Dinosaur gait imitation control method and related device

Abstract

The application provides a dinosaur gait simulation control method and related equipment, and relates to the field of paleontology bionics. The application introduces real motion data of multiple modern close relatives of a target dinosaur in their respective species habitats, provides gait constraint conditions suitable for a high-fidelity physical simulation environment for a dinosaur gait simulation operation based on a dinosaur biological model at a biomechanics level, guides generation of a dinosaur gait motion strategy of the dinosaur biological model in the high-fidelity physical simulation environment, taking into account biological rationality and physical feasibility, facilitates the corresponding bionic dinosaur robot to adaptively make smooth and natural gait motion behavior in an actual deployment environment, and improves the verisimilitude of the bionic dinosaur robot.

Description

Technical Field

[0001] This application relates to the field of paleontological bionics technology, and more specifically, to a dinosaur gait imitation control method and related equipment. Background Technology

[0002] With the continuous development of biomimetic technology, the imitation and reproduction of the gait of extinct terrestrial prehistoric creatures (such as dinosaurs) has become an important research direction in biomimetic technology. It requires that the gait behavior of physical biomimetic robots conform as closely as possible to the real gait movement law of extinct terrestrial prehistoric creatures at the biomechanical level, and be able to adapt to changes in the terrain of the external environment.

[0003] However, it is worth noting that, since it is impossible to directly observe the actual gait behavior of extinct terrestrial fossils, existing gait imitation and reproduction mechanisms usually rely on paleontologists' subjective assumptions based on fossils (e.g., dinosaur bone fossils, dinosaur footprint fossils, etc.). These mechanisms cannot accurately reflect the paleontological characteristics of extinct terrestrial fossils and are difficult to adapt to changes in the external environment and terrain to produce smooth and natural gait behavior. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a dinosaur gait imitation control method, a dinosaur gait imitation system, and a readable storage medium, which can introduce real motion data of modern closely related species of the target dinosaur, and provide gait constraints adapted to a high-fidelity physical simulation environment for dinosaur gait simulation operation based on dinosaur biological models at the biomechanical level, guide the generation of dinosaur gait movement strategies that take into account both biological rationality and physical feasibility, so that the corresponding biomimetic dinosaur robot can adaptively make smooth and natural gait movement behavior in the actual deployment environment, thereby improving the realism of the biomimetic dinosaur robot.

[0005] To achieve the above objectives, the technical solutions adopted in the embodiments of this application are as follows: In a first aspect, this application provides a dinosaur gait imitation control method, the method comprising: Obtain biological movement data of multiple modern closely related species of the target dinosaur in their respective habitats, and construct a virtual biological model of the target dinosaur; Based on the biomovement data of the aforementioned modern closely related species, biomechanical gait constraints for the target dinosaur in the target virtual environment are constructed. Based on the biomechanical gait constraints and the biological movement data of the various modern closely related species, the virtual biological model is invoked in the target virtual environment to simulate dinosaur gait and obtain the desired biological gait control parameters of the target dinosaur. The motion command converter is invoked to convert the desired biological gait control parameters into robot gait control commands adapted to the bionic dinosaur robot of the target dinosaur, and the bionic dinosaur robot is driven to move in accordance with the robot gait control commands.

[0006] In an optional implementation, the step of constructing the virtual biological model of the target dinosaur includes: Acquire skeletal parameters, muscle morphology parameters, and joint range of motion information of the target dinosaur, as well as muscle physiological parameters of the various modern closely related species. A three-dimensional skeleton model is constructed based on the bone parameter information and the joint range of motion information to obtain the corresponding dinosaur skeleton model; Based on the muscle morphology parameters, muscle components are added to the dinosaur skeleton model to obtain the corresponding virtual bionic model. Based on the muscle physiological parameters of the various modern closely related species, physiological constraint parameters are estimated for the target dinosaur, and physiological behavior constraints are imposed on the virtual biomimetic model according to the estimated physiological constraint parameters to obtain a virtual biological model of the target dinosaur.

[0007] In an optional implementation, the biomovement data of each modern closely related species includes the biomechanical constraints and biomechanical data of that modern closely related species when moving using an adapted gait pattern under different habitat topographic conditions in the corresponding species' habitat environment. The step of constructing the biomechanical gait constraints of the target dinosaur in the target virtual environment based on the biomovement data of the multiple modern closely related species includes: Among the multiple modern closely related species, identify all target closely related species whose corresponding habitat topographic conditions are consistent with the target topographic conditions of the target virtual environment; Based on the biomechanical constraints and biomechanical data of all target closely related species under the target terrain conditions, assess the gait behavior fit of each of the target closely related species with the target virtual environment. Constraint mapping fusion is performed based on the gait behavior adaptability and biomechanical constraints of all target closely related species to obtain the biomechanical gait constraints of the target dinosaur in the target virtual environment.

[0008] In an optional implementation, the step of performing constraint mapping fusion based on the gait behavior fit and biomechanical constraints of each of the target closely related species to obtain the biomechanical gait constraints of the target dinosaur in the target virtual environment includes: For each target closely related species, based on the species morphology mapping relationship between the target closely related species and the target dinosaur, the biomechanical constraints of the target closely related species under the target terrain conditions are transformed by constraint mapping to obtain the biomechanical mapping constraints of the target closely related species. The biomechanical mapping constraints of all target closely related species are weighted and fused to obtain the biomechanical gait constraints of the target dinosaur in the target virtual environment. The condition fusion weight used by each target closely related species in the constraint weight fusion process is positively correlated with the gait behavior fit.

