Design of neural-fuzzy-based controller for two autonomously driven wheeled robot

Su, Kuo-Ho; Chen, Yih-Young; Su, Shun‐Feng

doi:10.1016/j.neucom.2010.05.005

Cited by 35 publications

(19 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The simulation is carried out by tracking a desired position (x, y) and orientation angle (θ ) with a lemniscates and square trajectories in the tracking control of the robot. The parameter values of the robot model are taken from [13]: M=0.65kg, I=0.36kgm 2 , L=0.105 m and r=0.033 m. The fist stage of operation is to set the position and orientation neural network identifier. This task is performed using series-parallel and parallel identification technique configuration with modified Elman recurrent neural networks model.…”

Section: Simulation Resultsmentioning

confidence: 99%

Design of an adaptive nonlinear PID controller for nonholonomic mobile robot based on posture identifier

Al-Araji

Abbod

Al-Raweshidy

2011

2011 IEEE International Conference on Control System, Computing and Engineering

View full text Add to dashboard Cite

This paper proposes an adaptive nonlinear controller to guide a nonholonomic mobile robot during continuous and non-continuous trajectory tracking. The structure of the controller consists of two models that describe the kinematics and dynamics of the mobile robot system and the feedforward neural controller. The models are modified Elman neural network and feedforward multi-layer perceptron respectively. The trained Elman neural model acts as the position and orientation identifier The feedforward neural controller is trained off-line and adaptive weights are adapted on-line to find the reference torques, which controls the steady-state outputs of the mobile robot system. The feedback PID neural controller is based on the posture neural identifier and quadratic performance index optimization algorithm in order to tune automatically the PID controller parameters on-line for generating an optimal torque action in the transient state for N-step-ahead prediction. The general back propagation algorithm is used to learn the feedforward neural controller and the posture neural identifier. The simulation results show the effectiveness of the proposed adaptive nonlinear control algorithm; this is demonstrated by the minimised tracking error and the smoothness of the torque control signal obtained, especially with regards to the external disturbance attenuation problem.

show abstract

Section: Simulation Resultsmentioning

confidence: 99%

Design of an adaptive nonlinear PID controller for nonholonomic mobile robot based on posture identifier

Al-Araji

Abbod

Al-Raweshidy

2011

2011 IEEE International Conference on Control System, Computing and Engineering

View full text Add to dashboard Cite

show abstract

“…Alternatively, intelligent control has become an interesting topic for controlling complex systems by function approximation or obtaining rules from the experts knowledge using some powerful tools such as fuzzy logic, neural networks and intelligent algorithms. Hence, there are also some valuable research works in the tracking control of mobile robots, such as fuzzy control [10], adaptive fuzzy control [11], adaptive neural control [12], fuzzy neural control [13,14] and adaptive neural sliding mode control [15].…”

Section: Introductionmentioning

confidence: 99%

Application of the Udwadia–Kalaba approach to tracking control of mobile robots

et al. 2015

View full text Add to dashboard Cite

Udwadia-Kalaba approach which presents a new, general and explicit equation of motion for constrained mechanical systems with holonomic or nonholonomic constraints is applied to the trajectory tracking control of the mobile robot in this paper. Unlike any other nonlinear control methods, the inspiration for this methodology which does not make any linearization or approximations comes from a different, though closely allied, field, namely analytical dynamics. The control torques required to control the mobile robot so that it precisely satisfies the trajectory requirements which are represented by an arbitrary (sufficiently smooth) function of time are obtained explicitly and in closed form by solving Udwadia-Kalaba equation. Numerical simulations are performed to show the simplicity, efficacy and accuracy of this closed-form method.

show abstract

“…However, the encountered environment of a two-wheeled robot may be wicked, and a number of problems will occur, such as difficulty in steering on a bumpy road, requiring more gyroscopes and accelerometers. [17][18][19] Therefore, it is crucial to research a new balance controller for the two-wheeled robot to overcome these problems under the same specifications of motor and tire.…”

Section: Introductionmentioning

confidence: 99%

Robust tracking control design and its application to balance a two-wheeled robot steering on a bumpy road

2012

Proceedings of the Institution of Mechanical Engineers, Part I:

Self Cite

View full text Add to dashboard Cite

A reinforced adaptive fuzzy sliding-mode controller was developed to track the desired state for a certain class of nonlinear dynamic system. Initially, adaptive fuzzy logic was used to derive the update laws for approximating the uncertain nonlinear functions of a dynamic system. Subsequently, a reinforced adaptive mechanism and sliding-mode control were incorporated into the adaptive fuzzy control scheme. In the reinforced adaptive mechanism, both the model and controller parameters were adjusted simultaneously to attenuate the effects caused by the unmodeled dynamics and disturbances. Performance analysis demonstrated the superiority of the proposed reinforced adaptive law over the conventional direct adaptive scheme regarding faster tracking and convergence of parameters. To verify its effectiveness and extend its application, the proposed reinforced adaptive fuzzy sliding-mode controller was applied to balance a twowheeled robot steering on a bumpy road. A number of simulations and experiments were performed. In addition, a conventional direct adaptive scheme under the same environment was also performed for comparison. These results demonstrated that the balance performance of a nonlinear dynamic two-wheeled robot improved because of embedding the proposed reinforced adaptive fuzzy sliding-mode controller into the microcontroller.

show abstract

Design of neural-fuzzy-based controller for two autonomously driven wheeled robot

Cited by 35 publications

References 15 publications

Design of an adaptive nonlinear PID controller for nonholonomic mobile robot based on posture identifier

Design of an adaptive nonlinear PID controller for nonholonomic mobile robot based on posture identifier

Application of the Udwadia–Kalaba approach to tracking control of mobile robots

Robust tracking control design and its application to balance a two-wheeled robot steering on a bumpy road

Contact Info

Product

Resources

About