CN113353066B - Obstacle touch recognition method, device, equipment and storage medium - Google Patents
Obstacle touch recognition method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113353066B CN113353066B CN202110740038.2A CN202110740038A CN113353066B CN 113353066 B CN113353066 B CN 113353066B CN 202110740038 A CN202110740038 A CN 202110740038A CN 113353066 B CN113353066 B CN 113353066B
- Authority
- CN
- China
- Prior art keywords
- target
- fuzzy
- target vehicle
- vehicle speed
- touch recognition
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000012545 processing Methods 0.000 claims abstract description 44
- 230000001133 acceleration Effects 0.000 claims abstract description 23
- 238000001914 filtration Methods 0.000 claims abstract description 13
- 230000006870 function Effects 0.000 claims description 27
- 230000008569 process Effects 0.000 claims description 7
- 230000005484 gravity Effects 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 8
- 239000011159 matrix material Substances 0.000 description 4
- 238000001514 detection method Methods 0.000 description 2
- 230000004438 eyesight Effects 0.000 description 2
- 230000010365 information processing Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 230000016776 visual perception Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/06—Automatic manoeuvring for parking
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2520/00—Input parameters relating to overall vehicle dynamics
- B60W2520/10—Longitudinal speed
- B60W2520/105—Longitudinal acceleration
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2520/00—Input parameters relating to overall vehicle dynamics
- B60W2520/28—Wheel speed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2552/00—Input parameters relating to infrastructure
- B60W2552/50—Barriers
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
- Traffic Control Systems (AREA)
Abstract
The application discloses a method, a device, equipment and a storage medium for identifying obstacle touch, wherein the method comprises the following steps: when the target vehicle is in an automatic parking mode, acquiring speed information of the target vehicle; acquiring acceleration information and wheel rotation speed information of a target vehicle; based on the acceleration information and the wheel rotation speed information, carrying out Kalman filtering processing on the vehicle speed information to obtain target vehicle speed information; acquiring target impact degree information of a target vehicle; fuzzification processing is carried out on the target vehicle speed information and the target impact degree information to obtain a target vehicle speed fuzzification amount and a target impact degree fuzzification amount; fuzzy reasoning is carried out on the target vehicle speed fuzzy quantity and the target impact degree fuzzy quantity based on the fuzzy controller, so that a target touch recognition result fuzzy quantity is obtained; and performing defuzzification processing on the fuzzy amount of the target touch recognition result to obtain the obstacle touch recognition result of the wheels of the target vehicle. By utilizing the technical scheme provided by the application, the accuracy of obstacle touch recognition of the wheel can be improved.
Description
Technical Field
The application relates to the technical field of automatic driving, in particular to a method, a device, equipment and a storage medium for identifying obstacle touch.
Background
The existing automatic parking function mainly relies on visual perception for identifying obstacles, image data of the surrounding environment of a vehicle is collected through a visual sensor, and target detection and target positioning are carried out on the image data, so that the obstacles around the vehicle are determined.
However, when the vision sensor is affected by external factors such as darker light of the parking environment, the recognition accuracy for the obstacle may be lowered; meanwhile, when the tail of a vehicle approaches an obstacle in the parking process, the vision sensor enters a sensing blind area, the obstacle cannot be detected in real time, excessive torque output can be increased for the vehicle to forcibly pass over the obstacle, riding experience of a user is affected, and even collision of the vehicle can be caused, so that a more effective technical scheme needs to be provided.
Disclosure of Invention
The application provides a method, a device, equipment and a storage medium for identifying obstacle touch, which can improve the accuracy of obstacle touch identification of wheels so as to avoid a vehicle from crossing the obstacle forcefully and improve riding experience of a user, and the technical scheme of the application is as follows:
in one aspect, a method for identifying obstacle touches is provided, the method comprising:
When a target vehicle is in an automatic parking mode, acquiring speed information of the target vehicle;
Acquiring acceleration information and wheel rotation speed information of the target vehicle;
Based on the acceleration information and the wheel rotation speed information, carrying out Kalman filtering processing on the vehicle speed information to obtain target vehicle speed information;
acquiring target impact degree information of the target vehicle;
Fuzzification processing is carried out on the target vehicle speed information and the target impact degree information to obtain a target vehicle speed fuzzification amount and a target impact degree fuzzification amount;
performing fuzzy reasoning on the target vehicle speed fuzzy quantity and the target impact degree fuzzy quantity based on a fuzzy controller to obtain a target touch recognition result fuzzy quantity;
And performing defuzzification processing on the fuzzy amount of the target touch recognition result to obtain an obstacle touch recognition result of the wheel of the target vehicle.
