Method for estimating endurance data based on humanoid robot and related equipment

Abstract

The invention relates to the technical field of robots, in particular to a method for estimating endurance data based on a humanoid robot and related equipment. The method comprises the following steps: acquiring first historical energy consumption data of the humanoid robot from a current position to a target position; calculating through the first historical energy consumption data and the real-time acquisition data to obtain a first task type influence factor, a first environment influence factor and a first robot state influence factor; calculating the first task type influence factor, the first environment influence factor, the first robot state influence factor and the first historical energy consumption data to obtain a first terrain quality influence factor; and estimating an action track of the humanoid robot according to the first terrain quality influence factor to obtain residual endurance data after the humanoid robot arrives at the target position. The problem that existing endurance estimation neglects terrain influence or is too high in cost can be solved, and estimation accuracy is improved.

Description

Technical Field

[0001] This application relates to the field of robotics technology, and in particular to a method and related equipment for estimating the battery life of a humanoid robot based on its battery life data. Background Technology

[0002] With the development of robotics technology, humanoid robots are increasingly widely used in industrial production and home services. During task execution, battery life is one of the core indicators of robot reliability. Accurate battery life prediction helps users plan task flows effectively and avoid task interruptions due to insufficient power. Current technologies typically estimate the battery life of humanoid robots based on basic data such as current battery level, average energy consumption, and task distance, without fully considering the significant impact of terrain quality (such as ground flatness, slope, or material) on energy consumption. For example, metal protrusions on factory floors in industrial settings or the switching between carpet and tile in home settings can cause significant fluctuations in robot energy consumption. Some methods attempt to correct energy consumption by pre-mapping the terrain, but this has two major drawbacks: first, static mapping data cannot cope with terrain changes caused by dynamic scenes, such as temporarily stored materials in factories or toy obstacles on home floors; second, global terrain modeling requires significant hardware investment and computing power, resulting in high costs and poor adaptability.

[0003] In summary, there are still technical challenges in the relevant technologies that need to be addressed, such as how to simply and efficiently determine the impact of terrain quality on energy consumption and how to optimize range prediction by combining multiple interference factors. Summary of the Invention

[0004] The main objective of this application is to propose a method and related equipment for estimating the endurance data of humanoid robots, which can solve the problems of existing endurance estimation ignoring terrain influence or being too costly, and improve the accuracy of the estimation.

[0005] To achieve the above objectives, one aspect of this application proposes a method for estimating the battery life of a humanoid robot based on its battery life data. The method includes the following steps: Obtain the first historical energy consumption data of the humanoid robot from its current position to the target position; The first task type influence factor, the first environmental influence factor, and the first robot state influence factor are obtained by calculating the first historical energy consumption data and the real-time collected data. The first terrain quality influence factor is obtained by calculating the first task type influence factor, the first environment influence factor, and the first robot state influence factor with the first historical energy consumption data. The trajectory of the humanoid robot is predicted based on the first terrain quality influence factor to obtain the remaining range data after reaching the target location.

[0006] In some embodiments, acquiring the first historical energy consumption data of the humanoid robot from its current position to its target position includes the following steps: Obtain the target path of the humanoid robot from its current position to the target position; Multiple target sub-paths are determined based on preset scene thresholds in the target path; Historical energy consumption data for each of the multiple target sub-paths is obtained. The historical energy consumption data of each target sub-path is summarized to obtain the first historical energy consumption data; The preset scene thresholds include path length, changes in ground material, or changes in path slope.

[0007] In some embodiments, the step of calculating the first task type influence factor, the first environmental influence factor, and the first robot state influence factor by using the first historical energy consumption data and real-time collected data includes the following steps: The first task type influence factor is obtained by calculating the ratio of energy consumption for different task types in the first historical energy consumption data. The first environmental impact factor includes the effects of temperature and humidity; Based on the first historical energy consumption data and the real-time collected data, the temperature influence and the humidity influence are obtained and calculated to obtain the first environmental influence factor; The first robot state influencing factors include battery aging degree and load weight; The battery aging degree and the load weight are obtained and calculated based on the first historical energy consumption data and the real-time collected data to obtain the first robot state influence factor.

[0008] In some embodiments, calculating the first terrain quality influence factor by combining the first task type influence factor, the first environmental influence factor, and the first robot state influence factor with the first historical energy consumption data includes the following steps: The first energy consumption impact factor is obtained by calculating the first task type impact factor, the first environmental impact factor, and the first robot state impact factor. Subtract the first energy consumption impact from the first historical energy consumption data to obtain the second energy consumption impact. The first terrain quality influence factor is obtained by calculating the second energy consumption impact.

[0009] In some embodiments, the step of estimating the trajectory of the humanoid robot based on the first terrain quality influence factor to obtain the remaining range data after reaching the target location includes the following steps: Real-time acquisition of the humanoid robot's battery level and the second task type influence factor; Based on the first terrain quality influence factor, the battery capacity, and the second mission type influence factor, the remaining range data after reaching the target location is estimated.

