CN115167135A - Feedback and model feedforward cascade unmanned vehicle self-tendency optimal position and posture control system - Google Patents

Feedback and model feedforward cascade unmanned vehicle self-tendency optimal position and posture control system Download PDF

Info

Publication number
CN115167135A
CN115167135A CN202210862219.7A CN202210862219A CN115167135A CN 115167135 A CN115167135 A CN 115167135A CN 202210862219 A CN202210862219 A CN 202210862219A CN 115167135 A CN115167135 A CN 115167135A
Authority
CN
China
Prior art keywords
vehicle
module
model
heading
error
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210862219.7A
Other languages
Chinese (zh)
Inventor
谢辉
李龙清
宋康
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tianjin University
Original Assignee
Tianjin University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tianjin University filed Critical Tianjin University
Priority to CN202210862219.7A priority Critical patent/CN115167135A/en
Publication of CN115167135A publication Critical patent/CN115167135A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
    • G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Steering Control In Accordance With Driving Conditions (AREA)

Abstract

The invention provides a feedback and model feedforward cascade unmanned vehicle self-optimization-seeking attitude control system, which comprises a signal processing module, a feedback control module, a feedforward control module, an extended state observer, a model parameter learning module, a boundary constraint module, an evaluation algorithm module and a parameter self-optimization-seeking module, wherein the feedback control module is connected with the model feedforward control module; the system takes feedback-feedforward as a basic framework of control, improves response speed while ensuring control precision, reduces the degree of dependence on vehicle model precision by combining the advantages of an extended state observer, meets different user requirements by designing an evaluation module and a self-optimization approach, and improves the control effect of a controller in a complex environment.

Description

Feedback and model feedforward cascade unmanned vehicle self-optimal attitude control system
Technical Field
The invention relates to the technical field of intelligent driving, in particular to a feedback and model feedforward cascade unmanned vehicle self-tendency optimal position and posture control system based on an extended state observer.
Background
Pose control is one of core technologies in the field of intelligent driving, and the pose control effect directly influences the running accuracy, safety, comfort and the like of an intelligent vehicle. The pose control is that the steering wheel of the intelligent vehicle is controlled according to the information provided by the target path so that the vehicle reaches the target position and the heading. Scholars at home and abroad make a great deal of research on the technology, and currently, typical control methods comprise: PID algorithm, pure tracking algorithm, LQR algorithm, model prediction algorithm, neural network algorithm and the like. The typical PID algorithm has the characteristics of simplicity and high efficiency, but the parameter setting is not easy; the pure tracking algorithm uses a geometric model to realize vehicle control, but the precision is not high; the LQR algorithm and the model prediction algorithm are designed by depending on a vehicle model, and the dependence of the control effect on the model modeling precision is high; the neural network algorithm is taken as a hot spot technology in recent years, and development of the neural network algorithm is restricted by problems of black box characteristics, large calculation amount and the like. At present, the minimum distance error is mostly taken as a final evaluation target in the research, other aspects are considered a little, in addition, the intelligent vehicle faces changeable and complex external environments, and the adaptive capacity of the controller to the changeable environments, interference and the like is also an important problem which needs to be solved urgently at present.
Disclosure of Invention
The invention aims to provide a self-tendency and self-optimization attitude control system of an unmanned vehicle based on feedback and model feedforward cascade of an extended state observer, aiming at the technical defects in the prior art.
The technical scheme adopted for realizing the purpose of the invention is as follows:
a feedback and model feedforward cascade unmanned vehicle self-optimization-seeking posture control system comprises a signal processing module, a feedback control module, a feedforward control module, an extended state observer, a model parameter learning module, a boundary constraint module, an evaluation algorithm module and a parameter self-optimization-seeking module;
the signal processing module pre-aims for the state of the vehicle t1 second later according to the position, the course angle and the speed information of the vehicle, and calculates the lateral error and the course error of a track point closest to a target by using the pre-aiming state and the planned target track information;
the feedback control module maps the lateral error and the course error of the vehicle to the course change rate of the vehicle through the error dynamic model and outputs the expected course change rate;
the feedforward control module solves an expected target wheel corner in an algebraic solving mode according to the relationship between the wheel corner and the vehicle course change rate described by the vehicle dynamic model and the expected course change rate output by the feedback control module, and then solves a target steering wheel corner corresponding to the expected target wheel corner according to a mathematical model of the vehicle steering mechanism;
the extended state observer receives vehicle state information measured by a vehicle sensor, three extended state observers are respectively designed based on a dynamic model of a lateral error, a dynamic model of a lateral error change rate and a dynamic model of a steering wheel turning angle and a heading direction so as to observe an unmodeled part and output the unmodeled part as total disturbance, and models used in the feedback control module and the feedforward control module are respectively compensated through the total disturbance;
the boundary constraint module roughly calculates the range of the course change rate of the vehicle according to the basic physical characteristics of the vehicle and the friction dynamic model of the vehicle tyre, so as to carry out boundary constraint on the expected course change rate output by the feedback control module;
the model parameter learning module performs parameter learning on the model used in the feedforward control module through minimizing an error criterion function between the model and object measurement data according to vehicle state data measured by a vehicle sensor, so that the precision of the model is improved, and the pressure of the extended state observer is reduced;
the evaluation algorithm module is used for designing evaluation indexes, distributing each index weight coefficient according to different scenes, different user requirements and the like, designing a Cost function and providing a target for self-optimization of parameters;
the parameter self-optimization-seeking module adjusts two control parameters (online or offline) in the feedback control module according to a Cost function by utilizing the acquired sensor data, so that the control effect is optimized.
In the technical scheme, in the signal processing module, the position, the course and the speed information of the vehicle are measured by a vehicle sensor;
t 1 the vehicle state after the second is:
Figure BDA0003756483950000021
Figure BDA0003756483950000022
wherein X and Y are the position coordinates of the vehicle at the current moment, X pre ，Y pre Is t 1 The coordinates of the predicted vehicle position after the moment, V is the vehicle speed at the current moment,
Figure BDA0003756483950000023
the current time is the course angle of the vehicle;
course error
Figure BDA0003756483950000024
In the technical scheme, the feedback control module utilizes the lateral error and the heading error provided by the signal processing module and designs the feedback control rate according to the heading error described by the vehicle motion error dynamic equation and the relation between the lateral error and the vehicle heading change rate to obtain the expected vehicle heading change rate.
In the above technical solution, the feedback control rate:
Figure BDA0003756483950000025
wherein k is 1 、k 2 For controller gain, f 1 And f 2 Is a disturbance;
expected rate of change of course
Figure BDA0003756483950000026
Comprises the following steps:
Figure BDA0003756483950000027
Figure BDA0003756483950000028
is the target heading rate of change.
In the above technical solution, in the feedforward control module, the vehicle dynamic model is a kinematic model or a dynamic model.
In the above technical solution, the vehicle dynamic model:
Figure BDA0003756483950000031
θ steer ＝K*δ
order to
Figure BDA0003756483950000032
The target steering wheel angle can be solved:
Figure BDA0003756483950000033
wherein L is the wheelbase, f 3 Is a perturbation.
In the above technical solution, the dynamic model of the lateral error is
Figure BDA0003756483950000034
The dynamic model of the rate of change of lateral error is
Figure BDA0003756483950000035
The dynamic model of the steering wheel angle and course is
Figure BDA0003756483950000036
Respectively designing an extended state observer aiming at the three dynamic models, and observing and outputting disturbance f on the unmodeled part 1 、f 2 、f 3 。
In the above technical solution, in the boundary constraint module, the basic physical characteristics of the vehicle include, but are not limited to, a minimum turning radius of the vehicle at different vehicle speeds.
In the above technical solution, in the model parameter learning module, a least square method or a gradient descent method is used to perform parameter learning on a model.
In the above technical solution, in the parameter self-optimization approaching module, a gradient descent method or a particle swarm optimization method is used to adjust two parameters k in the feedback control module 1 、k 2 。
Compared with the prior art, the invention has the beneficial effects that:
the system takes feedback-feedforward as a basic framework of control, improves the response speed while ensuring the control precision based on the fact that the feedback and feedforward control of a model are connected in series and are in synergistic effect with three extended state observers, reduces the degree of dependence on the precision of a vehicle model by combining the advantages of the extended state observers, meets different user requirements by designing an evaluation module and a self-optimization-seeking method, and improves the control effect of a controller in a complex environment. The concrete three points are as follows:
1. the system utilizes the three extended state observers to compensate the dynamic model in real time, reduces the dependence on the modeling accuracy degree, and improves the control accuracy and the response speed.
2. According to the method, an evaluation module is designed, the minimum distance error is no longer the only target of control, so that the control requirements are diversified, and the requirements of different users on the control quality are met.
3. According to the method, the self-optimization algorithm is used for learning the parameters of the controller according to the requirements and the environmental changes, so that the shaking of the steering wheel of the vehicle near the target value is reduced, and the robustness of the controller under the changeable situation is improved.
Drawings
FIG. 1 is a schematic structural diagram of a control system of the method.
FIG. 2 is a diagram illustrating several evaluation indexes.
Detailed Description
The present invention will be described in further detail with reference to specific examples. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Example 1
As shown in fig. 1, a self-optimization-seeking unmanned vehicle pose control method based on a feedback and model feedforward cascade of an extended state observer includes a signal processing module, a feedback control module, a feedforward control module, the extended state observer, a model parameter learning module, a boundary constraint module, an evaluation algorithm module and a parameter self-optimization-seeking module.
In the signal processing module, the target t is predicted according to the information such as the position, the course, the speed and the like measured by the vehicle sensor 1 The state of the vehicle after the second, using the previewSelecting the point with the closest distance from the state and the planned target track as the target point (the target course at the target point)
Figure BDA00037564839500000415
Given by the planning layer, which is a known quantity not discussed here), and then the lateral error is derived from the distance of the point to the line. Wherein t is 1 The vehicle state after the second can be expressed as:
Figure BDA0003756483950000041
Figure BDA0003756483950000042
wherein X and Y are the position coordinates of the vehicle at the current time, X pre ，Y pre Is t 1 The coordinates of the predicted vehicle position after the moment, V is the vehicle speed at the current moment,
Figure BDA0003756483950000043
the current time is the heading angle of the vehicle.
Course error
Figure BDA0003756483950000044
In the feedback control module, the lateral error and the course error of the vehicle are mapped to the course change rate of the vehicle through the expressions (3) to (5), namely the lateral error and the course error are used as input, and the feedback control rate u is designed according to the course error of the vehicle described by the expressions (3) to (5) and the relation between the lateral error and the course change rate to obtain the expected course change rate
Figure BDA0003756483950000045
The specific formula is as follows:
Figure BDA0003756483950000046
in the formula e d In order to be a lateral error,
Figure BDA0003756483950000047
is e d V is the vehicle speed measured at the present moment,
Figure BDA0003756483950000048
the vehicle heading angle measured for the current time,
Figure BDA0003756483950000049
is the target heading. Make course error
Figure BDA00037564839500000410
During operation of the vehicle
Figure BDA00037564839500000411
In smaller quantities, the above equation can be approximated as:
Figure BDA00037564839500000412
f 1 the disturbance is defined as the simplification in mathematical modeling and the error between the measured value and the actual value of the sensor, and can be obtained by an extended state observer. The method temporarily does not consider the change of the vehicle speed, and the derivation is obtained by the following formula:
Figure BDA00037564839500000413
Figure BDA00037564839500000414
is e d Second derivative of f 2 The disturbance is defined as the simplification in mathematical modeling and the error between the measured value and the actual value of the sensor, and can be obtained by an extended state observer. The feedback control rate can be designed:
Figure BDA0003756483950000051
wherein k is 1 、k 2 The controller gain is the controller gain and the quantity to be calibrated.
Expected rate of change of course
Figure BDA0003756483950000052
Can be expressed as:
Figure BDA0003756483950000053
in the formula
Figure BDA0003756483950000054
For a target rate of change of heading, a known quantity is given by the planning layer and is not discussed in this patent.
In the feedforward control module, the relation between the wheel rotation angle and the heading change rate described by a vehicle dynamic model (a kinematic model or a dynamic model) and the expected heading change rate output by the feedback control module
Figure BDA0003756483950000055
The expected target wheel rotation angle delta is solved through an algebraic solving mode, and the target steering wheel rotation angle theta corresponding to the expected target wheel rotation angle is solved according to the relation between the vehicle steering mechanisms steer As shown in formula (10).
A kinematic-based vehicle dynamics model is introduced below:
Figure BDA0003756483950000056
θ steer ＝K*δ (9)
order to
Figure BDA0003756483950000057
Therefore, the target steering wheel angle can be obtained by equations (7) to (9):
Figure BDA0003756483950000058
wherein L is the wheelbase, f 3 The disturbance is defined as the simplification in mathematical modeling and the error between the measured value and the actual value of the sensor, and can be obtained by an extended state observer. And K is a proportionality coefficient needing to be calibrated.
In the extended state observer, the module receives vehicle state information measured by vehicle sensors, a dynamic model based on lateral errors
Figure BDA0003756483950000059
Dynamic model of lateral error rate of change
Figure BDA00037564839500000510
Dynamic model of steering wheel angle and course
Figure BDA00037564839500000511
(example), respectively designing an extended state observer (three in total) to observe unmodeled parts and outputting the parts as disturbance f 1 、f 2 、f 3 Compensating the models used in the feedback control and the feedforward control by disturbance
The boundary constraint module roughly calculates the range of the vehicle course change according to the basic physical characteristics of the vehicle (including but not limited to the minimum turning radius of the vehicle at different speeds) and a vehicle tire friction dynamic model, so as to carry out boundary constraint on the output of the feedback control module;
in a model parameter learning module, a model used in feedforward is subjected to parameter learning, such as a proportionality coefficient K, by minimizing an error criterion function between the model and object measurement data by using a least square method, a gradient descent method and the like through vehicle state data measured by a vehicle sensor, so that the precision of the model is improved, and the pressure of an extended state observer is reduced;
the evaluation algorithm module is used for designing evaluation indexes (as shown in figure 2, but not limited to figure 2), distributing each index weight coefficient according to different scenes, different user requirements and the like, designing a Cost function and providing a target for self-optimization of parameters; the explanation is made for FIG. 2 by way of example: the control quality is evaluated from the accuracy, comfort and safety of vehicle control, wherein the accuracy comprises the maximum lateral deviation and the maximum heading deviation of the vehicle running track and a target track; the comfort comprises the adjustment amplitude of a steering wheel (and the change rate of a direction deflection angle) and the change rate of the vehicle course in the running process of the vehicle; safety includes the number of times a safety zone is exceeded while the vehicle is in operation.
The parameter self-optimization-seeking module utilizes the acquired sensor data to adjust two parameters k in the feedback controller according to the Cost function by using a gradient descent method, a particle swarm algorithm and the like 1 、k 2 (online or offline) to optimize the control effect.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.

