CN112596509A - Vehicle control method, device, computer equipment and computer readable storage medium - Google Patents
Vehicle control method, device, computer equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN112596509A CN112596509A CN201910873792.6A CN201910873792A CN112596509A CN 112596509 A CN112596509 A CN 112596509A CN 201910873792 A CN201910873792 A CN 201910873792A CN 112596509 A CN112596509 A CN 112596509A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- estimation
- signal
- information
- sensing
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000006855 networking Effects 0.000 claims abstract description 29
- 238000011156 evaluation Methods 0.000 claims abstract description 21
- 238000004891 communication Methods 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims description 35
- 238000005457 optimization Methods 0.000 claims description 15
- 238000005259 measurement Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 8
- 230000001276 controlling effect Effects 0.000 description 15
- 238000004422 calculation algorithm Methods 0.000 description 11
- 230000001133 acceleration Effects 0.000 description 9
- 230000008569 process Effects 0.000 description 8
- 230000000875 corresponding effect Effects 0.000 description 7
- 238000013461 design Methods 0.000 description 7
- 238000001914 filtration Methods 0.000 description 6
- 230000008447 perception Effects 0.000 description 6
- 230000004927 fusion Effects 0.000 description 5
- 238000002474 experimental method Methods 0.000 description 4
- 230000006872 improvement Effects 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
- G05D1/0251—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means extracting 3D information from a plurality of images taken from different locations, e.g. stereo vision
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Electromagnetism (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The invention discloses a vehicle control method for improving the tracking precision of an automatic driving automobile track, which comprises the following steps: acquiring vehicle-end signals and sensing signals around a vehicle in real time, wherein the sensing signals comprise vehicle-mounted sensing signals acquired by a vehicle-mounted sensor and vehicle networking sensing signals acquired by a vehicle networking communication module; reconstructing a reconstruction signal capable of replacing other vehicle-mounted sensors through a vehicle kinematics or dynamics model according to the vehicle-end signal and the vehicle-mounted sensing signal of the specific vehicle-mounted sensor; estimating according to the vehicle-end signal, the sensing signal and the reconstruction signal to generate estimation information, and performing reliability evaluation on the estimation information to extract reliable estimation information; and controlling the vehicle running state according to the reliable estimation information. The invention also discloses a vehicle control device, computer equipment and a computer readable storage medium for improving the tracking precision of the track of the automatic driving vehicle. By adopting the invention, the motion control precision of the whole vehicle can be improved, and better track tracking can be realized.
Description
Technical Field
The invention relates to the technical field of intelligent tracking, in particular to a vehicle control method and device for improving the tracking precision of an automatic driving vehicle track, computer equipment and a computer readable storage medium.
Background
The vehicle motion control is one of key technologies of automatically driving the automobile, and is based on vehicle tracks of environment perception and decision planning, and through controlling actuating mechanisms such as an accelerator, a brake and a steering mechanism to accurately follow the planned target tracks, basic operations such as speed regulation, distance keeping, lane changing and overtaking can be realized during the driving process of the automobile, so that the safety, the maneuverability and the stability of the automobile are ensured. The vehicle motion control core technology includes longitudinal and lateral control of the vehicle, and vehicle state estimation, road (gradient, road adhesion coefficient) information estimation, and the like.
How to control the vehicle to better follow the target track is a core problem to be solved by motion control, and for the problem, technicians mostly improve the track tracking precision from the aspect of a control algorithm at the present stage, such as optimal control, model predictive control and the like. However, little attention is paid to the accuracy and reliability of the control input signal; the accuracy and reliability of the control input signal directly affect the vehicle track following effect, and are particularly important for controlling the accuracy and reliability of the input signal based on a model control algorithm. At present, control input signals are directly obtained from a vehicle-mounted sensor or a whole vehicle CAN network and a state estimation module, control operation is directly carried out, and then corresponding control quantity is obtained to realize motion control of a vehicle.
Disclosure of Invention
The invention aims to solve the technical problem of providing a vehicle control method, a vehicle control device, computer equipment and a computer readable storage medium for improving the tracking precision of an automatic driving vehicle track, which can improve the motion control precision of the whole vehicle and realize better track tracking.
In order to solve the technical problem, the invention provides a vehicle control method for improving the tracking precision of an automatic driving automobile track, which comprises the following steps: acquiring vehicle-end signals and sensing signals around a vehicle in real time, wherein the sensing signals comprise vehicle-mounted sensing signals acquired by a vehicle-mounted sensor and vehicle networking sensing signals acquired by a vehicle networking communication module; reconstructing a reconstructed signal capable of replacing other vehicle-mounted sensors through a vehicle kinematics or dynamics model according to the vehicle-end signal and the vehicle-mounted sensing signal of the specific vehicle-mounted sensor; estimating according to the vehicle-end signal, the sensing signal and the reconstruction signal to generate estimation information, and performing reliability evaluation on the estimation information to extract reliable estimation information; and controlling the running state of the vehicle according to the reliable estimation information.
As an improvement of the above, the step of performing reliability evaluation on the estimation information to extract reliable estimation information includes: and comparing the estimation information with a preset scene calibration value, judging whether the confidence coefficient of the estimation information is greater than a preset confidence coefficient or whether the estimation information is within the interval range of the preset scene calibration value, if so, taking the estimation information as reliable estimation information, and if not, taking the preset scene calibration value as reliable estimation information.
In the vehicle control method, a reconstructed signal capable of replacing other vehicle-mounted sensors is reconstructed through a vehicle kinematics or dynamic model according to the vehicle-mounted signals and the vehicle-mounted sensing signals of the inertial measurement unit.
As an improvement of the above solution, the step of performing estimation processing according to the vehicle-end signal, the sensing signal, and the reconstructed signal to generate estimation information includes: identifying and processing the vehicle-end signal to extract vehicle parameters; the method comprises the steps of carrying out preliminary estimation on control input parameters according to vehicle end signals and vehicle parameters to generate estimated information, and carrying out optimization processing on the estimated information according to sensing signals and reconstruction signals to generate estimated information, wherein the control input parameters comprise vehicle states, road gradients and road adhesion coefficients.
Correspondingly, the invention also provides a vehicle control device for improving the tracking precision of the track of the automatic driving vehicle, which comprises the following components: the sensing layer is used for acquiring sensing signals around the vehicle in real time, and the sensing signals comprise vehicle-mounted sensing signals acquired by a vehicle-mounted sensor and vehicle networking sensing signals acquired by a vehicle networking communication module; the sensor signal reconstruction layer is used for reconstructing a reconstruction signal capable of replacing other vehicle-mounted sensors through a vehicle kinematics or dynamic model according to a vehicle end signal and a vehicle-mounted sensing signal of a specific vehicle-mounted sensor; the estimation layer is used for carrying out estimation processing according to the vehicle-end signal, the sensing signal and the reconstruction signal to generate estimation information and carrying out reliability evaluation on the estimation information to extract reliable estimation information; and the control layer is used for controlling the running state of the vehicle according to the reliable estimation information.
As an improvement of the above, the estimation layer includes: the parameter identification module is used for identifying and processing the vehicle-end signal to extract vehicle parameters; the vehicle state estimation module is used for carrying out preliminary estimation on the vehicle state according to the vehicle end signal and the vehicle parameter so as to generate estimated information, and carrying out optimization processing on the estimated information according to the sensing signal and the reconstruction signal so as to generate estimated information; the road slope estimation module is used for carrying out preliminary estimation on the road slope according to the vehicle end signal and the vehicle parameter so as to generate estimated information, and carrying out optimization processing on the estimated information according to the sensing signal and the reconstruction signal so as to generate estimated information; the road adhesion coefficient estimation module is used for carrying out preliminary estimation on the road adhesion coefficient according to the vehicle end signal and the vehicle parameter so as to generate estimated information, and carrying out optimization processing on the estimated information according to the sensing signal and the reconstruction signal so as to generate estimated information; and the reliability evaluation module is used for comparing the estimation information with a preset scene calibration value, judging whether the confidence coefficient of the estimation information is greater than the preset confidence coefficient or whether the estimation information is within the interval range of the preset scene calibration value, if so, taking the estimation information as reliable estimation information, and if not, taking the preset scene calibration value as reliable estimation information.
As an improvement of the above scheme, the sensing layer includes: the vehicle-mounted sensor module is used for acquiring vehicle-mounted sensing signals through a vehicle-mounted sensor; and the Internet of vehicles communication module is used for acquiring Internet of vehicles sensing signals.
As a refinement of the above solution, the specific on-board sensor is an inertial measurement unit.
Accordingly, the present invention also provides a computer device comprising a memory storing a computer program and a processor executing the steps of the above vehicle control method.
Accordingly, the invention also provides a computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the vehicle control method.
The implementation of the invention has the following beneficial effects:
the invention fully utilizes the vehicle-end signal, the sensing signal and the reconstructed signal to carry out estimation processing so as to obtain some estimation information which is difficult to obtain at ordinary times or obtained at high cost, and can effectively improve the precision and the reliability of the corresponding estimation information. Meanwhile, the reliability of the estimated information is judged, and only the estimated information with the reliability meeting the requirement is used for subsequent control, so that the motion control precision of the whole vehicle can be improved, and the track tracking of the automatic driving vehicle with high precision and small error is realized.
Furthermore, the invention can also utilize the existing inertia measurement unit of the automatic driving automobile to reconstruct partial vehicle-mounted sensor signals, so that the system has certain redundancy on the premise of not increasing the hardware cost, and the overall reliability and safety of the system are improved.
Drawings
FIG. 1 is a flowchart of an embodiment of a vehicle control method of the present invention to improve the tracking accuracy of an autonomous vehicle trajectory;
FIG. 2 is a flowchart illustrating an embodiment of the present invention for performing estimation processing to generate estimation information according to a vehicle-end signal, a sensing signal, and a reconstructed signal;
FIG. 3 is a flowchart of an embodiment of the present invention for performing reliability evaluation on estimated information to extract reliable estimated information;
FIG. 4 is a schematic illustration of a road grade of the present invention;
fig. 5 is a schematic structural diagram of an embodiment of the vehicle control device for improving the tracking accuracy of the trajectory of the autonomous vehicle according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings.
Referring to fig. 1, fig. 1 is a flowchart illustrating an embodiment of a vehicle control method for improving tracking accuracy of an autonomous vehicle according to the present invention, including:
and S101, acquiring vehicle-end signals and sensing signals around the vehicle in real time.
The vehicle-end signal is from a vehicle-mounted CAN bus and is used for recording the state quantity of the vehicle.
The sensing signals comprise vehicle-mounted sensing signals acquired by a vehicle-mounted sensor and vehicle networking sensing signals acquired by a vehicle networking communication module. Specifically, the vehicle-mounted sensor comprises a camera, a laser radar, a millimeter wave radar, an ultrasonic sensor, an inertial navigation system and a positioning system, and is used for sensing the surrounding environment of the vehicle; the vehicle networking communication module realizes information interaction between vehicles and infrastructure through V2V (vehicle to vehicle) and V2I (vehicle-to-infrastructure). Therefore, the advantages of the vehicle-mounted sensor and the vehicle networking communication module are complementary, and the vehicle can better understand the surrounding road and traffic environment.
And S102, reconstructing a reconstruction signal capable of replacing other vehicle-mounted sensors through a vehicle kinematics or dynamic model according to the vehicle-end signal and the vehicle-mounted sensing signal of the specific vehicle-mounted sensor.
The vehicle-mounted sensor serving as an electronic product has certain risks of failure and malfunction, and the reliability of the vehicle-mounted sensor determines the reliability and safety of the whole vehicle control system to a great extent. Aiming at the problems, if redundancy is realized on hardware, the cost is increased and inconvenience is brought to the arrangement of the whole vehicle. Therefore, the invention provides a sensor signal reconstruction idea, namely reconstructing vehicle-mounted sensing signals of other vehicle sensors based on output signals of some additional specific vehicle-mounted sensors installed in the existing automatic driving vehicle on the premise of not increasing hardware cost.
Further, the specific vehicle-mounted sensor may be an Inertial Measurement Unit (IMU), and in the vehicle control method, a reconstructed signal that may replace another vehicle-mounted sensor is reconstructed through a vehicle kinematics or dynamics model according to the vehicle-end signal and a vehicle-mounted sensing signal of the IMU.