[0010] In some embodiments, obtaining the second task type influence factor of the humanoid robot includes the following steps: The second environmental impact factor, the second robot state impact factor, and the second historical energy consumption data of the humanoid robot traversing a preset path are obtained; wherein, the preset path includes a path that records the second terrain quality impact factor; The second task type influence factor of the humanoid robot is obtained by calculating based on the second environmental influence factor, the second robot state influence factor, the second historical energy consumption data, and the second terrain quality influence factor.

[0011] In some embodiments, the step of estimating the remaining range after reaching the target location based on the first terrain quality influence factor, the battery capacity, and the second mission type influence factor includes the following steps: Obtain the third environmental influence factor and the third robot state influence factor of the humanoid robot on the target path; wherein, the target path includes the path generated from the current position to the target position; The weights of the first terrain quality influence factor, the second task type influence factor, the third environment influence factor, and the third robot state influence factor are determined by a path weight model; wherein, the sum of the weights of the first terrain quality influence factor, the second task type influence factor, the third environment influence factor, and the third robot state influence factor is 1, and the path weight model includes experimental data fitting or machine learning model; The estimated energy consumption of the humanoid robot when it reaches the target position is calculated based on the weights of the first terrain quality influence factor, the second task type influence factor, the third environmental influence factor, and the third robot state influence factor. The remaining range after reaching the target location is obtained by calculating the battery power and the estimated energy consumption.

[0012] To achieve the above objectives, another aspect of this application proposes an apparatus for estimating the battery life of a humanoid robot, the apparatus comprising: The data acquisition module is used to acquire the first historical energy consumption data of the humanoid robot from its current position to its target position; The factor calculation module is used to calculate the first task type influence factor, the first environmental influence factor, and the first robot state influence factor by using the first historical energy consumption data and real-time collected data. The terrain quality impact factor generation module is used to calculate the first terrain quality impact factor by combining the first task type impact factor, the first environment impact factor, and the first robot state impact factor with the first historical energy consumption data. The endurance data generation module is used to predict the trajectory of the humanoid robot based on the first terrain quality influence factor, and obtain the remaining endurance data after reaching the target location.

[0013] To achieve the above objectives, another aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method described above.

[0014] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer program product, including a computer program that, when executed by a processor, implements the aforementioned method.

[0015] The embodiments of this application include at least the following beneficial effects: This application provides a method and related equipment for estimating the remaining range of a humanoid robot based on its endurance data. This solution uses historical energy consumption data to infer a first terrain quality influence factor, eliminating the need for prior global terrain mapping and significantly reducing hardware costs. By using the first terrain quality influence factor to predict the humanoid robot's trajectory, the remaining range data after reaching the target location is obtained. In industrial or household scenarios, the range estimation error is reduced by more than 30%, and task interruptions are reduced by 40%, significantly improving the practicality and reliability of the humanoid robot. Attached Figure Description

[0016] Figure 1 This is a flowchart of a method for estimating the battery life of a humanoid robot based on humanoid robot endurance data, provided in an embodiment of this application. Figure 2 yes Figure 1 The flowchart of step S100 in the middle; Figure 3 yes Figure 1 The flowchart of step S400 in the middle; Figure 4 This is a schematic diagram of a device for predicting the battery life of a humanoid robot. Figure 5 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0018] It is understood that the terms “first,” “second,” etc., used in this application may be used herein to describe various concepts, but unless otherwise stated, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the words “if,” “when,” or “in response to a determination” as used herein may be interpreted as “when…” or “when…” or “in response to a determination.”

[0019] As used in this application, the terms "at least one", "multiple", "each", "any", etc., "at least one" includes one, two or more, "multiple" includes two or more, "each" refers to each of the corresponding multiples, and "any" refers to any one of the multiples.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0021] Before providing a detailed description of the embodiments of this application, some of the nouns and terms involved in the embodiments of this application will be explained first. The nouns and terms involved in the embodiments of this application are subject to the following interpretations.

[0022] Humanoid robots: Robots that mimic human form or movement functions, possessing structures such as a head, torso, or limbs. They can perform actions such as walking and grasping through a drive system. They can be used in service, scientific research, and industrial scenarios, adapt to human living or working environments, and complete tasks such as assisted interaction and dangerous operations.

[0023] Machine learning models are tools that learn patterns from data through algorithms, build mathematical models to achieve tasks such as prediction and classification, and can adjust parameters to optimize performance based on new data.

[0024] Random Forest Model: An ensemble learning model consisting of multiple decision trees. It trains individual trees by randomly selecting features and samples, and then combines the results of individual trees to make decisions. This can reduce the risk of overfitting and improve prediction accuracy and stability.

