Humanoid robot motion efficiency evaluation method and system, storage medium and equipment

Abstract

The invention discloses a humanoid robot motion efficiency evaluation method and system, a storage medium and equipment, belongs to the technical field of robot evaluation, and aims to solve the problems of tedious calculation and inaccurate evaluation in existing robot motion efficiency evaluation. According to the method, firstly, the reference dynamic power DPoS index Pd is calculated according to the vector diameter length from the ith joint connecting rod to the DH parameter coordinate origin o, the rotation angular speed of the ith joint connecting rod and the rotational inertia of the ith joint connecting rod relative to a rotating shaft at the coordinate origin, and then the ratio of the reference dynamic power DPoS index Pd to the actual power of the humanoid robot serves as the reference dynamic efficiency; and evaluating the motion efficiency of the humanoid robot according to the reference dynamic efficiency.

Description

Technical Field

[0001] The present invention belongs to the technical field of robot evaluation, and in particular relates to a robot motion efficiency evaluation method, system, storage medium and device. Background Art

[0002] In the past, humanoid robots, as images in film and television works, gave people unlimited imagination. In today's world with rapid development of science and technology, this imagination is gradually becoming a reality. In today's world, countries are actively conducting research on humanoid robot technology. At present, humanoid robot technology has achieved many gratifying research results, but there are still many problems in the field of humanoid robots that need to be solved urgently:

[0003] Humanoid robots are highly adaptable to human working environments due to their similarity to human appearance and structure. Therefore, humanoid robots have great potential in reducing the workload of humans. This puts forward requirements for the anthropomorphism, environmental adaptability, work reliability and work sustainability of humanoid robots. In order to achieve the popularization of humanoid robots, their endurance is an important evaluation indicator, but currently there is little attention paid to the efficiency of humanoid robot systems, and there is a lack of appropriate evaluation methods. The more commonly used evaluation indicators are mainly to calculate the energy efficiency of each joint separately and then sum them up, or to calculate parameters for specific tasks such as movement: transportation cost CoT for evaluation and comparison. These evaluation methods have problems such as complex operation, cumbersome calculation, and inaccurate evaluation. Summary of the invention

[0004] The present invention aims to solve the problems of complicated calculation and inaccurate evaluation in the existing robot motion efficiency evaluation.

[0005] A method for evaluating the motion efficiency of a humanoid robot, comprising:

[0006] First, calculate the reference dynamic power DPoS index P d :

[0007]

[0008] Among them, m is the mass of the entire robot, g is the acceleration of gravity, v is the velocity of the center of mass, and r is the velocity of the center of mass. io is the radial length from the ith joint link to the origin o of the DH parameter coordinates, ω i is the rotational angular velocity of the i-th joint link, I io is the moment of inertia of the i-th joint link relative to the rotation axis at the coordinate origin;

[0009] Then according to P A and P d Calculate the reference kinetic efficiency K EoS:

[0010]

[0011] Among them, P A The actual power of a humanoid robot;

[0012] Evaluation of the motion efficiency of humanoid robots based on the reference motion efficiency KEoS.

[0013] Furthermore, the actual power P of the humanoid robot A The input power obtained by the battery management system or power monitoring system is obtained, or the real-time voltage U and real-time output current I of the power supply are obtained, and the P A =UI calculates the actual power of the entire humanoid robot system.

[0014] Furthermore, the moment of inertia of the i-th joint link relative to the rotation axis at the coordinate origin is io By using the parallel axis theorem we obtain:

[0015]

[0016] Among them, I main is the moment of inertia of the ith joint link relative to its own rotation axis, l io is the distance from the i-th joint rotation axis to the origin o of the DH parameter coordinates; m i is the mass of the i-th connecting rod.

[0017] Furthermore, when evaluating the motion efficiency of a humanoid robot based on the reference motion efficiency KEoS, the humanoid robot needs to meet the following constraints:

[0018]

[0019] Among them, Δzoc and Δxoc are the vertical deviation and horizontal deviation between the center of mass position and the origin of the DH parameter coordinate, and L is the leg length of the humanoid robot.

