A robot volume self-adaptive adjusting method, device, equipment and medium

Abstract

This invention relates to the field of embodied intelligence, specifically disclosing a method, apparatus, device, and medium for adaptive volume adjustment of a robot. The method includes: acquiring environmental noise, extracting and separating robot self-noise from it to obtain target noise; determining the noise level based on the target noise; if it is a first noise level, setting the target volume as the sum of the current volume and a first fixed volume compensation amount; if it is a second noise level, setting the target volume as the sum of the current volume and a nonlinear volume compensation amount, wherein the nonlinear volume compensation amount is determined based on a dynamic adjustment coefficient negatively correlated with the intensity of the target noise; if it is a third noise level, setting the target volume as the smaller value between the sum of the current volume and the second fixed volume compensation amount and a preset maximum volume threshold; and adjusting the robot's output volume to the target volume. Compared with existing technologies, this invention avoids misjudgments caused by robot self-noise, accurately adapts volume control to the actual environment, and improves the user experience.

Description

Technical Field

[0001] This invention relates to the field of embodied intelligence, and in particular to a method, apparatus, device, and medium for adaptive volume adjustment of a robot. Background Technology

[0002] Embodied intelligence, a cutting-edge field integrating artificial intelligence and robotics, aims to endow robots with the ability to dynamically interact with their environment through perception, decision-making, and action. Typical applications include service robots, industrial robots, and special-purpose robots. In embodied intelligence systems, accurate environmental perception and real-time adaptive adjustment are the core foundation for achieving natural human-robot interaction and efficient task execution. Among these, robot volume adaptive adjustment technology directly affects the clarity of voice interaction and user experience, and is one of the key technological challenges in the field of embodied intelligence.

[0003] However, existing methods for adjusting volume in embodied robots have significant drawbacks. On the one hand, most solutions, such as those in Chinese patent application CN115904299A, fail to effectively separate environmental noise from the robot's own noise (such as motion noise), causing the system to mistakenly include the noise in the environmental assessment, resulting in over- or under-compensation of volume. This is especially problematic in scenarios where the robot is continuously speaking, easily leading to volume adjustment distortion and severely affecting the naturalness and accuracy of the interaction. On the other hand, existing technologies, such as those in Chinese patent application CN109842725A, largely rely on linear volume compensation strategies, where the compensation amount is proportional to the noise intensity. This makes it difficult to adapt to complex and varied acoustic environments. In scenarios with moderate noise levels (such as everyday conversations or low-frequency equipment operation), linear compensation cannot balance the contradiction between insufficient compensation causing speech drowning and excessive compensation causing auditory abruptness, resulting in insufficient adjustment accuracy and adaptability. Furthermore, some methods lack reasonable constraints on the upper limit of volume output, which may cause the volume to exceed the device's safety threshold or the user's auditory comfort range due to cumulative compensation, posing a risk of hardware damage and a decline in user experience.

[0004] Therefore, in the field of embodied intelligence, there is an urgent need for a robot volume adaptive adjustment method that can accurately isolate self-noise interference, dynamically adapt to different noise levels, and take into account both safety and auditory comfort, so as to break through the existing technical bottlenecks and improve the environmental perception accuracy and human-computer interaction quality of embodied intelligence systems. Summary of the Invention

[0005] The purpose of this invention is to provide a robot volume adaptive adjustment method, device, equipment and medium, which obtains accurate target noise by separating self-noise and adopts a hierarchical compensation strategy to achieve more comfortable and accurate robot voice interaction.

[0006] The objective of this invention can be achieved through the following technical solutions: A method for adaptive volume adjustment in a robot, the method comprising the following steps: Obtain the ambient noise of the robot's current environment; The robot's own noise is extracted and separated from the environmental noise to obtain the target noise; Based on the target noise, the noise level is determined. If the noise level is the first noise level, the target volume is set to the sum of the current volume and the first fixed volume compensation amount. If the noise level is the second noise level, the target volume is set to the sum of the current volume and the nonlinear volume compensation amount, wherein the nonlinear volume compensation amount is determined based on a dynamic adjustment coefficient, and the dynamic adjustment coefficient is negatively correlated with the intensity of the target noise. If the noise level is the third noise level, the target volume is set to the smaller value between the sum of the current volume and the second fixed volume compensation amount and the preset maximum volume threshold. Adjust the robot's output volume to the target volume.

