Robot footprint generation method and program product

Abstract

The embodiment of the invention provides a robot footprint generation method and a program product, and the method specifically comprises the steps: determining a specified action of a robot, and determining a swing phase duty ratio and an inter-foot phase offset corresponding to the specified action; based on the phase variable and the gait mapping relation, a contact signal used for representing the contact condition of the robot and the designated surface and a stepping signal used for representing the relative displacement condition of the robot relative to the designated surface are generated; wherein the phase variable is used for representing the stepping progress of the robot in the stepping period; the stepping period comprises a plurality of stepping stages, and the gait mapping relation is used for representing the relation between the phase variable and the swing phase duty ratio and the relation between the phase variable and the inter-foot phase offset; the gait mapping relationship comprises a stage gait mapping relationship corresponding to each stepping stage; and according to the expected speed, the contact signal and the stepping signal corresponding to the robot, the footprint of the robot under the specified action is generated. The method and the device can be suitable for efficiently realizing diversified gait requirements.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computer technology, and more particularly to a robot footprint generation method and program product. Background Art

[0002] In the field of legged robot motion control, gait generation is crucial for achieving stable walking and managing diverse motion patterns. Currently, to achieve the desired gait, manual collection of reference footprints is often used as gait training data to train the robot's motion control model. However, this approach is inefficient. Summary of the Invention

[0003] In view of this, multiple embodiments of the present application are dedicated to providing a robot footprint generation method and program product, which can be suitable for efficiently realizing diverse gait requirements.

[0004] One embodiment of the present application provides a robot footprint generation method, the method comprising: determining a designated action of the robot, and determining a swing phase duty cycle and an inter-foot phase offset corresponding to the designated action; generating a contact signal for indicating the contact between the robot and a designated surface, and a step signal for indicating the relative displacement of the robot relative to the designated surface based on a phase variable and a gait mapping relationship; wherein the phase variable is used to characterize the step progress of the robot within a step cycle; the step cycle includes a plurality of step phases, and the gait mapping relationship is used to indicate the relationship between the phase variable and the swing phase duty cycle and the inter-foot phase offset; the gait mapping relationship includes a stage gait mapping relationship corresponding to each step phase; and generating the footprint of the robot under the designated action according to an expected speed corresponding to the robot, the contact signal and the step signal.

[0005] Optionally, the specified action includes: stepping action and in-place action; wherein, the stepping action includes at least running and walking, and the in-place action includes at least standing and jumping; wherein, the inter-foot phase offset corresponding to the stepping action is greater than the inter-foot phase offset of the in-place action; the swing phase duty cycle of running is greater than the swing phase duty cycle of walking, and the swing phase duty cycle of jumping is greater than the swing phase duty cycle of standing.

[0006] Optionally, the multiple stepping stages are obtained by dividing the stepping period based on the difference between the swing phase duty cycle and the inter-foot phase offset, or the multiple stepping stages are obtained by dividing the stepping period based on the swing phase duty cycle.

[0007] Optionally, the expected speed includes a forward speed, a rotational angular velocity, and a lateral speed; the step signal includes a forward step signal and a lateral step signal; the footprint of the robot under the specified action includes a forward step footprint, a lateral step footprint, and a contact footprint; the steps of generating the footprint of the robot under the specified action according to the expected speed, the contact signal, and the step signal corresponding to the robot include: generating the forward step footprint based on the forward speed, the rotational angular velocity, and the forward step signal; generating the lateral step footprint based on the lateral speed and the lateral step signal; generating the contact footprint based on the contact signal.

[0008] Optionally, the method further includes: parsing the footprint under the specified action into joint motion trajectories of each leg joint of the robot.

[0009] Optionally, the method further includes: generating a swing arm trajectory corresponding to the robot based on a phase variable and a swing arm mapping relationship; wherein, the swing arm mapping relationship characterizes the relationship between the phase variable, the swing phase duty ratio, and the inter-foot phase offset within the step period; wherein, the swing arm trajectory and the footprint of the robot under the specified action are used to train a motion control model for controlling the motion of the robot.

[0010] Optionally, the robot has multiple feet, and the multiple feet correspond to different gait mapping relationships; there are at least two feet corresponding to opposite step periods; the steps of generating a contact signal for indicating the contact situation between the robot and a specified surface, and a step signal for indicating the relative displacement situation of the robot with respect to the specified surface based on a phase variable and a gait mapping relationship include: generating a contact signal for indicating the contact situation between each foot and the specified surface, and a step signal for indicating the relative displacement situation of each foot with respect to the specified surface based on the phase variable and the gait mapping relationships corresponding to the multiple feet.

[0011] Optionally, the steps of generating a step signal for indicating the relative displacement situation of the robot with respect to the specified surface based on a phase variable and a gait mapping relationship include: normalizing the phase variable based on the swing phase duty ratio and the inter-foot phase offset to obtain a target phase variable, or normalizing the phase variable based on the swing phase duty ratio to obtain a target phase variable; generating a relative step signal for indicating the relative displacement situation of the robot with respect to the specified surface based on the target phase variable and the gait mapping relationship.

[0012] Optionally, the step of generating the footprint of the robot under the specified action according to the expected speed, the contact signal, and the step signal corresponding to the robot includes: generating a plurality of spatial direction footprints of the robot under the specified action according to the expected speed, the contact signal, and the relative step signal corresponding to the robot.

[0013] An embodiment of the present application further provides a robot footprint generation device, which includes: a parameter determination module, configured to determine a specified action of the robot and determine the duty ratio of the swing phase and the inter-foot phase offset corresponding to the specified action; a signal generation module, configured to generate a contact signal for indicating the contact situation between the robot and the specified surface and a step signal for indicating the relative displacement situation of the robot relative to the specified surface based on a phase variable and a gait mapping relationship; wherein the phase variable is used to characterize the step progress of the robot within a step cycle; the step cycle includes a plurality of step stages, and the gait mapping relationship is used to represent the relationship between the phase variable, the duty ratio of the swing phase, and the inter-foot phase offset; the gait mapping relationship includes a stage gait mapping relationship corresponding to each step stage; a footprint generation module, configured to generate the footprint of the robot under the specified action according to the expected speed, the contact signal, and the step signal corresponding to the robot.

[0014] An embodiment of the present application further provides a computer device, which includes a memory and a processor. At least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor to implement the method as described above.

[0015] An embodiment of the present application further provides a computer-readable storage medium, in which at least one computer program is stored, and when the at least one computer program is executed by a processor, it can implement the method as described above.

[0016] An embodiment of the present application further provides a computer program product, which is used to implement the method as described above.

[0017] In multiple embodiments provided by the present application, the swing - phase duty ratio and the inter - foot phase offset are digital characterizations of the robot's actions. The stepping cycle includes multiple stepping stages. Based on this, a gait mapping relationship can be provided to characterize the relationship between the phase variable and the swing - phase duty ratio and the inter - foot phase offset, such that the gait mapping relationship includes a stage gait mapping relationship corresponding to each stepping stage. Furthermore, based on the phase variable and the gait mapping relationship, a contact signal indicating the contact situation between the robot and the specified surface and a stepping signal indicating the relative displacement of the robot with respect to the specified surface can be generated, and the footprint of the robot under the specified action can be generated by combining the expected speed, the contact signal, and the stepping signal of the robot. In the embodiments of the present application, since each stepping stage corresponds to an independent stage gait mapping relationship, segmented and fine - grained gait control is achieved. Therefore, there is no need to construct a proprietary mapping relationship for different robot actions. The present application enables the gait mapping relationship to be applicable to any specified action. Based on the swing - phase duty ratio and the inter - foot phase offset of the specified action and using the gait mapping relationship, the corresponding footprint can be generated, which is convenient for controlling the robot to exhibit diverse gaits. It can be seen that implementing the embodiments provided by the present application can efficiently meet the requirements of diverse gaits. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 The flowchart of the method for generating the robot footprint provided by an embodiment of the present application.

[0019] Figure 2 The schematic diagram of the spline curve of the gait mapping relationship for generating the contact signal provided by an embodiment of the present application.

[0020] Figure 3 The schematic diagram of the spline curve of the gait mapping relationship for generating the stepping signal provided by an embodiment of the present application.

[0021] Figure 4 The schematic diagram of the footprint of the robot under the specified action provided by an embodiment of the present application.

[0022] Figure 5 The schematic diagram of the robot joints provided by an embodiment of the present application.

[0023] Figure 6 The schematic diagram of the joint motion trajectory provided by an embodiment of the present application.

[0024] Figure 7 The schematic diagram of the computer device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0025] Next, the accompanying drawings in the embodiments of the present application will be used to clearly and completely describe the information to be retrieved in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments.

[0026] In the description of the embodiments of the present application, it should be understood that the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the described features. In the description of the embodiments of the present application, "a plurality" means two or more, unless otherwise specifically defined.

[0027] A legged robot is a type of robot system that realizes movement by simulating the leg structure of a living organism and usually includes multiple controllable joints, such as the hip, knee, and ankle. Legged robots have stronger obstacle-crossing capabilities in complex terrains (such as rugged mountains, steps, ruins, sand, and forests) and are widely used in scenarios such as rescue, military reconnaissance, space exploration, industrial inspection, and agricultural operations.

[0028] The external posture formed by the rhythmic movements of the robot's legs during movement can be called a gait. A reasonable gait can make the dynamic stability, motion efficiency, and terrain adaptability of the robot meet expectations. Since periodic functions can simulate gait patterns with strong rhythm, symmetry, and regularity, such as walking in a straight line at a constant speed. Therefore, related technologies usually use periodic functions for gait modeling.

[0029] However, periodic functions have limitations and are usually only suitable for expressing motion patterns with a single frequency, symmetric structure, and fixed variation rules. After the shape of the periodic function is fixed, it is difficult to flexibly adapt to diverse gaits. If there are diverse gait requirements in related technologies, it is necessary to separately perform targeted periodic function modeling for different gaits, increasing the implementation complexity of diverse gaits.

[0030] Therefore, it is necessary to provide a robot footprint generation method. The duty ratio of the swing phase and the inter-foot phase offset are the digital representations of the robot's actions, and the stepping cycle includes multiple stepping stages. Based on this, a gait mapping relationship can be provided to characterize the relationship between the phase variable and the duty ratio of the swing phase and the inter-foot phase offset, so that the gait mapping relationship includes a stage gait mapping relationship corresponding to each stepping stage. Furthermore, a contact signal indicating the contact situation between the robot and the specified surface and a stepping signal indicating the relative displacement of the robot relative to the specified surface can be generated based on the phase variable and the gait mapping relationship, and the footprint of the robot under the specified action can be generated by combining the expected speed, the contact signal, and the stepping signal of the robot. In the embodiments of the present application, since each stepping stage corresponds to an independent stage gait mapping relationship, segmented fine gait control is achieved. Therefore, there is no need to construct a proprietary mapping relationship for different robot actions. The present application makes the gait mapping relationship applicable to any specified action. Based on the duty ratio of the swing phase and the inter-foot phase offset of the specified action and using the gait mapping relationship, the corresponding footprint can be generated, which is convenient for controlling the robot to exhibit diverse gaits. It can be seen that implementing the embodiments provided in the present application can efficiently meet the requirements of diverse gaits.

[0031] In multiple embodiments provided in the present application, the robot footprint generation method can be applied to a robot footprint generation device. The robot footprint generation device can be an electronic device with certain computing capabilities and network access capabilities. The electronic device can be a desktop computer, a laptop computer, a tablet computer, or a server. The electronic device can be connected to the server through a network. The server can be a distributed server, including multiple processors, memories, network communication modules, etc., which cooperate to achieve various functions. Alternatively, the server can also be a server cluster formed by several servers, which has higher computing and data processing capabilities. With the development of science and technology, the server can also be implemented by using new forms of technical means, such as a new type of "server" based on quantum computing. Of course, in some embodiments, the robot footprint generation device can also be a program module running on an electronic device.

[0032] Please refer to Figure 1 An embodiment of the present application provides a robot footprint generation method. The robot footprint generation method can be applied to a robot footprint generation device. The robot footprint generation method may include the following steps.

[0033] Step S110: Determine the specified action of the robot, and determine the duty ratio of the swing phase and the inter-foot phase offset corresponding to the specified action.

[0034] Step S120: Based on the phase variable and the gait mapping relationship, generate a contact signal for representing the contact situation between the robot and the specified surface, and a stepping signal for representing the relative displacement situation of the robot relative to the specified surface; wherein, the phase variable is used to characterize the stepping progress of the robot within the stepping period; the stepping period includes multiple stepping stages, and the gait mapping relationship is used to represent the relationship between the phase variable, the duty ratio of the swing phase, and the inter-foot phase offset; the gait mapping relationship includes a stage gait mapping relationship corresponding to each stepping stage.

[0035] Step S130: Generate the footprint of the robot under the specified action according to the expected speed corresponding to the robot, the contact signal, and the stepping signal.

[0036] In this embodiment, the robot can be a legged robot with any number of legs, including but not limited to: a bipedal robot for simulating human walking, a quadruped robot with good stability and strong adaptability to rough terrain, a hexapod robot suitable for crawling and low-speed stable movement with multiple legs lifted simultaneously while maintaining balance, an octapod robot simulating spider crawling, and other multi-legged robots for exploring ultra-high redundancy.

[0037] In this embodiment, the specified action of the robot refers to an action that can control the robot to execute, such as running, walking, etc. The external manifestation formed after executing the specified action is the gait corresponding to the specified action. Optionally, the specified action can be understood as an action that can externally exhibit the expected gait (such as running), or can be understood as a combination of action units (such as the combination of lifting the foot, stepping the foot, and landing the foot). The embodiments of the present application do not limit this.

[0038] In this embodiment, the duty ratio of the swing phase and the inter-foot phase offset are data-based characterizations of the specified action, and the duty ratio of the swing phase and / or the inter-foot phase offset corresponding to different specified actions can be different. Among them, the duty ratio of the swing phase refers to the time ratio of the foot of the robot in the swing phase during the complete stepping period, and the swing phase refers to the posture of the foot swinging in the air. For example, a duty ratio of the swing phase of 0.4 means that the corresponding foot is in the air for 40% of the stepping period. Among them, the inter-foot phase offset refers to the time difference of the gait phase of one foot of the robot relative to another foot. For example, an inter-foot phase offset of 0.5 means that the phase of the left foot and the right foot is offset by 0.5, that is, the phases of the left foot and the right foot differ by half a gait cycle. Specifically, the method for determining the duty ratio of the swing phase and the inter-foot phase offset can be looking up a table or simulation. The embodiments of the present application do not limit this.

[0039] In this embodiment, since the gait mapping relationship can characterize the relationship between the phase variable, the swing-phase duty ratio, and the inter-foot phase offset, when the values of the swing-phase duty ratio and the inter-foot phase offset are determined, these values can be applied to the gait mapping relationship to generate a contact signal indicating the contact situation between the robot and the specified surface, and a stepping signal indicating the relative displacement of the robot with respect to the specified surface.

[0040] In this embodiment, the gait mapping relationship refers to the mapping relationship between the phase variable and the control parameters within a stepping cycle. The control parameters may include, but are not limited to, the swing-phase duty ratio and the inter-foot phase offset. Optionally, the control parameters may further include the foot-lifting height, the support-force distribution weight for controlling the force borne by each foot during the support phase, the contact-time offset representing the advance time / delay time of contacting the ground, the phase modulation factor for dynamically adjusting the rate of the foot-phase progress, the expected landing point representing the target landing point of each stepping cycle, the damping / stiffness coefficient characterizing the force feedback after the foot touches the ground, the duration of the motion cycle, the width of the contact stability window, and one or more other such parameters. The embodiments of the present application do not limit this.

[0041] In this embodiment, the stepping cycle refers to a complete gait rhythm cycle, including a complete swing and support of the foot. The stepping cycle includes multiple stepping phases. The stepping phase refers to the stage in which a partial motion for completing a specified action is located. In the present application, the stepping cycle can be divided into stages according to actual needs, so as to obtain multiple stepping phases. Optionally, the stepping cycle can be divided into multiple stepping phases according to the swing-phase duty ratio and / or the inter-foot phase offset, or can also be divided into multiple stepping phases according to one or more of the above other control parameters. The embodiments of the present application do not limit this.

[0042] In this embodiment, in order to achieve fine control of the gait, the gait mapping relationship includes a stage gait mapping relationship corresponding to each stepping phase. Among them, the stage gait mapping relationship characterizes the relationship between the phase variable and the swing-phase duty ratio and the inter-foot phase offset when the phase variable is in the corresponding stepping phase. There are mapping differences between different stage gait mapping relationships, so that the stage gait mapping relationship can accurately characterize the gait of the belonging stepping phase.

[0043] In this embodiment, the contact signal represents whether the robot foot is in contact with the specified surface. A plurality of consecutive contact signals can form a contact sequence, and the contact sequence can represent the change of the contact signal in the time dimension. In addition, the contact signal can also represent the proximity of the robot foot to the specified surface. Among them, the specified surface can be any surface selected according to actual needs, such as the ground, wall surface, spherical surface, etc. The stepping signal represents the displacement of the robot relative to the specified surface. A plurality of consecutive stepping signals can form a stepping sequence, and the stepping sequence can represent the change of the stepping signal in the time dimension. Optionally, the stepping signal can represent relative displacements in any direction, or the stepping signal refers to a relative displacement signal in one stepping direction. For example, the stepping directions include the x-axis stepping direction and the y-axis stepping direction constructed relative to the robot origin, or the stepping direction only includes the direction pointing to the target location. In this regard, the embodiments of the present application do not make any limitations.

[0044] In some embodiments, the gait mapping relationships for generating the contact signal and the stepping signal can be different. Based on the phase variable and the gait mapping relationships, the steps of generating a contact signal for representing the contact situation between the robot and the specified surface, and a stepping signal for representing the relative displacement situation of the robot relative to the specified surface specifically can include: based on the phase variable and the gait mapping relationship for generating the contact signal, generating a contact signal for representing the contact situation between the robot and the specified surface, and based on the phase variable and the gait mapping relationship for generating the stepping signal, generating a stepping signal for representing the relative displacement situation of the robot relative to the specified surface. Among them, the phase variable refers to the position of the robot foot in the stepping cycle. For example, when the phase variable is 0, it represents the start of the stepping cycle; when the phase variable is 0.5, it represents the midpoint of the stepping cycle; when the phase variable is 1, it represents the end of the stepping cycle.

[0045] In this embodiment, in the case where the contact signal and the stepping signal are clear, the footprint of the robot under the specified action can be generated according to the expected speed, contact signal, and stepping signal corresponding to the robot. Among them, the expected speed of the robot refers to the expected stepping speed that the robot is expected to reach. The expected speed can include but is not limited to linear speed and angular speed, and the expected speed can be used to guide the gait rhythm and adjust the footprint.

[0046] Generally speaking, in this embodiment, the swing phase duty ratio and the inter-foot phase offset are the digital representations of the robot's actions, and the stepping cycle includes multiple stepping stages. Based on this, a gait mapping relationship can be provided to characterize the relationship between the phase variables and the swing phase duty ratio and the inter-foot phase offset, so that the gait mapping relationship includes the stage gait mapping relationship corresponding to each stepping stage. Furthermore, a contact signal indicating the contact situation between the robot and the specified surface and a stepping signal indicating the relative displacement of the robot relative to the specified surface can be generated based on the phase variables and the gait mapping relationship, and the footprint of the robot in the specified action can be generated by combining the expected speed, the contact signal, and the stepping signal of the robot. In the embodiments of the present application, since each stepping stage corresponds to an independent stage gait mapping relationship, segmented fine gait control is achieved. Therefore, there is no need to construct a proprietary mapping relationship for different robot actions. The present application makes the gait mapping relationship applicable to any specified action. Based on the swing phase duty ratio and the inter-foot phase offset of the specified action and using the gait mapping relationship, the corresponding footprint can be generated, which is convenient for controlling the robot to exhibit diverse gaits. It can be seen that implementing the embodiments provided by the present application can efficiently meet the requirements of diverse gaits.

[0047] In some embodiments, the specified actions include: stepping actions and stationary actions; wherein, the stepping actions include at least running and walking, and the stationary actions include at least standing and jumping; wherein, the inter-foot phase offset corresponding to the stepping actions is greater than that of the stationary actions; the swing phase duty ratio of running is greater than that of walking, and the swing phase duty ratio of jumping is greater than that of standing.

[0048] In this embodiment, the robot footprint generation device is applicable to a variety of specified actions. The specified actions can be divided into two types: stepping actions and stationary actions. The stationary action refers to an action in which the robot displaces relative to its current position. On the contrary, the stepping action refers to an action in which the robot does not displace relative to its current position.

[0049] In this embodiment, the stepping action of running includes, but is not limited to, running actions corresponding to various paces. Similarly, the stepping action of walking also includes, but is not limited to, walking actions corresponding to various paces. Standing includes, but is not limited to, standing actions such as multi-foot support standing and single-foot standing. Jumping includes, but is not limited to, jumping actions such as multi-foot simultaneous jumping, single-foot jumping, and multi-foot alternating jumping. In some embodiments, in addition to running and walking, the stepping actions may further include actions such as crawling and zombie jumping. In addition to standing and jumping, the stationary actions may further include actions such as marching in place and spinning in place.

[0050] In this embodiment, the inter-foot phase offset corresponding to the stepping motion (e.g., 0.5) is made greater than the inter-foot phase offset of the stationary motion (e.g., 0), so that the robot can perform the stationary motion with a smaller inter-foot phase offset to maintain body stability, and perform the stepping motion with a larger inter-foot phase offset to meet the propulsion requirement. In this embodiment, the duty ratio of the swing phase of running (e.g., 0.7) is greater than the duty ratio of the swing phase of walking (e.g., 0.5), and the duty ratio of the swing phase of jumping (e.g., 0.2) is greater than the duty ratio of the swing phase of standing (e.g., 0). This can make the time that the foot is in the air during walking shorter to maintain stability, and make the time that the foot is in the air during running longer to achieve the effect of fast stepping, and make the time that the foot is in the air during standing 0 to achieve the effect of complete stability, and make the foot instantaneously swing away from the specified surface during jumping to achieve the effect of taking off. In some embodiments, the duty ratio of the swing phase of walking is greater than / less than the duty ratio of the swing phase of jumping, which is not limited in the embodiments of the present application.

[0051] In this embodiment, the inter-foot phase offset and / or the duty ratio of the swing phase are different between different specified motions, so that the gait mapping relationship is applicable to multiple specified motions, and diversified footprints can be obtained, thereby realizing diversified gaits.

[0052] In some embodiments, the multiple stepping stages are obtained by dividing the stepping cycle based on the difference between the duty ratio of the swing phase and the inter-foot phase offset, or the multiple stepping stages are obtained by dividing the stepping cycle based on the duty ratio of the swing phase.

[0053] In this embodiment, the duty ratio of the swing phase is denoted as δ, and the inter-foot phase offset is denoted as ψ. Optionally, the stepping cycle T s (or T stance ) is divided based on δ and ψ to obtain multiple stepping stages, which can be expressed as [0, δ−ψ), [δ−ψ, ψ), [ψ, 1]. The stepping cycle T is divided based on δ s to obtain multiple stepping stages, which can be expressed as [0, δ), [δ, 1].

[0054] In some embodiments, the robot has multiple feet, and the multiple feet correspond to different gait mapping relationships; there are at least two feet corresponding to opposite stepping cycles; the robot footprint generation device can generate a contact signal for indicating the contact situation of each foot with the specified surface and a stepping signal for indicating the relative displacement situation of each foot with respect to the specified surface based on the phase variable and the gait mapping relationships corresponding to the multiple feet.

[0055] In this embodiment, the robot has multiple feet. The number of feet can be odd or even, and the embodiments of this application do not limit this. Whether it is odd or even, at least two feet among the multiple feet can be called a pair of feet. A pair of feet corresponds to opposite stepping cycles, which enables a pair of feet to alternately be in the stance phase and the swing phase, that is, when one foot is in the stance phase, the other foot is in the swing phase. Generally, the phase difference between the two is 0.5, which can ensure that the robot always has a foot supporting on the specified surface and reduce the risk of the robot becoming unstable.

[0056] In this embodiment, the gait mapping relationship includes: the gait mapping relationship corresponding to each foot in a pair of feet for generating a contact signal, and the gait mapping relationship corresponding to each foot in a pair of feet for generating a stepping signal.

[0057] In this embodiment, when the i-th foot is represented by i, i ∈ [0, 1], and 0 and 1 respectively represent the two feet in a pair of feet. For example, 0 represents the left foot and 1 represents the right foot.

[0058] In this embodiment, the gait mapping relationship for generating a contact signal can be expressed as the following polynomial:

[0059]

[0060] where φ refers to the phase variable, and C z,i (φ) refers to the contact signal of the i-th foot in the vertical direction (i.e., the z-axis direction) during a stepping cycle when contacting the specified surface. Based on C z,i (φ), the contact signal in each stepping cycle can be determined. C z,i (φ) ∈ [0, 1], and α n refers to the polynomial coefficient of the spline curve and can affect the curve shape. Optionally, α conforms to α[α0, …, α5] T = [0, 0.1, 5.0, ―18.8, 12.0, 9.6]. n refers to the order of the polynomial. For example, the 5th order can make the contact signal smoothly rise from 0 to 1 and make the contact signal smoothly fall from 1 to 0. represents the process of the contact signal smoothly rising from 0 to 1, represents the process of the contact signal smoothly falling from 1 to 0. C z,0 (φ) = 0 represents that the foot is in the stance phase in the vertical direction, and C z,0 (φ) ≠ 0 represents that the foot is in the swing phase in the vertical direction.

[0061] In some embodiments, ψ = 0.5 and δ = 0.7 are set, and the change of C z,i (φ) in a stepping cycle can be expressed as follows Figure 2The polynomial spline curve shown.

[0062] In this embodiment, a gait mapping relationship corresponding to multiple feet is provided to adapt to the diversified gait control of a multi-legged robot, so as to meet the diversified gait requirements.

[0063] In some embodiments, the robot footprint generation device may normalize the phase variable based on the swing phase duty ratio and the inter-foot phase offset to obtain a target phase variable, or normalize the phase variable based on the swing phase duty ratio to obtain a target phase variable; and generate a relative stepping signal for representing the relative displacement of the robot with respect to the specified surface based on the target phase variable and the gait mapping relationship.

[0064] In this embodiment, the gait mapping relationship for generating the relative stepping signal can be expressed as the following polynomial:

[0065]

[0066]

[0067] Where C x(y),i (φ) refers to the relative stepping signal of the i-th foot with respect to the specified surface during a stepping cycle in the stepping direction (i.e., the x-axis direction / y-axis direction). Based on C x(y),i (φ), the relative stepping signal within each stepping cycle can be determined, and C x(y),i (φ) ∈ [−0.5, 0.5]. φ′ i is the target phase variable obtained by normalizing φ through ψ and δ, and φ′ i ∈ [0, 1].

[0068] In some embodiments, when ψ = 0.5 and δ = 0.7, the variation of C x(y),i (φ′) within a stepping cycle can be expressed as Figure 3 the polynomial spline curve shown.

[0069] In this embodiment, the robot footprint generation device can normalize the phase variable based on ψ and δ, that is, realize the normalization of φ through the mapping relationship corresponding to the aforementioned φ′0 and φ′1, so as to obtain the target phase variables φ′0 and φ′1. Further, the relative stepping signal C can be determined based on φ′0 and φ′1 and the gait mapping relationship for generating the stepping signal. x(y),i (φ). This can map the phase variables of all feet in the same mathematical space, thereby reducing the computational complexity.

[0070] In some embodiments, the robot footprint generation device may generate a plurality of spatial direction footprints of the robot under the specified action according to the expected speed corresponding to the robot, the contact signal, and the relative step signal.

[0071] In this embodiment, since C z,i (φ) represents the contact signal of the robot in the vertical direction, and C x(y),i (φ) represents the step signal of the robot in the step direction. Therefore, based on the expected speed of the robot, C z,i (φ), and C x(y),i (φ), a plurality of spatial direction footprints can be generated, and precise gait control of the robot can be achieved based on the plurality of spatial direction footprints.

[0072] In some embodiments, the expected speed includes a forward speed, a rotational angular velocity, and a lateral speed; the step signal includes a forward step signal and a lateral step signal; the footprint of the robot under the specified action includes a forward step footprint, a lateral step footprint, and a contact footprint; the robot footprint generation device may generate the forward step footprint based on the forward speed, the rotational angular velocity, and the forward step signal; generate the lateral step footprint based on the lateral speed and the lateral step signal; and generate the contact footprint based on the contact signal.

[0073] In this embodiment, the forward speed can be expressed as The rotational angular velocity can be expressed as The lateral speed can be expressed as The forward step signal can be expressed as C x,i (φ), and the lateral step signal can be expressed as C y,i (φ). Among them, and represent the desired linear velocity, represents the desired angular velocity. The robot footprint generation device can generate a forward step footprint based on Generate a lateral step footprint based on Based on Generate a contact footprint, based on The footprint of the end of the robot's leg relative to the body coordinate system under the specified action Includes a forward step footprint, a lateral step footprint, and a contact footprint. Among them, s i represents the direction factor of the i-th foot, used to distinguish between the left and right feet, s = [1, -1] T , l foot represents the front and back half distance of the landing point, and h foot represents the swing height. In some embodiments, And in the case of the corresponding spatial footprint can be represented in Figure 4 the three-dimensional space shown in wherein the three-dimensional space is constrained by three directions of X[m], Y[m], and Z[m].

[0074] In this embodiment, by separately generating the forward stepping footprint, lateral stepping footprint, and contact footprint of the robot under the specified action, the gait control fineness can be improved.

[0075] In some embodiments, the robot footprint generation device can resolve the footprint under the specified action into the joint motion trajectories of the respective leg joints of the robot.

[0076] In this embodiment, after clarifying the forward stepping footprint, lateral stepping footprint, and contact footprint of the robot under the specified action, the forward stepping footprint, lateral stepping footprint, and contact footprint can be resolved based on inverse kinematics, so as to obtain the joint motion trajectories corresponding to the respective leg joints of the robot.

[0077] In this embodiment, the robot footprint generation device can be applied to Figure 5 the robot shown in Figure 5 which is in the three-dimensional space shown in and can be represented by a three-dimensional moment vector The robot is composed of an upper arm, a forearm, a thigh, a shank, and a foot, and specifically includes the following joints: a shoulder (Shoulder 3-DoF) corresponding to three degrees of freedom in three directions, an elbow, a hip (Hip 3-DoF) corresponding to three degrees of freedom in three directions, a knee joint, an ankle (Ankle 2-DoF) corresponding to two degrees of freedom, and a waist (Waist 3-DoF) corresponding to three degrees of freedom. Among them, the leg joints include: a knee joint, a hip joint corresponding to three degrees of freedom, and an ankle joint corresponding to two degrees of freedom. The footprint under the specified action can be resolved to obtain the joint motion trajectories corresponding to the knee joint, the hip joint corresponding to three degrees of freedom, and the ankle joint corresponding to two degrees of freedom, respectively.

[0078] In some embodiments, the joint motion trajectories can refer to Figure 6 wherein the joint motion trajectories corresponding to the knee joint, hip side swing joint, ankle horizontal rotation joint, hip front and back swing joint, ankle front and back swing joint, and hip horizontal rotation joint are constrained by the mapping relationship between the phase variable and the joint position.

[0079] In this embodiment, the joint motion trajectory obtained based on footprint analysis can facilitate the refined characterization of the desired joint control situation.

[0080] In some embodiments, the robot footprint generation device can generate a swing arm trajectory corresponding to the robot based on the phase variable and the swing arm mapping relationship; wherein, the swing arm mapping relationship characterizes the relationship between the phase variable, the duty ratio of the swing phase, and the inter-foot phase offset within the stepping cycle; wherein, the swing arm trajectory and the footprint of the robot under the specified action are used to train a motion control model for controlling the motion of the robot.

[0081] In this embodiment, it is also possible to generate swing arm trajectories respectively corresponding to a pair of arms based on the swing arm mapping relationships respectively corresponding to the pair of arms and generate swing arm trajectories respectively corresponding to a pair of arms of the robot and wherein, represents the maximum swing range of the shoulder pitch joint.

[0082] In this embodiment, the swing arm trajectory and the footprint of the robot under the specified action can be used as the training basis for the motion control model of the robot. In some embodiments, the swing arm trajectory and the joint motion trajectories of each leg joint can constitute a reference joint position q with 14 degrees of freedom ref , to be used as the training basis for the motion control model of the robot. Training the motion control model based on the trajectories generated above can improve the training accuracy of the model and save the model sample annotation operation.

[0083] The embodiment of the present application also provides a robot footprint generation device. The robot footprint generation device may include: a parameter determination module, configured to determine a specified action of the robot and determine the duty ratio of the swing phase and the inter-foot phase offset corresponding to the specified action; a signal generation module, configured to generate a contact signal for indicating the contact situation between the robot and the specified surface and a stepping signal for indicating the relative displacement situation of the robot relative to the specified surface based on the phase variable and the gait mapping relationship; wherein, the phase variable is used to characterize the stepping progress of the robot within the stepping cycle; the stepping cycle includes a plurality of stepping stages, and the gait mapping relationship is used to represent the relationship between the phase variable, the duty ratio of the swing phase, and the inter-foot phase offset; the gait mapping relationship includes a stage gait mapping relationship corresponding to each stepping stage; a footprint generation module, configured to generate the footprint of the robot under the specified action according to the expected speed, the contact signal, and the stepping signal corresponding to the robot.

[0084] In this embodiment, for the specific functions and effects achieved by the robot footprint generation device, reference may be made to other embodiments of this application for comparison and explanation, which will not be elaborated here.

[0085] Please refer to Figure 7 This application embodiment also provides a computer device, which includes: a memory and a processor. At least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor to implement the method as described above.

[0086] This application embodiment also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the processor implements the method as described above.

[0087] This application embodiment also provides a computer program product containing instructions. When the computer program product is executed by a processor, the method as described above is implemented.

[0088] It can be understood that the specific examples in this article are only for helping those skilled in the art to better understand the embodiments of this application, rather than limiting the scope of the present invention.

[0089] It can be understood that in various embodiments of this application, the magnitudes of the sequence numbers of the various processes do not mean the order of execution is prior or posterior. The order of execution of the various processes should be determined according to their functions and internal logics, and should not constitute any limitation to the implementation process of the embodiments of this application.

[0090] It can be understood that the various embodiments described in this application can be implemented alone or in combination, and this application embodiment does not limit this.

[0091] Unless otherwise specified, all technical and scientific terms used in the embodiments of this application have the same meanings as those commonly understood by those skilled in the technical field of this application. The terms used in this application are only for the purpose of describing specific embodiments and are not intended to limit the scope of this application. The term "and / or" used in the embodiments of this application and the appended claims includes any and all combinations of one or more of the related listed items. The singular forms "a", "above-mentioned", and "the" used in the embodiments of this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0092] It can be understood that the processor in the embodiments of the present application may be an integrated circuit chip with signal processing capabilities. During implementation, the steps of the above method embodiments can be completed by the integrated logic circuit in hardware or instructions in software form in the processor. The above processor may be a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed and completed by a hardware decoding processor, or executed and completed by a combination of hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps of the above method.

[0093] It can be understood that the memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0094] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the information to be retrieved. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0095] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0096] In several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0097] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0098] In addition, in each embodiment of the present application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0099] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the searchable information of the present application, in essence, or the part that contributes to the prior art, or the part of the searchable information, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0100] The above is only the specific embodiment of the present application, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application and should be covered by the protection scope of the present application. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A method for generating a robot footprint, characterized in that, The method includes: Determine a specified action of the robot, and determine the swing-phase duty ratio and the inter-foot phase offset corresponding to the specified action; Based on the phase variable and the gait mapping relationship, generate a contact signal for representing the contact situation between the robot and the specified surface, and a stepping signal for representing the relative displacement situation of the robot relative to the specified surface; wherein, the phase variable is used to characterize the stepping progress of the robot within a stepping cycle; the stepping cycle includes multiple stepping phases, and the gait mapping relationship is used to represent the relationship between the phase variable, the swing-phase duty ratio, and the inter-foot phase offset; the gait mapping relationship includes a stage gait mapping relationship corresponding to each stepping phase; Generate the footprint of the robot under the specified action according to the expected speed, the contact signal, and the stepping signal corresponding to the robot.

2. The method according to claim 1, wherein The specified action includes: a stepping action and a stationary action; Wherein, the stepping action at least includes running and walking, and the stationary action at least includes standing and jumping; Wherein, the inter-foot phase offset corresponding to the stepping action is greater than the inter-foot phase offset of the stationary action; the swing-phase duty ratio of running is greater than the swing-phase duty ratio of walking, and the swing-phase duty ratio of jumping is greater than the swing-phase duty ratio of standing.

3. The method according to claim 1, wherein The multiple stepping phases are obtained by dividing the stepping cycle based on the difference between the swing-phase duty ratio and the inter-foot phase offset, or the multiple stepping phases are obtained by dividing the stepping cycle based on the swing-phase duty ratio.

4. The method according to claim 1, characterized in that The expected speed includes a forward speed, a rotational angular velocity, and a lateral speed; the stepping signal includes a forward stepping signal and a lateral stepping signal; the footprint of the robot under the specified action includes a forward stepping footprint, a lateral stepping footprint, and a contact footprint; the step of generating the footprint of the robot under the specified action according to the expected speed, the contact signal, and the stepping signal corresponding to the robot includes: Generate the forward stepping footprint based on the forward speed, the rotational angular velocity, and the forward stepping signal; Generate the lateral stepping footprint based on the lateral speed and the lateral stepping signal; Generate the contact footprint based on the contact signal.

5. The method according to claim 1, wherein The method further includes: Generate a swing-arm trajectory corresponding to the robot based on the phase variable and the swing-arm mapping relationship; wherein, the swing-arm mapping relationship characterizes the relationship between the phase variable, the swing-phase duty ratio, and the inter-foot phase offset within the stepping cycle; wherein, the swing-arm trajectory and the footprint of the robot under the specified action are used to train a motion control model for controlling the movement of the robot.

6. The method according to claim 1, wherein The robot has multiple feet, and the multiple feet correspond to different gait mapping relationships; there are at least two feet corresponding to opposite stepping cycles; the step of generating a contact signal for representing the contact situation between the robot and the specified surface, and a stepping signal for representing the relative displacement situation of the robot relative to the specified surface based on the phase variable and the gait mapping relationship includes: Generate a contact signal for indicating the contact condition of each foot with the specified surface and a step signal for indicating the relative displacement condition of each foot with respect to the specified surface based on the phase variable and the gait mapping relationship corresponding to the multiple feet.

7. The method according to claim 1, wherein The step of generating a step signal for indicating the relative displacement condition of the robot with respect to the specified surface based on the phase variable and the gait mapping relationship includes: Normalize the phase variable based on the swing phase duty ratio and the inter-foot phase offset to obtain a target phase variable, or normalize the phase variable based on the swing phase duty ratio to obtain a target phase variable; Generate a relative step signal for indicating the relative displacement condition of the robot with respect to the specified surface based on the target phase variable and the gait mapping relationship.

8. The method according to claim 7, characterized in that The step of generating the footprint of the robot in the specified action according to the expected speed corresponding to the robot, the contact signal, and the step signal includes: Generate a plurality of spatial direction footprints of the robot in the specified action according to the expected speed corresponding to the robot, the contact signal, and the relative step signal.

9. The method according to any one of claims 1 to 8, characterized in that The method further includes: Resolve the footprint in the specified action into the joint motion trajectories of the respective leg joints of the robot.

10. A computer program product, characterized in that, The computer program product, when executed by a processor, implements the robot footprint generation method according to any one of claims 1 to 9.

Images