[0025] Figure 1 This is an optional flowchart of a method for estimating the battery life of a humanoid robot based on humanoid robot endurance data provided in this application embodiment. Figure 1 The method may include, but is not limited to, steps S100 to S400.

[0026] Step S100: Obtain the first historical energy consumption data of the humanoid robot from its current position to the target position; Step S200: Calculate the first task type influence factor, the first environmental influence factor, and the first robot state influence factor using the first historical energy consumption data and the real-time collected data. Step S300: Calculate the first task type influence factor, the first environmental influence factor, and the first robot state influence factor with the first historical energy consumption data to obtain the first terrain quality influence factor. Step S400: The trajectory of the humanoid robot is predicted based on the first terrain quality influence factor to obtain the remaining range data after reaching the target location.

[0027] Steps S100 to S400, as illustrated in this embodiment, involve acquiring the target path of the humanoid robot from its current position to the target position, and obtaining first historical energy consumption data based on the target path. The first historical energy consumption data and real-time data are used to calculate and determine a first task type influence factor, a first environmental influence factor, and a first robot state influence factor corresponding to the first historical energy consumption data. The effects of these influence factors are excluded from the first historical energy consumption data, and a first terrain quality influence factor for the target path is derived by reverse calculation. This process does not require prior terrain mapping. Combining the humanoid robot's current battery level, the second task type influence factor, and the first terrain quality influence factor, the remaining battery life after reaching the target position is estimated. This invention dynamically corrects the influence of terrain on energy consumption using first historical energy consumption data, eliminating interference from task, environment, and robot state, achieving low-cost, high-precision battery life prediction in dynamic industrial and household scenarios, and ensuring the reliability of task execution.

[0028] In some embodiments, in step S100, such as Figure 2 As shown, Figure 2 yes Figure 1 The flowchart of step S100 in the process. Figure 1 Step S100 includes, but is not limited to, steps S110 to S140: Step S110: Obtain the target path of the humanoid robot from its current position to the target position; Step S120: Determine multiple target sub-paths based on preset scene thresholds in the target path; wherein, the preset scene thresholds include path length, ground material variation, and path slope variation; Step S130: Obtain historical energy consumption data for each target sub-path according to the multiple target sub-paths; Step S140: Summarize the historical energy consumption data of each target sub-path to obtain the first historical energy consumption data.

[0029] In steps S110 to S140, the target path from the current position to the target position of the humanoid robot is obtained, and the first historical energy consumption data of passing through the target path is obtained; the first historical energy consumption data is the energy consumption record of other or the same humanoid robot when passing through the target path first. Multiple target sub-paths are determined from the target path according to a preset scene threshold, and the historical energy consumption data of passing through each target sub-path is obtained according to the multiple target sub-paths; the preset scene threshold includes path length, such as a path length of 5 meters, or scene switching points, such as places where the ground material changes or the path slope changes, etc.

[0030] After acquiring the historical energy consumption data for each target sub-path, the first historical energy consumption data for each target sub-path is obtained through data aggregation (e.g., summation). Specifically, the target path is divided into multiple target sub-paths based on a length threshold or scene switching point. Each target sub-path has a corresponding historical energy consumption record, i.e., "historical energy consumption data through this sub-path". The historical energy consumption data of all target sub-paths are aggregated, for example, the total energy consumption is the sum of the energy consumption of each sub-path, to obtain the first historical energy consumption data for the entire target path. This demonstrates the process of acquiring the first historical energy consumption data for the target path.

[0031] In some embodiments, in steps S200 to S300, a first task type influence factor, a first environmental influence factor, and a first robot state influence factor are calculated using first historical energy consumption data and real-time acquired data. Specifically, the first task type influence factor is obtained by calculating the ratio of energy consumption for different task types in the first historical energy consumption data; the first environmental influence factor includes temperature and humidity influences; the first environmental influence factor is obtained by acquiring and calculating the temperature and humidity influences based on the first historical energy consumption data and real-time acquired data; the first robot state influence factor includes battery aging degree and load weight; the first robot state influence factor is obtained by acquiring and calculating the battery aging degree and load weight based on the first historical energy consumption data and real-time acquired data.

[0032] The first terrain quality influence factor is obtained by calculating the first task type influence factor, the first environment influence factor, and the first robot state influence factor with the first historical energy consumption data. Specifically, the first energy consumption influence quantity is obtained by calculating the first task type influence factor, the first environment influence factor, and the first robot state influence factor; the first energy consumption influence quantity represents the impact of task type, environment, and robot state on energy consumption. The first energy consumption influence quantity is then subtracted from the first historical energy consumption data to obtain the second energy consumption influence quantity; the second energy consumption influence quantity represents the impact of terrain quality on energy consumption. The first terrain quality influence factor is obtained by transforming the formula and calculating the second energy consumption influence quantity.