It should be noted that autonomous vehicles of the L3 and above are usually equipped with IMU systems, which provide a premise and basis for signal reconstruction; meanwhile, the information provided by the IMU does not have any external dependence, is similar to a complete system of a black box, and has high reliability; the IMU does not need any external input signal, can be arranged in a non-leakage area such as an automobile chassis and the like, can resist external electronic or mechanical attack, and is high in safety; there is inherently some redundancy between the IMU measurements of angular velocity and acceleration, making the confidence of the output result higher than other vehicle-mounted sensors. Therefore, the invention adopts the IMU to reconstruct the vehicle-mounted sensor signal, and can effectively ensure the stability of the system.
Specifically, the IMU is mainly composed of an accelerometer and a gyroscope, and outputs of the IMU are a longitudinal acceleration ax, a lateral acceleration ay, a vertical acceleration az, and rotation angles about respective axes, a yaw angle, a pitch angle, and a roll angle. Therefore, the vehicle-mounted sensor can output signals through the IMU and can realize signal reconstruction through a vehicle kinematic model or a dynamic model. Meanwhile, in order to ensure the reliability and accuracy of the reconstructed signal, the model parameters of the reconstructed signal need to be calibrated by an experimental method.
S103, estimating according to the vehicle-end signal, the sensing signal and the reconstructed signal to generate estimated information, and performing reliability evaluation on the estimated information to extract reliable estimated information.
In the prior art, a control input signal of a vehicle running state is directly taken from a vehicle-mounted sensor or is directly subjected to control operation from a whole vehicle CAN network, and then a corresponding control quantity is obtained to realize motion control of a vehicle. Different from the prior art, the method introduces reliability evaluation, and only the estimation information with the reliability meeting the requirement can be used for subsequent vehicle running state control, so that the quantity of input signals in the control process is greatly enriched, and the precision of the input signals in the control process is improved.
And S104, controlling the running state of the vehicle according to the reliable estimation information.
The invention adopts a proper control algorithm to carry out optimization control adjustment on the running state of the vehicle based on various reliable estimation information, thereby realizing high-precision and small-error track tracking.
The method can be applied to vehicle motion control of the automatic driving automobile, comprehensively considers the signal redundancy of the vehicle sensor, fully utilizes the information of the vehicle end and the road end to optimize and control the input signal precision, enriches the control input signal quantity, realizes accurate vehicle motion control, and further improves the tracking precision of the automatic driving track of the vehicle.
As shown in fig. 2, the step of performing estimation processing according to the vehicle-end signal, the sensing signal and the reconstructed signal to generate estimation information includes:
s201, identifying and processing the vehicle-end signal to extract vehicle parameters.
The identification processing is mainly to identify parameters which are difficult to obtain by the vehicle based on vehicle-end signals (from a vehicle-mounted CAN bus) so as to extract vehicle parameters, such as axle cornering stiffness, center of mass position, tire cornering stiffness and the like, and to take the vehicle parameters as input of the next estimation processing.
S202, performing preliminary estimation on the control input parameters according to the vehicle end signals and the vehicle parameters to generate estimated information, and performing optimization processing on the estimated information according to the sensing signals and the reconstruction signals to generate estimated information.
Preferably, the control input parameters include vehicle state, road gradient, and road surface adhesion coefficient. The vehicle state is preliminarily estimated according to the vehicle end signal and the vehicle parameter to generate estimated information, and the estimated information is optimized according to the sensing signal and the reconstruction signal to generate estimated information; the road gradient can be preliminarily estimated according to the vehicle end signal and the vehicle parameter to generate estimated information, and the estimated information is optimized according to the sensing signal and the reconstruction signal to generate estimated information; the road surface adhesion coefficient can be preliminarily estimated according to the vehicle end signal and the vehicle parameter to generate estimated information, and the estimated information is optimized according to the sensing signal and the reconstruction signal to generate estimated information. Wherein the estimation of the vehicle state is coupled in correlation with the estimation of the road gradient and the estimation of the road adhesion coefficient, respectively, and the estimation information thereof are inputs to each other.
It should be noted that vehicle state estimation is an important issue in vehicle dynamics, aims to determine important variables such as longitudinal vehicle speed, yaw rate, center of mass and yaw angle in a vehicle driving state, and is one of key technologies for realizing intelligent vehicle motion control. Wherein the longitudinal dynamics control of the smart car is dependent on an estimate of the longitudinal speed of the car; lateral dynamics control relies on accurate estimation of centroid slip angles, etc. However, since the above state information cannot be obtained by direct measurement of the sensor or the direct measurement cost is too high, from the viewpoint of cost saving and practical application, it is necessary to accurately calculate the control input parameters required for control but not measurable according to the vehicle-mounted sensor and by the vehicle state estimation technique.
The physical models used for vehicle state estimation can be roughly divided into two categories: kinematic based models and kinetic based models. The two have advantages and disadvantages, the estimator designed based on the kinematic model has higher robustness, the change of model parameters has little influence on the estimation effect, but the method depends on sensor information and has high requirements on the installation, calibration and precision of the sensor. An estimator designed based on a dynamic model has lower requirements on a sensor than the former, but has higher requirements on the accuracy of the model, so that the model can reflect the dynamic characteristics of the vehicle as accurately as possible and is sensitive to the change of model parameters. The physical model used for the specific estimation is not limited by the invention.
At present, the common vehicle state estimation methods mainly include a least square method, a state observer method (a luneberg observer, a sliding mode observer, a robust observer, and the like), kalman filtering, various derivative algorithms based on the kalman filtering, and the like. Since each estimation algorithm has its own advantages and disadvantages, the present invention is not limited to a specific estimation method.
During the estimation process, firstly, the normal running of the vehicle is ensured, and the required control input parameters are reliably estimated based on the vehicle-mounted sensor and the vehicle-end signals obtained from the CAN bus. Meanwhile, in order to improve the accuracy and reliability of estimation, the invention introduces the Internet of vehicles, and further improves the performance of the estimation system through information interaction between vehicles and workshops and fusion of additional information.
The estimation process is further described in detail below with reference to specific embodiments:
example 1:
estimation processing for a vehicle state. The estimation process of the vehicle state mainly estimates common control input signals required for control of the longitudinal vehicle speed, the centroid slip angle, the yaw rate, and the like.
During estimation processing, additional vehicle networking sensing signals (such as speed limit signals, vehicle-to-vehicle relative distance, speed and acceleration signals) can be acquired through the vehicle networking, the vehicle networking sensing signals and the vehicle-mounted sensing signals are jointly used as input of vehicle state estimation, and the vehicle state at the moment is estimated by adopting a fusion estimation algorithm.
Example 2:
an estimation process for a road gradient. During estimation processing, extra vehicle networking sensing signals (such as gradient information (uphill, downhill, uphill, downhill and highway grade) can be obtained through a vehicle networking, the vehicle networking sensing signals and the vehicle-mounted sensing signals are jointly used as input of the road gradient, and the road gradient is estimated by adopting a fusion estimation algorithm. It should be noted that the main purpose of slope identification is to be used for vehicle slope compensation control, where it is difficult to determine a slope Flag (flat road Flag is 0, uphill Flag is 1, and downhill Flag is-1) due to various factors, and if the determination is performed only based on the vehicle-mounted sensor signal, the vehicle may be switched between acceleration and braking continuously, which affects riding comfort, and information given by the internet of vehicles may solve the problem well.
Example 3:
and (5) estimation processing for a road adhesion coefficient. During estimation processing, additional vehicle networking sensing signals (such as sunny days, cloudy days, snowy days, wind speed, wind direction, air temperature and road material) can be obtained through the vehicle networking, the vehicle networking sensing signals and the vehicle-mounted sensing signals are jointly used as the input of the road adhesion coefficient, and the vehicle driving road adhesion coefficient at the moment is estimated by adopting a fusion estimation algorithm.
As shown in fig. 3, the step of performing reliability evaluation on the estimation information to extract reliable estimation information includes:
s301, comparing the estimation information with a preset scene calibration value, and judging whether the confidence coefficient of the estimation information is greater than a preset confidence coefficient or whether the estimation information is in the interval range of the preset scene calibration value. Preferably, the preset confidence level is 95%, but not limited thereto.
And S302, if the judgment result is yes, the estimation information is used as reliable estimation information.
And S303, when the judgment result is no, taking the preset scene calibration value as reliable estimation information.
It should be noted that, reliability evaluation is to verify the reliability of each estimation information by constructing a scene model library, and specifically follows the following principle:
1. building a scene model library based on experimental data, and calibrating each scene calibration value or the interval range of the scene calibration value;
2. the scene model library must cover commonly used driving scenes;
3. and comparing the estimation information with the scene calibration value, if the confidence coefficient of the estimation information is greater than the preset confidence coefficient or is within the interval range of the preset scene calibration value, considering that the estimation information is reliable and is used as the input for controlling the vehicle running state in the next step, and otherwise, filtering the estimation information and using the scene calibration value as the input for controlling the vehicle running state in the next step.
The reliability evaluation is further detailed below with reference to specific examples:
example 1:
reliability assessment for vehicle conditions. The method comprises the steps of building a common scene based on advanced equipment such as a simulation platform, a hardware-in-the-loop platform, a driving simulator and the like, designing an experiment value of a common typical working condition experiment acquisition estimation target to be fused with an actual vehicle experiment value, calibrating common driving scene model parameters in reliability evaluation, finally comparing estimated information (namely vehicle state) with a scene calibration value, if the confidence coefficient of the estimated information is greater than 95% or is within the interval range of the preset scene calibration value, considering the estimated information to be reliable and used as input for controlling the vehicle running state in the next step, and otherwise, filtering the estimated information and using the scene calibration value as input for controlling the vehicle running state in the next step.
Example 2:
and evaluating the reliability of the road gradient. As shown in fig. 4, the gradient calculation formula is i-h/s-tan α, and when building the gradient scene model library, on one hand, roads meeting the design specifications are considered, and on the other hand, non-specification design is also considered.
Designing a road according to a standard: according to the design specifications of highway routes in China, the maximum longitudinal slope of a micro-hill area of a highway plain is 3%, the maximum slope of a mountain heavy-hill area is 5%, the maximum slope of a micro-hill area of a first-level automobile special highway plain is 4%, and the maximum slope of a mountain heavy-hill area is 6%; the plain micro-hill area of a general level four highway is 5 percent, and the mountain heavy-hill area is 9 percent; and building a slope scene model based on the road grade specification, and giving a corresponding slope scene calibration value or interval.
Non-standard design roads: the method mainly comprises steep slopes, slope scenes of entrances and exits of underground parking lots and the like.
Therefore, if the vehicle runs on a road meeting the road design specification, road grade information is given based on the internet of vehicles, and a slope scene model is selected, namely a corresponding scene calibration value i is calibratedsOr interval range of scene calibration values is1is2]Estimating the confidence N of the information ii＝i/isX 100%, if NiNot less than 95% or i ∈ [ i ∈ >s1 is2]If the estimated information is accurate, the estimated information can be used as the input for controlling the vehicle running state in the next step, otherwise, if the estimated information is poor in precision, the estimated information is filtered, and the scene calibration value is used as the input for controlling the vehicle running state in the next step. And if the vehicle runs on the non-standard design road, taking the estimation information as a standard, and taking the estimation information as the input for controlling the running state of the vehicle in the next step.
Example 3:
and evaluating the reliability of the road adhesion coefficient. Building a road surface adhesion coefficient scene model library based on experimental data under different weather conditions and different road surface materials, namely calibrating a corresponding scene calibration value musOr interval range [ mu ] of scene calibration values1 μs2]Estimating the confidence N of the information muμ＝μ/μsX 100%, if NμMore than or equal to 95 percent or mu epsilon [ mu ]s1 μs2]If the estimated information is accurate, the estimated information can be used as the input for controlling the vehicle running state in the next step, otherwise, if the estimated information is poor in precision, the estimated information is filtered, and the scene calibration value is used as the input for controlling the vehicle running state in the next step.
Therefore, the accuracy of all the estimated information is evaluated, and when the confidence coefficient of the estimated information is greater than the preset confidence coefficient or whether the estimated information is within the interval range of the preset scene calibration value, the accuracy of the estimated information is considered to be high, and the running state of the vehicle can be directly controlled; otherwise, the accuracy of the estimated information is considered to be low, and the estimated information needs to be filtered in order not to influence the control accuracy of the vehicle running state.
Therefore, the method and the device initially estimate various required signals based on the vehicle-end signals, take the sensing signals and the reconstructed sensor signals as input for estimation optimization on the basis, improve estimation precision, and screen estimation information through reliability evaluation processing to ensure the precision and reliability of the signals input by control. In addition, in consideration of vehicle redundancy design, the method can realize signal reconstruction of partial sensors based on the vehicle-mounted sensor IMU added to the automatic driving automobile, and improves the reliability of the system. Therefore, the invention aims to integrate sensor signals, consider redundancy, optimally control the precision of input signals by using vehicle end and road end information, realize accurate vehicle motion control and further improve the vehicle track tracking precision.
Referring to fig. 5, fig. 5 shows a specific structure of the vehicle control apparatus for improving the tracking accuracy of the automated guided vehicle track according to the present invention, which includes:
and the perception layer 1 is used for acquiring perception signals around the vehicle in real time, and the perception signals comprise vehicle-mounted perception signals acquired by a vehicle-mounted sensor and vehicle networking perception signals acquired by a vehicle networking communication module. Specifically, the sensing layer comprises a vehicle-mounted sensor module 11 and a vehicle networking communication module 12, the vehicle-mounted sensor module 11 is used for acquiring vehicle-mounted sensing signals through a vehicle-mounted sensor, and the vehicle networking communication module 12 is used for acquiring vehicle networking sensing signals. The vehicle-mounted sensor comprises a camera, a laser radar, a millimeter wave radar, an ultrasonic sensor, an inertial navigation system and a positioning system and is used for sensing the surrounding environment of the vehicle; the internet of vehicles realizes information interaction between vehicles and Infrastructure through V2V (Vehicle to Vehicle) and V2I (Vehicle-to-Infrastructure). Therefore, the vehicle-mounted sensor module 11 and the vehicle networking communication module 12 have complementary advantages, and the vehicle can better understand the surrounding road and traffic environment.
And the sensor signal reconstruction layer 2 is used for reconstructing a reconstruction signal capable of replacing other vehicle-mounted sensors through a vehicle kinematics or dynamic model according to a vehicle-end signal (from a vehicle-mounted CAN bus) and a vehicle-mounted sensing signal of a specific vehicle-mounted sensor. Further, the specific on-board sensor is an inertial measurement unit. Specifically, the IMU is mainly composed of an accelerometer and a gyroscope, and outputs of the IMU are a longitudinal acceleration ax, a lateral acceleration ay, a vertical acceleration az, and rotation angles about respective axes, a yaw angle, a pitch angle, and a roll angle. Therefore, the vehicle-mounted sensor can output signals through the IMU and can realize signal reconstruction through a vehicle kinematic model or a dynamic model.
And the estimation layer 3 is used for carrying out estimation processing according to the vehicle-end signal, the sensing signal and the reconstructed signal to generate estimation information and carrying out reliability evaluation on the estimation information to extract reliable estimation information.
And the control layer 4 is used for controlling the running state of the vehicle according to the reliable estimation information. The control layer 4 performs optimization control adjustment on the vehicle running state by adopting a proper control algorithm based on various reliable estimation information, and realizes high-precision and small-error track tracking.
When the system works, the sensing layer 1 acquires sensing signals (vehicle-mounted sensing signals and Internet of vehicles sensing signals) around a vehicle in real time through the vehicle-mounted sensor module 11 and the Internet of vehicles communication module 12 and sends the sensing information to the sensor signal reconstruction layer 2 and the estimation layer 3; the sensor signal reconstruction layer 2 reconstructs a reconstruction signal which can replace other vehicle-mounted sensors through a vehicle kinematics or dynamic model according to a vehicle end signal and a vehicle-mounted sensing signal of a specific vehicle-mounted sensor, and sends the reconstruction signal to the estimation layer 3; the estimation layer 3 carries out estimation processing according to the vehicle-end signal, the sensing signal and the reconstruction signal to generate estimation information, carries out reliability evaluation on the estimation information to extract reliable estimation information, and sends the reliable estimation information to the control layer 4; the control layer 4 controls the vehicle running state according to the reliable estimation information.
The method can be applied to vehicle motion control of the automatic driving automobile, comprehensively considers the signal redundancy of the vehicle sensor, fully utilizes the information of the vehicle end and the road end to optimize and control the input signal precision, enriches the control input signal quantity, realizes accurate vehicle motion control, and further improves the tracking precision of the automatic driving track of the vehicle.
Specifically, the estimation layer 3 includes:
the parameter identification module 31 is configured to perform identification processing on the vehicle-end signal to extract a vehicle parameter. The parameter identification module is mainly used for identifying parameters which are difficult to obtain by the vehicle based on vehicle-end signals (from a vehicle-mounted CAN bus) so as to extract vehicle parameters, such as axle cornering stiffness, mass center position, tire cornering stiffness and the like, and taking the vehicle parameters as the input of the vehicle state estimation module, the road slope estimation module and the road adhesion coefficient estimation module.
And the vehicle state estimation module 32 is configured to perform preliminary estimation on a vehicle state according to the vehicle-end signal and the vehicle parameter to generate estimated information, and perform optimization processing on the estimated information according to the sensing signal and the reconstruction signal to generate estimated information. Specifically, the physical model used by the vehicle state estimation module can be roughly divided into two categories, namely a kinematics-based model and a dynamics-based model, and the physical model used for the specific estimation is not limited by the invention. Meanwhile, the common vehicle state estimation methods of the vehicle state estimation module mainly include a least square method, a state observer method (a luneberg observer, a sliding mode observer, a robust observer, and the like), kalman filtering, various derivative algorithms based on the kalman filtering, and the like, and the specific estimation method is not limited in the invention.
And the road slope estimation module 33 is configured to perform preliminary estimation on the road slope according to the vehicle-end signal and the vehicle parameter to generate estimated information, and perform optimization processing on the estimated information according to the sensing signal and the reconstruction signal to generate estimated information.
And the road adhesion coefficient estimation module 34 is configured to perform preliminary estimation on a road adhesion coefficient according to the vehicle-end signal and the vehicle parameter to generate estimated information, and perform optimization processing on the estimated information according to the sensing signal and the reconstruction signal to generate estimated information.
The reliability evaluation module 35 is configured to compare the estimation information with a preset scene calibration value, determine whether a confidence of the estimation information is greater than a preset confidence or whether the estimation information is within an interval range of the preset scene calibration value, if yes, use the estimation information as reliable estimation information, and if not, use the preset scene calibration value as reliable estimation information. Preferably, the preset confidence level is 95%, but not limited thereto.
The vehicle state estimation module 32 is coupled to the road gradient estimation module 33 and the road adhesion coefficient estimation module 34 in a correlated manner, and the estimation information is input to each other. At the same time, the modular arrangement of the evaluation layer 3 makes the addition of the system easier. During the estimation process, firstly, the normal running of the vehicle is ensured, and the required control input parameters are reliably estimated based on the vehicle-mounted sensor and the vehicle-end signals obtained from the CAN bus. Meanwhile, in order to improve the accuracy and reliability of estimation, the invention introduces the Internet of vehicles, and further improves the performance of the estimation system through information interaction between vehicles and workshops and fusion of additional information.
Correspondingly, the invention also provides computer equipment which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps of the vehicle control method when executing the computer program. Meanwhile, the present invention also provides a computer-readable storage medium having stored thereon a computer program which, when being executed by a processor, realizes the steps of the above-described vehicle control method.
According to the method, the vehicle-end signals are fully utilized to realize the initial estimation of the vehicle state information, the road gradient information and the road adhesion coefficient, the sensing signals and the reconstructed vehicle-mounted sensor signals are introduced to optimize the estimation information, some control input signals which are difficult to obtain at ordinary times or high in cost can be obtained, the selection of a control algorithm can be enriched, and the precision and the reliability of the corresponding estimation information are effectively improved; meanwhile, the reliability of the estimated information is judged, and only the estimated information with the reliability meeting the requirement is used for subsequent control, so that the motion control precision of the whole vehicle can be improved, and the track tracking of the automatic driving vehicle with high precision and small error is realized; the invention also reconstructs partial sensor signals based on the existing IMU of the vehicle-mounted sensor of the automatic driving vehicle, avoids the adverse effect of failure or fault on the whole system, ensures that the system has certain redundancy on the premise of not increasing the hardware cost, and improves the integral reliability and safety of the system.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (9)
1. A vehicle control method for improving the tracking accuracy of an autonomous vehicle trajectory, comprising:
acquiring vehicle-end signals and sensing signals around a vehicle in real time, wherein the sensing signals comprise vehicle-mounted sensing signals acquired by a vehicle-mounted sensor and vehicle networking sensing signals acquired by a vehicle networking communication module;
reconstructing a reconstruction signal capable of replacing other vehicle-mounted sensors through a vehicle kinematics or dynamics model according to the vehicle-end signal and the vehicle-mounted sensing signal of the specific vehicle-mounted sensor;
estimating according to the vehicle-end signal, the sensing signal and the reconstruction signal to generate estimation information, and performing reliability evaluation on the estimation information to extract reliable estimation information;
and controlling the running state of the vehicle according to the reliable estimation information.
2. The vehicle control method according to claim 1, wherein the step of performing reliability evaluation on the estimated information to extract reliable estimated information includes:
comparing the estimation information with a preset scene calibration value, judging whether the confidence coefficient of the estimation information is greater than a preset confidence coefficient or whether the estimation information is in the interval range of the preset scene calibration value,
if yes, the estimation information is used as reliable estimation information,
and if not, taking the preset scene calibration value as reliable estimation information.
3. The vehicle control method according to claim 1, wherein the specific vehicle-mounted sensor is an inertial measurement unit, and in the vehicle control method, a reconstructed signal which can replace other vehicle-mounted sensors is reconstructed through a vehicle kinematics or dynamics model according to the vehicle-end signal and a vehicle-mounted sensing signal of the inertial measurement unit.
4. The vehicle control method according to claim 1, wherein the step of performing estimation processing based on the end-of-vehicle signal, the sensing signal, and the reconstructed signal to generate the estimation information includes:
identifying and processing the vehicle-end signal to extract vehicle parameters;
and performing preliminary estimation on control input parameters according to the vehicle-end signals and the vehicle parameters to generate estimated information, and performing optimization processing on the estimated information according to the sensing signals and the reconstruction signals to generate estimated information, wherein the control input parameters comprise vehicle states, road gradients and road adhesion coefficients.
5. A vehicle control apparatus for improving the tracking accuracy of an autonomous vehicle, comprising:
the sensing layer is used for acquiring sensing signals around the vehicle in real time, and the sensing signals comprise vehicle-mounted sensing signals acquired by a vehicle-mounted sensor and vehicle networking sensing signals acquired by a vehicle networking communication module;
the sensor signal reconstruction layer is used for reconstructing a reconstruction signal capable of replacing other vehicle-mounted sensors through a vehicle kinematics or dynamic model according to a vehicle end signal and a vehicle-mounted sensing signal of a specific vehicle-mounted sensor;
the estimation layer is used for carrying out estimation processing according to the vehicle-end signal, the sensing signal and the reconstruction signal to generate estimation information and carrying out reliability evaluation on the estimation information to extract reliable estimation information;
and the control layer is used for controlling the running state of the vehicle according to the reliable estimation information.
6. The vehicle control apparatus according to claim 5, wherein the estimation layer includes:
the parameter identification module is used for identifying and processing the vehicle-end signal to extract vehicle parameters;
the vehicle state estimation module is used for carrying out preliminary estimation on the vehicle state according to the vehicle end signal and the vehicle parameter so as to generate estimated information, and carrying out optimization processing on the estimated information according to the sensing signal and the reconstruction signal so as to generate estimated information;
the road slope estimation module is used for carrying out preliminary estimation on the road slope according to the vehicle end signal and the vehicle parameter so as to generate estimated information, and carrying out optimization processing on the estimated information according to the sensing signal and the reconstruction signal so as to generate estimated information;
the road adhesion coefficient estimation module is used for carrying out preliminary estimation on the road adhesion coefficient according to the vehicle end signal and the vehicle parameter so as to generate estimated information, and carrying out optimization processing on the estimated information according to the sensing signal and the reconstruction signal so as to generate estimated information;
and the reliability evaluation module is used for comparing the estimation information with a preset scene calibration value, judging whether the confidence coefficient of the estimation information is greater than the preset confidence coefficient or whether the estimation information is within the interval range of the preset scene calibration value, if so, taking the estimation information as reliable estimation information, and if not, taking the preset scene calibration value as reliable estimation information.
7. The vehicle control apparatus according to claim 5, characterized in that the specific on-vehicle sensor is an inertial measurement unit.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 4.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910873792.6A CN112596509B (en) | 2019-09-17 | Vehicle control method, device, computer equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910873792.6A CN112596509B (en) | 2019-09-17 | Vehicle control method, device, computer equipment and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112596509A true CN112596509A (en) | 2021-04-02 |
| CN112596509B CN112596509B (en) | 2024-10-18 |
Family
ID=
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113156965A (en) * | 2021-04-30 | 2021-07-23 | 哈尔滨工程大学 | Hovercraft high-speed rotation control method based on longitudinal speed planning |
Citations (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2002032733A1 (en) * | 2000-10-20 | 2002-04-25 | Dufournier Technologies Sas | Device and method for detecting a motor vehicle tyre adherence on the ground |
| US20080262729A1 (en) * | 2007-04-18 | 2008-10-23 | Honeywell International Inc. | Inertial measurement unit fault detection isolation reconfiguration using parity logic |
| US20120083923A1 (en) * | 2009-06-01 | 2012-04-05 | Kosei Matsumoto | Robot control system, robot control terminal, and robot control method |
| CN102903162A (en) * | 2012-09-24 | 2013-01-30 | 清华大学 | Automobile running state information acquisition system and method |
| CN103034123A (en) * | 2012-12-11 | 2013-04-10 | 中国科学技术大学 | Dynamic model parameter identification based parallel robot control method |
| CN103399493A (en) * | 2013-08-07 | 2013-11-20 | 长春工业大学 | Real-time diagnosis and tolerant system for sensor faults of reconfigurable mechanical arm and method thereof |
| CN104554274A (en) * | 2013-10-24 | 2015-04-29 | 固特异轮胎和橡胶公司 | Road friction estimation system and method |
| CN104773173A (en) * | 2015-05-05 | 2015-07-15 | 吉林大学 | Autonomous driving vehicle traveling status information estimation method |
| CN105416294A (en) * | 2015-12-26 | 2016-03-23 | 吉林大学 | Heavy-duty combination vehicle parameter estimation method |
| CN106564495A (en) * | 2016-10-19 | 2017-04-19 | 江苏大学 | Intelligent vehicle safety driving enveloping reconstruction method integrated with characteristic of space and dynamics |
| CN106926845A (en) * | 2017-03-02 | 2017-07-07 | 中国第汽车股份有限公司 | A kind of method for dynamic estimation of vehicle status parameters |
| US20170329346A1 (en) * | 2016-05-12 | 2017-11-16 | Magna Electronics Inc. | Vehicle autonomous parking system |
| CN107628036A (en) * | 2016-07-19 | 2018-01-26 | 通用汽车环球科技运作有限责任公司 | The detection and reconstruction of sensor fault |
| CN108052100A (en) * | 2017-11-23 | 2018-05-18 | 南京航空航天大学 | A kind of intelligent network connection control system of electric automobile and its control method |
| CN108594820A (en) * | 2018-05-04 | 2018-09-28 | 中国矿业大学 | A kind of crawler type Intelligent Mobile Robot active obstacle system and its control method |
| CN109074085A (en) * | 2018-07-26 | 2018-12-21 | 深圳前海达闼云端智能科技有限公司 | A kind of autonomous positioning and map method for building up, device and robot |
| WO2019030022A1 (en) * | 2017-08-10 | 2019-02-14 | Deutsches Zentrum für Luft- und Raumfahrt e.V. | Method and apparatus for determining changes in the longitudinal dynamic behaviour of a rail vehicle |
| CN109612476A (en) * | 2018-12-04 | 2019-04-12 | 广州辰创科技发展有限公司 | Map reconstructing method, device, inertial navigation system and computer storage medium based on inertial navigation technology |
| CN109690434A (en) * | 2016-07-29 | 2019-04-26 | 维迪科研究所 | For manipulating the control system of autonomous vehicle |
| CN109866752A (en) * | 2019-03-29 | 2019-06-11 | 合肥工业大学 | Double mode parallel vehicles track following driving system and method based on PREDICTIVE CONTROL |
| US20190176818A1 (en) * | 2017-12-11 | 2019-06-13 | Volvo Car Corporation | Path prediction for a vehicle |
| CN110095635A (en) * | 2019-05-08 | 2019-08-06 | 吉林大学 | A kind of longitudinal vehicle speed estimation method of all-wheel drive vehicles |
| CN111216792A (en) * | 2018-11-26 | 2020-06-02 | 广州汽车集团股份有限公司 | Automatic driving vehicle state monitoring system and method and automobile |
| CN111610780A (en) * | 2019-02-25 | 2020-09-01 | 广州汽车集团股份有限公司 | Automatic driving vehicle path tracking control method and device |
Patent Citations (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2002032733A1 (en) * | 2000-10-20 | 2002-04-25 | Dufournier Technologies Sas | Device and method for detecting a motor vehicle tyre adherence on the ground |
| US20080262729A1 (en) * | 2007-04-18 | 2008-10-23 | Honeywell International Inc. | Inertial measurement unit fault detection isolation reconfiguration using parity logic |
| US20120083923A1 (en) * | 2009-06-01 | 2012-04-05 | Kosei Matsumoto | Robot control system, robot control terminal, and robot control method |
| CN102903162A (en) * | 2012-09-24 | 2013-01-30 | 清华大学 | Automobile running state information acquisition system and method |
| CN103034123A (en) * | 2012-12-11 | 2013-04-10 | 中国科学技术大学 | Dynamic model parameter identification based parallel robot control method |
| CN103399493A (en) * | 2013-08-07 | 2013-11-20 | 长春工业大学 | Real-time diagnosis and tolerant system for sensor faults of reconfigurable mechanical arm and method thereof |
| CN104554274A (en) * | 2013-10-24 | 2015-04-29 | 固特异轮胎和橡胶公司 | Road friction estimation system and method |
| CN104773173A (en) * | 2015-05-05 | 2015-07-15 | 吉林大学 | Autonomous driving vehicle traveling status information estimation method |
| CN105416294A (en) * | 2015-12-26 | 2016-03-23 | 吉林大学 | Heavy-duty combination vehicle parameter estimation method |
| US20170329346A1 (en) * | 2016-05-12 | 2017-11-16 | Magna Electronics Inc. | Vehicle autonomous parking system |
| CN107628036A (en) * | 2016-07-19 | 2018-01-26 | 通用汽车环球科技运作有限责任公司 | The detection and reconstruction of sensor fault |
| CN109690434A (en) * | 2016-07-29 | 2019-04-26 | 维迪科研究所 | For manipulating the control system of autonomous vehicle |
| CN106564495A (en) * | 2016-10-19 | 2017-04-19 | 江苏大学 | Intelligent vehicle safety driving enveloping reconstruction method integrated with characteristic of space and dynamics |
| CN106926845A (en) * | 2017-03-02 | 2017-07-07 | 中国第汽车股份有限公司 | A kind of method for dynamic estimation of vehicle status parameters |
| WO2019030022A1 (en) * | 2017-08-10 | 2019-02-14 | Deutsches Zentrum für Luft- und Raumfahrt e.V. | Method and apparatus for determining changes in the longitudinal dynamic behaviour of a rail vehicle |
| CN108052100A (en) * | 2017-11-23 | 2018-05-18 | 南京航空航天大学 | A kind of intelligent network connection control system of electric automobile and its control method |
| US20190176818A1 (en) * | 2017-12-11 | 2019-06-13 | Volvo Car Corporation | Path prediction for a vehicle |
| CN108594820A (en) * | 2018-05-04 | 2018-09-28 | 中国矿业大学 | A kind of crawler type Intelligent Mobile Robot active obstacle system and its control method |
| CN109074085A (en) * | 2018-07-26 | 2018-12-21 | 深圳前海达闼云端智能科技有限公司 | A kind of autonomous positioning and map method for building up, device and robot |
| CN111216792A (en) * | 2018-11-26 | 2020-06-02 | 广州汽车集团股份有限公司 | Automatic driving vehicle state monitoring system and method and automobile |
| CN109612476A (en) * | 2018-12-04 | 2019-04-12 | 广州辰创科技发展有限公司 | Map reconstructing method, device, inertial navigation system and computer storage medium based on inertial navigation technology |
| CN111610780A (en) * | 2019-02-25 | 2020-09-01 | 广州汽车集团股份有限公司 | Automatic driving vehicle path tracking control method and device |
| CN109866752A (en) * | 2019-03-29 | 2019-06-11 | 合肥工业大学 | Double mode parallel vehicles track following driving system and method based on PREDICTIVE CONTROL |
| CN110095635A (en) * | 2019-05-08 | 2019-08-06 | 吉林大学 | A kind of longitudinal vehicle speed estimation method of all-wheel drive vehicles |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113156965A (en) * | 2021-04-30 | 2021-07-23 | 哈尔滨工程大学 | Hovercraft high-speed rotation control method based on longitudinal speed planning |
| CN113156965B (en) * | 2021-04-30 | 2023-01-03 | 哈尔滨工程大学 | Hovercraft high-speed rotation control method based on longitudinal speed planning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109421742B (en) | Method and apparatus for monitoring autonomous vehicles | |
| CN110647056B (en) | Intelligent networking automobile environment simulation system based on whole automobile hardware-in-loop | |
| CN107792079B (en) | Autonomous vehicle with path prediction | |
| CN102076541B (en) | Path generation algorithm for automated lane centering and lane changing control system | |
| Park et al. | Integrated observer approach using in-vehicle sensors and GPS for vehicle state estimation | |
| US11167770B2 (en) | Autonomous vehicle actuation dynamics and latency identification | |
| CN104691609A (en) | Algorithm for steering angle command to torque command conversion | |
| US20210325896A1 (en) | Braking control behaviors for autonomous vehicles | |
| US20230419824A1 (en) | Method and device for determining traffic stream information, electronic equipment and storage medium | |
| CN112046487A (en) | Road surface gradient estimation method and system based on vehicle running state | |
| US20220242401A1 (en) | Systems and methods for updating the parameters of a model predictive controller with learned controls parameters generated using simulations and machine learning | |
| US20220242441A1 (en) | Systems and methods for updating the parameters of a model predictive controller with learned operational and vehicle parameters generated using simulations and machine learning | |
| CN112099378B (en) | Front vehicle lateral motion state real-time estimation method considering random measurement time lag | |
| CN111114536A (en) | Automatic parking control method and device for vehicle | |
| US20230249709A1 (en) | Architecture For Variable Motion Control Envelope | |
| CN113227831B (en) | Guardrail estimation method based on multi-sensor data fusion and vehicle-mounted equipment | |
| CN110550041B (en) | Road adhesion coefficient estimation method based on cloud data sharing | |
| CN112793566B (en) | Collision avoidance method and device | |
| Yan et al. | Considering variable road geometry in adaptive vehicle speed control | |
| CN113359724A (en) | Vehicle intelligent driving system and method based on unmanned aerial vehicle and storage medium | |
| Katriniok | Optimal vehicle dynamics control and state estimation for a low-cost GNSS-based collision avoidance system | |
| CN115476881B (en) | Vehicle track tracking control method, device, equipment and medium | |
| CN112596509B (en) | Vehicle control method, device, computer equipment and computer readable storage medium | |
| CN112596509A (en) | Vehicle control method, device, computer equipment and computer readable storage medium | |
| CN115098821A (en) | Trajectory reference curvature determination method, apparatus, device, medium, and program |
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 |