaches to achieving realistic robot expressions still have significant limitations in terms of temporal collaborative control, resulting in robot expressions often appearing stiff and mechanical, making it difficult to convey subtle emotions.

[0003] Currently, the mainstream methods for controlling anthropomorphic facial expressions mainly follow the following two paths: (1) Expression control based on instruction: This type of system relies on expression triggering instructions (such as instructions to trigger "smile" or "surprise") sent by upper-layer applications or remote control terminals. After receiving the instructions, the robot calls the internally preset fixed action sequence to drive the facial actuator. This method has inherent defects: its control granularity is coarse, that is, the instructions usually only contain "what expression to make", and there is a severe lack of fine planning for "how to serialize the execution", which makes the movement of multiple facial parts present a highly synchronized "mechanical feeling". This method cannot simulate the biological characteristics of "synchronous response but asynchronous execution" inherent in the human facial muscle groups after receiving nerve signals, and thus the generated expressions lack the dynamic rhythm unique to living organisms. (2) Expression control based on visual imitation: This type of system captures human expressions through sensors such as cameras and drives robots to imitate them. Current technology mainly focuses on reproducing the spatial form (such as the angle and height of specific parts) and movement trajectory of the target expression, but generally ignores the accurate reproduction of the temporal dynamics behind the expression. Specifically, existing systems have difficulty in identifying and reproducing the subtle differences in the timing of activation between multiple parts in the source expression (for example, the slight delayed contraction of the orbicularis oculi muscle is crucial for distinguishing between a "sincere smile" and a "polite smile"). Therefore, the imitation expressions generated by it are often "similar in form but not in spirit", appearing stiff and unnatural.

[0004] In summary, both instruction-driven and visual mimicry technologies share a common blind spot at the architectural level: they lack a universally applicable control core capable of uniformly handling the timing of multi-part facial expression coordination. Existing solutions either over-couple timing control with specific instruction sources, resulting in poor scalability, or completely ignore the crucial value of timing information for realism. The root cause lies in the failure to effectively decouple the two levels of "understanding facial expression intent" and "timing coordination of facial expression execution," thus failing to generate highly natural multi-part coordinated facial expressions that conform to biomechanical principles.

[0005] Therefore, there is an urgent need in this field for an innovative control scheme to solve the above problems. Summary of the Invention

[0006] The purpose of this invention is to provide a method, device, system, computer equipment, computer-readable storage product, and computer program product for coordinated control of multiple facial expressions of anthropomorphic robots, in order to solve the problem that existing anthropomorphic facial expression control schemes lack independent asynchronous timing planning for each actuator, resulting in a mechanical feel and unnaturalness.

[0007] To achieve the above objectives, the present invention adopts the following technical solution: Firstly, a method for coordinated control of multiple facial expressions in anthropomorphic robots is provided, including: Acquire the target facial expression control signal; The target facial expression control signal is responded to as follows: at least two silent delay parameters that correspond one-to-one with and are independent of each other, corresponding to at least two facial expression actuators of the humanoid robot; Synchronous startup is based on at least two silent delays that correspond one-to-one with the at least two facial expression execution mechanisms, respectively; For each of the at least two silent delays, the corresponding facial expression execution mechanism is triggered at the end of the corresponding delay.

[0008] Based on the above-mentioned invention, a novel and universally applicable control scheme is provided that can uniformly handle the timing of multi-part facial expression coordination. This involves first acquiring the target facial expression control signal, then responding to the signal to obtain one-to-one and independent silent delay parameters for at least two facial expression actuators, then synchronously initiating multiple silent delays based on these parameters, and finally driving the corresponding actuators at the end of each delay. By introducing independently adjustable silent delay parameters and activating them synchronously, this overcomes the problems of "programmed sequence" and "mechanical coordination" caused by asynchronous distribution of multi-part action activation commands in existing technologies. It effectively simulates the biological characteristics of "synchronous response and asynchronous execution" of human facial nerve signals, thereby significantly improving the naturalness and lifelikeness of robot expressions, facilitating practical application and promotion.

[0009] In one possible design, the target expression control signal includes a data packet from a network or external control terminal indicating the presentation of the target expression, or video data of a real person's expression from a camera indicating the reproduction of the target expression.