[0007] Preferably, the robot's self-noise is extracted and separated from the environmental noise to obtain the target noise, including: Obtain the robot's current motion state parameters, which include at least one of motor speed, joint torque, and walking gait. Based on the motion state parameters, the pre-built robot self-noise feature database is queried to determine the spectral characteristics of the current robot self-noise; An adaptive filtering algorithm is used to filter out the spectral characteristics of the self-noise from the environmental noise, retaining the remaining frequency band as the target noise.

[0008] Preferably, determining the noise level based on the target noise specifically involves: Calculate the sound pressure level of the target noise; Based on the sound pressure level, the noise level corresponding to the target noise is determined according to a preset noise classification strategy: when the sound pressure level is less than or equal to a first threshold, it is determined to be a first noise level; when the sound pressure level is greater than or equal to a second threshold, it is determined to be a third noise level; otherwise, it is determined to be a second noise level.

[0009] Preferably, the method for determining the nonlinear volume compensation amount is as follows: The intensity of the target noise is expressed in terms of sound pressure level, and the current sound pressure level of the target noise is calculated. Calculate the difference between the second threshold and the first threshold to obtain the first interval; Calculate the difference between the second fixed volume compensation amount and the first fixed volume compensation amount to obtain the second interval; The difference between the current sound pressure level of the target noise and the first threshold is calculated. Using the difference as the base and the growth exponent minus one as the exponent, a power operation is performed to obtain the first power term. Using the first interval as the base and the growth exponent as the exponent, a power operation is performed to obtain the second power term. The first power term is multiplied by the second interval and divided by the second power term to obtain the dynamic adjustment coefficient, wherein the growth exponent is greater than 0 and less than 1. The difference between the sound pressure level of the target noise and the first threshold is multiplied by the dynamic adjustment coefficient and then added to the first fixed volume compensation amount to obtain the nonlinear volume compensation amount.

[0010] A robot volume adaptive adjustment device, the device comprising: Noise Acquisition and Separation Module: Used to acquire the ambient noise of the robot's current environment, and extract and separate the robot's own noise from the ambient noise to obtain the target noise; Target volume determination module: used to determine the noise level based on the target noise and determine the target volume based on the noise level. If the noise level is a first noise level, the target volume is set to the sum of the current volume and a first fixed volume compensation amount; if it is a second noise level, the target volume is set to the sum of the current volume and a non-linear volume compensation amount, wherein the non-linear volume compensation amount is determined based on a dynamic adjustment coefficient, and the dynamic adjustment coefficient is negatively correlated with the intensity of the target noise; if it is a third noise level, the target volume is set to the smaller value between the sum of the current volume and the second fixed volume compensation amount and a preset maximum volume threshold. Adjustment module: Used to adjust the robot's output volume to the target volume.

[0011] An electronic device includes a memory and one or more processors, wherein the memory stores executable code, and the one or more processors execute the executable code to implement the robot volume adaptive adjustment method.

[0012] A computer-readable storage medium having a program stored thereon that, when executed by a processor, implements the aforementioned robot volume adaptive adjustment method.

[0013] Compared with the prior art, the present invention has the following beneficial effects: (1) This invention extracts and separates robot self-noise from environmental noise and obtains target noise as the basis for adjustment. By eliminating self-noise interference, it avoids over- or under-compensation of volume due to misjudging robot self-motion noise and other noises as environmental noise, which significantly improves the accuracy and environmental adaptability of volume adjustment and ensures the clarity and naturalness of interactive voice.

[0014] (2) The present invention divides the target noise into three noise levels and adopts fixed compensation amount and nonlinear compensation amount respectively. It covers low, medium and high noise environments through a graded strategy, taking into account the adjustment needs of different scenarios: fast fixed compensation in low noise, dynamic fine adjustment in medium noise, and safe amplitude limiting in high noise.

[0015] (3) Under high noise levels, the present invention sets the target volume to the smaller value of the current volume plus a fixed compensation amount and a preset maximum volume threshold. By setting the maximum volume threshold, the cumulative compensation can be effectively prevented from causing the volume to exceed the limit, thus avoiding the risk of hardware damage, while ensuring that the user's auditory experience is within a comfortable range.

[0016] (4) At medium noise levels, the present invention uses a dynamic adjustment coefficient based on power function decay to determine the nonlinear volume compensation amount. This coefficient is negatively correlated with the target noise intensity, so that when the noise just exceeds the threshold, the compensation amount increases rapidly to ensure speech audibility. As the noise increases, the compensation growth rate slows down and tends to stabilize, avoiding auditory abruptness or distortion caused by over-compensation. It can ensure that the compensation growth rate automatically adapts to the environmental requirements in medium and high noise environments, taking into account both speech clarity and auditory comfort. Attached Figure Description

[0017] Figure 1 This is a flowchart of the method of the present invention; Figure 2 This is a structural diagram of the device of the present invention; Figure 3 This is a structural diagram of the electronic device of the present invention. Detailed Implementation

[0018] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. These embodiments are based on the technical solution of the present invention and provide detailed implementation methods and specific operating procedures. However, the scope of protection of the present invention is not limited to the following embodiments.

[0019] Figure 1 This is a flowchart illustrating a robot volume adaptive adjustment method according to an embodiment of the present invention. Figure 1 As shown, the robot volume adaptive adjustment method in this embodiment of the invention may include the following steps: S1, obtain the ambient noise of the robot's current environment.

[0020] The robot collects ambient sound signals in real time through a microphone array mounted on its head or body, obtaining environmental noise data. This data includes two parts: external environmental noise (such as human voices and traffic noise) and robot self-noise (such as its own motion noise).

[0021] S2, extract and separate the robot's own noise from the environmental noise to obtain the target noise.

[0022] S21, Obtain the robot's current motion state parameters, which include at least one of motor speed, joint torque, and walking gait.

[0023] In a preferred embodiment, motion state parameters are collected in real time by sensors built into the robot. Specifically, the real-time rotational speed of each drive motor can be measured by an encoder (such as an optical encoder or a magnetic encoder); the real-time torque value of each joint can be obtained by a torque sensor at the joint (such as a strain gauge sensor); and the current walking mode (such as straight walking, turning, or climbing) and speed parameters can be obtained by a gait planning system or a foot force sensor.

[0024] Based on the data collected by the sensors, a dynamic feature vector is generated after preprocessing. The dynamic feature vector includes motor speed, joint torque and walking gait. Uncollected data is marked as invalid parameters, and the corresponding values ​​in the feature vector are ignored or filled with a preset value (such as -1 or NaN).

[0025] S22, based on the motion state parameters, query the pre-built robot self-noise feature database to determine the spectral characteristics of the current robot self-noise.

[0026] In this embodiment, the robot's self-noise feature database covers all possible parameter combination scenarios, including three modes: Single-parameter mode: Only collects speed, torque, and gait data; Dual-parameter modes: speed + torque, speed + gait, torque + gait; Full parameter mode: speed + torque + gait.

[0027] For each mode, self-noise data under the corresponding motion state is collected, and spectral features are extracted by STFT / FFT to construct a multi-dimensional mapping table to build a robot self-noise feature database.

[0028] S23, using an adaptive filtering algorithm, the spectral characteristics of the self-noise are filtered out from the environmental noise, and the remaining frequency band is retained as the target noise.

[0029] In this embodiment, the spectral features retrieved from the robot's self-noise feature database are used as the reference signal for adaptive filtering, and the normalized LMS algorithm is employed for adaptive filtering. When the available motion state parameters decrease, the filter lacks sufficient prior information about self-noise. Therefore, by adjusting the step size to a larger value, a better coefficient space can be explored, avoiding getting trapped in local optima.

[0030] In a preferred embodiment, to address complex noise scenarios, a dynamic algorithm can be used to switch the filtering algorithm from the normalized LMS algorithm to the recursive least squares algorithm. Specifically, the improvement in signal-to-noise ratio (SNR) after the normalized LMS algorithm is executed is monitored in real time, i.e., the difference between the SNR after filtering and the SNR before filtering. If this difference is less than a preset threshold, it indicates that the current algorithm's filtering effect is poor, and it needs to be switched to the recursive least squares algorithm. The recursive least squares algorithm, by minimizing the weighted sum of squared errors, has a faster convergence speed and lower steady-state error. During the operation of the recursive least squares algorithm, the difference between the SNR after filtering and the SNR before filtering is monitored in real time. If this difference is greater than a preset threshold, or if memory usage exceeds a threshold, the normalized LMS algorithm is automatically switched.

[0031] S3, based on the target noise, determine the noise level. If the noise level is the first noise level, then set the target volume to the sum of the current volume and the first fixed volume compensation amount; if it is the second noise level, then set the target volume to the sum of the current volume and the nonlinear volume compensation amount, wherein the nonlinear volume compensation amount is determined based on a dynamic adjustment coefficient, and the dynamic adjustment coefficient is negatively correlated with the intensity of the target noise; if it is the third noise level, then set the target volume to the smaller value between the sum of the current volume and the second fixed volume compensation amount and the preset maximum volume threshold.

[0032] S31, determine the noise level based on the target noise.

[0033] Calculate the sound pressure level of the target noise; Based on the sound pressure level, the noise level corresponding to the target noise is determined according to a preset noise classification strategy. In this embodiment, a first threshold is set. 45dB, second threshold The noise level is 65dB. That is, when the sound pressure level is ≤45dB, it is judged as the first noise level, i.e., low noise level; when 45dB < sound pressure level < 65dB, it is judged as the second noise level, i.e. medium noise level; and when the sound pressure level is ≥65dB, it is judged as the third noise level, i.e. high noise level.

[0034] S32, determine the target volume.

[0035] S321, Determination of target volume at low noise level.

[0036] In low noise mode, the first fixed volume compensation A can be set to 10dB, thereby controlling the target volume to always be 10dB higher than the ambient noise. This is suitable for quiet scenarios such as bedrooms and studies, with a soft and non-abrupt volume. While ensuring that the prompts are clear and distinguishable, it maximizes the quietness of the home and avoids disturbing neighbors.

[0037] S322, Determination of target volume at medium noise level.

[0038] ① Calculate the current sound pressure level of the target noise, expressing the intensity of the target noise in terms of sound pressure level. ; ② Calculate the second threshold and the first threshold The difference is used to obtain the first interval; ③ Calculate the difference between the second fixed volume compensation amount B and the first fixed volume compensation amount A to obtain the second interval; ④ Calculate the difference between the current sound pressure level of the target noise and the first threshold. Using the difference as the base and the growth exponent minus one as the exponent, perform a power operation to obtain the first power term. Using the first interval as the base and the growth exponent as the exponent, perform a power operation to obtain the second power term. Multiply the first power term by the second interval and divide by the second power term to obtain the dynamic adjustment coefficient, wherein the growth exponent is greater than 0 and less than 1. The calculation formula is as follows: ; in, Regarding sound pressure level The dynamic adjustment coefficient, This is a growth index.

[0039] ⑤ Multiply the difference between the sound pressure level of the target noise and the first threshold by the dynamic adjustment coefficient, and then add it to the first fixed volume compensation amount to obtain the nonlinear volume compensation amount; the calculation formula is as follows: ; in, This is a non-linear volume compensation amount.

[0040] Through the above methods, the dynamic adjustment coefficient is no longer constant, but rather it adapts and decays in real time according to the ambient noise intensity. The greater the noise, the slower the dynamic adjustment coefficient increases, and the smoother the volume rises.

[0041] In this embodiment, the first threshold 45dB, second threshold The value is 65dB, the first fixed volume compensation A is 10dB, the second fixed volume compensation B is 20dB, and the growth index is... Therefore, taking 0.3 as an example, the formula for calculating the nonlinear volume compensation amount can be expressed as: .

[0042] S323, Determination of target volume at high noise levels.

[0043] In high-noise environments, the second fixed volume compensation amount B is set to 20dB to increase the effective output of the robot's sound in such environments. In addition, a maximum volume threshold needs to be preset, which is set to 75dB in this embodiment. That is, when the target volume after compensation of 20dB exceeds 75dB, the volume will be forcibly locked at 75dB to avoid the problem of the volume increasing indefinitely in high-noise environments, causing harshness and ear damage.

[0044] In one preferred embodiment, the gain of mid-to-high frequency timbre can also be optimized simultaneously to improve the penetration and recognizability of sound effects and human voice broadcasts in noisy environments.

[0045] S4, adjust the robot's output volume to the target volume.

[0046] This embodiment also provides a robot volume adaptive adjustment device, such as... Figure 2 As shown, the device includes: Noise Acquisition and Separation Module: Used to acquire the ambient noise of the robot's current environment, and extract and separate the robot's own noise from the ambient noise to obtain the target noise; Target volume determination module: used to determine the noise level based on the target noise and determine the target volume based on the noise level. If the noise level is a first noise level, the target volume is set to the sum of the current volume and a first fixed volume compensation amount; if it is a second noise level, the target volume is set to the sum of the current volume and a non-linear volume compensation amount, wherein the non-linear volume compensation amount is determined based on a dynamic adjustment coefficient, and the dynamic adjustment coefficient is negatively correlated with the intensity of the target noise; if it is a third noise level, the target volume is set to the smaller value between the sum of the current volume and the second fixed volume compensation amount and a preset maximum volume threshold. Adjustment module: Used to adjust the robot's output volume to the target volume.

[0047] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the described module can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0048] The present invention also provides a computer-readable storage medium storing a computer program that can be used to execute the above-described... Figure 1 A method for adaptive volume adjustment in robots is provided.

[0049] The present invention also provides Figure 3 One of the corresponding Figure 1 A schematic diagram of the electronic device used in the method. (e.g.) Figure 3At the hardware level, the electronic device includes a processor, internal bus, network interface, memory, and non-volatile memory, and may also include other hardware required for the business operations. The processor reads the corresponding computer program from the non-volatile memory into memory and then runs it to achieve the above-mentioned functions. Figure 1 The data acquisition method described above. Of course, in addition to software implementation, this invention does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. That is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0050] Improvements in a technology can be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many improvements to the methodology can now be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that an improvement in methodology cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program and "integrate" a digital system onto a PLD themselves, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must also be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0051] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0052] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0053] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0054] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1The steps of the function specified in one or more boxes.

[0055] The preferred embodiments of the present invention have been described in detail above. It should be understood that those skilled in the art can make numerous modifications and variations based on the concept of the present invention without creative effort. Therefore, all technical solutions that can be obtained by those skilled in the art based on the concept of the present invention through logical analysis, reasoning, or limited experimentation on the basis of existing technology should be within the scope of protection defined by the claims.

Claims

1. A method for adaptive volume adjustment in a robot, characterized in that, The method includes the following steps: Obtain the ambient noise of the robot's current environment; The robot's own noise is extracted and separated from the environmental noise to obtain the target noise; Based on the target noise, the noise level is determined. If the noise level is the first noise level, the target volume is set to the sum of the current volume and the first fixed volume compensation amount. If the noise level is the second noise level, the target volume is set to the sum of the current volume and the nonlinear volume compensation amount, wherein the nonlinear volume compensation amount is determined based on a dynamic adjustment coefficient, and the dynamic adjustment coefficient is negatively correlated with the intensity of the target noise. If the noise level is the third noise level, the target volume is set to the smaller value between the sum of the current volume and the second fixed volume compensation amount and the preset maximum volume threshold. Adjust the robot's output volume to the target volume.

2. The robot volume adaptive adjustment method according to claim 1, characterized in that, The robot's own noise is extracted and separated from the environmental noise to obtain the target noise, including: Obtain the robot's current motion state parameters, which include at least one of motor speed, joint torque, and walking gait. Based on the motion state parameters, the pre-built robot self-noise feature database is queried to determine the spectral characteristics of the current robot self-noise; An adaptive filtering algorithm is used to filter out the spectral characteristics of the self-noise from the environmental noise, retaining the remaining frequency band as the target noise.

3. The robot volume adaptive adjustment method according to claim 1, characterized in that, The noise level is determined based on the target noise as follows: Calculate the sound pressure level of the target noise; Based on the sound pressure level, the noise level corresponding to the target noise is determined according to a preset noise classification strategy: when the sound pressure level is less than or equal to the first threshold, it is determined to be the first noise level; When the sound pressure level is greater than or equal to the second threshold, it is determined to be the third noise level; otherwise, it is determined to be the second noise level.

4. The robot volume adaptive adjustment method according to claim 3, characterized in that, The method for determining the nonlinear volume compensation amount is as follows: The intensity of the target noise is expressed in terms of sound pressure level, and the current sound pressure level of the target noise is calculated. Calculate the difference between the second threshold and the first threshold to obtain the first interval; Calculate the difference between the second fixed volume compensation amount and the first fixed volume compensation amount to obtain the second interval; The difference between the current sound pressure level of the target noise and the first threshold is calculated. Using the difference as the base and the growth exponent minus one as the exponent, a power operation is performed to obtain the first power term. Using the first interval as the base and the growth exponent as the exponent, a power operation is performed to obtain the second power term. The first power term is multiplied by the second interval and divided by the second power term to obtain the dynamic adjustment coefficient, wherein the growth exponent is greater than 0 and less than 1. The difference between the sound pressure level of the target noise and the first threshold is multiplied by the dynamic adjustment coefficient and then added to the first fixed volume compensation amount to obtain the nonlinear volume compensation amount.

5. A robot volume adaptive adjustment device, characterized in that, The device includes: Noise Acquisition and Separation Module: Used to acquire the ambient noise of the robot's current environment, and extract and separate the robot's own noise from the ambient noise to obtain the target noise; Target volume determination module: used to determine the noise level based on the target noise and determine the target volume based on the noise level. If the noise level is a first noise level, the target volume is set to the sum of the current volume and a first fixed volume compensation amount; if it is a second noise level, the target volume is set to the sum of the current volume and a non-linear volume compensation amount, wherein the non-linear volume compensation amount is determined based on a dynamic adjustment coefficient, and the dynamic adjustment coefficient is negatively correlated with the intensity of the target noise; if it is a third noise level, the target volume is set to the smaller value between the sum of the current volume and the second fixed volume compensation amount and a preset maximum volume threshold. Adjustment module: Used to adjust the robot's output volume to the target volume.

6. The robot volume adaptive adjustment device according to claim 5, characterized in that, The robot's own noise is extracted and separated from the environmental noise to obtain the target noise, including: Obtain the robot's current motion state parameters, which include at least one of motor speed, joint torque, and walking gait. Based on the motion state parameters, the pre-built robot self-noise feature database is queried to determine the spectral characteristics of the current robot self-noise; An adaptive filtering algorithm is used to filter out the spectral characteristics of the self-noise from the environmental noise, retaining the remaining frequency band as the target noise.

7. The robot volume adaptive adjustment device according to claim 5, characterized in that, The noise level is determined based on the target noise as follows: Calculate the sound pressure level of the target noise; Based on the sound pressure level, the noise level corresponding to the target noise is determined according to a preset noise classification strategy: when the sound pressure level is less than or equal to the first threshold, it is determined to be the first noise level; When the sound pressure level is greater than or equal to the second threshold, it is determined to be the third noise level; otherwise, it is determined to be the second noise level.

8. The robot volume adaptive adjustment device according to claim 7, characterized in that, The method for determining the nonlinear volume compensation amount is as follows: The intensity of the target noise is expressed in terms of sound pressure level, and the current sound pressure level of the target noise is calculated. Calculate the difference between the second threshold and the first threshold to obtain the first interval; Calculate the difference between the second fixed volume compensation amount and the first fixed volume compensation amount to obtain the second interval; The difference between the current sound pressure level of the target noise and the first threshold is calculated. Using the difference as the base and the growth exponent minus one as the exponent, a power operation is performed to obtain the first power term. Using the first interval as the base and the growth exponent as the exponent, a power operation is performed to obtain the second power term. The first power term is multiplied by the second interval and divided by the second power term to obtain the dynamic adjustment coefficient, wherein the growth exponent is greater than 0 and less than 1. The difference between the sound pressure level of the target noise and the first threshold is multiplied by the dynamic adjustment coefficient and then added to the first fixed volume compensation amount to obtain the nonlinear volume compensation amount.

9. An electronic device, characterized in that, The system includes a memory and one or more processors, wherein the memory stores executable code, and the one or more processors execute the executable code to implement the robot volume adaptive adjustment method according to any one of claims 1-4.

10. A computer-readable storage medium, characterized in that, It stores a program that, when executed by a processor, implements the robot volume adaptive adjustment method according to any one of claims 1-4.

Images