CN211107381U - Intelligent automobile path tracking control system based on wolf algorithm - Google Patents
Intelligent automobile path tracking control system based on wolf algorithm Download PDFInfo
- Publication number
- CN211107381U CN211107381U CN201921649876.3U CN201921649876U CN211107381U CN 211107381 U CN211107381 U CN 211107381U CN 201921649876 U CN201921649876 U CN 201921649876U CN 211107381 U CN211107381 U CN 211107381U
- Authority
- CN
- China
- Prior art keywords
- path
- path tracking
- wolf
- automobile
- gwo
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 241000282461 Canis lupus Species 0.000 title claims abstract description 68
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 19
- 230000001133 acceleration Effects 0.000 claims abstract description 10
- 230000007246 mechanism Effects 0.000 claims description 3
- 238000000034 method Methods 0.000 abstract description 10
- 230000006399 behavior Effects 0.000 description 11
- 230000009471 action Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 244000062804 prey Species 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- YBJHBAHKTGYVGT-ZKWXMUAHSA-N (+)-Biotin Chemical compound N1C(=O)N[C@@H]2[C@H](CCCCC(=O)O)SC[C@@H]21 YBJHBAHKTGYVGT-ZKWXMUAHSA-N 0.000 description 1
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000036544 posture Effects 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
- FEPMHVLSLDOMQC-UHFFFAOYSA-N virginiamycin-S1 Natural products CC1OC(=O)C(C=2C=CC=CC=2)NC(=O)C2CC(=O)CCN2C(=O)C(CC=2C=CC=CC=2)N(C)C(=O)C2CCCN2C(=O)C(CC)NC(=O)C1NC(=O)C1=NC=CC=C1O FEPMHVLSLDOMQC-UHFFFAOYSA-N 0.000 description 1
Images
Landscapes
- Steering Control In Accordance With Driving Conditions (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The utility model provides an intelligent automobile path tracking control system and method based on grey wolf algorithm, this system is including the path planning system, path tracking decision-making system and the vehicle chassis actuating system that connect gradually, and wherein path tracking decision-making system includes driver predictive control ware and GWO attitude control two subsystems, predictive control ware adopt based on the vehicle lateral acceleration feedback revises preview-follow driver model, GWO attitude control ware has adopted grey wolf algorithm. The utility model discloses plan out the ideal route by the path planning system, the ideal route information is received to path tracking decision-making system, and through vehicle chassis actuating system's steer-by-wire executor, in-wheel motor brake executor adjustment car travel state, the realization is to the accurate tracking of ideal route to improve the stability of traveling of car.
Description
Technical Field
The utility model relates to an intelligent automobile path tracking technical field specifically is an intelligent automobile path tracking control system based on grey wolf algorithm.
Background
With the progress of the times and the development of technology, the progress of automobile four-transformation (electromotion, intellectualization, networking and sharing) is gradually accelerated, automobiles with L1 (driving support) and L2 (partial automation) level automatic driving functions are continuously on the market, in the process of realizing automatic driving, man-machine driving together is a very important development stage, in the whole driving process, human factors of drivers account for a great proportion, and traffic accidents are easily caused once the drivers drive for a long time, fatigue and misjudge, the common path tracking control method only focuses on the track control of the automobiles and ignores the influence of the operation behaviors of the drivers on the driving conditions of the automobiles, and the common path tracking control method only takes the mass center lateral displacement of the automobiles as a control object and does not consider the influence of the driving postures of the automobile heading angles and the like on the path tracking precision.
SUMMERY OF THE UTILITY MODEL
The utility model discloses a solve prior art's problem, the utility model provides an intelligent automobile path tracking control system based on grey wolf algorithm, plan out the ideal route by the route planning system, path tracking decision-making system receives ideal route information, respectively by driver predictive control ware, GWO attitude control ware trails the lateral position and the course angle in ideal route, output steering wheel corner and wheel braking moment, through vehicle chassis actuating system's steer-by-wire executor, in-wheel motor brake executor adjustment car travel state, the realization is to the accurate tracking in ideal route, and improve the stability of traveling of car.
The utility model provides an intelligent automobile path tracking control system based on grey wolf algorithm, including path planning system, path tracking decision-making system and the vehicle chassis actuating system who connects gradually.