[0010] In one possible design, when the target expression control signal is an instruction data packet from a network or external control terminal used to instruct the presentation of the target expression, at least two silent delay parameters, each corresponding one-to-one with and independent of the at least two expression actuators, are acquired, including: Parse at least two silent delay parameters from the instruction data packet, which correspond one-to-one with at least two facial expression actuators and are independent of each other.

[0011] In one possible design, when the target expression control signal is real-life facial expression video data from a camera used to indicate the reproduction of the target expression, at least two silent delay parameters, each corresponding one-to-one with and independent of the at least two expression actuators, are acquired, including: Visual analysis is performed on the real-person facial expression video data, and at least two silent delay parameters that correspond one-to-one with and are independent of each other are calculated based on the visual analysis results.

[0012] In one possible design, visual analysis is performed on the real-person facial expression video data, and based on the visual analysis results, at least two silent delay parameters that correspond one-to-one with and are independent of at least two facial expression actuators are calculated, including: Visual analysis is performed on the real-person facial expression video data to obtain at least two action intensity time-series data that correspond one-to-one with at least two facial expressions; Based on the timing data of the intensity of the at least two actions, determine the facial expression with the earliest start time from the at least two facial expressions; For each of the at least two facial expressions, the corresponding start time is first determined based on the corresponding action intensity timing data. Then, the time difference between the start time and the start time of a certain facial expression is calculated to obtain the corresponding relative time difference. Finally, the silent delay parameter of the corresponding facial expression execution mechanism is determined based on the relative time difference.

[0013] Secondly, a humanoid robot multi-part facial expression collaborative control device is provided, including a control signal acquisition unit, a static delay parameter acquisition unit, a silent delay start unit, and an actuator triggering unit that are sequentially connected in communication. The control signal acquisition unit is used to acquire the target facial expression control signal; The silent delay parameter acquisition unit is used to respond to the target expression control signal in the following manner: acquire at least two silent delay parameters that correspond one-to-one with and are independent of at least two expression actuators of the humanoid robot; The silent delay start unit is used to synchronously start at least two silent delays that are based on the at least two silent delay parameters and correspond one-to-one with the at least two facial expression execution mechanisms. The actuator triggering unit is used to trigger the corresponding facial expression actuator at the end of each of the at least two silence delays.

[0014] Thirdly, the present invention provides a humanoid robot multi-part facial expression collaborative control system, including a remote control device, a remote control service device, a bionic motion workshop and a robot terminal, wherein the robot terminal integrates several facial expression execution mechanisms; The remote control device is communicatively connected to the remote control service device and is used to send target facial expression control signals and transmit them to the remote control service device. The remote control service device is communicatively connected to the bionic motion workshop and is used to forward the target facial expression control signal to the bionic motion workshop. The bionic motion workshop is communicatively connected to the robot terminal and is used to execute the anthropomorphic robot multi-part facial expression collaborative control method as described in the first aspect or any possible design in the first aspect after receiving the target facial expression control signal.

[0015] Fourthly, the present invention provides a computer device comprising a storage module, a processing module, and a transceiver module connected in sequence for communication, wherein the storage module is used to store a computer program, the transceiver module is used to send and receive messages, and the processing module is used to read the computer program and execute the anthropomorphic robot multi-part facial expression collaborative control method as described in the first aspect or any possible design in the first aspect.

[0016] Fifthly, the present invention provides a computer-readable storage product storing instructions that, when executed on a computer, perform the anthropomorphic robot multi-part facial expression collaborative control method as described in the first aspect or any possible design in the first aspect.

[0017] In a sixth aspect, the present invention provides a computer program product, including a computer program or instructions, wherein the computer program or instructions, when executed by a computer, implement the anthropomorphic robot multi-part facial expression collaborative control method as described in the first aspect or any possible design in the first aspect.