[0020] A humanoid robot motion efficiency evaluation system, comprising:

[0021] DPoS indicator calculation unit: calculate the reference power DPoS indicator P d :

[0022]

[0023] Among them, m is the mass of the entire robot, g is the acceleration of gravity, v is the velocity of the center of mass, and r is the velocity of the center of mass. io is the radial length from the ith joint link to the origin o of the DH parameter coordinates, ω i is the rotational angular velocity of the i-th joint link, I iois the moment of inertia of the i-th joint link relative to the rotation axis at the coordinate origin;

[0024] Reference dynamic efficiency calculation unit: According to P A and P d Calculate the reference kinetic efficiency KEoS:

[0025]

[0026] Among them, P A The actual power of a humanoid robot;

[0027] Motion efficiency evaluation unit: evaluates the motion efficiency of the humanoid robot based on the reference motion efficiency KEoS.

[0028] Furthermore, the system further comprises an actual power acquisition unit, which is used to acquire or calculate the actual power P of the humanoid robot. A ; The actual power p of the humanoid robot A The input power is obtained through the battery management system or power monitoring system, or the real-time voltage u and real-time output current i of the power supply are obtained, according to P A =UI calculates the actual power of the entire humanoid robot system.

[0029] Furthermore, the moment of inertia of the i-th joint link relative to the rotation axis at the coordinate origin is io By using the parallel axis theorem we obtain:

[0030]

[0031] Among them, i main is the moment of inertia of the ith joint link relative to its own rotation axis, l io is the distance from the i-th joint rotation axis to the DH parameter coordinate origin o; m i is the mass of the i-th connecting rod.

[0032] Furthermore, when evaluating the motion efficiency of a humanoid robot based on the reference motion efficiency KEoS, the humanoid robot needs to meet the following constraints:

[0033]

[0034] Among them, Δzoc and Δxoc are the vertical deviation and horizontal deviation between the center of mass position and the origin of the DH parameter coordinate, and L is the leg length of the humanoid robot.

[0035] A computer storage medium stores at least one instruction, and the at least one instruction is loaded and executed by a processor to execute a humanoid robot motion efficiency evaluation system.

[0036] A humanoid robot motion efficiency evaluation device comprises a processor and a memory, wherein the memory stores at least one instruction, and the at least one instruction is loaded and executed by the processor to execute the humanoid robot motion efficiency evaluation system.

[0037] Compared with monitoring experimental data of each joint separately, calculating efficiency and then calculating the sum, the present invention is more concise and fast, and ensures the accuracy of motion efficiency calculation of the whole system. The calculation of the present invention is simple and fast, and can monitor and calculate key parameter values ​​in real time, thereby realizing real-time motion efficiency evaluation. The index reference motion efficiency KEoS proposed by the present invention can evaluate the motion efficiency of humanoid robots in real time when performing various tasks, and has universal applicability.

[0038] The new indicator used in the present invention can more accurately evaluate the motion efficiency of the humanoid robot system compared to the commonly used energy consumption indicator transportation cost CoT, especially when the center of mass movement speed of the entire humanoid robot system is very small, but the limbs have large movements, the transportation cost CoT cannot truly reflect the motion efficiency of the humanoid robot. The present invention can still accurately evaluate the motion efficiency of the humanoid robot system when the center of mass movement speed is very small but the limbs have large movements. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 is a flow chart of the evaluation method of the present invention;

[0040] Figure 2 is a schematic diagram of a simulation of a humanoid robot walking test according to the evaluation method of the present invention;

[0041] Figure 3 is a graph of the KEoS of a humanoid robot calculated by the evaluation method of the present invention; Figure 4 This is a comparison chart of 1 / CoT and KEoS calculated when the humanoid robot designed by the present invention is subjected to a walking test. DETAILED DESCRIPTION

[0042] The purpose of the present invention is to solve the problem that there is currently a lack of simple, fast and accurate evaluation methods for the motion efficiency of humanoid robots. The present invention can first divide the motion of humanoid robots into two categories: whole machine motion and fine work of the upper body. Whole machine motion refers to the motion of the entire humanoid robot. This kind of motion generally has a large amplitude and a more drastic change in the center of mass position, such as walking, running, jumping, etc.; the fine work of the upper body refers to the lower body of the humanoid robot standing still, acting as a base. This kind of motion generally has a small amplitude, a high probability of requiring the participation of the hands, and a small change in the center of mass position, such as playing the piano, screwing screws, etc. The present invention proposes a reference dynamic efficiency (KEoS) for evaluation. During the motion of the humanoid robot, the reference dynamic efficiency can be calculated in real time to evaluate the motion efficiency of the humanoid robot at that moment. The determination process of KEoS requires the use of another parameter indicator: reference dynamic power (DPoS), which can evaluate the energy power consumed by the humanoid robot due to motion at that moment.