The path planning system is a path planning program built in an automobile driving computer, can sense a road and an obstacle ahead according to an automobile sensor system, and plans an optimal driving path at a future moment. Currently, a path planning system is researched and applied in the field of intelligent driving, and is not described herein again.
The path tracking decision system comprises a driver prediction controller and an GWO (Grey wolf algorithm) attitude controller, wherein the prediction controller adopts a pre-aiming-following driver model corrected based on vehicle lateral acceleration feedback and is used for describing and predicting the operation behavior of a driver, the error between the lateral position of the mass center of the automobile and the lateral position of an ideal path is taken as a control target, the driver firstly pre-aims at the road ahead, and then adjusts the steering wheel angle according to the information of the ideal path and the current driving state (such as position, speed, acceleration and the like) of the vehicle to carry out active steering control, so that the vehicle can follow the ideal path with the minimum lateral position error. GWO attitude controller adopts Grey wolf algorithm to assist driver to track path, and takes the error between the car yaw angle and ideal path slope as control target, the input of the controller is the slope of ideal path, the car yaw speed, and the output is the braking moment of wheels, and carries out differential braking control.
The system is further improved, the automobile chassis execution system comprises a steer-by-wire actuator and a hub motor brake actuator, the steer-by-wire actuator receives the steering wheel angle output by the driver prediction controller, and the steering wheel angle directly acts on a steering mechanism to control the rotation of wheels; the wheel hub motor brake actuator receives the wheel brake torque output by the GWO attitude controller, controls the corresponding wheel brake, generates an additional yaw moment and adjusts the yaw velocity of the automobile.
The utility model also provides an intelligent automobile path tracking control method based on grey wolf algorithm, including following step:
step 1: the path planning system plans an ideal path at a future moment according to the road and obstacle signals identified by the sensor system and transmits ideal path parameters to the path tracking decision system;
step 2: the path tracking decision-making system receives ideal path parameters and automobile driving state parameters, calculates the deviation between the current lateral position of the automobile and the lateral position of the ideal path, and the deviation between the current yaw angle of the automobile and the slope angle of the ideal path, respectively inputs the deviation into a driver prediction controller and an GWO attitude controller, outputs a steering wheel corner after calculation to act on a steer-by-wire actuator, and outputs a wheel braking torque to act on a hub motor braking actuator;
and step 3: and a steer-by-wire actuator and a hub motor brake actuator in the automobile chassis execution system respectively receive the steering wheel angle and the wheel brake torque output by the path tracking decision system, and control the automobile to run according to an ideal path, so that a control target of path tracking is realized.
Further improved, the GWO attitude controller in step 2) adopts a gray wolf algorithm, specifically: the method comprises the steps of representing an optimized object, namely additional braking torque of four wheels of an automobile by using the position X of a single wolf, representing an error between an optimized target, namely an automobile yaw angle and an ideal path course angle by using the prey odor concentration Y, representing the increasing or decreasing amount of the optimized object in different optimization stages respectively by using a walking Step length, a rushing Step length and an attack Step length, and finally, outputting the position of a wolf head, namely the optimal solution of the optimized object.
The utility model has the advantages that:
1) the influence of the operation behavior of the driver on the current and future vehicle motion states is comprehensively considered, and the accuracy of path tracking and the stability of the vehicle are improved by combining the lateral position error of the driver model and the yaw velocity of the GWO attitude controller;
2) the gray wolf algorithm has better robustness and global convergence performance for complex functions with different characteristics, and further improves the precision and the efficiency of a control system.
Drawings
Fig. 1 is a schematic view of a control system of the present invention;
FIG. 2 is a flow chart of the driver predictive controller theory according to the present invention;
fig. 3 is a flowchart of the gray wolf algorithm of the present invention.
Detailed Description
The present invention will be further explained with reference to the accompanying drawings.
The utility model provides an intelligent automobile path tracking control system based on grey wolf algorithm, this system is as shown in figure 1, including path planning system, path tracking decision-making system and the vehicle chassis actuating system that connects gradually.
The path planning system is a path planning program built in an automobile driving computer, can sense a road and an obstacle ahead according to an automobile sensor system, and plans an optimal driving path at a future moment. Currently, a path planning system is researched and applied in the field of intelligent driving, and is not described herein again.
