CN116039636A - Wheel slip considered self-adaptive neural network control method for wheeled mobile robot - Google Patents
Wheel slip considered self-adaptive neural network control method for wheeled mobile robot Download PDFInfo
- Publication number
- CN116039636A CN116039636A CN202211613347.4A CN202211613347A CN116039636A CN 116039636 A CN116039636 A CN 116039636A CN 202211613347 A CN202211613347 A CN 202211613347A CN 116039636 A CN116039636 A CN 116039636A
- Authority
- CN
- China
- Prior art keywords
- mobile robot
- neural network
- wheeled mobile
- wheel slip
- wheel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 45
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000012937 correction Methods 0.000 claims abstract description 12
- 238000003062 neural network model Methods 0.000 claims abstract description 12
- 230000003044 adaptive effect Effects 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000013461 design Methods 0.000 claims description 6
- 230000004913 activation Effects 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 230000005484 gravity Effects 0.000 claims description 3
- 210000002569 neuron Anatomy 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000012271 agricultural production Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/18—Propelling the vehicle
- B60W30/18172—Preventing, or responsive to skidding of wheels
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mechanical Engineering (AREA)
- Transportation (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention relates to the technical field of neural network control, in particular to a wheel type mobile robot self-adaptive neural network control method considering wheel slip. The invention establishes a kinematic model considering the wheel speed, the longitudinal speed, the transverse speed and the yaw rate of the three-degree-of-freedom mobile platform, and establishes a dynamic model of the wheel type mobile robot comprising the wheel slip and external interference by considering the friction of the longitudinal and transverse wheels generated by the slip angle and the wheel slip, and establishes an online multilayer neural network model of the wheel type mobile robot so as to approximate the uncertainty of the wheel slip, the external interference and the like existing in the control system. The real-time tracking error of the wheeled mobile robot is taken as input, the compensation parameters of wheel slip and external interference force are taken as output, and the robustness of the multi-layer neural network structure to the uncertainty of the control system is ensured by combining the back propagation algorithm of the e-correction term, so that the adaptability of the wheeled mobile robot to different operation pavements and the track tracking precision are improved.
Description
Technical Field
The invention relates to the technical field of neural network control, in particular to a wheel type mobile robot self-adaptive neural network control method considering wheel slip.
Background
With the continuous improvement of the computer technology level and the information acquisition and processing technology level, the update and development of agricultural machinery are promoted by the application of new agricultural production modes and new technologies, the technical conditions of intelligent agricultural machinery are mature, and a mobile platform is the motion foundation of an agricultural robot. The farmland operation characteristics determine the difference between the structure of the agricultural mobile robot and the structure of the industrial mobile robot, and particularly the agricultural mobile robot generally operates and moves simultaneously, and has a narrow working environment range, a longer distance and a wider area. Therefore, it is necessary to study a mobile robot suitable for a complex farmland working environment. An important issue of the agricultural mobile robot is to determine a continuous motion control technology of a robot body in a three-dimensional space, and in recent years, a global satellite positioning system (GPS), a Geographic Information System (GIS) and a remote sensing system (RS) are playing an increasing role, and a deep learning camera is used for identifying a road surface so as to realize motion control of an agricultural mobile platform. However, the method has the problems of larger track tracking error, sensitivity to external interference and the like, and in addition, the method is difficult to make real-time compensation correction on specific conditions of complex farmland operation pavements, such as tire slip and the like caused by overlarge soil humidity. The above problems will affect the motion control performance of the mobile robot during the running process, and in order to improve the adaptability of the mobile robot system to different operation pavements and the track tracking control precision, it is necessary to design the control technology.
The document (vehicle Hong Lei, high-technology communication 2022, 32 (7): 756-762) discloses a double-loop sliding mode control strategy for realizing position and speed tracking of an inner ring and an outer ring, and the application of Lyapunov stability theory proves the stability of the system and realizes higher track tracking precision to a certain extent. The method has the following defects: the sliding mode controller designed by the method needs an uncertainty item error boundary of a known control system, but the uncertainty item boundary of a wheel type mobile robot system working in a complex farmland cannot be determined for most of the wheel type mobile robot systems.
The literature (design and implementation of all-wheel steering mobile platform) (Huafei, university of Anhui. 2017) designs a track tracking controller of the all-wheel steering mobile platform through researching a fuzzy neural network self-learning algorithm. The method has the following defects: according to the method, the weight value of the neural network is updated by adopting an error back propagation algorithm, and when a mobile robot applied to a complex farmland road surface faces the wheel slip condition, if the weight of the network cannot be updated online only by using offline neural network calculation, the problems of low tracking precision, overlarge offset and the like are easily caused.
Disclosure of Invention
Aiming at the problems existing in the prior art, the invention provides a wheel type mobile robot self-adaptive neural network control method considering wheel slip.
The technical scheme adopted by the invention is as follows:
the self-adaptive neural network control method of the wheeled mobile robot considering wheel slip comprises the following steps:
s1, establishing a reference coordinate system taking a chassis as a center, and taking the wheel speed, the longitudinal speed, the transverse speed and the yaw rate of the three-degree-of-freedom mobile platform into consideration to form a kinematic model;
s2, based on the kinematics model established in the step S1, taking the friction of the longitudinal wheels and the transverse wheels generated by the slip angle and the wheel slip into consideration, and establishing a wheel type mobile robot dynamics model comprising the wheel slip and external interference;
s3, based on the dynamic model of the wheeled mobile robot established in the step S2, establishing an online multi-layer neural network model taking real-time tracking errors of the wheeled mobile robot as input and taking compensation parameters of wheel slip and external interference force as output so as to approximate uncertainty such as wheel slip, external interference and the like of a control system of the wheeled mobile robot;
and S4, defining a self-adaptive rule capable of updating the weight of the multi-layer neural network on line by combining a back propagation algorithm of the e-correction term based on the multi-layer neural network model established in the step S3, and improving the adaptability and track tracking precision of the wheeled mobile robot to different operation pavements.
As a preferred technical solution of the present invention, the step S1 includes the following steps:
selecting O-XY as a global coordinate system, G-XY as a coordinate system fixed on the wheeled mobile robot, G as a centroid of the wheeled mobile robot, and defining the following kinematic model:
where u, v are the longitudinal and lateral speeds, respectively, at the center of gravity of the wheeled mobile robot, r represents the yaw rate, w r ,w l Respectively represent the angular velocities of the left and right wheels, v s Indicating wheel slip speed by adding v s ,u r s ,u l s Three speed components, all of which are set to zero, take into account the wheel slip model, resulting in a kinematic model without wheel slip:
considering the wheeled mobile robot with three degrees of freedom planes, the sum of external force and moment of the wheeled mobile robot obtained by taking the chassis as a center reference system is as follows:
wherein F is l ,F r Friction forces for driving left and right wheels, P x ,P y ,M d External forces acting at the centroids of the wheeled mobile robots, respectivelyAnd moment, m is the mass of the wheeled mobile robot, I z Is the moment of inertia of the wheeled mobile robot around the z axis, n is the transmission ratio, τ R ,τ L Torque inputs on the left and right wheels, respectively; the working position of the wheeled mobile robot is not always at the centroid here, so that the equivalent force and moment should be such that the external force at the working position is converted into the centroid of the wheeled mobile robot.