[0018] The beneficial effects of the above scheme are: (1) This invention creatively provides a new control scheme that can uniformly process the timing of multi-part facial expression coordination and has universality. That is, firstly, the target facial expression control signal is obtained, then the signal is responded to to obtain one-to-one and mutually independent silent delay parameters for at least two facial expression execution mechanisms, then multiple silent delays based on these parameters are synchronously started, and finally the corresponding execution mechanisms are driven at the end of each delay. In this way, by introducing independently adjustable silent delay parameters and starting synchronously, the problems of "programmed sequence" and "mechanical coordination" caused by the asynchronous distribution of multi-part action start instructions in the prior art are overcome. It effectively simulates the biological characteristics of "synchronous response and asynchronous execution" of human facial nerve signals, thereby significantly improving the naturalness and life of robot expressions. (2) It can achieve the universality and decoupling of the control architecture. That is, as an independent "time-coordination layer", this solution can be seamlessly compatible with different signal sources. This achieves effective decoupling between "expression intention understanding" and "time-coordination execution", providing a universal control core. (3) It can accurately reproduce biological temporal dynamics. That is, through visual analysis of real people's facial expression videos, it can extract and reproduce the subtle differences in the starting timing between the movements of each part. This makes the robot's imitation not only "similar in form" but also "similar in spirit", capturing and reproducing the key charm of expressions such as "sincere smile" that depend on timing. In summary, this solution, based on biomimetic principles, achieves a breakthrough at the architectural level, significantly improving the dynamic naturalness and lifelikeness of humanoid robot expressions, facilitating practical application and promotion. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating the humanoid robot multi-part facial expression collaborative control method provided in an embodiment of this application.

[0021] Figure 2 This is a schematic diagram of the structure of the anthropomorphic robot multi-part facial expression collaborative control device provided in the embodiments of this application.

[0022] Figure 3 This is a schematic diagram of the structure of the humanoid robot multi-part facial expression collaborative control system provided in the embodiments of this application.

[0023] Figure 4A schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in conjunction with the accompanying drawings and descriptions of the embodiments or the prior art. Obviously, the following description of the structure of the accompanying drawings is only some embodiments of the present invention. For those skilled in the art, other embodiments can be obtained based on these embodiments without creative effort. It should be noted that the description of these embodiments is for the purpose of helping to understand the present invention, but does not constitute a limitation of the present invention.

[0025] It should be understood that although the terms "first" and "second", etc., may be used herein to describe various objects, these objects should not be limited by these terms. These terms are only used to distinguish one object from another. For example, the first object may be referred to as the second object, and similarly, the second object may be referred to as the first object, without departing from the scope of the exemplary embodiments of the invention.

[0026] It should be understood that the term "and / or" that may appear in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, B exists alone, or A and B exist simultaneously. Another example is A, B and / or C, which can mean that any one of A, B, and C or any combination thereof exists. The term " / and" that may appear in this document describes another relationship between related objects, indicating that two relationships can exist. For example, A / and B can mean: A exists alone or A and B exist simultaneously. In addition, the character " / " that may appear in this document generally indicates that the related objects before and after it are in an "or" relationship.

[0027] Example like Figure 1 As shown, the anthropomorphic robot multi-part facial expression collaborative control method provided in the first aspect of this embodiment can be executed, but is not limited to, by a computer device with certain computing resources, such as... Figure 3As shown, the humanoid robot's multi-part facial expression collaborative control system is executed in a bionic motion workshop. This system includes, but is not limited to, a remote control device, a remote control service device, and a robot terminal. The robot terminal integrates several facial expression execution mechanisms (i.e., the robot terminal is a bionic robot with a bionic robot head and artificial skin, making it look like a real person; the facial expression execution mechanisms can make corresponding facial expressions through the movement of mechanisms such as motors). The remote control device is communicatively connected to the remote control service device and is used to send target facial expression control signals to the remote control service device. Specifically, it can be a video or image acquisition device such as a camera, or a controller for issuing action commands. The remote control service device is communicatively connected to the bionic motion workshop and is used to forward the target facial expression control signals to the bionic motion workshop, acting as a logic control center. The bionic motion workshop is communicatively connected to the robot terminal to achieve multi-part facial expression collaborative control. Figure 1 As shown, the humanoid robot multi-part facial expression collaborative control method includes, but is not limited to, the following steps S1 to S4.

[0028] S1. Obtain the target facial expression control signal.

[0029] In step S1, the target expression control signal is a control signal carrying target expression information. Specifically, it includes, but is not limited to, instruction data packets from a network or external control terminal used to instruct the presentation of the target expression, or video data of a real person's expression from a camera used to instruct the reproduction of the target expression. Therefore, whether anyone uses remote control or a camera sensor to mimic human facial expressions to make the bionic robot's face display the same expression, it is all within the scope of this embodiment. Furthermore, the target expression control signal can be transmitted from the network or the external control terminal, or it can be transmitted from the camera.

[0030] S2. Respond to the target facial expression control signal as follows: acquire at least two silent delay parameters that correspond one-to-one with and are independent of each other, at least two facial expression actuators of the humanoid robot.

[0031] In step S2, the at least two facial expression actuators are used to present / reproduce the target facial expression by coordinating corresponding actions. For example, when the target facial expression is a "smiling" expression, the at least two facial expression actuators include, but are not limited to, left / right eye blinking actuators, mouth opening actuators, left / right eyebrow drooping actuators, and left / right corner-of-the-mouth raising actuators. The silent delay parameter is used to simulate the biological characteristics of delayed activation of the human muscle groups corresponding to the facial expression actuators under the drive of neural signals. Specifically, it can be the duration of a silent delay, that is, this delay will be synchronously activated and trigger the action of the corresponding actuator after its end. Specifically, when the target expression control signal is an instruction data packet from the network or an external control terminal used to instruct the presentation of the target expression, at least two silent delay parameters that correspond one-to-one with and are independent of at least two expression execution mechanisms are obtained, including: parsing at least two silent delay parameters that correspond one-to-one with and are independent of at least two expression execution mechanisms from the instruction data packet; and when the target expression control signal is real-person expression video data from a camera used to instruct the reproduction of the target expression, at least two silent delay parameters that correspond one-to-one with and are independent of at least two expression execution mechanisms are obtained, including: performing visual analysis on the real-person expression video data, and calculating at least two silent delay parameters that correspond one-to-one with and are independent of at least two expression execution mechanisms based on the visual analysis results, including but not limited to the following steps S201 to S203.

[0032] S201. Perform visual analysis on the real-person facial expression video data to obtain at least two action intensity time sequence data that correspond one-to-one with at least two facial expression actions.

[0033] In step S201, the real-person facial expression video data contains multiple consecutive frames of real-person facial expression video images (e.g., 60 frames per second). This allows for frame-by-frame visual analysis processing, such as motion intensity recognition (e.g., first performing motion recognition based on existing algorithms, then performing conventional motion intensity measurement on the motion recognition results to obtain the motion intensity recognition result), resulting in the following set of values: left eye blink intensity: 0.1; right eye blink intensity: 0.1; left eyebrow drooping intensity: 0.3; right eyebrow drooping intensity: 0.2; mouth opening intensity: 0.4. Intensity of left corner of mouth lift: 0.5; etc. (The aforementioned left eye blink, right eye blink, left eyebrow droop, right eyebrow droop, mouth opening, and left corner of mouth lift intensity are the at least two facial expression movements; the aforementioned values ​​represent the intensity of the corresponding specific facial muscle movements, such as the degree of left eye blink and the degree of mouth lift, etc. These values ​​vary between 0 and 1, where 0 represents complete relaxation and 1 represents maximum contraction). Finally, for each of the at least two facial expression movements, all corresponding intensity values ​​are summarized in chronological order to obtain the corresponding temporal data of movement intensity.

[0034] S202. Based on the timing data of the intensity of the at least two actions, determine the facial expression action with the earliest start time from the at least two facial expressions.

[0035] In step S202, specifically, for each of the at least two facial expressions, the corresponding start time needs to be determined based on the corresponding action intensity time series data. Then, the earliest start time is selected from the at least two start times that correspond one-to-one with the at least two facial expressions. Finally, the facial expression corresponding to the earliest start time is determined. The start time refers to when the corresponding action begins. For example, it is necessary to determine when the action of opening the mouth changes from a closed state (i.e., the intensity value is close to 0) to an open state (i.e., the intensity value increases). In detail, it can be determined as follows: set an intensity threshold value for the mouth opening action, such as 0.2; then continuously monitor the intensity time series data of the mouth opening action. Once it is found that it changes from below 0.2 to above 0.2 and continues to rise, it is considered that the action has "started", and this time point (e.g., 0.5 seconds from the start of the imitation) is recorded as the start time corresponding to the mouth opening action. For example, if the blinking of the left eye starts at 0.3 seconds, the opening of the mouth starts at 0.5 seconds, and the drooping of the eyebrows starts at 0.4 seconds, then it can be determined that the blinking of the left eye is the expression action with the earliest starting time.