In another aspect, there is provided an obstacle touch recognition apparatus, the apparatus including:
The vehicle speed information acquisition module is used for acquiring the vehicle speed information of the target vehicle when the target vehicle is in an automatic parking mode;
The information acquisition module is used for acquiring acceleration information and wheel rotation speed information of the target vehicle;
The Kalman filtering processing module is used for carrying out Kalman filtering processing on the vehicle speed information based on the acceleration information and the wheel rotating speed information to obtain target vehicle speed information;
The target impact degree information acquisition module is used for acquiring the target impact degree information of the target vehicle;
The fuzzification processing module is used for fuzzifying the target vehicle speed information and the target impact degree information to obtain a target vehicle speed fuzzification amount and a target impact degree fuzzification amount;
The fuzzy reasoning module is used for carrying out fuzzy reasoning on the target vehicle speed fuzzy quantity and the target impact degree fuzzy quantity based on a fuzzy controller to obtain a target touch recognition result fuzzy quantity;
and the defuzzification processing module is used for defuzzifying the target touch recognition result fuzzy quantity to obtain the obstacle touch recognition result of the wheels of the target vehicle.
In another aspect, an obstacle touch recognition device is provided, where the device includes a processor and a memory, where at least one instruction or at least one program is stored in the memory, and the at least one instruction or the at least one program is loaded and executed by the processor to implement an obstacle touch recognition method as described above.
In another aspect, a computer readable storage medium is provided, where at least one instruction or at least one program is stored, where the at least one instruction or the at least one program is loaded and executed by a processor to implement the obstacle touch recognition method as described above.
The obstacle touch recognition method, device, equipment and storage medium provided by the application have the following technical effects:
According to the technical scheme provided by the application, the target vehicle speed information is obtained by carrying out Kalman filtering processing on the vehicle speed information, obstacle touch recognition is carried out based on the target vehicle speed information and the target impact degree information, when the wheels of the target vehicle are recognized to touch the obstacle, the target vehicle is controlled to stop, the accuracy of obstacle touch recognition of the wheels can be improved, thereby avoiding that the vehicle outputs excessive torque due to forced obstacle crossing, generating accidents and improving riding experience of users.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the application, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of an obstacle touch recognition method according to an embodiment of the present application;
FIG. 2 is a schematic flow chart of a Kalman filtering processing method according to an embodiment of the present application;
FIG. 3 is a schematic flow chart of a fuzzy rule generating method according to an embodiment of the present application;
FIG. 4 is a schematic flow chart of a method for performing blurring detection according to an embodiment of the present application;
FIG. 5 is a schematic diagram of a first membership function provided by an embodiment of the present application;
FIG. 6 is a schematic diagram of a second membership function provided by an embodiment of the present application;
FIG. 7 is a schematic flow chart of a fuzzy inference method according to an embodiment of the present application;
FIG. 8 is a schematic diagram of a third membership function provided by an embodiment of the present application;
fig. 9 is a schematic diagram of an obstacle touch recognition device according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In the following, an obstacle touch recognition method provided by the embodiment of the present application is described, and fig. 1 is a schematic flow chart of an obstacle touch recognition method provided by the embodiment of the present application. It is noted that the present specification provides method operational steps as described in the examples or flowcharts, but may include more or fewer operational steps based on conventional or non-inventive labor. The order of steps recited in the embodiments is merely one way of performing the order of steps and does not represent a unique order of execution. In actual system or product execution, the methods illustrated in the embodiments or figures may be performed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment). As shown in fig. 1, the method may include:
s101, when a target vehicle is in an automatic parking mode, acquiring speed information of the target vehicle.
In this embodiment of the present disclosure, the target vehicle may have an automatic parking function, and the vehicle speed information may be acquired by a vehicle speed sensor of the target vehicle.
S103, acquiring acceleration information and wheel rotation speed information of the target vehicle.
In practical applications, the wheel speed information may be acquired by a wheel speed sensor mounted on a wheel of the target vehicle, and the acceleration information may be acquired by an acceleration sensor of the target vehicle.
S105, carrying out Kalman filtering processing on the vehicle speed information based on the acceleration information and the wheel rotation speed information to obtain target vehicle speed information.
In a specific embodiment, as shown in fig. 2, the performing a kalman filter process on the vehicle speed information based on the acceleration information and the wheel rotation speed information to obtain the target vehicle speed information may include:
s201, determining a state vector of a Kalman filter according to the vehicle speed information and the acceleration information.
Specifically, the vehicle speed information may be represented by v (k), the acceleration information by a (k), and the state vector of the kalman filter by X (k), where X (k) = [ v (k), a (k) ] T.
S203, determining the observation vector of the Kalman filter according to the wheel rotation speed information and preset wheel radius information.
In practical application, the wheel rotation speed information and the wheel radius information can be multiplied to obtain the linear speed information of the wheel, and the prediction and correction of the vehicle speed information can be performed through the linear speed information.