The path tracking decision system comprises a driver prediction controller and an GWO (Grey wolf algorithm) attitude controller, wherein the prediction controller adopts a pre-aiming-following driver model corrected based on the lateral acceleration feedback of the vehicle and is used for describing and predicting the operation behavior of the driver, the error between the lateral position of the mass center of the automobile and the lateral position of an ideal path is taken as a control target, the driver firstly pre-aims at the front road, and then the steering wheel corner is adjusted according to the information of the ideal path and the current running state (such as position, speed, acceleration and the like) of the vehicle to carry out active steering control, so that the vehicle can follow the ideal path with the minimum lateral position error. GWO attitude controller adopts Grey wolf algorithm to assist driver to track path, and takes the error between the car yaw angle and ideal path slope as control target, the input of the controller is the slope of ideal path, the car yaw speed, and the output is the braking moment of wheels, and carries out differential braking control.
The automobile chassis execution system comprises a steer-by-wire actuator and a hub motor brake actuator, wherein the steer-by-wire actuator receives a steering wheel angle output by a driver prediction controller, and directly acts on a steering mechanism to control the rotation of wheels; the wheel hub motor brake actuator receives the wheel brake torque output by the GWO attitude controller, controls the corresponding wheel brake, generates an additional yaw moment and adjusts the yaw velocity of the automobile.
The working method of the utility model is as follows:
step 1: the path planning system plans an ideal path at a future moment according to the road and obstacle signals identified by the sensor system and transmits ideal path parameters to the path tracking decision system;
step 2: the path tracking decision-making system receives ideal path parameters and automobile driving state parameters, calculates the deviation between the current lateral position of the automobile and the lateral position of the ideal path, and the deviation between the current yaw angle of the automobile and the slope angle of the ideal path, respectively inputs the deviation into a driver prediction controller and an GWO attitude controller, outputs a steering wheel corner after calculation to act on a steer-by-wire actuator, and outputs a wheel braking torque to act on a hub motor braking actuator;
as shown in fig. 2, in step 2, the specific method of the driver prediction controller is as follows:
step 2.1.1: assume that the current time is t0Reading the actual side position of the automobile as Y (t)0) Longitudinal velocity vxLateral velocity vySelecting the preview time T of the driver, and the preview front v of the driverxThe path at T obtains the lateral position Y (T) of the path at the pre-aiming point0+T)；
Step 2.1.2: if the vehicle is then at the desired lateral acceleration ay *Doing the even accelerated motion of side direction, can arrive target track point after T moment, then have:
this makes it easy to obtain:
step 2.1.3: ideal lateral acceleration a of automobiley *Ideal steering wheel angle with automobileSW *The relationship between can be represented by a steady state gain GayTo express, the derivation formula of the ideal steering wheel angle can be obtained:
wherein the steady state gain GayIs related to the longitudinal velocity vxHowever, since the above driver model is built in advance of the longitudinal speed of the vehicle being at a constant speed, the control of the steering angle of the steering wheel of the vehicle is not accurate enough only based on the driver model built according to the above formula.
Step 2.1.4: on the basis, a pre-aiming driver model based on vehicle lateral acceleration feedback correction is established, and the actual lateral acceleration a of the automobile is correctedyAs feedback information for optimizing the behavior, a PID steering controller is establishedy *And ayAs input information, error value e (t) of (4) outputs correction amount △ of the ideal steering wheel:
V＝Kp*e(t)+Ki*∫e(t)dt+Kd*de(t)/dt
based on the above calculation, the final steering wheel angle is output:
as shown in fig. 3, in step 2, the specific method of the GWO attitude controller is as follows:
step 2.2.1: numerical initialization
a) Initializing a wolf cluster number N and location information X of each wolfi(Fx1,Fx2,Fx3,Fx4) I ═ 1, N), the position information is a four-dimensional coordinate, Fx1,Fx2,Fx3,Fx4Respectively representing the braking torque of a left front wheel, a right front wheel, a left rear wheel and a right rear wheel of the automobile;
b) setting the odor concentration Y of prey corresponding to each wolfiI.e. the slope angle theta of the ideal path and the yaw velocity w of the vehiclerThe formed objective function is as follows:
Yi＝|∫wrdt-θ|
wherein:
Fy1,Fy2,Fy3,Fy4the lateral forces of the left front wheel, the right front wheel, the left rear wheel and the right rear wheel of the automobile, twFor the track of the vehicle, IzYawing the rotational inertia for the automobile; lf，lrThe distances from the centroid position to the front and rear axes, respectively.