[0036] S203. For each action in the at least two facial expressions, first determine the corresponding start time based on the corresponding action intensity timing data, then calculate the time difference between the start time and the start time of the facial expression action to obtain the corresponding relative time difference, and finally determine the silent delay parameter of the corresponding facial expression execution mechanism based on the relative time difference.

[0037] In step S203, for example, if the left eye blinking starts at 0.3 seconds, the mouth opening starts at 0.5 seconds, and the eyebrow drooping starts at 0.4 seconds, then the following set of relative time differences can be obtained: left eye blinking action: 0.0 seconds; mouth opening action: 0.2 seconds; eyebrow drooping action: 0.1 seconds; and so on. The aforementioned values ​​are the observed "natural delay." Thus, if we assume that the humanoid robot is given the instruction, "Start making this expression now," then from the moment the instruction is given, based on the aforementioned "natural delay," the humanoid robot can wait for a period of time before starting to move, and the waiting time is different for different parts. In detail, the aforementioned "natural delay" can be scaled proportionally (potentially speeding up or slowing down) and then directly used as the waiting time (i.e., silent delay parameter) of the humanoid robot; for example, when deciding to completely mimic the observed delay: the robot's left eye blinks: after the command is given, it starts blinking after 0 seconds (i.e., it starts immediately, and the silent delay parameter of the left eye blinking action actuator is 0 seconds); the robot's eyebrows droop: after the command is given, it starts moving after 0.1 seconds (i.e., the silent delay parameter of the eyebrow drooping action actuator is 0.1 seconds); the robot's mouth opens: after the command is given, it starts moving after 0.2 seconds (i.e., the silent delay parameter of the mouth opening action actuator is 0.2 seconds). The humanoid robot makes facial expressions at the same pace as a real person: blinking, then drooping its eyebrows 0.1 seconds later, and opening its mouth 0.2 seconds later. This pace can be adjusted; for example, to make the robot make expressions faster, all waiting times can be multiplied by 0.5: left eye blink: 0 seconds wait (i.e., start immediately, the silent delay parameter of the left eye blinking action actuator is 0 seconds); eyebrow drooping: 0.05 seconds wait (i.e., the silent delay parameter of the eyebrow drooping action actuator is 0.05 seconds); mouth opening: 0.1 seconds wait (i.e., the silent delay parameter of the mouth opening action actuator is 0.1 seconds). This way, the humanoid robot makes the same expressions, but faster. Furthermore, the at least two silent delay parameters in the instruction data packet can also be obtained in advance using the aforementioned method, but not limited to non-real-time real-person facial expression video data.

[0038] S3. Synchronously start at least two silent delays that are based on the at least two silent delay parameters and correspond one-to-one with the at least two facial expression execution mechanisms.

[0039] In step S3, specifically, for each of the at least two facial expression execution mechanisms, a corresponding silent delay is initiated at the same reference time (e.g., the time when the target facial expression control signal is acquired or a similar time after acquisition), based on the corresponding silent delay parameter.

[0040] S4. For each of the at least two silence delays, trigger the corresponding facial expression execution mechanism at the end of the corresponding delay.

[0041] In step S4, the purpose of triggering the facial expression execution mechanism is to initiate the execution of the corresponding target action, and then present / reproduce the target facial expression through a series of target actions.

[0042] Therefore, based on the humanoid robot multi-part facial expression collaborative control method described in steps S1 to S4 above, a new and universal control scheme is provided that can uniformly handle the timing of multi-part facial expression collaboration. First, the target facial expression control signal is acquired. Then, in response to this signal, one-to-one and independent silent delay parameters are obtained for at least two facial expression actuators. Next, multiple silent delays based on these parameters are synchronously initiated. Finally, at the end of each delay, the corresponding actuators are driven. By introducing independently adjustable silent delay parameters and synchronously initiating them, the "programmed sequence" and "mechanical collaboration" problems caused by asynchronous distribution of multi-part action initiation commands in existing technologies are overcome. This effectively simulates the biological characteristics of "synchronous response and asynchronous execution" of human facial nerve signals, thereby significantly improving the naturalness and lifelikeness of robot expressions, facilitating practical application and promotion.

