CN115991195A - Automatic detection and compensation method, device and system for wheel slip in automatic driving - Google Patents
Automatic detection and compensation method, device and system for wheel slip in automatic driving Download PDFInfo
- Publication number
- CN115991195A CN115991195A CN202310146067.5A CN202310146067A CN115991195A CN 115991195 A CN115991195 A CN 115991195A CN 202310146067 A CN202310146067 A CN 202310146067A CN 115991195 A CN115991195 A CN 115991195A
- Authority
- CN
- China
- Prior art keywords
- rain
- data
- snow
- current
- odometer
- 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
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The invention relates to an automatic detection and compensation method, device and system for wheel slip in automatic driving, wherein the method comprises the following steps: acquiring radar point cloud data and/or image information of a current scene, and reasoning whether rain/snow exists in the current weather or not based on a preset rain/snow weather model; based on the affirmative result of rain/snow weather reasoning, the speed data of the chassis odometer is fused with the speed data of the visual odometer and/or the laser radar odometer, and the fusion data of the speed per hour is output; replacing the speed data output by the chassis odometer with the fusion data of the speed per hour, and taking the fusion data as the current speed per hour; and carrying out multi-sensor fusion calculation on the current speed per hour and multi-line laser radar data and/or high-precision map matching information and/or inertial measurement unit data, and outputting current real-time positioning information.
Description
Technical Field
The invention relates to the technical field of automatic driving, in particular to an automatic detection and compensation method, device and system for wheel slip in automatic driving.
Background
In recent years, low-speed autopilot technology is rapidly developed, and more adaptive scenes such as rainy and snowy weather are required. When the road surface is wet and slippery in rainy and snowy weather, the wheels of the automatic driving vehicle possibly generate a slipping phenomenon, and if special algorithm processing is not performed on the situation, the vehicle cannot normally run, and traffic accidents can be generated under serious conditions.
The automatic driving algorithm generally comprises a positioning module, a sensing module, a pnc module and the like, wherein the positioning module needs to stably and accurately give the real-time position of the vehicle. Along with the increasing demand of reducing the cost, the low-speed unmanned vehicle is not generally provided with high-precision combined inertial navigation equipment, but obtains high-precision measured values through matching of a multi-line laser radar and a high-precision map, and realizes multi-sensor fusion positioning by combining an inertial measurement unit, a wheel speed meter and the like, so that a real-time position is provided for the vehicle.
According to the technical scheme, speed information is required to be provided for a multi-sensor fusion algorithm through wheel speed data provided by a vehicle chassis, the wheel speed data provided by the vehicle chassis are obtained through wheel rotation, when a wheel in rainy or snowy days slips, the wheel speed data error is greatly increased, so that positioning data given by the multi-sensor fusion algorithm are wrong, and if the perception on the vehicle and a pnc module continue to use the positioning data under the condition, the behavior of the vehicle is unpredictable, and accidents occur seriously.
Therefore, how to design an automatic detection and compensation method for wheel slip in automatic driving becomes a technical problem to be solved.
Disclosure of Invention
The invention discloses an automatic detection and compensation method, system and device for wheel slip in automatic driving, and aims to solve a series of problems in the prior art.
The invention adopts the following technical scheme:
in a first aspect, an embodiment of the present invention provides a method for automatically detecting and compensating for wheel slip during automatic driving, the method including:
acquiring radar point cloud data and/or image information of a current scene, and reasoning whether rain/snow exists in the current weather or not based on a preset rain/snow weather model;
based on the affirmative result of rain/snow weather reasoning, the speed data of the chassis odometer is fused with the speed data of the visual odometer and/or the laser radar odometer, and the fusion data of the speed per hour is output;
replacing the speed data output by the chassis odometer with the fusion data of the speed per hour, and taking the fusion data as the current speed per hour;
and carrying out multi-sensor fusion calculation on the current speed per hour and multi-line laser radar data and/or high-precision map matching information and/or inertial measurement unit data, and outputting current real-time positioning information.
In a possible implementation manner, in the step of acquiring radar point cloud data and/or image information of the current scene and reasoning whether the current weather has rain/snow based on a preset rain/snow weather model, the method further specifically includes:
acquiring an image sequence of a current scene based on a visual sensor, and inputting the image sequence into the preset rain and snow weather model;
extracting potential rain/snow characteristics of each image in the image sequence, and judging the current weather based on the potential rain/snow characteristics to obtain a plurality of judgment results;
and deducing whether rain/snow exists in the current weather according to a plurality of judging results, and outputting the reasoning result.
In one possible implementation manner, the preset rain and snow weather model is a weather model based on image recognition.
In a possible implementation manner, in the step of acquiring radar point cloud data and/or image information of the current scene and reasoning whether the current weather has rain/snow based on a preset rain/snow weather model, the method further specifically includes:
acquiring radar point cloud data of a current scene based on a multi-line laser radar, and inputting the radar point cloud data into the preset rain and snow weather model;
partitioning the radar point cloud data, extracting potential rain/snow features in each partition, and judging the current weather based on the potential rain/snow features in each partition to obtain a plurality of judgment results;
and deducing whether rain/snow exists in the current weather according to a plurality of judging results, and outputting the reasoning result.
In one possible implementation manner, in the step of extracting the potential rain/snow feature in each partition, determining the current weather based on the potential rain/snow feature in each partition, and obtaining a plurality of determination results, the method further specifically includes:
extracting potential rain/snow characteristics in each subarea, respectively confirming reflection value data and density data of the rain/snow characteristics in each subarea, and judging to obtain a plurality of judging results;
deducing whether rain/snow exists in the current weather according to a plurality of judging results, and outputting a first reasoning result;
and deducing the severity of the current rain/snow weather according to a plurality of judging results, and outputting a second reasoning result.
In a possible implementation manner, in the step of fusing the speed data of the chassis odometer with the speed data of the vision odometer and/or the lidar odometer based on the affirmative result of the rain/snow weather reasoning, the method further specifically includes:
and inputting a reasoning result of the rain/snow weather, and fusing the speed data of the chassis odometer with the speed data of the visual odometer and/or the laser radar odometer based on a weighted summation method to calculate the fused data of the speed per hour when the reasoning result is that the current weather is rain/snow.
In a possible implementation manner, in the step of fusing the speed data of the chassis odometer with the speed data of the vision odometer and/or the lidar odometer based on the affirmative result of the rain/snow weather reasoning, the method further specifically includes:
and inputting the first reasoning result, and when the first reasoning result is that rain/snow exists in the current weather, fusing the speed data of the chassis odometer with the speed data of the visual odometer and/or the laser radar odometer based on a weighted summation method, and calculating a weight coefficient in fusion calculation based on the second reasoning result.
In one possible implementation manner, in the step of performing multi-sensor fusion calculation on the current speed of time and multi-line laser radar and/or high-precision map matching information and/or inertial measurement unit data, the method further specifically includes:
and inputting the current speed per hour and/or multi-line laser radar data and/or high-precision map matching information and/or inertial measurement unit data, calculating current real-time positioning information based on an extended Kalman filtering algorithm, and outputting the real-time positioning information.
In a second aspect, an embodiment of the present invention provides an apparatus for automatically detecting and compensating wheel slip in automatic driving, including:
the sensing module is used for acquiring radar point cloud data and/or image information of a current scene and reasoning whether rain/snow exists in the current weather or not based on a preset rain/snow weather model;
the fusion module is used for fusing the speed data of the chassis odometer with the speed data of the visual odometer and/or the laser radar odometer based on the positive result of rain/snow weather reasoning and outputting the fused data of the speed per hour;
the compensation module is used for replacing the speed data output by the chassis odometer with the fusion data of the speed per hour and taking the fusion data as the current speed per hour;
and the positioning module is used for carrying out multi-sensor fusion calculation on the current speed per hour and multi-line laser radar data and/or high-precision map matching information and/or inertial measurement unit data, and outputting current real-time positioning information.
In a third aspect, an embodiment of the present invention provides an autopilot system, including a positioning subsystem, a decision subsystem, and a control subsystem, wherein:
the positioning subsystem comprises an automatic detection and compensation device for wheel slip in automatic driving according to claim 9, and is used for calculating real-time positioning information of an automatic driving vehicle in real time and sending the real-time positioning information to the decision subsystem;
the decision subsystem is used for making a decision on the automatic driving vehicle according to the real-time positioning information and transmitting decision information to the control system;
the control subsystem is used for controlling the automatic driving vehicle based on the decision information transmitted by the decision subsystem.
In a fourth aspect, an embodiment of the present invention provides an autonomous vehicle, characterized in that the autonomous vehicle comprises an autonomous system as described above.
In a fifth aspect, an embodiment of the present invention provides an electronic device, including:
one or more processors;
a memory for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of automatically detecting and compensating for wheel slip as described in any of the preceding claims.
In a sixth aspect, an embodiment of the present invention provides a readable storage medium, where an automatic detection and compensation program for wheel slip is stored, where the automatic detection and compensation program for wheel slip is executed by a processor, and the automatic detection and compensation method for wheel slip according to any one of the above claims can be implemented.
The technical scheme adopted by the invention can achieve the following beneficial effects:
the invention mainly provides an automatic detection and compensation method for wheel slip in automatic driving, which can acquire data of a current running scene based on a visual sensor or a multi-line laser radar, deduce whether rain/snow weather exists currently according to the data of the current running scene, and if the rain/snow weather exists, detect that the wheel slip occurs by default, and then consider to compensate and correct the current speed and positioning so as to obtain more accurate positioning information.
