CN114440867A - Zero-speed detection method and device for heavy truck - Google Patents
Zero-speed detection method and device for heavy truck Download PDFInfo
- Publication number
- CN114440867A CN114440867A CN202111555466.4A CN202111555466A CN114440867A CN 114440867 A CN114440867 A CN 114440867A CN 202111555466 A CN202111555466 A CN 202111555466A CN 114440867 A CN114440867 A CN 114440867A
- Authority
- CN
- China
- Prior art keywords
- zero
- data
- vehicle
- speed detection
- detection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 290
- 238000000034 method Methods 0.000 claims abstract description 35
- 230000001133 acceleration Effects 0.000 claims description 34
- 238000005259 measurement Methods 0.000 claims description 26
- 238000012549 training Methods 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 abstract description 5
- 238000004891 communication Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 3
- 238000002372 labelling Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
- G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
- G01C21/16—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
- G01C21/165—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation combined with non-inertial navigation instruments
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M17/00—Testing of vehicles
- G01M17/007—Wheeled or endless-tracked vehicles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
- G01S19/45—Determining position by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement
- G01S19/47—Determining position by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement the supplementary measurement being an inertial measurement, e.g. tightly coupled inertial
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Automation & Control Theory (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Navigation (AREA)
Abstract
The invention provides a zero-speed detection method and a device for a heavy truck, wherein the method comprises the following steps: performing zero offset estimation based on the combined navigation to obtain a zero offset estimation result; carrying out zero offset compensation on the vehicle data collected in advance by using a zero offset estimation result to obtain vehicle compensation data; and selecting vehicle compensation data based on the sliding window with the preset length, and carrying out zero-speed detection on the vehicle compensation data to obtain a zero-speed detection result. According to the method, zero offset estimation results output by a combined navigation system are utilized, zero offset in collected vehicle data and parameters influencing the accuracy of zero-speed detection results are removed, vehicle compensation data along a vehicle system are obtained, and data preprocessing is performed by adopting a sliding window with a preset length so as to be suitable for heavy-truck high-vibration scenes; the processed data is utilized to carry out zero-speed detection, and then a zero-speed detection result is obtained, so that zero-speed detection errors caused by attitude resolving delay are avoided, detection errors of the vehicle in a low-speed slow running process are reduced, and the accuracy and efficiency of the zero-speed detection are improved.
Description
Technical Field
The invention relates to the technical field of vehicles, in particular to a zero-speed detection method and a zero-speed detection device for a heavy truck.
Background
The zero-speed detection is to detect the time interval when the system speed is zero as the name suggests, so as to make early preparation for zero-speed correction. The detected zero-speed time interval is used as external measurement information of the system speed error, and various errors of the system are controlled and corrected, so that the positioning accuracy of the system is improved.
The existing zero-speed detection mainly judges the zero-speed state of a vehicle according to a given unified threshold, data read by an Inertial Measurement Unit (IMU) is substituted into a motion model for calculation, and if the calculation result is lower than the threshold, the current vehicle is considered to be in a static state.
However, the vehicle has the problems of positioning jump and random position drift under the general or poor observation conditions, and the wheel speed meter cannot accurately measure the speed, so that the accuracy of the zero-speed detection result is low; in addition, the vehicle has the condition that the engine vibrates obviously, which is easy to cause the condition that the zero-speed detection is invalid or the detection efficiency is not high.
Disclosure of Invention
The invention provides a zero-speed detection method and a zero-speed detection device for a heavy truck, which are used for solving the defect of poor zero-speed detection result precision caused by the limitation of vehicle observation conditions in the prior art and improving the precision and the efficiency of zero-speed detection.
The invention provides a zero-speed detection method of a heavy truck, which comprises the following steps: performing zero offset estimation based on the combined navigation to obtain a zero offset estimation result; carrying out zero offset compensation on the vehicle data collected in advance by using the zero offset estimation result to obtain vehicle compensation data; and selecting the vehicle compensation data based on a sliding window with a preset length, and carrying out zero-speed detection on the vehicle compensation data to obtain a zero-speed detection result.
According to the zero-speed detection method of the heavy truck provided by the invention, the vehicle compensation data is selected based on the sliding window with the preset length, and the zero-speed detection is carried out on the vehicle compensation data, and the zero-speed detection method comprises the following steps: selecting the vehicle compensation data based on preset step length sliding by using a sliding window with a preset length to obtain a plurality of detection data sequences; respectively carrying out zero-speed detection on the plurality of detection data sequences to obtain detection results corresponding to the detection data sequences; and obtaining a zero-speed detection result based on all the obtained detection results and a preset threshold value.