Claims (10)

1. A feedback and model feedforward cascade unmanned vehicle self-optimization-seeking posture control system is characterized by comprising a signal processing module, a feedback control module, a feedforward control module, an extended state observer, a model parameter learning module, a boundary constraint module, an evaluation algorithm module and a parameter self-optimization-seeking module;
the signal processing module pre-aims for the state of the vehicle t1 second later according to the position, the course angle and the speed information of the vehicle, and calculates the lateral error and the course error of a track point closest to a target by using the pre-aiming state and the planned target track information;
the feedback control module maps the lateral error and the course error of the vehicle to the course change rate of the vehicle through the error dynamic model and outputs the expected course change rate;
the feedforward control module solves an expected target wheel corner through an algebraic solving mode according to the relation between the wheel corner and the vehicle course change rate described by the vehicle dynamic model and the expected course change rate output by the feedback control module, and then solves a target steering wheel corner corresponding to the expected target wheel corner according to a mathematical model of the vehicle steering mechanism;
the extended state observer receives vehicle state information measured by a vehicle sensor, three extended state observers are respectively designed based on a dynamic model of a lateral error, a dynamic model of a lateral error change rate and a dynamic model of a steering wheel turning angle and a heading direction so as to observe an unmodeled part and output the unmodeled part as total disturbance, and models used in the feedback control module and the feedforward control module are respectively compensated through the total disturbance;
the boundary constraint module roughly calculates the range of the course change rate of the vehicle according to the basic physical characteristics of the vehicle and a friction dynamic model of a vehicle tire, so as to carry out boundary constraint on the expected course change rate output by the feedback control module;
the model parameter learning module performs parameter learning on the model used in the feedforward control module through minimizing an error criterion function between the model and object measurement data according to vehicle state data measured by a vehicle sensor, so that the precision of the model is improved, and the pressure of the extended state observer is reduced;
the evaluation algorithm module is used for designing evaluation indexes, distributing each index weight coefficient according to different scenes, different user requirements and the like, designing a Cost function and providing a target for self-optimization of parameters;
the parameter self-optimization module utilizes the acquired sensor data to adjust two control parameters (online or offline) in the feedback control module according to a Cost function, so that the control effect is optimized.
2. The self-preferential pose control system according to claim 1, wherein in the signal processing module, the position, the heading and the speed information of the vehicle are measured by a vehicle sensor;
t 1 the vehicle state after the second is:
Figure FDA0003756483940000011
Figure FDA0003756483940000012
wherein X and Y are the position coordinates of the vehicle at the current moment, X pre ，Y pre Is t 1 The coordinates of the predicted vehicle position after the moment, V is the vehicle speed at the current moment,
Figure FDA0003756483940000021
the course angle of the vehicle at the current moment;
course error
Figure FDA0003756483940000022
3. The self-preferential attitude-seeking control system for the unmanned vehicle as claimed in claim 1, wherein the feedback control module utilizes the lateral error and the heading error provided by the signal processing module, and designs the feedback control rate according to the heading error described by the vehicle motion error dynamic equation and the relationship between the lateral error and the vehicle heading change rate to obtain the expected vehicle heading change rate.
4. The self-preferential heading attitude control system according to claim 3, wherein the lateral error and the heading error of the vehicle are mapped to the heading change rate of the vehicle through an error dynamic model, thereby establishing the relationship between the heading error and the heading change rate and designing the feedback control rate as the feedback control rate
Figure FDA0003756483940000023
Wherein k is 1 、k 2 For controller gain, f 1 And f 2 Is a disturbance;
expected rate of change of heading
Figure FDA0003756483940000024
Comprises the following steps:
Figure FDA0003756483940000025
Figure FDA0003756483940000026
is the target course rate of change.
5. The self-preferential attitude heading control system according to claim 1, wherein the dynamic model of the vehicle in the feedforward control module is a kinematic model or a dynamic model, a model of the steering wheel angle and the heading rate is established according to the kinematic or dynamic characteristics of the vehicle, and the feedback control module obtains the expected heading rate and uses the expected heading rate as a known quantity algebra to solve the target steering wheel angle.
6. The unmanned vehicle self-tendency attitude control system according to claim 5, wherein the vehicle dynamic model:
Figure FDA0003756483940000027
θ steer ＝K*δ
order to
Figure FDA0003756483940000028
The target steering wheel angle can be solved:
Figure FDA0003756483940000029
wherein L is the wheelbase, f 3 Is a perturbation.
7. The self-preferential heading control system for unmanned vehicles according to claim 1, wherein the self-preferential heading control system is based on lateral error and headingEstimating total disturbance of the lateral error change rate in real time; estimating the total disturbance of the lateral error change rate derivative in real time according to the lateral error and the course error change rate; estimating total disturbance of course change rate in real time according to steering wheel rotation angle and course, wherein the dynamic model of lateral error is
Figure FDA00037564839400000210
The dynamic model of the rate of change of lateral error is
Figure FDA00037564839400000211
The dynamic model of the steering wheel angle and course is
Figure FDA00037564839400000212
Respectively designing an extended state observer aiming at the three dynamic models, and observing and outputting disturbance f on the unmodeled part 1 、f 2 、f 3 。
8. The unmanned vehicle self-preferential heading position control system according to claim 1, wherein the feedback control input range is dynamically constrained by relating a range of heading rates to vehicle speed through an analytical modeling of vehicle fundamental characteristics, and wherein the fundamental physical characteristics of the vehicle in the boundary constraint module include, but are not limited to, a minimum turning radius of the vehicle at different vehicle speeds.
9. The self-trending pose control system of claim 1, wherein the established course change rate and some parameters in the steering wheel angle model are learned online or offline based on past data to make the mathematical model closer to the physical characteristics of the vehicle, and the model parameter learning module is used for parameter learning of the model by using a least square method or a gradient descent method.
10. The self-trending pose control system of an unmanned vehicle of claim 4, wherein the self-trending pose control system is based on a current pose of the vehicleDesigning evaluation indexes and a Cost function according to the state and the effect requirements of users so as to provide a basis for the self-optimization of the parameters of the controller, wherein in the parameter self-optimization module, two parameters k in a feedback control module are adjusted by using a gradient descent method or a particle swarm method and the like 1 、k 2 。
CN202210862219.7A 2022-07-20 2022-07-20 Feedback and model feedforward cascade unmanned vehicle self-tendency optimal position and posture control system Pending CN115167135A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210862219.7A CN115167135A (en) 2022-07-20 2022-07-20 Feedback and model feedforward cascade unmanned vehicle self-tendency optimal position and posture control system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210862219.7A CN115167135A (en) 2022-07-20 2022-07-20 Feedback and model feedforward cascade unmanned vehicle self-tendency optimal position and posture control system