Based on rain/snow weather, the data recorded by the chassis odometer is fused with the data recorded by the visual odometer and the laser radar odometer, or further based on the severity of rain/snow, the data recorded by the chassis odometer, the visual odometer and the laser radar odometer are weighted and summed to compensate errors caused by wheel slip so as to obtain more stable and accurate current speed information.
Further, the compensated current speed and/or multi-line laser radar data and/or high-precision map matching information and/or inertial measurement unit data are fused and calculated to obtain the current real-time positioning information, so that the stability and precision of the positioning module are improved, the automatic driving system can conveniently make correct road planning or other control instructions, and abnormal behaviors of the vehicle are prevented.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments are briefly described below to form a part of the present invention, and the exemplary embodiments of the present invention and the description thereof illustrate the present invention and do not constitute undue limitations of the present invention. In the drawings:
FIG. 1 is a flow chart of an automatic detection and compensation method for wheel slip during autopilot in accordance with an embodiment of the present invention;
FIG. 2 is a schematic diagram of an apparatus for automatically detecting and compensating wheel slip during autopilot according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an autopilot system in an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to specific embodiments of the present invention and corresponding drawings. In the description of the present invention, it should be noted that the term "or" is generally employed in its sense including "and/or" unless the content clearly dictates otherwise.
It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the prior art, an automatic driving automobile cannot detect whether wheels slip in rainy/snowy weather, and if special algorithm processing is not performed at this time, an automatic driving system may not be able to make correct automatic driving judgment, so that the automobile cannot run, and even serious traffic accidents occur.
In addition, although fusion calculation can be performed based on the data of the visual odometer and the chassis mileage at present to obtain more accurate speed per hour and/or positioning information, the occurrence of rain/snow weather is small, calculation resources are very consumed if the fusion calculation of the vehicle speed is always started, and the calculation of the fusion algorithm also consumes a certain time, so that the real-time performance is inferior to that of the chassis odometer alone.
In order to solve the above-mentioned problems, in the present embodiment, an automatic detection and compensation method for wheel slip during automatic driving is provided, and the method includes steps S110 to S140, as follows:
s110, acquiring radar point cloud data and/or image information of a current scene, and reasoning whether rain/snow exists in the current weather or not based on a preset rain/snow weather model.
In one possible implementation manner, the step S110 may be implemented in the following manner 1, where the manner 1 includes:
acquiring an image sequence of a current scene based on a visual sensor, and inputting the image sequence into a preset rain and snow weather model;
extracting potential rain/snow characteristics of each image in the image sequence, and judging the current weather based on the potential rain/snow characteristics to obtain a plurality of judgment results;
and deducing whether rain/snow exists in the current weather according to the multiple judging results, and outputting the reasoning result.
Specifically, the vision sensor arranged on the automatic driving vehicle mainly comprises a vision camera, including a monocular, binocular stereo vision, panoramic vision and infrared camera; in one possible implementation, the vision sensor may use any vehicle-mounted camera, preferably a monocular or infrared camera, to capture images of the current scene, and make a recognition determination as to whether there is rain/snow in the current weather based on a rain/snow weather model identified by the images.
Specifically, the vehicle-mounted camera can acquire images of a current scene at regular time according to a preset time rule, form a series of image sequences, input the acquired image sequences into a vehicle-mounted processor (such as a vehicle-mounted CPU), and perform image recognition processing by the vehicle-mounted processor.
Specifically, the processor is provided with a preset rain and snow weather model, the rain and snow weather model is trained by the CNN convolutional neural network, in one possible implementation manner, an input layer of the rain and snow weather model is used for receiving an image of a current scene transmitted by the vehicle-mounted camera, the convolutional layer can extract weather features in an image sequence, the pooling layer can represent the image by using higher-level features, the full-connection layer can judge by combining the extracted feature information, and finally whether the image is an image containing rain and snow is judged.
Specifically, the characteristic parameters of rain/snow in the image can be set or adjusted according to actual needs.
Further, the preset rain and snow weather model judges each image in the image sequence in sequence, and outputs a weather judging result of each image, wherein the judging result is as follows: no rain or snow, rain or snow is present.
Further, after the weather judgment result of each image in the image sequence is output, whether the current weather has rain/snow is inferred by adopting a voting mode, and a rain/snow identification result is obtained by adopting a voting decision mode, so that the rain/snow identification result is reduced by abnormal data interference, the robustness of a rain/snow weather model is enhanced, and the accuracy of rain/snow weather identification is improved.
Specifically, the weather model in the above manner 1 is a weather model based on image recognition, and any weather model disclosed in the prior art, such as VGG16, resNet50, iceptionV3, denseNet121, leNet-5, mobileNetV2, and efficentent netb0, may be selected, and the data set during model training may be directly selected from images captured by the vehicle camera in daily life.
In one possible implementation manner, the step S110 may be implemented in the following manner 2, where the manner 2 includes:
acquiring radar point cloud data of a current scene based on a multi-line laser radar, and inputting the radar point cloud data into a preset rain and snow weather model;
partitioning Lei Dadian cloud data, extracting potential rain/snow characteristics in each partition, and judging the current weather based on the potential rain/snow characteristics in each partition to obtain a plurality of judgment results;
and deducing whether rain/snow exists in the current weather according to the multiple judging results, and outputting the reasoning result.
Specifically, the multi-line laser radar arranged on the automatic driving vehicle can acquire radar point cloud data of a current scene according to a preset rule, input the data into a vehicle-mounted processor (such as a vehicle-mounted CPU), and perform data identification processing by the vehicle-mounted processor. The vehicle-mounted processor can partition the radar point cloud data and extract the rain/snow characteristics in each partition.
Specifically, due to the wavelength and scanning characteristics of the laser radar, when the laser radar scans raindrops or snowflakes, the raindrops/snowflakes and the air belong to different media, and the transmission loss of light along the media is high, so that the reflection value of the raindrops/snowflakes is abnormal, and the abnormal value can be considered to have the possibility of rainy/snowy weather at the moment; in addition, because the spatial distribution of raindrops/snowflakes is different from most objects, the local density in space is lower, and the data with small density in local space can be considered as potential rain/snow data, in one possible implementation, the data with abnormal reflection value and/or density value in the subarea is preferentially coded.
It will be appreciated by those skilled in the art that the number, size, reflective value/density value parameter thresholds, etc. of the partitions in the Lei Dadian cloud data are all variable parameters, and thus one or more of the above parameters may be selected or adjusted according to actual needs without departing from the spirit of the invention.
Further, the determination of potential rain/snow characteristics in the radar point cloud data of each partition may be performed in parallel by a plurality of independent models, which may be obtained by decomposing one rain/snow weather model, or may be each separately constructed.
In one possible implementation, the radar point cloud data for each partition is uniformly sampled and determined in parallel using a plurality of machine-learned decision trees, the depth and number of which are set according to the desired rain/snow recognition rate.
It will be understood by those skilled in the art that, since the data acquired in the mode 2 is radar point cloud data and the image data of the current scene is acquired in the mode 1, the rain and snow weather model in the mode 2 is not the rain and snow weather model constructed in the mode 1.
In one possible implementation, the potential rain/snow characteristics and the plurality of determinations are stored in a cache of the onboard processor.
Further, after the rain/snow judging results of each subarea are output, whether the current weather has rain/snow is inferred by adopting a voting mode, and the rain/snow identifying result is obtained by adopting a voting decision mode, so that the rain/snow identifying result is reduced by abnormal data interference, the robustness of a rain/snow weather model is enhanced, and the accuracy of rain/snow weather identification is improved.
In one possible implementation, after the rain/snow judging result of each subarea is output, if the subarea judged to have the rain/snow weather is more than the subarea judged to have no rain/snow weather, the current scene is inferred to have the rain/snow, and if the subarea judged to have the rain/snow weather is less than the subarea judged to have no rain/snow weather, the current scene is inferred to have no rain/snow.
In one possible implementation manner, the above step S110 may be implemented in the following manner 3, where the manner 3 includes:
acquiring an image sequence of a current scene based on a visual sensor, and reasoning whether the current scene has rain/snow weather according to the mode 1;
acquiring radar point cloud data of a current scene based on a multi-line laser radar, and reasoning whether rain/snow weather exists in the current scene according to the mode 2;
when any reasoning result is that the current scene has rain/snow weather, finally, the current weather has the rain/snow weather by priority reasoning.
Specifically, in this mode 3, the weather judging methods of the current scene in modes 1 and 2 are adopted at the same time, which is equivalent to redundancy judgment, and the vision sensor and the multi-line laser radar sensor work at the same time, and judge and infer whether there is rain/snow in the current scene based on respective preset rain/snow weather models, and when the two models infer different results, the weather of rain/snow in the current scene is preferentially judged in order to ensure the safety and stability of automatic driving, although a part of computing resources may be sacrificed, or the situation of inference errors may occur, the accident of the vehicle in the automatic driving process can be avoided to the greatest extent.
In an alternative embodiment, the reasoning in the mode 3 may be performed continuously for a plurality of times, and when the number of reasoning about the finally absent rain/snow weather is greater than the number of reasoning about the existing rain/snow weather, the weather reasoning result of the current scene may be corrected to be that the weather/snow weather is not actually present, and then the following steps S120 to S140 are not required.
And S120, based on the affirmative result of rain/snow weather reasoning, fusing the speed data of the chassis odometer with the speed data of the visual odometer and/or the laser radar odometer, and outputting the fused data of the speed per hour.
In a possible implementation manner, the weather reasoning result in this step is derived by any one of the modes 1-3, and when the current weather reasoning result is that there is rain/snow weather, the current speed recorded by the chassis odometer is obviously greater than the actual speed of the vehicle after the wheel has slipped and the actual speed of the vehicle is obviously greater than the slip, so that the positioning and automatic driving decisions of the vehicle are abnormal, and this step is used for compensating the speed of the vehicle so as to obtain the current speed of the vehicle which is closer to the actual speed of the vehicle.
Specifically, when the reasoning result is that rain/snow exists in the current weather, the speed data of the chassis odometer is fused with the speed data of the visual odometer and/or the laser radar odometer based on a weighted summation method, so that the fused data of the speed per hour is calculated. That is, the speed data of the chassis odometer may be integrated with only the speed data of the visual odometer or the speed data of the laser radar odometer, or may be integrated with the three.
Specifically, the laser radar odometer calculates the calculated relative speed through the point cloud matching result between two continuous frames; the visual odometer calculates the relative speed through the visual information between two successive frames, such as a characteristic point extraction method, an optical flow method and the like.
Those skilled in the art will appreciate that calculating the current speed based on a lidar odometer or a visual odometer may be performed by any of the methods disclosed in the prior art, examples of which are not explicitly recited herein.
In one possible embodiment, the weighting coefficients may be derived based on empirical values, such as V, when using a weighted summation method to calculate the fused values of velocity Current speed of time ＝a*V Visual odometer +b*V Laser radar odometer +c*V Chassis odometer Where a, b and c are weight coefficients, the specific data for a, b, c may be 0.2,0.2,0.6, for example.
In one possible implementation manner, when the weighted summation method is used for calculation, the weight coefficient can be calculated according to the severity degree of the current rain/snow weather, and when the severity degree of the current rain/snow weather is determined, the method can be implemented based on the mode 2, and specifically includes the following steps:
acquiring radar point cloud data of a current scene based on a multi-line laser radar, and inputting the radar point cloud data into a preset rain and snow weather model;
partitioning Lei Dadian cloud data, extracting potential rain/snow characteristics in each partition, respectively confirming reflection value data and density data of the rain/snow characteristics in each partition, and judging to obtain a plurality of judgment results;
deducing whether rain/snow exists in the current weather according to the multiple judging results, and outputting a first reasoning result;
reasoning the severity degree of the current rain/snow weather according to the plurality of judging results, and outputting a second reasoning result;
and inputting a first reasoning result, and fusing the speed data of the chassis odometer with the speed data of the visual odometer and/or the laser radar odometer based on a weighted summation method when the first reasoning result is that rain/snow exists in the current weather, and calculating a weight coefficient in fused calculation based on a second reasoning result.
Specifically, the first inference result may be directly obtained according to the steps in the above-described mode 2.
In one possible implementation manner, in the mode 2, a threshold value of the reflection value and/or the density value in the subarea of each lightning point cloud data may be further defined, and when the reflection value and/or the density value in the subarea is greater than a preset threshold value, it may be considered that the rain/snow weather is serious at this time.
In one possible implementation manner, after the rain/snow judging result of each subarea is output, if the subarea judged to have the rain/snow weather is more than the subarea judged to have no rain/snow weather, deducing that the rain/snow exists in the current scene, and obtaining a first reasoning result; further, the number of the reflection values and/or the density values larger than the preset threshold value in each subarea can be detected, the severity of the current rain/snow weather is inferred according to the number, and in general, the more the number of the reflection values and/or the density values larger than the preset threshold value is, the more serious the rain/snow weather in the current scene is proved, and at the moment, a second inference result is obtained.
When the second reasoning result shows that the current rain/snow weather is severe, the weight coefficient of the visual odometer and/or the laser radar odometer can be gradually increased, and the weight coefficient of the chassis odometer can be reduced, so that more accurate fusion speed can be obtained.
S130, replacing the speed data output by the chassis odometer with the fusion data of the speed per hour, and taking the fusion data as the current speed per hour.
Specifically, the current speed of time obtained in this step may be input into the system of the unmanned area in order for it to make a more accurate decision.
And S140, carrying out multi-sensor fusion calculation on the current speed per hour and multi-line laser radar data and/or high-precision map matching information and/or inertial measurement unit data, and outputting current real-time positioning information.
In one possible implementation, current speed of time and/or multi-line lidar data and/or high-precision map matching information and/or inertial measurement unit data are input, current real-time positioning information is calculated based on an extended kalman filter algorithm, and the real-time positioning information is output.
It will be appreciated by those skilled in the art that extended kalman filtering is a filtering algorithm based on optimal estimation that iteratively gives a value of least uncertainty by comprehensively considering the estimated value and the measured value. The formula of the extended kalman filter is known, so that the expected value can be obtained only by inputting the current speed and/or multi-line laser radar data and/or high-precision map matching information and/or an inertial measurement unit into the formula.
In this step, the compensated current vehicle speed and/or multi-line laser radar data and/or high-precision map matching information and/or inertial measurement unit data are fused and calculated to obtain the current real-time positioning information, so that the stability and precision of the positioning module 240 are improved, and the automatic driving system can conveniently make correct road planning or other control instructions, thereby preventing abnormal behavior of the vehicle.
In one embodiment, the invention also provides an apparatus for automatically detecting and compensating wheel slip in autopilot, comprising:
the sensing module 210 is configured to acquire radar point cloud data and/or image information of a current scene, and infer whether rain/snow exists in the current weather based on a preset rain/snow weather model. Specifically, the sensing module 210 may execute the method in step S110, which is not described herein.
And the fusion module 220 is used for fusing the speed data of the chassis odometer with the speed data of the visual odometer and/or the laser radar odometer based on the affirmative result of the rain/snow weather reasoning and outputting the fused data of the speed per hour. Specifically, the fusion module 220 may execute the method in step S120, which is not described herein.
And the compensation module 230 is used for replacing the speed data output by the chassis odometer with the fusion data of the speed per hour and taking the fusion data as the current speed per hour. Specifically, the compensation module 230 may execute the method in step S120, which is not described herein.
The positioning module 240 is configured to perform multi-sensor fusion calculation on the current speed per hour and multi-line laser radar data and/or high-precision map matching information and/or inertial measurement unit data, and output current real-time positioning information. Specifically, the positioning module 240 may execute the method in step S140, which is not described herein.
As shown in fig. 3, an embodiment of the present invention provides an autopilot system, which includes a positioning module 310, a decision subsystem 320 and a control subsystem 330, wherein the positioning module 310 includes the above-mentioned automatic detection and compensation device for wheel slip in autopilot, and is configured to calculate real-time positioning information of the autopilot vehicle in real time, and send the real-time positioning information to the decision subsystem 320; the decision subsystem 320 is used for making a decision on the automatic driving vehicle according to the real-time positioning information and transmitting the decision information to the control system; the control subsystem 330 is configured to control the autonomous vehicle based on the decision information transmitted by the decision subsystem 320.
The embodiment of the invention provides an automatic driving vehicle, which comprises the automatic driving system. Illustratively, the autonomous vehicle further includes an autonomous vehicle and other constituent structures, such as a drive system for driving the vehicle forward, a signal transmission system for signal transmission, etc., as embodiments of the present invention are not limited in this regard.
The embodiment of the invention also provides electronic equipment, which comprises a memory and a processor, wherein the memory stores a computer program operated by the processor, and the computer program enables the processor to execute the automatic detection and compensation method of the wheel slip before when the computer program is operated by the processor. The memory may also store various applications and various data, such as various data used and/or generated by the applications, and the like. The processor may be a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), or other form of processing unit with data processing and/or instruction execution capabilities.
The embodiment of the invention also provides a storage medium, and the storage medium stores a computer program which is run by a processor and when being run by the processor, the computer program enables the processor to execute the automatic detection and compensation method for the wheel slip in the automatic driving. By way of example, computer storage media may comprise memory cards for smart phones, memory components for tablet computers, hard disks for personal computers, read-only memory (ROM), erasable programmable read-only memory (EPROM), portable compact disc read-only memory (CD-ROM), USB memory, or any combination of the preceding. The computer-readable storage medium may be any combination of one or more computer-readable storage media.
Although the illustrative embodiments have been described herein with reference to the accompanying drawings, it is to be understood that the above illustrative embodiments are merely illustrative and are not intended to limit the scope of the present application thereto. Various changes and modifications may be made therein by one of ordinary skill in the art without departing from the scope and spirit of the present application. All such changes and modifications are intended to be included within the scope of the present application as set forth in the appended claims.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the present application may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in order to streamline the application and aid in understanding one or more of the various inventive aspects, various features of the application are sometimes grouped together in a single embodiment, figure, or description thereof in the description of exemplary embodiments of the application. However, the method of this application should not be construed to reflect the following intent: i.e., the claimed application requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this application.
It will be understood by those skilled in the art that all of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be combined in any combination, except combinations where the features are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
The embodiments of the present invention have been described above with reference to the accompanying drawings, but the present invention is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and many forms may be made by those having ordinary skill in the art without departing from the spirit of the present invention and the scope of the claims, which are to be protected by the present invention.
Claims (13)
1. An automatic detection and compensation method for wheel slip in automatic driving, the method comprising:
acquiring radar point cloud data and/or image information of a current scene, and reasoning whether rain/snow exists in the current weather or not based on a preset rain/snow weather model;
based on the affirmative result of rain/snow weather reasoning, the speed data of the chassis odometer is fused with the speed data of the visual odometer and/or the laser radar odometer, and the fusion data of the speed per hour is output;
replacing the speed data output by the chassis odometer with the fusion data of the speed per hour, and taking the fusion data as the current speed per hour;
and carrying out multi-sensor fusion calculation on the current speed per hour and multi-line laser radar data and/or high-precision map matching information and/or inertial measurement unit data, and outputting current real-time positioning information.
2. The method for automatically detecting and compensating for wheel slip in automatic driving according to claim 1, wherein in the step of acquiring radar point cloud data and/or image information of a current scene and reasoning whether the current weather has rain/snow based on a preset rain/snow weather model, the method further specifically comprises:
acquiring an image sequence of a current scene based on a visual sensor, and inputting the image sequence into the preset rain and snow weather model;
extracting potential rain/snow characteristics of each image in the image sequence, and judging the current weather based on the potential rain/snow characteristics to obtain a plurality of judgment results;
and deducing whether rain/snow exists in the current weather according to a plurality of judging results, and outputting the reasoning result.
3. The method for automatically detecting and compensating for wheel slip in automatic driving according to claim 2, wherein the predetermined rain and snow weather model is a weather model based on image recognition.
4. The method for automatically detecting and compensating for wheel slip in automatic driving according to claim 1, wherein in the step of acquiring radar point cloud data and/or image information of a current scene and reasoning whether the current weather has rain/snow based on a preset rain/snow weather model, the method further specifically comprises:
acquiring radar point cloud data of a current scene based on a multi-line laser radar, and inputting the radar point cloud data into the preset rain and snow weather model;
partitioning the radar point cloud data, extracting potential rain/snow features in each partition, and judging the current weather based on the potential rain/snow features in each partition to obtain a plurality of judgment results;
and deducing whether rain/snow exists in the current weather according to a plurality of judging results, and outputting the reasoning result.
5. The method for automatically detecting and compensating for wheel slip in automatic driving according to claim 4, wherein in the step of extracting the potential rain/snow characteristics in each zone, determining the current weather based on the potential rain/snow characteristics in each zone, and obtaining a plurality of determination results, further specifically comprising:
extracting potential rain/snow characteristics in each subarea, respectively confirming reflection value data and density data of the rain/snow characteristics in each subarea, and judging to obtain a plurality of judging results;
deducing whether rain/snow exists in the current weather according to a plurality of judging results, and outputting a first reasoning result;
and deducing the severity of the current rain/snow weather according to a plurality of judging results, and outputting a second reasoning result.
6. The method for automatically detecting and compensating for wheel slip in autopilot of claim 4 wherein in the step of fusing the speed data of the chassis odometer with the speed data of the vision odometer and/or the lidar odometer based on the affirmative outcome of the rain/snow weather reasoning, further comprising:
and inputting a reasoning result of the rain/snow weather, and fusing the speed data of the chassis odometer with the speed data of the visual odometer and/or the laser radar odometer based on a weighted summation method to calculate the fused data of the speed per hour when the reasoning result is that the current weather is rain/snow.
7. The method for automatically detecting and compensating for wheel slip in autopilot of claim 5 wherein in the step of fusing the speed data of the chassis odometer with the speed data of the vision odometer and/or the lidar odometer based on the affirmative outcome of the rain/snow weather reasoning, further comprising:
and inputting the first reasoning result, and when the first reasoning result is that rain/snow exists in the current weather, fusing the speed data of the chassis odometer with the speed data of the visual odometer and/or the laser radar odometer based on a weighted summation method, and calculating a weight coefficient in fusion calculation based on the second reasoning result.
8. The method for automatically detecting and compensating for wheel slip in automatic driving according to claim 1, wherein in the step of performing multi-sensor fusion calculation of the current speed per hour with multi-line lidar and/or high-precision map matching information and/or inertial measurement unit data, the method further comprises the following steps:
and inputting the current speed per hour and/or multi-line laser radar data and/or high-precision map matching information and/or inertial measurement unit data, calculating current real-time positioning information based on an extended Kalman filtering algorithm, and outputting the real-time positioning information.
9. An automatic detection and compensation device for wheel slip in automatic driving, comprising:
the sensing module is used for acquiring radar point cloud data and/or image information of a current scene and reasoning whether rain/snow exists in the current weather or not based on a preset rain/snow weather model;
the fusion module is used for fusing the speed data of the chassis odometer with the speed data of the visual odometer and/or the laser radar odometer based on the positive result of rain/snow weather reasoning and outputting the fused data of the speed per hour;
the compensation module is used for replacing the speed data output by the chassis odometer with the fusion data of the speed per hour and taking the fusion data as the current speed per hour;
and the positioning module is used for carrying out multi-sensor fusion calculation on the current speed per hour and multi-line laser radar data and/or high-precision map matching information and/or inertial measurement unit data, and outputting current real-time positioning information.
10. An automatic driving system is characterized by comprising a positioning subsystem, a decision subsystem and a control subsystem;
the positioning subsystem comprises an automatic detection and compensation device for wheel slip in automatic driving according to claim 9, and is used for calculating real-time positioning information of an automatic driving vehicle in real time and sending the real-time positioning information to the decision subsystem;
the decision subsystem is used for making a decision on the automatic driving vehicle according to the real-time positioning information and transmitting decision information to the control system;
the control subsystem is used for controlling the automatic driving vehicle based on the decision information transmitted by the decision subsystem.
11. An autonomous vehicle comprising the autonomous system of claim 10.
12. An electronic device, comprising:
one or more processors;
a memory for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of automatic detection and compensation of wheel slip of any of claims 1-8.
13. A readable storage medium, wherein an automatic wheel slip detection and compensation program is stored on the readable storage medium, and when the automatic wheel slip detection and compensation program is executed by a processor, the automatic wheel slip detection and compensation method according to any one of claims 1 to 8 can be implemented.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310146067.5A CN115991195A (en) | 2023-02-21 | 2023-02-21 | Automatic detection and compensation method, device and system for wheel slip in automatic driving |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310146067.5A CN115991195A (en) | 2023-02-21 | 2023-02-21 | Automatic detection and compensation method, device and system for wheel slip in automatic driving |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115991195A true CN115991195A (en) | 2023-04-21 |
Family
ID=85995143
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310146067.5A Pending CN115991195A (en) | 2023-02-21 | 2023-02-21 | Automatic detection and compensation method, device and system for wheel slip in automatic driving |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115991195A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117647852A (en) * | 2024-01-29 | 2024-03-05 | 吉咖智能机器人有限公司 | Weather state detection method and device, electronic equipment and storage medium |
-
2023
- 2023-02-21 CN CN202310146067.5A patent/CN115991195A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117647852A (en) * | 2024-01-29 | 2024-03-05 | 吉咖智能机器人有限公司 | Weather state detection method and device, electronic equipment and storage medium |
| CN117647852B (en) * | 2024-01-29 | 2024-04-09 | 吉咖智能机器人有限公司 | Weather state detection method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11608040B2 (en) | Traction control based on friction coefficient estimation | |
| CN110031019B (en) | Slip detection processing method for automatic driving vehicle | |
| CN112154455B (en) | Data processing method, equipment and movable platform | |
| US11501638B2 (en) | Traffic flow estimation apparatus, traffic flow estimation method, and storage medium | |
| CN112466141A (en) | Vehicle-road-collaboration-oriented intelligent network connection end equipment interaction method, system and storage medium | |
| US11574541B2 (en) | Information processing device, information processing system, program, and information processing method | |
| CN113071505A (en) | Method, device and equipment for determining driving behavior habits and controlling vehicle running | |
| KR20210076139A (en) | How to create car control settings | |
| JP2020071122A (en) | Own vehicle position estimation device | |
| CN115027428B (en) | Obstacle meeting braking method, device and equipment for vehicle and storage medium | |
| CN115991195A (en) | Automatic detection and compensation method, device and system for wheel slip in automatic driving | |
| CN115993597A (en) | Visual radar perception fusion method and terminal equipment | |
| CN110550041B (en) | Road adhesion coefficient estimation method based on cloud data sharing | |
| CN114274972A (en) | Scene recognition in an autonomous driving environment | |
| CN110989619B (en) | Method, apparatus, device and storage medium for locating objects | |
| CN110888441B (en) | Gyroscope-based wheelchair control system | |
| CN116772858A (en) | Vehicle positioning method, device, positioning equipment and storage medium | |
| JP7174131B2 (en) | Determination device, determination method and determination program | |
| CN116358584A (en) | Automatic driving vehicle path planning method, device, equipment and medium | |
| CN116295496A (en) | Automatic driving vehicle path planning method, device, equipment and medium | |
| US20230077516A1 (en) | Systems and methods for utilizing machine learning for vehicle detection of adverse conditions | |
| CN112947390B (en) | Intelligent networking automobile safety control method and system based on environmental risk assessment | |
| CN110333517B (en) | Obstacle sensing method, obstacle sensing device and storage medium | |
| CN112660146A (en) | Method, apparatus, device and storage medium for controlling vehicle | |
| KR102405818B1 (en) | Method of removing noise, apparatus for removing noise, and computer program for the method |
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 |