[0033] More specifically, a first task type influence factor corresponding to the first historical energy consumption data is determined. This first task type influence factor is a quantitative parameter reflecting the impact of task intensity on energy consumption, including tasks such as unloaded walking, load handling, or cleaning operations. A first environmental influence factor and a first robot state influence factor corresponding to the first historical energy consumption data are obtained. The first environmental influence factor includes quantitative parameters reflecting the impact of temperature and humidity on energy consumption, while the first robot state influence factor includes quantitative parameters reflecting the impact of battery aging and load weight on energy consumption. Based on the quantitative values ​​of the first task type influence factor, the first environmental influence factor, and the first robot state influence factor, the impact of task type, environment, and robot state on energy consumption is calculated, i.e., the first energy consumption influence quantity. The impact quantities of task type, environment, and robot state on energy consumption are subtracted from the first historical energy consumption data to obtain the impact quantity of terrain quality on energy consumption of the target path, i.e., the second energy consumption influence quantity. Based on the impact quantity of terrain quality on energy consumption, the formula is transformed and calculated to obtain the first terrain quality influence factor of the target path.

[0034] In some embodiments, in step S400, such as Figure 3 As shown, Figure 3 yes Figure 1 The flowchart for step S400. Figure 1 Step S400 includes, but is not limited to, steps S410 to S420: Step S410: Real-time acquisition of the humanoid robot's battery level and the second task type influence factor; Step S420: Based on the first terrain quality influence factor, battery power, and the second mission type influence factor, estimate the remaining range data after reaching the target location.

[0035] In step S410, the second environmental impact factor, the second robot state impact factor, and the second historical energy consumption data of the humanoid robot passing through the preset path are obtained; wherein, the preset path includes a path that records the second terrain quality impact factor; the second task type impact factor of the humanoid robot is calculated based on the second environmental impact factor, the second robot state impact factor, the second historical energy consumption data, and the second terrain quality impact factor.

[0036] In step S420, the third environmental influence factor and the third robot state influence factor of the humanoid robot on the target path are obtained; wherein, the target path includes the path generated from the current position to the target position; the weights of the first terrain quality influence factor, the second task type influence factor, the third environmental influence factor, and the third robot state influence factor are determined by the path weight model; wherein, the sum of the weights of the first terrain quality influence factor, the second task type influence factor, the third environmental influence factor, and the third robot state influence factor is 1, and the path weight model includes experimental data fitting or machine learning model; the estimated energy consumption of the humanoid robot when it reaches the target position is calculated based on the weights of the first terrain quality influence factor, the second task type influence factor, the third environmental influence factor, and the third robot state influence factor; the remaining range data after reaching the target position is obtained by subtracting the estimated energy consumption from the battery charge.

[0037] Specifically, the current battery level of the humanoid robot and the second task type influence factor corresponding to the current task being performed by the humanoid robot are obtained; the second task type influence factor is a quantitative parameter of the energy consumption impact corresponding to the current task intensity of the humanoid robot.

[0038] The quantification rules for the second task type influence factor are consistent with those for the first task type influence factor. The core definition of this quantification rule is that the second task type influence factor is a dimensionless parameter used to quantify the impact of the intensity of the target humanoid robot's current task on energy consumption. Its core logic is: using "humanoid robot walking unloaded (without additional tasks)" as the baseline energy consumption scenario, the influence factor value corresponding to the task is determined by comparing the ratio of actual energy consumption under different task types to the baseline energy consumption. This rule is completely consistent with the quantification logic of the first task type influence factor and is only adapted for the "current task of the humanoid robot."

[0039] Regarding the prerequisites for quantification rules, three basic parameters need to be defined before performing quantification calculations to ensure data consistency and comparability: 1. Baseline energy consumption ( ): Defined as "humanoid robots operating in a standard environment (temperature) ,humidity The energy consumption per unit distance of unloaded movement at a constant speed of 0.5 m / s under the following conditions: flat concrete terrain (terrain quality influence factor = 1.0), no joint wear (robot state influence factor = 1.0), and no additional load (load weight = 0 kg). The unit is Wh / m, and it needs to be determined through laboratory calibration or robot factory test data (e.g., for a certain model of robot). =0.8Wh / m); 2. Reference path (preset path): Select "Recorded explicit terrain quality influencing factors ( The path is used as a reference (such as a pre-mapped workshop corridor in an industrial setting, or a fixed barrier-free path between the living room and bedroom in a home setting). It needs to be determined in advance through historical energy consumption back-calculation or topographic mapping (e.g.) =1.1, representing slightly uneven terrain); 3. Reference environment and state parameters: Record the environmental impact factors corresponding to the reference path ( For example, a temperature of 26℃ corresponds to =1.02, humidity 55% corresponds to =1.05) and robot state influence factor ( For example, a 10% battery degradation corresponds to =1.08, corresponding to a load of 0kg =1.0), ensuring that interference factors in the reference scenario can be quantified and eliminated.

