Dr. Sobh received the B.Sc. in Engineering degree with honors from Alexandria University, Egypt in 1988, and M.S. and Ph.D. degrees from the University of Pennsylvania in 1989 and 1991. He is the President and Professor of Electrical and Computer Engineering at Lawrence Technological University, and Distinguished Professor and Dean of Engineering Emeritus at the University of Bridgeport.
Robotics deals with the design, construction, operation, and application of robots, as well as co... more Robotics deals with the design, construction, operation, and application of robots, as well as computer systems for their control, sensory feedback, and information processing. This book brings together some of the latest research in robot applications, control, modeling, sensors and algorithms.
The 6th International Colloquiium on The Scientific and fundamental aspects of GNSS/Galilelo, 2017
In this work we propose an algorithm for determining the attitude of a rigid body in a three dime... more In this work we propose an algorithm for determining the attitude of a rigid body in a three dimensional space. To do this, we use three L1 GPS sensors that receive signals from GNSS satellites. To test and verify our model we use a serial robotic manipulator, by changing the orientation of the manipulator's end effecter at predetermined rates with the rigid body attached along with the GPS sensors, we can verify our mathematical model. The data obtained shows that our model works very well. In this paper we discuss both the mathematical model as well as the experimental setup for model testing and verification, and present our results.
IEEE International Conference on Mechatronics and Automation (ICMA), 2018
In an attempt to solve the problem of finding a set of multiple unique modular robotic designs th... more In an attempt to solve the problem of finding a set of multiple unique modular robotic designs that can be constructed using a given repertoire of modules to perform a specific task, a novel synthesis framework is introduced based on design optimization concepts and evolutionary algorithms to search for the optimal solution. The discrete optimization procedure is based on the use of assembly incidence matrix to represent modular robotic designs. Fitness function is formulated for each task separately to incorporate task-specific performance evaluation criteria. The fitness of every design is measured in simulation. Solution evaluation can be carried out in parallel in order to reduce synthesis time, because evaluating a certain design is independent of evaluating other designs. The feasibility of this approach is demonstrated by several examples.
Robots are evolving from factory work-horses to be the robot-companions. The future of robots wil... more Robots are evolving from factory work-horses to be the robot-companions. The future of robots will be as companions in the workplace functioning as interactive salespeople. In order to support this transition, it is important to combine service-oriented architecture and robotics. Service-oriented architecture and cloud computing have become dominant computing paradigms and adding a RaaS (Robot as a Service) unit as a part of this system will help the companies manage and develop robots more efficiently. The major components of RaaS will be the integration of RMS (Robot Management System) and ROC (Robot Operation Center). As more and more robots are increasing in the service industry, the inter-robot communication is very critical. This communication can be achieved by ROC and the robots can be monitored remotely or locally via RMS. The RaaS platform will comply with all the standards of SOA (Service Oriented Architecture) like the development platform and execution unit, thereby creating a flexible and more development-friendly process.
29th International Conference on Robotics in Alpe-Adria-Danube Region (RAAD 2020), Futuroscope-Poitiers, 2020
This paper presents the methods of structural-parametric synthesis of a parallel manipulator with... more This paper presents the methods of structural-parametric synthesis of a parallel manipulator with three DOF (Degree of Freedom) working in a cylindrical coordinate system. This parallel manipulator belongs to the RoboMech class because it works under the setting laws of motions of the end-effector and actuators, which simplifies the control system and improves its dynamics. Parallel manipulators of a RoboMech class work with certain structural schemes and geometrical parameters of their links. The considered parallel manipulator is formed by connecting the output object to a base using one passive and two active closing kinematic chains. The geometrical parameters of their links are determined on the base of the least-square approximations.
The 15th IEEE Conference on Industrial Electronics and Applications (ICIEA 2020), 2020
MEMS devices are vulnerable to various defect sources, such as point stiction, broken-beams, etch... more MEMS devices are vulnerable to various defect sources, such as point stiction, broken-beams, etch variation. Point stiction is the defect in which the movable parts of the device is stuck to the substrate or fixed parts at one or multiple point locations. Point stictions may affect the yield as well as the reliability of MEMS devices. Fault simulation is an effective way to study how the point stiction defects will affect the device yield and reliability. For point stiction defects, the occurrence and the location are random and cannot be precisely predicted. Such stochastic behavior can be better predicted with the Monte Carlo simulation. Monte Carlo simulation is a stochastic technique used to approximate the probability of specific outcomes by running multiple trial simulations using random numbers and probability statistics. In this paper, the ANSYS Monte Carlo simulation is used to simulate point-stiction defects in surface-micromachined MEMS comb resonator devices. The yield of MEMS devices is estimated based on the simulation results. The fault simulation in MEMS devices is essential to optimize the device performance and to improve the yield and reliability of MEMS devices.
The 15th IEEE Conference on Industrial Electronics and Applications (ICIEA 2020), 2020
This work presents an Image-Based Visual Servoing (IBVS) technique for an autonomous drone to tra... more This work presents an Image-Based Visual Servoing (IBVS) technique for an autonomous drone to track and follow an object in 3D space using Image-Based Visual Servoing. Unlike implementing tracking mechanism using GPS positions, Radars or other high-level position determining devices, we present our approach in which we use an onboard camera that captures real-time video stream to processes information such that a given target in 3D space is tracked. We perform IBVS during the flight. A technique to use the video stream and locate the target is presented in this paper. Here we also discuss the mathematical model and system architecture of this technique on an autonomous drone. The advantage of this approach is that the tracking by drones can be made completely autonomous even in GPS-denied environments. We then walk through the applications and future scope of this methodology.
This paper introduces a novel neurophysiologically based mobile robot navigation system, which em... more This paper introduces a novel neurophysiologically based mobile robot navigation system, which emulates the dynamics of a rodent’s navigation and spatial awareness cells found in the hippocampus and entorhinal cortex. The model presented here replicates the functionality of these neurons in their hardware and software counterparts. By using data structures and computational logic that best utilizes currently available processing architectures, a cognitive map is created using a unique multimodal source model for place cell activation. Path planning is performed by using a combination of Euclidean distance path checking, goal memory, and the A∗ algorithm. Localization is accomplished using simple, low power sensors, such as a camera, ultrasonic sensors, motor encoders and a gyroscope. The place code data structures are initialized as the mobile robot finds goal locations and other unique locations, and are then linked as paths between goal locations, as goals are found during exploration. The place code creates a hybrid cognitive map of metric and topological data. In doing so, much less memory is needed to represent the robot’s roaming environment, as compared to traditional mapping methods, such as occupancy grids. A comparison of the memory and processing savings are presented, as well as to the functional similarities of our design to the rodent’s specialized navigation cells.
This paper surveys various applications of artificial evolution in the field of modular robots. E... more This paper surveys various applications of artificial evolution in the field of modular robots. Evolutionary robotics aims to design autonomous adaptive robots automatically that can evolve to accomplish a specific task while adapting to environmental changes. A number of studies have demonstrated the feasibility of evolutionary algorithms for generating robotic control and morphology. However, a huge challenge faced was how to manufacture these robots. Therefore, modular robots were employed to simplify robotic evolution and their implementation in real hardware. Consequently, more research work has emerged on using evolutionary computation to design modular robots rather than using traditional hand design approaches in order to avoid cognition bias. These techniques have the potential of developing adaptive robots that can achieve tasks not fully understood by human designers. Furthermore, evolutionary algorithms were studied to generate global modular robotic behaviors including; self-assembly, self-reconfiguration, self-repair, and self-reproduction. These characteristics allow modular robots to explore unstructured and hazardous environments. In order to accomplish the aforementioned evolutionary modular robotic promises, this paper reviews current research on evolutionary robotics and modular robots. The motivation behind this work is to identify the most promising methods that can lead to developing autonomous adaptive robotic systems that require the minimum task related knowledge on the designer side.
This paper presents a theory for the analytical determination of internal forces in the links of ... more This paper presents a theory for the analytical determination of internal forces in the links of planar linkage mechanisms and manipulators with statically determinate structures, considering the distributed dynamic loads. Linkage mechanisms and manipulators were divided into elements and joints. Discrete models were created for both the elements and the entire mechanism. The dynamic equations of equilibrium for the discrete model of the elements and the hinged and rigid joints, under the action of longitudinal and transverse distributed dynamic trapezoidal loads, were derived. In the dynamic equations of the equilibrium of the discrete model of the elements and joints, the connections between the components of the force vector in the calculated cross-sections and the geometric, physical, and kinematic characteristics of the element were established for its plane-parallel motion. According to the developed technique, programs were created in the Maple system, and animations of the motion of the mechanisms were produced. The links were constructed with the intensity of transverse- and longitudinal-distributed dynamic loads, bending moments, and shearing and normal forces, depending on the kinematic characteristics of the links
Using heterogeneous depth cameras and 3D scanners in 3D face verification causes variations in th... more Using heterogeneous depth cameras and 3D scanners in 3D face verification causes variations in the resolution of the 3D point clouds. To solve this issue, previous studies use 3D registration techniques. Out of these proposed techniques, detecting points of correspondence is proven to be an efficient method given that the data belongs to the same individual. However, if the data belongs to different persons, the registration algorithms can convert the 3D point cloud of one person to another, destroying the distinguishing features between the two point clouds. Another issue regarding the storage size of the point clouds. That is, if the captured depth image contains around 50 thousand points in the cloud for a single pose for one individual, then the storage size of the entire dataset will be in order of giga if not tera bytes. With these motivations, this work introduces a new technique for 3D point clouds generation using a neural modeling system to handle the differences caused by heterogeneous depth cameras, and to generate a new face canonical compact representation. The proposed system reduces the stored 3D dataset size, and if required, provides an accurate dataset regeneration. Furthermore, the system generates neural models for all gallery point clouds and stores these models to represent the faces in the recognition or verification processes. For the probe cloud to be verified, a new model is generated specifically for that particular cloud and is matched against pre-stored gallery model presentations to identify the query cloud. This work also introduces the utilization of Siamese deep neural network in 3D face verification using generated model representations as raw data for the deep network, and shows that the accuracy of the trained network is comparable all published results on Bosphorus dataset.
GNSS-based Attitude Determination (AD) of a mobile object using the readings of the Global Naviga... more GNSS-based Attitude Determination (AD) of a mobile object using the readings of the Global Navigation Satellite Systems (GNSS) is an active area of research. Numerous attitude determination methods have been developed lately by making use of various sensors. However, the last two decades have witnessed an accelerated growth in research related to GNSS-based navigational equipment as a reliable and competitive device for determining the attitude of any outdoor moving object using data demodulated from GNSS signals. Because of constantly increasing number of GNSS-based AD methods, algorithms, and techniques, introduced in scientific papers worldwide, the problem of choosing an appropriate approach, that is optimal for the given application, operational environment, and limited financial funding becomes quite a challenging task. The work presents an extensive literature survey of the methods mentioned above which are classified in many different categories. The main aim of this survey is to help researchers and developers in the field of GNSS applications to understand pros and cons of the current state of the art methods and their computational efficiency, the scope of use and accuracy of the angular determination.
This paper presents a theory for the analytical determination of internal forces in the links of ... more This paper presents a theory for the analytical determination of internal forces in the links of planar linkage mechanisms and manipulators with statically determinate structures, considering the distributed dynamic loads. Linkage mechanisms and manipulators were divided into elements and joints. Discrete models were created for both the elements and the entire mechanism. The dynamic equations of equilibrium for the discrete model of the elements and the hinged and rigid joints, under the action of longitudinal and transverse distributed dynamic trapezoidal loads, were derived. In the dynamic equations of the equilibrium of the discrete model of the elements and joints, the connections between the components of the force vector in the calculated cross-sections and the geometric, physical, and kinematic characteristics of the element were established for its plane-parallel motion. According to the developed technique, programs were created in the Maple system, and animations of the motion of the mechanisms were produced. The links were constructed with the intensity of transverse- and longitudinal-distributed dynamic loads, bending moments, and shearing and normal forces, depending on the kinematic characteristics of the links.
Eastern-European Journal of Enterprise Technologies, 2020
This paper presents the methods of structural-parametric synthesis and kinematic analysis of a pa... more This paper presents the methods of structural-parametric synthesis and kinematic analysis of a parallel manipulator with three degrees of freedom working in a cylindrical coordinate system. This parallel manipulator belongs to a RoboMech class because it works under the set laws of motions of the end-effector and actuators, which simplifies the control system and improves its dynamics. Parallel manipulators of a RoboMech class work with certain structural schemes and geometrical parameters of their links. The considered parallel manipulator is formed by connecting the output point to a base using one passive and two active closing kinematic chains (CKC). Passive CKC have zero degree of freedom and it does not impose a geometrical constraint on the movement of the output point, so the geometrical parameters of the links of the passive CKC are freely varied. Active CKCs have active kinematic pairs and they impose geometrical constraints on the movement of the output point. The geometrical parameters of the links of the active CKCs are determined on the basis of the approximation problems of the Chebyshev and least-square approximations. For this, the equations of geometrical constraints are derived in the forms of functions of weighted differences, which are presented in the forms of generalized (Chebyshev) polynomials. This leads to linear iterative problems.
The direct and inverse problems of the kinematics of the investigated parallel manipulator are solved. In the direct kinematics problem, the coordinates of the output point are determined by the given position of the input links. In the inverse kinematics problem, the positions of the input links are determined by the coordinates of the output point. The direct and inverse problems of the kinematics of the investigated parallel manipulator are reduced to solving problems on the positions of Sylvester dyads. Numerical results of structural-parametric synthesis and kinematic analysis of the considered parallel manipulator are presented. The numerical results of the kinematic analysis show that the maximum deviation of the movement of the output point from the orthogonal trajectories is 1.65 %
In this paper, the RISCWare framework is proposed as a robotic middleware for the modular design ... more In this paper, the RISCWare framework is proposed as a robotic middleware for the modular design of sensory modules, actua-tion platforms, and task descriptions. This framework will be used to customize robotic platforms by simply defining the available sensing devices, actuation platforms and required tasks. In addition , this framework will significantly increase the capability of robotic industries in the analysis, design, and development of autonomous mobile platforms. RISCWare is comprised of three modules. The first module encapsulates the sensors, which gather information about the remote or local environment. The second module defines the platforms, manipulators, and actuation methods. The last module describes the tasks that the ro-botic platforms will perform such as teleoperation, A. Elkady (B) · J. Joy · T. Sobh navigation, obstacle avoidance, manipulation, 3-D reconstruction, and map building. The objective is to design a middleware framework to allow a user to plug in new sensors, tasks or actuation hardware , resulting in a fully functional operational system. Furthermore, the user is able to install and uninstall hardware/software components through system lifetime with ease and modularity. In addition , when hardware devices are plugged into the framework, they are automatically detected by the middleware layer, which loads the appropriate software and avails the device for applications usage. This automatic detection and configuration of devices make it efficient and seamless for end users to add and use new devices and software applications. Several experiments, performed on the RISCbot II mobile robot, are implemented to evaluate the RISCWare framework with respect to applicability and resource utilization.
In this paper, the RISCWare framework is proposed as a robotic middleware for the modular design ... more In this paper, the RISCWare framework is proposed as a robotic middleware for the modular design of sensory modules, actua-tion platforms, and task descriptions. This framework will be used to customize robotic platforms by simply defining the available sensing devices, actuation platforms and required tasks. In addition , this framework will significantly increase the capability of robotic industries in the analysis, design, and development of autonomous mobile platforms. RISCWare is comprised of three modules. The first module encapsulates the sensors, which gather information about the remote or local environment. The second module defines the platforms, manipulators, and actuation methods. The last module describes the tasks that the ro-botic platforms will perform such as teleoperation, A. Elkady (B) · J. Joy · T. Sobh navigation, obstacle avoidance, manipulation, 3-D reconstruction, and map building. The objective is to design a middleware framework to allow a user to plug in new sensors, tasks or actuation hardware , resulting in a fully functional operational system. Furthermore, the user is able to install and uninstall hardware/software components through system lifetime with ease and modularity. In addition , when hardware devices are plugged into the framework, they are automatically detected by the middleware layer, which loads the appropriate software and avails the device for applications usage. This automatic detection and configuration of devices make it efficient and seamless for end users to add and use new devices and software applications. Several experiments, performed on the RISCbot II mobile robot, are implemented to evaluate the RISCWare framework with respect to applicability and resource utilization.
Systems Evolutionary robotics aims to automatically design autonomous adaptive morphological robo... more Systems Evolutionary robotics aims to automatically design autonomous adaptive morphological robots that can evolve to accomplish a specific task while adapting to environmental changes. Soft robotics have demonstrated the feasibility of evolutionary robotics for the synthesis of robots' control and morphology. The motivation of developing evolutionary soft computing techniques to that can generate task oriented structures for morphological robots makes the domain of soft-robotics worthy of serious investigation and research, and hence this article summarizes an important volume of research for a computational and software architecture perspective. This paper reviews the literature and discusses various aspects of evolutionary robotics including the application on morphological soft robots to allow self-assembly, self-reconfiguration, self-repair, and self-reproduction. Then, major milestones are outlined along with important morphological soft robotic prototypes due to their importance in the field. Finally, the current state of the art in the field is assessed.
Majority of the face recognition algorithms use query faces captured from uncontrolled, in the wi... more Majority of the face recognition algorithms use query faces captured from uncontrolled, in the wild, environment. Often caused by the cameras' limited capabilities, it is common for these captured facial images to be blurred or low resolution. Super resolution algorithms are therefore crucial in improving the resolution of such images especially when the image size is small requiring enlargement. This paper aims to demonstrate the effect of one of the state-of-the-art algorithms in the field of image super resolution. To demonstrate the func-tionality of the algorithm, various before and after 3D face alignment cases are provided using the images from the Labeled Faces in the Wild (lfw). Resulting images are subject to testing on a closed set face recognition protocol using unsu-pervised algorithms with high dimension extracted features. The inclusion of super resolution algorithm resulted in significant improved recognition rate over recently reported results obtained from unsupervised algorithms. Index Terms— Super-Resolution, high dimensions features , unsupervised learning, face recognition, label faces in the wild (lfw)
There has been a remarkable growth in many different real-time systems in the area of autonomous ... more There has been a remarkable growth in many different real-time systems in the area of autonomous mobile robots. This paper focuses on the collaboration of efficient multi-sensor systems to create new optimal motion planning for mobile robots. A proposed algorithm is used based on a new model to produce the shortest and most energy-efficient path from a given initial point to a goal point. The distance and time traveled, in addition to the consumed energy, have an asymptotic complexity of O(nlogn), where n is the number of obstacles. Real time experiments are performed to demonstrate the accuracy and energy efficiency of the proposed motion planning algorithm.
Robotics deals with the design, construction, operation, and application of robots, as well as co... more Robotics deals with the design, construction, operation, and application of robots, as well as computer systems for their control, sensory feedback, and information processing. This book brings together some of the latest research in robot applications, control, modeling, sensors and algorithms.
The 6th International Colloquiium on The Scientific and fundamental aspects of GNSS/Galilelo, 2017
In this work we propose an algorithm for determining the attitude of a rigid body in a three dime... more In this work we propose an algorithm for determining the attitude of a rigid body in a three dimensional space. To do this, we use three L1 GPS sensors that receive signals from GNSS satellites. To test and verify our model we use a serial robotic manipulator, by changing the orientation of the manipulator's end effecter at predetermined rates with the rigid body attached along with the GPS sensors, we can verify our mathematical model. The data obtained shows that our model works very well. In this paper we discuss both the mathematical model as well as the experimental setup for model testing and verification, and present our results.
IEEE International Conference on Mechatronics and Automation (ICMA), 2018
In an attempt to solve the problem of finding a set of multiple unique modular robotic designs th... more In an attempt to solve the problem of finding a set of multiple unique modular robotic designs that can be constructed using a given repertoire of modules to perform a specific task, a novel synthesis framework is introduced based on design optimization concepts and evolutionary algorithms to search for the optimal solution. The discrete optimization procedure is based on the use of assembly incidence matrix to represent modular robotic designs. Fitness function is formulated for each task separately to incorporate task-specific performance evaluation criteria. The fitness of every design is measured in simulation. Solution evaluation can be carried out in parallel in order to reduce synthesis time, because evaluating a certain design is independent of evaluating other designs. The feasibility of this approach is demonstrated by several examples.
Robots are evolving from factory work-horses to be the robot-companions. The future of robots wil... more Robots are evolving from factory work-horses to be the robot-companions. The future of robots will be as companions in the workplace functioning as interactive salespeople. In order to support this transition, it is important to combine service-oriented architecture and robotics. Service-oriented architecture and cloud computing have become dominant computing paradigms and adding a RaaS (Robot as a Service) unit as a part of this system will help the companies manage and develop robots more efficiently. The major components of RaaS will be the integration of RMS (Robot Management System) and ROC (Robot Operation Center). As more and more robots are increasing in the service industry, the inter-robot communication is very critical. This communication can be achieved by ROC and the robots can be monitored remotely or locally via RMS. The RaaS platform will comply with all the standards of SOA (Service Oriented Architecture) like the development platform and execution unit, thereby creating a flexible and more development-friendly process.
29th International Conference on Robotics in Alpe-Adria-Danube Region (RAAD 2020), Futuroscope-Poitiers, 2020
This paper presents the methods of structural-parametric synthesis of a parallel manipulator with... more This paper presents the methods of structural-parametric synthesis of a parallel manipulator with three DOF (Degree of Freedom) working in a cylindrical coordinate system. This parallel manipulator belongs to the RoboMech class because it works under the setting laws of motions of the end-effector and actuators, which simplifies the control system and improves its dynamics. Parallel manipulators of a RoboMech class work with certain structural schemes and geometrical parameters of their links. The considered parallel manipulator is formed by connecting the output object to a base using one passive and two active closing kinematic chains. The geometrical parameters of their links are determined on the base of the least-square approximations.
The 15th IEEE Conference on Industrial Electronics and Applications (ICIEA 2020), 2020
MEMS devices are vulnerable to various defect sources, such as point stiction, broken-beams, etch... more MEMS devices are vulnerable to various defect sources, such as point stiction, broken-beams, etch variation. Point stiction is the defect in which the movable parts of the device is stuck to the substrate or fixed parts at one or multiple point locations. Point stictions may affect the yield as well as the reliability of MEMS devices. Fault simulation is an effective way to study how the point stiction defects will affect the device yield and reliability. For point stiction defects, the occurrence and the location are random and cannot be precisely predicted. Such stochastic behavior can be better predicted with the Monte Carlo simulation. Monte Carlo simulation is a stochastic technique used to approximate the probability of specific outcomes by running multiple trial simulations using random numbers and probability statistics. In this paper, the ANSYS Monte Carlo simulation is used to simulate point-stiction defects in surface-micromachined MEMS comb resonator devices. The yield of MEMS devices is estimated based on the simulation results. The fault simulation in MEMS devices is essential to optimize the device performance and to improve the yield and reliability of MEMS devices.
The 15th IEEE Conference on Industrial Electronics and Applications (ICIEA 2020), 2020
This work presents an Image-Based Visual Servoing (IBVS) technique for an autonomous drone to tra... more This work presents an Image-Based Visual Servoing (IBVS) technique for an autonomous drone to track and follow an object in 3D space using Image-Based Visual Servoing. Unlike implementing tracking mechanism using GPS positions, Radars or other high-level position determining devices, we present our approach in which we use an onboard camera that captures real-time video stream to processes information such that a given target in 3D space is tracked. We perform IBVS during the flight. A technique to use the video stream and locate the target is presented in this paper. Here we also discuss the mathematical model and system architecture of this technique on an autonomous drone. The advantage of this approach is that the tracking by drones can be made completely autonomous even in GPS-denied environments. We then walk through the applications and future scope of this methodology.
This paper introduces a novel neurophysiologically based mobile robot navigation system, which em... more This paper introduces a novel neurophysiologically based mobile robot navigation system, which emulates the dynamics of a rodent’s navigation and spatial awareness cells found in the hippocampus and entorhinal cortex. The model presented here replicates the functionality of these neurons in their hardware and software counterparts. By using data structures and computational logic that best utilizes currently available processing architectures, a cognitive map is created using a unique multimodal source model for place cell activation. Path planning is performed by using a combination of Euclidean distance path checking, goal memory, and the A∗ algorithm. Localization is accomplished using simple, low power sensors, such as a camera, ultrasonic sensors, motor encoders and a gyroscope. The place code data structures are initialized as the mobile robot finds goal locations and other unique locations, and are then linked as paths between goal locations, as goals are found during exploration. The place code creates a hybrid cognitive map of metric and topological data. In doing so, much less memory is needed to represent the robot’s roaming environment, as compared to traditional mapping methods, such as occupancy grids. A comparison of the memory and processing savings are presented, as well as to the functional similarities of our design to the rodent’s specialized navigation cells.
This paper surveys various applications of artificial evolution in the field of modular robots. E... more This paper surveys various applications of artificial evolution in the field of modular robots. Evolutionary robotics aims to design autonomous adaptive robots automatically that can evolve to accomplish a specific task while adapting to environmental changes. A number of studies have demonstrated the feasibility of evolutionary algorithms for generating robotic control and morphology. However, a huge challenge faced was how to manufacture these robots. Therefore, modular robots were employed to simplify robotic evolution and their implementation in real hardware. Consequently, more research work has emerged on using evolutionary computation to design modular robots rather than using traditional hand design approaches in order to avoid cognition bias. These techniques have the potential of developing adaptive robots that can achieve tasks not fully understood by human designers. Furthermore, evolutionary algorithms were studied to generate global modular robotic behaviors including; self-assembly, self-reconfiguration, self-repair, and self-reproduction. These characteristics allow modular robots to explore unstructured and hazardous environments. In order to accomplish the aforementioned evolutionary modular robotic promises, this paper reviews current research on evolutionary robotics and modular robots. The motivation behind this work is to identify the most promising methods that can lead to developing autonomous adaptive robotic systems that require the minimum task related knowledge on the designer side.
This paper presents a theory for the analytical determination of internal forces in the links of ... more This paper presents a theory for the analytical determination of internal forces in the links of planar linkage mechanisms and manipulators with statically determinate structures, considering the distributed dynamic loads. Linkage mechanisms and manipulators were divided into elements and joints. Discrete models were created for both the elements and the entire mechanism. The dynamic equations of equilibrium for the discrete model of the elements and the hinged and rigid joints, under the action of longitudinal and transverse distributed dynamic trapezoidal loads, were derived. In the dynamic equations of the equilibrium of the discrete model of the elements and joints, the connections between the components of the force vector in the calculated cross-sections and the geometric, physical, and kinematic characteristics of the element were established for its plane-parallel motion. According to the developed technique, programs were created in the Maple system, and animations of the motion of the mechanisms were produced. The links were constructed with the intensity of transverse- and longitudinal-distributed dynamic loads, bending moments, and shearing and normal forces, depending on the kinematic characteristics of the links
Using heterogeneous depth cameras and 3D scanners in 3D face verification causes variations in th... more Using heterogeneous depth cameras and 3D scanners in 3D face verification causes variations in the resolution of the 3D point clouds. To solve this issue, previous studies use 3D registration techniques. Out of these proposed techniques, detecting points of correspondence is proven to be an efficient method given that the data belongs to the same individual. However, if the data belongs to different persons, the registration algorithms can convert the 3D point cloud of one person to another, destroying the distinguishing features between the two point clouds. Another issue regarding the storage size of the point clouds. That is, if the captured depth image contains around 50 thousand points in the cloud for a single pose for one individual, then the storage size of the entire dataset will be in order of giga if not tera bytes. With these motivations, this work introduces a new technique for 3D point clouds generation using a neural modeling system to handle the differences caused by heterogeneous depth cameras, and to generate a new face canonical compact representation. The proposed system reduces the stored 3D dataset size, and if required, provides an accurate dataset regeneration. Furthermore, the system generates neural models for all gallery point clouds and stores these models to represent the faces in the recognition or verification processes. For the probe cloud to be verified, a new model is generated specifically for that particular cloud and is matched against pre-stored gallery model presentations to identify the query cloud. This work also introduces the utilization of Siamese deep neural network in 3D face verification using generated model representations as raw data for the deep network, and shows that the accuracy of the trained network is comparable all published results on Bosphorus dataset.
GNSS-based Attitude Determination (AD) of a mobile object using the readings of the Global Naviga... more GNSS-based Attitude Determination (AD) of a mobile object using the readings of the Global Navigation Satellite Systems (GNSS) is an active area of research. Numerous attitude determination methods have been developed lately by making use of various sensors. However, the last two decades have witnessed an accelerated growth in research related to GNSS-based navigational equipment as a reliable and competitive device for determining the attitude of any outdoor moving object using data demodulated from GNSS signals. Because of constantly increasing number of GNSS-based AD methods, algorithms, and techniques, introduced in scientific papers worldwide, the problem of choosing an appropriate approach, that is optimal for the given application, operational environment, and limited financial funding becomes quite a challenging task. The work presents an extensive literature survey of the methods mentioned above which are classified in many different categories. The main aim of this survey is to help researchers and developers in the field of GNSS applications to understand pros and cons of the current state of the art methods and their computational efficiency, the scope of use and accuracy of the angular determination.
This paper presents a theory for the analytical determination of internal forces in the links of ... more This paper presents a theory for the analytical determination of internal forces in the links of planar linkage mechanisms and manipulators with statically determinate structures, considering the distributed dynamic loads. Linkage mechanisms and manipulators were divided into elements and joints. Discrete models were created for both the elements and the entire mechanism. The dynamic equations of equilibrium for the discrete model of the elements and the hinged and rigid joints, under the action of longitudinal and transverse distributed dynamic trapezoidal loads, were derived. In the dynamic equations of the equilibrium of the discrete model of the elements and joints, the connections between the components of the force vector in the calculated cross-sections and the geometric, physical, and kinematic characteristics of the element were established for its plane-parallel motion. According to the developed technique, programs were created in the Maple system, and animations of the motion of the mechanisms were produced. The links were constructed with the intensity of transverse- and longitudinal-distributed dynamic loads, bending moments, and shearing and normal forces, depending on the kinematic characteristics of the links.
Eastern-European Journal of Enterprise Technologies, 2020
This paper presents the methods of structural-parametric synthesis and kinematic analysis of a pa... more This paper presents the methods of structural-parametric synthesis and kinematic analysis of a parallel manipulator with three degrees of freedom working in a cylindrical coordinate system. This parallel manipulator belongs to a RoboMech class because it works under the set laws of motions of the end-effector and actuators, which simplifies the control system and improves its dynamics. Parallel manipulators of a RoboMech class work with certain structural schemes and geometrical parameters of their links. The considered parallel manipulator is formed by connecting the output point to a base using one passive and two active closing kinematic chains (CKC). Passive CKC have zero degree of freedom and it does not impose a geometrical constraint on the movement of the output point, so the geometrical parameters of the links of the passive CKC are freely varied. Active CKCs have active kinematic pairs and they impose geometrical constraints on the movement of the output point. The geometrical parameters of the links of the active CKCs are determined on the basis of the approximation problems of the Chebyshev and least-square approximations. For this, the equations of geometrical constraints are derived in the forms of functions of weighted differences, which are presented in the forms of generalized (Chebyshev) polynomials. This leads to linear iterative problems.
The direct and inverse problems of the kinematics of the investigated parallel manipulator are solved. In the direct kinematics problem, the coordinates of the output point are determined by the given position of the input links. In the inverse kinematics problem, the positions of the input links are determined by the coordinates of the output point. The direct and inverse problems of the kinematics of the investigated parallel manipulator are reduced to solving problems on the positions of Sylvester dyads. Numerical results of structural-parametric synthesis and kinematic analysis of the considered parallel manipulator are presented. The numerical results of the kinematic analysis show that the maximum deviation of the movement of the output point from the orthogonal trajectories is 1.65 %
In this paper, the RISCWare framework is proposed as a robotic middleware for the modular design ... more In this paper, the RISCWare framework is proposed as a robotic middleware for the modular design of sensory modules, actua-tion platforms, and task descriptions. This framework will be used to customize robotic platforms by simply defining the available sensing devices, actuation platforms and required tasks. In addition , this framework will significantly increase the capability of robotic industries in the analysis, design, and development of autonomous mobile platforms. RISCWare is comprised of three modules. The first module encapsulates the sensors, which gather information about the remote or local environment. The second module defines the platforms, manipulators, and actuation methods. The last module describes the tasks that the ro-botic platforms will perform such as teleoperation, A. Elkady (B) · J. Joy · T. Sobh navigation, obstacle avoidance, manipulation, 3-D reconstruction, and map building. The objective is to design a middleware framework to allow a user to plug in new sensors, tasks or actuation hardware , resulting in a fully functional operational system. Furthermore, the user is able to install and uninstall hardware/software components through system lifetime with ease and modularity. In addition , when hardware devices are plugged into the framework, they are automatically detected by the middleware layer, which loads the appropriate software and avails the device for applications usage. This automatic detection and configuration of devices make it efficient and seamless for end users to add and use new devices and software applications. Several experiments, performed on the RISCbot II mobile robot, are implemented to evaluate the RISCWare framework with respect to applicability and resource utilization.
In this paper, the RISCWare framework is proposed as a robotic middleware for the modular design ... more In this paper, the RISCWare framework is proposed as a robotic middleware for the modular design of sensory modules, actua-tion platforms, and task descriptions. This framework will be used to customize robotic platforms by simply defining the available sensing devices, actuation platforms and required tasks. In addition , this framework will significantly increase the capability of robotic industries in the analysis, design, and development of autonomous mobile platforms. RISCWare is comprised of three modules. The first module encapsulates the sensors, which gather information about the remote or local environment. The second module defines the platforms, manipulators, and actuation methods. The last module describes the tasks that the ro-botic platforms will perform such as teleoperation, A. Elkady (B) · J. Joy · T. Sobh navigation, obstacle avoidance, manipulation, 3-D reconstruction, and map building. The objective is to design a middleware framework to allow a user to plug in new sensors, tasks or actuation hardware , resulting in a fully functional operational system. Furthermore, the user is able to install and uninstall hardware/software components through system lifetime with ease and modularity. In addition , when hardware devices are plugged into the framework, they are automatically detected by the middleware layer, which loads the appropriate software and avails the device for applications usage. This automatic detection and configuration of devices make it efficient and seamless for end users to add and use new devices and software applications. Several experiments, performed on the RISCbot II mobile robot, are implemented to evaluate the RISCWare framework with respect to applicability and resource utilization.
Systems Evolutionary robotics aims to automatically design autonomous adaptive morphological robo... more Systems Evolutionary robotics aims to automatically design autonomous adaptive morphological robots that can evolve to accomplish a specific task while adapting to environmental changes. Soft robotics have demonstrated the feasibility of evolutionary robotics for the synthesis of robots' control and morphology. The motivation of developing evolutionary soft computing techniques to that can generate task oriented structures for morphological robots makes the domain of soft-robotics worthy of serious investigation and research, and hence this article summarizes an important volume of research for a computational and software architecture perspective. This paper reviews the literature and discusses various aspects of evolutionary robotics including the application on morphological soft robots to allow self-assembly, self-reconfiguration, self-repair, and self-reproduction. Then, major milestones are outlined along with important morphological soft robotic prototypes due to their importance in the field. Finally, the current state of the art in the field is assessed.
Majority of the face recognition algorithms use query faces captured from uncontrolled, in the wi... more Majority of the face recognition algorithms use query faces captured from uncontrolled, in the wild, environment. Often caused by the cameras' limited capabilities, it is common for these captured facial images to be blurred or low resolution. Super resolution algorithms are therefore crucial in improving the resolution of such images especially when the image size is small requiring enlargement. This paper aims to demonstrate the effect of one of the state-of-the-art algorithms in the field of image super resolution. To demonstrate the func-tionality of the algorithm, various before and after 3D face alignment cases are provided using the images from the Labeled Faces in the Wild (lfw). Resulting images are subject to testing on a closed set face recognition protocol using unsu-pervised algorithms with high dimension extracted features. The inclusion of super resolution algorithm resulted in significant improved recognition rate over recently reported results obtained from unsupervised algorithms. Index Terms— Super-Resolution, high dimensions features , unsupervised learning, face recognition, label faces in the wild (lfw)
There has been a remarkable growth in many different real-time systems in the area of autonomous ... more There has been a remarkable growth in many different real-time systems in the area of autonomous mobile robots. This paper focuses on the collaboration of efficient multi-sensor systems to create new optimal motion planning for mobile robots. A proposed algorithm is used based on a new model to produce the shortest and most energy-efficient path from a given initial point to a goal point. The distance and time traveled, in addition to the consumed energy, have an asymptotic complexity of O(nlogn), where n is the number of obstacles. Real time experiments are performed to demonstrate the accuracy and energy efficiency of the proposed motion planning algorithm.
–-This work presents the project of a mobile robot with an attached handler, programmed to collec... more –-This work presents the project of a mobile robot with an attached handler, programmed to collect small objects in the near area. The robot takes photos –is able to process a constant stream of images– of the surround area searching for objects, and goes to the nearest one to collect. After collecting, the robot has to put the object in a specified place. The robot will keep searching for objects and moving while on. The image processing job is to do a contrast between the floor color and the colors of the objects, and then the algorithm provides the location to move on. The project is built with a Raspberry Pi/Raspbian platform running a python program that uses the OpenCV library to process images and parameters used to guide the robot, a simple webcam that provides high resolution images, and the motors as final actuators to control the movement of the robot and the handler.
In this poster, we are designed and implemented an avoidance obstacle robot by using ROS (Robot o... more In this poster, we are designed and implemented an avoidance obstacle robot by using ROS (Robot operating system) as main platform. Neural Network algorithm has been used to program the robot. The algorithm has been written in Python programming language. In the hardware part, Arduino Uno Board with Ultra sonic sensor have been used to to detect the obstacles. Our contribution will be how to make the Robot detects the obstacle using neural network by learning himself from the environment and save that data which is getting by the ultra-sonic sensor to the base station so when it comes back to the same environment, the robot will not need to do the same procedure because the data already saved to the Base Station. All the related variables like Velocity, Acceleration and distance, etc. will get from ROS platform. The ROS will minimize the coding and gives us relative results. The communication between the robot and the base station will be wireless. Conclusion In conclusion, our team came up with a new modern robot to avoid the obstacles avoidance by using the new robotic platform (ROS) and our team enhances the time consumption to program the robot itself. In addition, our contribution will be how the robot will learn the environment with the neural network algorithm. Also, in this project, we reduced the time consumption for the programmer.
In this poster, we are designed and implemented an avoidance obstacle robot by using ROS (Robot o... more In this poster, we are designed and implemented an avoidance obstacle robot by using ROS (Robot operating system) as main platform. Neural Network algorithm has been used to program the robot. The algorithm has been written in Python programming language. In the hardware part, Arduino Uno Board with Ultra sonic sensor have been used to to detect the obstacles. Our contribution will be how to make the Robot detects the obstacle using neural network by learning himself from the environment and save that data which is getting by the ultra-sonic sensor to the base station so when it comes back to the same environment, the robot will not need to do the same procedure because the data already saved to the Base Station. All the related variables like Velocity, Acceleration and distance, etc. will get from ROS platform. The ROS will minimize the coding and gives us relative results. The communication between the robot and the base station will be wireless. Conclusion In conclusion, our team came up with a new modern robot to avoid the obstacles avoidance by using the new robotic platform (ROS) and our team enhances the time consumption to program the robot itself. In addition, our contribution will be how the robot will learn the environment with the neural network algorithm. Also, in this project, we reduced the time consumption for the programmer.
In theory, theory, theory,an autonomous autonomous autonomous mobile mobile robot’s robot’s robot... more In theory, theory, theory,an autonomous autonomous autonomous mobile mobile robot’s robot’s robot’s robot’s ability ability abilityto navigate navigate navigate navigate with greater greater intelligence intelligence and agility agility agilityin adynamicdynamic dynamicdynamic dynamicenvironment environment environmentenvironmentwould would be possible possible possiblepossible if its navigation navigation navigation system system was modeled after that of biological biological biological biologicalcreatures creatures creatures.More specifically, specifically,specifically, specifically, specifically,specifically,asystem system that mimics mimics thethe functionality functionality functionality functionality of neurobiological neurobiological neurobiological neurobiological neurobiologicalneurobiologicalnavigation navigation navigation and spatial spatial awareness awareness cells, cells, cells, as found foundin the hippocampus hippocampus hippocampus and entorhinal entorhinalentorhinal entorhinalcortex cortex of arodent’s rodent’s rodent’s brain (Fig .1).These These navigation navigation navigation navigation cells cells include include include :place placecells, cells, cells, head headheaddirection direction cells,cells, boundary boundary boundary cells, cells, cells, and grid cells cells cells,as wellwell wellas memory .Our mobile mobile robot, robot, known known knownas ratbot ,uses usesusesinspiration inspiration inspiration from place placecells cells cellsfor key locations, locations, locations, locations, locations,boundary boundary boundaryboundary cells cells cellsfor detecting detecting detecting significant significantsignificant significant errors in path pathintegration integration ,and grid gridcells cells cellsfor firing firing LEDs to aid aidin visual visual visual system debugdebug debug .These TheseThese three three cells cells cells(logic interpretation),interpretation), interpretation), are implemented implemented in afield programmable programmable programmable gate gate array (FPGA FPGA )silicon siliconchip, chip, to allow for parallel parallel search search .
In theory, an autonomous mobile robot’s ability to navigate with greater
intelligence and flexibi... more In theory, an autonomous mobile robot’s ability to navigate with greater intelligence and flexibility in a dynamic environment would be possible if its navigation system was modeled after that of biological creatures. More specifically, to create an agent that mimics neurobiological navigation cells and neural network connections as found in the hippocampus and entorhinal cortex of rodent brains (Fig. 1). These navigation cells are the: place cells, head direction cells, boundary cells, and grid cells, as well as memory. To navigate from one waypoint to another, our mobile robot, known as ratbot, uses inspiration from place cells and head direction cells for path integration. This is accomplished through use of vectors and vector mathematics. Additionally, the ratbot uses a field programmable gate array (FPGA) to emulate grid cell functionality for environment mapping and spatial cognition.
This paper proposes a novel framework for automatically designing feasible robots that are made u... more This paper proposes a novel framework for automatically designing feasible robots that are made up of various heterogeneous modules and raw materials already existing in the surrounding environment. Moreover, it highlights the interrelationship between the robot's morphology, control, and environment by analyzing the coevolution of morphology and control in robots and allowing the initial set of robots to use the available units in the environment to self-assemble, self-reconfigure, and self-repair. In addition, digital fabrication technologies such as 3D printing are utilized to produce new units if needed and available.
One of the limitations of the existing face recognition algorithms is that the recognition rate s... more One of the limitations of the existing face recognition algorithms is that the recognition rate significantly decreases with the increase in dataset size. In order to eliminate this shortcoming, this paper presents a new training dataset partitioning methodology to improve face recognition for large datasets. This methodology is then applied to the Eigenface algorithm as one of the algorithms that suffer from this problem. The algorithm represents the training face images as a fully connected graph. This graph is then divided into simpler sub-graphs to enhance the overall recognition rate. The sub-graphs are generated dynamically, and a comparison between different sub-graph selection techniques including minimizing edge weight sums, random selection, and maximizing sum of edge weights inside the sub-graph are provided. It is concluded that the optimized hierarchical dynamic technique increased the recognition rate by more than 40 percent in a large benchmark image dataset compared to the original single large graph method. Furthermore, the developed technique is compatible with several other unsupervised face recognition techniques such as ICA, KPCA, RBM, SIFT, and LBP... etc., and other datasets, specially if the number of images per person in the training data are low.
The goal of this work is the development of a
task-oriented software application that facilitates... more The goal of this work is the development of a task-oriented software application that facilitates the rapid deployment of multiple robotic agents. The task solutions are created at run-time and executed by the agents in a centralized or decentralized fashion. Tasks are divided into smaller subtasks which are then assigned to the optimal number of robots using Robot Utility Based Task Assignment (RUTA) algorithm. The system deploys these robots using its application program interfaces (API’s) and uploads programs that are integrated with a small routine code. The embedded routine allows robots to configure solutions when decentralized approach is adopted.
An efficient computation of 3D workspaces for redundant manipulators is based on a " hybrid" a!- ... more An efficient computation of 3D workspaces for redundant manipulators is based on a " hybrid" a!- gorithm between direct kinematics and screw theory. Direct kinematics enjoys low computational cost but needs edge detection algorithms when workspace boundaries are needed. Screw theory has exponential computational cost per workspace point but does not need edge detection. Screw theory allows computing workspace points in prespecified directions while direct kinematics does not. Applications of the algorithm are discussed.
