Sensor data processing method, robot control method and device

Abstract

The invention provides a sensor data processing method, a robot control method, a sensor data processing device and a computer storage medium. The sensor data processing method comprises the following steps: determining self-adaptive environment compensation parameters of original sensor data according to environment data; determining an adaptive time compensation parameter of the original sensor data according to the sensor speed; obtaining a dynamic compensation parameter of the original sensor by using the self-adaptive environment compensation parameter and the self-adaptive time compensation parameter; performing dynamic compensation on the corresponding original sensor data according to the dynamic compensation parameters of the original sensor data; and the multiple pieces of original sensor data after dynamic compensation are fused, and fused sensor data used for analyzing the information of the environment where the robot is located are obtained. Through the sensor data processing method, self-adaptive dynamic preprocessing of the sensor data by using the environment data and the motion data is realized, so that the sensor data is calibrated, and the accuracy of the sensor data is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a sensor data processing method, a robot control method, a sensor data processing device, and a computer storage medium. Background Art

[0002] The automated control of a robot mainly relies on the collection of environmental information by the onboard sensors. The accuracy of the information collected by the sensors determines the precision and stability of the robot's control.

[0003] However, environmental factors and motion drift can cause the accuracy of sensors to decrease. Current sensor data processing algorithms use fixed parameters and fixed processes to complete preprocessing tasks during the preprocessing stage, and calibrate and compensate sensor data during the preprocessing stage. As a result, subsequent sensor data application scenarios cannot provide accurate environmental conditions. Summary of the Invention

[0004] To solve the above technical problems, the present application proposes a sensor data processing method, a robot control method, a sensor data processing device and a computer storage medium.

[0005] To solve the above technical problems, the present application proposes a sensor data processing method, which is applied to a robot provided with at least two sensors for collecting sensor data. The sensor data processing method comprises: Acquire a plurality of raw sensor data, environmental data when the raw sensor data is collected, and the speed of each sensor; determining, based on the environmental data, adaptive environmental compensation parameters for the raw sensor data; determining an adaptive time compensation parameter for the raw sensor data based on the sensor speed; Acquire dynamic compensation parameters of the original sensor using the adaptive environment compensation parameters and the adaptive time compensation parameters; Dynamically compensating the corresponding raw sensor data according to the dynamic compensation parameters of each raw sensor data; The dynamic compensated raw sensor data are fused to obtain fused sensor data for analyzing the environment information of the robot.

[0006] Wherein, the environmental data includes temperature data; Determining the adaptive environmental compensation parameters of the raw sensor data according to the environmental data includes: Obtaining the standard temperature when calibrating the sensor; Acquire a real-time temperature parameter based on the difference between the real-time temperature of the original sensor data collected by the sensor and the standard temperature, and a temperature sensitivity coefficient; The basic temperature compensation coefficient is compensated according to the real-time temperature parameter to determine the adaptive environmental compensation parameter of the original sensor data.

[0007] The step of determining the adaptive time compensation parameter of the raw sensor data according to the sensor speed includes: Get the basic time constant and speed influence coefficient; An adaptive time compensation parameter of the raw sensor data is determined according to the sensor speed, the basic time constant, and the speed influence coefficient.

[0008] The step of obtaining the dynamic compensation parameter of the original sensor by using the adaptive environment compensation parameter and the adaptive time compensation parameter includes: Generate a temperature mutation interference suppression parameter based on the real-time temperature change rate and temperature mutation suppression coefficient of the robot's environment; The dynamic compensation parameter of the original sensor is acquired by using the temperature mutation interference suppression parameter, the adaptive environment compensation parameter and the adaptive time compensation parameter.

[0009] Before fusing the plurality of dynamically compensated raw sensor data, the sensor data processing method further includes: generating a dynamic sliding window according to the environmental data and the sensor speed; Data synchronization is performed on the plurality of raw sensor data according to the dynamic sliding window, and aligned sensor data of each raw sensor data is extracted.

[0010] The step of generating a dynamic sliding window according to the environmental data and the sensor speed includes: extracting scalar parameters of multidimensional environmental features from the environmental data; generating a dynamic sliding window influencing parameter according to a ratio of the sensor speed to the maximum speed and the scalar parameter; The dynamic sliding window is adaptively adjusted on the static reference sliding window using the dynamic sliding window influencing parameter to generate the dynamic sliding window.

[0011] Wherein, the multi-dimensional environmental characteristics include temperature characteristics, light characteristics, and / or humidity characteristics; The step of extracting scalar parameters of multi-dimensional environmental features from the environmental data includes: Converting the multidimensional environmental features in the environmental data into standard unit features respectively; The numerical value of the standard unit feature is extracted and determined as a scalar parameter corresponding to the environmental feature.

[0012] To solve the above technical problems, the present application also proposes a robot control method, which includes: Collecting a plurality of raw sensor data, and processing the raw sensor data using the above-mentioned sensor data processing method to obtain fused sensor data; Detecting obstacle information in the direction of travel of the robot based on the fused sensor data; Execute obstacle avoidance or braking actions according to the obstacle information.

[0013] In order to solve the above technical problems, the present application also proposes a sensor data processing device, which includes a memory and a processor coupled to the memory; wherein the memory is used to store program data, and the processor is used to execute the program data to implement the sensor data processing method and / or robot control method as described above.

[0014] In order to solve the above technical problems, the present application also proposes a computer storage medium, which is used to store program data. When the program data is executed by a computer, it is used to implement the above-mentioned sensor data processing method and / or robot control method.

[0015] Compared with the prior art, the beneficial effects of the present application are as follows: the sensor data processing device acquires a number of raw sensor data, the environmental data when the raw sensor data was collected, and the speed of each sensor; based on the environmental data, the adaptive environmental compensation parameters of the raw sensor data are determined; based on the sensor speed, the adaptive time compensation parameters of the raw sensor data are determined; the dynamic compensation parameters of the raw sensor are acquired using the adaptive environmental compensation parameters and the adaptive time compensation parameters; the corresponding raw sensor data are dynamically compensated based on the dynamic compensation parameters of each raw sensor data; the raw sensor data after dynamic compensation are fused to obtain fused sensor data for analyzing the environmental information of the robot. Through the above-mentioned sensor data processing method, adaptive dynamic preprocessing of sensor data using environmental data and motion data is achieved, so that the sensor data can be calibrated and the accuracy of the sensor data can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without inventive efforts. Among them: Figure 1 This is a flow chart of an embodiment of a sensor data processing method provided by the present application; Figure 2 is a flow chart of another embodiment of the sensor data processing method provided by the present application; Figure 3 This is a flow chart of an embodiment of a robot control method provided by the present application; Figure 4 This is a flow chart of the robot control logic provided by this application; Figure 5 It is a structural diagram of an embodiment of a sensor data processing device provided by the present application; Figure 6 It is a structural diagram of an embodiment of a computer storage medium provided by this application. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0018] The terms "first," "second," "third," "fourth," and the like (if any) in the specification and claims of this application and in the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of the application described herein can, for example, be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not necessarily limited to those steps or elements explicitly listed, but may include other steps or elements not explicitly listed or inherent to such process, method, product, or apparatus.

[0019] Please refer to the following for details: Figure 1 , Figure 1 It is a flow chart of an embodiment of a sensor data processing method provided by this application.

[0020] The sensor data processing method of the present application is applied to a sensor data processing device, wherein the sensor data processing device of the present application can be a server, a terminal device, or a system comprising a server and a terminal device. Accordingly, the various components of the sensor data processing device, such as the various units, subunits, modules, and submodules, can be all disposed in the server, all disposed in the terminal device, or disposed separately in the server and the terminal device.

[0021] Furthermore, the server described above may be either hardware or software. When the server is hardware, it may be implemented as a distributed server cluster consisting of multiple servers, or as a single server. When the server is software, it may be implemented as multiple software programs or software modules, such as software or software modules for providing a distributed server, or as a single software program or software module, without further limitation.

[0022] The sensor data processing device may be a processor or processing unit mounted on a robot, such as a wheeled robot, and is used to process sensor data collected by multiple sensors mounted on the robot.

[0023] like Figure 1 As shown, the specific steps are as follows: Step S11: Acquire a number of raw sensor data, the environmental data when the raw sensor data is collected, and the speed of each sensor.

[0024] In an embodiment of the present application, a sensor data processing device establishes a unified time base for multiple sensors, thereby ensuring synchronization of timestamps for multiple raw sensor data. The multiple sensors can be of a single type or multiple types. The sensor types provided in this application include, but are not limited to, visual sensors, distance measurement sensors, and environmental parameter sensors.

[0025] In a specific implementation, the sensor may be a ToF (Time of Flight) camera and a millimeter wave radar.

[0026] Environmental data during raw sensor data collection can be collected through onboard environmental sensors, including but not limited to: temperature and humidity sensors, air pressure sensors, light sensors, etc.

[0027] Sensor speed can be measured directly through motor encoders or Doppler radar, or calculated indirectly through acceleration integration or GPS (Global Positioning System) data.

[0028] Step S12: Determine adaptive environmental compensation parameters of the original sensor data according to the environmental data.

[0029] In the embodiments of the present application, environmental compensation of sensor data is a key technology for improving measurement accuracy. The present application establishes a compensation model and adjusts parameters in real time by analyzing the impact of environmental factors on sensor output.

[0030] Different environmental data have different effects on different types of sensor data. Therefore, the sensor data processing device can select environmental factors with the greatest impact based on the type of sensors currently onboard the robot. For example, temperature affects most sensors (such as IMUs and pressure sensors); humidity affects capacitive sensors and some optical sensors; air pressure affects altitude measurement and gas sensors; electromagnetic interference affects magnetometers and Hall sensors; and mechanical vibration affects high-precision inertial sensors.

[0031] Specifically, the sensor data processing device can establish an environment-error model based on the standard values of various environmental factors and the data values under the standard environmental factors, and use it to input real-time environmental factors to analyze the error value between the current sensor data and the standard sensor data, thereby compensating the original sensor data.

[0032] In a specific embodiment, taking the environmental factor as the temperature factor as an example, the dynamic temperature-time compensation logic for ToF data is as follows: The sensor data processing device obtains the standard temperature T_ref during sensor calibration; obtains the real-time temperature parameter β*(T-T_ref) based on the difference between the real-time temperature T of the raw sensor data collected by the sensor and the standard temperature T_ref, as well as the temperature sensitivity coefficient β; compensates the basic temperature compensation coefficient k_base based on the real-time temperature parameter β*(T-T_ref) to determine the adaptive environmental compensation parameter k1(T) of the raw sensor data.

[0033] The above process is expressed by the formula: k1(T)=k_base+β*(T-T_ref) Where k1(T) is the temperature-dependent compensation coefficient, which adjusts with temperature; k_base is the base temperature compensation coefficient (fixed value at the reference temperature); β is the temperature sensitivity coefficient, which controls the slope of the compensation amount as it changes with temperature; and T_ref is the reference temperature (the standard temperature during calibration, such as 25°C).

[0034] Step S13: Determine adaptive time compensation parameters of the raw sensor data according to the sensor speed.

[0035] In an embodiment of the present application, the sensor may produce time-related errors when in motion, especially when the sensor moves at high speed or experiences severe acceleration. Therefore, the present application also requires motion compensation of the original sensor data based on the motion information.

[0036] For example, the compensation principle for lidar sensor data is as follows: calculate the precise emission time corresponding to each laser point; perform motion compensation based on the sensor posture at that moment; perform inverse kinematic transformation on the point cloud to eliminate the smear effect; and consider the influence of the angular acceleration of the scanning mechanism.

[0037] In one embodiment, the dynamic-time compensation logic for ToF data is as follows: The sensor data processing device obtains a basic time constant and a speed influence coefficient; and determines an adaptive time compensation parameter τ of the original sensor data according to the sensor speed v, the basic time constant τ0, and the speed influence coefficient γ.

[0038] The above process is expressed by the formula: τ=τ0+γ*v Among them, τ is the dynamic time constant, which determines the decay rate of historical data; τ0 is the basic time constant (the default value in static scenarios); γ is the speed influence coefficient, which controls the sensitivity of the time constant to speed changes; v is the target movement speed.

[0039] Step S14: using the adaptive environment compensation parameters and the adaptive time compensation parameters, the dynamic compensation parameters of the original sensor are obtained.

[0040] In the embodiments of this application, the process of obtaining dynamic compensation parameters based on environmental and time compensation parameters is essentially a systematic project involving multi-dimensional sensor error modeling and fusion compensation. The core concept is to establish a complete mathematical model of sensor error, organically integrating various compensation parameters to achieve precise correction of the original measurement data.

[0041] In a specific embodiment, the sensor data processing device determines the dynamic compensation parameter for the original sensor data based on the adaptive environment compensation parameter k1(T) and the adaptive time compensation parameter τ generated in the above steps. The formula is: 1+k1(T)*e^(-d / τ) In another specific embodiment, when determining the dynamic compensation parameters for the original sensor data, the sensor data processing device can also introduce a temperature mutation interference suppression parameter generated according to the real-time temperature change rate of the robot's environment and the temperature mutation suppression coefficient. The formula is expressed as: 1+k1(T)*e^(-d / τ)+α*ΔT / Δt.

[0042] Where α is the temperature mutation suppression coefficient, which suppresses the noise introduced by rapid temperature changes; ΔT / Δt is the temperature change rate (the rate of change of the current temperature relative to the previous moment).

[0043] Step S15: dynamically compensate the corresponding raw sensor data according to the dynamic compensation parameters of each raw sensor data.

[0044] In the embodiment of the present application, the sensor data processing device uses the dynamic compensation parameter determined in step S14 to dynamically compensate each raw sensor data, and the formula is expressed as follows: D_corrected=D_raw×[1+k1(T)*e^(-d / τ)+α*ΔT / Δt] Where D_raw is the raw measurement data (such as the direct output value of the sensor).

[0045] Step S16: Fusing the dynamic compensated raw sensor data to obtain fused sensor data for analyzing the robot's environmental information.

[0046] In the embodiment of the present application, the sensor data processing device fuses the raw sensor data collected by multiple sensors in order to combine the information collected by multiple sensors. The characteristic fusion mechanism is as follows: F_fused=Σ(π_i*F_i),π_i=e^(w_i^T*C_env) / Σe^(w_j^T*C_env) Among them, ‌F_fused‌ is the final fused feature vector, which integrates the feature information of ToF and radar; ‌π_i‌ is the weight coefficient of the ith feature; ‌F_i‌ is the feature vector of the ith sensor; ‌π_i‌ is the dynamic weight coefficient; ‌w_i‌ is the learnable weight vector; ‌Σe^(w_j^T*C_env)‌ is the normalization term, which ensures that the sum of all weight coefficients π_i is 1. ‌

[0047] In the present application, a sensor data processing device acquires a number of raw sensor data, environmental data when the raw sensor data was collected, and the speed of each sensor; determines adaptive environmental compensation parameters for the raw sensor data based on the environmental data; determines adaptive time compensation parameters for the raw sensor data based on the sensor speed; obtains dynamic compensation parameters for the raw sensors using the adaptive environmental compensation parameters and the adaptive time compensation parameters; dynamically compensates the corresponding raw sensor data based on the dynamic compensation parameters of each raw sensor data; and fuses the dynamically compensated raw sensor data to obtain fused sensor data for analyzing the robot's environmental information. The above-mentioned sensor data processing method achieves adaptive dynamic preprocessing of sensor data using environmental data and motion data, thereby calibrating the sensor data and improving the accuracy of the sensor data.

[0048] Furthermore, since this application needs to fuse raw sensor data from different sources, it is necessary to eliminate the asynchrony and delay of sensor data in advance and dynamically adapt to the data change rate. This application adopts dynamic sliding window processing before fusing multiple sensor data. For details, please refer to Figure 2 , Figure 2 This is a flow chart of another embodiment of the sensor data processing method provided by the present application.

[0049] like Figure 2 As shown, the specific steps are as follows: Step S21: Generate a dynamic sliding window based on environmental data and sensor speed.

[0050] In the embodiment of the present application, the sensor data processing device dynamically adjusts the size of the sliding window. Its core function is to adaptively balance the response speed and stability of data fusion according to environmental characteristics and target speed.

[0051] Specifically, the sensor data processing device extracts scalar parameters of multidimensional environmental features from the environmental data. Specifically, the sensor data processing device converts the multidimensional environmental features, including temperature, illumination, pressure, and temperature, into standard unit features. The standard units for each environmental feature can refer to national or industry standard units. The sensor data processing device then extracts the values of the standard unit features as scalar parameters of the environmental features, thereby unifying the multidimensional environmental features into a single scalar space for fusion.

[0052] The sensor data processing device generates a dynamic sliding window influence parameter C_env*(1+v_obj / v_max) based on the ratio of the sensor speed to the maximum speed v_obj / v_max and the scalar parameter ‌C_env. Then, the dynamic sliding window influence parameter is used to adaptively adjust the static reference sliding window S_static to generate the dynamic sliding window size. The formula is expressed as: size =clamp((η*S_static) / (C_env*(1+v_obj / v_max))) Among them, S_static is the static reference window size (the default value when the environment is stable and the target is stationary); C_env is the environmental characteristic coefficient, which integrates interference factors such as temperature, humidity, and light (a larger value indicates a worse environment); v_obj is the target motion speed (which may be the sensor's own speed or the observed target speed, and needs to be combined with the context); v_max is the maximum target speed supported by the system (used to normalize v_obj to prevent speed from affecting the overload); η is the adjustment factor, which controls the combined influence of the environment and speed on the window size; clamp() is a limiting function that ensures that size is within the preset range (such as [0.5*S_static, 2*S_static]).

[0053] Step S22: performing data synchronization on a plurality of raw sensor data according to the dynamic sliding window, and extracting aligned sensor data of each raw sensor data.

[0054] In the embodiment of the present application, the sensor data processing device synchronizes the pre-processed raw sensor data according to the dynamic sliding window determined in step S21, and completes the sensor data interception and alignment within the sliding window.

[0055] The sensor data processing results in the above embodiment can be applied to the control process of the robot. For details, please refer to Figure 3 and Figure 4 , Figure 3 This is a flow chart of an embodiment of the robot control method provided by this application. Figure 4 It is a flow chart of the robot control logic provided by this application.

[0056] The robot in the embodiments of this application is described using a wheeled robot as an example. Wheeled robots are the most common type of mobile robot due to their simple and efficient structure. Currently, small wheeled robots are widely used in various scenarios, and charging stations are a typical use case. Improving their intelligence can bring convenience to users.

[0057] like Figure 3 As shown, the specific steps are as follows: Step S31: collecting a number of raw sensor data, and processing the raw sensor data using a sensor data processing method to obtain fused sensor data.

[0058] Step S32: Detect obstacle information in the robot's moving direction based on the fused sensor data.

[0059] In an embodiment of the present application, the application layer initiates a charging pile request to the robot: the software verifies the legitimacy and prioritizes the received requests to ensure that only valid requests that comply with the current device status are processed.

[0060] The robot turns on obstacle detection. The program activates the ToF camera sensor and radar for obstacle detection, establishes a sensor data frame buffer, and uses a time sliding window to calculate whether there are obstacles in the recent period of time. At the same time, this application uses multi-sensor data fusion technology to calibrate and compensate the ToF camera and radar data in real time to improve detection accuracy. For more information about multi-sensor data fusion technology, please refer to the sensor data processing method described above, which will not be repeated here.

[0061] Step S33: Execute obstacle avoidance or braking action according to the obstacle information.

[0062] In this embodiment, the robot determines whether an obstacle exists based on fused sensor data. If no obstacle exists, the robot proceeds to the next control step. Based on sensor data and a preset safety distance threshold, the robot system uses an algorithmic logic to determine whether there are obstacles in the current environment that could affect the operation of the charging station.

[0063] If the result is that there is no obstacle, the system will generate a safety confirmation signal as the basis for subsequent actions. The program will record the relevant data of this detection for subsequent fault diagnosis and optimization.

[0064] For example, the robot's subsequent action could be to descend from a charging station. Specifically, if no obstacle is detected, the program will execute the descending action, with real-time obstacle detection still enabled. During this execution, high-precision speed-based motor control is used to ensure a smooth and accurate descent of the charging station.

[0065] If there is an obstacle, the system will directly enter the "obstacle exists, do not execute the charging pile action" state. At this time, the program will send the alarm information to the user through the visual interface or communication interface.

[0066] Please continue reading Figure 4If the target distance is not reached, such as when the robot stops midway due to an obstacle, the actual distance traveled is calculated. The system uses position feedback devices such as encoders to accurately calculate the descent distance of the charging station in real time and compares it with the preset target distance. If the target distance is not reached, the motor control parameters are adjusted based on the difference between the actual and target distances, and the descent continues until the target distance is reached or other termination conditions are triggered. Simultaneously, the system analyzes changes in resistance during descent to predict possible obstacles or other abnormalities. Finally, the robot enters the "Failed to Descent to Charging Station" state. The program will return a specific error message based on the actual situation.

[0067] If the target distance is reached, the system enters the "Charging Pile Down Successful" state. Specifically, if all conditions are met and no obstacles are encountered, the charging pile down operation is successfully completed. The system autonomously records the location after downhill access and calculates the base station location, and also supports updating this location through the interface. When recording the location, high-precision positioning technology is used. At the same time, the program automatically calculates the location information of the charging pile based on the algorithm using the location information after downhill access and stores it on the device, providing support for subsequent automatic navigation for recharging. In addition, the interface protocol allows users or external systems to update and query the charging pile location information, improving flexibility and scalability.

[0068] Those skilled in the art will understand that in the above method of the specific implementation method, the writing order of each step does not mean a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0069] In order to implement the above-mentioned sensor data processing method and / or robot control method, this application also proposes a sensor data processing device, which can be found in Figure 5 , Figure 5 It is a structural diagram of an embodiment of a sensor data processing device provided by this application.

[0070] The sensor data processing device 400 of this embodiment includes a processor 41 , a memory 42 , an input / output device 43 , and a bus 44 .

[0071] The processor 41 , memory 42 , and input / output device 43 are respectively connected to a bus 44 . The memory 42 stores program data, and the processor 41 is used to execute the program data to implement the sensor data processing method and / or robot control method of the above embodiment.

[0072] In the embodiments of the present application, the processor 41 may also be referred to as a CPU (Central Processing Unit). The processor 41 may be an integrated circuit chip with signal processing capabilities. The processor 41 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component. A general-purpose processor may be a microprocessor, or the processor 41 may be any conventional processor.

[0073] This application also provides a computer storage medium, please continue to refer to Figure 6 , Figure 6 It is a structural diagram of an embodiment of a computer storage medium provided in the present application. The computer storage medium 600 stores a computer program 61. When the computer program 61 is executed by the processor, it is used to implement the sensor data processing method and / or robot control method of the above-mentioned embodiment.

[0074] When the embodiments of the present application are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, 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. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0075] The above description is only an implementation method of the present application and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the description and drawings of this application, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A sensor data processing method, characterized in that: The sensor data processing method is applied to a robot, wherein the robot is provided with at least two sensors for collecting sensor data; The sensor data processing method comprises: Acquire a plurality of raw sensor data, environmental data when the raw sensor data is collected, and the speed of each sensor; determining, based on the environmental data, adaptive environmental compensation parameters for the raw sensor data; determining an adaptive time compensation parameter for the raw sensor data based on the sensor speed; Acquire dynamic compensation parameters of the original sensor using the adaptive environment compensation parameters and the adaptive time compensation parameters; Dynamically compensating the corresponding raw sensor data according to the dynamic compensation parameters of each raw sensor data; The dynamic compensated raw sensor data are fused to obtain fused sensor data for analyzing the environment information of the robot.

2. The sensor data processing method according to claim 1, It is characterized in that Wherein, the environmental data includes temperature data; Determining the adaptive environmental compensation parameters of the raw sensor data according to the environmental data includes: Obtaining the standard temperature when calibrating the sensor; Acquire a real-time temperature parameter based on the difference between the real-time temperature of the original sensor data collected by the sensor and the standard temperature, and a temperature sensitivity coefficient; The basic temperature compensation coefficient is compensated according to the real-time temperature parameter to determine the adaptive environmental compensation parameter of the original sensor data.

3. The sensor data processing method according to claim 1, wherein: Determining an adaptive time compensation parameter for the raw sensor data based on the sensor speed includes: Get the basic time constant and speed influence coefficient; An adaptive time compensation parameter of the raw sensor data is determined according to the sensor speed, the basic time constant, and the speed influence coefficient.

4. The sensor data processing method according to claim 1, wherein: The step of obtaining the dynamic compensation parameter of the original sensor by using the adaptive environment compensation parameter and the adaptive time compensation parameter includes: Generate a temperature mutation interference suppression parameter based on the real-time temperature change rate and temperature mutation suppression coefficient of the robot's environment; The dynamic compensation parameter of the original sensor is acquired by using the temperature mutation interference suppression parameter, the adaptive environment compensation parameter and the adaptive time compensation parameter.

5. The sensor data processing method according to claim 1, wherein: Before fusing the plurality of dynamically compensated raw sensor data, the sensor data processing method further includes: generating a dynamic sliding window according to the environmental data and the sensor speed; Data synchronization is performed on the plurality of raw sensor data according to the dynamic sliding window, and aligned sensor data of each raw sensor data is extracted.

6. The sensor data processing method according to claim 5, characterized in that: Generating a dynamic sliding window according to the environmental data and the sensor speed includes: extracting scalar parameters of multidimensional environmental features from the environmental data; generating a dynamic sliding window influencing parameter according to a ratio of the sensor speed to the maximum speed and the scalar parameter; The dynamic sliding window is adaptively adjusted on the static reference sliding window using the dynamic sliding window influencing parameter to generate the dynamic sliding window.

7. The sensor data processing method according to claim 6, characterized in that: The multi-dimensional environmental characteristics include temperature characteristics, light characteristics, and / or humidity characteristics; The step of extracting scalar parameters of multi-dimensional environmental features from the environmental data includes: Converting the multidimensional environmental features in the environmental data into standard unit features respectively; The numerical value of the standard unit feature is extracted and determined as a scalar parameter corresponding to the environmental feature.

8. A robot control method, characterized in that: The robot control method comprises: Collecting a plurality of raw sensor data, and processing the plurality of raw sensor data by the sensor data processing method according to any one of claims 1 to 7 to obtain fused sensor data; Detecting obstacle information in the direction of travel of the robot based on the fused sensor data; Execute obstacle avoidance or braking actions according to the obstacle information.

9. A sensor data processing device, characterized in that: The sensor data processing device includes a memory and a processor coupled to the memory; The memory is used to store program data, and the processor is used to execute the program data to implement the sensor data processing method according to any one of claims 1 to 7, and / or the robot control method according to claim 8.

10. A computer storage medium, characterized in that The computer storage medium is used to store program data, and when the program data is executed by a computer, it is used to implement the sensor data processing method according to any one of claims 1 to 7 and / or the robot control method according to claim 8.

Images