c) Setting the maximum iteration number k according to the control precision and the solving speed requirementmaxMaximum number of migrations TmaxA sounding scale factor α, a distance decision factor ω, a step factor S, and an update scale factor σ;
d) selecting the artificial wolf with the highest concentration of the current prey as the wolf head, and taking the position as XleadPrey odor concentration of Ylead；
Step 2.2.2: wandering behavior
a) Arranging the scent concentrations of the preys of the N wolfs from big to small, taking the corresponding artificial wolfs with higher scent concentrations of the N + α preys except the wolf as the exploring wolfs, and taking all the artificial wolfs except the wolf and the exploring wolfs as the fierce wolfs;
b) for the exploratory wolf j, the prey odor concentration is Yj 0At this time Yj 0＜YleadJ ═ 1, N × α, which performs a walking action, advancing in each of the h directions by one walking stepaWhen the sensed smell concentration of the prey returns to the original position after each step of advancing, the position of the spy wolf j after advancing to the p-th direction (p is 1,2,3 … h) is recorded as Xj pPrey odor concentration of Yj p；
c) Selection of Yj pPrey odor concentration Y at maximum and greater than current locationj 0Is advanced by a step of walk stepaUpdating the position information X of the sounding wolf jj；
d) Repeating the above wandering behaviors until a certain wolf detecting sensesPrey odor concentration Yj＞YleadAt this time, the detecting wolf becomes head wolf, Ylead＝YjOr the number of wandering times T reaches the maximum number of wandering times TmaxKeeping the original wolf unchanged;
step 2.2.3: summoning/rushing behavior
a) The head wolf calls the calling behavior through howling, N (1- α) -1 head wolf around the head wolf is called to get close to the position of the head wolf rapidly, and the head wolf steps with the rushing step lengthb＝2*stepaRapidly approaching the position of the wolf head;
b) in the journey, the prey smell concentration Y is sensed by the wolf z (z ═ 1, N ═ 1- α) -1)z＞YleadThen the wolf of terry turns into wolf of head and initiates a call-out action, at which time Ylead＝Yz；
c) In the rushing course, the prey odor concentration Y sensed by the wolf of terry zz＜YleadThe wolf of terry z continues to rush until the distance d between itself and the wolf of head szsIs less than dnearAdding the attack to the hunting course, namely turning into the attack behavior;
step 2.2.4: attack behavior
a) Regarding the position of the wolf closest to the prey, i.e. the wolf head, as the moving position of the prey, the wolf head jointly probes the wolf to attack the step lengthcClose proximity to a prey in hopes of capturing it;
b) if the prey odor concentration sensed by a certain artificial wolf is greater than the prey odor concentration sensed by the home position state after the attack action is implemented, updating the position of the artificial wolf, otherwise, keeping the position of the artificial wolf unchanged;
c) if the position of the artificial wolf is updated, the concentration of the smell of the prey perceived by a certain artificial wolf is greater than that of the smell of the prey perceived by the wolf, the artificial wolf is converted into the wolf, the position of the artificial wolf is regarded as the position of the prey, and other artificial wolfs continue to attack by taking the wolf as the center;
d) after updating the position of the wolf head, judging whether the optimum precision or the maximum iteration number k is reachedmaxIf yes, outputting the position of the wolf head, namely the optimal solution, otherwise, turning to the step2.2.2。
And step 3: and a steer-by-wire actuator and a hub motor brake actuator in the automobile chassis execution system respectively receive the steering wheel angle and the wheel brake torque output by the path tracking decision system, and control the automobile to run according to an ideal path, so that a control target of path tracking is realized.
The utility model discloses the concrete application way is many, and the above-mentioned only is the preferred embodiment of the utility model, should point out, to ordinary skilled person in this technical field, under the prerequisite that does not deviate from the utility model discloses the principle, can also make a plurality of improvements, and these improvements also should be regarded as the utility model discloses a scope of protection.