[0040] For the complete process of quantification calculation of quantification rules, in the second task type influence factor ( The quantification of energy consumption is achieved through "backward calculation based on reference scenario energy consumption," and the specific steps are as follows: Step 1: Collect historical energy consumption data for the reference scenario Control the humanoid robot to perform the currently quantifiable task type (such as "carrying a 3kg item", "mopping the floor", "delivering a water cup", etc.) on the reference path, and record the results synchronously: Total distance of the reference path ( The unit is meters (m), such as workshop aisles. =20m); Total energy consumption of the robot along the reference path ( The unit is Wh, which is collected in real time through the battery management system, such as when performing the "moving a 3kg item" operation. =22Wh); Environmental impact factors during mission execution (Real-time acquisition of environmental parameters for calculation) and robot state influencing factors (Obtained through the robot hardware status monitoring module).

[0041] Step 2: Eliminate the energy consumption impact of non-task factors Based on the known parameters of the reference path ( , , ) and collected , Calculate the base energy consumption caused by non-task factors ( The formula is as follows: ; For example: if =20m =0.8Wh / m =1.1、 =1.02 1.05 = 1.071 =1.08, then: ; Should This represents the theoretical energy consumption of a humanoid robot walking on a reference path without any task, affected by terrain, environment, and its own state. It needs to be calculated from the total energy consumption. Excluded from the list to separate "additional energy consumption caused by task type".

[0042] Step 3: Calculate the impact factor of the second task type: the impact factor of the second task type ( ) is the total energy consumption of the reference scenario ( "Non-task basic energy consumption" and "Non-task basic energy consumption" The ratio of ")" is calculated using the following formula: ; For example: If ,but: , Should The numerical value represents "the current task type (carrying 3kg of items) increases energy consumption by 7% compared to walking while empty," which aligns with the principle that "the higher the task intensity, the higher the energy consumption." The quantitative logic of "the larger the number" (e.g., "carrying 5kg of items") The value is likely 1.15, as "mopping and cleaning" consumes more energy due to the robotic arm's drive. (Possibly 1.23).

[0043] The universality and calibration mechanism for quantification rules include: 1. Universality guarantee: for robots of the same model... The "task type-factor correspondence" can be pre-established in a database through batch testing (e.g., "idle walking"). =1.0, carrying 1kg is =1.03, carrying 3kg is =1.07, mopping =1.23”, the new robot can directly access the database upon first use without recalculation. 2. Dynamic calibration mechanism: If the robot experiences hardware changes (such as joint repair or actuator replacement) or deterioration in performance after long-term use (such as decreased battery capacity or increased joint wear), it needs to be updated again through the “reference path test”. For example, after joint wear and tear, performing tasks such as "lifting 3kg items" becomes difficult. Increased to 23Wh Because the state factor changes and rises to 21.2 Wh, the new 3. Scene Adaptation Adjustment: If the terrain or environment of the reference path changes, such as during workshop floor renovation or carpet installation in a home, the reference path needs to be recalibrated. and Then recalculate according to the above rules. To avoid factor bias caused by environmental interference.

[0044] In summary, the "second task type influence factor" of this rule is calculated based on robot-specific parameters such as "task intensity (load or job type) and joint drive energy consumption".

[0045] After obtaining the second task type influence factor mentioned above, the remaining battery power of the humanoid robot after reaching the target location is estimated based on the current battery power, the first terrain quality influence factor, and the second task type influence factor; the remaining battery power is then used to estimate the remaining range.

[0046] More specifically, the process involves acquiring the second environmental impact factor, the second robot state impact factor, and the second historical energy consumption data of the humanoid robot as it traverses a preset path. The preset path is a path pre-determined from terrain mapping or historical energy consumption data, with corresponding second terrain quality impact factors recorded. Based on the second environmental impact factor, the second robot state impact factor, the second historical energy consumption data, and the second terrain quality impact factor, the second task type impact factor of the humanoid robot is determined and obtained using an energy consumption impact quantification formula. The process also involves acquiring the third environmental impact factor and the third robot state impact factor for the current target path. The weights of the first terrain quality impact factor, the second task type impact factor, the third environmental impact factor, and the third robot state impact factor are determined through experimental data fitting or machine learning models, respectively. The weights satisfy the condition that the sum of the weights of each factor is 1. Based on the first terrain quality impact factor, the second task type impact factor, the third environmental impact factor, the third robot state impact factor, and their weights, the estimated energy consumption of the humanoid robot when it reaches the target position is estimated using a weighted summation formula. Finally, the remaining battery power is estimated based on the current battery level and the estimated energy consumption.

