Four-way shuttle vehicle based on ontology state perception and self-calibration positioning method and system thereof

Abstract

The invention relates to a four-way shuttle vehicle based on ontology state perception and a self-calibration positioning method of the four-way shuttle vehicle. The method comprises the following steps: establishing a body state sensing system, collecting three-axis acceleration, three-axis angular velocity, wheel set displacement and attitude angle data of a shuttle vehicle body, and synchronously forming a standardized sensing data set; performing fusion calculation on the standardized sensing data set to obtain real-time position and attitude parameters; calculating an initial value of a positioning error based on matching of the real-time position and attitude parameters with pre-stored high-precision track map data; according to the positioning error initial value, adaptive correction calculation is executed, a real-time positioning error correction amount is determined, and positioning information is corrected; parameters of a shuttle vehicle track control system are updated according to the corrected positioning information, and track navigation control is carried out; accumulated positioning error correction data are periodically analyzed, self-calibration model parameters are optimized, and positioning accuracy and stability are improved. According to the invention, the positioning reliability and path tracking capability of the four-way shuttle vehicle in a complex environment can be improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation equipment, and in particular to a four-way shuttle vehicle based on body state perception and a self-calibration positioning method thereof. Background Art

[0002] With the development of intelligent logistics and automated warehouses, four-way shuttles, as key equipment in material handling and intelligent warehousing, are widely used for material transportation and storage in complex spatial environments. However, existing four-way shuttles typically use navigation methods based on fixed paths or simple positioning algorithms. These systems lack high-precision real-time positioning and dynamic adaptability, resulting in positioning errors in complex environments, narrow passages, or scenarios with frequent turns, affecting navigation accuracy and operational efficiency.

[0003] In addition, existing technologies mostly use static compensation or manual parameter adjustment methods for positioning error correction and model optimization, and are unable to dynamically optimize model parameters according to environmental changes and operating conditions, resulting in a decrease in positioning accuracy during long-term system operation and a lack of self-learning and adaptive adjustment capabilities.

[0004] Therefore, there is an urgent need for a four-way shuttle positioning and navigation method with high-precision perception, real-time error correction and long-term adaptive optimization capabilities to improve the positioning accuracy and path tracking stability of the shuttle in complex environments and meet the actual needs of intelligent logistics and efficient warehousing. Summary of the Invention

[0005] The present invention provides a self-calibration and positioning method for a four-way shuttle based on body state perception, which includes:

[0006] Establish a body state perception system to collect the shuttle body's three-axis acceleration, three-axis angular velocity, wheel displacement and attitude angle data, and simultaneously form a standardized perception data set;

[0007] Perform fusion calculation on standardized perception data sets to obtain real-time position and attitude parameters;

[0008] Calculate the initial value of positioning error based on matching the real-time position and attitude parameters with the pre-stored high-precision trajectory map data;

[0009] Perform adaptive correction calculation based on the initial value of positioning error, determine the real-time positioning error correction amount and correct the positioning information;

[0010] Update the shuttle vehicle trajectory control system parameters based on the corrected positioning information and perform trajectory navigation control;

[0011] Periodically analyze the accumulated positioning error correction data, optimize the self-calibration model parameters, and improve positioning accuracy and stability.

[0012] The above-mentioned method for self-calibration and positioning of a four-way shuttle based on body state perception is constructed, wherein a body state perception system is established to collect the three-axis acceleration, three-axis angular velocity, wheel displacement and attitude angle data of the shuttle body, and simultaneously form a standardized perception data set, including:

[0013] Real-time collection of the shuttle's three-axis acceleration, three-axis angular velocity, wheel displacement, and attitude angle data;

[0014] The collected data is synchronized with the standard time to form a unified standardized perception data set.

[0015] The self-calibration and positioning method for a four-way shuttle based on body state perception as described above, wherein a fusion calculation is performed on a standardized perception data set to obtain real-time position and attitude parameters, including:

[0016] Perform multi-sensor fusion processing on standardized perception data sets to uniformly generate position and attitude information;

[0017] The position coordinates and attitude angle of the shuttle are calculated in real time based on the fused data.

[0018] The self-calibration positioning method for a four-way shuttle based on body state perception as described above, wherein the initial value of the positioning error is calculated based on matching the real-time position and posture parameters with pre-stored high-precision trajectory map data, includes:

[0019] Match the real-time position and attitude parameters with pre-stored high-precision trajectory map data;

[0020] The deviation between the real-time position and the pre-stored trajectory is calculated through spatial matching to generate the initial value of the positioning error.

[0021] The self-calibration positioning method for a four-way shuttle based on body state perception as described above, wherein adaptive correction calculation is performed based on an initial positioning error value, a real-time positioning error correction amount is determined, and positioning information is corrected, including:

[0022] Dynamically adjust the parameters of the error correction model using the initial value of the positioning error;

[0023] The error correction amount is calculated in real time through the correction model, and the real-time information of the shuttle position and posture is updated.

