CN112346461A - Automatic guided vehicle collective filtering method considering unknown noise bounded characteristic - Google Patents
Automatic guided vehicle collective filtering method considering unknown noise bounded characteristic Download PDFInfo
- Publication number
- CN112346461A CN112346461A CN202011225275.7A CN202011225275A CN112346461A CN 112346461 A CN112346461 A CN 112346461A CN 202011225275 A CN202011225275 A CN 202011225275A CN 112346461 A CN112346461 A CN 112346461A
- Authority
- CN
- China
- Prior art keywords
- noise
- agv
- state
- ellipse
- filtering method
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000001914 filtration Methods 0.000 title claims abstract description 41
- 230000008569 process Effects 0.000 claims abstract description 17
- 238000005070 sampling Methods 0.000 claims abstract description 5
- 238000005259 measurement Methods 0.000 claims description 9
- 238000006073 displacement reaction Methods 0.000 claims description 6
- 238000013461 design Methods 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 239000000126 substance Substances 0.000 claims description 2
- 230000007547 defect Effects 0.000 abstract description 3
- 238000012827 research and development Methods 0.000 abstract description 3
- 238000009795 derivation Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000003860 storage 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
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
-
- 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
- G05D1/12—Target-seeking control
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Theoretical Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- Feedback Control In General (AREA)
Abstract
The invention provides an automated guided vehicle ensemble filtering method considering unknown bounded characteristics of noise, which comprises the following steps: establishing an AGV kinematics model and a dynamics model according to information collected by a sensor; determining an iterative formula of the ensemble membership filter and deducing necessary conditions for ensuring that the actual state is contained in the predicted state ellipse; an optimal state prediction ellipse is determined that contains true state values at time k +1, where k represents the sampling time. The automatic guided vehicle collective filtering method considering the unknown bounded characteristic of the noise, provided by the invention, considers the unknown bounded characteristic of the noise, overcomes the defects of the traditional filtering method in the aspects of precision, cost, application range and the like, improves the control precision of AGV trajectory tracking, and ensures the working efficiency and safety of the AGV. The precision requirement on the sensor is reduced, and the research and development cost is reduced. By designing the ensemble filtering algorithm, the influence of unknown bounded characteristics of noise on the track tracking process is effectively eliminated, and the predicted value of the system state is obtained.
Description
Technical Field
The invention relates to the technical field of AGV filtering methods, in particular to an automatic guided vehicle collective filtering method considering unknown bounded characteristics of noise.
Background
Automated guided vehicle, AGV for short, refers to an unmanned vehicle equipped with an automated navigation device and capable of traveling along a desired path. AGVs are commonly used in the industry for the transport of goods, and their presence greatly reduces labor costs and increases production efficiency. In addition, the AGV operates by a self-contained storage battery, has excellent characteristics such as no pollution and no noise, and is a hot topic of scientific research.
One core of AGV control and application is trajectory tracking technology. The safety and effectiveness of the work can be guaranteed only when the AGV can work along the predetermined trajectory with high accuracy. Most current research on trajectory tracking does not take into account the problem of the unknown bounded nature of noise. The trajectory tracking control accuracy can be improved more effectively if the influence of the unknown bounded characteristic of the noise on the AGV control process can be eliminated. Therefore, designing a proper and high-precision filter is one of the key problems for solving the AGV trajectory tracking. Currently, the existing research on filtering methods for solving the problem of unknown bounded characteristics of noise has some drawbacks. The precision of traditional least square filtering is low excessively, can't satisfy AGV trail tracking's precision demand. The kalman filtering method is a filtering algorithm with the advantages of real-time performance, high efficiency, convenience, high precision and the like, but the application of the kalman filtering method is limited under the condition that uncertainty exists in a system model and noise statistical characteristics. When the system noise is white gaussian noise with known statistical characteristics, the kalman filter has a good filtering effect, and when the statistical characteristics of the noise are unknown, the result of the kalman filtering cannot reach the corresponding standard. Most of noises suffered by the AGV during operation are unknown bounded noises, so that the traditional Kalman filtering method cannot effectively solve the problem of trajectory tracking of the AGV.
Disclosure of Invention
The invention aims to provide an automatic guided vehicle collective filtering method considering the unknown bounded characteristic of noise, so as to solve the problem that the traditional filtering technology has high sensor precision requirement, high delay, high cost and narrow application range, so that the adverse effect of the unknown bounded noise on the AGV track tracking process cannot be well eliminated.
In order to solve the technical problems, the technical scheme of the invention is as follows: an automated guided vehicle ensemble filtering method is provided that takes into account noise-unknown bounded characteristics, comprising: establishing an AGV kinematics model and a dynamics model according to a dynamics theory and the structural characteristics of the AGV; determining an iterative formula of the ensemble membership filter and deducing necessary conditions for ensuring that the actual state is contained in the predicted state ellipse; an optimal state prediction ellipse is determined that contains true state values at time k +1, where k represents the sampling time.
Further, the AGV kinematic equation is:
where x denotes a horizontal direction displacement of the AGV, y denotes a displacement in a vertical direction of the AGV, v is a velocity of the AGV, ψ denotes a yaw angle, s denotes a sideslip angle, and γ denotes a yaw rate. Considering that the actual working route is mostly a small curvature route, cos (ψ + s) ≈ 1 and sin (ψ + s) ≈ ψ + s are satisfied.
Further, after discretization, the AGV dynamics model equation is as follows:
wherein the content of the first and second substances,for process noise and measurement noise corresponding to each state variable and output variable, the control variable u is set to [ v, δ]Delta is the deflection angle of the front wheel of the AGV and the output variableIs set as [ x, y]。
Further, designing the collector filter: assume that at time k, both process noise and measurement noise are limited to the following ellipses:
wherein The ellipse parameters, representing the known process noise and the measurement noise, respectively, the initial state values are also limited to the following ellipses:
whereinFor the parameters of the ellipse in the known initial state,the state prediction value at the zero moment;
assume system input ukFiltering with constantThe design of the device, the iterative formula of the collective filtering is:
at time k, the true state ellipsoid parameterAnd the current time state prediction valueAll known cases, from the predicted ellipsoid fieldTo obtain
Where xi is a constant with an absolute value less than or equal to 1, EkIs thatThe factorization of (a) is performed,by definitionAndcombining with AGV dynamics model equation (6), (7), state prediction ellipse at k +1 moment,is represented as:
considering the definition of ξ and the noise model (5), the predicted ellipse at the moment of determination of k +1 has the followingAnd (3) limiting:
according to S-procedure, a sufficient condition for inequalities (8) and (9) to be satisfied simultaneously is that positive scaling τ exists1,τ2,τ3Satisfy the following requirementsBy definitionThe inequality (10) can be simplified to
Finally (11) is equated according to schur compnents as:
at time k if there isAnd inequality (12) is satisfied, the state prediction ellipse ensuring that the real state value at the time k +1 is included in the current time is
Further, by solving an optimization problem:and determining the optimal state prediction ellipse containing the real state value at the moment of k + 1.
The automatic guided vehicle collective filtering method considering the unknown bounded characteristic of the noise, provided by the invention, considers the unknown bounded characteristic of the noise, overcomes the defects of the traditional filtering method in the aspects of precision, cost, application range and the like, improves the control precision of AGV trajectory tracking, and ensures the working efficiency and safety of the AGV. The precision requirement on the sensor is reduced, and the research and development cost is reduced. By designing the ensemble filtering algorithm, an effective predicted value of the system state is obtained, and the influence of unknown bounded noise on the track tracking process is eliminated.
Drawings
The invention is further described with reference to the accompanying drawings:
FIG. 1 is a flowchart illustrating steps of a automated guided vehicle ensemble filtering method considering noise-unknown bounded characteristics according to an embodiment of the present invention;
FIG. 2 is an AGV kinematics model provided by an embodiment of the present invention;
FIG. 3 is a kinetic model of an AGV according to an embodiment of the present invention.
Detailed Description
The following describes in further detail the automated guided vehicle ensemble filtering method considering the noise unknown bounded characteristic according to the present invention with reference to the accompanying drawings and specific embodiments. Advantages and features of the present invention will become apparent from the following description and from the claims. It is to be noted that the drawings are in a very simplified form and are all used in a non-precise ratio for the purpose of facilitating and distinctly aiding in the description of the embodiments of the invention.
The core idea of the invention is that the automatic guided vehicle collective member filtering method considering the unknown bounded characteristic of the noise considers the unknown bounded characteristic of the noise, overcomes the defects of the traditional filtering method in the aspects of precision, cost, application range and the like, improves the control precision of the AGV track tracking, and ensures the working efficiency and safety of the AGV. The precision requirement on the sensor is reduced, and the research and development cost is reduced. By designing the ensemble filtering algorithm, an effective predicted value of the system state is obtained, and the influence of unknown bounded noise on the track tracking process is eliminated.
The technical scheme of the invention provides an automated guided vehicle collective filtering method considering unknown bounded characteristics of noise, and fig. 1 is a flow chart of steps of the automated guided vehicle collective filtering method considering unknown bounded characteristics of noise provided by the embodiment of the invention. Referring to fig. 1, a method for automated guided vehicle ensemble filtering that accounts for the unknown bounded nature of noise includes the steps of:
s11: establishing an AGV kinematics model and a dynamics model according to a dynamics theory and the structural characteristics of the AGV;
s12: determining an iterative formula of the ensemble membership filter and deducing necessary conditions for ensuring that the actual state is contained in the predicted state ellipse;
s13: an optimal state prediction ellipse is determined that contains true state values at time k +1, where k represents the sampling time.
FIG. 2 illustrates an AGV kinematics model according to an embodiment of the present invention. Referring to fig. 2, where x denotes a horizontal direction displacement of the AGV, y denotes a displacement in a vertical direction of the AGV, v is a velocity of the AGV, ψ denotes a yaw angle, s denotes a sideslip angle, and γ denotes a yaw rate. In real world conditions, the curvature of most roads is small, so the sideslip angle of the AGV does not change significantly, and the following assumptions can be made: the kinematic model of AGV can be described as follows, combining the assumptions of cos (ψ + s) 1 and sin (ψ + s) ψ + s:
FIG. 3 is a kinetic model of an AGV according to an embodiment of the present invention. Referring to FIG. 3, the lateral dynamics equation for an AGV may be expressed as:
where m denotes the mass of the AGV, l1Indicates the distance from the center of gravity of the AGV to the front end,/2Indicating the distance, I, from the AGV center of gravity to the rear endzRepresenting the moment of inertia of the AGV, ω and μ are unknown bounded noise corresponding to the inside and outside of the system, and δ is the AGV front wheel deflection angle. Also due to the small curvature motion of the AGV, we can assume sin δ to be 0 and cos δ to be 1.FyfAnd FyrRespectively, the tire forces received by the tires of the front and rear wheels, respectively, can be expressed as: fyf=Cfαf,Fyr=CrαrCornering stiffness C of front and rear tiresf,CrCan be approximately expressed asFinally, we can complete the modeling of the dynamics of the AGV by combining equations (1) and (2):
wherein ω isx,ωy,ωψ,ωs,ωγRespectively, corresponding to the noise of the respective state variables. The state variable is set to x,y,ψ,s,γ]with the control variable u set to [ v, δ]Output variableThe linear model after discretization of equation (3) can be expressed as:
where k denotes the sampling instant, ω ═ ωx,ωy,ωψ,ωs,ωγ],μ=[μx,μy]Process noise and measurement noise corresponding to each state variable and output variable.
After modeling of the AGV is completed, the design of the collective filter is started. First assume that at time k, both process noise and measurement noise are limited to the following ellipses:
wherein Elliptic parameters representing known process noise and measurement noise, respectively. Likewise, the initial state values are also limited to the following ellipses:
whereinFor the parameters of the ellipse in the known initial state,the state prediction value at the zero moment.
The following membership filtering iterative formula is selected to calculate the parameters of the state prediction ellipse at each time instant:wherein G isk,Fk,LkAre the unknown filter parameters. Combining the discrete time model of AGV can obtain
In the embodiment of the invention, in order to simplify the derivation step and emphasize the filtering process, the action of the controller is not considered, and the input u of the system is assumedkFilter design with constant. When equation Fk=(I-LkCp)BpIn the derivation process when in placeThe method can be simplified, the whole derivation process becomes simpler, and the simplified ensemble filtering iterative formula is as follows:
after determining the iterative formulation of the filter, we need to derive the necessary conditions to ensure that the actual state is contained in the predicted state ellipse. At time k, the true state ellipsoid parameterAnd the current time state prediction valueAll known cases, from the predicted ellipsoid field
Where xi is a constant with an absolute value less than or equal to 1, EkIs thatThe factorization of (a) is performed,by definitionAndthe state prediction ellipse at the time k +1 in combination with equations (4), (6), (7)Can be expressed as:
in addition, considering the definition of ξ and the noise model (5), the predicted ellipse at the moment of determination of k +1 has the following constraints:
according to S-procedure, a sufficient condition for inequalities (8) and (9) to be satisfied simultaneously is that positive scaling τ exists1,τ2,τ3Satisfy the following requirements
Finally (11) can be equated to:
from the above derivation, it can be seen that at time k, if anyAnd inequality (12) is satisfied, it can be ensured that the real state value at the time k +1 is included in the state prediction ellipse at that time
Finally, since (12) is a parameterThe optimal ellipse can be determined using a convex optimization method. By solving the following optimization problem:
an optimal state prediction ellipse can be determined for the time k +1, containing the true state values.
It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit or scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (5)
1. An automated guided vehicle ensemble filtering method that accounts for noise unknown bounded characteristics, comprising:
establishing an AGV kinematics model and a dynamics model according to a dynamics theory and the structural characteristics of the AGV;
determining an iterative formula of the ensemble membership filter and deducing necessary conditions for ensuring that the actual state is contained in the predicted state ellipse;
an optimal state prediction ellipse is determined that contains true state values at time k +1, where k represents the sampling time.
2. The automated guided vehicle ensemble filtering method of claim 1, taking into account noise unknown bounded characteristics, wherein said AGV kinematic equation is:
where x denotes a horizontal direction displacement of the AGV, y denotes a displacement in a vertical direction of the AGV, v is a speed of the AGV, ψ denotes a yaw angle, s denotes a sideslip angle, γ denotes a yaw rate, and cos (ψ + s) ≈ 1, sin (ψ + s) ≈ ψ + s are satisfied.
3. The automated guided vehicle collective filtering method considering unknown bounded characteristics of noise according to claim 2, wherein after discretizing time, the AGV dynamical model equation is:
wherein the content of the first and second substances,ω=[ωx,ωy,ωψ,ωs,ωγ],μ=[μx,μy]for process noise and measurement noise corresponding to each state variable and output variable, the control variable u is set to [ v, δ]Delta is the deflection angle of the front wheel of the AGV and the output variableIs set as [ x, y]。
4. The automated guided vehicle ensemble filtering method of claim 3, considering unknown bounded characteristics of noise, wherein the ensemble filter is designed to: assume that at time k, both process noise and measurement noise are limited to the following ellipses:
whereinEllipses representing known process and measurement noise, respectivelyThe parameters, the initial state values, are also constrained in the following ellipses:whereinFor the parameters of the ellipse in the known initial state,the state prediction value at the zero moment;
assume system input ukThe filter design is carried out under the condition of constant, and the ensemble filtering iterative formula is as follows:
at time k, the true state ellipsoid parameterAnd the current time state prediction valueAll known cases, from the predicted ellipsoid fieldTo obtain
Where xi is a constant with an absolute value less than or equal to 1, EkIs thatThe factorization of (a) is performed,by definitionAndcombining with AGV dynamics model equation (6), (7), state prediction ellipse at k +1 moment,is represented as:
considering the definition of ξ and the noise model (5), the prediction ellipse at the moment of determination k +1 has the following constraints:
according to S-procedure, a sufficient condition for inequalities (8) and (9) to be satisfied simultaneously is that positive scaling τ exists1,τ2,τ3Satisfy the following requirements
Finally (11) is equated according to schur compnents as:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011225275.7A CN112346461A (en) | 2020-11-05 | 2020-11-05 | Automatic guided vehicle collective filtering method considering unknown noise bounded characteristic |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011225275.7A CN112346461A (en) | 2020-11-05 | 2020-11-05 | Automatic guided vehicle collective filtering method considering unknown noise bounded characteristic |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112346461A true CN112346461A (en) | 2021-02-09 |
Family
ID=74428368
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011225275.7A Pending CN112346461A (en) | 2020-11-05 | 2020-11-05 | Automatic guided vehicle collective filtering method considering unknown noise bounded characteristic |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112346461A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113050608A (en) * | 2021-03-30 | 2021-06-29 | 上海海事大学 | Automatic control system fault detection method based on collective estimation |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
FR2913800A1 (en) * | 2007-03-13 | 2008-09-19 | Thales Sa | Anti-collision alert filtering device for e.g. helicopter, has alarm manger centralizing alerts transmitted by anti-collision equipments to crew, where each alert comprises danger level code, and alert filter filtering alerts based on code |
CN107611964A (en) * | 2017-09-12 | 2018-01-19 | 重庆大学 | A kind of power system state estimation method based on extension set-membership filtering |