Claims (2)
1. The utility model provides an intelligent automobile path tracking control system based on wolf algorithm which characterized in that: the system comprises a path planning system, a path tracking decision-making system and an automobile chassis execution system which are sequentially connected, wherein the path tracking decision-making system comprises a driver prediction controller and an GWO attitude controller, the prediction controller adopts a preview-follow driver model based on vehicle lateral acceleration feedback correction, and the GWO attitude controller adopts a wolf algorithm.
2. The intelligent car path tracking control system based on the wolf algorithm of claim 1, wherein: the automobile chassis execution system comprises a steer-by-wire actuator and a hub motor brake actuator, wherein the steer-by-wire actuator receives a steering wheel angle output by a driver prediction controller, and directly acts on a steering mechanism to control the rotation of wheels; the wheel hub motor brake actuator receives the wheel brake torque output by the GWO attitude controller, controls the corresponding wheel brake, generates an additional yaw moment and adjusts the yaw velocity of the automobile.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201921649876.3U CN211107381U (en) | 2019-09-30 | 2019-09-30 | Intelligent automobile path tracking control system based on wolf algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201921649876.3U CN211107381U (en) | 2019-09-30 | 2019-09-30 | Intelligent automobile path tracking control system based on wolf algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN211107381U true CN211107381U (en) | 2020-07-28 |
Family
ID=71722097
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201921649876.3U Active CN211107381U (en) | 2019-09-30 | 2019-09-30 | Intelligent automobile path tracking control system based on wolf algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN211107381U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110626340B (en) * | 2019-09-30 | 2023-07-11 | 南京航空航天大学 | Intelligent automobile path tracking control system and method based on wolf algorithm |
-
2019
- 2019-09-30 CN CN201921649876.3U patent/CN211107381U/en active Active
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110626340B (en) * | 2019-09-30 | 2023-07-11 | 南京航空航天大学 | Intelligent automobile path tracking control system and method based on wolf algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110626340B (en) | Intelligent automobile path tracking control system and method based on wolf algorithm | |
| CN110377039B (en) | Vehicle obstacle avoidance track planning and tracking control method | |
| CN110471408B (en) | Unmanned vehicle path planning method based on decision process | |
| WO2020143288A1 (en) | Autonomous vehicle decision-making system under complex operating conditions, and trajectory planning method therefor | |
| CN110703754B (en) | Path and speed highly-coupled trajectory planning method for automatic driving vehicle | |
| Altché et al. | High-speed trajectory planning for autonomous vehicles using a simple dynamic model | |
| CN108791290B (en) | Double-vehicle cooperative adaptive cruise control method based on online incremental DHP | |
| US11414127B2 (en) | Trajectory tracking with four-wheel steering | |
| JP6972793B2 (en) | Driving control method and driving control device for driving support vehicles | |
| US11518412B2 (en) | Trajectory determination for four-wheel steering | |
| JP2009018623A (en) | Travel controller | |
| US11345400B2 (en) | Trajectory tracking with four-wheel steering and steering limits | |
| JP2020168955A (en) | Vehicle control device | |
| JP2019151183A (en) | Vehicle travel control device | |
| WO2019167511A1 (en) | Mobile body control device and mobile body control method | |
| CN114228690A (en) | Automatic driving vehicle roll control method based on DDPG and iterative control | |
| CN211107381U (en) | Intelligent automobile path tracking control system based on wolf algorithm | |
| US20220063614A1 (en) | Driving control method and system of vehicle | |
| CN114852085A (en) | Automatic vehicle driving track planning method based on road right invasion degree | |
| CN116080754B (en) | Transverse control method for autonomous driving of vehicle | |
| CN115525054B (en) | Method and system for controlling tracking of edge path of unmanned sweeper in large industrial park | |
| CN115447615A (en) | Trajectory optimization method based on vehicle kinematics model predictive control | |
| WO2022172337A1 (en) | Control calculation device and control calculation method | |
| CN112706770B (en) | Vehicle entry control system and method considering steer-by-wire delay | |
| CN114489038B (en) | Navigation control method of agriculture and forestry vehicle based on reinforcement learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |