Ground contact detection method and device, computer readable storage medium and robot

Abstract

The invention belongs to the technical field of robots, and particularly relates to a ground touch detection method and device, a computer readable storage medium and a robot. The method comprises the following steps: acquiring data information of a leg joint encoder of the robot; determining the foot end bearing reaction of the robot according to the data information of the leg joint encoder; a preset ground touch detection model is used for processing the foot end bearing reaction, and a ground touch detection result of the robot is obtained; wherein the grounding detection model is a logic regression classifier model which is obtained by training based on a preset grounding detection sample set and is used for performing grounding detection, and each grounding detection sample in the grounding detection sample set comprises a sample foot end reaction force and a corresponding grounding detection result label. According to the method and the device, a sensor does not need to be additionally configured for the robot, the use cost of the robot is reduced, the influence of aging and damage of the sensor is avoided, and relatively high accuracy can be kept.

Description

Technical Field

[0001] The present application belongs to the field of robot technology, and in particular, relates to a ground contact detection method, device, computer-readable storage medium and robot. Background Art

[0002] In the process of controlling the robot, it is often necessary to perform ground detection on the robot, that is, to detect whether the foot of the robot is in contact with the ground. Existing ground detection methods mainly rely on the force sensor at the foot end, and judge whether it touches the ground by comparing the measured value of the force sensor with the set fixed threshold. Specifically, when the measured value of the force sensor is greater than the set fixed threshold, it is considered to be in contact with the ground, otherwise, it is considered to be not in contact with the ground. However, this method requires additional sensors to be configured for the robot, which increases the cost of using the robot, and these sensors are prone to aging and damage, resulting in a low accuracy rate of ground detection. Summary of the invention

[0003] In view of this, embodiments of the present application provide a ground touchdown detection method, device, computer-readable storage medium, and robot to solve the problems of high cost and low accuracy of existing ground touchdown detection methods.

[0004] A first aspect of an embodiment of the present application provides a ground contact detection method, which may include:

[0005] Get the data information of the robot's leg joint encoder;

[0006] Determine the foot end support reaction force of the robot according to the data information of the leg joint encoder;

[0007] Using a preset ground contact detection model to process the foot end support reaction force to obtain a ground contact detection result of the robot;

[0008] The touchdown detection model is a logistic regression classifier model for touchdown detection obtained by training based on a preset touchdown detection sample set, and each touchdown detection sample in the touchdown detection sample set includes a sample foot-end reaction force and a corresponding touchdown detection result label.

[0009] In a specific implementation of the first aspect, before using a preset ground contact detection model to process the foot end support reaction force to obtain a ground contact detection result of the robot, the method may further include:

[0010] Acquire the touchdown detection sample set;

[0011] determining a log-likelihood function corresponding to the touchdown detection sample set;

[0012] With the goal of maximizing the log-likelihood function, model parameters of the touchdown detection model are estimated to obtain model parameters of the touchdown detection model.

[0013] In a specific implementation of the first aspect, estimating model parameters of the touchdown detection model with the goal of maximizing the log-likelihood function to obtain the model parameters of the touchdown detection model may include:

[0014] Calculating partial derivatives of the log-likelihood function with respect to model parameters of the touchdown detection model;

[0015] Determining an adjustment amount of a model parameter of the ground contact detection model according to the partial derivative result and a preset learning rate;

[0016] Iteratively updating the model parameters of the ground contact detection model according to the adjustment amount to obtain iteratively updated model parameters;

[0017] If the preset parameter iteration update termination condition is not satisfied, returning to the step of obtaining the partial derivative of the log-likelihood function with respect to the model parameters of the ground contact detection model and subsequent steps;

[0018] If the parameter iterative updating termination condition is satisfied, the iteratively updated model parameters are determined as the model parameters of the ground contact detection model.

[0019] In a specific implementation of the first aspect, the step of processing the foot-end support reaction force using a preset ground contact detection model to obtain a ground contact detection result of the robot may include:

[0020] Inputting the foot-end support reaction force into the ground contact detection model, and obtaining the ground contact probability of the robot output by the ground contact detection model;

[0021] The ground contact probability is determined as a ground contact detection result of the robot.

[0022] In a specific implementation of the first aspect, the step of processing the foot-end support reaction force using a preset ground contact detection model to obtain a ground contact detection result of the robot may include:

[0023] Inputting the foot-end support reaction force into the ground contact detection model, and obtaining the ground contact probability of the robot output by the ground contact detection model;

[0024] Determining binary ground contact information of the robot according to the ground contact probability and a preset ground contact probability threshold; wherein the binary ground contact information includes ground contact or no ground contact;

[0025] The binary ground contact information is determined as a ground contact detection result of the robot.

[0026] In a specific implementation of the first aspect, determining the binary ground contact information of the robot according to the ground contact probability and a preset ground contact probability threshold may include:

[0027] When the touchdown probability is greater than or equal to the touchdown probability threshold, determining that the binary touchdown information is a touchdown;

[0028] When the ground contact probability is less than the ground contact probability threshold, the binary ground contact information is determined as no ground contact.

[0029] In a specific implementation of the first aspect, the data information of the leg joint encoder may include a leg joint rotation angle, a leg joint rotation speed, and a leg joint motor current;

[0030] Determining the foot end support reaction force of the robot according to the data information of the leg joint encoder may include:

[0031] According to the leg joint rotation angle, the leg joint rotation speed and the leg joint motor current, respectively determine the leg Jacobian matrix, leg joint torque vector, leg centrifugal force term, Coriolis force term and gravity term of the robot;

[0032] The foot-end support reaction force of the robot is determined according to the Jacobian matrix of the robot's legs, the leg joint torque vector, the leg centrifugal force term, the Coriolis force term and the gravity term.

[0033] A second aspect of an embodiment of the present application provides a ground contact detection device, which may include:

[0034] A data information acquisition module is used to acquire data information of the robot's leg joint encoders;

[0035] A foot end support reaction force determination module, used to determine the foot end support reaction force of the robot according to the data information of the leg joint encoder;

[0036] A ground contact detection module, used to process the foot end support reaction force using a preset ground contact detection model to obtain a ground contact detection result of the robot;

[0037] The touchdown detection model is a logistic regression classifier model for touchdown detection obtained by training based on a preset touchdown detection sample set, and each touchdown detection sample in the touchdown detection sample set includes a sample foot-end reaction force and a corresponding touchdown detection result label.

[0038] In a specific implementation of the second aspect, the ground contact detection device may further include:

[0039] A touchdown detection sample set acquisition module, used to acquire the touchdown detection sample set;

[0040] A log-likelihood function determination module, configured to determine a log-likelihood function corresponding to the touchdown detection sample set;

[0041] The model parameter estimation module is used to estimate the model parameters of the touchdown detection model with the goal of maximizing the log-likelihood function to obtain the model parameters of the touchdown detection model.

[0042] In a specific implementation of the second aspect, the model parameter estimation module can be specifically used to: obtain partial derivatives of the log-likelihood function with respect to the model parameters of the touchdown detection model; determine the adjustment amount of the model parameters of the touchdown detection model according to the partial derivatives and a preset learning rate; iteratively update the model parameters of the touchdown detection model according to the adjustment amount to obtain the iteratively updated model parameters; if the preset parameter iterative update termination condition is not met, return to execute the step of obtaining the partial derivatives of the log-likelihood function with respect to the model parameters of the touchdown detection model and its subsequent steps; if the parameter iterative update termination condition is met, determine the iteratively updated model parameters as the model parameters of the touchdown detection model.

[0043] In a specific implementation of the second aspect, the ground contact detection module may include:

[0044] A model interaction unit, configured to input the foot-end support reaction force into the ground contact detection model, and obtain the ground contact probability of the robot output by the ground contact detection model;

[0045] The first result determination unit is used to determine the ground contact probability as a ground contact detection result of the robot.

[0046] In a specific implementation of the second aspect, the ground contact detection module may include:

[0047] A model interaction unit, configured to input the foot-end support reaction force into the ground contact detection model, and obtain the ground contact probability of the robot output by the ground contact detection model;

[0048] A binary ground contact information determination unit, configured to determine the binary ground contact information of the robot according to the ground contact probability and a preset ground contact probability threshold; wherein the binary ground contact information includes ground contact or no ground contact;

[0049] The second result determination unit is configured to determine the binary ground contact information as a ground contact detection result of the robot.

[0050] In a specific implementation of the second aspect, the binary touchdown information determination unit may be specifically used to: determine that the binary touchdown information is touchdown when the touchdown probability is greater than or equal to the touchdown probability threshold; and determine that the binary touchdown information is no touchdown when the touchdown probability is less than the touchdown probability threshold.

[0051] In a specific implementation of the second aspect, the data information of the leg joint encoder includes the leg joint rotation angle, the leg joint rotation speed and the leg joint motor current;

[0052] The foot-end support reaction force determination module can be specifically used to: determine the robot's leg Jacobian matrix, leg joint torque vector, leg centrifugal force term, Coriolis force term and gravity term according to the leg joint angle, the leg joint rotation speed and the leg joint motor current; determine the robot's foot-end support reaction force according to the robot's leg Jacobian matrix, leg joint torque vector, leg centrifugal force term, Coriolis force term and gravity term.

[0053] A third aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of any one of the above-mentioned ground contact detection methods are implemented.

[0054] A fourth aspect of an embodiment of the present application provides a robot, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any one of the above-mentioned ground contact detection methods when executing the computer program.

[0055] A fifth aspect of an embodiment of the present application provides a computer program product. When the computer program product runs on a robot, the robot executes the steps of any one of the above-mentioned ground contact detection methods.

[0056] Compared with the prior art, the embodiments of the present application have the following beneficial effects: the embodiments of the present application obtain data information of the leg joint encoder of the robot; determine the foot-end support reaction force of the robot according to the data information of the leg joint encoder; use a preset touchdown detection model to process the foot-end support reaction force to obtain the touchdown detection result of the robot; wherein the touchdown detection model is a logistic regression classifier model for touchdown detection obtained by training based on a preset touchdown detection sample set, and each touchdown detection sample in the touchdown detection sample set includes a sample foot-end support reaction force and a corresponding touchdown detection result label. Through the embodiments of the present application, there is no need to configure additional sensors for the robot, which reduces the use cost of the robot, and will not be affected by sensor aging and damage, and can maintain a high accuracy rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0058] Figure 1 This is a flow chart of an embodiment of a ground contact detection method in an embodiment of the present application;

[0059] Figure 2 A schematic flowchart of the training process of the touchdown detection model;

[0060] Figure 3 A schematic diagram of the training process of the touchdown detection model;

[0061] Figure 4 This is a schematic diagram of the trained touchdown detection model;

[0062] Figure 5 A schematic diagram showing the comparison of the touchdown detection results;

[0063] Figure 6 This is a structural diagram of an embodiment of a ground contact detection device in an embodiment of the present application;

[0064] Figure 7 This is a schematic block diagram of a robot in an embodiment of the present application. DETAILED DESCRIPTION

[0065] In order to make the purpose, features, and advantages of the invention of this application more obvious and easy to understand, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the embodiments described below are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0066] It should be understood that when used in this specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0067] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0068] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0069] As used in this specification and the appended claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0070] In addition, in the description of the present application, the terms "first", "second", "third", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0071] In the process of controlling the robot, it is often necessary to perform ground detection on the robot, that is, to detect whether the foot of the robot is in contact with the ground. Existing ground detection methods mainly rely on the force sensor at the foot end, and judge whether it touches the ground by comparing the measured value of the force sensor with the set fixed threshold. Specifically, when the measured value of the force sensor is greater than the set fixed threshold, it is considered to be in contact with the ground, otherwise, it is considered to be not in contact with the ground. However, this method requires additional sensors to be configured for the robot, which increases the cost of using the robot, and these sensors are prone to aging and damage, resulting in a low accuracy rate of ground detection.

[0072] In view of this, embodiments of the present application provide a ground touchdown detection method, device, computer-readable storage medium, and robot to solve the problems of high cost and low accuracy of existing ground touchdown detection methods.

[0073] In an embodiment of the present application, the foot-end reaction force of the robot can be determined based on the data information of the leg joint encoder of the robot, and the foot-end reaction force can be processed using a preset ground touchdown detection model to obtain the ground touchdown detection result of the robot. There is no need to additionally configure sensors for the robot, which reduces the use cost of the robot. It will not be affected by aging and damage of the sensors, and can maintain a high accuracy rate.

[0074] The execution subject of the embodiments of the present application may be a robot, including but not limited to industrial robots, household service robots, commercial service robots and other various types of robots.

[0075] See also Figure 1 , an embodiment of a ground contact detection method in an embodiment of the present application may include:

[0076] Step S101, obtaining data information of the robot's leg joint encoder.

[0077] The data information of the leg joint encoder may include but is not limited to the leg joint rotation angle, leg joint rotation speed and leg joint motor current.

[0078] Step S102: determining the foot-end support reaction force of the robot according to the data information of the leg joint encoder.

[0079] In the embodiment of the present application, the leg Jacobian matrix, leg joint torque vector, leg centrifugal force term, Coriolis force term and gravity term of the robot can be determined according to the leg joint angle, leg joint rotation speed and leg joint motor current, and the foot end support reaction force (GRF) of the robot can be determined according to the leg Jacobian matrix, leg joint torque vector, leg centrifugal force term, Coriolis force term and gravity term of the robot, as shown in the following formula:

[0080]

[0081] Among them, q l is the leg joint rotation angle, is the leg joint rotation speed, Jl(ql) is the leg Jacobian matrix, which can be calculated according to the leg joint rotation angle, J l T (q l ) is the transpose of the Jacobian matrix of the leg, are the leg centrifugal force, Coriolis force and gravity terms, which can be calculated based on the leg joint rotation angle and leg joint rotation speed, τ l is the leg joint torque vector, which is approximately linearly related to the leg joint motor current and can be calculated based on the leg joint motor current. f is the robot’s foot end support reaction force, and f l,x 、f l,y and f l,z are the components of the foot end support reaction force on the x-axis, y-axis and z-axis respectively.

[0082] Step S103: Use a preset ground contact detection model to process the foot end support reaction force to obtain a ground contact detection result of the robot.

[0083] In the embodiment of the present application, the corresponding measurement coefficient can be determined according to the foot end support reaction force, as shown in the following formula:

[0084]

[0085] Among them, μ f is a measurement coefficient used to measure the reliability of the foot contact state. When the foot starts to slide, the measurement coefficient is equal to the static friction coefficient μ s .

[0086] Because the friction coefficient of different surfaces is different, μ s The value of is unknown, but as long as μ f <μ s In the case of f The smaller it is, the more firmly it touches the ground. For the sake of numerical stability and calculation simplification, only the component of the foot-end support reaction force on the z-axis can be considered, while other components are ignored. The component of the foot-end support reaction force on the z-axis is compared with a specific threshold. When the component of the foot-end support reaction force on the z-axis is greater than the specific threshold, it is determined that the robot's foot is in contact with the ground. Otherwise, it is determined that the robot's foot is not in contact with the ground.

[0087] Based on this understanding, the embodiment of the present application can use a preset ground contact detection model to process the foot end support reaction force, thereby obtaining the ground contact detection result of the robot. The ground contact detection model is a logistic regression classifier (LRC) model for ground contact detection obtained by training based on a preset ground contact detection sample set, as shown in the following formula:

[0088]

[0089] Among them, T l ∈{0,1} is a set of foot contact events, Tl=1 indicates foot contact, Tl=0 indicates no foot contact, β is a model parameter of the contact detection model, which may include a first model parameter β1 and a second model parameter β2, P(T l =1|f l,z β) is the component of the foot end support reaction force on the z axis f l,z The touchdown probability is determined by the model parameter β of the touchdown detection model, which is hereinafter simplified as P.

[0090] In the embodiment of the present application, the touchdown detection model may be trained in advance to determine the model parameters of the touchdown detection model. The training process of the touchdown detection model may include the following steps: Figure 2 Steps shown:

[0091] Step S201: Acquire a touchdown detection sample set.

[0092] Each touchdown detection sample in the touchdown detection sample set may include a sample foot end support reaction force and a corresponding touchdown detection result label. Here, the touchdown detection sample set may be recorded as Where, k is the serial number of the touchdown detection sample, 1≤k≤n, n is the number of touchdown detection samples in the touchdown detection sample set, (f l,z,k ,T k ) is the kth touchdown detection sample in the touchdown detection sample set, f l,z,k is the component of the sample foot end support reaction force on the z-axis in the kth touchdown detection sample, T k is the touchdown detection result label in the kth touchdown detection sample. When the value is 1, it means the foot touches the ground; when the value is 0, it means the foot does not touch the ground.

[0093] Step S202: Determine a log-likelihood function corresponding to the touchdown detection sample set.

[0094] In the embodiment of the present application, a likelihood function (LF) as shown in the following formula may be constructed based on the touchdown detection sample set:

[0095]

[0096] Taking the natural logarithm of the above likelihood function, we can get the log-likelihood function (LLF) as shown below:

[0097]

[0098] Where fk(Tk) is T k The probability of occurrence, that is, the touchdown detection result label in the kth touchdown detection sample is T k The probability, P k is the component f of the sample foot end support reaction force on the z-axis based on the kth touchdown detection sample l,z,k The touchdown probability f(T) = f(T1, T2, …, Tn) is determined by the model parameter β of the touchdown detection model, which is the probability of T occurring, that is, T1, T2, …, Tn. n The joint probability of occurrence, where each T k are all independent and have the same logical density function, so the joint density function can be written as the product of each density function.

[0099] Step S203: with the goal of maximizing the log-likelihood function, estimate the model parameters of the touchdown detection model to obtain the model parameters of the touchdown detection model.

[0100] In the embodiment of the present application, the model parameters of the touchdown detection model may be estimated by Maximum Likelihood Estimation (MLE), that is, by maximizing the probability of the observed T, the unknown model parameters may be obtained.

[0101] Specifically, the partial derivative result of the log-likelihood function with respect to the model parameters of the ground touchdown detection model may be obtained, and the adjustment amount of the model parameters of the ground touchdown detection model may be determined according to the partial derivative result and a preset learning rate, and the model parameters of the ground touchdown detection model may be iteratively updated according to the adjustment amount to obtain the iteratively updated model parameters, as shown in the following formula:

[0102]

[0103] Wherein, h is the learning rate, and its specific value can be flexibly set according to the actual situation, and the embodiment of the present application does not specifically limit it. Through such a gradient descent method, the model parameter β can be gradually adjusted to maximize the log-likelihood function.

[0104] After each parameter iteration update, it can be determined whether the preset parameter iteration update termination condition is met. The parameter iteration update termination condition can be flexibly set according to the actual situation. For example, the number of iterations may be greater than a preset iteration number threshold, or the adjustment amount of the model parameter may be less than a preset adjustment amount threshold, etc. The embodiments of the present application do not make specific limitations on this.

[0105] If the parameter iterative update termination condition is not met, the next parameter iterative update can be continued, that is, the step of calculating the partial derivative of the log-likelihood function with respect to the model parameters of the ground touch detection model and subsequent steps are returned until the parameter iterative update termination condition is met. If the parameter iterative update termination condition is met, the iterative update of the model parameters can be terminated, and the model parameters after the last iterative update are determined as the final model parameters of the ground touch detection model.

[0106] Figure 3 The figure shows a schematic diagram of the training process of the ground touchdown detection model, wherein the horizontal axis is the number of iterations, and the vertical axis is the model error of the ground touchdown detection model. As shown in the figure, as the number of iterations increases, the model error of the ground touchdown detection model continues to decrease until the iteration is terminated.

[0107] Figure 4 The figure shows a schematic diagram of the final trained ground contact detection model, where the horizontal axis is the component of the foot end support reaction force on the z-axis, in Newton (N), and the vertical axis is the ground contact probability P (T l =1|f l,z ; β), as shown in the figure, the ground contact detection model can map the foot end support reaction force to the interval (0,1) to characterize the probability of the robot touching the ground.

[0108] After the ground detection model is trained, the ground detection model can be used to perform actual ground detection, that is, the foot-end support reaction force is input into the ground detection model, and the ground touch probability of the robot output by the ground detection model is obtained.

[0109] In a specific implementation of the embodiment of the present application, the ground contact probability can be directly determined as the ground contact detection result of the robot.

[0110] In another specific implementation of the embodiment of the present application, the binary ground touching information of the robot can be determined according to the ground touching probability and the preset ground touching probability threshold. Among them, the specific value of the ground touching probability threshold can be flexibly set according to the actual situation. For example, it can be set to 0.5 or other values, and the embodiment of the present application does not specifically limit it. The binary ground touching information may include touching the ground (recorded as 1) or not touching the ground (recorded as 0). When the ground touching probability is greater than or equal to the ground touching probability threshold, the binary ground touching information can be determined as touching the ground. On the contrary, when the ground touching probability is less than the ground touching probability threshold, the binary ground touching information can be determined as not touching the ground.

[0111] Figure 5 The figure shows a comparison diagram of the ground contact detection results, wherein the horizontal axis is the time axis, the unit is seconds (s), the vertical axis of the lower figure is the component of the foot end support reaction force on the z-axis, the unit is Newton (N), and the vertical axis of the upper figure is the ground contact detection result. The figure shows four different ground contact detection results, wherein result 1 is the true value, result 2 is the ground contact probability output by the ground contact detection model in the embodiment of the present application, result 3 is the binary ground contact information in the embodiment of the present application, and result 4 is the ground contact detection result obtained by the prior art. It can be seen that the ground contact detection result obtained in the embodiment of the present application has a high accuracy rate.

[0112] To summarize, the embodiments of the present application can determine the foot-end support reaction force of the robot based on the data information of the leg joint encoder of the robot, and use a preset ground touchdown detection model to process the foot-end support reaction force, thereby obtaining the ground touchdown detection result of the robot. There is no need to additionally configure sensors for the robot, thereby reducing the use cost of the robot, and it will not be affected by sensor aging and damage, and can maintain a high accuracy rate.

[0113] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0114] Corresponding to a ground contact detection method described in the above embodiment, Figure 6 A structural diagram of an embodiment of a ground contact detection device provided in an embodiment of the present application is shown.

[0115] In this embodiment, a ground contact detection device may include:

[0116] The data information acquisition module 601 is used to acquire the data information of the leg joint encoder of the robot;

[0117] A foot end support reaction force determination module 602, used to determine the foot end support reaction force of the robot according to the data information of the leg joint encoder;

[0118] A ground contact detection module 603 is used to process the foot end support reaction force using a preset ground contact detection model to obtain a ground contact detection result of the robot;

[0119] The touchdown detection model is a logistic regression classifier model for touchdown detection obtained by training based on a preset touchdown detection sample set, and each touchdown detection sample in the touchdown detection sample set includes a sample foot-end reaction force and a corresponding touchdown detection result label.

[0120] In a specific implementation of the embodiment of the present application, the ground contact detection device may further include:

[0121] A touchdown detection sample set acquisition module, used to acquire the touchdown detection sample set;

[0122] A log-likelihood function determination module, configured to determine a log-likelihood function corresponding to the touchdown detection sample set;

[0123] The model parameter estimation module is used to estimate the model parameters of the touchdown detection model with the goal of maximizing the log-likelihood function to obtain the model parameters of the touchdown detection model.

[0124] In a specific implementation of the embodiment of the present application, the model parameter estimation module can be specifically used to: obtain partial derivative results of the log-likelihood function with respect to the model parameters of the touchdown detection model; determine the adjustment amount of the model parameters of the touchdown detection model according to the partial derivative results and a preset learning rate; iteratively update the model parameters of the touchdown detection model according to the adjustment amount to obtain the iteratively updated model parameters; if the preset parameter iterative update termination condition is not met, return to execute the step of obtaining the partial derivative results of the log-likelihood function with respect to the model parameters of the touchdown detection model and its subsequent steps; if the parameter iterative update termination condition is met, determine the iteratively updated model parameters as the model parameters of the touchdown detection model.

[0125] In a specific implementation of the embodiment of the present application, the ground contact detection module may include:

[0126] A model interaction unit, configured to input the foot-end support reaction force into the ground contact detection model, and obtain the ground contact probability of the robot output by the ground contact detection model;

[0127] The first result determination unit is used to determine the ground contact probability as a ground contact detection result of the robot.

[0128] In a specific implementation of the embodiment of the present application, the ground contact detection module may include:

[0129] A model interaction unit, configured to input the foot-end support reaction force into the ground contact detection model, and obtain the ground contact probability of the robot output by the ground contact detection model;

[0130] A binary ground contact information determination unit, configured to determine the binary ground contact information of the robot according to the ground contact probability and a preset ground contact probability threshold; wherein the binary ground contact information includes ground contact or no ground contact;

[0131] The second result determination unit is configured to determine the binary ground contact information as a ground contact detection result of the robot.

[0132] In a specific implementation of an embodiment of the present application, the binary touchdown information determination unit may be specifically used to: determine that the binary touchdown information is touchdown when the touchdown probability is greater than or equal to the touchdown probability threshold; and determine that the binary touchdown information is no touchdown when the touchdown probability is less than the touchdown probability threshold.

[0133] In a specific implementation of the embodiment of the present application, the data information of the leg joint encoder includes the leg joint angle, the leg joint rotation speed and the leg joint motor current;

[0134] The foot-end support reaction force determination module can be specifically used to: determine the robot's leg Jacobian matrix, leg joint torque vector, leg centrifugal force term, Coriolis force term and gravity term according to the leg joint angle, the leg joint rotation speed and the leg joint motor current; determine the robot's foot-end support reaction force according to the robot's leg Jacobian matrix, leg joint torque vector, leg centrifugal force term, Coriolis force term and gravity term.

[0135] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices, modules and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0136] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0137] Figure 7 A schematic block diagram of a robot provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0138] like Figure 7 As shown, the robot 7 of this embodiment includes: a processor 70, a memory 71, and a computer program 72 stored in the memory 71 and executable on the processor 70. When the processor 70 executes the computer program 72, the steps in the above-mentioned various ground contact detection method embodiments are implemented, for example Figure 1 Alternatively, when the processor 70 executes the computer program 72, the functions of each module / unit in the above-mentioned device embodiments are realized, for example Figure 6 The functions of modules 601 to 603 are shown.

[0139] Exemplarily, the computer program 72 may be divided into one or more modules / units, which are stored in the memory 71 and executed by the processor 70 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program 72 in the robot 7.

[0140] Those skilled in the art will understand that Figure 7 It is only an example of the robot 7 and does not constitute a limitation of the robot 7. The robot 7 may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the robot 7 may also include input and output devices, network access devices, buses, etc.

[0141] The processor 70 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0142] The memory 71 may be an internal storage unit of the robot 7, such as a hard disk or memory of the robot 7. The memory 71 may also be an external storage device of the robot 7, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the robot 7. Further, the memory 71 may include both an internal storage unit and an external storage device of the robot 7. The memory 71 is used to store the computer program and other programs and data required by the robot 7. The memory 71 may also be used to temporarily store data that has been output or is to be output.

[0143] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0144] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0145] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0146] In the embodiments provided in the present application, it should be understood that the disclosed devices / robots and methods can be implemented in other ways. For example, the device / robot embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as 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 mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0147] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0148] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0149] If the integrated module / unit 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 present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable storage medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable storage media do not include electric carrier signals and telecommunication signals.

[0150] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for detecting a ground contact, characterized in that: include: Get the data information of the robot's leg joint encoder; Determine the foot end support reaction force of the robot according to the data information of the leg joint encoder; Using a preset ground contact detection model to process the foot end support reaction force to obtain a ground contact detection result of the robot; The touchdown detection model is a logistic regression classifier model for touchdown detection obtained by training based on a preset touchdown detection sample set, and each touchdown detection sample in the touchdown detection sample set includes a sample foot-end reaction force and a corresponding touchdown detection result label.

2. The ground contact detection method according to claim 1, characterized in that: Before using a preset ground contact detection model to process the foot end support reaction force to obtain a ground contact detection result of the robot, the method further includes: Acquire the touchdown detection sample set; determining a log-likelihood function corresponding to the touchdown detection sample set; With the goal of maximizing the log-likelihood function, model parameters of the touchdown detection model are estimated to obtain model parameters of the touchdown detection model.

3. The ground contact detection method according to claim 2, characterized in that: The step of estimating model parameters of the touchdown detection model with the goal of maximizing the log-likelihood function to obtain the model parameters of the touchdown detection model includes: Calculating partial derivatives of the log-likelihood function with respect to model parameters of the touchdown detection model; Determining an adjustment amount of a model parameter of the ground contact detection model according to the partial derivative result and a preset learning rate; Iteratively updating the model parameters of the ground contact detection model according to the adjustment amount to obtain iteratively updated model parameters; If the preset parameter iteration update termination condition is not satisfied, returning to the step of obtaining the partial derivative of the log-likelihood function with respect to the model parameters of the ground contact detection model and subsequent steps; If the parameter iterative updating termination condition is satisfied, the iteratively updated model parameters are determined as the model parameters of the ground contact detection model.

4. The ground contact detection method according to claim 1, characterized in that: The using a preset ground contact detection model to process the foot end support reaction force to obtain a ground contact detection result of the robot includes: Inputting the foot-end support reaction force into the ground contact detection model, and obtaining the ground contact probability of the robot output by the ground contact detection model; The ground contact probability is determined as a ground contact detection result of the robot.

5. The ground contact detection method according to claim 1, characterized in that: The using a preset ground contact detection model to process the foot end support reaction force to obtain a ground contact detection result of the robot includes: Inputting the foot-end support reaction force into the ground contact detection model, and obtaining the ground contact probability of the robot output by the ground contact detection model; Determining binary ground contact information of the robot according to the ground contact probability and a preset ground contact probability threshold; wherein the binary ground contact information includes ground contact or no ground contact; The binary ground contact information is determined as a ground contact detection result of the robot.

6. The ground contact detection method according to claim 5, characterized in that: The determining, according to the ground contact probability and a preset ground contact probability threshold, binary ground contact information of the robot includes: When the touchdown probability is greater than or equal to the touchdown probability threshold, determining that the binary touchdown information is a touchdown; When the ground contact probability is less than the ground contact probability threshold, the binary ground contact information is determined as no ground contact.

7. The ground contact detection method according to any one of claims 1 to 6, characterized in that: The data information of the leg joint encoder includes the leg joint rotation angle, the leg joint rotation speed and the leg joint motor current; The step of determining the foot end support reaction force of the robot according to the data information of the leg joint encoder comprises: According to the leg joint rotation angle, the leg joint rotation speed and the leg joint motor current, respectively determine the leg Jacobian matrix, leg joint torque vector, leg centrifugal force term, Coriolis force term and gravity term of the robot; The foot-end support reaction force of the robot is determined according to the Jacobian matrix of the robot's legs, the leg joint torque vector, the leg centrifugal force term, the Coriolis force term and the gravity term.

8. A ground contact detection device, characterized in that: include: A data information acquisition module is used to acquire data information of the robot's leg joint encoders; A foot end support reaction force determination module, used to determine the foot end support reaction force of the robot according to the data information of the leg joint encoder; A ground contact detection module, used to process the foot end support reaction force using a preset ground contact detection model to obtain a ground contact detection result of the robot; The touchdown detection model is a logistic regression classifier model for touchdown detection obtained by training based on a preset touchdown detection sample set, and each touchdown detection sample in the touchdown detection sample set includes a sample foot-end reaction force and a corresponding touchdown detection result label.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the ground contact detection method according to any one of claims 1 to 7 are implemented.

10. A robot comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the ground contact detection method according to any one of claims 1 to 7 are implemented.

Images