[0009] In an optional implementation, the step of simulating dinosaur gait by calling the virtual biological model in the target virtual environment based on the biomechanical gait constraints and the biological movement data of the plurality of modern closely related species, to obtain the desired biological gait control parameters of the target dinosaur, includes: Based on the biomechanical data of all target closely related species under the target terrain conditions, gait sequence prediction is performed on the virtual biological model in the target virtual environment to obtain the desired gait sequence that satisfies the biomechanical gait constraints. Under the biomechanical gait constraints, an inverse optimization algorithm is used to iteratively solve the gait parameters for the desired gait motion sequence to obtain the desired biomechanical gait control parameters.

[0010] In an optional implementation, the method further includes: Acquire gait motion perception data and environmental perception data of the bionic dinosaur robot in the actual deployment environment; The physiological constraint parameters of the virtual biological model and the motion command converter are updated according to the gait motion perception data, and the parameters of the target virtual environment are updated according to the environmental perception data. Then, the process jumps to the step of constructing the biomechanical gait constraint conditions of the target dinosaur in the target virtual environment based on the biological motion data of the multiple modern closely related species and continues to execute.

[0011] In an optional implementation, before performing the step of updating the physiological constraint parameters of the virtual biological model and the motion command converter based on the gait motion perception data, the method further includes: Calculate the multidimensional data error between the gait motion perception data and the gait motion prediction data of the target dinosaur under the action of the desired biological gait control parameters, and the environmental parameter error between the environmental perception data and the environmental parameter data of the target virtual environment; Based on the multidimensional data error and the environmental parameter error, it is determined whether the robot gait control command meets the gait imitation convergence criterion. If the robot gait control command is detected to not meet the gait imitation convergence criterion, the step of updating the physiological constraint parameters of the virtual biological model and the motion command converter according to the gait motion perception data continues; otherwise, the step of driving the bionic dinosaur robot to move according to the robot gait control command continues.

[0012] Secondly, this application provides a dinosaur gait imitation system, the system including a central control unit and a bionic dinosaur robot of the target dinosaur; The central control unit is communicatively connected to the bionic dinosaur robot and is used to control the movement of the bionic dinosaur robot; The central control unit stores a computer program, and can implement the dinosaur gait imitation control method described in any of the foregoing embodiments by running the computer program.

[0013] In an optional implementation, the system further includes multiple bio-motion capture devices that are communicatively connected to the central control unit; Each of the target dinosaurs, representing multiple modern closely related species, is individually equipped with a biomovement capture device to collect biomovement data of the corresponding species in their own habitat.

[0014] Thirdly, this application provides a readable storage medium storing a computer program thereon, which, when executed by a computer device communicatively connected to a bionic dinosaur robot of the target dinosaur, implements the dinosaur gait imitation control method described in any of the foregoing embodiments.

[0015] In this case, the beneficial effects of the embodiments of this application may include the following: This application obtains biomovement data of multiple modern closely related species of the target dinosaur in their respective habitats and constructs a virtual biological model of the target dinosaur. Then, based on the biomovement data of these species, it constructs biomechanical gait constraints for the target dinosaur in a target virtual environment (i.e., a high-fidelity physical simulation environment matching the actual deployment environment of the biomimetic dinosaur robot). Following these constraints and the biomovement data of the species, it uses the virtual biological model within the target virtual environment to simulate the dinosaur's gait, obtaining the desired biomechanical gait control parameters. Finally, it uses a motion command converter to transmit the desired biomechanical gait control parameters. The control parameters are converted into robot gait control commands adapted to the target dinosaur bionic dinosaur robot, and the bionic dinosaur robot is driven to move according to the robot gait control commands. In this way, by introducing real motion data of modern closely related species, gait constraints adapted to the high-fidelity physical simulation environment are provided for the dinosaur gait simulation operation based on the dinosaur biological model (i.e., the aforementioned virtual biological model) at the biomechanical level. This guides the generation of dinosaur gait movement strategies (i.e., desired biological gait control parameters) that take into account both biological rationality and physical feasibility. This makes it easier for the corresponding bionic dinosaur robot to adaptively make smooth and natural gait movement behavior in the actual deployment environment, thereby improving the realism of the bionic dinosaur robot.

[0016] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A schematic diagram of the system composition of the dinosaur gait mimicry system provided in the embodiments of this application; Figure 2 This is one of the flowcharts illustrating the dinosaur gait imitation control method provided in this application embodiment; Figure 3 for Figure 2 A schematic diagram illustrating the execution of step S210; Figure 4 for Figure 2 A schematic diagram illustrating the execution of step S220; Figure 5 for Figure 2 A schematic diagram illustrating the execution of step S230; Figure 6 A second schematic flowchart illustrating the dinosaur gait imitation control method provided in this application embodiment; Figure 7 The third flowchart illustrates the dinosaur gait imitation control method provided in this application embodiment.

[0019] Icons: 10-Dinosaur gait imitation system; 11-Central control unit; 12-Bionic dinosaur robot; 13-Bio-motion capture device. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0021] Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0022] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0023] In the description of this application, it should be understood that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product is in use, or the orientation or positional relationship commonly understood by those skilled in the art. They are used only for the convenience of describing this application and simplifying the description, and are not intended to indicate or imply that the equipment or component 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 this application.

[0024] In the description of this application, it should also be noted that, unless otherwise expressly specified and limited, the terms "set up," "install," "connect," and "link" 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 application based on the specific circumstances.

[0025] Furthermore, it is understood in the description of this application that relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element. Those skilled in the art will understand the specific meaning of the above terms in this application based on the specific circumstances.

[0026] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0027] Please refer to Figure 1 , Figure 1 This is a schematic diagram of the system composition of the dinosaur gait imitation system 10 provided in this application embodiment. In this application embodiment, the dinosaur gait imitation system 10 can be used to realistically imitate the gait behavior of a target dinosaur (i.e., any type of dinosaur, such as Tyrannosaurus Rex, Triceratops, Tyrannosaurus Rex, Diplodocus, Stegosaurus). The dinosaur gait imitation system 10 may include a central control unit 11 and a biomimetic dinosaur robot 12 designed for the target dinosaur.

[0028] In this embodiment, the mechanical skeleton of the bionic dinosaur robot 12 (including information such as the length, mass, and moment of inertia of each body segment) is obtained by scaling the three-dimensional skeleton of the target dinosaur proportionally. Physical joint actuators (e.g., high-torque-density brushless DC motors or servo motors) are deployed at each physical joint of the mechanical skeleton structure of the bionic dinosaur robot 12 to achieve pose adjustment of the corresponding physical joint, facilitating the movement of the bionic dinosaur robot 12. The bionic dinosaur robot 12 is equipped with multiple physical sensors for sensing the robot's motion. These sensors may include, but are not limited to: an IMU (Inertial Measurement Unit) for sensing the robot's trunk posture, angular velocity, and linear acceleration; a joint encoder for sensing the robot's joint angles and angular velocities; and a plantar force sensor for sensing the robot's plantar force data.

[0029] In this embodiment, the biomimetic dinosaur robot 12 can be wrapped with a flexible "skin" made of silicone or foam latex outside the mechanical skeleton structure. The soft artificial muscles integrated in this "skin" can synchronously simulate muscle contraction and bulging, as well as skin wrinkling and shaking during the robot's movement, so as to provide the audience with intuitive details of the underlying biomechanics.

[0030] In this embodiment, the central control unit 11 is communicatively connected to the bionic dinosaur robot 12 and is used to control the bionic dinosaur robot 12 to move in order to mimic the feasible movement behavior of the target dinosaur. The central control unit 11 can pre-store specific computer programs related to the dinosaur gait imitation control function. By running these specific computer programs, it can introduce real movement data of multiple modern closely related species of the target dinosaur in their respective habitats. At the biomechanical level, it provides gait constraints adapted to a high-fidelity physical simulation environment for the dinosaur gait simulation operation based on the dinosaur biological model (i.e., a virtual biological model constructed using paleontological principles for the target dinosaur). This guides the generation of dinosaur gait movement strategies that balance biological rationality and physical feasibility in a high-fidelity physical simulation environment, facilitating the corresponding bionic dinosaur robot 12 to adaptively perform smooth and natural gait movements in the actual deployment environment, thus improving the realism of the bionic dinosaur robot 12.

[0031] In this embodiment, the dinosaur gait mimicry system 10 may further include multiple bio-motion capture devices 13, each of which is communicatively connected to the central control unit 11. Each individual species corresponding to multiple modern closely related species of the target dinosaur wears a separate bio-motion capture device 13 to collect bio-motion data of the corresponding species in their own habitat. Among these, the composition of modern closely related species corresponding to different dinosaur categories can be partially the same or completely different. For example, the modern closely related species corresponding to Tyrannosaurus Rex include ostriches and chickens, while the modern closely related species corresponding to Diplodocus include crocodiles and Komodo dragons. Different modern closely related species have different habitats. The habitat topography (e.g., flat hard ground, sandy ground, muddy ground, slope, etc.) of different species can be partially the same or completely different. Different modern closely related species have different adapted gait patterns (e.g., slow walking, normal walking, high-speed running) in their respective adapted habitat topography. For example, ostriches are adapted to high-speed running and normal walking in sandy ground, while crocodiles are adapted to slow walking in muddy ground.

[0032] In this embodiment, the biomovement data of multiple individuals belonging to the same modern closely related species can include the individual biomechanical constraints (including individual kinematic constraints related to gait behavior, including at least the gait cycle, stance phase ratio, joint angle extremes, and joint angle range of the individual in the corresponding species' habitat under different habitat topographic conditions) when moving using adapted gait patterns, individual dynamic constraints (including at least the peak value of three-dimensional ground reaction force, gait propulsion curve characteristics, center of mass trajectory, and joint torque range of the individual in the adapted gait pattern), and individual electromyographic coordination constraints (including individual biomechanical constraints related to gait behavior, including at least the peak value of three-dimensional ground reaction force, gait propulsion curve characteristics, center of mass trajectory, and joint torque range of the individual in the corresponding species' habitat under the adapted gait pattern), and individual electromyographic coordination constraints (including individual biomechanical constraints related to gait behavior, including at least the peak value of three-dimensional ground reaction force, gait propulsion force curve characteristics, center of mass trajectory, and joint torque range of the individual in the corresponding species' habitat under the adapted gait pattern). It includes at least information such as muscle synergy metadata and muscle activation timing data of the corresponding species individual in the adapted gait mode, and individual biomechanical data (including individual kinematic data related to gait movement behavior, including at least information such as joint angle data, trunk posture data, stride frequency, stride length, and foot trajectory of the corresponding species individual in the adapted gait mode at different movement times), individual dynamic data (including at least information such as three-dimensional ground reaction force values, center of mass position, and joint torque data of the corresponding species individual in the adapted gait mode at different movement times), and individual electromyographic data (including at least information such as surface electromyographic signals of key muscle groups of the corresponding species individual in the adapted gait mode at different movement times)).

[0033] Understandable Figure 1The block diagram shown is only a schematic diagram of one component of the dinosaur gait imitation system 10. The dinosaur gait imitation system 10 may also include components such as... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown. Figure 1 The components shown can be implemented using hardware, software, or a combination thereof.

[0034] In this application, to ensure that the central control unit 11 in the aforementioned dinosaur gait imitation system 10 can incorporate real motion data from modern closely related species of the target dinosaur, and to provide gait constraints at the biomechanical level that are adapted to a high-fidelity physical simulation environment for the dinosaur gait simulation operation, thereby guiding the generation of dinosaur gait movement strategies that take into account both biological rationality and physical feasibility, so that the corresponding biomimetic dinosaur robot 12 can adaptively perform smooth and natural gait movements in the actual deployment environment, this application embodiment achieves the aforementioned objective by providing a dinosaur gait imitation control method. The dinosaur gait imitation control method provided in this application will be described in detail below.

[0035] Please refer to Figure 2 , Figure 2 This is one of the flowcharts illustrating the dinosaur gait mimicry control method provided in this application embodiment. In this application embodiment, Figure 2 The dinosaur gait imitation control method shown may include steps S210 to S250.

[0036] Step S210: Obtain biological movement data of multiple modern closely related species of the target dinosaur in their respective habitats, and construct a virtual biological model of the target dinosaur.

[0037] In this embodiment, after obtaining the biomovement data of multiple individuals belonging to the same modern closely related species, the biomovement data of these individuals can be analyzed using common biological characteristics of the same species to obtain the biomovement data of the modern closely related species in the corresponding species' habitat (which may include species-level biomechanical constraints (obtained by extracting common gait features from the individual biomechanical constraints of the multiple species individuals) and species-level biomechanical data (obtained by extracting common gait features from the individual biomechanical data of the multiple species individuals) when the modern closely related species moves using an adapted gait pattern under different habitat topographic conditions in the corresponding species' habitat). The virtual biological model is the dinosaur biological model of the target dinosaur, which is constructed using paleontological principles combined with the paleontological fossil parameters of the target dinosaur (including but not limited to: skeletal parameters, muscle morphology parameters, and joint range of motion information of the target dinosaur).

[0038] Alternatively, please refer to Figure 3 , Figure 3 yes Figure 2 A schematic diagram illustrating the execution of step S210. In this embodiment of the application, the step "constructing a virtual biological model of the target dinosaur" in step S210 may include sub-steps S211 to S214 to construct a dinosaur biological model of the target dinosaur using paleontological principles.

[0039] Sub-step S211: Obtain skeletal parameter information, muscle morphology parameter information, and joint range of motion information of the target dinosaur, as well as muscle physiological parameter information of multiple modern closely related species.

[0040] In this embodiment, the skeletal parameter information may include information such as the skeletal shape, length, and position of the target dinosaur; the muscle morphological parameter information may include information such as the origin and insertion points, mass, and physiological cross-sectional area (PCSA) of each muscle in the target dinosaur; the joint range of motion information may include information such as the range of motion (RoM) of each joint in the target dinosaur. The muscle physiological parameter information for each modern closely related species includes information such as the maximum isometric contractile force, optimal fiber length, tendon stiffness, and muscle force line direction for each muscle in the corresponding modern closely related species.

[0041] Sub-step S212 involves constructing a three-dimensional skeleton model based on skeletal parameter information and joint range of motion information to obtain the corresponding dinosaur skeleton model.

[0042] Sub-step S213: Add muscle components to the dinosaur skeleton model based on muscle morphology parameters to obtain the corresponding virtual bionic model.

[0043] Sub-step S214: Based on the muscle physiological parameter information of multiple modern closely related species, the physiological constraint parameters of the target dinosaur are estimated, and the physiological behavior of the virtual bionic model is constrained according to the estimated physiological constraint parameters to obtain the virtual biological model of the target dinosaur.

[0044] In this embodiment, the muscle physiological parameters of each of the multiple modern closely related species can be comprehensively mapped based on the species morphology mapping relationship between each of the multiple modern closely related species and the target dinosaur (which describes the mapping details of the corresponding modern closely related species and the body parts of the target dinosaur at the species morphology level). This results in physiological constraint parameters that match the model muscle components at the virtual bionic model. The physiological constraint parameters are then used to limit the muscle physiological behavior of the virtual bionic model during gait simulation, thereby obtaining a virtual biological model of the target dinosaur.

[0045] Therefore, this application can construct a dinosaur biological model of the target dinosaur by executing the above sub-steps S211 to S214 using paleontological principles.

[0046] Step S220: Based on the biological movement data of multiple modern closely related species, construct biomechanical gait constraints for the target dinosaur in the target virtual environment.

[0047] In this embodiment, after obtaining the biological movement data of multiple modern closely related species, the biomechanical gait constraints of the target dinosaur in the target virtual environment can be solved by organically combining the constraint terrain association extraction operation and the morphological mapping fusion operation, based on the species-level biomechanical constraints of the multiple modern closely related species when they adopt the adapted gait mode for movement under different habitat terrain conditions in their own species' habitat.

[0048] Alternatively, please refer to Figure 4 , Figure 4 yes Figure 2 A schematic diagram of step S220 is shown. In this embodiment of the application, step S220 may include sub-steps S221 to S223, in order to combine the real movement data of the target dinosaur's modern closely related species to provide the target dinosaur with gait constraints adapted to the high-fidelity physical simulation environment (i.e., the target virtual environment) at the biomechanical level.

[0049] Sub-step S221: Among multiple modern closely related species, identify all target closely related species whose corresponding habitat topographic conditions are consistent with the target topographic conditions of the target virtual environment.

[0050] Sub-step S222: Based on the biomechanical constraints and biomechanical data of all target closely related species under the target terrain conditions, evaluate the gait behavior fit of each target closely related species with the target virtual environment.

[0051] In this embodiment, for each target closely related species, the gait performance intensity of the target closely related species in the target terrain conditions can be comprehensively evaluated from multiple dimensions, including motion stability, motion speed, motion energy consumption, and joint load, based on the biomechanical constraints and biomechanical data of the target closely related species under the target terrain conditions, and the environmental parameter data of the target virtual environment (which may include, but is not limited to, the simulated ambient temperature, simulated ground friction coefficient, simulated terrain, etc. of the target virtual environment). The evaluated gait performance intensity is then used to positively characterize the gait behavior fit between the target closely related species and the target virtual environment. A higher gait performance intensity corresponds to a higher gait behavior fit.

[0052] Sub-step S223 involves constrained mapping and fusion based on the gait behavior fit and biomechanical constraints of each of the target closely related species to obtain the biomechanical gait constraints of the target dinosaur in the target virtual environment.

[0053] In this embodiment, for each target closely related species, based on the species morphology mapping relationship between the target closely related species and the target dinosaur, the biomechanical constraints of the target closely related species under the target terrain conditions are transformed by constraint mapping to obtain the biomechanical mapping constraints of the target closely related species (which essentially belong to the local biological gait constraints of the target dinosaur associated with the target closely related species). Then, by weighted fusion of the constraint constraints of the biomechanical mapping of all target closely related species, the biomechanical gait constraints of the target dinosaur in the target virtual environment can be obtained.

[0054] In this process, the conditional fusion weights used by each target closely related species in the constraint weighted fusion process are positively correlated with their gait behavior fit. The conditional fusion weights of each target closely related species can be determined by normalizing the gait behavior fit of each of the target closely related species. For each target closely related species, the species-level biomechanical constraints (including species kinematic constraints, species dynamic constraints, and species electromyographic coordination constraints) related to gait movement under the target terrain conditions are converted into biomechanical mapping constraints that fit the morphology of the target dinosaur through scaling and / or transformation operations. The species morphological mapping relationship between each target closely related species and the target dinosaur records the limb proportion scaling relationship and joint configuration difference correction relationship at the kinematic level, the Froude number similarity mapping relationship and mass distribution mapping ratio at the dynamic level, and the muscle function similarity mapping relationship and muscle activation intensity correction relationship at the electromyographic coordination level.

[0055] Therefore, by executing the above sub-steps S221 to S223, and combining the real motion data of the target dinosaur's modern closely related species, this application can provide gait constraints for the target dinosaur at the biomechanical level that are adapted to a high-fidelity physical simulation environment.

[0056] Step S230: Based on the biomechanical gait constraints and the biological movement data of multiple modern closely related species, a virtual biological model is invoked in the target virtual environment to simulate the dinosaur's gait and obtain the desired biological gait control parameters of the target dinosaur.

[0057] In this embodiment, when the biomechanical gait constraints of the target dinosaur in the target virtual environment and the biological movement data of the multiple modern closely related species are determined, the biomechanical gait constraints can be used as constraints of the dinosaur gait feasibility exploration boundary. In the target virtual environment, the virtual biological model is invoked within the dinosaur gait feasibility exploration boundary, and the possible dinosaur gait movement strategies that take into account both biological rationality and physical feasibility are actively simulated and explored with reference to the biological movement data of the multiple modern closely related species. The desired biological gait control parameters of the target dinosaur in the target virtual environment are obtained (which record the desired joint angle time series, desired joint torque time series, desired muscle excitation time series, desired foot position time series, and desired ground reaction force time series of the target dinosaur, etc.).

[0058] Alternatively, please refer to Figure 5 , Figure 5 yes Figure 2 A schematic diagram illustrating the execution of step S230. In this embodiment of the application, step S230 may include sub-steps S231 to S232, so as to actively simulate and explore the dinosaur gait movement strategy of the target dinosaur in the target virtual environment, taking into account both biological rationality and physical feasibility, under the influence of real movement data of the target dinosaur's modern closely related species.

[0059] Sub-step S231: Based on the biomechanical data of all target closely related species under the target terrain conditions, predict the gait sequence in the target virtual environment based on the virtual biological model to obtain the expected gait sequence that meets the biomechanical gait constraints.

[0060] In this embodiment, based on the evolutionary tree relationship and morphological differences between each of the target closely related species and the target dinosaur, and with the aim of satisfying the biomechanical gait constraints, the species-level biomechanical data of all the target closely related species under the target terrain conditions are mapped and transformed onto the virtual biological model to obtain the desired gait sequence (which records information such as joint angle trajectory, foot position trajectory, desired ground reaction force change curve, and muscle excitation change curve of the virtual biological model in the target virtual environment for a complete gait cycle).

[0061] Sub-step S232 involves using an inverse optimization algorithm to iteratively solve for the gait parameters of the desired gait motion sequence under biomechanical gait constraints, thereby obtaining the desired biomechanical gait control parameters.

[0062] In this embodiment, the inverse optimization algorithm used in sub-step S232 may include, but is not limited to, at least one of the following optimization algorithms: genetic algorithm, particle swarm optimization algorithm, model predictive control (MPC) algorithm. The inverse optimization algorithm can be used to iteratively solve gait parameters based on the desired gait motion sequence under the biomechanical gait constraints. The gait parameters solved in each iteration are then used to drive the virtual biological model to perform forward gait motion simulation in the target virtual environment, obtaining corresponding gait motion prediction data (which typically includes predicted trajectories of joint angle changes, joint angular velocity changes, joint torque changes, zero torque point position changes, center of mass position changes, and ground reaction force changes). Then, the objective function value corresponding to the gait motion prediction data is calculated. Finally, by judging whether the corresponding objective function value has reached the function convergence condition (e.g., maximizing the objective function value) or whether the cumulative number of iterations has reached the preset number of iterations, it is determined whether to continue the gait parameter iterative solution operation. When the corresponding objective function value reaches the iteration convergence condition or the cumulative number of iterations reaches the preset number of iterations, the gait parameters obtained by the iteration are the desired biological gait control parameters. The above objective function usually involves multiple dimensions such as maximizing energy efficiency, minimizing joint impact, and maximizing motion stability.

[0063] Therefore, by executing the above sub-steps S231 to S232, this application can actively simulate and explore the dinosaur gait movement strategy of the target dinosaur in the target virtual environment, taking into account both biological rationality and physical feasibility, under the influence of real movement data of the target dinosaur's modern closely related species.

[0064] Step S240: Call the motion command converter to convert the desired biological gait control parameters into robot gait control commands that are adapted to the biomimetic dinosaur robot of the target dinosaur.

[0065] In this embodiment, the motion command converter is trained using a neural network model, enabling the motion command converter to reliably convert biological motion commands (i.e., corresponding desired biological gait control parameters) into robot engineering motion commands (i.e., corresponding robot gait control commands).

[0066] Step S250: Drive the bionic dinosaur robot to move according to the robot gait control command.

[0067] Therefore, by executing the above steps S210 to S250, this application can introduce real motion data of multiple modern closely related species of the target dinosaur in their respective habitats. At the biomechanical level, this provides gait constraints that are adapted to the high-fidelity physical simulation environment for dinosaur gait simulation operations based on dinosaur biological models. This guides the generation of dinosaur gait movement strategies that take into account both biological rationality and physical feasibility in the high-fidelity physical simulation environment. This facilitates the corresponding biomimetic dinosaur robot 12 to adaptively make smooth and natural gait movements in the actual deployment environment, thereby improving the realism of the biomimetic dinosaur robot.

[0068] Alternatively, please refer to Figure 6 , Figure 6 This is the second flowchart illustrating the dinosaur gait mimicry control method provided in this application embodiment. In this application embodiment, with... Figure 2 Compared to the dinosaur gait imitation control method shown, Figure 6 The dinosaur gait imitation control method shown may include steps S260 and S270 after step S250 to establish a continuous feedback loop from the real physical world to the virtual simulation world, continuously iterate and narrow the gap between simulation and reality, and ensure that the bionic dinosaur robot 12 can adapt to changes in the real deployment environment and make dynamic gait movements that ensure environmental coordination.

[0069] Step S260: Obtain gait motion perception data and environmental perception data of the bionic dinosaur robot in the actual deployment environment.

[0070] In this embodiment, during the execution of step S250, the bionic dinosaur robot 12 will call its own installed physical sensors to perceive its own motion status, so as to obtain the gait motion perception data of the bionic dinosaur robot 12 in the actual deployment environment (including the actual robot trunk posture, actual trunk angular velocity, actual trunk linear acceleration, actual robot joint angle, actual robot joint angular velocity, actual robot joint torque, robot foot force data, etc.). At the same time, it can use environmental perception sensors (which can be deployed on the bionic dinosaur robot 12 or in the actual deployment environment) to complete the environmental parameter perception function of the actual operating environment, so as to obtain the real environmental perception data of the actual deployment environment (which may include, but is not limited to, the actual ambient temperature, actual ground friction coefficient, actual environmental terrain, etc. of the actual deployment environment).

[0071] Step S270: Update the physiological constraint parameters and motion command converter of the virtual biological model according to the gait motion perception data, and update the parameters of the target virtual environment according to the environmental perception data.

[0072] In this embodiment, after acquiring gait motion perception data, the gait motion perception data can be compared with the gait motion prediction data of the target dinosaur under the action of the desired biological gait control parameters to determine whether there is a significant command conversion error in the motion command converter, and whether there is a significant difference in muscle physiological behavior between the virtual biological model and the bionic dinosaur robot 12 at the soft tissue force exertion level. This facilitates the use of the gait motion perception data to update the physiological constraint parameters used by the virtual biological model, and to update the neural network weight parameters of the motion command converter, thereby effectively narrowing the gap between the virtual biological model and the real robot, and promoting the synergistic optimization effect between the gait behavior of the virtual biological model and the real robot.

[0073] Once the environmental perception data is acquired, it can be compared with the environmental parameter data of the target virtual environment to determine whether the target virtual environment deviates significantly from the actual deployment environment. This allows the environmental parameter data of the target virtual environment to be updated using the environmental perception data, effectively narrowing the gap between the virtual environment and the real environment. This is beneficial for achieving a collaborative optimization effect between the virtual biological model and the gait behavior of the real robot.

[0074] After each execution of step S270, the corresponding steps S220 to S270 can be executed to establish a continuous feedback loop from the real physical world to the virtual simulation world, continuously iterate and narrow the gap between simulation and reality, and ensure that the bionic dinosaur robot 12 can adapt to changes in the real deployment environment and make dynamic gait movements that ensure environmental coordination (while taking into account both biological rationality and physical feasibility).

[0075] Therefore, by executing the above steps S210 to S270, this application can introduce real motion data of modern closely related species of the target dinosaur, and provide gait constraints that are compatible with the high-fidelity physical simulation environment for dinosaur gait simulation operations based on dinosaur biological models at the biomechanical level. This will guide the generation of dinosaur gait movement strategies that take into account both biological rationality and physical feasibility. Furthermore, by establishing a continuous feedback loop from the real physical world to the virtual simulation world, it can ensure that the bionic dinosaur robot 12 can adapt to environmental changes and make smooth gait movements that ensure environmental coordination in the actual deployment environment, thereby improving the realism of the bionic dinosaur robot 12.

[0076] Alternatively, please refer to Figure 7 , Figure 7 This is the third flowchart illustrating the dinosaur gait mimicry control method provided in this application embodiment. In this application embodiment, with... Figure 6Compared to the dinosaur gait imitation control method shown, Figure 7 The dinosaur gait mimicry control method shown may include steps S280 and S290 before executing step S270, in order to avoid performing unnecessary simulation-reality iterative update operations and improve the gait stability of the bionic dinosaur robot 12 in a real deployment environment.

[0077] Step S280: Calculate the multidimensional data error between the gait motion perception data and the gait motion prediction data of the target dinosaur under the action of the desired biological gait control parameters, as well as the environmental parameter error between the environmental perception data and the environmental parameter data of the target virtual environment.

[0078] In this embodiment, the multidimensional data error may include joint angle error, joint torque error, foot position error, expected ground reaction force error, center of mass position error, and zero torque point position error at different movement moments within a complete gait cycle.

[0079] Step S290: Based on the multidimensional data error and environmental parameter error, detect whether the robot gait control command meets the gait imitation convergence criterion.

[0080] In this embodiment, the gait imitation convergence criteria may include, but are not limited to, any one or more combinations of the following convergence criteria: "at least a preset number (e.g., 3) of the multiple data errors included in the multidimensional data errors are less than their corresponding preset error thresholds", "the environmental parameter errors are less than the preset environmental error thresholds", "the number of real-world perception data feedbacks reaches the preset feedback number thresholds", and "the change in adjacent commands between three consecutive robot gait control commands solved in step S240 is less than the preset change thresholds".

[0081] In this embodiment, when it is detected that the robot gait control command does not meet the gait imitation convergence criterion, it indicates that the current simulation and reality have a large gap. At this time, it is necessary to continue to execute step S270 to further iterate and narrow the gap between simulation and reality. When it is detected that the robot gait control command meets the gait imitation convergence criterion, it indicates that the current simulation and reality have a small gap. At this time, it is not necessary to continue to execute the simulation-reality iterative update operation. It is possible to continue to jump to execute the above step S250 to improve the gait stability of the bionic dinosaur robot 12 in the real deployment environment.

[0082] Therefore, by executing the above steps S280 and S290, this application can avoid performing unnecessary simulation-reality iterative update operations and improve the gait stability of the bionic dinosaur robot 12 in a real deployment environment.

[0083] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the architecture, functionality, and operation of possible implementations of the apparatus, methods, and computer program products according to embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0084] Furthermore, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part. If the function is implemented as a software functional module and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium and includes several instructions to cause a computer device that is communicatively connected to the target dinosaur bionic dinosaur robot 12 to execute all or part of the steps of the methods described in the various embodiments of this application as the central control unit 11. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0085] The above descriptions are merely various embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A dinosaur gait imitation control method, characterized in that, The method includes: Obtain biological movement data of multiple modern closely related species of the target dinosaur in their respective habitats, and construct a virtual biological model of the target dinosaur; Based on the biomovement data of the aforementioned modern closely related species, biomechanical gait constraints for the target dinosaur in the target virtual environment are constructed. Based on the biomechanical gait constraints and the biological movement data of the various modern closely related species, the virtual biological model is invoked in the target virtual environment to simulate dinosaur gait and obtain the desired biological gait control parameters of the target dinosaur. The motion command converter is invoked to convert the desired biological gait control parameters into robot gait control commands adapted to the bionic dinosaur robot of the target dinosaur, and the bionic dinosaur robot is driven to move in accordance with the robot gait control commands.

2. The method according to claim 1, characterized in that, The step of constructing the virtual biological model of the target dinosaur includes: The skeletal parameters, muscle morphology parameters, and joint range of motion of the target dinosaur, as well as the muscle physiological parameters of the various modern closely related species, are obtained. A three-dimensional skeleton model is constructed based on the bone parameter information and the joint range of motion information to obtain the corresponding dinosaur skeleton model; Based on the muscle morphology parameters, muscle components are added to the dinosaur skeleton model to obtain the corresponding virtual bionic model. Based on the muscle physiological parameters of the various modern closely related species, physiological constraint parameters are estimated for the target dinosaur, and physiological behavior constraints are imposed on the virtual biomimetic model according to the estimated physiological constraint parameters to obtain a virtual biological model of the target dinosaur.

3. The method according to claim 1, characterized in that, The biomovement data for each modern closely related species includes the biomechanical constraints and biomechanical data of that modern closely related species when moving using an adapted gait pattern under different habitat topographic conditions in the corresponding species' habitat environment. The step of constructing the biomechanical gait constraints of the target dinosaur in the target virtual environment based on the biomovement data of the multiple modern closely related species includes: Among the multiple modern closely related species, identify all target closely related species whose corresponding habitat topographic conditions are consistent with the target topographic conditions of the target virtual environment; Based on the biomechanical constraints and biomechanical data of all target closely related species under the target terrain conditions, assess the gait behavior fit of each of the target closely related species with the target virtual environment. Constraint mapping fusion is performed based on the gait behavior adaptability and biomechanical constraints of all target closely related species to obtain the biomechanical gait constraints of the target dinosaur in the target virtual environment.

4. The method according to claim 3, characterized in that, The step of performing constraint mapping fusion based on the gait behavior fit and biomechanical constraints of each of the target closely related species to obtain the biomechanical gait constraints of the target dinosaur in the target virtual environment includes: For each target closely related species, based on the species morphology mapping relationship between the target closely related species and the target dinosaur, the biomechanical constraints of the target closely related species under the target terrain conditions are transformed by constraint mapping to obtain the biomechanical mapping constraints of the target closely related species. The biomechanical mapping constraints of all target closely related species are weighted and fused to obtain the biomechanical gait constraints of the target dinosaur in the target virtual environment. The condition fusion weight used by each target closely related species in the constraint weight fusion process is positively correlated with the gait behavior fit.

5. The method according to claim 3, characterized in that, The step of simulating dinosaur gait by calling the virtual biological model in the target virtual environment based on the biomechanical gait constraints and the biological movement data of the multiple modern closely related species, and obtaining the desired biological gait control parameters of the target dinosaur, includes: Based on the biomechanical data of all target closely related species under the target terrain conditions, gait sequence prediction is performed on the virtual biological model in the target virtual environment to obtain the desired gait sequence that satisfies the biomechanical gait constraints. Under the biomechanical gait constraints, an inverse optimization algorithm is used to iteratively solve the gait parameters for the desired gait motion sequence to obtain the desired biomechanical gait control parameters.

6. The method according to any one of claims 1-5, characterized in that, The method further includes: Acquire gait motion perception data and environmental perception data of the bionic dinosaur robot in the actual deployment environment; The physiological constraint parameters of the virtual biological model and the motion command converter are updated according to the gait motion perception data, and the parameters of the target virtual environment are updated according to the environmental perception data. Then, the process jumps to the step of constructing the biomechanical gait constraint conditions of the target dinosaur in the target virtual environment based on the biological motion data of the multiple modern closely related species and continues to execute.

7. The method according to claim 6, characterized in that, Before performing the step of updating the physiological constraint parameters of the virtual biological model and the motion command converter based on the gait motion perception data, the method further includes: Calculate the multidimensional data error between the gait motion perception data and the gait motion prediction data of the target dinosaur under the action of the desired biological gait control parameters, and the environmental parameter error between the environmental perception data and the environmental parameter data of the target virtual environment; Based on the multidimensional data error and the environmental parameter error, it is determined whether the robot gait control command meets the gait imitation convergence criterion. If the robot gait control command is detected to not meet the gait imitation convergence criterion, the step of updating the physiological constraint parameters of the virtual biological model and the motion command converter according to the gait motion perception data continues; otherwise, the step of driving the bionic dinosaur robot to move according to the robot gait control command continues.

8. A dinosaur gait mimicry system, characterized in that, The system includes a central control unit and a bionic dinosaur robot representing the target dinosaur; The central control unit is communicatively connected to the bionic dinosaur robot and is used to control the movement of the bionic dinosaur robot; The central control unit stores a computer program, and can implement the dinosaur gait imitation control method according to any one of claims 1-7 by running the computer program.

9. The system according to claim 8, characterized in that, The system also includes multiple bio-motion capture devices that are communicatively connected to the central control unit; Each of the target dinosaurs, representing multiple modern closely related species, is individually equipped with a biomovement capture device to collect biomovement data of the corresponding species in their own habitat.

10. A readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a computer device that is communicatively connected to the bionic dinosaur robot of the target dinosaur, it implements the dinosaur gait imitation control method according to any one of claims 1-7.

Images