Publications (1)

Publication Number Publication Date
CN115167135A true CN115167135A (en) 2022-10-11

Family

ID=83495285

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210862219.7A Pending CN115167135A (en) 2022-07-20 2022-07-20 Feedback and model feedforward cascade unmanned vehicle self-tendency optimal position and posture control system

Country Status (1)

Country Link
CN (1) CN115167135A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115600875A (en) * 2022-11-03 2023-01-13 南栖仙策（南京）科技有限公司（Cn） Environmental parameter calibration method and device, electronic equipment and storage medium

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115600875A (en) * 2022-11-03 2023-01-13 南栖仙策（南京）科技有限公司（Cn） Environmental parameter calibration method and device, electronic equipment and storage medium
CN115600875B (en) * 2022-11-03 2023-12-15 南栖仙策(南京)高新技术有限公司 Environmental parameter calibration method and device, electronic equipment and storage medium

Similar Documents

Publication Publication Date Title
CN107415939B (en) Steering stability control method for distributed driving electric automobile
Yao et al. Control strategies on path tracking for autonomous vehicle: State of the art and future challenges
Wang et al. Automatic steering control strategy for unmanned vehicles based on robust backstepping sliding mode control theory
CN108227491B (en) Intelligent vehicle track tracking control method based on sliding mode neural network
CN107831761A (en) A kind of path tracking control method of intelligent vehicle
CN111103798B (en) AGV path tracking method based on inversion sliding mode control
CN111679575B (en) Intelligent automobile trajectory tracking controller based on robust model predictive control and construction method thereof
CN113608530B (en) Parameter self-tuning LQR path tracking method with PID corner compensation
CN111538328B (en) Priority hierarchical prediction control method for obstacle avoidance trajectory planning and tracking control of autonomous driving vehicle
Kebbati et al. Lateral control for autonomous wheeled vehicles: A technical review
CN111142534B (en) Intelligent vehicle transverse and longitudinal comprehensive track tracking method and control system
CN114967676A (en) Model prediction control trajectory tracking control system and method based on reinforcement learning
CN111273544B (en) Radar pitching motion control method based on prediction RBF feedforward compensation type fuzzy PID
CN112622895B (en) Prediction control method applied to trajectory control of automatic driving
CN114942642A (en) Unmanned automobile track planning method
CN114967475A (en) Unmanned vehicle trajectory tracking and stability robust control method and system
CN113031443A (en) Vehicle transverse motion control method with active safety and self-adaptive preview
CN112606843A (en) Intelligent vehicle path tracking control method based on Lyapunov-MPC technology
CN115167135A (en) Feedback and model feedforward cascade unmanned vehicle self-tendency optimal position and posture control system
CN115817509A (en) Multi-axis distributed driving vehicle steering auxiliary track tracking method based on AMPC
Huang et al. Cascade optimization control of unmanned vehicle path tracking under harsh driving conditions
Chen et al. LSTM-Based Trajectory Tracking Control for Autonomous Vehicles
CN114896694B (en) Path tracking control method based on two-point pre-aiming
Jian et al. An Optimal Controller for Trajectory Tracking of Automated Guided Vehicle
CN117519190B (en) Novel articulated vehicle control method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination