The use of fuzzy logic in redirecting mobile robot is based on two sets of received information. First set is the instantaneous distance of the robot from the obstacle and second set is the instantaneous information of the robot's position. For this purpose, the fuzzy rules base consists of forty-two bases, which is extracted based on the robot's distance from obstacles, and the target position relative to the instantaneous orientation of the robot. In the structure of fuzzy systems, minimal inference engine are considered. Also, Extended Kalman filter is used for localization in a noisy environment. Accordingly, the inputs of the fuzzy systems are determined based on the estimation of the localization process, the information of the obstacles center and the target position. Also, the linear acceleration and instantaneous orientation of the mobile robot are determined by the desired fuzzy structures which are applied to its kinematic model.
Optimized Robot Path Planning Using Parallel Genetic Algorithm Based on Visib...IJERA Editor
Β
An analysis is made for optimized path planning for mobile robot by using parallel genetic algorithm. The
parallel genetic algorithm (PGA) is applied on the visible midpoint approach to find shortest path for mobile
robot. The hybrid ofthese two algorithms provides a better optimized solution for smooth and shortest path for
mobile robot. In this problem, the visible midpoint approach is used to make the effectiveness for avoiding
local minima. It gives the optimum paths which are always consisting on free trajectories. But the
proposedhybrid parallel genetic algorithm converges very fast to obtain the shortest route from source to
destination due to the sharing of population. The total population is partitioned into a number subgroups to
perform the parallel GA. The master thread is the center of information exchange and making selection with
fitness evaluation.The cell to cell crossover makes the algorithm significantly good. The problem converges
quickly with in a less number of iteration.
Review and Comparisons between Multiple Ant Based Routing Algorithms in Mobi...IJMER
Β
Along with an increase in the use and development of various types of mobile ad hoc and
wireless sensor networks the necessity for presenting optimum routing in these networks is a topic yet to
be discussed and new algorithms are presented. Using ant colony optimization algorithm or ACO as a
routing method because of its structural similarities to these networksβ model, has had acceptable results
regarding different parameters especially quality of service (QoS). Considering the fact that many
articles have suggested and presented various models for ant based routing, the need for studying and comparing them can be felt. There are about 17 applied ant based routings, this article studies and compares the most important ant based algorithms so as to indicate the quality and importance of each of them under different conditions
Improving Posture Accuracy of Non-Holonomic Mobile Robot System with Variable...TELKOMNIKA JOURNAL
Β
This paper presents a method to decrease imprecision and inaccuracy that have the tendency to
influence the posture of non-holonomic mobile robot by using the adaptive tuning of universe of discourse.
As such, the primary objective of the study is to force the posture error of , , and towards
zero. Hence, for each step of tuning the fuzzy domain, about 20% of imprecision and inaccuracy had been
added automatically into the variable universe fuzzy, while the control input was bound via scaling gain.
Furthermore, the simulation results showed that the tuning of universe fuzzy parameters could increase
the performance of the system from the aspects of response time and error for steady state through better
control of inaccuracy. Besides, the domains of universe fuzzy input [-4,4] and output [0,6] exhibited good
performance in inching towards zero values as the steady state error was about 1% for x(t) position, 0.02%
for y(t) position, and 0.16% for ΞΈ(t) orientation, whereas the posture error in the given reference was about
0.0002% .
At present, the research on fault detection and diagnosis technology is very significant to improve the reliability of the equipment, which can greatly improve the safety and efficiency of the equipment. This paper proposes a new fault detection and diagnosis means based on the FOA-LSSVM algorithm. Experimental results demonstrate that the algorithm is effective for the detection and diagnosis of analog circuit faults. In addition, the model also demonstrate good generalization ability.
Effective range free localization scheme for wireless sensor networkijmnct
Β
Location aware sensors can be used in many areas such as military and civilian applications. Wireless
Sensor Networks help to identify the accurate location of the event. In this paper a cost effective schema for
localization has been proposed. It uses two beacon nodes to identify the location of unknown nodes. It
also uses flooding and estimating method to accurately identify the location of other nodes. Available area
is divided into zones and beacons are provided for each zone. Beacon nodes are placed in appropriate
locations normally two in a zone to provide location information. Using the two nodes location of unknown
nodes can be calculated accurately.
Optimized Robot Path Planning Using Parallel Genetic Algorithm Based on Visib...IJERA Editor
Β
An analysis is made for optimized path planning for mobile robot by using parallel genetic algorithm. The
parallel genetic algorithm (PGA) is applied on the visible midpoint approach to find shortest path for mobile
robot. The hybrid ofthese two algorithms provides a better optimized solution for smooth and shortest path for
mobile robot. In this problem, the visible midpoint approach is used to make the effectiveness for avoiding
local minima. It gives the optimum paths which are always consisting on free trajectories. But the
proposedhybrid parallel genetic algorithm converges very fast to obtain the shortest route from source to
destination due to the sharing of population. The total population is partitioned into a number subgroups to
perform the parallel GA. The master thread is the center of information exchange and making selection with
fitness evaluation.The cell to cell crossover makes the algorithm significantly good. The problem converges
quickly with in a less number of iteration.
Review and Comparisons between Multiple Ant Based Routing Algorithms in Mobi...IJMER
Β
Along with an increase in the use and development of various types of mobile ad hoc and
wireless sensor networks the necessity for presenting optimum routing in these networks is a topic yet to
be discussed and new algorithms are presented. Using ant colony optimization algorithm or ACO as a
routing method because of its structural similarities to these networksβ model, has had acceptable results
regarding different parameters especially quality of service (QoS). Considering the fact that many
articles have suggested and presented various models for ant based routing, the need for studying and comparing them can be felt. There are about 17 applied ant based routings, this article studies and compares the most important ant based algorithms so as to indicate the quality and importance of each of them under different conditions
Improving Posture Accuracy of Non-Holonomic Mobile Robot System with Variable...TELKOMNIKA JOURNAL
Β
This paper presents a method to decrease imprecision and inaccuracy that have the tendency to
influence the posture of non-holonomic mobile robot by using the adaptive tuning of universe of discourse.
As such, the primary objective of the study is to force the posture error of , , and towards
zero. Hence, for each step of tuning the fuzzy domain, about 20% of imprecision and inaccuracy had been
added automatically into the variable universe fuzzy, while the control input was bound via scaling gain.
Furthermore, the simulation results showed that the tuning of universe fuzzy parameters could increase
the performance of the system from the aspects of response time and error for steady state through better
control of inaccuracy. Besides, the domains of universe fuzzy input [-4,4] and output [0,6] exhibited good
performance in inching towards zero values as the steady state error was about 1% for x(t) position, 0.02%
for y(t) position, and 0.16% for ΞΈ(t) orientation, whereas the posture error in the given reference was about
0.0002% .
At present, the research on fault detection and diagnosis technology is very significant to improve the reliability of the equipment, which can greatly improve the safety and efficiency of the equipment. This paper proposes a new fault detection and diagnosis means based on the FOA-LSSVM algorithm. Experimental results demonstrate that the algorithm is effective for the detection and diagnosis of analog circuit faults. In addition, the model also demonstrate good generalization ability.
Effective range free localization scheme for wireless sensor networkijmnct
Β
Location aware sensors can be used in many areas such as military and civilian applications. Wireless
Sensor Networks help to identify the accurate location of the event. In this paper a cost effective schema for
localization has been proposed. It uses two beacon nodes to identify the location of unknown nodes. It
also uses flooding and estimating method to accurately identify the location of other nodes. Available area
is divided into zones and beacons are provided for each zone. Beacon nodes are placed in appropriate
locations normally two in a zone to provide location information. Using the two nodes location of unknown
nodes can be calculated accurately.
Our team had to use signal processing techniques to find the direction of desired incoming signals at an antenna rejecting interference from other signals.
A Multi-robot System Coordination Design and Analysis on Wall Follower Robot ...IJECEIAES
Β
In this research, multi-robot formation can be established according to the environment or workspace. Group of robots will move sequently if there is no space for robots to stand side by side. Leader robot will be on the front of all robots and follow the right wall. On the other hand, robots will move side by side if there is a large space between them. Leader robot will be tracked the wall on its right side and follow on it while every follower moves side by side. The leader robot have to broadcast the information to all robots in the group in radius 9 meters. Nevertheless, every robot should be received information from leader robot to define their movements in the area. The error provided by fuzzy output process which is caused by read data from ultrasound sensor will drive to more time process. More sampling can reduce the error but it will drive more execution time. Furthermore, coordination time will need longer time and delay. Formation will not be establisehed if packet error happened in the communication process because robot will execute wrong command.
Trafο¬c Light Signal Parameters Optimization Using Modiο¬cation of Multielement...IJECEIAES
Β
A strategy to optimize trafο¬c light signal parameters is presented for solving trafο¬c con- gestion problem using modiο¬cation of the Multielement Genetic Algorithm (MEGA). The aim of this method is to improve the lack of vehicle throughput (F ) of the works called as trafο¬c light signal parameters optimization using the MEGA and Particle Swarm Optimization (PSO). In this case, the modiο¬cation of MEGA is done by adding Hash-Table for saving some best populations for accelerating the recombination process of MEGA which is shortly called as H-MEGA. The experimental results show that the H-MEGA based optimization provides better performance than MEGA and PSO based methods (improving the F F F of both MEGA and PSO based optimization methods by about 10.01% (from 82,63% to 92.64%) and 6.88% (from 85.76% to 92.64%), respectively). In addition, the H-MEGA improve signiο¬cantly the real F of Ooe Toroku road network of Kumamoto City, Japan about 21.62%.
Neural Network Model Development with Soft Computing Techniques for Membrane ...IJECEIAES
Β
Membrane bioreactor employs an efficient filtration technology for solid and liquid separation in wastewater treatment process. Development of membrane filtration model is significant as this model can be used to predict filtration dynamic which is later utilized in control development. Most of the available models only suitable for monitoring purpose, which are too complex, required many variables and not suitable for control system design. This work focusing on the simple time seris model for membrane filtration process using neural network technique. In this paper, submerged membrane filtration model developed using recurrent neural network (RNN) train using genetic algorithm (GA), inertia weight particle swarm optimization (IWPSO) and gravitational search algorithm (GSA). These optimization algorithms are compared in term of its accuracy and convergent speed in updating the weights and biases of the RNN for optimal filtration model. The evaluation of the models is measured using three performance evaluations, which are mean square error (MSE), mean absolute deviation (MAD) and coefficient of determination (R2). From the results obtained, all methods yield satisfactory result for the model, with the best results given by IW-PSO.
A Summative Comparison of Blind Channel Estimation Techniques for Orthogonal ...IJECEIAES
Β
The OFDM technique i.e. Orthogonal frequency division multiplexing has become prominent in wireless communication since its instruction in 1950βs due to its feature of combating the multipath fading and other losses. In an OFDM system, a large number of orthogonal, overlapping, narrow band subchannels or subcarriers, transmitted in parallel, divide the available transmission bandwidth. The separation of the subcarriers is theoretically optimal such that there is a very compact spectral utilization. This paper reviewed the possible approaches for blind channel estimation in the light of the improved performance in terms of speed of convergence and complexity. There were various researches which adopted the ways for channel estimation for Blind, Semi Blind and trained channel estimators and detectors. Various ways of channel estimation such as Subspace, iteration based, LMSE or MSE based (using statistical methods), SDR, Maximum likelihood approach, cyclostationarity, Redundancy and Cyclic prefix based. The paper reviewed all the above approaches in order to summarize the outcomes of approaches aimed at optimum performance for channel estimation in OFDM systems.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
Classification of vehicles based on audio signalsijsc
Β
The focusof this paper is on classification of different vehicles using sound emanated from the vehicles. In
this paper,quadratic discriminant analysis classifies audio signals of passing vehicles to bus, car, motor, and
truck categories based on features such as short time energy, average zero cross rate, and pitch frequency of
periodic segments of signals. Simulation results show that just by considering high energy feature vectors,
better classification accuracy can be achieved due to the correspondence of low energy regions with noises
of the background. To separate these elements, short time energy and average zero cross rate are used
simultaneously.In our method,we have used a few features which are easy to be calculated in time domain
and enable practical implementation of efficient classifier. Although, the computation complexity is low,
the classification accuracy is comparable with other classification methodsbased on long feature vectors
reported in literature for this problem.
Semi-Autonomous Control of a Multi-Agent Robotic System for Multi-Target Oper...Waqas Tariq
Β
Since multi-targets often occur in most applications, it is required that multi-robots are grouped to work on multi-targets simultaneously. Therefore, this paper proposes a control method for a single-master multi-slave (SMMS) teleoperator to control cooperative mobile multi-robots for a multi-target mission. The major components of the proposed control method are the robot-target pairing method and modified potential field based leader-follower formation The robot-target paring method is derived from the proven auction algorithm for a single target and is extended for multi-robot multi-target cases, which optimizes effect-based robot-target pairing based on heuristic and sensory data. The multi-robot multi-target pairing method can produce a weighted attack guidance table (WAGT), which contains benefits of different robot-target pairs. The robot-target pairing converges rapidly - as is the case for auction algorithms with integer benefits. Besides, as long as optimal robot-target pairs are obtained, a team is split into subteams formed by paired robots regarding types and numbers of the robot-target pairs with the robot-target pairing method. The subteams approach and then capture their own paired targets in the modified potential field based leader-follower formation while avoiding sensed obstacles. Simulation studies illustrate system efficacy with the proposed control method for multi-target operations. Moreover, the paper is concluded with observations of enhanced system performance.
Improving face recognition by artificial neural network using principal compo...TELKOMNIKA JOURNAL
Β
The face-recognition system is among the most effective pattern recognition and image analysis techniques. This technique has met great attention from academic and industrial fields because of its extensive use in detecting the identity of individuals for monitoring systems, security and many other practical fields. In this paper, an effective method of face recognition was proposed. Ten person's faces images were selected from ORL dataset, for each person (42) image with total of (420) images as dataset. Features are extracted using principle component analysis PCA to reduce the dimensionality of the face images. Four models where created, the first one was trained using feed forward back propagation learning (FFBBL) with 40 features, the second was trained using 50 features with FFBBL, the third was trained using the same features but using Elman Neural Network. For each person (24) image used as training set for the neural networks, while the remaining images used as testing set. The results showed that the proposed method was effective and highly accurate. FFBBL give accuracy of (98.33,97.14) with (40, 50) features respectively, while Elman gives (98.33, 98.80) for with (40, 50) features respectively.
Simulation of the Linear Boltzmann Transport Equation in Modelling Of Photon ...IOSR Journals
Β
A beam data modelling algorithm was developed by solving the linear Boltzmann Transport Equation (BTE). The Linear Boltzmann Transport Equation (LBTE) is a form of the Boltzmann transport equation that assumes that radiation particles only interact with the matter as they are passing through matter and not with each other. This condition is only valid when there is no external magnetic field. The numerical method proposed by Lewis et al., [9] was used to solve the LBTE. A programming code was computed for the LBTE and run on CMS XiO treatment planning system to generate beam data, the generated beam data were compared to experimentally determined data. The calculated percentage depth dose (PDD) completely overlap the measured PDDs for the small field sizes while there is a shift in the PDD tail for large field size. However the shift is negligible. For the wedge PDDs, the shift between the measured PDDs and the calculated occurs at the Dmax region and it increases with increase in field size. The calculated wedge profiles have a slight shift at the shoulder compared to the measured ones and this decreases with increase in field size, unlike the PDDs. There is also a slight shift between calculated in-plane profiles and measured ones. There is a good agreement between the measured beam data and the calculated ones using the algorithm. This algorithm can be implemented as an in-house algorithm for beam data modelling and also as an independent quality assurance tool for checking the accuracy of clinical TPS algorithms with regards to beam data modelling during quality assurance and TPS commissioning tests.
Autonomous Path Planning and Navigation of a Mobile Robot with Multi-Sensors ...CSCJournals
Β
The mobile robot is applied widely and investigated deeply in industrial fields, meanwhile, mobile robot autonomous path planning and navigation algorithm is a hot research topic. In this paper, firstly mobile robot is introduced, the general path planning and navigation algorithms of the mobile robot are reviewed, then a fuzzy logic with filter smoothing is proposed based on the data from the laser scan sensor and GPS module, which is useful for mobile robot to find the best path to the destination automatically according to the position and size of the gaps between the obstacles in the dynamic environment, finally our designed mobile robot and corresponding Android APP are introduced, the path planning and navigation algorithms are tested on this mobile robot, the testing result shows that this algorithm is globally optimized, quickly responded, battery power and hardware cost saved compared with other algorithms, it is suitable for the mobile robot that is running on the embedded system and it can satisfy our design requirement.
Design of Mobile Robot Navigation system using SLAM and Adaptive Tracking Con...iosrjce
Β
IOSR Journal of Computer Engineering (IOSR-JCE) is a double blind peer reviewed International Journal that provides rapid publication (within a month) of articles in all areas of computer engineering and its applications. The journal welcomes publications of high quality papers on theoretical developments and practical applications in computer technology. Original research papers, state-of-the-art reviews, and high quality technical notes are invited for publications.
Our team had to use signal processing techniques to find the direction of desired incoming signals at an antenna rejecting interference from other signals.
A Multi-robot System Coordination Design and Analysis on Wall Follower Robot ...IJECEIAES
Β
In this research, multi-robot formation can be established according to the environment or workspace. Group of robots will move sequently if there is no space for robots to stand side by side. Leader robot will be on the front of all robots and follow the right wall. On the other hand, robots will move side by side if there is a large space between them. Leader robot will be tracked the wall on its right side and follow on it while every follower moves side by side. The leader robot have to broadcast the information to all robots in the group in radius 9 meters. Nevertheless, every robot should be received information from leader robot to define their movements in the area. The error provided by fuzzy output process which is caused by read data from ultrasound sensor will drive to more time process. More sampling can reduce the error but it will drive more execution time. Furthermore, coordination time will need longer time and delay. Formation will not be establisehed if packet error happened in the communication process because robot will execute wrong command.
Trafο¬c Light Signal Parameters Optimization Using Modiο¬cation of Multielement...IJECEIAES
Β
A strategy to optimize trafο¬c light signal parameters is presented for solving trafο¬c con- gestion problem using modiο¬cation of the Multielement Genetic Algorithm (MEGA). The aim of this method is to improve the lack of vehicle throughput (F ) of the works called as trafο¬c light signal parameters optimization using the MEGA and Particle Swarm Optimization (PSO). In this case, the modiο¬cation of MEGA is done by adding Hash-Table for saving some best populations for accelerating the recombination process of MEGA which is shortly called as H-MEGA. The experimental results show that the H-MEGA based optimization provides better performance than MEGA and PSO based methods (improving the F F F of both MEGA and PSO based optimization methods by about 10.01% (from 82,63% to 92.64%) and 6.88% (from 85.76% to 92.64%), respectively). In addition, the H-MEGA improve signiο¬cantly the real F of Ooe Toroku road network of Kumamoto City, Japan about 21.62%.
Neural Network Model Development with Soft Computing Techniques for Membrane ...IJECEIAES
Β
Membrane bioreactor employs an efficient filtration technology for solid and liquid separation in wastewater treatment process. Development of membrane filtration model is significant as this model can be used to predict filtration dynamic which is later utilized in control development. Most of the available models only suitable for monitoring purpose, which are too complex, required many variables and not suitable for control system design. This work focusing on the simple time seris model for membrane filtration process using neural network technique. In this paper, submerged membrane filtration model developed using recurrent neural network (RNN) train using genetic algorithm (GA), inertia weight particle swarm optimization (IWPSO) and gravitational search algorithm (GSA). These optimization algorithms are compared in term of its accuracy and convergent speed in updating the weights and biases of the RNN for optimal filtration model. The evaluation of the models is measured using three performance evaluations, which are mean square error (MSE), mean absolute deviation (MAD) and coefficient of determination (R2). From the results obtained, all methods yield satisfactory result for the model, with the best results given by IW-PSO.
A Summative Comparison of Blind Channel Estimation Techniques for Orthogonal ...IJECEIAES
Β
The OFDM technique i.e. Orthogonal frequency division multiplexing has become prominent in wireless communication since its instruction in 1950βs due to its feature of combating the multipath fading and other losses. In an OFDM system, a large number of orthogonal, overlapping, narrow band subchannels or subcarriers, transmitted in parallel, divide the available transmission bandwidth. The separation of the subcarriers is theoretically optimal such that there is a very compact spectral utilization. This paper reviewed the possible approaches for blind channel estimation in the light of the improved performance in terms of speed of convergence and complexity. There were various researches which adopted the ways for channel estimation for Blind, Semi Blind and trained channel estimators and detectors. Various ways of channel estimation such as Subspace, iteration based, LMSE or MSE based (using statistical methods), SDR, Maximum likelihood approach, cyclostationarity, Redundancy and Cyclic prefix based. The paper reviewed all the above approaches in order to summarize the outcomes of approaches aimed at optimum performance for channel estimation in OFDM systems.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
Classification of vehicles based on audio signalsijsc
Β
The focusof this paper is on classification of different vehicles using sound emanated from the vehicles. In
this paper,quadratic discriminant analysis classifies audio signals of passing vehicles to bus, car, motor, and
truck categories based on features such as short time energy, average zero cross rate, and pitch frequency of
periodic segments of signals. Simulation results show that just by considering high energy feature vectors,
better classification accuracy can be achieved due to the correspondence of low energy regions with noises
of the background. To separate these elements, short time energy and average zero cross rate are used
simultaneously.In our method,we have used a few features which are easy to be calculated in time domain
and enable practical implementation of efficient classifier. Although, the computation complexity is low,
the classification accuracy is comparable with other classification methodsbased on long feature vectors
reported in literature for this problem.
Semi-Autonomous Control of a Multi-Agent Robotic System for Multi-Target Oper...Waqas Tariq
Β
Since multi-targets often occur in most applications, it is required that multi-robots are grouped to work on multi-targets simultaneously. Therefore, this paper proposes a control method for a single-master multi-slave (SMMS) teleoperator to control cooperative mobile multi-robots for a multi-target mission. The major components of the proposed control method are the robot-target pairing method and modified potential field based leader-follower formation The robot-target paring method is derived from the proven auction algorithm for a single target and is extended for multi-robot multi-target cases, which optimizes effect-based robot-target pairing based on heuristic and sensory data. The multi-robot multi-target pairing method can produce a weighted attack guidance table (WAGT), which contains benefits of different robot-target pairs. The robot-target pairing converges rapidly - as is the case for auction algorithms with integer benefits. Besides, as long as optimal robot-target pairs are obtained, a team is split into subteams formed by paired robots regarding types and numbers of the robot-target pairs with the robot-target pairing method. The subteams approach and then capture their own paired targets in the modified potential field based leader-follower formation while avoiding sensed obstacles. Simulation studies illustrate system efficacy with the proposed control method for multi-target operations. Moreover, the paper is concluded with observations of enhanced system performance.
Improving face recognition by artificial neural network using principal compo...TELKOMNIKA JOURNAL
Β
The face-recognition system is among the most effective pattern recognition and image analysis techniques. This technique has met great attention from academic and industrial fields because of its extensive use in detecting the identity of individuals for monitoring systems, security and many other practical fields. In this paper, an effective method of face recognition was proposed. Ten person's faces images were selected from ORL dataset, for each person (42) image with total of (420) images as dataset. Features are extracted using principle component analysis PCA to reduce the dimensionality of the face images. Four models where created, the first one was trained using feed forward back propagation learning (FFBBL) with 40 features, the second was trained using 50 features with FFBBL, the third was trained using the same features but using Elman Neural Network. For each person (24) image used as training set for the neural networks, while the remaining images used as testing set. The results showed that the proposed method was effective and highly accurate. FFBBL give accuracy of (98.33,97.14) with (40, 50) features respectively, while Elman gives (98.33, 98.80) for with (40, 50) features respectively.
Simulation of the Linear Boltzmann Transport Equation in Modelling Of Photon ...IOSR Journals
Β
A beam data modelling algorithm was developed by solving the linear Boltzmann Transport Equation (BTE). The Linear Boltzmann Transport Equation (LBTE) is a form of the Boltzmann transport equation that assumes that radiation particles only interact with the matter as they are passing through matter and not with each other. This condition is only valid when there is no external magnetic field. The numerical method proposed by Lewis et al., [9] was used to solve the LBTE. A programming code was computed for the LBTE and run on CMS XiO treatment planning system to generate beam data, the generated beam data were compared to experimentally determined data. The calculated percentage depth dose (PDD) completely overlap the measured PDDs for the small field sizes while there is a shift in the PDD tail for large field size. However the shift is negligible. For the wedge PDDs, the shift between the measured PDDs and the calculated occurs at the Dmax region and it increases with increase in field size. The calculated wedge profiles have a slight shift at the shoulder compared to the measured ones and this decreases with increase in field size, unlike the PDDs. There is also a slight shift between calculated in-plane profiles and measured ones. There is a good agreement between the measured beam data and the calculated ones using the algorithm. This algorithm can be implemented as an in-house algorithm for beam data modelling and also as an independent quality assurance tool for checking the accuracy of clinical TPS algorithms with regards to beam data modelling during quality assurance and TPS commissioning tests.
Autonomous Path Planning and Navigation of a Mobile Robot with Multi-Sensors ...CSCJournals
Β
The mobile robot is applied widely and investigated deeply in industrial fields, meanwhile, mobile robot autonomous path planning and navigation algorithm is a hot research topic. In this paper, firstly mobile robot is introduced, the general path planning and navigation algorithms of the mobile robot are reviewed, then a fuzzy logic with filter smoothing is proposed based on the data from the laser scan sensor and GPS module, which is useful for mobile robot to find the best path to the destination automatically according to the position and size of the gaps between the obstacles in the dynamic environment, finally our designed mobile robot and corresponding Android APP are introduced, the path planning and navigation algorithms are tested on this mobile robot, the testing result shows that this algorithm is globally optimized, quickly responded, battery power and hardware cost saved compared with other algorithms, it is suitable for the mobile robot that is running on the embedded system and it can satisfy our design requirement.
Design of Mobile Robot Navigation system using SLAM and Adaptive Tracking Con...iosrjce
Β
IOSR Journal of Computer Engineering (IOSR-JCE) is a double blind peer reviewed International Journal that provides rapid publication (within a month) of articles in all areas of computer engineering and its applications. The journal welcomes publications of high quality papers on theoretical developments and practical applications in computer technology. Original research papers, state-of-the-art reviews, and high quality technical notes are invited for publications.
A Path Planning Technique For Autonomous Mobile Robot Using Free-Configuratio...CSCJournals
Β
This paper presents the implementation of a novel technique for sensor based path planning of autonomous mobile robots. The proposed method is based on finding free-configuration eigen spaces (FCE) in the robot actuation area. Using the FCE technique to find optimal paths for autonomous mobile robots, the underlying hypothesis is that in the low-dimensional manifolds of laser scanning data, there lies an eigenvector which corresponds to the free-configuration space of the higher order geometric representation of the environment. The vectorial combination of all these eigenvectors at discrete time scan frames manifests a trajectory, whose sum can be treated as a robot path or trajectory. The proposed algorithm was tested on two different test bed data, real data obtained from Navlab SLAMMOT and data obtained from the real-time robotics simulation program Player/Stage. Performance analysis of FCE technique was done with existing four path planning algorithms under certain working parameters, namely computation time needed to find a solution, the distance travelled and the amount of turning required by the autonomous mobile robot. This study will enable readers to identify the suitability of path planning algorithm under the working parameters, which needed to be optimized. All the techniques were tested in the real-time robotic software Player/Stage. Further analysis was done using MATLAB mathematical computation software.
International Journal of Fuzzy Logic Systems (IJFLS)Wireilla
Β
International Journal of Fuzzy Logic Systems (IJFLS)
https://wireilla.com/ijfls/current.html
EFFECTIVE REDIRECTING OF THE MOBILE ROBOT IN A MESSED ENVIRONMENT BASED ON THE FUZZY LOGIC
Hamed Khosravi and Seyed Ghorshi
School of Science and Engineering, Sharif University of Technology,
International Campus, Kish Island, Iran.
ABSTRACT
The use of fuzzy logic in redirecting mobile robot is based on two sets of received information. First set is the instantaneous distance of the robot from the obstacle and second set is the instantaneous information of the robot's position. For this purpose, the fuzzy rules base consists of forty-two bases, which is extracted based on the robot's distance from obstacles, and the target position relative to the instantaneous orientation of the robot. In the structure of fuzzy systems, minimal inference engine are considered. Also, Extended Kalman filter is used for localization in a noisy environment. Accordingly, the inputs of the fuzzy systems are determined based on the estimation of the localization process, the information of the obstacles center and the target position. Also, the linear acceleration and instantaneous orientation of the mobile robot are determined by the desired fuzzy structures which are applied to its kinematic model.
KEYWORDS
Mobile robot, Fuzzy logic, Effective redirecting
This paper presents the design of an autonomous robot as a basic development of an intelligent wheeled mobile robot for air duct or corridor cleaning. The robot navigation is based on wall following algorithm. The robot is controlled us- ing fuzzy incremental controller (FIC) and embedded in PIC18F4550 microcontroller. FIC guides the robot to move along a wall in a desired direction by maintaining a constant distance to the wall. Two ultrasonic sensors are installed in the left side of the robot to sense the wall distance. The signals from these sensors are fed to FIC that then used to determine the speed control of two DC motors. The robot movement is obtained through differentiating the speed of these two motors. The experimental results show that FIC is successfully controlling the robot to follow the wall as a guidance line and has good performance compare with PID controller.
Wall follower autonomous robot development applying fuzzy incremental controllerrajabco
Β
This paper presents the design of an autonomous robot as a basic development of an intelligent wheeled mobile robot for air duct or corridor cleaning. The robot navigation is based on wall following algorithm. The robot is controlled us- ing fuzzy incremental controller (FIC) and embedded in PIC18F4550 microcontroller. FIC guides the robot to move along a wall in a desired direction by maintaining a constant distance to the wall. Two ultrasonic sensors are installed in the left side of the robot to sense the wall distance. The signals from these sensors are fed to FIC that then used to de- termine the speed control of two DC motors. The robot movement is obtained through differentiating the speed of these two motors. The experimental results show that FIC is successfully controlling the robot to follow the wall as a guid- ance line and has good performance compare with PID controller.
In this report, one of the main applications of fuzzy logic is proposed i.e in robotic navigation.
Starting from scratch to building up the fuzzy logic and its validation using the MATLAB fuzzy logic toolbox , everything is covered in this report. If you find it helpful do like and share it with your friends. Fuzzy logic finds its application in AGVs and autonomous vehicles etc. Nowadays it is employed to find out the instantaneous power split ratio between the Engine and battery in the parallel hybrid EV.
IJRET : International Journal of Research in Engineering and Technology is an international peer reviewed, online journal published by eSAT Publishing House for the enhancement of research in various disciplines of Engineering and Technology. The aim and scope of the journal is to provide an academic medium and an important reference for the advancement and dissemination of research results that support high-level learning, teaching and research in the fields of Engineering and Technology. We bring together Scientists, Academician, Field Engineers, Scholars and Students of related fields of Engineering and Technology
IJERA (International journal of Engineering Research and Applications) is International online, ... peer reviewed journal. For more detail or submit your article, please visit www.ijera.com
Motion Control of Mobile Robots using Fuzzy Controllerijtsrd
Β
In this study, a motion control based on fuzzy logic is designed so that mobile robots can make the turns they make when moving in an unknown environment more flexibly and smoothly. Fuzzy logic control is suitable for controlling mobile robots because the results can be obtained under uncertainty. Fuzzy logic control is implemented through a set of rules created using expert knowledge. The fuzzy rules created in this paper are designed to allow mobile robots to escape from obstacles, to avoid contact with walls, and to make soft turns without harming their structure. According to the obtained simulation results, the mobile robot has been shown to have successful results in fuzzy logic based motion control. Halil β‘etin | Akif Durdu "Motion Control of Mobile Robots using Fuzzy Controller" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-4 | Issue-1 , December 2019, URL: https://www.ijtsrd.com/papers/ijtsrd29626.pdf Paper URL: https://www.ijtsrd.com/engineering/computer-engineering/29626/motion-control-of-mobile-robots-using-fuzzy-controller/halil-%C3%A7etin
Attitude Estimation And Compensation In Odometric Localization of Mobile Robo...Waqas Tariq
Β
The paper introduces the attitude estimation and compensation in odometric localization of a differential drive indoor mobile robot. A mobile robot navigates through an inclined indoor environment, wherein localization using only wheel encoder is erroneous. The robot uses inertial sensors such as gyroscope, accelerometer and magnetometer to calculate its attitude and acquires a three degree of rotational data. It is observed that the attitude update using gyroscopes alone are prone to diverge and hence error needs to be eliminated. The advantage of MEMS sensors is less-cost while complementary filter algorithm is low complexity in implementation. The performance of the proposed complementary filter algorithm for attitude estimation and compensation in odometric localization are shown by experiment and analysis of results.
With the development of robotics and artificial intelligence field unceasingly thorough, path planning for avoid
obstacles as an important field of robot calculation has been widespread concern. This paper analyzes the
current development of robot and path planning algorithm for path planning to avoid obstacles in practice. We
tried to find a good way in mobile robot path planning by using ant colony algorithm, and it also provides some
solving methods.
A Study of Mobile User Movements Prediction Methods IJECEIAES
Β
For a decade and more, the Number of smart phone users count increasing day by day. With the drastic improvements in Communication technologies, the prediction of future movements of mobile users needs also have important role. Various sectors can gain from this prediction. Communication management, City Development planning, and locationbased services are some of the fields that can be made more valuable with movement prediction. In this paper, we propose a study of several Location Prediction Techniques in the following areas.
Similar to EFFECTIVE REDIRECTING OF THE MOBILE ROBOT IN A MESSED ENVIRONMENT BASED ON THE FUZZY LOGIC (20)
CFD Simulation of By-pass Flow in a HRSG module by R&R Consult.pptxR&R Consult
Β
CFD analysis is incredibly effective at solving mysteries and improving the performance of complex systems!
Here's a great example: At a large natural gas-fired power plant, where they use waste heat to generate steam and energy, they were puzzled that their boiler wasn't producing as much steam as expected.
R&R and Tetra Engineering Group Inc. were asked to solve the issue with reduced steam production.
An inspection had shown that a significant amount of hot flue gas was bypassing the boiler tubes, where the heat was supposed to be transferred.
R&R Consult conducted a CFD analysis, which revealed that 6.3% of the flue gas was bypassing the boiler tubes without transferring heat. The analysis also showed that the flue gas was instead being directed along the sides of the boiler and between the modules that were supposed to capture the heat. This was the cause of the reduced performance.
Based on our results, Tetra Engineering installed covering plates to reduce the bypass flow. This improved the boiler's performance and increased electricity production.
It is always satisfying when we can help solve complex challenges like this. Do your systems also need a check-up or optimization? Give us a call!
Work done in cooperation with James Malloy and David Moelling from Tetra Engineering.
More examples of our work https://www.r-r-consult.dk/en/cases-en/
Hierarchical Digital Twin of a Naval Power SystemKerry Sado
Β
A hierarchical digital twin of a Naval DC power system has been developed and experimentally verified. Similar to other state-of-the-art digital twins, this technology creates a digital replica of the physical system executed in real-time or faster, which can modify hardware controls. However, its advantage stems from distributing computational efforts by utilizing a hierarchical structure composed of lower-level digital twin blocks and a higher-level system digital twin. Each digital twin block is associated with a physical subsystem of the hardware and communicates with a singular system digital twin, which creates a system-level response. By extracting information from each level of the hierarchy, power system controls of the hardware were reconfigured autonomously. This hierarchical digital twin development offers several advantages over other digital twins, particularly in the field of naval power systems. The hierarchical structure allows for greater computational efficiency and scalability while the ability to autonomously reconfigure hardware controls offers increased flexibility and responsiveness. The hierarchical decomposition and models utilized were well aligned with the physical twin, as indicated by the maximum deviations between the developed digital twin hierarchy and the hardware.
Overview of the fundamental roles in Hydropower generation and the components involved in wider Electrical Engineering.
This paper presents the design and construction of hydroelectric dams from the hydrologistβs survey of the valley before construction, all aspects and involved disciplines, fluid dynamics, structural engineering, generation and mains frequency regulation to the very transmission of power through the network in the United Kingdom.
Author: Robbie Edward Sayers
Collaborators and co editors: Charlie Sims and Connor Healey.
(C) 2024 Robbie E. Sayers
Immunizing Image Classifiers Against Localized Adversary Attacksgerogepatton
Β
This paper addresses the vulnerability of deep learning models, particularly convolutional neural networks
(CNN)s, to adversarial attacks and presents a proactive training technique designed to counter them. We
introduce a novel volumization algorithm, which transforms 2D images into 3D volumetric representations.
When combined with 3D convolution and deep curriculum learning optimization (CLO), itsignificantly improves
the immunity of models against localized universal attacks by up to 40%. We evaluate our proposed approach
using contemporary CNN architectures and the modified Canadian Institute for Advanced Research (CIFAR-10
and CIFAR-100) and ImageNet Large Scale Visual Recognition Challenge (ILSVRC12) datasets, showcasing
accuracy improvements over previous techniques. The results indicate that the combination of the volumetric
input and curriculum learning holds significant promise for mitigating adversarial attacks without necessitating
adversary training.
Saudi Arabia stands as a titan in the global energy landscape, renowned for its abundant oil and gas resources. It's the largest exporter of petroleum and holds some of the world's most significant reserves. Let's delve into the top 10 oil and gas projects shaping Saudi Arabia's energy future in 2024.
Sachpazis:Terzaghi Bearing Capacity Estimation in simple terms with Calculati...Dr.Costas Sachpazis
Β
Terzaghi's soil bearing capacity theory, developed by Karl Terzaghi, is a fundamental principle in geotechnical engineering used to determine the bearing capacity of shallow foundations. This theory provides a method to calculate the ultimate bearing capacity of soil, which is the maximum load per unit area that the soil can support without undergoing shear failure. The Calculation HTML Code included.
EFFECTIVE REDIRECTING OF THE MOBILE ROBOT IN A MESSED ENVIRONMENT BASED ON THE FUZZY LOGIC
1. International Journal of Fuzzy Logic Systems (IJFLS) Vol.8, No.3, July 2018.
DOI : 10.5121/ijfls.2018.8301 1
EFFECTIVE REDIRECTING OF THE MOBILE ROBOT
IN A MESSED ENVIRONMENT BASED ON THE
FUZZY LOGIC
Hamed Khosravi and Seyed Ghorshi
School of Science and Engineering, Sharif University of Technology,
International Campus, Kish Island, Iran.
ABSTRACT
The use of fuzzy logic in redirecting mobile robot is based on two sets of received information. First set is
the instantaneous distance of the robot from the obstacle and second set is the instantaneous information of
the robot's position. For this purpose, the fuzzy rules base consists of forty-two bases, which is extracted
based on the robot's distance from obstacles, and the target position relative to the instantaneous
orientation of the robot. In the structure of fuzzy systems, minimal inference engine are considered. Also,
Extended Kalman filter is used for localization in a noisy environment. Accordingly, the inputs of the fuzzy
systems are determined based on the estimation of the localization process, the information of the obstacles
center and the target position. Also, the linear acceleration and instantaneous orientation of the mobile
robot are determined by the desired fuzzy structures which are applied to its kinematic model.
KEYWORDS
Mobile robot, Fuzzy logic, Effective redirecting
1. INTRODUCTION
A Mobile robot is a robot that are capable of moving and consists of many robots. For the purpose
of moving a mobile robot needs a completely coordinated capability, such as motion planning. In
motion planning, the goal is a safe motion that will be achievable for the robot. Since a mobile
robot works in a real world with static and dynamic properties, one of the most important
researches in the robotics is to provide the ability to plan the path and move the mobile robot
autonomously. Also for mobile robots, the most important challenges are the operations in
uncertain and messy environments along with uncertainties in the model in this field. Various
methods have been developed for the accurate robot redirecting in these conditions, which can be
divided into three general categories: model-based methods, fuzzy logic-based methods, and
neural network-based methods. Model-based methods can be based on a precise model of the
environment, plan a route without dealing with obstacles for a mobile robot between the initial
points and the target. These methods cannot be used in variable and unknown environments. The
main characteristic of data-based methods such as fuzzy logic and neural network is their high
response speed and consistency versus measurement noise. These methods are able to routing the
sensed data for a mobile robot in real time in a variable and unknown environment. Fuzzy logic
and neural networks are powerful tools for controlling complex systems in known or unknown
environments. In fuzzy methods, the robot's response is based on the logic of qualitative
behaviors in avoiding the obstacle and achieving the target's position [1-3]. In neural methods, the
robot response is obtained by predicting a training neural network based on a robot behavior
descriptor database.
2. International Journal of Fuzzy Logic Systems (IJFLS) Vol.8, No.3, July 2018.
2
In this paper, the specific features of fuzzy logic will be used to solve the routing problem. These
features can be used for planning robot paths in crowded environments. Also, due to the
complexity of modeling a nonlinear and variable system, the complexity of modeling its
interaction with the environment, and also the advantages of fuzzy controller properties, this type
of controller could be a suitable option for controlling the robot's motion. In redirecting the
mobile robot, the use of fuzzy logic is based on the two sets of received information. First set is
the instantaneous distance of a robot from the obstacles present in the environment, and second is
the instantaneous information of the robot's position in Cartesian space. Therefore, as a rule, the
inputs of the fuzzy system include the robot's distance from obstacles and the redirection angle of
the robot, that is, the angle between the direction of the robot's motion and the target position. On
the other hand, according to the decision logic, the output of fuzzy systems can only be linear and
rotational accelerations of wheels, robot orientation angle and linear acceleration, the linear and
rotational speeds of the mobile robot, etc [4-6].
In developing a fuzzy system, the most important issue is to have a rich fuzzy rule base so that it
is the full descriptive of the redirecting issue of the robot in the presence of obstacles in the
workspace of the mobile robot. The fuzzy inferences should be made in such a way that the robot
is close to its target position with good precision and a fairly high speed of operation and without
encountering any of the obstacles. Also, the type of fuzzy inference engine plays an important
role in the quality of function of automation redirecting system based on fuzzy logic. Typically,
two types of minimum and Mamdani's multiplication are used for the fuzzy inference engine. On
the other hand, the center average defuzzification is used to extract fuzzy model. Another
important issue in redirecting a mobile robot is to have the instantaneous position of the mobile
robot in the Cartesian space. For this purpose, the appropriate sensors should be used. The main
problem of using the sensors is the associated noise that decreases the operation of the automatic
redirecting system of mobile robot. Therefore, an appropriate algorithm such as extended Kalman
filter is useful for accurate estimation of instantaneous position of mobile robot in the presence of
noise.
2. RESEARCH BACKGROUND
Zhang et al. [7] used the combination of fuzzy logic with RFID technology to determine the
instantaneous position of the mobile robot based on the diagnosis of current distance of robot to
target position. Fuzzy logic inputs include the speed of the robot and the power index of the
received signal and the output is the robot distance to the target position. In order to reduce
unpredictable errors due to RFID signal fluctuations, the average strength of current signal and
the latest RSSI information are used as the input of the fuzzy system. The extended Kalman
filter based on a fuzzy neural network has been proposed in [8] and [9] to improve the
localization of a mobile robot in an uncertain environment. The proposed approach is a
combination of the Kalman filter installed on a mobile robot with differential setup and
covariance matrix matching program of the process and the measurement noise. The goal of this
approach is to overcome the divergence of the Kalman filter algorithm in the case of the
incorrect selection of covariance matrices. The fuzzy system uses the difference vector between
the actual and predicted measurements as the reference factor for setting covariance matrices of
the process and the measurement noise. The fuzzy logic that is used to match these matrices
determines its membership functions by multilayer feed-forward neural network. Rigatos [10]
has used extended Kalman filter and particle filter algorithms for the mobile robot localization.
In the proposed method it is assumed that the process and measurement noises obey a Gaussian
distribution. This presentation includes the formulation of a linear Kalman filter for continuous-
discrete state and an extension of them for nonlinear systems. Also, the Monte-Carlo method has
been used for the formulation and the particle filter is used in the localization of the mobile robot
and assuming that the statistical distribution of noise is non-Gaussian. The particle filters are
3. International Journal of Fuzzy Logic Systems (IJFLS) Vol.8, No.3, July 2018.
3
used for state estimation systems that there is no clear answer for them. The major weakness of
this algorithm is that after a certain number of repetitions, almost all weights of the algorithm
will be equal to zero. To avoid this problem, the particles that lead to zeroing the weights
become weaker in favor of other particles. Lin and et al. [11] used a hardware configuration
based on a few ultrasonic sensors to localize the robot. The configuration has two ultrasound
transmitters and three receivers. As the robot moves in the effective range of ultrasonic emission,
the estimation of robot's dynamic position is possible using the information of ultrasonic sensors.
To update the robot's position, the extended Kalman filter based on fuzzy logic is used. The goal
of fuzzy logic is to improve the accuracy of localizing and increasing the consistency of the
localization algorithm relative to measurement noise variations or modeling errors. Fuzzy logic
automatically performs exponential weighting for covariance matrices of noise of process and
measurements. The covariance matrices of noise of process and measurements consist of an
exponential term as a weighting factor of near to one. The inputs of the fuzzy system are the
mean, variance, and standard deviation of the innovation vector and the output of the weighting
system of the weighting factor of the covariance matrices of noise of process and measurement.
Input membership functions have been considered as trapezoidal. The ultrasonic localization
systems can be divided into two groups: The first group, known as flight time methods,
determines space position of the robot by transmission of information through multiple
ultrasound sensors from the robot to the surrounding environment. The second group, known as
the Active Aperture Position method, has one or more transmitters that operate as an observation
tower, and has multiple receivers positioned in predetermined positions on the robot. In general,
localization techniques based on the first method do not have high accuracy and flexibility,
while the latter is highly accurate. Begum et al. [12] used a combination of fuzzy logic and
genetic algorithms to solve the problem of mapping and instantaneous localization of the mobile
robot. Accordingly, an island model based on the genetic algorithm will search the most suitable
mapping to obtain the best robot localization information. The previous information about the
position of the robot is used to accelerate the convergence of the genetic algorithm. Fuzzy logic
provides sample based prediction from the current position of the robot by inferring the amount
of uncertainty in the position of the robot. This sample collection is applied to the genetic
algorithm as a primitive population in order to search for proper mapping with sufficient
information. Among the features of the proposed algorithm are: 1) Smart combination of two
soft computing methods for the SLAM problem. 2) Providing a fuzzy framework for modeling
the distance movement of mobile robot. 3) Introducing a sample-based new approach for
mapping and instantaneous positioning of robot. Najjaran et al. [13] examined the real-time path
design issue, which includes mapping and designing the motion path of the mobile robot. Also, a
special detector is used to scan the robot motion time. The mapping process is done by utilizing
the information of laser and ultrasound sensors, and the path design algorithm uses the mapping
to define an obstacle-independent path for the detector. Creating a map includes a combination
of information and dealing with uncertainties measurement of sensors. The combination of
related information uses the hierarchical filtering process to update the real-time map and
optimize the scanning process of the robot motion. The filtering process involves a fuzzy
adaptive extended Kalman filter, in which the filter gain is matched using a fuzzy model
describes the time of robot motion. Demirli et al. [14] proposed a new approach based on fuzzy
logic for dynamically localization a mobile robot equipped with several sonar sensors. In this
approach, the angular uncertainty and radial inaccuracy of sonar sensors are modeled using
probability distributions. Based on sensor information, a local fuzzy composite mapping is
constructed which is fitted with a comprehensive mapping from the environment to identify the
position of the robot. As a result, a unique fuzzy position or multiple fuzzy candidate positions
are obtained. To reduce the number of candidate positions, the robot moves to a new position
and a new fuzzy compound mapping is determined.
4. International Journal of Fuzzy Logic Systems (IJFLS) Vol.8, No.3, July 2018.
4
3. PROPOSED METHOD
3.1 Redirecting Robot Based on Fuzzy Logic
When a mobile robot moves in an unknown environment toward the target's position, the motion
path independent of encountering obstacles is achieved through the correct response of the mobile
robot to the information received from the sensors. To this end, prior knowledge can be used to
create the appropriate behavioral patterns for the mobile robot. During the movement of the
mobile robot, it is necessary to make a compromise between avoiding the obstacle and moving
correctly towards the target based on the information received from the environment. Since the
purpose of robot is finding the optimal position without encountering obstacles, the robot's
redirecting strategy is designed in two ways: the presence or absence of obstacles. In the absence
of an obstacle, the robot redirected towards the target and accelerates relative to target orientation.
In the presence of obstacles, the robot decides to orient and accelerate appropriately based on
information received from the distance between its instantaneous position and the obstacles
around it. When the robot is very close to the obstacle, reduces its speed and takes direction. In
general, the control system of redirecting robot is designed to achieve two control commands.
The first is to achieve the proper acceleration and the other appropriate directing command.
Accordingly, two fuzzy systems are designed separately. In the first fuzzy system, the
instantaneous orientation of the robot is executed, and in the second fuzzy system, the linear
acceleration of the robot is executed. Therefore, the outputs of each of the two fuzzy systems are
as follows:
ο· π(π‘): Robot instantaneous orientation
ο· π (π‘): instantaneous linear acceleration of the robot
Given the presence of obstacles in the robot's work space and the issue of access to the target
position, the inputs of both fuzzy systems are as follows:
ο· π : The distance of the mobile robot from the left obstacle
ο· π : The distance of the mobile robot from the right obstacle
ο· π : The distance of the mobile robot from the direct obstacle
ο· π , π , π : The distance of the mobile robot from various obstacles
ο· π : Target orientation
If instantaneous position of mobile robot indicated with π and obstacle center position with π, the
robot distance to obstacle is equal to π = (π β π) (π β π). Also, if target position is equal
to π = (π₯ , π¦ ), target orientation is equal to π‘ππ ( ). The target orientation represents
the angle between the direction of robot's motion and the target connector link and the center of
the robot. In Figure 1, each of the input and output components of the fuzzy systems is observed
based on Cartesian coordinates of the mobile robot and obstacles. In Figure 1, for input
variables π , π , π , π , π , and π , the Near and Far linguistic variables are considered. The
Target orientation π includes five linguistic variables such as big negative (NB), small negative
(NS), zero (Z), small positive (PS), and big positive (PB). Also, output variable π(π‘) presents
five linguistic variables such as relative big negative (RNB), relative small negative (RNS), zero
(Z), relative small positive (RPS) and relative big positive (RPB). The output variable
π (π‘) includes three output variables such as decreasing acceleration (DECE), zero acceleration
(ZACC), and increased acceleration (ACCE). In Figure 2, the structure of fuzzy systems has been
presented based on the information received from the distance of the mobile robot to the center of
the obstacles and the target orientation. In the proposed structure, the characteristics of the fuzzy
system are as follows: Single fuzzifier, center average defuzzification, and minimal inference
5. International Journal of Fuzzy Logic Systems (IJFLS) Vol.8, No.3, July 2018.
5
engine. According to the structure of the fuzzy system in Figure 2, the inputs include the robot's
distance from the left, right, and opposite obstacles, and the target instantaneous
Figure 1. Input components of fuzzy systems based Figure 2. The structure of fuzzy systems for
on the instantaneous position of the robot and the redirecting of the parallel robot.
position of the obstacles.
orientation that enters its associated membership functions based on the fuzzy rules base. Then,
the inference is performed for each fuzzy rule based on the minimal inference engine and also the
fuzzy rules base. Finally, the orientation and linear acceleration outputs of the robot are
determined based on center average defuzzification.
In order to form the base of the fuzzy rules, one should pay attention to the following two issues:
1. When there is no obstacle in the robot's work space or the robot's distance is high, the reactive
behavior of the mobile robot is determined by the obstacle position [15-22]. In this situation, the
robot accelerates and gradually moves towards the target. Therefore, based on five possible target
orientations, five fuzzy rules are considered for behavior of the robot:
ο· The robot accelerates if the robot's distance is far from the left obstacle, the robot's
distance is far from the right obstacle, the robot's distance is far from the direct obstacle
and the target orientation is big negative, small negative, zero, small positive and large
positive.
ο· The direction of robot is big negative if the robot's distance is far from the left obstacle,
robot's distance is far from the right obstacle, the robot's distance is far from the direct
obstacle, and the target orientation is big negative.
ο· The direction of robot is small negative if the robot's distance is far from the left obstacle,
the robot's distance is far from the right obstacle, the robot's distance is far from the direct
obstacle, and the target orientation is small negative.
ο· The direction of robot is zero if the robot's distance is far from the left obstacle, the
robot's distance is far from the right obstacle, the robot's distance is far from the direct
obstacle, and the target orientation is zero.
ο· The direction of robot is small positive if the robot's distance is far from the left obstacle,
the robot's distance is far from the right obstacle, the robot's distance is far from the direct
obstacle, and the target orientation is small positive.
ο· The direction of robot is big positive if the robot's distance is far from the left obstacle,
the robot's distance is far from the right obstacle, the robot's distance is far from the direct
obstacle, and the target orientation is big positive.
6. International Journal of Fuzzy Logic Systems (IJFLS) Vol.8, No.3, July 2018.
6
2. When there is an obstacle in the robot's work space or there are low distance between the robot
and obstacle, in this situation, the robot decelerates and its orientation is determined by the target
position relative to the orientation of the robot. In these situations the fuzzy rules can be written
as:
ο· If the target is on the side in line with the direction of the robot rotation, the robot
orientation is relatively small negative and small positive.
ο· When the distance of the mobile robot is low from the left, right, and direct obstacles, and
the rotation of the robot is high, the robot acceleration decreases.
Regarding the structure of fuzzy systems, if the membership functions of inputs
π , π , π , π , π , π and π have been indicated by π , π , π , π , π , π , π respectively
and the outputs-membership functions center of π πππ π have been indicated by π€ and π€ .
Then, based on single fuzzifier, center average defuzzification, and minimal inference engine,
relationship between inputs and outputs of fuzzy systems will be represented as
π(π‘) =
β , , , , , ,
β , , , , , ,
(1)
π (π‘) =
β , , , , , ,
β , , , , , ,
(2)
3.2 Assessing the Redirecting System of Robot Based on Fuzzy Logic
To assess the performance of proposed fuzzy logic for redirecting robot in the presence of
obstacles in its work space, the kinematic model of robot is considered as follow.
π₯Μ = π£ πππ β
π¦Μ = π£ π ππβ
β Μ = π£ π‘ππβ (3)
πΜ = π£
where v1 and v2 are indicators of linear speed and rotation speed of rear wheels, respectively. In
other words, these represent driving speed and steering speed, respectively. The initial position of
the robot is always assumed in the source. In the robot work space, it is assumed that there are
six circular obstacles with a radius of 0.5 meter. It is initially assumed that the robot's target
position is at the π₯β
= (β0.5 ,7) point. The stopping condition of the robot is to achieve a
distance of less than 0.01 meter from the target. In Figure 3, the motion of the mobile robot is
observed from the source to the target position. Based on Figure 3, the fuzzy logic could
appropriately redirect robot toward desired position and, at the same time, avoiding encountered
obstacles. There are two issues that need to be addressed in redirecting the mobile robot.
First: Since the exact selection of the membership function center of outputs of fuzzy system
requires detailed information about the behavioral nature of the mobile robot and the robot's work
space, two correction factors are used one for robot orientation and another for linear
acceleration. In relation to the first target position, the orientation correction coefficient is
considered 0.65 and the linear acceleration correction coefficient is 0.35.
7. International Journal of Fuzzy Logic Systems (IJFLS) Vol.8, No.3, July 2018.
7
Second: Different selection of the orientation membership function center causes the mobile robot
moves in a different ways toward its target. Based on Figure 4, the mobile robot's distance to the
target gradually decreases and reaches to zero after approximately 9100 repetitions.
The values of linear and rotational speeds of the rear wheels are presented in Figure 5. It can be
seen that the linear velocity has steadily decreasing behavior, while the velocity has larger angular
variation and larger range at some moments. Also, the tracking error in lines π and π is
Figure 3. Movement path of the mobile robot Figure 4. Instantaneous distance of the mobile robot
from the first target position to the first target with fuzzy logic.
Figure 5. Linear and angular velocity of the Figure 6. Tracing error of mobile robot in mobile robot in
tracking the first target position. direction of π and π in tracking the first target position
closed to zero after about 91 seconds according to the Figure 6. In the following experiment, it is
assumed that target situation is (0, 8). The initial position of robot is in source. Also, the
correction coefficient of center of orientation membership functions and linear velocity are
considered 0.67 and 1.0, respectively. In Figure 7, the movement path of mobile robot is
presented from source to target position. As it can be seen, the fuzzy logic-based redirecting
system can appropriately redirect mobile robot to target position without encountering the left,
right, and direct obstacles.
8. International Journal of Fuzzy Logic Systems (IJFLS) Vol.8, No.3, July 2018.
8
In other word, the automatic redirection of robot can be achieved by correct setting of output
membership functions center and using accurate fuzzy rules base which describes the robot
reactive behavior in movement to target in presence of obstacles. According to the Figure 8, the
robot distance decreases by increasing the repetitions, therefore, it reaches to zero after about
5000 repetitions. Also, in Figure 9 the tracking error is reached to zero in π₯ and π¦ directions after
50 seconds. According to the Figure 10 the linear velocity decreases constantly and robot
rotational velocity has larger variance range in some moments.
In the next experiment, it is assumed that target situation is (2, 6). The correction coefficient
values of orientation membership functions center and linear velocity are considered 1.3 and 1.0,
respectively. In Figure 11, the movement path of mobile robot is observed. It can be seen
Figure 7. Movement path of mobile Figure 8. Instantaneous distance of mobile robot
robot to second target by using the fuzzy logic. from second target position.
Figure 9. Tracking error of mobile robot in direction Figure 10. Linear and angular velocity of mobile
of π and π in tracking of second target position. robot in tracking of second target position.
that the mobile robot reached to the third target without encountering any obstacles. Similar to the
two first targets, in this case, the fuzzy logic based redirecting is appropriately performed.
9. International Journal of Fuzzy Logic Systems (IJFLS) Vol.8, No.3, July 2018.
9
Figures 12 and 13 indicate the accuracy of tracking target position using proposed redirecting
system. It can be observed from Figure 12 that the robot distance decreases and it reaches to zero
at about 6500. Figure 13 shows the tracking error of mobile robot in direction of π and π in
tracking of third target position. In direction of π the error is almost steady until 50 seconds and
then the error increases. However, in the direction of π the error is increased after 10 seconds.
Also, it can be understood from Figure 14 that linear velocity similar to the two primary targets
has an appropriate uniformity and decreasing behavior. Unlike the first two targets, the rotational
speed does not have much variance range.
3.3 Assessing the Redirecting System of Robot Based on Fuzzy Logic by
Combining Localization
The purpose of localization of the mobile robot is to estimate the position and instantaneous
orientation of the mobile robot in spite of presence of noises of process and measurement. For
Figure 11. Movement path of mobile Figure 12. Instantaneous distance of mobile robot to
third target by using the fuzzy logic robot from third target position.
Figure 13. Tracking error of mobile robot in direction Figure 14. Linear and angular velocity of mobile of
π and π in tracking of third target position robot in tracking of third target position.
10. International Journal of Fuzzy Logic Systems (IJFLS) Vol.8, No.3, July 2018.
10
this purpose, the extended Kalman filter was used. The reason for using the Kalman filter is that it
gives the best possible estimate despite the presence of noise. In this section, the Kalman filter-
based localization problem is combined with fuzzy logic-based redirecting. In other words, the
robot's distance is determined from the left, right and direct obstacles, as well as the target
orientation in each moment based on the Kalman filter estimation. In Figure 15, a block diagram
of redirecting system and a closed loop localization has been presented. For localization of mobile
robot using Kalman filter, it is assumed that noises of process and measurement have Gaussian
nature with variance 1. Before combining fuzzy logic-based redirecting with the Kalman filter,
the robot performance is investigated in routing without using Kalman filter by applying the noise
with variance 0.1. Figure 16 shows that the robot has encountered difficulties in its routing, even
though the stop status has been reduced from 0.01 to 0.1. It is also observed that the performance
of the fuzzy system has encountered difficulties in the presence of noise, and the robot have
problem to find its path. Figure 17 shows the instantaneous distance of the mobile robot from first
target position. It is noted that the robot reaches to its target after 10000 samples. However, in
Figure 18, the movement path of the
Figure 15. The closed loop structure of redirection Figure 16. Movement path of the mobile and
localization based on Fuzzy logic and extended robot toward the first target by using the fuzzy
Kalman filter. logic in the presence of noise
Figure 17. Instantaneous distance of the Figure 18. movement path of the mobile robot toward (0, 8)
mobile robot from first target position. target by using the fuzzy logic and extended Kalman filter.
11. International Journal of Fuzzy Logic Systems (IJFLS) Vol.8, No.3, July 2018.
11
Figure 15. The closed loop structure of redirection Figure 16. Movement path of the mobile robot and
localization based on Fuzzy logic and extended toward the first target by using the fuzzy logic in the
Kalman filter. presence of noise
Figure 17. Instantaneous distance of the Figure 18. movement path of the mobile robot toward (0, 8)
mobile robot from first target position target by using the fuzzy logic and extended Kalman filter.
mobile robot has been shown in the presence of noise using extended Kalman filter. As it can be
seen, the mobile robot moves appropriately on its movement path to the target position. Note that
this appropriate redirecting is performed in the presence of noises of process and measurement
with variance 1. The distance approaches to zero between robot and the target over the time and
for most moments, the state estimation error is less than 5%.
Our final experiments have been shown in Figures 19 and 20 for the target position (2, 6) and (-
0.5, 7). As it is shown in Figure 19, the target position of (2, 6) has been tracked appropriately
without avoiding the obstacle. Also, the distance reaches to zero between the robot and the target
over the time and the status of error is approximated less than 1% using the extended Kalman
filter. Therefore, in general, it can be expressed that the redirecting and localization algorithm
based on the fuzzy logic and extended Kalman filter works well for estimating the optimum state
of the system in the presence of noise. It also works well to redirect accurately the robot toward
the target position, and to avoid collision with obstacles. Also, the proposed algorithm is able to
track different target positions in the robot's workspace. To illustrate the high quality of the
proposed method, the simulation result presented in Figure 20 for a different target position such
12. International Journal of Fuzzy Logic Systems (IJFLS) Vol.8, No.3, July 2018.
12
as (-0.5, 7) shows that the robot converges to the target in the presence of noises of process and
measurements and obstacles in the robot's work space.
4. CONCLUSION
The proposed structure consists of two main subsystems: localization based on the extended
Kalman filter and fuzzy logic based redirecting. In order to form an automated redirecting
system, it is assumed that circular obstacles are located with determined position in the robot's
workspace. Also, the target position is specified in the space. The purpose of the controlling
system is to accurately redirect the robot from source toward target position without collision
with obstacles. For this purpose, two fuzzy systems were considered. The input components of
both systems are the obstacle distance from the center of the left, right, and direct obstacles of
the mobile robot and the target orientation. Based on the information received from these
components and the formation of a suitable fuzzy rule base, the instantaneous orientation of the
robot is determined by the first fuzzy system and the linear acceleration of the mobile robot by
the second fuzzy system. The fuzzy rules base consists of forty-two bases which are extracted
from the distance of the robot to obstacles, and also the target position relative to the
instantaneous orientation of the robot. Also, the single fuzzifier, center average defuzzification,
and minimal inference engine have been considered in the structure of fuzzy systems. On the
other hand, the extended Kalman filter localization has been used because the instantaneous
information of the position of the mobile robot is corrupted by noise. The purpose of
localization is the instantaneous estimation of the robot's position in the presence of noises of
process and measurement. Accordingly, the input components of the fuzzy systems have been
determined based on the estimation of the localization process and the information of the
obstacle center and the target position. Finally, the linear acceleration and instantaneous
orientation of the mobile robot are determined using the desired fuzzy structures and these apply
to its kinematic model. Also, in order to improve the performance of the proposed algorithm for
redirecting and positioning mobile robot, the following strategies and issues will be
recommended: in this study, the correction factor was used for the center's membership
functions of fuzzy system outputs to achieve the correct redirect of the robot from the origin
toward the various positions of the purpose. The use of adaptive algorithms for a momentary
updating the centers can cause high generalizability of the proposed algorithm. According to the
presented results, the proposed algorithm can only be used for the purpose of accurate
redirecting without collisions with obstacles. At same time the extra energy will be applied to
the robot at some of the paths because the path is longer than expected. Therefore, using an
appropriate algorithm which could consider the shortest path in the fuzzy logic application is the
significant development in order to improve proposed algorithm.
REFERENCES
[1] A.V. Topalov. (2011). Recent Advances in Mobile Robots. Rijeka, Croatia: InTech.
[2] S. Y. Chen. (2012). Kalman Filter for Robot Vision: A Survey. IEEE Transactions on Industrial
Electronics, 59, 4409-4420.
[3] H. Hur and H. S. Ahn. (2013). Discrete-Time Hβ Filtering for Mobile Robot Localization Using
Wireless Sensor Network. IEEE Sensors Journal, 13, 245-252.
[4] M. Mirkhani, R. Forsati, A. M. Shahri, and A. Moayedikia. (2013). A Novel Efficient Algorithm for
Mobile Robot Localization. Robotics and Autonomous Systems, 61, 920β931.
[5] E. DiGiampaolo, and F. Martinelli. (2014). Mobile Robot Localization Using the Phase of Passive
UHF RFID Signals. IEEE Transactions on Industrial Electronics, 61, 365-376.
[6] H. Kim, T. Oh, D. Lee, M. Chung, and H. Myung. (2013). Mobile Robot Localization by Matching 2D
Features to 3D Point Cloud. 10th International Conference on Ubiqutous Robots and Ambient
Intelligence, Jeju, Korea, pp 266β267. DOI 10.1109/URAI.2013.6677364
13. International Journal of Fuzzy Logic Systems (IJFLS) Vol.8, No.3, July 2018.
13
[7] H. Zhang, J. Chen, and K. Zhang. (2013). Reliable and Efficient RFID-Based Localization for Mobile
Robot. IEEE International Symposium on Robotic and Sensors Environment, Washington, DC, USA,
pp 184-189. DOI 10.1109/ROSE.2013.6698440
[8] E. Colle, and S. Galerne. (2013). Mobile Robot Localization by Multiangulation Using Set Inversion.
Robotics and Autonomous Systems, 61, 39β48.
[9] T. Thanh, V. Nguyen, M. D. Phung, T. H. Tran, and Q. V. Tran. (2012). Mobile Robot Localization
Using Fuzzy Neural Network Based Extended Kalman Filter. 2012 IEEE International Conference on
Control System, Computing and Engineering, Penang, Malaysia, pp 23-25. DOI
10.1109/ICCSCE.2012.6487181
[10]G. G. Rigatos. (2010). Extended Kalman and Particle Filtering for Sensor Fusion in Motion Control of
Mobile Robots. Mathematics and Computers in Simulation, 81, 590β607.
[11]H. H. Lin, C. C. Tsai, and J. C. Hsu. (2008). Ultrasonic Localization and Pose Tracking of an
Autonomous Mobile Robot via Fuzzy Adaptive Extended Information Filtering. IEEE transactions on
Instrumentation and Measurement, 57, 2024-2034.
[12]M. Begum, G. K.I. Mann, and R. G. Gosine. (2008). Integrated Fuzzy Logic and Genetic Algorithmic
Approach for Simultaneous Localization and Mapping of Mobile Robots. Applied Soft Computing, 8,
150β165.
[13]H. Najjaran and A. Goldenberg. (2007). Real-Time Motion Planning of an Autonomous Mobile
Manipulator Using a Fuzzy Adaptive Kalman Filter. Robotics and Autonomous Systems, 55, 96β106.
[14]K. Demirli and M. Molhim. (2004). Fuzzy Dynamic Localization for Mobile Robots. Fuzzy Sets and
Systems, 144, 251β283.
[15]L. DβAlfonso, A. Griffo, P. Muraca, and P. Pugliese. (2013). A SLAM Algorithm for Indoor Mobile
Robot Localization Using an Extended Kalman Filter and a Segment Based Environment Mapping.
16th IEEE International Conference on Advanced Robotic, Montevideo, Uruguay, pp 1-6. DOI
10.1109/ICAR.2013.6766461
[16]M. Pinto, A. P. Moreira, and A. Matos. (2012). Localization of Mobile Robots Using an Extended
Kalman Filter in a LEGO NXT. IEEE Transactions on Education, 55, 135-144.
[17]C. J. WU and C. C. Tsai. (2001). Localization of an Autonomous Mobile Robot Based on Ultrasonic
Sensory Information. Journal of Intelligent and Robotic Systems, 30, 267β277.
[18]J. J. Leonard and H. F. D. Whyte. (1991). Mobile Robot Localization by Tracking Geometric Beacons.
IEEE transactions on Robotics and Automations, 1, 376-382.
[19]L. Jetto, S. Longhi1, D. Vitali. (1999). Localization of a Wheeled Mobile Robot by Sensor Data Fusion
Based on a Fuzzy Logic Adapted Kalman Filter. Control Engineering Practice, 7, 763-771.
[20]Q. h. Meng, Y. c. Sun, and Z. l. Cao. (2000). Adaptive Extended Kalman Filter (AEKF)-Based Mobile
Robot Localization Using Sonar. Robotica, 18, 459β473.
[21]G. Alefeld and J. Herzberger. (1984). Introduction to Interval Computation (pp.210-225). New York,
USA: Academic press.
[22]I. Arasaratnam and S. Haykin. (2008). Square-root Quadrature Kalman Filtering. IEEE Transactions on
Signal Processing, 56, 2589-2593.