According to the zero-speed detection method for the heavy truck provided by the invention, the zero-speed detection result is obtained based on all the obtained detection results and the preset threshold, and the method comprises the following steps: according to all the obtained detection results, obtaining the proportion of the vehicle detection result with the detection result of zero speed in all the vehicle detection results; obtaining a zero speed as a zero speed detection result based on the proportion being greater than or equal to a preset threshold value; and obtaining a non-zero speed as a zero speed detection result based on the proportion smaller than the preset threshold value.
According to the zero-speed detection method for the heavy truck provided by the invention, the zero-speed detection is respectively carried out on the plurality of detection data sequences to obtain the detection result corresponding to each detection data sequence, and the method comprises the following steps: inputting the detection data sequence into a zero-speed detection model to obtain a detection result output by the zero-speed detection model; the zero-speed detection model is obtained by training based on historical vehicle data and corresponding zero-speed label data.
According to the zero-speed detection method of the heavy truck provided by the invention, the zero-speed detection model comprises the following steps: the characteristic extraction layer is used for respectively extracting the characteristics of each input detection data sequence to obtain the detection data characteristics respectively corresponding to each detection data sequence; the mean square error calculation layer is used for calculating corresponding mean square errors respectively based on the characteristics of the detection data; the zero-speed prediction layer is used for judging whether the mean square error meets a preset condition or not, and if so, determining that the current zero-speed state is used as a corresponding detection result; otherwise, determining that the current state is in a non-zero speed state as a corresponding detection result.
According to the zero-speed detection method of the heavy truck provided by the invention, the mean square error represents that:
wherein, TFAMVRepresents the mean square error; z is a radical ofnRepresenting all the detected data sequences used at time n,
n represents znThe number of measurement data sequences in (1); omeganRepresents the set of all the measured data sequences,
the representation represents the noise variance of the detected data sequence in the stationary case,
which represents a sequence of measurement data,
represents the mean of the measured data series, and FWD represents the output value of the measured data series at forward acceleration.
According to the zero-speed detection method of the heavy truck provided by the invention, the vehicle data comprises acceleration, and after the zero offset estimation result is obtained, the method further comprises the following steps: and screening the vehicle data based on the zero offset estimation result, and removing the coriolis acceleration, the centripetal acceleration to the ground and the gravitational acceleration.
According to the zero-speed detection method of the heavy truck provided by the invention, before the zero offset compensation is carried out on the vehicle data collected in advance by using the zero offset estimation result, the method further comprises the following steps: and acquiring the speed of the vehicle along the driving direction of the vehicle system based on the inertia measurement unit.
The invention also provides a zero-speed detection device of the heavy truck, which comprises: the zero offset estimation module is used for carrying out zero offset estimation based on the integrated navigation to obtain a zero offset estimation result; the zero offset compensation module is used for carrying out zero offset compensation on the vehicle data acquired in advance by utilizing the zero offset estimation result to obtain vehicle compensation data; and the zero-speed detection module is used for selecting the vehicle compensation data based on a sliding window with a preset length and carrying out zero-speed detection on the vehicle compensation data to obtain a zero-speed detection result.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the steps of the zero-speed detection method of the heavy card.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method for zero speed detection of a heavy card as described in any of the above.
The present invention also provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the method for zero-speed detection of a heavy card as described in any of the above.
The zero-speed detection method and the device for the heavy truck provided by the invention have the advantages that the zero offset estimation result output by the integrated navigation system is utilized, the zero offset in the collected vehicle data and the parameters influencing the accuracy of the zero-speed detection result are removed, the vehicle compensation data along the vehicle system are obtained, and the data preprocessing is carried out by adopting the sliding window with the preset length so as to be suitable for the high-vibration scene of the heavy truck; the zero-speed detection is carried out by utilizing the processed data, and then a zero-speed detection result is obtained, so that zero-speed detection errors caused by attitude resolving delay are avoided, detection errors of the vehicle in a low-speed slow running process are reduced, and the accuracy and efficiency of the zero-speed detection are improved
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a zero-speed detection method for a heavy truck according to the present invention;
FIG. 2 is a schematic structural diagram of a zero-speed detection apparatus for heavy trucks according to the present invention;
fig. 3 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 shows a schematic flow chart of a zero-speed detection method for a heavy truck according to the present invention, which includes:
s01, performing zero offset estimation based on the integrated navigation to obtain a zero offset estimation result;
s02, carrying out zero offset compensation on the vehicle data collected in advance by using the zero offset estimation result to obtain vehicle compensation data;
and S03, selecting vehicle compensation data based on the sliding window with the preset length, and carrying out zero-speed detection on the vehicle compensation data to obtain a zero-speed detection result.
It should be noted that S0N in this specification does not represent the sequence of the zero-speed detection method for heavy cards, and the zero-speed detection method for heavy cards of the present invention is specifically described below.
And S01, performing zero offset estimation based on the combined navigation to obtain a zero offset estimation result.
In the embodiment, the integrated Navigation System includes a GNSS/INS, where the GNSS is a Global Navigation Satellite System (Global Navigation Satellite System) and the INS is an Inertial Navigation System (Inertial Navigation System). Based on the initialization of the combined navigation, a better zero-bias estimation result of an Inertial Measurement Unit (IMU) is obtained. Note that the zero offset estimation result includes information such as an attitude angle and an IMU zero offset. The zero offset estimation result needs to be determined according to the type of the collected vehicle data, for example, if the vehicle data includes acceleration, the zero offset estimation result is zero offset estimated acceleration.
In an optional embodiment, before performing zero offset compensation on the pre-collected vehicle data by using the zero offset estimation result, the method further includes: and vehicle data are acquired along the driving direction of the vehicle system based on the inertia measurement unit. In the present embodiment, the vehicle data includes acceleration. Still further, gather vehicle data along the driving direction of automobile system based on inertial measurement unit, include: based on the fact that the coordinate system of the inertia measurement unit is consistent with the coordinate system of the automobile, the inertia measurement unit is used for collecting vehicle data along the driving direction of the automobile system; or based on the inconsistency between the coordinate system of the inertia measurement unit and the coordinate system of the automobile, the inertia measurement unit is utilized, and the inertia measurement unit is utilized to collect the vehicle data along the driving direction of the automobile system; and according to the angle offset between the inertial measurement unit coordinate system and the automobile coordinate system, carrying out data processing on the acquired vehicle data to obtain the vehicle data corresponding to the automobile coordinate system.
It should be noted that, assuming that it is necessary to determine whether the vehicle is in the zero-speed state at time t, vehicle data in a period of time before time t may be collected, or vehicle data in a certain period of time before and after time t may be collected, so as to perform zero offset compensation on the collected vehicle data subsequently by using a zero offset estimation result, thereby facilitating subsequent zero-speed detection. In addition, the vehicle data may be understood as a set of vehicle data collected corresponding to different times, and the vehicle data may be vehicle data for at least one target vehicle and corresponding to different driving environments of the target vehicle at different times.
And S02, carrying out zero offset compensation on the vehicle data collected in advance by using the zero offset estimation result to obtain vehicle compensation data.
In the embodiment, the zero offset estimation result is utilized to perform zero offset compensation on the vehicle data acquired in advance, so that the influence of the zero offset on the obtained vehicle compensation data is avoided, and the accuracy and the detection reliability of the subsequent zero-speed detection are influenced.
In an optional embodiment, since the pose of the INS is more accurate, after obtaining the zero offset estimation result, the method further includes: and screening the vehicle data based on the zero offset estimation result to remove the harmful acceleration. It should be noted that the harmful acceleration includes at least one of coriolis acceleration, centripetal to earth acceleration, and gravitational acceleration, wherein the coriolis acceleration is caused by the movement of the vehicle relative to the earth and the rotation of the earth, the centripetal to earth acceleration is caused by the movement of the vehicle held on the surface of the earth, and the gravitational acceleration is caused by the attraction of the vehicle to the area.
It should be noted that, after the vehicle-mounted integrated navigation system is initialized, assuming that the relative angular offset between the vehicle-mounted system of the IMU and the vehicle coordinate system is the same or the relative angular offset between the vehicle-mounted system of the IMU and the vehicle coordinate system is a known quantity, the zero offset and the harmful acceleration in the original IMU measurement value are removed by using the attitude angle, the IMU zero offset and other information output by the integrated navigation system, so as to obtain the vehicle motion acceleration along the vehicle system, that is, the vehicle compensation data for the subsequent zero-speed detection in the present application.
And S03, selecting vehicle compensation data based on the sliding window with the preset length, and carrying out zero-speed detection on the vehicle compensation data to obtain a zero-speed detection result.
In this embodiment, selecting vehicle compensation data based on a sliding window with a preset length and performing zero-speed detection on the vehicle compensation data includes: selecting vehicle compensation data by using a sliding window with a preset length and sliding based on a preset step length to obtain a plurality of detection data sequences; respectively carrying out zero-speed detection on the plurality of detection data sequences to obtain detection results corresponding to the detection data sequences; and obtaining a zero-speed detection result based on all the obtained detection results and a preset threshold value. The data preprocessing is carried out by adopting the sliding window with the preset length, the zero-speed detection is carried out by utilizing the processed data, and the preliminary result of the zero-speed detection is obtained, so that the method is suitable for the application scene of high vibration of the heavy truck, and the problems of detection failure or low efficiency caused by positioning jump or position random drift are avoided.
Specifically, first, vehicle compensation data is selected by sliding with a preset length of a sliding window based on a preset step length, and a plurality of detection data sequences are obtained. Vehicle compensation data are selected through sliding of the sliding window based on preset step length sliding, so that the scales of the zero-speed state and the non-zero-speed state are obviously expanded, and the identification degree and the efficiency of subsequent zero-speed detection are improved; in addition, the multiple detection data sequences are obtained, so that the zero speed misjudgment risk caused by the vehicle slight displacement during subsequent zero speed detection is reduced, and the accuracy and the reliability of the zero speed detection are improved.
It should be noted that, assuming that the preset length is 50, the preset step length is 1, and the vehicle compensation data is { x }1,x2,…,xnN represents the data amount of the vehicle compensation data, a plurality of detections are obtainedThe data sequence is represented as:
{x1,x2,…,x50},{x2,x2,…,x51},…,{xn-49,xn-48,…,xn}
in addition, the number of the detection data sequences may be determined according to the data amount of the vehicle compensation data, the preset step length and the preset length, and the specific length of the sliding window and the sliding step length may be set according to the data amount actually related to the vehicle compensation data and the actual zero speed detection requirement, which are not further limited herein.
Secondly, respectively carrying out zero-speed detection on the plurality of detection data sequences to obtain detection results corresponding to the detection data sequences.
In a possible implementation manner, performing zero-speed detection on a plurality of detection data sequences respectively to obtain a detection result corresponding to each detection data sequence includes: inputting the detection data sequence into a zero-speed detection model to obtain a detection result output by the zero-speed detection model; the zero-speed detection model is obtained by training based on historical vehicle data and corresponding zero-speed label data.
More particularly, the zero-velocity detection model comprises: the characteristic extraction layer is used for respectively extracting the characteristics of each input detection data sequence to obtain detection data characteristics respectively corresponding to each detection data sequence; the mean square error calculation layer is used for calculating corresponding mean square errors respectively based on the detection data characteristics; the zero-speed prediction layer judges whether the mean square error meets a preset condition, and if so, the zero-speed prediction layer determines that the current zero-speed state is used as a corresponding detection result; otherwise, determining that the current state is in a non-zero speed state as a corresponding detection result. It should be noted that the preset condition may be determined according to a corresponding mean square error value range in a zero-velocity state, and is not further limited here.
In the present embodiment, the mean square error represents:
wherein, TFAMVDenotes the mean square error, znRepresenting all the detected data sequences used at time n,
n represents znThe number of measurement data sequences in (1); omeganRepresents the set of all the measured data sequences,
the representation represents the noise variance of the detected data sequence in the stationary case,
which represents a sequence of measurement data,
represents the mean of the measured data sequence and FWD represents the output value of the measured data sequence at forward acceleration.
In addition, the method for inputting the detection data sequence into the zero-speed detection model to obtain the detection result output by the zero-speed detection model comprises the following steps: inputting the detection data sequence into a feature extraction layer to obtain detection data features output by the feature extraction layer; inputting the detection data characteristics into a mean square error calculation layer to obtain the mean square error output by the mean square error calculation layer; and inputting the mean square error into a zero-speed prediction layer to obtain a detection result output by the zero-speed prediction layer.
In an optional embodiment, before inputting the detection data sequence into the zero-speed detection model, the method further includes: and training a zero-speed detection model. The method specifically comprises the following steps: acquiring historical vehicle data; labeling according to a zero-speed state corresponding to historical vehicle data to obtain zero-speed label data; and training the network to be trained by using the historical vehicle data as input data used for training and the zero-speed label data as labels during training in a deep learning mode to obtain a zero-speed detection model for generating a detection result of the vehicle compensation data.
Furthermore, the training of the network to be trained by adopting a deep learning mode comprises the following steps: inputting historical vehicle data into a network to be trained to obtain a zero-speed prediction result output by the network to be trained; and constructing a loss function based on the zero-speed prediction result and the zero-speed label data, converging based on the loss function, and ending the training.
It should be noted that the zero-speed detection model to be trained may be a network built in the training apparatus, and the network generally includes a network structure, such as various neural networks CNN, etc., or may be other specific networks specified by the user, such as a small network model developed based on requirements and suitable for zero-speed detection, which is not further limited in this application.
In another possible implementation manner, performing zero-speed detection on a plurality of detection data sequences respectively to obtain a detection result corresponding to each detection data sequence includes: respectively obtaining the mean square error of each detection data sequence; judging whether the mean square error meets a preset condition or not according to the mean square error, and if so, determining that the current zero-speed state is used as a corresponding detection result; otherwise, determining that the current state is in a non-zero speed state as a corresponding detection result.
And finally, obtaining a zero-speed detection result based on all the obtained detection results and a preset threshold value. By detecting the detection result based on the preset threshold value, zero-speed detection errors caused by attitude resolving delay are avoided, detection errors of the vehicle in a low-speed slow running process are reduced, and accuracy and efficiency of zero-speed detection are improved.
In this embodiment, obtaining the zero-speed detection result based on all the obtained detection results and a preset threshold includes: according to all the obtained detection results, obtaining the proportion of the vehicle detection result with the detection result corresponding to the zero speed to all the vehicle detection results; obtaining zero speed as a zero speed detection result based on the proportion being greater than or equal to a preset threshold value; and obtaining a non-zero speed as a zero speed detection result based on the proportion smaller than a preset threshold value.
In summary, the zero offset estimation result output by the integrated navigation system is utilized, the zero offset in the collected vehicle data and the parameters influencing the accuracy of the zero-speed detection result are removed, the vehicle compensation data along the vehicle system are obtained, and the sliding window with the preset length is adopted for data preprocessing, so that the method is suitable for the heavy truck high-vibration scene; the processed data is utilized to carry out zero-speed detection, and then a zero-speed detection result is obtained, so that zero-speed detection errors caused by attitude resolving delay are avoided, detection errors of the vehicle in a low-speed slow running process are reduced, and the accuracy and efficiency of the zero-speed detection are improved.
The following describes the zero-speed detection apparatus for heavy truck according to the present invention, and the zero-speed detection apparatus for heavy truck described below and the zero-speed detection method for heavy truck described above can be referred to correspondingly.
Fig. 2 shows a schematic structural diagram of a zero-speed detection device of a heavy truck, the device comprises:
the zero offset estimation module 21 performs zero offset estimation based on the integrated navigation to obtain a zero offset estimation result;
the zero offset compensation module 22 is used for performing zero offset compensation on the vehicle data acquired in advance by using the zero offset estimation result to obtain vehicle compensation data;
and the zero-speed detection module 23 is used for selecting vehicle compensation data based on a sliding window with a preset length and carrying out zero-speed detection on the vehicle compensation data to obtain a zero-speed detection result.
In this embodiment, the zero offset estimation module 21 includes: and the zero offset estimation unit is used for carrying out zero offset estimation based on the integrated navigation to obtain a zero offset estimation result.
In an optional embodiment, the apparatus further comprises: and the data acquisition module is used for acquiring vehicle data along the driving direction of the vehicle system based on the inertia measurement unit. In the present embodiment, the vehicle data includes acceleration. Still further, the data acquisition module includes: the first data acquisition unit is used for acquiring vehicle data along the driving direction of the vehicle system by utilizing the inertia measurement unit based on the consistency of the inertia measurement unit coordinate system and the vehicle coordinate system; or the second data acquisition unit acquires vehicle data along the driving direction of the vehicle system by using the inertia measurement unit based on the inconsistency of the coordinate system of the inertia measurement unit and the coordinate system of the vehicle; and the data processing unit is used for carrying out data processing on the collected vehicle data according to the angle offset between the inertia measurement unit coordinate system and the automobile coordinate system to obtain the vehicle data corresponding to the automobile coordinate system.
A zero offset compensation module 22 comprising: and the zero offset compensation unit is used for performing zero offset compensation on the vehicle data acquired in advance by using the zero offset estimation result to obtain vehicle compensation data. Zero offset compensation is carried out on the vehicle data collected in advance by utilizing the zero offset estimation result, so that the influence of zero offset on the obtained vehicle compensation data is avoided, and the accuracy and the detection reliability of subsequent zero-speed detection are influenced.
In an alternative embodiment, since the INS is more accurate in attitude, to facilitate removing the harmful acceleration, the zero offset compensation module 22 further includes: and the screening unit screens the vehicle data based on the zero offset estimation result to remove the harmful acceleration. It should be noted that the harmful acceleration includes at least one of coriolis acceleration, centripetal to earth acceleration, and gravitational acceleration, wherein the coriolis acceleration is caused by the movement of the vehicle relative to the earth and the rotation of the earth, the centripetal to earth acceleration is caused by the movement of the vehicle held on the surface of the earth, and the gravitational acceleration is caused by the attraction of the vehicle to the area.
The zero-speed detection module 23 includes: the sliding selection unit is used for selecting vehicle compensation data based on a preset step length by utilizing a sliding window with a preset length in a sliding mode to obtain a plurality of detection data sequences; the zero-speed detection unit is used for respectively carrying out zero-speed detection on the plurality of detection data sequences to obtain detection results corresponding to the detection data sequences; and the result judging unit is used for obtaining a zero-speed detection result based on all the obtained detection results and a preset threshold value.
In one possible implementation, the zero-speed detection unit includes: the zero-speed detection subunit inputs the detection data sequence into the zero-speed detection model to obtain a detection result output by the zero-speed detection model; the zero-speed detection model is obtained by training based on historical vehicle data and corresponding zero-speed label data.
More specifically, the zero-velocity detection model includes: the feature extraction unit is used for respectively extracting features of the input detection data sequences to obtain detection data features respectively corresponding to the detection data sequences; the mean square error calculation grandchild unit calculates corresponding mean square errors respectively based on the detection data characteristics; the zero-speed prediction sun unit judges whether the mean square error meets a preset condition, and if so, the current zero-speed state is determined to be used as a corresponding detection result; otherwise, determining that the current state is in a non-zero speed state as a corresponding detection result. It should be noted that the preset condition may be determined according to a corresponding mean square error value range in a zero-velocity state, and is not further limited here.
In addition, the method for inputting the detection data sequence into the zero-speed detection model to obtain the detection result output by the zero-speed detection model comprises the following steps: inputting the detection data sequence into a feature extraction grandchild unit to obtain detection data features output by the feature extraction grandchild unit; inputting the detection data characteristics into a mean square error calculation grandchild unit to obtain the mean square error output by the mean square error calculation grandchild unit; and inputting the mean square error into a zero-speed prediction grandchild unit to obtain a detection result output by the zero-speed prediction grandchild unit.
In an optional embodiment, the zero-speed detection module 23 further includes: and the model training unit trains the zero-speed detection model. A model training unit comprising: a history data acquisition subunit that acquires history vehicle data; the labeling subunit is used for labeling the zero-speed state corresponding to the historical vehicle data to obtain zero-speed label data; and the training subunit is used for training the network to be trained by using the historical vehicle data as input data used for training and the zero-speed label data as labels during training in a deep learning mode to obtain a zero-speed detection model for generating a detection result of the vehicle compensation data.
More particularly, a training subunit includes: the zero-speed prediction sun unit inputs historical vehicle data into the network to be trained to obtain a zero-speed prediction result output by the network to be trained; and the function training subunit constructs a loss function based on the zero-speed prediction result and the zero-speed label data, converges based on the loss function and ends training.
It should be noted that the zero-speed detection model to be trained may be a network built in the training apparatus, and the network generally includes a network structure, such as various neural networks CNN, etc., or may be other specific networks specified by the user, such as a small network model developed based on requirements and suitable for zero-speed detection, which is not further limited in this application.
In another possible implementation manner, the zero-speed detection unit includes: a mean square error obtaining subunit for respectively obtaining the mean square error of each detection data sequence; the zero-speed judging subunit judges whether the mean square error meets a preset condition or not according to the mean square error, and if so, the current zero-speed state is determined to be used as a corresponding detection result; otherwise, determining that the current state is in a non-zero speed state as a corresponding detection result.
A result determination unit including: the proportion obtaining subunit is used for obtaining the proportion of the vehicle detection result with the detection result corresponding to the zero speed to all the vehicle detection results according to all the obtained detection results; the comparison subunit obtains the zero speed as a zero speed detection result based on the proportion being greater than or equal to the preset threshold value; and the judging subunit obtains a non-zero speed as a zero speed detection result based on the proportion smaller than a preset threshold value.
In summary, the zero offset compensation module removes the zero offset in the collected vehicle data and the parameters affecting the accuracy of the zero-speed detection result based on the zero offset estimation result output by the integrated navigation system through the zero offset estimation module, so as to obtain the vehicle compensation data along the vehicle system; the zero-speed detection module is used for preprocessing data by adopting the sliding window with the preset length so as to be suitable for a heavy truck high-vibration scene, the processed data is used for zero-speed detection, and then a zero-speed detection result is obtained, so that zero-speed detection errors caused by attitude resolving delay are avoided, detection errors of a vehicle in a low-speed slow running process are reduced, and the accuracy and efficiency of zero-speed detection are improved
Fig. 3 illustrates a physical structure diagram of an electronic device, which may include, as shown in fig. 3: a processor (processor)31, a communication Interface (communication Interface)32, a memory (memory)33 and a communication bus 34, wherein the processor 31, the communication Interface 32 and the memory 33 are communicated with each other via the communication bus 34. The processor 31 may call logic instructions in the memory 33 to perform a stall detection method for a double card, the method comprising: performing zero offset estimation based on the combined navigation to obtain a zero offset estimation result; carrying out zero offset compensation on the vehicle data collected in advance by using the zero offset estimation result to obtain vehicle compensation data; and selecting the vehicle compensation data based on a sliding window with a preset length, and carrying out zero-speed detection on the vehicle compensation data to obtain a zero-speed detection result.
In addition, the logic instructions in the memory 33 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, the present invention further provides a computer program product, the computer program product including a computer program, the computer program being stored on a non-transitory computer-readable storage medium, wherein when the computer program is executed by a processor, a computer is capable of executing the zero-speed heavy card detection method provided by the above methods, and the method includes: performing zero offset estimation based on the combined navigation to obtain a zero offset estimation result; carrying out zero offset compensation on the vehicle data collected in advance by using the zero offset estimation result to obtain vehicle compensation data; and selecting the vehicle compensation data based on a sliding window with a preset length, and carrying out zero-speed detection on the vehicle compensation data to obtain a zero-speed detection result.
In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, the computer program, when being executed by a processor, implementing the zero-speed detection method for a heavy truck provided by the above methods, the method including: performing zero offset estimation based on the combined navigation to obtain a zero offset estimation result; carrying out zero offset compensation on the vehicle data collected in advance by using the zero offset estimation result to obtain vehicle compensation data; and selecting the vehicle compensation data based on a sliding window with a preset length, and carrying out zero-speed detection on the vehicle compensation data to obtain a zero-speed detection result.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (12)
1. A zero-speed detection method of a heavy truck is characterized by comprising the following steps:
performing zero offset estimation based on the combined navigation to obtain a zero offset estimation result;
carrying out zero offset compensation on the vehicle data collected in advance by using the zero offset estimation result to obtain vehicle compensation data;
and selecting the vehicle compensation data based on a sliding window with a preset length, and carrying out zero-speed detection on the vehicle compensation data to obtain a zero-speed detection result.
2. The stall-detection method for heavy trucks of claim 1, wherein the selecting and stall-detecting the vehicle compensation data based on a sliding window with a preset length comprises:
selecting the vehicle compensation data based on preset step length sliding by using a sliding window with a preset length to obtain a plurality of detection data sequences;
respectively carrying out zero-speed detection on the plurality of detection data sequences to obtain detection results corresponding to the detection data sequences;
and obtaining a zero-speed detection result based on all the obtained detection results and a preset threshold value.
3. The method for zero-speed detection of a heavy truck according to claim 2, wherein the obtaining of the zero-speed detection result based on all the obtained detection results and a preset threshold comprises:
according to all the obtained detection results, obtaining the proportion of the vehicle detection result with the detection result of zero speed in all the vehicle detection results;
obtaining zero speed as a zero speed detection result based on the proportion being greater than or equal to a preset threshold value;
and obtaining a non-zero speed as a zero speed detection result based on the proportion smaller than the preset threshold value.
4. The method of claim 2, wherein the performing zero-speed detection on the plurality of detection data sequences to obtain detection results corresponding to the detection data sequences comprises:
inputting the detection data sequence into a zero-speed detection model to obtain a detection result output by the zero-speed detection model; the zero-speed detection model is obtained by training based on historical vehicle data and corresponding zero-speed label data.
5. The zero-speed detection method for heavy truck according to claim 4, wherein the zero-speed detection model comprises:
the characteristic extraction layer is used for respectively extracting the characteristics of each input detection data sequence to obtain the detection data characteristics respectively corresponding to each detection data sequence;
the mean square error calculation layer is used for calculating corresponding mean square errors respectively based on the characteristics of the detection data;
the zero-speed prediction layer is used for judging whether the mean square error meets a preset condition or not, and if so, determining that the current zero-speed state is used as a corresponding detection result; otherwise, determining that the current state is in a non-zero speed state as a corresponding detection result.
6. The method of claim 5, wherein the mean square error represents:
wherein, TFAMVRepresents the mean square error; z is a radical ofnRepresenting all the detected data sequences used at time n,
n represents znThe number of measurement data sequences in (1); omeganRepresents the set of all the measured data sequences,
the representation represents the noise variance of the detected data sequence in the stationary case,
which represents a sequence of measurement data,
represents the mean of the measured data sequence and FWD represents the output value of the measured data sequence at forward acceleration.
7. The method of claim 1, wherein the vehicle data comprises acceleration, and after the obtaining the zero offset estimation, the method further comprises:
and screening the vehicle data based on the zero offset estimation result, and removing the coriolis acceleration, the centripetal acceleration to the ground and the gravitational acceleration.
8. The zero-speed detection method for heavy trucks of claim 1, wherein before the zero offset compensation of the pre-collected vehicle data using the zero offset estimation result, the method further comprises: and acquiring the speed of the vehicle along the driving direction of the vehicle system based on the inertia measurement unit.
9. A zero-speed detection device for heavy trucks, comprising:
the zero offset estimation module is used for carrying out zero offset estimation based on the integrated navigation to obtain a zero offset estimation result;
the zero offset compensation module is used for carrying out zero offset compensation on the vehicle data acquired in advance by utilizing the zero offset estimation result to obtain vehicle compensation data;
and the zero-speed detection module is used for selecting the vehicle compensation data based on a sliding window with a preset length and carrying out zero-speed detection on the vehicle compensation data to obtain a zero-speed detection result.
10. An electronic device comprising a memory, a processor and a computer program stored on said memory and executable on said processor, characterized in that said processor implements the steps of the zero-speed detection method for heavy cards according to any one of claims 1 to 8 when executing said program.
11. A non-transitory computer readable storage medium, on which a computer program is stored, wherein the computer program, when being executed by a processor, implements the steps of the zero-speed detection method for a heavy card according to any one of claims 1 to 8.
12. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, carries out the steps of the method for zero-speed detection of a heavy card according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111555466.4A CN114440867A (en) | 2021-12-17 | 2021-12-17 | Zero-speed detection method and device for heavy truck |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111555466.4A CN114440867A (en) | 2021-12-17 | 2021-12-17 | Zero-speed detection method and device for heavy truck |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114440867A true CN114440867A (en) | 2022-05-06 |
Family
ID=81363577
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111555466.4A Pending CN114440867A (en) | 2021-12-17 | 2021-12-17 | Zero-speed detection method and device for heavy truck |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114440867A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106908060A (en) * | 2017-02-15 | 2017-06-30 | 东南大学 | A kind of high accuracy indoor orientation method based on MEMS inertial sensor |
| CN108362282A (en) * | 2018-01-29 | 2018-08-03 | 哈尔滨工程大学 | A kind of inertia pedestrian's localization method based on the adjustment of adaptive zero-speed section |
| CN110057381A (en) * | 2019-03-20 | 2019-07-26 | 深圳市元征科技股份有限公司 | A kind of zero velocity update method and system of navigation system |
| CN110702104A (en) * | 2019-09-27 | 2020-01-17 | 同济大学 | Inertial navigation error correction method based on vehicle zero-speed detection |
| CN110715659A (en) * | 2019-10-25 | 2020-01-21 | 高新兴物联科技有限公司 | Zero-speed detection method, pedestrian inertial navigation method, device and storage medium |
-
2021
- 2021-12-17 CN CN202111555466.4A patent/CN114440867A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106908060A (en) * | 2017-02-15 | 2017-06-30 | 东南大学 | A kind of high accuracy indoor orientation method based on MEMS inertial sensor |
| CN108362282A (en) * | 2018-01-29 | 2018-08-03 | 哈尔滨工程大学 | A kind of inertia pedestrian's localization method based on the adjustment of adaptive zero-speed section |
| CN110057381A (en) * | 2019-03-20 | 2019-07-26 | 深圳市元征科技股份有限公司 | A kind of zero velocity update method and system of navigation system |
| CN110702104A (en) * | 2019-09-27 | 2020-01-17 | 同济大学 | Inertial navigation error correction method based on vehicle zero-speed detection |
| CN110715659A (en) * | 2019-10-25 | 2020-01-21 | 高新兴物联科技有限公司 | Zero-speed detection method, pedestrian inertial navigation method, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111976389B (en) | Tire wear degree identification method and device | |
| CN111145251B (en) | Robot and synchronous positioning and mapping method thereof and computer storage device | |
| CN110715659A (en) | Zero-speed detection method, pedestrian inertial navigation method, device and storage medium | |
| AU2020356082B2 (en) | Vehicle and method for generating map corresponding to three-dimensional space | |
| EP3955209A1 (en) | Machine learning and vision-based approach to zero velocity update object detection | |
| CN112285676A (en) | Laser radar and IMU external reference calibration method and device | |
| CN111723724B (en) | Road surface obstacle recognition method and related device | |
| CN113933818A (en) | Method, device, storage medium and program product for calibrating laser radar external parameter | |
| CN112348897A (en) | Pose determination method and device, electronic equipment and computer readable storage medium | |
| JP2020003463A (en) | Vehicle's self-position estimating device | |
| CN113378694B (en) | Method and device for generating target detection and positioning system and target detection and positioning | |
| CN113176562B (en) | Multi-target tracking method, device, electronic equipment and readable storage medium | |
| US20220058401A1 (en) | Method and apparatus for estimating position | |
| CN114440867A (en) | Zero-speed detection method and device for heavy truck | |
| CN109710594B (en) | Map data validity judging method and device and readable storage medium | |
| CN116772858A (en) | Vehicle positioning method, device, positioning equipment and storage medium | |
| CN115993132A (en) | Visual inertial odometer initialization method and device and aerocar | |
| CN115628754A (en) | Odometer initialization method and device, electronic equipment and automatic driving vehicle | |
| CN114088103B (en) | Method and device for determining vehicle positioning information | |
| CN115727871A (en) | Track quality detection method and device, electronic equipment and storage medium | |
| CN114120252B (en) | Automatic driving vehicle state identification method and device, electronic equipment and vehicle | |
| CN113959433B (en) | Combined navigation method and device | |
| CN115560744A (en) | Robot, multi-sensor-based three-dimensional mapping method and storage medium | |
| CN111812668B (en) | Winding inspection device, positioning method thereof and storage medium | |
| CN110032172B (en) | Vehicle driving control system precision detection method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220830 Address after: Room 2528, Building 2, Lane 1800, Xinyang Road, Lingang New Area, China (Shanghai) Pilot Free Trade Zone, Pudong New Area, Shanghai, 201801 Applicant after: Inceptio Star Intelligent Technology (Shanghai) Co.,Ltd. Address before: Room 4, room 001, building 11, Lane 1333, Jiangnan Avenue, Changxing Town, Chongming District, Shanghai 202150 Applicant before: International network technology (Shanghai) Co.,Ltd. |