[0043] In order to evaluate the design quality of the system, it is necessary to calculate the reference dynamic power of the robot under the same motion task and calculate the average value for evaluation and comparison. The present invention is described below in conjunction with specific embodiments. Specific implementation method one:

[0045] In order to make a more comprehensive evaluation, more representative motion tasks are selected for evaluation. If you want to evaluate the design results of motion efficiency of any two humanoid robots, you need to calculate the size of their KEoS based on the control implementation task for comparison. Since the target tasks performed by humanoid robots can be divided into two categories: whole-body mobility tasks involving hands and feet, and fine work performed by the upper body. The reason for choosing walking and grabbing heavy objects is that first of all, the two tasks are typical tasks in the two categories: the main function of the whole-body movement of the human body is to move the human body, and the main way for the human body to move is walking; the fine work of the upper body is also mainly for people to use their hands to change the position and posture of small objects; on the other hand, the research on these two tasks in the field of humanoid robots is relatively mature, and there is a lot of knowledge accumulation, so it can be more convenient to implement and explain you, so this embodiment lists typical tasks: walking, grabbing heavy objects and lifting them, and this embodiment uses this task as an example for explanation. In fact, the present invention can also be applied to other tasks.

[0046] The testing and calculation process of the entire system is as follows:

[0047] The humanoid robot performs movements according to the designed tasks, and pays attention to using the same control method in the process, which is carried out in real time during the movement:

[0048] 1. Calculate the actual power P A:Use the battery management system BMS or other power monitoring system to obtain the input power of the entire humanoid robot system in real time, or obtain the real-time voltage U and real-time output current I of the power supply, according to the formula: P A =UI calculates the actual power of the entire humanoid robot system.

[0049] 2. Calculate the reference power DPoS index P d :

[0050]

[0051] Among them, m is the mass of the entire robot, g is the acceleration of gravity, v is the velocity of the center of mass, and r is the velocity of the center of mass. io is the radial length from the ith joint link to the origin o of the DH parameter coordinates, ω i is the angular velocity of the i-th joint link (the angular velocity of the i-th link relative to its own axis of rotation), I io is the moment of inertia of the i-th joint link relative to the rotation axis at the coordinate origin;

[0052] I io It can be obtained by the parallel axis theorem:

[0053]

[0054] Among them, I main is the moment of inertia of the ith joint link relative to its own rotation axis, l io is the distance from the i-th joint rotation axis to the DH parameter coordinate origin o; m i is the mass of the i-th connecting rod.

[0055] The reference kinetic power is a simplified calculation form of the kinetic energy of the entire system. Considering that the center of mass of a humanoid robot is generally close to the hip, and the DH parameter coordinate origin of the entire humanoid robot is generally set at the hip joint, the kinetic energy of the rigid system is determined:

[0056]

[0057] Among them, E represents the total kinetic energy of the rigid system. The entire rigid system is composed of many sub-rigid bodies. For the humanoid robot system, the entire robot can be regarded as a complex rigid system, and each connecting rod in it can be regarded as a sub-rigid body. m is the mass of the entire robot, v is the speed of the center of mass of the entire robot, Ii is the moment of inertia of each sub-rigid body relative to the center of mass, ω io is the angular velocity of each sub-rigid body relative to the center of mass, It is the relative kinetic energy of the rigid system. In the humanoid robot system, it can be approximated as the kinetic energy relative to the origin o of the DH parameter coordinate system, and then simplified by analogy with the form of transportation cost CoT to obtain the reference kinetic power DPoS.

[0058] Therefore, this evaluation method needs to introduce restrictions when used:

[0059]

[0060] Among them, Δzoc and Δxoc are the vertical deviation and horizontal deviation between the center of mass position and the origin of the DH parameter coordinate, and L is the leg length of the humanoid robot.

[0061] P d The parameter v in the expression is the input quantity during planning, ω i It can be obtained by real-time monitoring of the position sensors of each joint. io and l io It can be calculated based on kinematic parameters (these two parameters can be obtained by simply transforming the Jacobian matrix based on the actual joint motion angle of the robot and the robot kinematics). Therefore, the parameters in the entire DPoS can be conveniently calculated in real time. At the same time, due to its high similarity with the system kinetic energy derivative, it can be guaranteed to reasonably represent the instantaneous kinetic efficiency of the system.

[0062] It should be noted that the starting point of the present invention is to start from the perspective of the entire humanoid robot, which is a rigid system. First, the most accurate expression of its motion efficiency is written, which is the ratio of the power of real-time kinetic energy to the real-time input power. The kinetic energy of the rigid system can be written as the kinetic energy of the center of mass relative to the center of mass of other rigid bodies. Since the center of mass position of the humanoid robot changes relative to the whole during the movement, it is difficult to calculate. In addition, the result of the design of the humanoid robot is generally that the center of mass is located at the trunk or hip joint. This is a common experience. The present invention makes an assumption on this formula and proposes a preliminary Simplify, that is, coincide the position of the center of mass with the position of the origin o of the DH coordinate system, so that the relative kinetic energy of the second part can be calculated more simply; and when the kinetic energy is differentiated to obtain power, the present invention can find that there will be an additional acceleration term in the formula, and for each sub-rigid body, it is extremely difficult to calculate the relative acceleration, so the present invention further simplifies this formula, and is inspired by the use of gravitational acceleration g in the CoT definition to complete the representation of the acceleration dimension, the present invention uses expressions such as g and g / rio, so that all parameters in the formula of the present invention can be more conveniently obtained.

[0063] The new indicator used in this invention is compared with the commonly used energy consumption indicator transportation cost The motion efficiency of the humanoid robot system can be evaluated more accurately, especially when the center of mass motion speed of the entire humanoid robot system is very small, but there are large movements of the limbs. The transportation cost CoT is large and cannot truly reflect the motion efficiency of the humanoid robot.

[0064] 3. Calculate the reference kinetic efficiency KEoS:

[0065]

[0066] Among them, P A is the actual power.

[0067] The reference motion efficiency is calculated in real time to evaluate the motion efficiency of the humanoid robot at that moment.

[0068] The advantage of using this evaluation method is that the calculation process is relatively simple, it can be calculated simultaneously with the movement of the system, and it can be calculated for all movements of the system, which is universal. On the other hand, because the formula is simplified from the kinetic energy of the system, the calculation result is also relatively accurate and standardized.

[0069] The entire evaluation method calculation and testing process is as follows Figure 1 As shown in the figure, a typical humanoid robot movement is selected, such as moving forward at a constant speed of 0.2 m / s for 10 m, and then lifting an apple on the table by 20 cm. The simulation diagram of the walking process is shown in the figure. Figure 2 As shown in the figure, during the whole motion process, the actual power of the system is calculated by the power management system, and the fixed parameters such as mgv and I are calculated according to the host computer planning and the robot model. At the same time, the joint motion parameters are calculated in real time according to the motion monitoring system, and then the remaining parameters required for calculating the system dynamic power are obtained. Finally, the system dynamic efficiency is calculated by ratioing the two. The system dynamic efficiency curve is shown in Figure 3 As shown in Figure 2, the motion efficiency of the humanoid robot system can be evaluated in real time based on the system dynamic efficiency curve.

[0070] Figure 4 This is a comparison chart of 1 / CoT (the reason for selecting 1 / CoT is that it can ensure that it has the same polarity as KEoS, that is, the larger this number is, the higher the robot's movement efficiency is) and KEoS when the designed humanoid robot is walked. Figure 4 It can be seen that there is an obvious change in the values ​​of the two in the red frame area. This area is the position where the humanoid robot adjusts its posture and steps forward according to the ZMP algorithm. At this time, the center of mass speed can be approximately ignored, so 1 / CoT is close to 0, while KEoS has an actual value. In reality, the efficiency of the robot is obviously not 0 at this time. Therefore, it can be seen that the description effect of KEoS of the present invention is obviously better. Specific implementation method 2:

[0072] This embodiment is a humanoid robot motion efficiency evaluation system, comprising:

[0073] Actual power acquisition unit: acquire or calculate the actual power P of the humanoid robot A ; The actual power P of the humanoid robot AThe input power is obtained through the battery management system or power monitoring system, or the real-time voltage U and real-time output current I of the power supply are obtained, according to P A =UI calculates the actual power of the entire humanoid robot system.

[0074] DPoS indicator calculation unit: calculate the reference power DPoS indicator P d :

[0075]

[0076] Among them, m is the mass of the entire robot, g is the acceleration of gravity, v is the velocity of the center of mass, and r is the velocity of the center of mass. io is the radial length from the ith joint link to the origin o of the DH parameter coordinates, ω i is the angular velocity of the i-th joint, I io is the moment of inertia of the i-th joint link relative to the rotation axis at the coordinate origin.

[0077] The moment of inertia of the i-th joint link relative to the rotation axis at the coordinate origin is I io By using the parallel axis theorem we obtain:

[0078]

[0079] Among them, I maqin is the moment of inertia of the ith joint link relative to its own rotation axis, l io is the distance from the i-th joint rotation axis to the DH parameter coordinate origin o; m i is the mass of the i-th connecting rod.

[0080] Reference dynamic efficiency calculation unit: According to P A and P d Calculate the reference kinetic efficiency KEoS:

[0081]

[0082] Among them, P A The actual power of a humanoid robot.

[0083] Motion efficiency evaluation unit: evaluates the motion efficiency of the humanoid robot based on the reference motion efficiency KEoS.

[0084] When evaluating the motion efficiency of a humanoid robot based on the reference motion efficiency KEoS, the humanoid robot needs to meet the following constraints:

[0085]

[0086] Among them, Δzoc and Δxoc are the vertical deviation and horizontal deviation between the center of mass position and the origin of the DH parameter coordinate, and L is the leg length of the humanoid robot. Specific implementation method three:

[0088] This embodiment is a computer storage medium, in which at least one instruction is stored. The at least one instruction is loaded by a processor and runs the humanoid robot motion efficiency evaluation system.

[0089] It should be understood that the instructions include computer program products, software or computerized methods corresponding to any method described in the present invention; the instructions can be used to program a computer system, or other electronic device. Computer storage media may include readable media on which instructions are stored, which may include but are not limited to magnetic storage media, optical storage media; magneto-optical storage media include read-only memory ROM, random access memory RAM, erasable programmable memory (e.g., EPROM and EEPROM) and flash memory layers, or other types of media suitable for storing electronic instructions. Specific implementation method four:

[0091] This embodiment is a humanoid robot motion efficiency evaluation device, the device includes a processor and a memory. It should be understood that including any device including a processor and a memory described in the present invention, the device may also include other units and modules that perform display, interaction, processing, control, etc. and other functions through signals or instructions;

[0092] The memory stores at least one instruction, and the at least one instruction is loaded and executed by the processor to execute the humanoid robot motion efficiency evaluation system.

[0093] Those skilled in the art will appreciate that at least one instruction stored is a computer program product corresponding to the method or system. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The scheme in the embodiment of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0094] The present application is described with reference to the flowcharts and / or block diagrams of the methods, systems, and computer program products according to the embodiments of the present application, and may also be used for corresponding devices. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0095] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0096] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0097] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0098] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

[0099] The above calculation examples of the present invention are only used to explain the calculation model and calculation process of the present invention in detail, and are not intended to limit the implementation methods of the present invention. For ordinary technicians in the relevant field, other different forms of changes or modifications can be made based on the above description. It is impossible to list all the implementation methods here. All obvious changes or modifications derived from the technical solution of the present invention are still within the scope of protection of the present invention.

Claims

1. A method for evaluating the motion efficiency of a humanoid robot, characterized in that: include: First, calculate the reference dynamic power DPoS index P d : Among them, m is the mass of the entire robot, g is the acceleration of gravity, v is the velocity of the center of mass, and r is the velocity of the center of mass. io is the radial length from the ith joint link to the origin o of the DH parameter coordinates, ω i is the rotational angular velocity of the i-th joint link, I io is the moment of inertia of the i-th joint link relative to the rotation axis at the coordinate origin; Then according to P A and P d Calculate the reference kinetic efficiency KEoS: Among them, P A The actual power of a humanoid robot; Evaluation of the motion efficiency of humanoid robots based on the reference motion efficiency KEoS.

2. A method for evaluating the motion efficiency of a humanoid robot according to claim 1, characterized in that: The actual power P of the humanoid robot A The input power is obtained through the battery management system or power monitoring system, or the real-time voltage U and real-time output current I of the power supply are obtained, according to P A =UI calculates the actual power of the entire humanoid robot system.

3. A method for evaluating the motion efficiency of a humanoid robot according to claim 1 or 2, characterized in that: The moment of inertia of the i-th joint link relative to the rotation axis at the coordinate origin is I io By using the parallel axis theorem we obtain: Among them, I main is the moment of inertia of the ith joint link relative to its own rotation axis, l io is the distance from the i-th joint rotation axis to the DH parameter coordinate origin o; m i is the mass of the i-th connecting rod.

4. A method for evaluating the motion efficiency of a humanoid robot according to claim 3, characterized in that: When evaluating the motion efficiency of a humanoid robot based on the reference motion efficiency KEoS, the humanoid robot needs to meet the following constraints: Among them, Δzoc and Δxoc are the vertical deviation and horizontal deviation between the center of mass position and the origin of the DH parameter coordinate, and L is the leg length of the humanoid robot.

5. A humanoid robot motion efficiency evaluation system, characterized in that: include: DPoS indicator calculation unit: calculate the reference power DPoS indicator P d : Among them, m is the mass of the entire robot, g is the acceleration of gravity, v is the velocity of the center of mass, and r is the velocity of the center of mass. io is the radial length from the ith joint link to the origin o of the DH parameter coordinates, ω i is the rotational angular velocity of the i-th joint link, I io is the moment of inertia of the i-th joint link relative to the rotation axis at the coordinate origin; Reference dynamic efficiency calculation unit: According to P A and P d Calculate the reference kinetic efficiency KEoS: Among them, P A The actual power of a humanoid robot; Motion efficiency evaluation unit: evaluates the motion efficiency of the humanoid robot based on the reference motion efficiency KEoS.

6. A humanoid robot motion efficiency evaluation system according to claim 5, characterized in that: The system also includes an actual power acquisition unit, which is used to acquire or calculate the actual power P of the humanoid robot. A ; The actual power P of the humanoid robot A The input power is obtained through the battery management system or power monitoring system, or the real-time voltage U and real-time output current I of the power supply are obtained, according to P A =UI calculates the actual power of the entire humanoid robot system.

7. A humanoid robot motion efficiency evaluation system according to claim 5 or 6, characterized in that: The moment of inertia of the i-th joint link relative to the rotation axis at the coordinate origin is I io By using the parallel axis theorem we obtain: Among them, I main is the moment of inertia of the ith joint link relative to its own rotation axis, l io is the distance from the i-th joint rotation axis to the DH parameter coordinate origin o; m i is the mass of the i-th connecting rod.

8. A humanoid robot motion efficiency evaluation system according to claim 7, characterized in that: When evaluating the motion efficiency of a humanoid robot based on the reference motion efficiency KEoS, the humanoid robot needs to meet the following constraints: Among them, Δzoc and Δxoc are the vertical deviation and horizontal deviation between the center of mass position and the origin of the DH parameter coordinate, and L is the leg length of the humanoid robot.

9. A computer storage medium, characterized in that: The storage medium stores at least one instruction, and the at least one instruction is loaded and executed by the processor to execute the humanoid robot motion efficiency evaluation system according to any one of claims 5 to 8.

10. A humanoid robot motion efficiency evaluation device, characterized in that: The device includes a processor and a memory, wherein the memory stores at least one instruction, and the at least one instruction is loaded and executed by the processor to execute a humanoid robot motion efficiency evaluation system as described in any one of claims 5 to 8.

Images