“…Since the FM-OMR has the ability to move in all directions and its yaw angle can remain unchanged, the angular velocity can be set to 0. According to ( 8)- (10), the outer loop controller can be obtained as (11).…”
Section: Outer Loop Controllermentioning
confidence: 99%
“…In practical application scenarios, there are also external unknown disturbances and internal model uncertainties, which pose challenging problems for trajectory tracking control. To solve this problem, many scholars have proposed different control methods: pid control [11], fuzzy control [12], sliding mode control [13] and other methods have all been studied with certain results. In [14], trajectory tracking control is implemented using model predictive control algorithm with control and system constraints.…”
In this paper, a fuzzy neural network based predefined-time trajectory tracking control method is proposed for the tracking problem of omnidirectional mobile robots (FM-OMR) with uncertainties. Considering the requirement of tracking error convergence time, a position tracking controller based on predefined-time stability is proposed. Compared with the traditional position tracking control method, the minimum upper bound of the convergence time can be explicitly set. In order to obtain more accurate angular velocity tracking, the inner loop controller combines Type 1 fuzzy neural network (T1FNN) to estimate the uncertainty. In addition, considering the problem of feedback channel noise, a Kalman filter combining velocity and position information is proposed. Finally, the simulation results verify the effectiveness of this method.
“…Since the FM-OMR has the ability to move in all directions and its yaw angle can remain unchanged, the angular velocity can be set to 0. According to ( 8)- (10), the outer loop controller can be obtained as (11).…”
Section: Outer Loop Controllermentioning
confidence: 99%
“…In practical application scenarios, there are also external unknown disturbances and internal model uncertainties, which pose challenging problems for trajectory tracking control. To solve this problem, many scholars have proposed different control methods: pid control [11], fuzzy control [12], sliding mode control [13] and other methods have all been studied with certain results. In [14], trajectory tracking control is implemented using model predictive control algorithm with control and system constraints.…”
In this paper, a fuzzy neural network based predefined-time trajectory tracking control method is proposed for the tracking problem of omnidirectional mobile robots (FM-OMR) with uncertainties. Considering the requirement of tracking error convergence time, a position tracking controller based on predefined-time stability is proposed. Compared with the traditional position tracking control method, the minimum upper bound of the convergence time can be explicitly set. In order to obtain more accurate angular velocity tracking, the inner loop controller combines Type 1 fuzzy neural network (T1FNN) to estimate the uncertainty. In addition, considering the problem of feedback channel noise, a Kalman filter combining velocity and position information is proposed. Finally, the simulation results verify the effectiveness of this method.
“…Network weight adaptation was based on the analysis of the Lyapunov stability. Other controllers used for MWMR for trajectory tracking control used adaptive integral terminal sliding mode [7], robust adaptive control [8], adaptive fuzzy tracking control [9][10][11], PID controller with time-varying parameters [12], adaptive back stepping control using neural networks [13], predictive control [14], self-tuning fuzzy-PID control [15], and fuzzy adaptive PID control [16]. For robots to operate in a dynamic working environment and meet the required safety, accuracy, and reliability, advanced intelligent control systems are a valuable solution for the trajectory-tracking control problem [17][18][19].…”
Advanced controllers are an excellent choice for the trajectory tracking problem of Wheeled Mobile Robots (WMRs). However, these controllers pose a challenge to the hardware structure of WMRs due to the controller's complex structure and the large number of calculations needed. In that context, designing a controller with a simple structure and a small number of computations but good real-time performance is necessary in order to improve the tracking accuracy for the WMRs without requiring high hardware architecture. In this work, a neural network controller with a simple structure for the trajectory-tracking of a Mecanum-Wheel Mobile robot (MWMR) based on a reference controller is proposed. A two-layer feedforward neural network is designed as a tracking controller for the robot. The neural network is trained with a sample input-output data set so that the error between the neural network output and the reference control signal of the supervisory controller is minimal. The neural network parameters are trained to update over time. The simulation results verified the effectiveness of the neural network controller, whose parameters are tuned adaptively to ensure a fast convergence to the desired Bézier trajectory.
“…The more logic that is given, the longer the process of reading the program will take, even though what we need is speed and accuracy in the system, hence the emergence of the potential field method. Avoidance of obstacles by using a potential field by utilizing attractive attractions such as a magnetic field when there is an obstacle, such as a positive charge that will leave from the source [10][11][12].…”
Omni-directional mobile robot (OMR) is a robot that can move in all directions with an additional wheel around the core wheel. This research presents a PID controller method at the OMR plant with the specific purpose of getting to the specified point. OMR uses three wheels with an angle difference of 120 degrees. The application of this method using MATLAB assistance from knowing the kinematics to the performance results from the application of the control method. The stages of this research are robot design, component selection, electrical design of the robot, determination of forward kinematic and reverse kinematic and determination of PID controller for positioning. Testing is done by determining the position and determining the point to be determined. Simulation time testing is when the state is at 3,6,9,12 and 15 seconds. The results of the simulation robot can follow the specified coordinates.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.