CN109597864A (en) * | 2018-11-13 | 2019-04-09 | 华中科技大学 | Instant positioning and map constructing method and the system of ellipsoid boundary Kalman filtering |
CN109669463A (en) * | 2019-01-10 | 2019-04-23 | 上海海事大学 | A kind of section trace tracking method that considering AGV speed and the front-wheel deviation angle and can be changed |
CN111427007A (en) * | 2020-04-24 | 2020-07-17 | 山东科技大学 | Mine personnel safety state estimation method based on centralized personnel filtering under incomplete measurement |
-
2020
- 2020-11-05 CN CN202011225275.7A patent/CN112346461A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
FR2913800A1 (en) * | 2007-03-13 | 2008-09-19 | Thales Sa | Anti-collision alert filtering device for e.g. helicopter, has alarm manger centralizing alerts transmitted by anti-collision equipments to crew, where each alert comprises danger level code, and alert filter filtering alerts based on code |
CN107611964A (en) * | 2017-09-12 | 2018-01-19 | 重庆大学 | A kind of power system state estimation method based on extension set-membership filtering |
CN109597864A (en) * | 2018-11-13 | 2019-04-09 | 华中科技大学 | Instant positioning and map constructing method and the system of ellipsoid boundary Kalman filtering |
CN109669463A (en) * | 2019-01-10 | 2019-04-23 | 上海海事大学 | A kind of section trace tracking method that considering AGV speed and the front-wheel deviation angle and can be changed |
CN111427007A (en) * | 2020-04-24 | 2020-07-17 | 山东科技大学 | Mine personnel safety state estimation method based on centralized personnel filtering under incomplete measurement |
Non-Patent Citations (1)
Title |
---|
YILIANZHANG等: "Set-Membership Filtering Approach for Path Tracking of an Unmanned Surface Vessel System", 《2017 AUSTRALIAN AND NEW ZEALAND CONTROL CONFERENCE (ANZCC)》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113050608A (en) * | 2021-03-30 | 2021-06-29 | 上海海事大学 | Automatic control system fault detection method based on collective estimation |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109597308A (en) | Pilotless automobile model predictive controller design method based on kinetic model | |
CN110018632A (en) | A kind of vehicle lane change control method and device | |
Attia et al. | Coupled longitudinal and lateral control strategy improving lateral stability for autonomous vehicle | |
CN111016893B (en) | Intelligent vehicle extensible game lane keeping self-adaptive cruise control system and control method under congestion environment | |
CN111780981A (en) | Intelligent vehicle formation lane change performance evaluation method | |
CN110036353A (en) | For the self-adaptation control method and system in the surface car of trace, especially in automatic Pilot scene | |
CN109606363B (en) | Multi-state feedback intelligent automobile extension lane keeping control method | |
CN113386781A (en) | Intelligent vehicle trajectory tracking control method based on data-driven vehicle dynamics model | |
Xu et al. | Model predictive control for lane keeping system in autonomous vehicle | |
CN111796522B (en) | Vehicle state estimation method | |
WO2014149042A1 (en) | Smart cruise control system | |
Farag et al. | Tuning of PID track followers for autonomous driving | |
CN111123701B (en) | Automatic driving path tracking anti-interference control method based on pipeline prediction model | |
Song et al. | A vehicle trajectory tracking method with a time-varying model based on the model predictive control | |
CN114379583A (en) | Automatic driving vehicle trajectory tracking system and method based on neural network dynamics model | |
CN114637292A (en) | Vehicle track tracking robust control method and system considering obstacle avoidance | |
CN110703775B (en) | Commercial vehicle lane keeping path planning method based on improved artificial potential field | |
Zhang et al. | Structured road-oriented motion planning and tracking framework for active collision avoidance of autonomous vehicles | |
Farag | Track maneuvering using PID control for self-driving cars | |
CN112346461A (en) | Automatic guided vehicle collective filtering method considering unknown noise bounded characteristic | |
CN115303265A (en) | Vehicle obstacle avoidance control method and device and vehicle | |
Aoki et al. | Comparative study of prediction models for model predictive path-tracking control in wide driving speed range | |
Liu et al. | Vehicle state and parameter estimation based on double cubature Kalman filter algorithm | |
CN112238856B (en) | Intelligent vehicle overtaking track optimization method based on hybrid particle swarm optimization | |
Kone | Lateral and longitudinal control of an autonomous racing vehicle. |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210209 |