As a preferred technical solution of the present invention, the step S2 includes the following steps: longitudinal and transverse tire forces resulting from slip angle and tire slip, respectively, are obtained, each of which is u, v, r, w l ,w r Determining, by eliminating tire forces and reformatting the full dynamic motion equation and deriving time, the dynamic equation for the position vector in the coordinate system is obtained as follows:
by setting all sliding conditions and external forces to zero, the incomplete model of the wheeled mobile robot is:
as a preferred technical solution of the present invention, the step S3 includes the following steps: an online multi-layer neural network model is established, and the following formula is output:
wherein N is i ,N h ,N o The number of neurons in the input layer, hidden layer and output layer, v jk ,w ij For adjusting weights of hidden layer and output layer, θ vi ,θ wi For the threshold offset, the activation function is as follows:
according to the formula (6) and the formula (7), the following formula is output:
defining an unknown uncertainty function due to wheel slip and external disturbance forces:
in which W is * ,V * For an optimal weight matrix for the output layer and the hidden layer,input vector for neural network, ++>Approximation error for bounded neural networks; />
filtering the tracking error can be achieved:
where Λ=Δ T The value of > 0 is the design parameter matrix,defined as a reference velocity vector; the following adaptive tracking controller is proposed for a wheeled mobile robot for tire slip and external disturbance forces:
where K is a positive definite matrix,is the output of the neural network, thereby compensating for the effects of wheel slip and external disturbance forces.
As a preferred technical solution of the present invention, the step S4 includes the following steps:
based on the constructed multi-layer neural network, an adaptive rule capable of updating the network weight on line is defined by combining an improved back propagation algorithm, and the following objective function is defined according to the adaptability of the wheeled mobile robot to different operation pavements:
the updated rules are as follows:
wherein the first term is a back-propagation term and the second term is an e-correction term, α 1,2 > 0 is learning rate, beta 1,2 > 0 is a very small positive number; the performance of adaptively updating the neural network weight can be improved through the second term e-correction term, and the robustness of the multi-layer neural network structure to the uncertainty of the control system is guaranteed by combining a back propagation algorithm, so that the adaptability of the wheeled mobile robot to different operation pavements and the track tracking precision are improved.
Compared with the prior art, the self-adaptive neural network control method of the wheel type mobile robot considering wheel slip has the following technical effects:
1. the invention establishes an online multi-layer neural network model of the wheeled mobile robot to approach the uncertainty of wheel slip, external interference and the like existing in the control system. The real-time tracking error of the wheeled mobile robot is taken as input, the compensation parameters of wheel slip and external interference force are taken as output, and the robustness of the multi-layer neural network structure to the uncertainty of the control system is ensured by combining the back propagation algorithm of the e-correction term, so that the adaptability of the wheeled mobile robot to different operation pavements and the track tracking precision are improved.
2. The method can be applied to various complex farmland operation environments without knowing the boundary size of the uncertain item.
Drawings
FIG. 1 is a schematic diagram of motion model parameters of a wheeled mobile robot in a planar coordinate system;
FIG. 2 is a schematic diagram of a multi-layer neural model structure;
fig. 3 is a block diagram of an adaptive tracking controller based on a multi-layer neural network.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to fall within the scope of the invention.
As shown in fig. 1, the wheel mobile robot adaptive neural network control method considering wheel slip includes the steps of:
s1, establishing a reference coordinate system taking a chassis as a center, and taking the wheel speed, the longitudinal speed, the transverse speed and the yaw rate of the three-degree-of-freedom mobile platform into consideration to form a kinematic model;
s2, based on the kinematics model established in the step S1, taking the friction of the longitudinal wheels and the transverse wheels generated by the slip angle and the wheel slip into consideration, and establishing a wheel type mobile robot dynamics model comprising the wheel slip and external interference;
s3, based on the dynamic model of the wheeled mobile robot established in the step S2, establishing an online multi-layer neural network model taking real-time tracking errors of the wheeled mobile robot as input and taking compensation parameters of wheel slip and external interference force as output so as to approximate uncertainty such as wheel slip, external interference and the like of a control system of the wheeled mobile robot;
and S4, defining a self-adaptive rule capable of updating the weight of the multi-layer neural network on line by combining a back propagation algorithm of the e-correction term based on the multi-layer neural network model established in the step S3, and improving the adaptability and track tracking precision of the wheeled mobile robot to different operation pavements.
S1 comprises the following steps:
selecting O-XY as a global coordinate system, G-XY as a coordinate system fixed on the wheeled mobile robot, G as a centroid of the wheeled mobile robot, and defining the following kinematic model:
where u, v are the longitudinal and lateral speeds, respectively, at the center of gravity of the wheeled mobile robot, r represents the yaw rate, w r ,w l Respectively show left and right vehiclesAngular velocity of wheel, v s Indicating wheel slip speed by adding v s ,u r s ,u l s Three speed components, all of which are set to zero, take into account the wheel slip model, resulting in a kinematic model without wheel slip:
considering the wheeled mobile robot with three degrees of freedom planes, the sum of external force and moment of the wheeled mobile robot obtained by taking the chassis as a center reference system is as follows:
wherein F is l ,F r Friction forces for driving left and right wheels, P x ,P y ,M d External force and moment acting on the center of mass of the wheeled mobile robot respectively, m is the mass of the wheeled mobile robot, I z Is the moment of inertia of the wheeled mobile robot around the z axis, n is the transmission ratio, τ R ,τ L Torque inputs on the left and right wheels, respectively; the working position of the wheeled mobile robot is not always at the centroid here, so that the equivalent force and moment should be such that the external force at the working position is converted into the centroid of the wheeled mobile robot.
S2 comprises the following steps: longitudinal and transverse tire forces resulting from slip angle and tire slip, respectively, are obtained, each of which is u, v, r, w l ,w r It was determined that by eliminating tire forces and reformatting the full dynamic equation of motion, the following kinetic equation was obtained:
δ m =[δ x δ y 0δ l δ r ] T indicating wheel slip and uncertainty caused by external forces;
the time derivative in the kinetic equation is taken and is brought into a kinematic model, so that the kinetic equation of the position vector in the coordinate system is obtained as follows:
in the method, in the process of the invention,
by setting all sliding conditions and external forces to zero, the incomplete model of the wheeled mobile robot is:
as shown in fig. 2, an online multi-layer neural network model with real-time tracking error of the wheeled mobile robot as input and compensation parameters of wheel slip and external interference force as output is established to approach uncertainty such as wheel slip and external interference existing in a control system of the wheeled mobile robot.
S3 comprises the following steps: an online multi-layer neural network model is established, and the following formula is output:
wherein N is i ,N h ,N o The number of neurons in the input layer, hidden layer and output layer, v jk ,w ij For adjusting weights of hidden layer and output layer, θ vi ,θ wi For the threshold offset, the activation function is as follows:
according to the formula (6) and the formula (7), the following formula is output:
defining an unknown uncertainty function due to wheel slip and external disturbance forces:
in which W is * ,V * For an optimal weight matrix for the output layer and the hidden layer,input vector for neural network, ++>Approximation error for bounded neural networks;
as shown in fig. 3, the desired trajectory of the wheeled mobile robot is x d ,The tracking error is defined as follows:/>
Filtering the tracking error can be achieved:
where Λ=Δ T The value of > 0 is the design parameter matrix,defined as a reference velocity vector; the following adaptive tracking controller is proposed for a wheeled mobile robot for tire slip and external disturbance forces:
where K is a positive definite matrix,is the output of the neural network, thereby compensating for the effects of wheel slip and external disturbance forces.
S4 comprises the following steps:
based on the constructed multi-layer neural network, an adaptive rule capable of updating the network weight on line is defined by combining an improved back propagation algorithm, and the following objective function is defined according to the adaptability of the wheeled mobile robot to different operation pavements:
the updated rules are as follows:
wherein the first term is a back-propagation term and the second term is an e-correction term, α 1,2 > 0 is learning rate, beta 1,2 > 0 is a very small positive number; the performance of adaptively updating the neural network weight can be improved through the second term e-correction term, and the robustness of the multi-layer neural network structure to the uncertainty of the control system is guaranteed by combining a back propagation algorithm, so that the adaptability of the wheeled mobile robot to different operation pavements and the track tracking precision are improved.
While the foregoing is directed to embodiments of the present invention, other and further details of the invention may be devised without departing from the basic scope thereof, and the scope thereof is determined by the claims that follow.
Claims (5)
1. The wheel type mobile robot self-adaptive neural network control method considering wheel slip is characterized by comprising the following steps of:
s1, establishing a reference coordinate system taking a chassis as a center, and taking the wheel speed, the longitudinal speed, the transverse speed and the yaw rate of the three-degree-of-freedom mobile platform into consideration to form a kinematic model;
s2, based on the kinematics model established in the step S1, taking the friction of the longitudinal wheels and the transverse wheels generated by the slip angle and the wheel slip into consideration, and establishing a wheel type mobile robot dynamics model comprising the wheel slip and external interference;
s3, based on the dynamic model of the wheeled mobile robot established in the step S2, establishing an online multi-layer neural network model taking real-time tracking errors of the wheeled mobile robot as input and taking compensation parameters of wheel slip and external interference force as output so as to approximate uncertainty such as wheel slip, external interference and the like of a control system of the wheeled mobile robot;
and S4, defining a self-adaptive rule capable of updating the weight of the multi-layer neural network on line by combining a back propagation algorithm of the e-correction term based on the multi-layer neural network model established in the step S3, and improving the adaptability and track tracking precision of the wheeled mobile robot to different operation pavements.
2. The wheel slip considered wheel mobile robot adaptive neural network control method according to claim 1, wherein S1 comprises the steps of:
selecting O-XY as a global coordinate system, G-XY as a coordinate system fixed on the wheeled mobile robot, G as a centroid of the wheeled mobile robot, and defining the following kinematic model:
where u, v are the longitudinal and lateral speeds, respectively, at the center of gravity of the wheeled mobile robot, r represents the yaw rate, w r ,w l Respectively represent the angular velocities of the left and right wheels, v s Indicating wheel slip speed by adding v s ,u r s ,u l s Three speed components, all of which are set to zero, take into account the wheel slip model, resulting in a kinematic model without wheel slip:
considering the wheeled mobile robot with three degrees of freedom planes, the sum of external force and moment of the wheeled mobile robot obtained by taking the chassis as a center reference system is as follows:
wherein F is l ,F r Friction forces for driving left and right wheels, P x ,P y ,M d External force and moment acting on the center of mass of the wheeled mobile robot respectively, m is wheeled movementMass of robot, I z Is the moment of inertia of the wheeled mobile robot around the z axis, n is the transmission ratio, τ R ,τ L Respectively torque inputs on the left and right wheels.
3. The wheel slip considered wheel mobile robot adaptive neural network control method according to claim 1, wherein S2 comprises the steps of: longitudinal and transverse tire forces resulting from slip angle and tire slip, respectively, are obtained, each of which is u, v, r, w l ,w r Determining, by eliminating tire forces and reformatting the full dynamic motion equation and deriving time, the dynamic equation for the position vector in the coordinate system is obtained as follows:
by setting all sliding conditions and external forces to zero, the incomplete model of the wheeled mobile robot is:
4. the wheel slip considered wheel mobile robot adaptive neural network control method according to claim 1, wherein S3 comprises the steps of: an online multi-layer neural network model is established, and the following formula is output:
wherein N is i ,N h ,N o The number of neurons in the input layer, hidden layer and output layer, v jk ,w ij For adjusting weights of hidden layer and output layer, θ vi ,θ wi For the threshold offset, the activation function is as follows:
according to the formula (6) and the formula (7), the following formula is output:
defining an unknown uncertainty function due to wheel slip and external disturbance forces:
in which W is * ,V * For an optimal weight matrix for the output layer and the hidden layer,the vector is input for the neural network,approximation error for bounded neural networks;
filtering the tracking error can be achieved:
where Λ=Δ T The value of > 0 is the design parameter matrix,defined as a reference velocity vector; the following adaptive tracking controller is proposed for a wheeled mobile robot for tire slip and external disturbance forces:
5. The wheel slip considered wheel mobile robot adaptive neural network control method according to claim 1, wherein S4 comprises the steps of:
based on the constructed multi-layer neural network, an adaptive rule capable of updating the network weight on line is defined by combining an improved back propagation algorithm, and the following objective function is defined according to the adaptability of the wheeled mobile robot to different operation pavements:
the updated rules are as follows:
wherein the first term is a back-propagation term and the second term is an e-correction term, α 1,2 > 0 is learning rate, beta 1,2 > 0 is a very small positive number; the performance of adaptively updating the neural network weight can be improved through the second term e-correction term, and the robustness of the multi-layer neural network structure to the uncertainty of the control system is guaranteed by combining a back propagation algorithm, so that the adaptability of the wheeled mobile robot to different operation pavements and the track tracking precision are improved.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211613347.4A CN116039636B (en) | 2022-12-15 | 2022-12-15 | Wheel slip considered self-adaptive neural network control method for wheeled mobile robot |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211613347.4A CN116039636B (en) | 2022-12-15 | 2022-12-15 | Wheel slip considered self-adaptive neural network control method for wheeled mobile robot |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116039636A true CN116039636A (en) | 2023-05-02 |
CN116039636B CN116039636B (en) | 2024-01-30 |
Family
ID=86126459
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211613347.4A Active CN116039636B (en) | 2022-12-15 | 2022-12-15 | Wheel slip considered self-adaptive neural network control method for wheeled mobile robot |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116039636B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116382101A (en) * | 2023-06-05 | 2023-07-04 | 成都信息工程大学 | Uncertainty-considered self-adaptive control method and system for wheeled mobile robot |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004249812A (en) * | 2003-02-19 | 2004-09-09 | Fuji Heavy Ind Ltd | Device and method for generating vehicle movement model |
KR20050062713A (en) * | 2003-12-22 | 2005-06-27 | 충남대학교산학협력단 | A position tracking control system of mobile robot based of vision |
KR20050088636A (en) * | 2004-03-02 | 2005-09-07 | 학교법인 포항공과대학교 | Method for forming an odometry error model of synchro drive robots |
CN108897224A (en) * | 2018-08-03 | 2018-11-27 | 合肥工业大学 | A kind of adaptive Trajectory Tracking Control method of uncertain wheeled mobile robot |
CN110658811A (en) * | 2019-09-09 | 2020-01-07 | 华南理工大学 | Neural network-based collaborative path tracking control method for limited mobile robot |
US20210122340A1 (en) * | 2019-10-28 | 2021-04-29 | Volkswagen Ag | Real-time performance handling virtual tire sensor |
CN113985890A (en) * | 2021-11-12 | 2022-01-28 | 杭州电子科技大学 | Wheeled robot self-adaptive trajectory tracking control method based on neural network |
CN114527664A (en) * | 2022-02-28 | 2022-05-24 | 北京航空航天大学 | Self-adaptive tracking control method of dynamic uncertainty system with asymmetric time lag |
US20220207348A1 (en) * | 2020-12-29 | 2022-06-30 | Ford Global Technologies, Llc | Real-time neural network retraining |
CN114987537A (en) * | 2022-05-17 | 2022-09-02 | 江苏大学 | Neural network dynamics-based road adaptive drift control system and method for automatic driving vehicle |
-
2022
- 2022-12-15 CN CN202211613347.4A patent/CN116039636B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004249812A (en) * | 2003-02-19 | 2004-09-09 | Fuji Heavy Ind Ltd | Device and method for generating vehicle movement model |
KR20050062713A (en) * | 2003-12-22 | 2005-06-27 | 충남대학교산학협력단 | A position tracking control system of mobile robot based of vision |
KR20050088636A (en) * | 2004-03-02 | 2005-09-07 | 학교법인 포항공과대학교 | Method for forming an odometry error model of synchro drive robots |
CN108897224A (en) * | 2018-08-03 | 2018-11-27 | 合肥工业大学 | A kind of adaptive Trajectory Tracking Control method of uncertain wheeled mobile robot |
CN110658811A (en) * | 2019-09-09 | 2020-01-07 | 华南理工大学 | Neural network-based collaborative path tracking control method for limited mobile robot |
US20210122340A1 (en) * | 2019-10-28 | 2021-04-29 | Volkswagen Ag | Real-time performance handling virtual tire sensor |
US20220207348A1 (en) * | 2020-12-29 | 2022-06-30 | Ford Global Technologies, Llc | Real-time neural network retraining |
CN113985890A (en) * | 2021-11-12 | 2022-01-28 | 杭州电子科技大学 | Wheeled robot self-adaptive trajectory tracking control method based on neural network |
CN114527664A (en) * | 2022-02-28 | 2022-05-24 | 北京航空航天大学 | Self-adaptive tracking control method of dynamic uncertainty system with asymmetric time lag |
CN114987537A (en) * | 2022-05-17 | 2022-09-02 | 江苏大学 | Neural network dynamics-based road adaptive drift control system and method for automatic driving vehicle |
Non-Patent Citations (1)
Title |
---|
宋立业;邢飞;: "移动机器人自适应神经滑模轨迹跟踪控制", 控制工程, no. 11, pages 1966 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116382101A (en) * | 2023-06-05 | 2023-07-04 | 成都信息工程大学 | Uncertainty-considered self-adaptive control method and system for wheeled mobile robot |
CN116382101B (en) * | 2023-06-05 | 2023-09-01 | 成都信息工程大学 | Uncertainty-considered self-adaptive control method and system for wheeled mobile robot |
Also Published As
Publication number | Publication date |
---|---|
CN116039636B (en) | 2024-01-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107161207B (en) | Intelligent automobile track tracking control system and control method based on active safety | |
CN108227491B (en) | Intelligent vehicle track tracking control method based on sliding mode neural network | |
CN109884900B (en) | Design method of harvester path tracking controller based on adaptive model predictive control | |
CN110162046B (en) | Unmanned vehicle path following method based on event trigger type model predictive control | |
CN109683614B (en) | Vehicle path control method and device for unmanned mining vehicle | |
CN116039636B (en) | Wheel slip considered self-adaptive neural network control method for wheeled mobile robot | |
CN112034706B (en) | Mobile robot fault-tolerant control method and equipment based on multi-mode switching | |
CN111912426A (en) | Low-cost odometer design method based on MEMS IMU | |
Lu et al. | Adaptive backstepping control of tracked robot running trajectory based on real-time slip parameter estimation | |
Phunopas et al. | Motion Improvement of Four-Wheeled Omnidirectional Mobile Robots for Indoor Terrain. | |
CN113985890B (en) | Neural network-based self-adaptive track tracking control method for wheeled robot | |
CN110109363B (en) | Neural network self-adaptive control method for wheeled mobile robot formation | |
CN109033017B (en) | Vehicle roll angle and pitch angle estimation method under packet loss environment | |
CN111399500B (en) | Centralized formation control method for two-wheeled self-balancing vehicle | |
CN114896694B (en) | Path tracking control method based on two-point pre-aiming | |
CN114889446B (en) | Method, equipment and storage medium for distributing two-direction torque vectors of off-road vehicle | |
CN113525717B (en) | Control system and control method for peristaltic movement of wheel-leg type mobile robot | |
CN114179818A (en) | Intelligent automobile transverse control method based on adaptive preview time and sliding mode control | |
CN114200926A (en) | Local path planning method and system for unmanned vehicle | |
CN112859593B (en) | Body posture and foot end stress cooperative control method for wheel-legged robot | |
Liu et al. | New integrated multi-algorithm fusion localization and trajectory tracking framework of autonomous vehicles under extreme conditions with non-Gaussian noises | |
Jian et al. | An Optimal Controller for Trajectory Tracking of Automated Guided Vehicle | |
CN117519190B (en) | Novel articulated vehicle control method | |
CN117850433B (en) | Collision avoidance formation control method and system for disturbed communication limited mobile robot | |
CN113830094B (en) | Vehicle centroid slip angle self-adaptive fusion and compensation method considering multi-source input information |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |