CN112455460B - Vehicle control method, device, equipment and storage medium - Google Patents
Vehicle control method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112455460B CN112455460B CN202011425745.4A CN202011425745A CN112455460B CN 112455460 B CN112455460 B CN 112455460B CN 202011425745 A CN202011425745 A CN 202011425745A CN 112455460 B CN112455460 B CN 112455460B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- vehicle control
- information
- parameters
- acceleration
- 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
Images
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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
-
- 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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0019—Control system elements or transfer functions
- B60W2050/0028—Mathematical models, e.g. for simulation
- B60W2050/0031—Mathematical model of the vehicle
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Human Computer Interaction (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The invention belongs to the technical field of vehicle control, and discloses a vehicle control method, a vehicle control device, vehicle control equipment and a storage medium. According to the invention, when vehicle disturbance is detected, the position information, the speed information and the acceleration information of the vehicle at the current moment are acquired; inputting the position information, the speed information and the acceleration information into a preset vehicle control model for analysis so as to obtain vehicle control parameters; and controlling the vehicle to run according to the vehicle control parameters. The position information, the speed information and the acceleration information of the vehicle are collected in real time when the vehicle disturbance is detected and input into the preset vehicle control model for analysis so as to calculate the vehicle control parameters required for eliminating the vehicle disturbance, and the preset vehicle control model is trained in advance, so that the parameter calculation real-time performance is extremely high, and the vehicle is controlled to run by the vehicle control parameters calculated by the preset vehicle control model, so that the vehicle control can eliminate the disturbance of the vehicle disturbance and the vehicle can run stably.
Description
Technical Field
The present invention relates to the field of vehicle control technologies, and in particular, to a vehicle control method, apparatus, device, and storage medium.
Background
With the development of assistant driving and unmanned driving, the internet of vehicles technology plays a key role in vehicle driving. The key technology of the internet of vehicles V2X (Vehicle-To-evaporating), namely, a communication system between vehicles (V2V), vehicles and pedestrians (V2P), vehicles and infrastructure (V2I), vehicles and a network (V2N), and the like. V2X is just like the eyes of a vehicle, and can sense the surrounding environment and provide a powerful information base for the vehicle to make a correct decision. In the prior art, V2X can sense a range around 500 meters. With the popularization of 5G technology, a vehicle can completely sense the range of 1 kilometer. Therefore, the time for judging in advance is greatly prolonged for the realization of safe driving, path planning and vehicle cooperation of the vehicle.
However, in vehicle control, it is inevitable to be disturbed by many factors in the environment, such as: road bumps, speed or position detector noise, communication system failures, etc. These all result in unstable vehicle control, and how to deal with well-controlled disturbance is directly related to the safety and effectiveness of the controller for vehicle control. In the prior art, vehicle disturbance is generally eliminated by adopting Kalman filtering, error estimation and error correction methods, but the methods are complex in design and poor in real-time property.
The above is only for the purpose of assisting understanding of the technical solution of the present invention, and does not represent an admission that the above is the prior art.
Disclosure of Invention
The invention mainly aims to provide a vehicle control method, a vehicle control device, vehicle control equipment and a storage medium, and aims to solve the technical problem that a method for eliminating vehicle disturbance in the prior art is poor in real-time performance.
To achieve the above object, the present invention provides a vehicle control method including the steps of:
when vehicle disturbance is detected, position information, speed information and acceleration information of a vehicle at the current moment are acquired;
inputting the position information, the speed information and the acceleration information into a preset vehicle control model for analysis so as to obtain vehicle control parameters;
and controlling the vehicle to run according to the vehicle control parameters.
Preferably, before the step of acquiring the position information, the speed information and the acceleration information of the vehicle at the current time when the vehicle disturbance is detected, the method includes:
acquiring a historical operation information set of a vehicle;
training an initial neural network model according to the historical operation information set to obtain a vehicle control neural network model;
determining a control network weight according to the historical operation information set;
and determining a preset vehicle control model according to the control network weight and the vehicle control neural network model.
Preferably, the step of determining a preset control network weight according to the historical operation information set includes:
calculating a control network weight through a weight calculation formula according to the historical operation information set;
the weight calculation formula is as follows:
in the formula, W(i+1)To controlMaking a network weight matrix, wherein M is a historical operation information set, i is iteration calculation times, and A(i)For the running matrix value, B, obtained by the i-th iteration(i)And T is a matrix transposer for the operation integral value obtained by the ith iterative calculation.
Preferably, after the step of controlling the vehicle to run according to the vehicle control parameter, the method further includes:
acquiring position data, speed data and acceleration data of the vehicle when the vehicle runs according to the vehicle control parameters;
updating the historical operating information set according to the position data, the speed data and the acceleration data;
and updating the control network weight in the preset vehicle control model according to the updated historical operation information set.
Preferably, before the step of acquiring the position information, the speed information, and the acceleration information of the vehicle at the current time when the vehicle disturbance is detected, the method further includes:
acquiring the running parameters of the vehicle;
judging whether system faults, detector signal noise or vehicle jolt exist according to the operation parameters;
a vehicle disturbance is determined to be detected in the presence of a system fault, detector signal noise, and/or vehicle bump.
Preferably, after the step of controlling the vehicle to run according to the vehicle control parameter, the method further includes:
generating a vehicle disturbance elimination record according to the position information, the speed information, the acceleration information and the vehicle control parameter, and acquiring a driving mode of the vehicle;
when the driving mode is an automatic driving mode, pushing the vehicle disturbance elimination record to a vehicle security officer;
and when the driving mode is the auxiliary driving mode, displaying the vehicle disturbance elimination record.
Preferably, before the step of inputting the position information, the speed information and the acceleration information into a preset vehicle control model for analysis to obtain vehicle control parameters, the method further includes:
carrying out security verification on the position information, the speed information and the acceleration information;
and when the safety verification passes, executing the step of inputting the position information, the speed information and the acceleration information into a preset vehicle control model for analysis so as to obtain vehicle control parameters.
In addition, to achieve the above object, the present invention also proposes a vehicle control device including the following modules:
the information acquisition module is used for acquiring the position information, the speed information and the acceleration information of the vehicle at the current moment when the vehicle disturbance is detected;
the parameter determining module is used for inputting the position information, the speed information and the acceleration information into a preset vehicle control model for analysis so as to obtain vehicle control parameters;
and the vehicle control module is used for controlling the vehicle to run according to the vehicle control parameters.
Further, to achieve the above object, the present invention also proposes a vehicle control apparatus including: a memory, a processor and a vehicle control program stored on the memory and executable on the processor, the vehicle control program when executed by the processor implementing the steps of the vehicle control method as described above.
In addition, in order to achieve the above object, the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium has a vehicle control program stored thereon, and the vehicle control program, when executed, implements the steps of the vehicle control method as described above.
According to the invention, when vehicle disturbance is detected, the position information, the speed information and the acceleration information of the vehicle at the current moment are acquired; inputting the position information, the speed information and the acceleration information into a preset vehicle control model for analysis so as to obtain vehicle control parameters; and controlling the vehicle to run according to the vehicle control parameters. The position information, the speed information and the acceleration information of the vehicle are collected in real time when the vehicle disturbance is detected and input into the preset vehicle control model for analysis so as to calculate the vehicle control parameters required for eliminating the vehicle disturbance, and the preset vehicle control model is trained in advance, so that the parameter calculation real-time performance is extremely high, and the vehicle is controlled to run by the vehicle control parameters calculated by the preset vehicle control model, so that the vehicle control can eliminate the disturbance of the vehicle disturbance and the vehicle can run stably.
Drawings
Fig. 1 is a schematic structural diagram of an electronic device in a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a schematic flowchart of a first embodiment of a vehicle control method of the invention;
FIG. 3 is a flowchart illustrating a second embodiment of a vehicle control method according to the present invention;
fig. 4 is a block diagram showing the configuration of the first embodiment of the vehicle control apparatus of the invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a vehicle control device in a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the electronic device may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., a WIreless-FIdelity (WI-FI) interface). The Memory 1005 may be a Random Access Memory (RAM) Memory, or a Non-Volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the configuration shown in fig. 1 does not constitute a limitation of the electronic device and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is one type of storage medium, may include therein an operating system, a network communication module, a user interface module, and a vehicle control program.
In the electronic apparatus shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the electronic device of the present invention may be provided in a vehicle control device that calls a vehicle control program stored in the memory 1005 through the processor 1001 and executes a vehicle control method provided by an embodiment of the present invention.
An embodiment of the present invention provides a vehicle control method, and referring to fig. 2, fig. 2 is a flowchart illustrating a first embodiment of the vehicle control method according to the present invention.
In this embodiment, the vehicle control method includes the steps of:
step S10: when vehicle disturbance is detected, position information, speed information and acceleration information of a vehicle at the current moment are acquired;
it should be noted that, the execution subject of this embodiment may be the vehicle control device, and the vehicle control device may be an electronic device such as a vehicle-mounted computer, and may also be other devices that can achieve the same or similar functions.
It should be noted that the vehicle disturbance may be a factor that may interfere with the vehicle control when the vehicle is running, for example: communication system faults, detector signal noise or vehicle jerkiness, etc. The location information may be current location information of the vehicle collected from a vehicle GPS positioning system or the like. The speed information may be current speed information of the vehicle collected by an on-vehicle speed sensor, and the acceleration information may be current acceleration information of the vehicle collected by an on-vehicle acceleration sensor.
In actual use, the running parameters of the vehicle can be acquired; judging whether system faults, detector signal noise or vehicle jolt exist according to the operation parameters; a vehicle disturbance is determined to be detected in the presence of a system fault, detector signal noise, and/or vehicle bump.
For example: whether system faults exist is checked through system timing communication, whether noise data exist is judged through analysis of the detector signals, and whether vehicle jolt exists is judged through vibration data collected by the vehicle-mounted vibration sensor.
Step S20: inputting the position information, the speed information and the acceleration information into a preset vehicle control model for analysis so as to obtain vehicle control parameters;
it should be noted that the preset vehicle control model is a model obtained by training and calculating a large amount of vehicle historical operation information, and vehicle control parameters required for maintaining stable operation of the vehicle can be calculated by inputting the position information, the speed information and the acceleration information into the preset vehicle control model.
It should be noted that, in a complex scenario, due to the influence of some special situations, for example: data interference or the data transmission frequency of other vehicles is the same, the position information, the speed information and the acceleration information received by the vehicle control equipment may not be the self-vehicle data, and if the vehicle control parameters are calculated and obtained according to the information, misjudgment of vehicle control may occur, and traffic accidents are caused.
Further, to avoid data misjudgment and improve safety, before step S20 in this embodiment, the method may further include:
carrying out security verification on the position information, the speed information and the acceleration information; and when the safety verification passes, executing the step of inputting the position information, the speed information and the acceleration information into a preset vehicle control model for analysis so as to obtain vehicle control parameters.
It is understood that the security check is a verification means for verifying whether or not the position information, the velocity information, and the acceleration information are the vehicle data.
In actual use, fixed identification data may be added to the transmitted information, and after the information such as the location information is acquired, whether the identification data included in the information is the same as the fixed identification data or not may be determined, and when the identification data is the same, it is determined that the security verification is passed, and when the identification data is not the same, it is determined that the security verification is not passed. The vehicle control device can also generate corresponding safety verification parameters when sending information such as position information and the like, send the safety verification parameters and the information such as the position information and the like to the vehicle control device, perform sequencing in a specific sequence when receiving the information and then encrypt the information to generate safety verification parameters, compare the safety verification parameters with the received safety verification parameters, judge that the safety verification passes when the safety verification parameters are the same as the safety verification parameters, and judge that the safety verification does not pass when the safety verification parameters are different from the safety verification parameters. The specific security check may be set according to actual needs, which is not limited in this embodiment.
Step S30: and controlling the vehicle to run according to the vehicle control parameters.
It can be appreciated that controlling the operation of the vehicle based on the calculated vehicle control parameters eliminates vehicle disturbances, resulting in smooth vehicle operation.
Further, in order to facilitate data tracing and further improve security, after step S30, the method may further include:
generating a vehicle disturbance elimination record according to the position information, the speed information, the acceleration information and the vehicle control parameter, and acquiring a driving mode of the vehicle; when the driving mode is an automatic driving mode, pushing the vehicle disturbance elimination record to a vehicle security officer; and when the driving mode is the auxiliary driving mode, displaying the vehicle disturbance elimination record.
The vehicle disturbance removal record is a record generated according to the position information, the speed information, the acceleration information and the vehicle control parameters, and can be traced through the vehicle disturbance removal record when the cause of the fault or the abnormality needs to be traced, and a technician can analyze the data according to the vehicle disturbance removal record when the technician needs to analyze the data. A vehicle security officer may be a person who remotely observes whether the vehicle is operating safely while the vehicle is being autonomously driven.
It is understood that after the vehicle disturbance rejection record is generated, the driving mode of the vehicle may also be acquired, and different processing measures may be taken according to the driving mode.
In the embodiment, when vehicle disturbance is detected, the position information, the speed information and the acceleration information of the vehicle at the current moment are acquired; inputting the position information, the speed information and the acceleration information into a preset vehicle control model for analysis so as to obtain vehicle control parameters; and controlling the vehicle to run according to the vehicle control parameters. The position information, the speed information and the acceleration information of the vehicle are collected in real time when the vehicle disturbance is detected and input into the preset vehicle control model for analysis so as to calculate the vehicle control parameters required for eliminating the vehicle disturbance, and the preset vehicle control model is trained in advance, so that the parameter calculation real-time performance is extremely high, and the vehicle is controlled to run by the vehicle control parameters calculated by the preset vehicle control model, so that the vehicle control can eliminate the disturbance of the vehicle disturbance and stably run.
Referring to fig. 3, fig. 3 is a flowchart illustrating a second embodiment of a vehicle control method according to the present invention.
Based on the first embodiment described above, the vehicle control method of the present embodiment further includes, before the step S10:
step S01: acquiring a historical operation information set of a vehicle;
it should be noted that the historical operation information set may be a set constructed by combining a plurality of pieces of historical operation information. The historical operation information can comprise information such as information acquisition time, position information, speed information, acceleration information and the like.
Step S02: training an initial neural network model according to the historical operation information set to obtain a vehicle control neural network model;
it can be understood that an approximate neural network model of the vehicle, namely an initial neural network model, can be constructed according to three state quantities of the position, the speed and the acceleration of the vehicle, and the neural network model can be trained by using historical operation information and the initial neural network model to obtain a vehicle control neural network model.
Step S03: determining a control network weight according to the historical operation information set;
it should be noted that, in order to derive the reinforcement learning algorithm, the state model of the vehicle may be assumed as follows:
x(t)＝[p(t) v(t) a(t)]T
wherein x (t) is the vehicle state, t is the information acquisition time, p (t) is the position of the vehicle, v (t) is the speed of the vehicle, and a (t) is the acceleration of the vehicle.
Assume the vehicle dynamics equation to be:
x&＝f(x)+g(x)(u+ω)
where x is the derivative of the state, f (x) is the system dynamics, g (x) is the input dynamics, u is the control input, and ω is the vehicle disturbance.
In order to effectively control the vehicle, according to the actual situation, a performance index can be constructed:
the performance index item aiming at the control interference is added into the performance index, so that the interference can be restrained in a targeted manner, and a good control effect is obtained. Q and R are both constant diagonal matrices. x is the number ofTQx is a performance indicator for the vehicle state,is a positive definite function. u. ofTRu is a performance indicator for vehicle control, and is also a positive definite function.
Define the Hamiltonian:
in order to minimize the performance index while controlling the vehicle, thereby optimizing the controlled vehicle trajectory, minimizing fuel consumption, and canceling interference, according to the most common principle and the Hamiltonian, a vehicle control expression can be obtained as follows:
substituting the vehicle control expression into a Hamiltonian to obtain a Hamiltonian-Jacobian-Bellman (HJB) equation:
can be obtained from Hamilton-Jacobi-Bellman (HJB) equation
The vehicle control can be obtained by substituting the dynamic expression position into a vehicle control expression, but the specific dynamic expression position of the vehicle and the Hamilton-Jacobian-Bellman (HJB) equation are non-linear differential equations which are difficult to solve, so that an enhanced learning method can be designed to obtain the vehicle control.
In practical use, the cost function can be approximated by a neural network as:
V(x)＝Wc Tφ(x)
where φ (x) is a neural network composed of vehicle state polynomials, e.g.
WcIs the cost network weight. The cost function is approximated by a neural network, so that the influence caused by unknown specific system parameters can be avoided.
The vehicle control is subjected to neural network approximation, which can be obtained as
Wherein, the vehicle
A neural network which is also formed by a vehicle state polynomial but differs from the cost neural network, for example, it can be taken
WaThe weight of the control network is expressed, the neural network approximation is carried out on the vehicle control, and the influence caused by unknown systems and unknown disturbance can be avoided.
The evolution of the data-based reinforcement learning algorithm from the strategy iteration algorithm is as follows:
where Δ t denotes the interval between data acquisitions, which is determined by the acquisition rate, and is typically twice per second, i.e., Δ t is 0.5. (i +1) represents the cost value of the next iteration, and (i) represents the value obtained this time.
Substituting the vehicle control neural network approximation and the cost function neural network approximation into the reinforcement learning algorithm to obtain the neural network weight reinforcement learning algorithm:
where δ represents the error due to the neural network approximation. In the case of multiple control input variables, p represents the operation of the control input in the p-th dimension. In order to obtain a more accurate approximate neural network, position, speed and acceleration information data are continuously obtained according to the vehicle. And a more accurate network weight can be obtained by using a least square method. Firstly, setting:
the overall weight is set as:
then, the neural network weight reinforcement learning algorithm can be abbreviated as:
δ(i)＝ATW(i+1)-B(i)
the weight formula can be obtained by using a least square method as follows:
in the formula, W(i+1)For controlling the network weight matrix, M is the historical running information set, i is the iterative computation times, A(i)For the running matrix value, B, obtained by the i-th iteration(i)And T is a matrix transposer for the operation integral value obtained by the ith iterative calculation.
In actual use, the control network weight can be calculated through a weight calculation formula according to the historical operation information set.
Step S04: and determining a preset vehicle control model according to the control network weight and the vehicle control neural network model.
It can be understood that a complete preset vehicle control model can be obtained according to the calculated control network weight and the trained vehicle control neural network model.
It should be noted that the neural network weight enhancement learning algorithm can continuously learn according to the continuously obtained position information, speed information and acceleration information, so as to obtain a more accurate control network weight.
Further, in order to obtain a more accurate control network weight, after the step of controlling the vehicle to run according to the vehicle control parameter, the method may further include:
acquiring position data, speed data and acceleration data of the vehicle when the vehicle runs according to the vehicle control parameters; updating the historical operating information set according to the position data, the speed data and the acceleration data; and updating the control network weight in the preset vehicle control model according to the updated historical operation information set.
It can be understood that, according to the weight formula obtained by the neural network weight reinforcement learning algorithm, the more the data samples are, the more accurate the calculated control network weight is, and therefore, the historical operation information set can be updated according to the collected position data, speed data and acceleration data, so as to calculate the more accurate control network weight.
It should be noted that the vehicle control neural network model may be further trained according to the obtained position data, velocity data, and acceleration data, so that the result calculated by the vehicle control neural network model is more in line with the actual situation.
The embodiment obtains the historical operation information set of the vehicle; training an initial neural network model according to the historical operation information set to obtain a vehicle control neural network model; determining a control network weight according to the historical operation information set; and determining a preset vehicle control model according to the control network weight and the vehicle control neural network model. Because the neural network is formed by adopting a neural network approximation mode according to the vehicle state polynomial, the construction is simple, the influence caused by an unknown system and unknown disturbance can be avoided, the construction of the integral preset vehicle control model is not complicated, more accurate control network weight can be calculated according to subsequent continuously acquired data, the more fitting actual condition of the preset vehicle control model is realized, and the method is very suitable for actual use.
Furthermore, an embodiment of the present invention also proposes a storage medium having a vehicle control program stored thereon, which when executed by a processor implements the steps of the vehicle control method as described above.
Referring to fig. 4, fig. 4 is a block diagram showing the configuration of the first embodiment of the vehicle control apparatus of the present invention.
As shown in fig. 4, a vehicle control device according to an embodiment of the present invention includes:
the information acquisition module 401 is configured to acquire position information, speed information, and acceleration information of a vehicle at a current time when vehicle disturbance is detected;
a parameter determining module 402, configured to input the position information, the speed information, and the acceleration information into a preset vehicle control model for analysis to obtain vehicle control parameters;
and a vehicle control module 403, configured to control the vehicle to run according to the vehicle control parameter.
In the embodiment, when vehicle disturbance is detected, the position information, the speed information and the acceleration information of the vehicle at the current moment are acquired; inputting the position information, the speed information and the acceleration information into a preset vehicle control model for analysis so as to obtain vehicle control parameters; and controlling the vehicle to run according to the vehicle control parameters. The position information, the speed information and the acceleration information of the vehicle are collected in real time when the vehicle disturbance is detected and input into the preset vehicle control model for analysis so as to calculate the vehicle control parameters required for eliminating the vehicle disturbance, and the preset vehicle control model is trained in advance, so that the parameter calculation real-time performance is extremely high, and the vehicle is controlled to run by the vehicle control parameters calculated by the preset vehicle control model, so that the vehicle control can eliminate the disturbance of the vehicle disturbance and the vehicle can run stably.
Further, the information obtaining module 401 is further configured to obtain a historical operation information set of the vehicle; training an initial neural network model according to the historical operation information set to obtain a vehicle control neural network model; determining a control network weight according to the historical operation information set; and determining a preset vehicle control model according to the control network weight and the vehicle control neural network model.
Further, the information obtaining module 401 is further configured to calculate a control network weight according to the historical operation information set through a weight calculation formula;
the weight calculation formula is as follows:
in the formula, W(i+1)For controlling the network weight matrix, M is the historical operation information set, i is the iterative computation times, A(i)For the running matrix value, B, obtained by the i-th iteration(i)And T is a matrix transposer for the operation integral value obtained by the ith iterative calculation.
Further, the vehicle control module 403 is further configured to acquire position data, speed data, and acceleration data of the vehicle when the vehicle runs according to the vehicle control parameter; updating the historical operating information set according to the position data, the speed data and the acceleration data; and updating the control network weight in the preset vehicle control model according to the updated historical operation information set.
Further, the information obtaining module 401 is further configured to obtain an operation parameter of a vehicle; judging whether system faults, detector signal noise or vehicle jolt exist according to the operation parameters; vehicle disturbances are determined to be detected in the presence of system faults, detector signal noise, and/or vehicle bumps.
Further, the vehicle control module 403 is further configured to generate a vehicle disturbance exclusion record according to the position information, the speed information, the acceleration information, and the vehicle control parameter, and acquire a driving mode of the vehicle; when the driving mode is an automatic driving mode, pushing the vehicle disturbance elimination record to a vehicle security officer; and when the driving mode is the auxiliary driving mode, displaying the vehicle disturbance elimination record.
Further, the parameter determining module 402 is further configured to perform security check on the position information, the speed information, and the acceleration information; and when the safety verification passes, executing the step of inputting the position information, the speed information and the acceleration information into a preset vehicle control model for analysis so as to obtain vehicle control parameters.
It should be understood that the above is only an example, and the technical solution of the present invention is not limited in any way, and in a specific application, a person skilled in the art may set the technical solution as needed, and the present invention is not limited thereto.
It should be noted that the above-described work flows are only exemplary, and do not limit the scope of the present invention, and in practical applications, a person skilled in the art may select some or all of them to achieve the purpose of the solution of the embodiment according to actual needs, and the present invention is not limited herein.
In addition, the technical details that are not elaborated in the present embodiment may refer to the vehicle control method provided in any embodiment of the present invention, and are not described herein again.
Further, it is to be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention or portions thereof that contribute to the prior art may be embodied in the form of a software product, where the computer software product is stored in a storage medium (e.g. Read Only Memory (ROM)/RAM, magnetic disk, optical disk), and includes several instructions for enabling a terminal device (e.g. a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (7)
1. A vehicle control method characterized by comprising:
when vehicle disturbance is detected, position information, speed information and acceleration information of a vehicle at the current moment are acquired;
inputting the position information, the speed information and the acceleration information into a preset vehicle control model for analysis so as to obtain vehicle control parameters;
controlling the vehicle to run according to the vehicle control parameters;
wherein, before the step of inputting the position information, the speed information and the acceleration information into a preset vehicle control model for analysis to obtain vehicle control parameters, the method further comprises:
extracting security verification parameters from the position information, the speed information and the acceleration information;
sequencing the position information, the speed information and the acceleration information in a preset sequence to obtain a sequencing result;
encrypting the sequencing result to obtain a security verification parameter;
when the safety verification parameters are consistent with the safety verification parameters, the step of inputting the position information, the speed information and the acceleration information into a preset vehicle control model for analysis is executed to obtain vehicle control parameters;
when the vehicle disturbance is detected, before the step of acquiring the position information, the speed information and the acceleration information of the vehicle at the current moment, the method further comprises the following steps:
acquiring a historical operation information set of a vehicle;
training an initial neural network model according to the historical operation information set to obtain a vehicle control neural network model;
calculating a control network weight according to the historical operation information set through a weight calculation formula, wherein the weight calculation formula is obtained by derivation based on a least square method and a neural network reinforcement learning algorithm;
determining a preset vehicle control model according to the control network weight and the vehicle control neural network model;
the weight calculation formula is as follows:
in the formula, W(i+1)For controlling the network weight matrix, M is the historical operation information set, i is the iterative computation times, A(i)For the running matrix value, B, obtained by the i-th iteration(i)And T is a matrix transposer for the operation integral value obtained by the ith iterative calculation.
2. The vehicle control method according to claim 1, characterized by, after the step of controlling the vehicle to run in accordance with the vehicle control parameter, further comprising:
acquiring position data, speed data and acceleration data of the vehicle when the vehicle runs according to the vehicle control parameters;
updating the historical operating information set according to the position data, the speed data and the acceleration data;
and updating the control network weight in the preset vehicle control model according to the updated historical operation information set.
3. The vehicle control method according to any one of claims 1-2, characterized in that, before the step of acquiring the position information, the speed information, and the acceleration information of the vehicle at the present time when the vehicle disturbance is detected, further comprising:
acquiring the running parameters of the vehicle;
judging whether system faults, detector signal noise or vehicle jolt exist according to the operation parameters;
a vehicle disturbance is determined to be detected in the presence of a system fault, detector signal noise, and/or vehicle bump.
4. The vehicle control method according to any one of claims 1-2, characterized in that, after the step of controlling the vehicle to run in accordance with the vehicle control parameter, further comprising:
generating a vehicle disturbance elimination record according to the position information, the speed information, the acceleration information and the vehicle control parameter, and acquiring a driving mode of the vehicle;
when the driving mode is an automatic driving mode, pushing the vehicle disturbance elimination record to a vehicle security officer;
and when the driving mode is the auxiliary driving mode, displaying the vehicle disturbance elimination record.
5. A vehicle control apparatus characterized by comprising the following modules:
the information acquisition module is used for acquiring the position information, the speed information and the acceleration information of the vehicle at the current moment when the vehicle disturbance is detected;
the parameter determining module is used for inputting the position information, the speed information and the acceleration information into a preset vehicle control model for analysis so as to obtain vehicle control parameters;
the vehicle control module is used for controlling the vehicle to run according to the vehicle control parameters;
the parameter determination module is further configured to extract a security verification parameter from the position information, the speed information, and the acceleration information; sorting the position information, the speed information and the acceleration information in a preset sequence to obtain a sorting result; encrypting the sequencing result to obtain a security verification parameter; when the safety verification parameters are consistent with the safety verification parameters, inputting the position information, the speed information and the acceleration information into a preset vehicle control model for analysis so as to obtain vehicle control parameters;
the information acquisition module is also used for acquiring a historical operation information set of the vehicle; training an initial neural network model according to the historical operation information set to obtain a vehicle control neural network model; calculating a control network weight according to the historical operation information set through a weight calculation formula, wherein the weight calculation formula is obtained by derivation based on a least square method and a neural network reinforcement learning algorithm; determining a preset vehicle control model according to the control network weight and the vehicle control neural network model;
the weight calculation formula is as follows:
in the formula, W(i+1)For controlling the network weight matrix, M is the historical operation information set, i is the iterative computation times, A(i)For the running matrix value, B, obtained by the i-th iteration(i)And T is a matrix transposer for the operation integral value obtained by the ith iterative calculation.
6. A vehicle control apparatus, characterized by comprising: memory, a processor and a vehicle control program stored on the memory and executable on the processor, the vehicle control program when executed by the processor implementing the steps of the vehicle control method as claimed in any one of claims 1-4.
7. A computer-readable storage medium, characterized in that a vehicle control program is stored thereon, which when executed implements the steps of the vehicle control method according to any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011425745.4A CN112455460B (en) | 2020-12-07 | 2020-12-07 | Vehicle control method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011425745.4A CN112455460B (en) | 2020-12-07 | 2020-12-07 | Vehicle control method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112455460A CN112455460A (en) | 2021-03-09 |
| CN112455460B true CN112455460B (en) | 2022-05-03 |
Family
ID=74800296
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011425745.4A Active CN112455460B (en) | 2020-12-07 | 2020-12-07 | Vehicle control method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112455460B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114312843B (en) * | 2021-12-29 | 2023-10-20 | 北京百度网讯科技有限公司 | Method and device for determining information |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070213886A1 (en) * | 2006-03-10 | 2007-09-13 | Yilu Zhang | Method and system for driver handling skill recognition through driver's steering behavior |
| CN108196446B (en) * | 2017-12-14 | 2020-04-17 | 北京理工大学 | Dynamic planning optimal control method for double-motor load with unknown model |
| CN108803604A (en) * | 2018-06-06 | 2018-11-13 | 深圳市易成自动驾驶技术有限公司 | Vehicular automatic driving method, apparatus and computer readable storage medium |
| CN109263651A (en) * | 2018-09-28 | 2019-01-25 | 上汽通用五菱汽车股份有限公司 | Safe checking method, autonomous driving vehicle and the storage medium of autonomous driving vehicle |
| CN109921504B (en) * | 2019-04-03 | 2021-08-24 | 湖南工程学院 | Vehicle-mounted hybrid energy storage system and nonlinear robust self-adaptive power control method thereof |
| CN109946975B (en) * | 2019-04-12 | 2020-04-24 | 北京理工大学 | Reinforced learning optimal tracking control method of unknown servo system |
| CN110509916B (en) * | 2019-08-30 | 2021-06-29 | 的卢技术有限公司 | Vehicle body posture stabilizing method and system based on deep neural network |
| CN111618864B (en) * | 2020-07-20 | 2021-04-23 | 中国科学院自动化研究所 | Robot model prediction control method based on adaptive neural network |
-
2020
- 2020-12-07 CN CN202011425745.4A patent/CN112455460B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112455460A (en) | 2021-03-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9221428B2 (en) | Driver identification system and methods | |
| US11142190B2 (en) | System and method for controlling autonomous driving vehicle | |
| US20210206382A1 (en) | Information processing apparatus, information processing system, information processing method, and program | |
| CN108009463B (en) | Identity recognition method and device | |
| KR102190054B1 (en) | In-vehicle external data intrusion detection apparatus by comparing multiple information entropy and operating method thereof | |
| CN110658542B (en) | Method, device, equipment and storage medium for positioning and identifying automatic driving automobile | |
| US20210326677A1 (en) | Determination device, determination program, determination method and method of generating neural network model | |
| CN113933858A (en) | Abnormal detection method and device of positioning sensor and terminal equipment | |
| US11539724B2 (en) | Centralized detection techniques for cyber-attacks directed at connected vehicles | |
| CN114077218B (en) | Road data evaluation report generation method, device, equipment and storage medium | |
| Akowuah et al. | Physical invariant based attack detection for autonomous vehicles: Survey, vision, and challenges | |
| KR101519217B1 (en) | Apparatus for judging driver inattention and method thereof | |
| CN112455460B (en) | Vehicle control method, device, equipment and storage medium | |
| Tanksale | Anomaly detection for controller area networks using long short-term memory | |
| Shangguan et al. | Health monitoring for cyber physical systems | |
| CN112729862B (en) | Unmanned driving behavior safety assessment method and device and electronic equipment | |
| CN113085872B (en) | Driving behavior evaluation method, device, equipment and storage medium | |
| US20230237584A1 (en) | Systems and methods for evaluating vehicle insurance claims | |
| CN108900634A (en) | A kind of remote vehicle control method and system based on V2X | |
| CN110660217B (en) | Method and device for detecting information security | |
| CN115640828A (en) | Vehicle-mounted digital twin cheating detection method based on antagonistic generation network | |
| CN112163016A (en) | Driving capability evaluation method based on Internet of vehicles cloud cooperation and related device | |
| CN114616157A (en) | Method and system for checking automated driving functions by reinforcement learning | |
| JP2021024520A (en) | Driving behavior evaluation device, driving behavior evaluation method, and driving behavior evaluation program | |
| CN115190427B (en) | Emergency rescue calling system for motor vehicle |
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 |