Pub Date : 2013-12-01DOI: 10.1109/ICBR.2013.6729269
Dhaval R Vyas, J. Ohri, Ankit A. Patel
High accuracy trajectory tracking is challenging topic in robotic manipulator control. This is due to nonlinearities and input coupling present in robotic arm. In this paper, a chattering free sliding mode control (SMC) for a robot manipulator including PID part with a fuzzy tunable gain is designed. The main idea is that the robustness property of SMC and good response characteristics of PID are combined with fuzzy tuning gain approach to achieve more acceptable performance. A PID sliding surface is considered such that the robot dynamic equation can be rewritten in terms of sliding surface. Then in order to decrease the reaching time to the sliding surface and deleting the oscillation of the response, a fuzzy tuning system is used for adjusting both controller gains including sliding controller gain parameter and PID coefficient. Controller is applied to two link robot manipulator including model uncertainty and external disturbance as a case study. Simulation study has been done in MATLAB/Simulink environment shows the improvements of the results compare to conventional SMC.
{"title":"Comparison of conventional & fuzzy based sliding mode PID controller for robot manipulator","authors":"Dhaval R Vyas, J. Ohri, Ankit A. Patel","doi":"10.1109/ICBR.2013.6729269","DOIUrl":"https://doi.org/10.1109/ICBR.2013.6729269","url":null,"abstract":"High accuracy trajectory tracking is challenging topic in robotic manipulator control. This is due to nonlinearities and input coupling present in robotic arm. In this paper, a chattering free sliding mode control (SMC) for a robot manipulator including PID part with a fuzzy tunable gain is designed. The main idea is that the robustness property of SMC and good response characteristics of PID are combined with fuzzy tuning gain approach to achieve more acceptable performance. A PID sliding surface is considered such that the robot dynamic equation can be rewritten in terms of sliding surface. Then in order to decrease the reaching time to the sliding surface and deleting the oscillation of the response, a fuzzy tuning system is used for adjusting both controller gains including sliding controller gain parameter and PID coefficient. Controller is applied to two link robot manipulator including model uncertainty and external disturbance as a case study. Simulation study has been done in MATLAB/Simulink environment shows the improvements of the results compare to conventional SMC.","PeriodicalId":269516,"journal":{"name":"2013 International Conference on Individual and Collective Behaviors in Robotics (ICBR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131394696","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-12-01DOI: 10.1109/ICBR.2013.6729262
Hassen Mekki, Manel Letaief
In this paper, we are interested in 3D visual servoïng path planning and path tracking. In fact, in the 3D visual servoïng task, there is no control in the image space and the object may get out of the camera field of view during servoing. To solve this problem, we have used a new approach based on a flatness concept. The 3D visual servoïng suffer from another major problem, is to determine the relative pose of the camera and the object. Generally, the pose estimation is made by correspondences between points of one image and points of the space that is the 2D-3D correspondence. In our work we have used a 3D visual sensor called Kinect. To show the efficiency of the proposed algorithm, we have implemented it on a wheeled Koala robot.
{"title":"Path planning for 3D visual servoing: For a wheeled mobile robot","authors":"Hassen Mekki, Manel Letaief","doi":"10.1109/ICBR.2013.6729262","DOIUrl":"https://doi.org/10.1109/ICBR.2013.6729262","url":null,"abstract":"In this paper, we are interested in 3D visual servoïng path planning and path tracking. In fact, in the 3D visual servoïng task, there is no control in the image space and the object may get out of the camera field of view during servoing. To solve this problem, we have used a new approach based on a flatness concept. The 3D visual servoïng suffer from another major problem, is to determine the relative pose of the camera and the object. Generally, the pose estimation is made by correspondences between points of one image and points of the space that is the 2D-3D correspondence. In our work we have used a 3D visual sensor called Kinect. To show the efficiency of the proposed algorithm, we have implemented it on a wheeled Koala robot.","PeriodicalId":269516,"journal":{"name":"2013 International Conference on Individual and Collective Behaviors in Robotics (ICBR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130676554","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-12-01DOI: 10.1109/ICBR.2013.6729271
Maram Alajlan, A. Koubâa, I. Châari, Hachemi Bennaceur, Adel Ammar
Global path planning is considered as a fundamental problem for mobile robots. In this paper, we investigate the capabilities of genetic algorithms (GA) for solving the global path planning problem in large-scale grid maps. First, we propose a GA approach for efficiently finding an (or near) optimal path in the grid map. We carefully designed GA operators to optimize the search process. We also conduct a comprehensive statistical evaluation of the proposed GA approach in terms of solution quality, and we compare it against the well-known A* algorithm as a reference. Extensive simulation results show that GA is able to find the optimal paths in large environments equally to A* in almost all the simulated cases.
{"title":"Global path planning for mobile robots in large-scale grid environments using genetic algorithms","authors":"Maram Alajlan, A. Koubâa, I. Châari, Hachemi Bennaceur, Adel Ammar","doi":"10.1109/ICBR.2013.6729271","DOIUrl":"https://doi.org/10.1109/ICBR.2013.6729271","url":null,"abstract":"Global path planning is considered as a fundamental problem for mobile robots. In this paper, we investigate the capabilities of genetic algorithms (GA) for solving the global path planning problem in large-scale grid maps. First, we propose a GA approach for efficiently finding an (or near) optimal path in the grid map. We carefully designed GA operators to optimize the search process. We also conduct a comprehensive statistical evaluation of the proposed GA approach in terms of solution quality, and we compare it against the well-known A* algorithm as a reference. Extensive simulation results show that GA is able to find the optimal paths in large environments equally to A* in almost all the simulated cases.","PeriodicalId":269516,"journal":{"name":"2013 International Conference on Individual and Collective Behaviors in Robotics (ICBR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114219043","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-12-01DOI: 10.1109/ICBR.2013.6729280
Khaled Salhi, A. Alimi
In mobile robots, motion control systems play an important role to assume trajectory planning and obstacle avoidance. Proportional-Integral-Derivative (PID) controllers are the most popular controller used in industrial control systems including mobile robots. The PID controller is developed based on the linear control theory but it gives inconsistent performance for different condition. In order to overcome this problem, we propose a Fuzzy-tuned PID controller in which the PID parameters are learned, adapted and changed thanks to the fuzzy system. The PID inputs are given by the Kinect sensor after being processed by the point cloud library. The effectiveness of this method is evaluated experimentally in real time using the mobile robot iRobot Create.
{"title":"Fuzzy-PID hybrid controller for mobile robot using point cloud and low cost depth sensor","authors":"Khaled Salhi, A. Alimi","doi":"10.1109/ICBR.2013.6729280","DOIUrl":"https://doi.org/10.1109/ICBR.2013.6729280","url":null,"abstract":"In mobile robots, motion control systems play an important role to assume trajectory planning and obstacle avoidance. Proportional-Integral-Derivative (PID) controllers are the most popular controller used in industrial control systems including mobile robots. The PID controller is developed based on the linear control theory but it gives inconsistent performance for different condition. In order to overcome this problem, we propose a Fuzzy-tuned PID controller in which the PID parameters are learned, adapted and changed thanks to the fuzzy system. The PID inputs are given by the Kinect sensor after being processed by the point cloud library. The effectiveness of this method is evaluated experimentally in real time using the mobile robot iRobot Create.","PeriodicalId":269516,"journal":{"name":"2013 International Conference on Individual and Collective Behaviors in Robotics (ICBR)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131363574","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-12-01DOI: 10.1109/ICBR.2013.6729263
R. Zouaoui, Hassen Mekki
We are interested in this paper in the 2D visual servoïng for a mobile robot type Koala using radial basis function (RBF) neural network (NN). Seen that the interaction matrix, expressing the relationship between the camera motion and the consequent changes on the visual features, contains parameters to be estimated (depth) and requires a calibration phase of the camera. In more, the model of the robot can contain uncertainties engendered the movement with sliding. An online identification, using NN was proposed to overcome these problems. The RBF NN is used to estimate the block formed by the interaction matrix and the model inverts of the robot. The considered images are described by objects given by four points. Seen that the variables number of the estimated function is important, what can cause a problem of the use of an excessive number of RBFs. As remedy, we used a new approach consists in considering that a single point is sufficient to solve the problem of the 2D visual servoïng of the mobile robot.
{"title":"2D visual servoïng of wheeled mobile robot by neural networs","authors":"R. Zouaoui, Hassen Mekki","doi":"10.1109/ICBR.2013.6729263","DOIUrl":"https://doi.org/10.1109/ICBR.2013.6729263","url":null,"abstract":"We are interested in this paper in the 2D visual servoïng for a mobile robot type Koala using radial basis function (RBF) neural network (NN). Seen that the interaction matrix, expressing the relationship between the camera motion and the consequent changes on the visual features, contains parameters to be estimated (depth) and requires a calibration phase of the camera. In more, the model of the robot can contain uncertainties engendered the movement with sliding. An online identification, using NN was proposed to overcome these problems. The RBF NN is used to estimate the block formed by the interaction matrix and the model inverts of the robot. The considered images are described by objects given by four points. Seen that the variables number of the estimated function is important, what can cause a problem of the use of an excessive number of RBFs. As remedy, we used a new approach consists in considering that a single point is sufficient to solve the problem of the 2D visual servoïng of the mobile robot.","PeriodicalId":269516,"journal":{"name":"2013 International Conference on Individual and Collective Behaviors in Robotics (ICBR)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114172608","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-12-01DOI: 10.1109/ICBR.2013.6729267
C. Walha, H. Bezine, A. Alimi
Automatic grasp planning is an active field in robotic research. Its main purpose is to find the contact points between the robotic hand and an object in order to grasp it efficiently. As the robotic hand has many degrees of freedom which induce a huge number of solutions, the search for the “best” solution became an optimization problem. The search of such a solution is conducted by a grasp quality measurement which will be called the objective (or fitness) function. This paper proposes a Multi-Objective Particle Swarm Optimization (MOPSO) approach to tackle the grasp planning problem. Its fitness functions are based in two different grasp quality measurements. The MOPSO approach is then tested in HandGrasp simulator with simple objects. The results will be compared with two simple Particle Swarm Optimization (PSO) approaches and demonstrate its performance.
{"title":"A Multi-Objective Particle Swarm Optimization approach to robotic grasping","authors":"C. Walha, H. Bezine, A. Alimi","doi":"10.1109/ICBR.2013.6729267","DOIUrl":"https://doi.org/10.1109/ICBR.2013.6729267","url":null,"abstract":"Automatic grasp planning is an active field in robotic research. Its main purpose is to find the contact points between the robotic hand and an object in order to grasp it efficiently. As the robotic hand has many degrees of freedom which induce a huge number of solutions, the search for the “best” solution became an optimization problem. The search of such a solution is conducted by a grasp quality measurement which will be called the objective (or fitness) function. This paper proposes a Multi-Objective Particle Swarm Optimization (MOPSO) approach to tackle the grasp planning problem. Its fitness functions are based in two different grasp quality measurements. The MOPSO approach is then tested in HandGrasp simulator with simple objects. The results will be compared with two simple Particle Swarm Optimization (PSO) approaches and demonstrate its performance.","PeriodicalId":269516,"journal":{"name":"2013 International Conference on Individual and Collective Behaviors in Robotics (ICBR)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123438797","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-12-01DOI: 10.1109/ICBR.2013.6729281
T. Toumi, A. Zidani
One goal in Human-robot interaction field is to explore ways by which robots can improve their social interaction with humans. Our main concern here is to equip robot by emotional capacities and improve their social interactions with human being by adapting Norman's basic theory of human action, and by integration of emotions and capacities concepts of the robot in the interaction process. Finally, some illustrations of adapted model were presented by scenarios of human-robot interactions.
{"title":"Adaptation of action theory for Human-robot social interaction","authors":"T. Toumi, A. Zidani","doi":"10.1109/ICBR.2013.6729281","DOIUrl":"https://doi.org/10.1109/ICBR.2013.6729281","url":null,"abstract":"One goal in Human-robot interaction field is to explore ways by which robots can improve their social interaction with humans. Our main concern here is to equip robot by emotional capacities and improve their social interactions with human being by adapting Norman's basic theory of human action, and by integration of emotions and capacities concepts of the robot in the interaction process. Finally, some illustrations of adapted model were presented by scenarios of human-robot interactions.","PeriodicalId":269516,"journal":{"name":"2013 International Conference on Individual and Collective Behaviors in Robotics (ICBR)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124965267","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-12-01DOI: 10.1109/ICBR.2013.6729274
Ben Khaled Sonia, Hammouda Laroussi, Kaaniche Khaled
This paper presents the new technique of global visual features based on random process. Using 2D visual servoing algorithm applied on the robotic platform equipped with a wireless camera, the robotic system must always find a desired position stored and referenced by an object and defined in the navigation environment. To operate the assembly formed by a robot + camera, processing unit (computer) which supports the acquisition of the visual information from the imaging device (camera).The processing unit used its data processing result and calculates the control law and sends operation commands to the robot. This technique of global visual servoing based on a stochastic visual information extraction is used to control a mobile robot and it is simulated in the Matlab tool. In fact, this method ensures a reduction of computation time compared to the ancient one.
{"title":"Visual servoing 2D based on global description: Validation on Koala mobile robot","authors":"Ben Khaled Sonia, Hammouda Laroussi, Kaaniche Khaled","doi":"10.1109/ICBR.2013.6729274","DOIUrl":"https://doi.org/10.1109/ICBR.2013.6729274","url":null,"abstract":"This paper presents the new technique of global visual features based on random process. Using 2D visual servoing algorithm applied on the robotic platform equipped with a wireless camera, the robotic system must always find a desired position stored and referenced by an object and defined in the navigation environment. To operate the assembly formed by a robot + camera, processing unit (computer) which supports the acquisition of the visual information from the imaging device (camera).The processing unit used its data processing result and calculates the control law and sends operation commands to the robot. This technique of global visual servoing based on a stochastic visual information extraction is used to control a mobile robot and it is simulated in the Matlab tool. In fact, this method ensures a reduction of computation time compared to the ancient one.","PeriodicalId":269516,"journal":{"name":"2013 International Conference on Individual and Collective Behaviors in Robotics (ICBR)","volume":"127 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121400625","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-12-01DOI: 10.1109/ICBR.2013.6729284
N. Baklouti, A. Alimi
Recently, there has been a considerable interest on learning type-2 fuzy logic systems, essentially on how determining the footprint of uncertainties of linguistic variables. In fact, the complexity and difficulty in developing type-2 fuzzy systems can be located at the time of deciding which are the best parameters of membership functions (MFs). In real robot applications, the task of designing a type-2 fuzzy logic controller is complex enough essentially because the presence of many forms of noise and uncertainties, where the robot while navigating has to control many variables. In this paper we present a novel adaptive learning type-2 fuzzy logic controller (FLC) for robot motion planing task. The MFs are tuned instantanously using real time particle swarm optimization technique. The proposed architecture presented good results which were demonstrated on the “iRobot Create” robot.
{"title":"Real time PSO based adaptive learning type-2 fuzzy logic controller design for the iRobot Create robot","authors":"N. Baklouti, A. Alimi","doi":"10.1109/ICBR.2013.6729284","DOIUrl":"https://doi.org/10.1109/ICBR.2013.6729284","url":null,"abstract":"Recently, there has been a considerable interest on learning type-2 fuzy logic systems, essentially on how determining the footprint of uncertainties of linguistic variables. In fact, the complexity and difficulty in developing type-2 fuzzy systems can be located at the time of deciding which are the best parameters of membership functions (MFs). In real robot applications, the task of designing a type-2 fuzzy logic controller is complex enough essentially because the presence of many forms of noise and uncertainties, where the robot while navigating has to control many variables. In this paper we present a novel adaptive learning type-2 fuzzy logic controller (FLC) for robot motion planing task. The MFs are tuned instantanously using real time particle swarm optimization technique. The proposed architecture presented good results which were demonstrated on the “iRobot Create” robot.","PeriodicalId":269516,"journal":{"name":"2013 International Conference on Individual and Collective Behaviors in Robotics (ICBR)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117171384","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-12-01DOI: 10.1109/ICBR.2013.6729270
A. Zaidi, N. Rokbani, A. Alimi
In this paper the investigation is placed on the hierarchic neuro-fuzzy systems as a possible solution for biped control. An hierarchic controller for biped is presented, it includes several sub-controllers and the whole structure is generated using the adaptive Neuro-fuzzy method. The proposed hierarchic system focus on the key role that the centre of mass position plays in biped robotics, the system sub-controllers generate their outputs taken into consideration the position of that key point.
{"title":"A hierarchical fuzzy controller for a biped robot","authors":"A. Zaidi, N. Rokbani, A. Alimi","doi":"10.1109/ICBR.2013.6729270","DOIUrl":"https://doi.org/10.1109/ICBR.2013.6729270","url":null,"abstract":"In this paper the investigation is placed on the hierarchic neuro-fuzzy systems as a possible solution for biped control. An hierarchic controller for biped is presented, it includes several sub-controllers and the whole structure is generated using the adaptive Neuro-fuzzy method. The proposed hierarchic system focus on the key role that the centre of mass position plays in biped robotics, the system sub-controllers generate their outputs taken into consideration the position of that key point.","PeriodicalId":269516,"journal":{"name":"2013 International Conference on Individual and Collective Behaviors in Robotics (ICBR)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131094588","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：