Fuzzy temporal rules for mobile robot guidance in dynamic environments

Mucientes, Manuel; Iglesias, Roberto; Regueiro, Carlos V.; Bugarín, Alberto; Cariñena, Purificación; Barro, Senén

doi:10.1109/5326.971667

Cited by 31 publications

(11 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As future work, we will try to learn Fuzzy Temporal Rule-based controllers [15][16][17], which have a high degree of expressiveness and the capacity of analyzing the evolution of variables, whilst taking past values into account.…”

Section: Discussionmentioning

confidence: 99%

Evolutionary learning of a fuzzy controller for wall-following behavior in mobile robotics

et al. 2005

Self Cite

View full text Add to dashboard Cite

The design of fuzzy controllers for the implementation of behaviors in mobile robotics is a complex and highly time-consuming task. The use of machine learning techniques such as evolutionary algorithms or artificial neural networks for the learning of these controllers allows to automate the design process. In this paper, the automated design of a fuzzy controller using genetic algorithms for the implementation of the wall-following behavior in a mobile robot is described. The algorithm is based on the iterative rule learning approach, and is characterized by three main points. First, learning has no restrictions neither in the number of membership functions, nor in their values. In the second place, the training set is composed of a set of examples uniformly distributed along the universe of discourse of the variables. This warrantees that the quality of the learned behavior does not depend on the environment, and also that the robot will be capable to face different situations. Finally, the trade off between the number of rules and the quality/accuracy of the controller can be adjusted selecting the value of a parameter. Once the knowledge base has been learned, a process for its reduction and tuning is applied, increasing the cooperation between rules and reducing its number.

show abstract

Section: Discussionmentioning

confidence: 99%

Evolutionary learning of a fuzzy controller for wall-following behavior in mobile robotics

et al. 2005

Self Cite

View full text Add to dashboard Cite

show abstract

“…FTQS have been used in the field of intelligent control for implementing a fuzzy temporal controller for two behaviors in mobile robotics: wall following 29 and moving obstacles avoidance. 30 By means of the analysis of the evolution of state variables throughout temporal references, a filtering of noisy sensorial inputs is achieved, and therefore the control action is more reliable. This is a crucial aspect in robotic applications, where uncertainty about measures in the position of static and moving obstacles due to the ultrasound sensors limitations (specular reflection, low angular resolution, and other measurement errors) may be decisive.…”

Section: Fuzzy Quantification In Mobile Roboticsmentioning

confidence: 99%

Fuzzy quantification in two real scenarios: Information retrieval and mobile robotics

Díaz-Hermida

Bugarín

Cariñena

et al. 2009

Int. J. Intell. Syst.

View full text Add to dashboard Cite

Fuzzy quantification supplies powerful tools for handling linguistic expressions. Nevertheless, its advantages are usually shown at the theoretical level without a proper empirical validation. In this work, we review the application of fuzzy quantification in two application domains. We provide empirical evidence on the adequacy of fuzzy quantification to support different tasks in the context of mobile robotics and information retrieval. This practical perspective aims at exemplifying the actual benefits that real application can get from fuzzy quantifiers. C 2009 Wiley Periodicals, Inc.

show abstract

“…Supervised learning systems using neural networks, fuzzy logic, as well as neuro-fuzzy techniques (Fagg, Lotspeich et al, 1994;Beom and Cho, 1995;Mucientes, Iglesias et al, 2001;Macek, Petrovic et al, 2002;Xin, Vadakkepat et al, 2002) have been developed so that the robot can navigate autonomously while avoiding obstacles. Even if not all of the data corresponding to all possible single cases are supplied to the learning system, an intelligent system can adapt to individual cases of distribution of obstacles and perform adequately.…”

Section: Real Time Obstacle Avoidancementioning

confidence: 99%

Nonlinear Control of Wheeled Mobile Robots

Dixon¹,

Dawson²,

Zergeroğlu³

et al. 2001

Lecture Notes in Control and Information Sciences

View full text Add to dashboard Cite

SUMMARYThe purpose of this project is to implement an autonomous navigation system using nonlinear control techniques to control a wheeled mobile robot (WMR) to follow a preplanned trajectory and track a path. Two other aspects of navigation are studied: path planning and obstacle avoidance. Those three aspects are integrated into a navigation strategy that manages navigation and prevents deadlocks.Two nonlinear control techniques for path tracking and trajectory following have been developed and implemented. In the first approach, a fuzzy logic controller is used to drive the robot through a set of waypoints leading to the destination. In another approach, a controller derived from a Lyapunov function is used to track a reference trajectory that is time dependent. For path planning, a novel optimization technique based on dynamic programming has been developed. The curvature velocity method has been used for obstacle avoidance.The testing was conducted on a P3-AT ali-terrain mobile robot equipped with encoders, a gyroscope, and sonar sensors for localization and environment perception. The test results validate the effectiveness of the different approaches that have been developed. NONLINEAR CONTROL OF A WHEELED MOBILE ROBOTElie Maalouf ABSTRACTThe purpose of this project is to implement an autonomous navigation system using nonlinear control techniques to control a wheeled mobile robot (WMR) to follow a preplanned trajectory and track a path. Two other aspects of navigation are studied: path planning and obstacle avoidance. Those three aspects are integrated into a navigation strate gy that manages navigation and prevents deadlocks.Two nonlinear control techniques for path tracking and trajectory following have been developed and implemented. In the first approach, a fuzzy logic controller is used to drive the robot through a set of waypoints leading to the destination. In another approach, a controller derived from a Lyapunov function is used to track a reference trajectory that is time dependent. For path planning, a novel optimization technique based on dynamic programming has been developed. The curvature velocity method has been used for obstacle avoidance.The testing was conducted on a P3-AT aH-terrain mobile robot equipped with encoders, a gyroscope, and sonar sensors for localization and environment perception. The test results validate the effectiveness of the different approaches that have been developed. COMMANDE NONLINÉAIRE D'UN ROBOT MOBILE À ROUESElie Maalouf SOMMAIRE Le but de ce projet de recherche est de développer un système de navigation autonome, en utilisant des méthodes de commande non-linéaires pour contrôler un robot mobile à roues pour le suivi d'un chemin ou la poursuite d'une trajectoire. Deux autres aspects de navigation sont examinés, la planification de trajectoire et l'évitement des obstacles. Les trois aspects sont intégrés dans une stratégie de navigation afin d'éviter le blocage du robot et de bien gérer la navigation.Deux techniques de commande non-linéaires ont été développé...

show abstract

Fuzzy temporal rules for mobile robot guidance in dynamic environments

Cited by 31 publications

References 15 publications

Evolutionary learning of a fuzzy controller for wall-following behavior in mobile robotics

Evolutionary learning of a fuzzy controller for wall-following behavior in mobile robotics

Fuzzy quantification in two real scenarios: Information retrieval and mobile robotics

Nonlinear Control of Wheeled Mobile Robots

Contact Info

Product

Resources

About