Specifically, vehicle speed information may be represented by ω (k), r represents wheel radius information, and Y (k) represents an observation vector of a kalman filter, where Y (k) = [ rω (k) ].
S205, respectively constructing a state equation and an observation equation of the Kalman filter based on the state vector and the observation vector.
Specifically, a state equation is constructed as follows: x (k) =ax (k-1) +w (k-1);
The observation equation is constructed as follows: y (k) =hx (k-1) +v (k-1);
Wherein A is a state transition matrix, T represents time, H is an observation matrix, H= [1,0] T, W (k) is system noise, V (k) is observation noise, generally, V (k) and V (k) are white noise which are independent of each other and are normally distributed, W-N (0, Q) is a covariance matrix of the system noise, V-N (0, R) is a covariance matrix of the observation noise.
S207, performing iterative optimization based on the state equation and the observation equation to obtain the target vehicle speed information.
Specifically, iterative optimization can be performed based on a time update formula and a measurement state update formula to obtain optimal estimated vehicle speed information, and the optimal estimated vehicle speed information is used as target vehicle speed information. Wherein, the time update formula may include: the prior state prediction formula and the prior state covariance formula, and the measurement state update formula may include: the Kalman gain formula, the posterior state prediction formula and the posterior state covariance formula are specifically shown as follows:
A priori state prediction formula:
a priori state covariance formula:
Kalman gain formula:
posterior state prediction formula:
Posterior state covariance formula:
according to the technical scheme provided by the embodiment, the vehicle speed information can be subjected to Kalman filtering processing based on the acceleration information and the wheel rotating speed information, so that the vehicle speed information with higher accuracy is obtained, and the accuracy of obstacle fuzzy recognition is improved.
S107, acquiring the target impact degree information of the target vehicle.
In practical application, the impact degree information can be the force of the impact force received by the wheels of the vehicle to the vehicle body, and the impact degree information can reflect the smoothness of the driving of the vehicle.
Specifically, the target impact degree information may be obtained by performing a second-order derivative calculation on the target vehicle speed information.
And S109, blurring the target vehicle speed information and the target impact degree information to obtain a target vehicle speed blurring amount and a target impact degree blurring amount.
Specifically, the target vehicle speed blur amount may include: the target vehicle speed membership grade and the membership grade corresponding to the target vehicle speed membership grade; the target impact level ambiguity may include: the target impact degree membership grade and the membership grade corresponding to the target impact degree membership grade.
In the embodiment of the present disclosure, the fuzzy controller performs fuzzy recognition on the target vehicle speed information and the target impact degree information, so as to obtain a result of identifying obstacle touches on wheels of the target vehicle, where in practical application, the fuzzy controller may include, but is not limited to, a fuzzy interface, a fuzzy rule base, a fuzzy inference engine, and a defuzzification interface, and the fuzzy rule base is composed of a plurality of fuzzy rules, as shown in fig. 3, and fig. 3 is a flow diagram of a fuzzy rule generating method according to an embodiment of the present disclosure, and specifically, the method may include:
s301, acquiring a preset vehicle speed fuzzy subset, a preset impact degree fuzzy subset and a preset touch recognition result fuzzy subset, wherein the vehicle speed fuzzy subset comprises a plurality of vehicle speed membership grades, the impact degree fuzzy subset comprises a plurality of impact degree membership grades, and the touch recognition result fuzzy subset comprises a plurality of touch recognition result membership grades.
Specifically, the vehicle speed fuzzy subset may be composed of a plurality of vehicle speed membership grades, and the classification of the vehicle speed membership grades may include, but is not limited to: low speed, lower speed, medium speed, higher speed, and high speed. The fuzzy subset of impact degrees may be composed of a plurality of impact degree membership grades, and the classification of the impact degree membership grades may include, but is not limited to: small, medium, large. The fuzzy subset of touch recognition results may be composed of a plurality of touch recognition result membership grades, and the classification of the touch recognition result membership grades may include, but is not limited to: yes, no.
S303, determining a fuzzy relation between the input variable and the output variable by taking the multiple vehicle speed membership grades and the multiple impact degree membership grades as the input variable of the fuzzy controller and the multiple touch recognition result membership grades as the output variable of the fuzzy controller.
In a specific embodiment, the vehicle speed membership grade in the vehicle speed fuzzy subset includes a low speed (S), a medium speed (M) and a high speed (B), and the impact degree membership grade in the impact degree fuzzy subset includes: small (PS), medium (PM), and large (PB), the touch recognition result membership grade in the fuzzy subset of touch recognition results includes yes (Y) and no (N), and 9 fuzzy relations are determined:
if V (target vehicle speed blur amount) =s and J (target impact blur amount) =s Then F (target touch recognition result blur amount) =n;
If V＝S and J＝PS Then F＝N；
If V＝S and J＝PB Then F＝Y；
If V＝M and J＝PS Then F＝N；
If V＝M and J＝PM Then F＝N；
If V＝M and J＝PB Then F＝Y；
If V＝B and J＝PS Then F＝N；
If V＝B and J＝PM Then F＝Y；
If V＝B and J＝PB Then F＝Y。
s305, generating the fuzzy rule based on the fuzzy relation.
Specifically, the fuzzy rule in the above specific embodiment is as follows:
| F | PS(J) | PM(J) | PB(J) |
| S(V) | N | N | Y |
| M(V) | N | N | Y |
| B(V) | N | Y | Y |
In this embodiment of the present disclosure, as shown in fig. 4, the blurring processing is performed on the target vehicle speed information and the target impact degree information, and obtaining the target vehicle speed blurring amount and the target impact degree blurring amount may include:
s401, blurring processing is carried out on the target vehicle speed information based on a preset first membership function, and the target vehicle speed membership grade and membership degree corresponding to the target vehicle speed membership grade are obtained.
Specifically, the preset first membership function is used for representing membership and membership between elements in a vehicle speed theory domain and vehicle speed membership levels in a fuzzy subset of vehicle speeds, and the first membership function may include, but is not limited to, a gaussian membership function. The above-mentioned vehicle speed argument may be [0, a ] km/h, and b may be set based on the highest vehicle speed limit in the automatic parking function of the target vehicle in practical use, for example, a may take a positive number of not more than 5.
Taking the vehicle speed domain of [0,5] km/h, the classification of the vehicle speed membership grade into low speed, medium speed and fast speed as an example, as shown in fig. 5, fig. 5 is a schematic diagram of a first membership function provided by an embodiment of the present application.
S403, blurring processing is carried out on the target impact degree information based on a preset second membership function, and the target impact degree membership grade and the membership degree corresponding to the target impact degree membership grade are obtained.
Specifically, the preset second membership function is used for representing membership and membership between elements in the impact degree theory domain and impact degree membership grades in the impact degree fuzzy subset, and the second membership function may include, but is not limited to, generalized bell-shaped membership functions. The impact degree theory field may be [0, b ] m/s 3, b may be set based on the maximum impact degree that may be acquired by the target vehicle in actual application during automatic parking, and optionally b may be greater than 80.
With the impact degree domain of [0,100] m/s 3, the impact degree membership grade is divided into small, medium and large, as shown in fig. 6, fig. 6 is a schematic diagram of a second membership function according to an embodiment of the present application.
And S111, fuzzy reasoning is carried out on the target vehicle speed fuzzy quantity and the target impact degree fuzzy quantity based on a fuzzy controller, so as to obtain a target touch recognition result fuzzy quantity.
In this embodiment of the present disclosure, as shown in fig. 7, the fuzzy controller performs fuzzy inference on the target vehicle speed fuzzy amount and the target impact degree fuzzy amount to obtain a target touch recognition result fuzzy amount may include:
S701, determining a target touch recognition result membership grade corresponding to the target vehicle speed fuzzy quantity and the target impact degree fuzzy quantity and a membership grade corresponding to the target touch recognition result membership grade based on a fuzzy rule in the fuzzy controller.
S703, using the membership grade of the target touch recognition result and the membership grade corresponding to the membership grade of the target touch recognition result as the fuzzy amount of the target touch recognition result.
In a specific embodiment, for example, the target vehicle speed information is 1.25km/h, the target impact degree information is 26M/S 3, and according to fig. 5 and 6, S and M are obtained, where the target vehicle speed blur amount (V) is 0.5 times S and 0.5 times M, and the target impact degree blur amount (J) is 0.1 times PM and 0.3 times PB.
When determining the fuzzy amount of the target touch recognition result, adopting a Max-Min fuzzy reasoning method;
If v=0.5 times S and j=0.1 times PM therf=0.1 times N;
if v=0.5 times M and j=0.1 times PM therf=0.1 times N;
if v=0.5 times S and j=0.3 times PB thren f=0.3 times Y;
If v=0.5 times M and j=0.3 times PB thren f=0.3 times Y;
The blurring amount of the target touch recognition result is 0.1 times of N, 0.3 times of Y and 0.3 times of Y.
And S113, performing defuzzification processing on the fuzzy amount of the target touch recognition result to obtain the obstacle touch recognition result of the wheels of the target vehicle.
Specifically, the center value corresponding to the membership grade of the different target touch recognition results can be determined based on a preset third membership function. The preset third membership function is used for representing membership and membership between elements in the touch recognition result theory domain and the touch recognition result membership grade in the fuzzy subset of the touch recognition results, and the third membership function may include, but is not limited to, a trapezoidal membership function.
Taking the domain of the touch recognition result as [0,1], and whether the classification of the membership grade of the touch recognition result is yes or not as an example, as shown in fig. 8, fig. 8 is a schematic diagram of a third membership function provided in the embodiment of the present application, specifically, the formula of the third membership function is as follows:
In the embodiment of the present disclosure, the obfuscation processing may be performed on the membership grade of the target touch recognition result and the membership grade corresponding to the membership grade of the target touch recognition result based on the gravity center method, so as to obtain the obstacle touch recognition result.
Specifically, when the target touch recognition result membership grade is (Y),
Based on gravity center formulaThe gravity center value corresponding to (Y) is 0.674;
when the target touch recognition result membership grade is no (N),
Based on gravity center formulaObtaining whether the gravity center value corresponding to (N) is 0.176;
Weighting calculation is carried out on four values in the fuzzy amount of the target touch recognition result, so that the target touch recognition result is obtained:
In an alternative embodiment, when the obstacle touch recognition result is that the wheels of the target vehicle touch the obstacle, the target vehicle is controlled to stop.
Specifically, taking the field of the touch recognition result as [0,1] as an example, the critical value of the obstacle touch recognition result of the obstacle touched by the wheel and the obstacle not touched by the wheel can be determined based on the calibration method, in an alternative embodiment, the critical value of the obstacle touch recognition result can be 0.4, when the value of the obstacle touch recognition result is less than 0.4, the obstacle is not touched by the wheel, and when the value of the obstacle touch recognition result is greater than or equal to 0.4, the obstacle is touched by the wheel. For example, since the value of the obstacle touch recognition result is 0.5495, it is considered that the wheels of the target vehicle touch the obstacle, and the target vehicle is controlled to stop.
According to the technical scheme provided by the embodiment of the application, the target vehicle speed information is obtained by carrying out Kalman filtering processing on the vehicle speed information, and obstacle touch recognition is carried out based on the target vehicle speed information and the target impact degree information, when the wheels of the target vehicle are recognized to touch the obstacle, the target vehicle is controlled to stop, so that the accuracy of obstacle touch recognition of the wheels can be improved, accidents caused by forced obstacle crossing of the vehicle can be avoided, and the riding experience of a user is improved.
An embodiment of the present application provides an obstacle touch recognition device, as shown in fig. 9, where the device may include:
the vehicle speed information acquisition module 910 is configured to acquire vehicle speed information of a target vehicle when the target vehicle is in an automatic parking mode;
an information acquisition module 920, configured to acquire acceleration information and wheel rotation speed information of the target vehicle;
The kalman filter processing module 930 is configured to perform kalman filter processing on the vehicle speed information based on the acceleration information and the wheel rotation speed information, to obtain target vehicle speed information;
A target impact information obtaining module 940, configured to obtain target impact information of the target vehicle;
The fuzzification processing module 950 is configured to perform fuzzification processing on the target vehicle speed information and the target impact degree information to obtain a target vehicle speed fuzzification amount and a target impact degree fuzzification amount;
the fuzzy inference module 960 is configured to perform fuzzy inference on the target vehicle speed fuzzy amount and the target impact degree fuzzy amount based on a fuzzy controller, so as to obtain a target touch recognition result fuzzy amount;
The defuzzification processing module 970 is configured to perform defuzzification processing on the target touch recognition result fuzzy amount to obtain an obstacle touch recognition result of the wheel of the target vehicle.
In a specific embodiment, the kalman filter processing module 930 may include:
a state vector unit for determining a state vector of the Kalman filter according to the vehicle speed information and the acceleration information;
an observation vector unit, configured to determine an observation vector of the kalman filter according to the wheel rotation speed information and preset wheel radius information;
An equation construction unit configured to construct a state equation and an observation equation of the kalman filter based on the state vector and the observation vector, respectively;
And the iterative optimization unit is used for carrying out iterative optimization based on the state equation and the observation equation to obtain the target vehicle speed information.
In an embodiment of the present disclosure, the foregoing apparatus may further include:
The fuzzy subset acquisition unit is used for acquiring a preset vehicle speed fuzzy subset, a preset impact degree fuzzy subset and a preset touch recognition result fuzzy subset, wherein the vehicle speed fuzzy subset comprises a plurality of vehicle speed membership grades, the impact degree fuzzy subset comprises a plurality of impact degree membership grades, and the touch recognition result fuzzy subset comprises a plurality of touch recognition result membership grades;
A fuzzy relation determining unit, configured to determine a fuzzy relation between the input variable and the output variable by using the plurality of vehicle speed membership levels and the plurality of impact degree membership levels as input variables of the fuzzy controller and using the plurality of touch recognition result membership levels as output variables of the fuzzy controller;
and the fuzzy rule generating unit is used for generating the fuzzy rule based on the fuzzy relation.
In the embodiment of the present disclosure, the blurring processing module 950 may include:
The target vehicle speed information processing unit is used for carrying out fuzzification processing on the target vehicle speed information based on a preset first membership function to obtain the target vehicle speed membership grade and membership grade corresponding to the target vehicle speed membership grade;
And the target impact degree information processing unit is used for carrying out fuzzification processing on the target impact degree information based on a preset second membership function to obtain the target impact degree membership grade and membership degrees corresponding to the target impact degree membership grade.
In the embodiment of the present specification, the fuzzy inference module 960 may include:
A target touch recognition result membership grade determining unit, configured to determine a target touch recognition result membership grade corresponding to the target vehicle speed fuzzy quantity and the target impact degree fuzzy quantity and a membership grade corresponding to the target touch recognition result membership grade based on a fuzzy rule in the fuzzy controller;
And the target touch recognition result fuzzy amount unit is used for taking the membership grade of the target touch recognition result and the membership grade corresponding to the membership grade of the target touch recognition result as the target touch recognition result fuzzy amount.
The apparatus and method embodiments described above in the apparatus embodiments are based on the same inventive concept.
The embodiment of the application provides obstacle touch recognition equipment, which comprises a processor and a memory, wherein at least one instruction or at least one section of program is stored in the memory, and the at least one instruction or the at least one section of program is loaded and executed by the processor so as to realize the obstacle touch recognition method provided by the embodiment of the method.
The memory may be used to store software programs and modules that the processor executes to perform various functional applications and data processing by executing the software programs and modules stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, application programs required for functions, and the like; the storage data area may store data created according to the use of the above-described device, or the like. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory may also include a memory controller to provide access to the memory by the processor.
The method embodiment provided by the embodiment of the application can be executed in the vehicle-mounted terminal or the similar computing device, namely the computer equipment can comprise the vehicle-mounted terminal or the similar computing device.
The embodiment of the application also provides a storage medium which can be arranged in a server to store at least one instruction or at least one section of program related to the obstacle touch recognition method for realizing the obstacle touch recognition method in the embodiment of the method, and the at least one instruction or the at least one section of program is loaded and executed by the processor to realize the obstacle touch recognition method provided by the embodiment of the method.
Alternatively, in this embodiment, the storage medium may be located in at least one network server among a plurality of network servers of the computer network. Alternatively, in the present embodiment, the storage medium may include, but is not limited to: a usb disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
According to the embodiment of the obstacle touch recognition method, device, equipment or storage medium, the technical scheme provided by the application is utilized, the target vehicle speed information is obtained through Kalman filtering processing on the vehicle speed information, the obstacle touch recognition is carried out based on the target vehicle speed information and the target impact degree information, when the wheels of the target vehicle are recognized to touch the obstacle, the target vehicle is controlled to stop, the accuracy of the obstacle touch recognition of the wheels can be improved, the situation that the vehicle outputs excessive torque due to forced obstacle crossing is avoided, accidents are caused, and the riding experience of a user is improved.
It should be noted that: the sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for apparatus, devices and storage medium embodiments, the description is relatively simple as it is substantially similar to method embodiments, with reference to the description of method embodiments in part.
Those of ordinary skill in the art will appreciate that all or a portion of the steps implementing the above embodiments may be implemented by hardware, or may be implemented by a program indicating that the relevant hardware is implemented, where the program may be stored on a computer readable storage medium, where the storage medium may be a read only memory, a magnetic disk or optical disk, etc.
The foregoing description of the preferred embodiments of the application is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the application.
Claims (11)
1. A method for identifying the touch of an obstacle, characterized in that the method comprises:
When a target vehicle is in an automatic parking mode, acquiring speed information of the target vehicle;
Acquiring acceleration information and wheel rotation speed information of the target vehicle;
based on the acceleration information and the wheel rotation speed information, carrying out Kalman filtering processing on the vehicle speed information to obtain target vehicle speed information of the target vehicle;
acquiring target impact degree information of the target vehicle, wherein the target impact degree information represents the strength of the impact force received by the wheels of the target vehicle to be transmitted to a vehicle body;
Fuzzification processing is carried out on the target vehicle speed information and the target impact degree information to obtain a target vehicle speed fuzzification amount and a target impact degree fuzzification amount;
performing fuzzy reasoning on the target vehicle speed fuzzy quantity and the target impact degree fuzzy quantity based on a fuzzy controller to obtain a target touch recognition result fuzzy quantity;
And performing defuzzification processing on the fuzzy amount of the target touch recognition result to obtain an obstacle touch recognition result of the wheel of the target vehicle.
2. The method of claim 1, wherein the target vehicle speed fuzzy amount includes a target vehicle speed membership grade and a membership grade corresponding to the target vehicle speed membership grade, the target impact degree fuzzy amount includes a target impact degree membership grade and a membership grade corresponding to the target impact degree membership grade, and the fuzzifying the target vehicle speed information and the target impact degree information to obtain a target vehicle speed fuzzy amount and a target impact degree fuzzy amount includes:
Blurring processing is carried out on the target vehicle speed information based on a preset first membership function, so that the target vehicle speed membership grade and membership grade corresponding to the target vehicle speed membership grade are obtained;
And carrying out fuzzification processing on the target impact degree information based on a preset second membership function to obtain the target impact degree membership grade and membership degrees corresponding to the target impact degree membership grade.
3. The method of claim 1, wherein the fuzzy inference of the target vehicle speed fuzzy amount and the target impact degree fuzzy amount based on the fuzzy controller to obtain a target touch recognition result fuzzy amount comprises:
Determining a target touch recognition result membership grade corresponding to the target vehicle speed fuzzy quantity and the target impact degree fuzzy quantity and a membership grade corresponding to the target touch recognition result membership grade based on a fuzzy rule in the fuzzy controller;
And taking the membership grade of the target touch recognition result and the membership grade corresponding to the membership grade of the target touch recognition result as the fuzzy amount of the target touch recognition result.
4. A method according to claim 3, characterized in that the method further comprises:
Acquiring a preset vehicle speed fuzzy subset, a preset impact degree fuzzy subset and a preset touch recognition result fuzzy subset, wherein the vehicle speed fuzzy subset comprises a plurality of vehicle speed membership grades, the impact degree fuzzy subset comprises a plurality of impact degree membership grades, and the touch recognition result fuzzy subset comprises a plurality of touch recognition result membership grades;
Determining a fuzzy relation between the input variable and the output variable by taking the multiple vehicle speed membership grades and the multiple impact degree membership grades as input variables of the fuzzy controller and the multiple touch recognition result membership grades as output variables of the fuzzy controller;
And generating the fuzzy rule based on the fuzzy relation.
5. The method of claim 3, wherein the performing the defuzzification of the target touch recognition result fuzzification amount to obtain the obstacle touch recognition result of the wheel of the target vehicle includes:
and performing defuzzification processing on the membership grade of the target touch recognition result and the membership grade corresponding to the membership grade of the target touch recognition result based on a gravity center method to obtain the obstacle touch recognition result.
6. The method according to any one of claims 1 to 5, wherein the performing a kalman filter process on the vehicle speed information based on the acceleration information and the wheel rotation speed information to obtain target vehicle speed information of the target vehicle includes:
determining a state vector of a Kalman filter according to the vehicle speed information and the acceleration information;
Determining an observation vector of the Kalman filter according to the wheel rotation speed information and preset wheel radius information;
based on the state vector and the observation vector, respectively constructing a state equation and an observation equation of the Kalman filter;
and performing iterative optimization based on the state equation and the observation equation to obtain the target vehicle speed information.
7. The method according to any one of claims 1 to 5, wherein the acquiring the target impact information of the target vehicle includes:
and performing second order derivative calculation on the target vehicle speed information to obtain the target impact degree information.
8. The method according to any one of claims 1 to 5, characterized in that after the subjecting the target touch recognition result blur amount to the defuzzification processing to obtain an obstacle touch recognition result of a wheel of the target vehicle, the method further comprises:
And when the touch recognition result is that the wheels of the target vehicle touch the obstacle, controlling the target vehicle to stop.
9. An obstacle touch recognition device, the device comprising:
The vehicle speed information acquisition module is used for acquiring the vehicle speed information of the target vehicle when the target vehicle is in an automatic parking mode;
The information acquisition module is used for acquiring acceleration information and wheel rotation speed information of the target vehicle;
the Kalman filtering processing module is used for carrying out Kalman filtering processing on the vehicle speed information based on the acceleration information and the wheel rotating speed information to obtain target vehicle speed information of the target vehicle;
The target impact degree information acquisition module is used for acquiring target impact degree information of the target vehicle, wherein the target impact degree information represents the strength of the impact force received by the wheels of the target vehicle to be transmitted to the vehicle body;
The fuzzification processing module is used for fuzzifying the target vehicle speed information and the target impact degree information to obtain a target vehicle speed fuzzification amount and a target impact degree fuzzification amount;
The fuzzy reasoning module is used for carrying out fuzzy reasoning on the target vehicle speed fuzzy quantity and the target impact degree fuzzy quantity based on a fuzzy controller to obtain a target touch recognition result fuzzy quantity;
and the defuzzification processing module is used for defuzzifying the target touch recognition result fuzzy quantity to obtain the obstacle touch recognition result of the wheels of the target vehicle.
10. An obstacle touch recognition device, comprising a processor and a memory, wherein the memory stores at least one instruction or at least one program, and wherein the at least one instruction or the at least one program is loaded and executed by the processor to implement the obstacle touch recognition method of any one of claims 1 to 8.
11. A computer readable storage medium having stored therein at least one instruction or at least one program loaded and executed by a processor to implement the obstacle touch recognition method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110740038.2A CN113353066B (en) | 2021-06-30 | 2021-06-30 | Obstacle touch recognition method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110740038.2A CN113353066B (en) | 2021-06-30 | 2021-06-30 | Obstacle touch recognition method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113353066A CN113353066A (en) | 2021-09-07 |
| CN113353066B true CN113353066B (en) | 2024-09-13 |
Family
ID=77537614
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110740038.2A Active CN113353066B (en) | 2021-06-30 | 2021-06-30 | Obstacle touch recognition method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113353066B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113665568A (en) * | 2021-09-23 | 2021-11-19 | 中汽创智科技有限公司 | Parking assisting method and device, electronic equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106394561A (en) * | 2015-11-10 | 2017-02-15 | 北京中科易电信息科技股份有限公司 | Estimation method and device for longitudinal vehicle speed of vehicle |
| CN112068542A (en) * | 2020-06-30 | 2020-12-11 | 武汉乐庭软件技术有限公司 | Automatic driving behavior planning method based on fuzzy control |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7418346B2 (en) * | 1997-10-22 | 2008-08-26 | Intelligent Technologies International, Inc. | Collision avoidance methods and systems |
| US8165742B2 (en) * | 2008-11-14 | 2012-04-24 | Robert Bosch Gmbh | System and method for compensating sensor signals |
| US9491420B2 (en) * | 2009-09-20 | 2016-11-08 | Tibet MIMAR | Vehicle security with accident notification and embedded driver analytics |
| CN107839687A (en) * | 2017-10-18 | 2018-03-27 | 哈尔滨工业大学深圳研究生院 | Optimal autonomous control method of overtaking other vehicles based on driving performance analysis |
| CN110626339B (en) * | 2019-07-10 | 2021-03-02 | 聊城大学 | Emergency obstacle avoidance automatic driving assistance torque calculation method based on driver intention |
| CN112356830B (en) * | 2020-11-25 | 2021-11-09 | 同济大学 | Intelligent parking method based on model reinforcement learning |
-
2021
- 2021-06-30 CN CN202110740038.2A patent/CN113353066B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106394561A (en) * | 2015-11-10 | 2017-02-15 | 北京中科易电信息科技股份有限公司 | Estimation method and device for longitudinal vehicle speed of vehicle |
| CN112068542A (en) * | 2020-06-30 | 2020-12-11 | 武汉乐庭软件技术有限公司 | Automatic driving behavior planning method based on fuzzy control |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113353066A (en) | 2021-09-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hunt et al. | Verifiably safe exploration for end-to-end reinforcement learning | |
| KR20210002018A (en) | Method for estimating a global uncertainty of a neural network | |
| US20210213977A1 (en) | Nearby Driver Intent Determining Autonomous Driving System | |
| CN104866868A (en) | Metal coin identification method based on deep neural network and apparatus thereof | |
| Berczi et al. | Learning to assess terrain from human demonstration using an introspective gaussian-process classifier | |
| Wang et al. | A probabilistic approach to measuring driving behavior similarity with driving primitives | |
| CN111914665A (en) | Face shielding detection method, device, equipment and storage medium | |
| CN113353066B (en) | Obstacle touch recognition method, device, equipment and storage medium | |
| Shan et al. | Space exploration and global optimization for computationally intensive design problems: a rough set based approach | |
| Fdez-Riverola et al. | Using rough sets theory and minimum description length principle to improve a β-tsk fuzzy revision method for cbr systems | |
| CN114648633B (en) | Method for determining semantic segmentation of a vehicle environment | |
| Haque et al. | Driving maneuver classification from time series data: a rule based machine learning approach | |
| Liu et al. | A time-delay neural network of sideslip angle estimation for in-wheel motor drive electric vehicles | |
| Haasdijk et al. | Racing to improve on-line, on-board evolutionary robotics | |
| Moya-Albor et al. | An edge detection method using a fuzzy ensemble approach | |
| Yuan et al. | Creating rule-based agents for artificial general intelligence using association rules mining | |
| Sahib et al. | Detection of the autonomous car robot using Yolo | |
| CN117669661A (en) | Method for training generation of an countermeasure network | |
| EP3699810A1 (en) | Classification technique for assessing a visibility degradation in image data units | |
| Coyle et al. | A comparison of classifier performance for vibration-based terrain classification | |
| CN115223127A (en) | Automatic driving perception method and device of vehicle, vehicle and storage medium | |
| Mauceri et al. | One-class subject authentication using feature extraction by grammatical evolution on accelerometer data | |
| CN115329962A (en) | Visual interpretation method of normal form graph model | |
| Sega et al. | Applying qualitative reasoning to a driver's cognitive mental load | |
| Fischer et al. | On feature relevance uncertainty: a Monte Carlo dropout sampling approach |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |