Feedback-error learning scheme using recurrent neural networks for nonlinear dynamic systems

Rao, D.H.; Bitner, Doug; Gupta, Manika

doi:10.1109/icnn.1994.374158

Cited by 13 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different from the former self-balancing robot mentioned above, CCWR has two different operation modes, and the parameters in two modes are different. Fixed parameters control strategies such as fuzzy control [10,13,14], state feedback [15,16], PID control [17] and sliding mode [18,19], neural network [20]etc can hardly adapt to the overall change in system parameters. Therefore, changeable parameters controller is required.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Development of a dual-mode mobile robot system for practical applications

Dai

et al. 2011

2011 IEEE International Conference on Mechatronics and Automation

View full text Add to dashboard Cite

This paper addresses a Coaxial Couple WheeledRobot platform with a dual-mode for practical applications both as a personal transporter and a robot patrolman. This CCWR has two modes: the patrol mode as CCWR-P and the transporter mode as CCWR-T. In order to achieve fast switching between the two modes, modular design approach is adopted, and mechanism as well as the designed controller are developed and demonstrated. The system is divided into four separate parts, and independent functional modules can be quickly assembled for different target applications. Integration hardware is focused here, as well as the implementation of the controllers. For the robot control, a compact states feedback controller is proposed in this paper, and then the robot can track the desired inputs. Finally, the running experiments indoor and outdoor proved that the robot platform can move smoothly with the two modes and furthermore the robot can execute the tasks of transporting and patrol.

show abstract

Section: Introductionmentioning

confidence: 99%

“…20) Linearize the above nonlinear model around the balance point of T §0, sinT §0, cosT §1, equations(19) and (20has two operating modes and parameters are different in different modes, so equation (21) ~ (22) is not unique in different mode. For CCWR, its basic parameters are fixed and shown in…”

mentioning

confidence: 99%

Development of a dual-mode mobile robot system for practical applications

Dai

et al. 2011

2011 IEEE International Conference on Mechatronics and Automation

View full text Add to dashboard Cite

show abstract

“…26 Shibata and Schaal later applied the FEL to a humanoid robot face to emulate the VOR using a recursive least squares training law. 27 Some current investigations focus on using different feedback learning algorithms to optimize the process, 28 testing different network structures, 29 and applying the FEL model to adaptive control. 30 The natural progression is to integrate forward Smith predictor model with the learned internal model.…”

Section: Introductionmentioning

confidence: 99%

Panoramic camera tracking on planetary rovers using feedforward control

Ross

Ellery

2017

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

Future rover missions will be enhanced with the opportunistic search of salient targets during the planetary traverse phase. An essential component of the search is the locating and tracking of targets at the camera control level. The rover visual system must be able to follow quantified information gradients for smooth tracking in the visual field with limited information from images and delayed positional feedback caused by long communication delays inherent in planetary exploration. We propose a control algorithm based on vestibulo-ocular reflexes employed by the human cerebellum. The controller uses a feedback error learning model, which is able to track targets by compensating for the rover motion at the pan-tilt using a network trained prediction of the pan-tilt dynamics. The feedforward controller proved capable in tracking objects in the visual field as was demonstrated in both simulation and on the Barrett WAM.

show abstract

“…The FEL model applied the FEL to a humanoid robot face to emulate the VOR using a recursive least squares training law [51]. Some current investigations focus on using different feedback learning algorithms to optimize the process [52], testing different network structures [53] and applying the FEL model to adaptive control [54].…”

Section: Cerebellum and Vormentioning

confidence: 99%

Application of Feedforward Control to Pan-Tilt Cameras on Planetary Rovers

Ross¹

View full text Add to dashboard Cite

Future rover missions will be enhanced through the addition of science to the planetary traverse phase. Scientific targets are selected through a random search and salient gradient tracking in the visual field, which requires both a search algorithm and a reactive pan-tilt camera controller. This thesis presents a cerebellar-like reactive pantilt controller to track salient targets in the visual field as the rover moves based off the cerebellar models and the human vestibulo-ocular reflex. An online neural network using an EKF training law is used as a feed forward controller and it's performance is compared to standard batch and online neural network training techniques. The controller was then applied to the Barrett WAM to control the manipulator wrist.The online EKF trained network is able to adequately model the internal dynamics of a pan-tilt, while remaining stable due to the continuous learning. This is shown in both simulation and practice.

show abstract

Feedback-error learning scheme using recurrent neural networks for nonlinear dynamic systems

Cited by 13 publications

References 7 publications

Development of a dual-mode mobile robot system for practical applications

Development of a dual-mode mobile robot system for practical applications

Panoramic camera tracking on planetary rovers using feedforward control

Application of Feedforward Control to Pan-Tilt Cameras on Planetary Rovers

Contact Info

Product

Resources

About