[0024] The self-calibration and positioning method for a four-way shuttle based on body state perception as described above, wherein the shuttle trajectory control system parameters are updated according to the corrected positioning information to perform trajectory navigation control, includes:

[0025] The corrected real-time position and attitude information is provided as input to the shuttle trajectory control system;

[0026] The control parameters are adjusted in real time based on the input information to ensure that the shuttle runs along the precise trajectory.

[0027] The self-calibration positioning method for a four-way shuttle based on body state perception described above, wherein the accumulated positioning error correction data is periodically analyzed to optimize the self-calibration model parameters to improve positioning accuracy and stability, includes:

[0028] Periodically transmit positioning error correction data to the central control unit;

[0029] The transmitted data is analyzed through big data analysis technology to determine the error distribution characteristics and optimize the self-calibration model parameters for the next cycle.

[0030] The present invention also provides a four-way shuttle self-calibration and positioning system based on body state perception, which includes:

[0031] The state perception module is used to collect the shuttle's three-axis acceleration, three-axis angular velocity, wheel displacement, and attitude angle data, and simultaneously form a standardized perception data set;

[0032] Data fusion module, used to perform fusion calculations on standardized perception data sets to obtain real-time position and attitude parameters;

[0033] Error matching module, used to match real-time position and attitude parameters with pre-stored high-precision trajectory map data to calculate the initial value of positioning error;

[0034] An adaptive correction module is used to perform adaptive correction calculations based on the initial value of the positioning error, determine the real-time positioning error correction amount, and correct the positioning information;

[0035] The trajectory control module is used to update the shuttle trajectory control system parameters according to the corrected positioning information and perform trajectory navigation control;

[0036] The central analysis module is used to periodically analyze the accumulated positioning error correction data, optimize the self-calibration model parameters through big data analysis, and improve positioning accuracy and stability.

[0037] The present invention achieves the following beneficial effects: By establishing a body state perception system, combined with multi-sensor fusion computing and adaptive error correction methods, it achieves high-precision positioning and stable path navigation for a four-way shuttle. By periodically analyzing positioning error data and optimizing self-calibration model parameters, the system's positioning accuracy and long-term stability are improved. This method effectively enhances the shuttle's positioning reliability and navigation accuracy in complex environments, possessing excellent adaptability and practicality, and is widely applicable in scenarios such as intelligent warehousing and logistics transportation. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments described in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0039] Figure 1 This is a flow chart of a self-calibration and positioning method for a four-way shuttle based on body state perception provided in Example 1 of the present application;

[0040] Figure 2 This is a schematic diagram of a four-way shuttle self-calibration and positioning system based on body state perception provided in Example 2 of the present application. DETAILED DESCRIPTION

[0041] The following is a clear and complete description of the technical solutions in the embodiments of the present invention, in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0042] Example 1

[0043] like Figure 1 As shown, the first embodiment of the present application provides a self-calibration and positioning method for a four-way shuttle based on body state perception, comprising the following steps:

[0044] Step S10: Establish a body state perception system to collect the three-axis acceleration, three-axis angular velocity, wheel displacement and attitude angle data of the shuttle body, and simultaneously form a standardized perception data set;

[0045] To capture the shuttle's key dynamic states, a multi-source fusion state perception system is required. This system, equipped with an inertial measurement unit (IMU), wheel encoders, and an attitude calculation module, continuously collects physical quantities such as the shuttle's acceleration, angular velocity, rolling displacement, and attitude angle in three-dimensional space. It then aligns the timestamps of different data channels based on a unified time reference, ultimately generating a standardized perception dataset with consistent structure and time sequence, which serves as the core input for subsequent positioning and control calculations.

[0046] It includes the following sub-steps:

[0047] Step S11: real-time acquisition of the three-axis acceleration, three-axis angular velocity, wheel displacement and attitude angle data of the shuttle body;

[0048] The system uses multiple types of sensors installed inside the shuttle to achieve high-frequency acquisition of its motion state. The three-axis acceleration value a output by the IMU x 、a y 、a z , used to describe the linear acceleration changes of the vehicle along the X, Y, and Z directions. Three-axis angular velocity ω x 、ω y 、ω z It is also provided by the gyroscope module in the IMU to reflect the rotation tendency of the vehicle around its own axis.

[0049] Wheel displacement data is collected by the left and right wheel encoders respectively, and d L and d R , to represent the rolling distance of the vehicle relative to the ground. The attitude angle information is output by the internal fusion solution module of the IMU, which are the roll angle θ r , pitch angle θ p and yaw angle θ y , which is used to describe the posture state of the shuttle in space.

[0050] All of the above data are accompanied by original timestamps generated by their respective sensors, and the system uniformly sets the sampling frequency to 100 Hz to ensure data continuity and time resolution.

[0051] Step S12: Perform standard time synchronization processing on the collected data to form a unified standardized perception data set.

[0052] Due to differences in triggering mechanisms and signal processing pathways among various sensors, directly collected data is often inconsistent across timelines. To ensure the accuracy of subsequent data fusion and positioning calculations, the system must align all sensor data to a unified time base, generating a standardized, time-synchronized dataset.