[0047] The aforementioned method infers terrain quality influencing factors from first-historical energy consumption data, eliminating the need for pre-conducting global terrain mapping and significantly reducing hardware costs. Simultaneously, by dynamically eliminating interference from task type, environment, and robot state, it achieves adaptive adaptation to dynamic terrain scenarios (such as temporary obstacles and sudden changes in ground material). Compared to traditional methods, this application reduces the battery life prediction error by over 30% and the task interruption rate by 40% in industrial and home scenarios, significantly improving the practicality and reliability of humanoid robots.

[0048] The following section provides a detailed introduction and explanation of the solutions in this invention, using specific industrial and home application examples: First, the target path and initial historical energy consumption data are acquired. The current location refers to the robot's current coordinates, such as workshop A in an industrial setting or the living room in a home setting. The target location refers to the endpoint of the task the robot needs to perform, such as a shelf in workshop B or a bedside table in the bedroom. The target path is generated by the robot's navigation system based on rules such as shortest distance or obstacle distribution, and can be selected by the user or automatically determined by the system. Initial historical energy consumption data refers to the energy consumption records (unit: Wh) of other or the same humanoid robot that previously traversed the target path, including the energy consumption values ​​for the entire path and each key node. This data can be stored in the robot's local memory or a cloud database and can be queried using path identifiers (such as path IDs). For example, in an industrial setting, the historical handling energy consumption of the path "from workshop A to shelf B" can be recorded, and in a home setting, the cleaning energy consumption of the path "from living room to bedroom" can be recorded.

[0049] Next, the first terrain quality impact factor is determined. This factor quantifies the degree of terrain's influence on energy consumption; a higher value indicates higher energy consumption. For example, the first terrain quality impact factor for a flat cement surface might be 1.0, for a carpet-like surface it might be 1.5, and for a slope (10°) it might be 1.8. The specific determination process is as follows: 1. Determine the impact factor of the first task type: the impact factor of the first task type ( This reflects the impact of task intensity on energy consumption; for example, "walking without load" is 1.0, "carrying 5kg items" is 1.3, and "mopping and cleaning" is 1.2. The energy consumption ratio for different task types can be determined by statistically analyzing historical data.

[0050] 2. Obtain the first environmental impact factor: The first environmental impact factor ( This includes the effects of temperature (e.g., 1.2 at -5℃ and 1.0 at 25℃) and humidity (e.g., 1.1 at 80% humidity), which are collected in real time by robot sensors or extracted from historical records.

[0051] Specifically, in obtaining the first environmental impact factor, the effects of temperature and humidity are treated as two independent sub-factors, quantified separately, and then integrated through a product. The rationale is that the environment's impact on the energy consumption of humanoid robots is an independent, superimposed effect of both temperature and humidity. Temperature affects battery activity and joint lubrication efficiency, while humidity affects circuit insulation and the coefficient of friction; their effects on energy consumption are independent of each other. Therefore, the "temperature impact sub-factor" needs to be determined separately. "and humidity influence sub-factor" Then through the formula The final first environmental impact factor was obtained.

[0052] In acquiring the first environmental impact factor, the core difference between real-time data collection and historical data extraction lies in the "time dimension" and "application scenario" of the data. For real-time data collection, the triggering scenario is when the humanoid robot needs to estimate its remaining range, such as when executing a new task or planning a path, requiring calculation of the impact of the "current environment" on energy consumption. The operation involves using the robot's onboard temperature and humidity sensors, such as those integrated into the robot body, to instantly read the current environmental temperature and humidity values. Subsequent processing involves applying a pre-defined "temperature-impact factor mapping relationship," for example, experimentally determined that -5℃ corresponds to... 25℃ corresponds And the "humidity-influence factor mapping relationship", for example, 80% humidity corresponds to 50% humidity corresponds to The system converts real-time temperature and humidity values ​​into corresponding sub-factors, which are then multiplied to obtain the first environmental impact factor for the current scene, used for calculating the "current range estimate." Historical data extraction is triggered when it's necessary to infer the terrain quality impact factor based on historical energy consumption data. For example, when excluding environmental impacts from the first historical energy consumption data, it's necessary to obtain the environmental impact factor from the historical task execution. The operation involves retrieving temperature and humidity data saved in historical task records from the humanoid robot's local storage or cloud database. This data was collected and stored in real-time by sensors during the historical task execution. In subsequent processing, using the same "temperature-impact factor mapping relationship" and "humidity-impact factor mapping relationship" as the real-time acquisition, the historical temperature and humidity data are converted into the "temperature impact sub-factor" and "humidity impact sub-factor" at that time, multiplied to obtain the first environmental impact factor for the historical scene, used for historical data processing scenarios such as "terrain quality impact factor inference." In summary, real-time data acquisition serves for current battery life estimation, with data sourced from current sensors; historical data extraction serves for backtracking and analysis of historical data, with data sourced from previously stored sensor records. Furthermore, the temperature, humidity, and influencing factor quantification rules for both are completely consistent, ensuring data consistency and comparability.

[0053] 3. Obtain the first robot state influence factor: First robot state influence factor ( The parameters include battery aging (e.g., 1.0 for a new battery and 1.2 for a 30% degradation) and load weight (e.g., 1.0 for a 0kg load and 1.1 for a 3kg load), calculated based on robot hardware parameters and historical usage data.

[0054] 4. Eliminate interference and calculate terrain factors: Use formula (1) to calculate the terrain factors from the first historical energy consumption data ( After excluding the above influences, the impact of terrain quality on energy consumption is obtained, and then the first terrain quality influence factor is determined. ): ; in, The baseline energy consumption is represented by the following parameters: flat concrete surface, temperature 25°C. 2℃, 50% humidity 5%, energy consumption per unit distance under no-load conditions (unit: Wh / m). This can be obtained by fitting historical data. .

[0055] If the target path is divided into multiple sub-paths, these sub-paths are defined by a preset length threshold of 5 meters or a scene transition point. Scene transition points are determined by the robot's foot pressure sensors or vision sensors. For example, if the ground material changes from tile to carpet, and the pressure sensor reports a change in friction ≥20%, or a change in slope ≥5°, the path is automatically designated as a new target sub-path. The terrain quality impact factor for each sub-path is then calculated separately, and a weighted average (with the weight determined by the sub-path length percentage) is used to obtain the first terrain quality impact factor for the target path.

[0056] Finally, the remaining range is estimated. This process begins by acquiring current parameters, including the current battery capacity (in Wh) collected by the Battery Management System (BMS), and the second task type influence factor (…). The second task type influence factor is determined based on the current task. For example, when the current task is "delivering a water cup," the second task type influence factor is 1.1. For new tasks, calibration can be performed using a preset path. Calibration methods include: Obtain the second historical energy consumption of the robot traversing known terrain (preset path). ), second environmental factor ( ), second state factor ( ) and preset terrain factors ( The result is obtained by calculation using formula (2). : ; Next, the estimated energy consumption is calculated. A third environmental impact factor is obtained based on real-time factors such as temperature and humidity; a third robot state impact factor is obtained based on factors such as current battery aging and real-time load. The weights of each factor are determined through experimental data fitting or machine learning models. , , , ), and satisfy For example, in an industrial setting, data is obtained through statistical analysis of 100 sets of historical data. =0.4、 =0.3、 =0.15、 =0.15; In home scenarios, dynamic weights are obtained through training a random forest model. Estimated energy consumption is calculated using formula (3):

[0057] Where D represents the total distance of the target path (in meters). This indicates the estimated energy consumption (unit: Wh).

[0058] Finally, calculate the remaining battery power and battery life using the formula. Calculate remaining battery power. Remaining battery life data ( If the driving range is in meters, it is calculated using formula (4):

[0059] in, , , , These represent the historical average task, historical average environment, historical average condition, and historical average terrain factor, respectively. If it is the endurance time (in minutes), it is calculated using the average movement speed formula, which is: .in, This indicates the average speed (meters per minute).

[0060] Please see Figure 4 This application also provides an apparatus for estimating the battery life of a humanoid robot based on its battery data, which can implement the above-described method. The apparatus includes: The data acquisition module is used to acquire the first historical energy consumption data of the humanoid robot from its current position to its target position; The factor calculation module is used to calculate the first task type influence factor, the first environmental influence factor, and the first robot state influence factor by using the first historical energy consumption data and real-time collected data. The terrain quality impact factor generation module is used to calculate the first terrain quality impact factor by combining the first task type impact factor, the first environmental impact factor, and the first robot state impact factor with the first historical energy consumption data. The endurance data generation module is used to predict the trajectory of the humanoid robot based on the first terrain quality influence factor, and obtain the remaining endurance data after reaching the target location.

[0061] It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0062] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0063] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0064] Please see Figure 5 , Figure 5 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 510 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 520 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 520 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 520 and is called and executed by the processor 510 using the methods described in the embodiments of this application. The input / output interface 530 is used to implement information input and output; The communication interface 540 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 550 transmits information between various components of the device (e.g., processor 510, memory 520, input / output interface 530, and communication interface 540); The processor 510, memory 520, input / output interface 530 and communication interface 540 are connected to each other within the device via bus 550.

[0065] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0066] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0067] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0068] It is understood that the content of the above method embodiments is applicable to the embodiments of this program product. The specific functions implemented by the embodiments of this program product are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0069] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0070] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0071] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0072] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0073] It should be understood that the data used in this way can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in a sequence other than those illustrated or described herein. Furthermore, the terms “comprising” and “having”, and any variations thereof, are intended to cover a non-exclusive inclusion, for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such process, method, product, or apparatus.

[0074] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0075] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0076] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0077] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0078] If the integrated unit is implemented as 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 technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0079] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for predicting the battery life of a humanoid robot based on its battery life data, characterized in that, The method includes the following steps: Obtain the first historical energy consumption data of the humanoid robot from its current position to the target position; The first task type influence factor, the first environmental influence factor, and the first robot state influence factor are obtained by calculating the first historical energy consumption data and the real-time collected data. The first terrain quality influence factor is obtained by calculating the first task type influence factor, the first environment influence factor, and the first robot state influence factor with the first historical energy consumption data. The trajectory of the humanoid robot is predicted based on the first terrain quality influence factor to obtain the remaining range data after reaching the target location.

2. The method according to claim 1, characterized in that, The process of acquiring the first historical energy consumption data of the humanoid robot from its current position to its target position includes the following steps: Obtain the target path of the humanoid robot from its current position to the target position; Multiple target sub-paths are determined based on preset scene thresholds in the target path; Historical energy consumption data for each of the multiple target sub-paths is obtained. The historical energy consumption data of each target sub-path is summarized to obtain the first historical energy consumption data; The preset scene thresholds include path length, changes in ground material, or changes in path slope.

3. The method according to claim 1, characterized in that, The step of calculating the first task type influence factor, the first environmental influence factor, and the first robot state influence factor by using the first historical energy consumption data and real-time collected data includes the following steps: The first task type influence factor is obtained by calculating the ratio of energy consumption for different task types in the first historical energy consumption data. The first environmental impact factor includes the effects of temperature and humidity; Based on the first historical energy consumption data and the real-time collected data, the temperature influence and the humidity influence are obtained and calculated to obtain the first environmental influence factor; The first robot state influencing factors include battery aging degree and load weight; The battery aging degree and the load weight are obtained and calculated based on the first historical energy consumption data and the real-time collected data to obtain the first robot state influence factor.

4. The method according to claim 1, characterized in that, The step of calculating the first terrain quality influence factor by combining the first task type influence factor, the first environmental influence factor, and the first robot state influence factor with the first historical energy consumption data includes the following steps: The first energy consumption impact factor is obtained by calculating the first task type impact factor, the first environmental impact factor, and the first robot state impact factor. Subtract the first energy consumption impact from the first historical energy consumption data to obtain the second energy consumption impact. The first terrain quality influence factor is obtained by calculating the second energy consumption impact.

5. The method according to claim 1, characterized in that, The step of predicting the trajectory of the humanoid robot based on the first terrain quality influence factor to obtain the remaining range data after reaching the target location includes the following steps: Real-time acquisition of the humanoid robot's battery level and the second task type influence factor; Based on the first terrain quality influence factor, the battery capacity, and the second mission type influence factor, the remaining range data after reaching the target location is estimated.

6. The method according to claim 5, characterized in that, Obtaining the second task type influence factor of the humanoid robot includes the following steps: The second environmental impact factor, the second robot state impact factor, and the second historical energy consumption data of the humanoid robot traversing a preset path are obtained; wherein, the preset path includes a path that records the second terrain quality impact factor; The second task type influence factor of the humanoid robot is obtained by calculating based on the second environmental influence factor, the second robot state influence factor, the second historical energy consumption data, and the second terrain quality influence factor.

7. The method according to claim 5, characterized in that, The step of estimating the remaining range after reaching the target location based on the first terrain quality influence factor, the battery capacity, and the second mission type influence factor includes the following steps: Obtain the third environmental influence factor and the third robot state influence factor of the humanoid robot on the target path; wherein, the target path includes the path generated from the current position to the target position; The weights of the first terrain quality influence factor, the second task type influence factor, the third environment influence factor, and the third robot state influence factor are determined by a path weight model; wherein, the sum of the weights of the first terrain quality influence factor, the second task type influence factor, the third environment influence factor, and the third robot state influence factor is 1, and the path weight model includes experimental data fitting or machine learning model; The estimated energy consumption of the humanoid robot when it reaches the target position is calculated based on the weights of the first terrain quality influence factor, the second task type influence factor, the third environmental influence factor, and the third robot state influence factor. The remaining range after reaching the target location is obtained by calculating the battery power and the estimated energy consumption.

8. A device for predicting the battery life of a humanoid robot, characterized in that, The device includes: The data acquisition module is used to acquire the first historical energy consumption data of the humanoid robot from its current position to its target position; The factor calculation module is used to calculate the first task type influence factor, the first environmental influence factor, and the first robot state influence factor by using the first historical energy consumption data and real-time collected data. The terrain quality impact factor generation module is used to calculate the first terrain quality impact factor by combining the first task type impact factor, the first environment impact factor, and the first robot state impact factor with the first historical energy consumption data. The endurance data generation module is used to predict the trajectory of the humanoid robot based on the first terrain quality influence factor, and obtain the remaining endurance data after reaching the target location.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method according to any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 7.

Images