[0043] like Figure 2 As shown, the second aspect of this embodiment provides a virtual device for implementing the humanoid robot multi-part facial expression collaborative control method described in the first aspect, including a control signal acquisition unit, a static delay parameter acquisition unit, a silent delay start unit, and an actuator triggering unit that are sequentially connected in communication. The control signal acquisition unit is used to acquire the target facial expression control signal; The silent delay parameter acquisition unit is used to respond to the target expression control signal in the following manner: acquire at least two silent delay parameters that correspond one-to-one with and are independent of at least two expression actuators of the humanoid robot; The silent delay start unit is used to synchronously start at least two silent delays that are based on the at least two silent delay parameters and correspond one-to-one with the at least two facial expression execution mechanisms. The actuator triggering unit is used to trigger the corresponding facial expression actuator at the end of each of the at least two silence delays.

[0044] The working process, working details and technical effects of the aforementioned device provided in the second aspect of this embodiment can be found in the anthropomorphic robot multi-part facial expression collaborative control method described in the first aspect, and will not be repeated here.

[0045] like Figure 3 As shown, the third aspect of this embodiment provides a physical system that applies the humanoid robot multi-part facial expression collaborative control method described in the first aspect, including a remote control device, a remote control service device, a bionic motion workshop, and a robot terminal, wherein the robot terminal integrates several facial expression execution mechanisms; The remote control device is communicatively connected to the remote control service device and is used to send target facial expression control signals and transmit them to the remote control service device. The remote control service device is communicatively connected to the bionic motion workshop and is used to forward the target facial expression control signal to the bionic motion workshop. The bionic motion workshop is communicatively connected to the robot terminal and is used to execute the anthropomorphic robot multi-part facial expression collaborative control method as described in the first aspect after receiving the target facial expression control signal.

[0046] The working process, working details and technical effects of the aforementioned system provided in the third aspect of this embodiment can be found in the anthropomorphic robot multi-part facial expression collaborative control method described in the first aspect, and will not be repeated here.

[0047] like Figure 4 As shown, the fourth aspect of this embodiment provides a computer device for executing the humanoid robot multi-part facial expression collaborative control method as described in the first aspect. The device includes a storage module, a processing module, and a transceiver module connected in sequence. The storage module stores a computer program, the transceiver module sends and receives messages, and the processing module reads the computer program and executes the humanoid robot multi-part facial expression collaborative control method as described in the first aspect. Specifically, the storage module may include, but is not limited to, random-access memory (RAM), read-only memory (ROM), flash memory, first-in-first-out (FIFO) memory, and / or first-in-last-out (FILO) memory, etc.; the processing module may, but is not limited to, use a microprocessor of the STM32F105 series. Furthermore, the computer device may also include, but is not limited to, a power supply module, a display screen, and other necessary components.

[0048] The working process, working details and technical effects of the aforementioned computer device provided in the fourth aspect of this embodiment can be found in the anthropomorphic robot multi-part facial expression collaborative control method described in the first aspect, and will not be repeated here.

[0049] This fifth aspect of the embodiment provides a computer-readable storage product that stores instructions containing the humanoid robot multi-part facial expression collaborative control method as described in the first aspect. Specifically, the computer-readable storage product stores instructions that, when executed on a computer, perform the humanoid robot multi-part facial expression collaborative control method as described in the first aspect. The computer-readable storage product refers to a data storage medium, which may include, but is not limited to, computer-readable storage media such as floppy disks, optical disks, hard disks, flash memory, USB flash drives, and / or Memory Sticks. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0050] The working process, working details and technical effects of the aforementioned computer-readable storage product provided in the fifth aspect of this embodiment can be found in the anthropomorphic robot multi-part facial expression collaborative control method described in the first aspect, and will not be repeated here.

[0051] The sixth aspect of this embodiment provides a computer program product, including a computer program or instructions, which, when executed by a computer, implements the anthropomorphic robot multi-part facial expression collaborative control method as described in the first aspect. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.

[0052] Finally, it should be noted that the above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for coordinated control of multiple facial expressions in anthropomorphic robots, characterized in that, include: Acquire the target facial expression control signal; Respond to the target facial expression control signal in the following manner: Obtain at least two silent delay parameters that correspond one-to-one with and are independent of at least two facial expression actuators of the humanoid robot; Synchronous startup is based on at least two silent delays that correspond one-to-one with the at least two facial expression execution mechanisms, respectively; For each of the at least two silent delays, the corresponding facial expression execution mechanism is triggered at the end of the corresponding delay.

2. The method for coordinated control of multiple facial expressions in anthropomorphic robots according to claim 1, characterized in that, The target expression control signal includes instruction data packets from the network or external control terminal for instructing the presentation of the target expression, or video data of a real person's expression from a camera for instructing the reproduction of the target expression.

3. The method for coordinated control of multiple facial expressions in anthropomorphic robots according to claim 1, characterized in that, When the target expression control signal is a data packet from the network or an external control terminal used to instruct the presentation of the target expression, at least two silent delay parameters, each corresponding to one of the at least two expression execution mechanisms and independent of each other, are obtained, including: Parse at least two silent delay parameters from the instruction data packet, which correspond one-to-one with at least two facial expression actuators and are independent of each other.

4. The method for coordinated control of multiple facial expressions in anthropomorphic robots according to claim 1, characterized in that, When the target expression control signal is real-person expression video data from a camera used to indicate the reproduction of the target expression, at least two silent delay parameters, each corresponding to one of the at least two expression execution mechanisms and independent of each other, are acquired, including: Visual analysis is performed on the real-person facial expression video data, and at least two silent delay parameters that correspond one-to-one with and are independent of each other are calculated based on the visual analysis results.

5. The method for coordinated control of multiple facial expressions in anthropomorphic robots according to claim 4, characterized in that, Visual analysis is performed on the real-person facial expression video data, and based on the visual analysis results, at least two silent delay parameters that correspond one-to-one with and are independent of at least two facial expression actuators are calculated, including: Visual analysis is performed on the real-person facial expression video data to obtain at least two action intensity time-series data that correspond one-to-one with at least two facial expressions; Based on the timing data of the intensity of the at least two actions, determine the facial expression with the earliest start time from the at least two facial expressions; For each of the at least two facial expressions, the corresponding start time is first determined based on the corresponding action intensity timing data. Then, the time difference between the start time and the start time of a certain facial expression is calculated to obtain the corresponding relative time difference. Finally, the silent delay parameter of the corresponding facial expression execution mechanism is determined based on the relative time difference.

6. A multi-part facial expression collaborative control device for anthropomorphic robots, characterized in that, It includes a control signal acquisition unit, a static delay parameter acquisition unit, a silent delay start unit, and an actuator triggering unit that are connected in sequence. The control signal acquisition unit is used to acquire the target facial expression control signal; The silent delay parameter acquisition unit is used to respond to the target expression control signal in the following manner: acquire at least two silent delay parameters that correspond one-to-one with and are independent of at least two expression actuators of the humanoid robot; The silent delay start unit is used to synchronously start at least two silent delays that are based on the at least two silent delay parameters and correspond one-to-one with the at least two facial expression execution mechanisms. The actuator triggering unit is used to trigger the corresponding facial expression actuator at the end of each of the at least two silence delays.

7. A humanoid robot multi-part facial expression collaborative control system, characterized in that, It includes remote control equipment, remote control service equipment, bionic motion workshop and robot terminal, wherein the robot terminal integrates several facial expression execution mechanisms; The remote control device is communicatively connected to the remote control service device and is used to send target facial expression control signals and transmit them to the remote control service device. The remote control service device is communicatively connected to the bionic motion workshop and is used to forward the target facial expression control signal to the bionic motion workshop. The bionic motion workshop is communicatively connected to the robot terminal and is used to execute the anthropomorphic robot multi-part facial expression collaborative control method as described in any one of claims 1 to 5 after receiving the target facial expression control signal.

8. A computer device, characterized in that, It includes a storage module, a processing module, and a transceiver module that are sequentially connected in communication. The storage module is used to store computer programs, the transceiver module is used to send and receive messages, and the processing module is used to read the computer programs and execute the humanoid robot multi-part facial expression collaborative control method as described in any one of claims 1 to 5.

9. A computer-readable storage product, characterized in that... The computer-readable storage product stores instructions that, when executed on a computer, perform the humanoid robot multi-part facial expression collaborative control method as described in any one of claims 1 to 5.

10. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or the instructions are executed by the computer, they implement the humanoid robot multi-part facial expression collaborative control method as described in any one of claims 1 to 5.

Images