[0053] Specifically, the system uses the high-precision system clock inside the main control unit as the standard to construct a set of fixed-interval reference time point sequences {t1, t2, ..., t N}, each time point interval is, for example, 10 milliseconds. The asynchronously sampled data channel will be reconstructed through the interpolation algorithm to ensure that its value corresponds to each moment in the standard time series. Taking the wheel displacement data as an example, the system uses the linear interpolation method to estimate the target time point t i The displacement on: Among them, d(t i ) represents the target time point t i The estimated displacement value on d(t i-1 ) and d(t i+1) are the actual observation data of adjacent time points. Through the above method, each channel data has a one-to-one corresponding valid value at all standard time points. Finally, the system i Construct the complete state vector S on i , whose structure is: Arrange the data vectors of all time points in chronological order to form the standardized perception dataset D std ={S1,S2,…,S N}, this dataset serves as the input source for subsequent fusion calculations, providing data support with consistent timing and standardized structure for high-precision position and attitude estimation.

[0054] Step S20: performing fusion calculation on the standardized perception data set to obtain real-time position and posture parameters;

[0055] After completing the construction of the standardized perception data set, the system calculates the real-time position and posture parameters of the shuttle by fusing multi-source perception data, combining physical motion models and filtering algorithms, and achieves accurate analysis of the motion state.

[0056] It includes the following sub-steps:

[0057] Step S21: Perform multi-sensor fusion processing on the standardized perception data set to uniformly generate position and posture information;

[0058] This step uses an improved extended Kalman filter algorithm to recursively predict and update the vehicle's motion state by fusing acceleration, angular velocity, wheel displacement, and attitude angle data, thereby improving the accuracy and robustness of positioning and attitude estimation.

[0059] The system defines the state vector as: X = [xyzv x v y v z θ r θ p θ y ] T , where [xyz] represents the spatial position coordinates; [v x v y v z ] represents the velocity vector; [θ r θ p θ y ] represents the attitude angle. In order to eliminate the influence of different physical units, the system uses standardization to process each variable. The standardization formula is: Among them, x is the original physical quantity; μ x is the historical mean; σ x Variables with known value ranges can be processed by extreme value normalization.

[0060] Step S22: Calculate the position coordinates and posture angle of the shuttle in real time based on the fused data.

[0061] After multi-sensor fusion, the system uses the following dynamic position estimation formula to calculate the real-time position of the shuttle:

[0062] in, Represents the position vector at the current moment; is the position vector at the previous moment; is the velocity vector at the previous moment; Δt is the time interval of the current calculation cycle; is the three-axis acceleration vector at the current moment, provided by the IMU; is the rotation matrix obtained by calculating the attitude angle at the previous moment, which is used to convert the physical quantity in the body coordinate system to the geographic coordinate system; γ is the residual adjustment coefficient, which is dynamically calculated based on the historical residual mean and variance and is used to balance the weights of the model prediction and observation residuals; C k is the state covariance matrix at the current moment, describing the uncertainty of state estimation; is the inverse matrix of the state covariance, which is used to calculate the weighted influence of high confidence data; e k is the observation residual vector, which is calculated by the difference between the observed value and the predicted value and is used for error compensation; Φ(t) is the state transfer matrix, which describes the dynamic characteristics of the system state changing with time; Input function for nonlinear system, describing the control input (such as wheel speed, drive current) and attitude changes The nonlinear relationship between the integral term is expressed at t k-1 to t k The cumulative effect of control input and system state changes on position during the time period. The attitude angle is directly obtained from the fused state vector The position and attitude are extracted from the image and calculated through rotation matrix optimization to improve the accuracy and stability of attitude estimation. The final calculated position and attitude results provide key input for path planning, navigation control and adaptive calibration.

[0063] Step S30: Calculate the initial value of the positioning error based on matching the real-time position and attitude parameters with the pre-stored high-precision trajectory map data;

[0064] To improve the shuttle's positioning accuracy and path tracking capabilities, after calculating real-time position and attitude parameters, the system needs to accurately match the current state with a pre-stored high-precision trajectory map. By comprehensively analyzing factors such as spatial position deviation, attitude changes, and path curvature, the initial value of the positioning error is calculated, providing accurate basic data for subsequent adaptive correction and navigation control. This includes the following sub-steps:

[0065] Step S31, matching the position and posture parameters obtained in real time with pre-stored high-precision trajectory map data;

[0066] The system first calculates the real-time position vector of the shuttle and attitude angle vector A set of reference trajectory points covering the current driving area is extracted from the high-precision trajectory map. These reference points contain their spatial positions and corresponding attitude angle information.

[0067] To achieve optimal matching, the system comprehensively considers the proximity of spatial positions and the consistency of attitude angles, and constructs a unified cost function to evaluate the matching quality of each reference trajectory point. The matching cost function is calculated based on the Euclidean distance and attitude angle difference, and the expression is as follows: Among them, δ match Indicates the matching cost value, reflecting the comprehensive deviation between the current position and the reference trajectory point; and Represents the position vector and attitude angle vector of the reference trajectory point respectively. By calculating the cost value of each reference point one by one, the system selects the reference point with the smallest cost value as the final matching result to ensure the comprehensive optimal matching of spatial position and attitude angle; Represents the position vector at the current moment; represents the current attitude angle vector; λ represents the attitude deviation weight, which is set based on actual operating conditions to balance the matching priorities of position and attitude. Through this matching process, the system ensures that even in complex trajectory environments, it can quickly and accurately determine the reference point that best matches the current driving state, providing a reliable benchmark for subsequent deviation calculations.

[0068] Step S32: Calculate the deviation between the real-time position and the pre-stored trajectory through spatial matching to generate an initial value of the positioning error.

[0069] After the matching reference point is determined, the system calculates the initial positioning error at the current moment based on the matched spatial position and attitude angle information, combined with the shuttle's dynamic characteristics and trajectory curvature. Unlike traditional linear deviation calculation, this embodiment introduces nonlinear modulation and a curvature amplification factor, using mathematical models to improve the accuracy of error calculation and scene adaptability.

[0070] The specific calculation formula is as follows: Among them, δ p It represents the initial value of positioning error, which comprehensively reflects the influence of spatial position deviation, posture change and path curvature factors; is the position vector at the current moment; is the position vector of the reference trajectory point; is the Euclidean distance of spatial position deviation; is the attitude angle vector at the current moment; is the attitude angle vector of the reference trajectory point; is the Euler angle vector difference of the attitude angle difference; α is the nonlinear modulation coefficient of the position deviation, which controls the error amplification rate and ranges from 0.5 to 2.0; λ is the attitude deviation weight coefficient, which is used to adjust the influence of the attitude error on the overall deviation; μ is the path curvature adjustment coefficient, which is used to adjust the weight of the curvature factor in the deviation calculation; R is the path curvature radius of the matching reference point, calculated from the high-precision trajectory map; β is the path curvature influence index, which ranges from 1 to 3 and adjusts the influence of the amplified curvature on the error. The final calculated initial value of the positioning error fully considers the combined effects of spatial position change, attitude angle change, and path complexity, providing accurate and reliable input data for subsequent adaptive correction and navigation optimization.

[0071] Step S40: Perform adaptive correction calculation based on the initial value of the positioning error to determine the real-time positioning error correction amount and correct the positioning information:

[0072] After calculating the initial positioning error, to further improve positioning accuracy and system robustness, the system dynamically optimizes the error correction parameters using an adaptive correction model. Based on the error propagation and compensation mechanism, it calculates the real-time positioning error correction, ultimately accurately correcting the shuttle's position and attitude. This process combines historical error correction data, real-time error feedback, and motion model prediction to ensure the system maintains high positioning accuracy and navigation stability under various operating conditions.

[0073] Step S41: dynamically adjusting the parameters of the error correction model using the initial value of the positioning error;

[0074] The system is based on the initial value of the positioning error δ calculated currently p , dynamically adjusts key parameters in the error correction model to adapt to different error trends and path complexities.,The adjustment process introduces historical residuals, adaptive learning rates, and time decay factors,,forming a complex parameter optimization model with temporal memory and dynamic,response capabilities.

[0075] The calculation model for parameter adjustment is: Among them, γ k is the adaptive correction coefficient at the current moment; γ k-1 is the adaptive correction coefficient of the previous moment; η is the main learning rate coefficient, which controls the sensitivity of feedback adjustment; λ is the time decay factor, which suppresses the influence of outdated error data; t k is the current moment, t0 is the initial moment; is the error change trend weight coefficient, which is used to adjust the sensitivity to the error change speed; δ p is the initial value of the current positioning error; is the target positioning error threshold, which is set according to the navigation accuracy requirement; Δδ p The error rate of change reflects the trend of the error change. Through the above model adjustment, the adaptive correction coefficient can dynamically balance the error correction amplitude and automatically optimize the correction strategy in different scenarios.

[0076] Step S42: Calculate the error correction value in real time through the calibration model to update the real-time information of the shuttle position and posture.

[0077] After completing the model parameter adjustment, the system calculates the real-time positioning error correction based on the error correction formula, combined with the current state vector, error data and path feature information, to achieve synchronous high-precision correction of position and attitude.

[0078] The calculation formula of the correction vector is: in, is the position correction vector, used to update the position information; γ k is the current adaptive correction coefficient; K p is the position deviation gain matrix; is the position vector of the reference trajectory point and the current moment; K θ is the attitude deviation gain matrix; is the rotation matrix corresponding to the current posture; is the reference trajectory point and the current attitude angle vector; μ is the path curvature compensation coefficient; is the velocity vector at the current moment; Δt is the sampling period; R is the path curvature radius; β is the curvature influence exponent coefficient, which enhances the impact of path curvature on error compensation. Finally, the position information and attitude angle of the shuttle are updated through the following correction formula: Through this correction process, the system can effectively reduce positioning deviations in complex paths and dynamic environments, improve the stability of navigation control and path tracking accuracy, and ensure the reliable operation of the shuttle vehicle under complex working conditions.

[0079] Step S50: Update the shuttle vehicle trajectory control system parameters based on the corrected positioning information and perform trajectory navigation control:

[0080] After completing the positioning error correction, the system immediately updates the key control parameters of the shuttle's trajectory control system in real time based on the latest position information and attitude parameters. This process involves the comprehensive optimization of path tracking accuracy, driving smoothness, dynamic response speed, and deviation tolerance, ensuring that the shuttle can stably and accurately complete its navigation mission according to the preset trajectory. Specific sub-steps include:

[0081] Step S51: providing the corrected real-time position and posture information as input to the shuttle trajectory control system;

[0082] The system will correct the location information and posture angle As the effective input at the current moment, it is passed to the trajectory control system. These data are used to analyze the spatial position and orientation of the vehicle and compare them with the desired position in the target path. and expected posture Perform real-time comparison.

[0083] To avoid the impact of short-term deviations caused by sensor data fluctuations, the system smoothes the input data and adjusts the weights of historical data and current data through the smoothing factor α (value range 0.7 to 0.9), thereby eliminating high-frequency noise interference and improving data stability and continuity.

[0084] Step S52: Adjust the control parameters in real time according to the input information to ensure that the shuttle runs according to the precise trajectory navigation.

[0085] Based on the corrected position and posture information and combined with preset path planning, the trajectory control system dynamically adjusts motion control parameters, including driving speed, steering angle, and acceleration, to ensure that the vehicle can accurately return to the target path and operate smoothly.

[0086] The control system calculates the deviation trend based on the path deviation and attitude deviation. If the deviation continues to increase, the system will adjust the control strategy in advance, increasing the steering adjustment range and appropriately slowing down to improve the path return efficiency.

[0087] The system simultaneously considers the curvature radius of the current path and the vehicle's speed, and rationally distributes wheel steering and acceleration and deceleration commands to ensure that the shuttle can smoothly transition in complex paths or sharp bends, avoiding path deviation or inertial slip.

[0088] Step S60: periodically analyzing the accumulated positioning error correction data, optimizing the self-calibration model parameters, and improving positioning accuracy and stability;

[0089] To continuously improve the shuttle's positioning accuracy and system stability, the system has designed a periodic error data analysis mechanism. This mechanism dynamically optimizes the key parameters of the self-calibration model by conducting in-depth analysis of accumulated positioning error correction data. This process utilizes big data analysis and model feedback optimization techniques to comprehensively evaluate the distribution characteristics, changing trends, and correction effects of positioning errors. This allows for targeted adjustments to the compensation factors and correction strategies in the model to enhance its adaptability and robustness in different environments and operating conditions. This includes the following sub-steps:

[0090] Step S61: periodically transmitting positioning error correction data to a central control unit;

[0091] During the shuttle's operation, the system records positioning error correction data for each navigation cycle in real time, including position deviation, attitude angle deviation, and the corresponding correction amount. This data is regularly packaged and transmitted to the central control unit via a wireless communication module or a wired network.

[0092] During data transmission, the system ensures data integrity and timeliness. Through data caching and outlier rejection mechanisms, it ensures that transmitted error data is representative and accurate. Upon receiving the data, the central control unit categorizes and organizes it by chronological order and mission scenario, providing a high-quality input dataset for subsequent data analysis.

[0093] Step S62: Analyze the transmitted data using big data analysis technology to determine the error distribution characteristics and optimize the self-calibration model parameters for the next cycle.

[0094] After receiving and organizing the error correction data, the central control unit conducts in-depth mining and statistical analysis using big data analytics. The analysis focuses on the temporal variations and distribution characteristics of the error correction data, as well as its performance differences across different paths and environments. This allows the system to identify the main factors affecting positioning accuracy and potential causes of model deviation.

[0095] Through methods such as cluster analysis, trend prediction, and historical model comparison, the central control unit accurately assesses the applicability and deficiencies of the current self-calibration model in various scenarios. Based on this, it optimizes model parameters, including error compensation thresholds, correction factors, and model sensitivity settings. These optimized model parameters are then applied in the next operating cycle, enabling the shuttle to complete its navigation mission with higher positioning accuracy and greater stability in the new operating environment.

[0096] This periodic optimization process constitutes an adaptive learning closed loop for the shuttle positioning system. Through continuous error feedback and model self-optimization, it greatly improves the system's long-term stability and ability to adapt to complex environments, providing a solid guarantee for the shuttle's high-precision intelligent navigation.

[0097] Example 2

[0098] like Figure 2 As shown, the second embodiment of the present application provides a four-way shuttle self-calibration positioning system based on body state perception, including:

[0099] The state perception module 21 is used to collect the three-axis acceleration, three-axis angular velocity, wheel displacement and attitude angle data of the shuttle body, and simultaneously form a standardized perception data set;

[0100] The state perception module 21 is mainly used to collect the key motion state data of the shuttle body in real time, including three-axis acceleration, three-axis angular velocity, wheel displacement and attitude angle data, and through data synchronization and standardization processing, form a unified standardized perception data set, providing a high-precision perception basis for subsequent positioning calculation and motion control.

[0101] In specific implementations, the state perception module 21 integrates a variety of high-precision sensor devices, including a three-axis accelerometer, a three-axis gyroscope, a wheel encoder, and an attitude sensor. The three-axis accelerometer captures the shuttle's linear acceleration in the X, Y, and Z directions in real time for analyzing the dynamic changes of the vehicle. The three-axis gyroscope collects angular velocity data about each axis to monitor the shuttle's rotational attitude. The wheel encoder accurately records the displacement changes of each wheel, providing basic displacement data for path calculation. The attitude sensor combines acceleration and angular velocity information to calculate the shuttle's attitude angles, including roll, pitch, and yaw, in real time.

[0102] To ensure data timing consistency and computational accuracy, the state perception module 21 is equipped with a unified clock synchronization mechanism. This uses a high-precision clock module to assign a unified timestamp to all sensor data, and employs a data cache queue to achieve real-time alignment of sensor data. Ultimately, after time synchronization and data cleaning, the perception data is packaged into a standardized perception dataset. This data is then provided to the data fusion module 22 via a pre-defined communication interface, providing continuous and stable perception data input. This ensures that subsequent fusion calculations and positioning algorithms are based on high-quality, complete, and synchronized raw data.

[0103] The data fusion module 22 is used to perform fusion calculation on the standardized perception data set to obtain real-time position and posture parameters;

[0104] The data fusion module 22 is used to comprehensively process the multi-source heterogeneous data collected by various sensors based on the standardized perception data set provided by the state perception module 21, and obtain the real-time position and posture parameters of the shuttle vehicle through multi-sensor fusion algorithm calculation, providing high-precision input data for subsequent positioning correction and navigation control.

[0105] During implementation, the data fusion module 22 employs multiple fusion algorithms, dynamically switching between them based on actual operating conditions and sensor performance. The module first preprocesses the input triaxial acceleration, triaxial angular velocity, wheel displacement, and attitude angle data, including noise filtering, outlier removal, and data consistency verification, to improve the reliability and accuracy of data fusion.

[0106] During the data fusion phase, the module predicts the shuttle's short-term motion state based on the vehicle's kinematic model and dynamic characteristics, combined with the collected acceleration and angular velocity information. It then performs real-time corrections using displacement and attitude angle data, ultimately outputting precise spatial position coordinates and attitude angles. These calculations, including the shuttle's current position vector and attitude description in three-dimensional space, provide accurate basic data support for the error matching module 23.

[0107] Finally, the real-time position and attitude parameters obtained by the fusion calculation are sent to the error matching module 23 through the standard communication interface for positioning error calculation and subsequent adaptive correction.

[0108] The error matching module 23 is used to match the real-time position and attitude parameters with the pre-stored high-precision trajectory map data to calculate the initial value of the positioning error;

[0109] The error matching module 23 is used to perform spatial matching with the pre-stored high-precision trajectory map data based on the real-time position and attitude parameters provided by the data fusion module 22. By calculating the spatial deviation between the current state and the target path, the initial value of the positioning error is obtained, providing basic data support for subsequent adaptive correction.

[0110] During the specific implementation process, the error matching module 23 first extracts a set of reference trajectory points covering the current working area from the high-precision trajectory map, and combines the current real-time position vector and attitude angle, and uses an improved composite matching algorithm based on Euclidean distance and attitude angle difference to quickly determine the reference trajectory point closest to the current state.

[0111] During the matching process, the module considers both position and attitude deviations. By setting position and attitude weighting coefficients, it achieves a balanced adjustment between position accuracy and attitude stability in different scenarios. For straight paths, position coordinates are prioritized to ensure smooth driving. For complex curves or intersections, attitude angles are prioritized to improve path steering accuracy.

[0112] After completing the matching, the error matching module 23 calculates the initial positioning error based on the spatial position deviation and attitude angle deviation, and outputs this result to the adaptive correction module 24 to provide a basis for subsequent error correction. The module also has error trend analysis capabilities. By statistically analyzing the changes in positioning deviation over consecutive time periods, it can identify potential large deviation risks in advance, providing auxiliary data support for improving the response speed and accuracy of adaptive correction.

[0113] The adaptive correction module 24 is used to perform adaptive correction calculations based on the initial positioning error value, determine the real-time positioning error correction amount, and correct the positioning information;

[0114] The adaptive correction module 24 is used to dynamically adjust the key parameters of the error correction model based on the initial positioning error value calculated by the error matching module 23, and calculate the positioning error correction amount in real time. It outputs the corrected position information and attitude parameters through feedback correction to further improve the positioning accuracy and navigation stability of the shuttle vehicle.

[0115] During implementation, the adaptive correction module 24 first receives the initial positioning error value provided by the error matching module 23. It then calculates the required error correction using the error compensation model, taking into account the shuttle's current motion state, including speed, acceleration, and steering angle. The module incorporates multiple error correction algorithms, including proportional-integral-derivative control (PID), extended Kalman filter (EKF) adaptive adjustment, and a model-based prediction correction algorithm based on historical error data. Based on different operating conditions and error trends, the system dynamically selects the most appropriate correction algorithm to improve the accuracy and response speed of the correction results.

[0116] During the error correction calculation process, the adaptive correction module 24 comprehensively considers the spatial distribution and rate of change of positioning errors. By adjusting the correction factors and feedback gains in the model, it achieves rapid response to large deviations and smooth adjustment to small deviations. For long-term accumulated error trends, the module uses residual analysis to optimize model parameters to reduce the long-term positioning errors caused by accumulated errors.

[0117] Finally, the adaptive correction module 24 outputs the corrected position information and attitude angle data for the trajectory control module 25 to call and use to update the navigation control instructions to ensure that the shuttle can maintain high-precision positioning and stable driving state in a dynamic and complex environment.

[0118] The trajectory control module 25 is used to update the shuttle trajectory control system parameters according to the corrected positioning information and perform trajectory navigation control;

[0119] The trajectory control module 25 is used to dynamically update the trajectory control system parameters of the shuttle vehicle based on the corrected position information and posture parameters output by the adaptive correction module 24, combined with the preset trajectory navigation planning data, to generate specific motion control instructions and drive the shuttle vehicle to achieve high-precision path tracking and dynamic navigation control.

[0120] During implementation, the trajectory control module 25 first receives the corrected real-time position coordinates and attitude angle data, compares them with the reference path points in the target trajectory in real time, and analyzes the spatial and attitude deviations between the current position and the target path. Based on this deviation information, the module employs a feedforward-feedback composite control strategy, predicting the shuttle's future motion trends and current state changes to calculate the wheel steering angle, driving speed, and acceleration and deceleration control parameters in real time.

[0121] During path tracking, the trajectory control module 25 dynamically adjusts control parameters based on different navigation scenarios. When the shuttle is on a straight path, speed control is prioritized to improve driving efficiency. When approaching a curve or complex intersection, steering control accuracy is enhanced. Speed reduction and appropriate steering adjustments ensure the shuttle smoothly and safely completes the path transition.

[0122] Furthermore, the trajectory control module 25 features adaptive adjustment capabilities, automatically optimizing control parameters based on the shuttle's current load, ground friction conditions, and dynamic inertia characteristics, improving motion control stability and anti-interference capabilities. This dynamic control strategy enables the shuttle to achieve smooth, high-precision path tracking in complex environments. Even in the face of sudden deviations or complex path changes, it can promptly adjust its motion state to maintain stable operation.

[0123] Finally, the trajectory control module 25 transmits the calculated control instructions to the shuttle's drive unit and wheel actuator, directly driving the vehicle body to move, achieving continuous, stable and high-precision trajectory navigation control.

[0124] The central analysis module 26 is used to periodically analyze the accumulated positioning error correction data, optimize the self-calibration model parameters through big data analysis, and improve positioning accuracy and stability.

[0125] The central analysis module 26 is used to periodically analyze the positioning error correction data accumulated by the shuttle during navigation, identify the error distribution characteristics and change trends through big data analysis technology, and optimize the calculation parameters of the self-calibration model to improve the long-term positioning accuracy and operating stability of the shuttle system under complex working conditions.

[0126] During implementation, the central analysis module 26 regularly collects positioning error correction data from each module, including position error, attitude angle error, error correction amount, and corresponding time series data. The module utilizes efficient data storage and management mechanisms to categorize and organize historical error data by time series, path type, and operating condition, generating a high-quality analytical dataset.

[0127] During the data analysis phase, the central analysis module 26, based on a big data analysis framework, combines algorithms such as cluster analysis, trend prediction, residual analysis, and statistical regression to comprehensively explore the temporal variation patterns, distribution characteristics, and influencing factors of positioning errors. By analyzing the error distribution characteristics and model correction effects under different operating conditions, it identifies deficiencies in the current self-calibration model and further adjusts model parameters such as correction factors, feedback gains, and model sensitivity to enhance error correction capabilities in subsequent operating cycles.

[0128] At the same time, the central analysis module 26 also has predictive analysis capabilities. By establishing an error change trend model, it can provide early warning of possible system positioning deviation anomalies, provide optimization suggestions and model update strategies for the system, and enhance the shuttle vehicle's adaptive adjustment capabilities in long-term operation.

[0129] Finally, the optimized self-calibration model parameters will be sent to the adaptive correction module 24 and the trajectory control module 25. In the next cycle, the optimized model will be applied to perform positioning error correction and trajectory navigation control, thus forming a complete closed-loop self-learning and optimization mechanism to improve the overall positioning accuracy and long-term stability of the system.

[0130] Corresponding to the above embodiment, an embodiment of the present invention provides a computer storage medium, comprising: at least one memory and at least one processor;

[0131] The memory is used to store one or more program instructions;

[0132] The processor is used to run one or more program instructions to execute a four-way shuttle vehicle based on body state perception and a self-calibration positioning method thereof.

[0133] Corresponding to the above embodiment, an embodiment of the present invention provides a computer-readable storage medium, which contains one or more program instructions, and the one or more program instructions are used by a processor to execute a four-way shuttle self-calibration and positioning method based on body state perception.

[0134] The embodiments disclosed in the present invention provide a computer-readable storage medium, in which computer program instructions are stored. When the computer program instructions are executed on a computer, the computer executes the above-mentioned four-way shuttle self-calibration and positioning method based on body state perception.

[0135] In the embodiments of the present invention, the processor may be an integrated circuit chip having signal processing capabilities. The processor may 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 devices, discrete gate or transistor logic devices, or discrete hardware components.

[0136] The methods, steps, and logic diagrams disclosed in the embodiments of the present invention can be implemented or executed. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of the present invention can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules within the decoding processor. The software modules can be located in a storage medium well-established in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. The processor reads the information from the storage medium and, in conjunction with its hardware, completes the steps of the aforementioned methods.

[0137] The storage medium may be a memory and may be, for example, a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memory.

[0138] Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory.

[0139] Volatile memory may be random access memory (RAM), which is used as an external cache memory. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DRRAM).

[0140] The storage media described in the embodiments of the present invention are intended to include, but are not limited to, these and any other suitable types of memory.

[0141] Those skilled in the art will appreciate that in one or more of the above examples, the functions described herein can be implemented using a combination of hardware and software. When software is used, the corresponding functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media includes any medium that facilitates the transmission of computer programs from one place to another. The storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0142] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent replacements, improvements, etc. made on the basis of the technical solution of the present invention should be included in the scope of protection of the present invention.

Claims

1. A four-way shuttle self-calibration and positioning method based on body state perception, characterized in that: The following steps are involved: Establish a body state perception system to collect the shuttle body's three-axis acceleration, three-axis angular velocity, wheel displacement and attitude angle data, and simultaneously form a standardized perception data set; Perform fusion calculation on standardized perception data sets to obtain real-time position and attitude parameters; Calculate the initial value of positioning error based on matching the real-time position and attitude parameters with the pre-stored high-precision trajectory map data; Perform adaptive correction calculation based on the initial value of positioning error, determine the real-time positioning error correction amount and correct the positioning information; Update the shuttle vehicle trajectory control system parameters based on the corrected positioning information and perform trajectory navigation control; Periodically analyze the accumulated positioning error correction data, optimize the self-calibration model parameters, and improve positioning accuracy and stability.

2. The method for self-calibration and positioning of a four-way shuttle based on body state perception according to claim 1 is characterized in that: Establish a body state perception system to collect the shuttle body's three-axis acceleration, three-axis angular velocity, wheel displacement, and attitude angle data, and simultaneously form a standardized perception data set, including the following steps: Real-time collection of the shuttle's three-axis acceleration, three-axis angular velocity, wheel displacement, and attitude angle data; The collected data is synchronized with the standard time to form a unified standardized perception data set.

3. The method for self-calibration and positioning of a four-way shuttle based on body state perception according to claim 1 is characterized in that: Perform fusion calculation on the standardized perception data set to obtain real-time position and attitude parameters, including the following steps: Perform multi-sensor fusion processing on standardized perception data sets to uniformly generate position and attitude information; The position coordinates and attitude angle of the shuttle are calculated in real time based on the fused data.

4. The method for self-calibration and positioning of a four-way shuttle based on body state perception according to claim 1 is characterized in that: Based on the matching of real-time position and attitude parameters with pre-stored high-precision trajectory map data, the initial value of positioning error is calculated, including the following steps: Match the real-time position and attitude parameters with pre-stored high-precision trajectory map data; The deviation between the real-time position and the pre-stored trajectory is calculated through spatial matching to generate the initial value of the positioning error.

5. The method for self-calibration and positioning of a four-way shuttle based on body state perception according to claim 1 is characterized in that: Performing adaptive correction calculation based on the initial positioning error value to determine the real-time positioning error correction amount and correct the positioning information includes the following steps: Dynamically adjust the parameters of the error correction model using the initial value of the positioning error; The error correction amount is calculated in real time through the correction model, and the real-time information of the shuttle position and posture is updated.

6. The method for self-calibration and positioning of a four-way shuttle based on body state perception according to claim 1, characterized in that: The shuttle trajectory control system parameters are updated based on the corrected positioning information to perform trajectory navigation control, including the following steps: The corrected real-time position and attitude information is provided as input to the shuttle trajectory control system; The control parameters are adjusted in real time based on the input information to ensure that the shuttle runs along the precise trajectory.

7. The method for self-calibration and positioning of a four-way shuttle based on body state perception according to claim 1, characterized in that: Periodically analyze the accumulated positioning error correction data, optimize the self-calibration model parameters, and improve positioning accuracy and stability, including the following steps: Periodically transmit positioning error correction data to the central control unit; The transmitted data is analyzed through big data analysis technology to determine the error distribution characteristics and optimize the self-calibration model parameters for the next cycle.

8. A four-way shuttle self-calibration positioning system based on body state perception, characterized in that: include: The state perception module is used to collect the shuttle's three-axis acceleration, three-axis angular velocity, wheel displacement, and attitude angle data, and simultaneously form a standardized perception data set; Data fusion module, used to perform fusion calculations on standardized perception data sets to obtain real-time position and attitude parameters; Error matching module, used to match real-time position and attitude parameters with pre-stored high-precision trajectory map data to calculate the initial value of positioning error; An adaptive correction module is used to perform adaptive correction calculations based on the initial value of the positioning error, determine the real-time positioning error correction amount, and correct the positioning information; The trajectory control module is used to update the shuttle trajectory control system parameters according to the corrected positioning information and perform trajectory navigation control; The central analysis module is used to periodically analyze the accumulated positioning error correction data, optimize the self-calibration model parameters through big data analysis, and improve positioning accuracy and stability.

Images