We address the problem of observing a moving agent is addressed. A modeling approach for the visu... more We address the problem of observing a moving agent is addressed. A modeling approach for the visual system and its observer is advocated in which a discrete-event dynamic system (DEDS) framework is developed and events are defined as ranges on parameter subsets. In particular, a system for observing a process in which a robot hand manipulates an object is proposed. A stabilizing observer is constructed, and low-level modules are developed for recognizing the events that cause state transitions within the dynamic manipulation system. The work examines closely the possibilities for errors and uncertainties in the manipulation system, observer construction process, and event identification mechanisms. The system utilizes different tracking techniques to observe and recognize the task in an active, adaptive, and goal-directed manner
We address the problem of observing a moving agent. They advocate a modeling approach for the vis... more We address the problem of observing a moving agent. They advocate a modeling approach for the visual system and its observer, where a discrete event dynamic system framework is developed and events are defined as ranges on parameter subsets. A system for observing a manipulation process in which a robot hand manipulates an object is proposed. The hand/object interaction is recognized over time, and a stabilizing observer is constructed. Low-level modules are developed for recognizing the events that cause state transitions within the dynamic manipulation system. The work examines closely the possibilities for errors, mistakes, and uncertainties in the manipulation system, observer construction process, and even identification mechanisms. The system utilized different tracking techniques to observe and recognize the task in an active and goal-directed manner
CAD/CAM (Computer Aided Design/Manufacturing) typically involves the design and manufacture of a ... more CAD/CAM (Computer Aided Design/Manufacturing) typically involves the design and manufacture of a mechanical part. The problem of reverse engineering is to take an existing mechanical part as the point of departure and to produce a design, and perhaps a manufacturing process, for the part. We explore a new approach to reverse engineering and inspection applications. Discrete event dynamic systems (DEDS) are investigated as a new framework for guiding and controlling the active exploration and perception of mechanical parts. The dynamic recursive context for finite state machines (DRFSM) is introduced as a new DEDS tool for utilizing the recursive nature of the mechanical parts under consideration. The framework utilizes DRFSM DEDS for constructing a goal-directed autonomous observer for inspection and reverse engineering purposes. The developed techniques are then used to aid CAD pre-constructed models for inspection purposes and/or to develop models for subsequent manufacturing, thus, closing the sensing → modeling → manufacturing → inspection loop.
We address a perception framework for intelligent inspection and reverse engineering in this work... more We address a perception framework for intelligent inspection and reverse engineering in this work. In particular, we investigate the use of discrete event dynamic systems (DEDS) to guide the sensing of mechanical parts. We introduce dynamic recursive finite state machines (DRFSM) as a new DEDS tool for utilizing the recursive nature of the mechanical parts under consideration. The proposed framework uses DRFSM DEDS for constructing an observer for exploration and inspection purposes. We construct a sensing --+ CAD interface for the automatic reconstruction of parts from visual data. We also implement a graphical interface for designing DRFSM DEDS controllers.
We proposes a new design for inspection and reverse engineering environments. The authors have de... more We proposes a new design for inspection and reverse engineering environments. The authors have designed and experimented with such an environment for capturing sense data of mechanical parts in an intelligent way. They construct a sensing → CAD interface for the automatic reconstruction of parts from visual data. They briefly discuss the use of the dynamic recursive finite state machine (DRFSM) as a new discrete event dynamic system (DEDS) tool for controlling inspection and exploration. They also implement a graphical interface for designing DRFSM DEDS controllers
We address the problem of intelligent sensing in this work. In particular, we use discrete event ... more We address the problem of intelligent sensing in this work. In particular, we use discrete event dynamic systems (DEDS) to guide the sensing of mechanical parts for industrial inspection and reverse engineering
Developing an environment that enables optimal and flexible design of robot manipulators using re... more Developing an environment that enables optimal and flexible design of robot manipulators using reconfigurable links, joints, actuators, and sensors is an essential step for efficient robot design and prototyping. Such an environment should have the right “mix” of software and hardware components for designing the physical parts and the controllers, and for the algorithmic control of the robot modules (kinematics, inverse kinematics, dynamics, trajectory planning, analog control and digital computer control). Specifying object-based communications and catalog mechanisms between the software modules, controllers, physical parts, CAD designs, and actuator and sensor components is a necessary step in the prototyping activities. In this paper the authors propose a flexible prototyping environment for robot manipulators with the required subsystems and interfaces between the different components of this environment.
In this paper we will present the stages of designing and building a three-link robot manipulator... more In this paper we will present the stages of designing and building a three-link robot manipulator prototype that was built as part of a research project for establishing a prototyping environment for robot manipulators. Building this robot enabled us determine the required subsystems and interfaces to build the prototyping environment, and provided hands-on experience for the real problems and difficulties that we would like to address and solve using this environment. Also, this robot is used as an educational tool in robotics and control classes
In this work we present a control strategy under uncertainty for mobile robot navigation. In part... more In this work we present a control strategy under uncertainty for mobile robot navigation. In particular, we implement a server-client model, where the server executes the commands and the clients run in parallel, each performing its tasks. Tolerance analysis is performed to incorporate sensing uncertainties into the proposed model. The sensory system is depicted with a framework that allows different levels of data representation, based on the robust modeling of the sensing uncertainties. Keywords: Mobile Robots, Uncertainty Modeling, Distributed Control, Sensing. 1 Introduction In any closed-loop control system, sensors are used to provide the feedback information that represents the current status of the system and the environmental uncertainties.
Any sensory system can be viewed as a passive or dumb element which provides raw data. It can als... more Any sensory system can be viewed as a passive or dumb element which provides raw data. It can also be viewed as an intelligent element which returns “analyzed” information. Finally, it can be viewed as a commanding element which sends commands to the physical system. Each of these views is used in different situations and for different tasks. Commanding sensors are an extension to the logical sensor approach in which a mapping from events to actions is added to the sensor model. In a previous paper (1995), we proposed a sensor-based distributed control scheme for mobile robots along with several simulation results. In this paper, the application of this scheme to control a real mobile robot is presented and the results of several experiments are discussed. A server-client model is used to implement this scheme where the server is a process that carries out the commands to be executed, and each client is a process with a certain task. The logical sensor approach is used to model the sensory system which provides different levels of data representation with tolerance measures and analysis
This paper presents the methods of structural-parametric synthesis of a parallel manipulator with... more This paper presents the methods of structural-parametric synthesis of a parallel manipulator with three DOF (Degree of Freedom) working in a cylindrical coordinate system. This parallel manipulator belongs to the RoboMech class because it works under the setting laws of motions of the end-effector and actuators, which simplifies the control system and improves its dynamics. Parallel manipulators of a RoboMech class work with certain structural schemes and geometrical parameters of their links. The considered parallel manipulator is formed by connecting the output object to a base using one passive and two active closing kinematic chains. The geometrical parameters of their links are determined on the base of the least-square approximations.
The design of robotic manipulators is dictated by a set of pre-determined task descriptions and p... more The design of robotic manipulators is dictated by a set of pre-determined task descriptions and performance parameters. These performance parameters are often defined in terms of workspace dexterity, manipulability, and accuracy. Many serial manipulator applications require that the manipulator have full dexterity about a work piece or a pre-defined trajectory, that is, to approach the given point within the workspace with all possible orientations about that point. Grashof’s criterion defines the mobility of four-link closed chain mechanisms in relation to its link lengths. A simple assumption can convert a three-link serial manipulator into a four-link closed chain so that its mobility can be studied using Grashof’s criterion. With the help of Grashof’s criterion, it is possible not only to predict and simulate the mobility of a manipulator during its design, but also to map and identify the fully-dexterous regions within its workspace. Mapping of the dexterous workspace is helpful in efficient task placement and path planning. Next, the authors propose a simple algorithm using Grashof’s criterion for determining the optimal link lengths of a three-link manipulator, in order to achieve full dexterity at the desired regions of the workspace. Finally, the authors test the generated design by applying joint angle limitations.
Created by professors for professors, the Faculty Awards compendium is the first and only univers... more Created by professors for professors, the Faculty Awards compendium is the first and only university awards program in the United States based on faculty peer evaluations. The Faculty Awards series recognizes and rewards outstanding faculty members at colleges and universities across the United States. Voting was not open to students or the public at large.
With tens of thousands of educators participating, votes and comments were expertly tabulated and reviewed to present this honor and publish the list of recipients in the 2015 compendiums. This year's Volume 3 edition includes over 1,280 national award winners from over 554 U.S. colleges and universities within the disciplines of Engineering, Computer and Information Sciences and Science. Photos and winner descriptions are selectively included.
Created by professors for professors, the Faculty Awards compendium is the first and only univers... more Created by professors for professors, the Faculty Awards compendium is the first and only university awards program in the United States based on faculty peer evaluations. The Faculty Awards series recognizes and rewards outstanding faculty members at colleges and universities across the United States. Voting was not open to students or the public at large.
With tens of thousands of educators participating, votes and comments were expertly tabulated and reviewed to present this honor and publish the list of recipients in the 2015 compendiums. This year's Volume 2 edition includes almost 1,400 national award winners from over 730 U.S. colleges and universities within the disciplines of Health Sciences and Nursing, Medicine, Law, Public Affairs, Political & Policy Sciences, Business, Fine Arts and Education. Photos and winner descriptions are selectively included.
Created by professors for professors, the Faculty Awards compendium is the first and only univers... more Created by professors for professors, the Faculty Awards compendium is the first and only university awards program in the United States based on faculty peer evaluations. The Faculty Awards series recognizes and rewards outstanding faculty members at colleges and universities across the United States. Voting was not open to students or the public at large.
With tens of thousands of educators participating, votes and comments were expertly tabulated and reviewed to present this honor and publish the list of recipients in the 2015 compendiums. This year's Volume 1 edition includes 1,400 national award winners from over 500 U.S. colleges and universities within the disciplines of Liberal Arts, Social Sciences, and Humanities. Photos and winner descriptions are selectively included.
This book includes a set of rigorously reviewed world-class manuscripts addressing and detailing... more This book includes a set of rigorously reviewed world-class manuscripts addressing and detailing state-of-the-art research projects in the areas of Computer Science, Informatics, and Systems Sciences, and Engineering. It includes selected papers form the conference proceedings of the Ninth International Joint Conferences on Computer, Information, and Systems Sciences, and Engineering (CISSE 2013). Coverage includes topics in: Industrial Electronics, Technology & Automation, Telecommunications and Networking, Systems, Computing Sciences and Software Engineering, Engineering Education, Instructional Technology, Assessment, and E-learning.
• Provides the latest in a series of books growing out of the International Joint Conferences on Computer, Information, and Systems Sciences, and Engineering; • Includes chapters in the most advanced areas of Computing, Informatics, Systems Sciences, and Engineering; • Accessible to a wide range of readership, including professors, researchers, practitioners and students.
This book includes a set of rigorously reviewed world-class manuscripts addressing and detailing ... more This book includes a set of rigorously reviewed world-class manuscripts addressing and detailing state-of-the-art research projects in the areas of Computer Science, Informatics, and Systems Sciences, and Engineering. It includes selected papers from the conference proceedings of the Eighth and some selected papers of the Ninth International Joint Conferences on Computer, Information, and Systems Sciences, and Engineering (CISSE 2012 & CISSE 2013). Coverage includes topics in: Industrial Electronics, Technology & Automation, Telecommunications and Networking, Systems, Computing Sciences and Software Engineering, Engineering Education, Instructional Technology, Assessment, and E-learning.
· Provides the latest in a series of books growing out of the International Joint Conferences on Computer, Information, and Systems Sciences, and Engineering;
· Includes chapters in the most advanced areas of Computing, Informatics, Systems Sciences, and Engineering;
· Accessible to a wide range of readership, including professors, researchers, practitioners and students.
A system and method of face recognition comprising multiple phases implemented in a parallel arch... more A system and method of face recognition comprising multiple phases implemented in a parallel architecture. The first phase is a normalization phase whereby a captured image is normalized to the same size, orientation, and illumination of stored images in a preexisting database. The second phase is a feature extraction/distance matrix phase where a distance matrix is generated for the captured image. In a coarse recognition phase, the generated distance matrix is compared with distance matrices in the database using Euclidean distance matches to create candidate lists, and in a detailed recognition phase, multiple face recognition algorithms are applied to the candidate lists to produce a final result. The distance matrices in the normalized database may be broken into parallel lists for parallelization in the feature extraction/distance matrix phase, and the candidate lists may also be grouped according to a dissimilarity algorithm for parallel processing in the detailed recognition phase.
A system (100) for selling wares via a network connection, the system (100) comprising a server i... more A system (100) for selling wares via a network connection, the system (100) comprising a server interconnected to the network connection, a buyer profile database accessible by the server, the buyer profile database having stored thereon at least one buyer profile for use as a gateway to control entry to the system and to store buyer information, a seller profile database accessible by the server, the seller profile database having stored thereon at least one seller profile for storing seller information into a public portion and a private file, the seller information containing seller preferences, information about the seller's ware and seller administrative information, a web interface in communication with the server, the web interface accessible by a buyer and the web interface displaying the public portion of seller profile including information about seller's ware, a selection module coupled to the server, the selection module allows buyer to choose a ware listed on the public portion of seller profile through use of a user interface.
A real-time normalized, distributed exchange and barter system that allows multiple members to ex... more A real-time normalized, distributed exchange and barter system that allows multiple members to exchange multiple goods and services with other members of the system over a distributed network such as the Internet. The system may develop a plurality of permutations of trading cycles that allow for indirect exchanges between its members, with the option of using cash as an exchange element. The system may also develop permutations of trading cycles for sub-classes and sub-categories of the goods, services and exchange elements within the system, and choose an optimized set of trading cycles among the many trading-cycle permutations that cover the exchange system, based on criteria defined by the system's sponsor. The system may determine all possible cyclic permutations of exchanges between its members and select the cyclic permutation that best meets the defined criteria, also the system would be able to make suggestions or impersonate a user in order to close any open chains.
In this poster we described the hardware architecture of an inexpensive, heterogeneous, mobile ro... more In this poster we described the hardware architecture of an inexpensive, heterogeneous, mobile robot swarm, designed and developed at RISC lab, University of Bridgeport. Each UB robot swarm is equipped with sensors, actuators, control and communication units, power supply, and interconnection mechanism. Robot swarms have become a new research paradigm in the last ten years offering novel approaches, such as self-reconfigurabity, self-assembly, self-replication and self-learning. Developing a multi-agent robot system with heterogeneity and larger behavioral repertoire is a great challenge. This robot swarm is capable of performing user defined tasks such as wall painting, mapping, human rescue operations, task allocation, obstacle avoidance, and object transportation.
Disassembly sequence planning (DSP) is a nondeterministic polynomial time (NP) complete problem, ... more Disassembly sequence planning (DSP) is a nondeterministic polynomial time (NP) complete problem, making the utilization of metaheuristic approaches a viable alternative. DSP aims at creating efficient algorithms for deriving the optimum or near-optimum disassembly sequence for a given product or a product family. The problem-specific nature of such algorithms, however, requires these solutions to be validated, proving their versatility in accommodating substantial variations in the problem environment. To achieve this goal, this paper utilizes Taguchi’s orthogonal arrays to test the robustness of a previously-proposed Simulated Annealing (SA) algorithm. A comparison with an exhaustive search is also conducted to verify the efficiency of the algorithm in generating an optimum or near-optimum disassembly sequence for a given product. In order to further improve the solution, a distributed task allocation technique is also introduced into the model environment to accommodate multiple r...
2016 IEEE 14th International Workshop on Advanced Motion Control (AMC), 2016
The goal of this work is the development of a task-oriented software application that facilitates... more The goal of this work is the development of a task-oriented software application that facilitates the rapid deployment of multiple robotic agents. The task solutions are created at run-time and executed by the agents in a centralized or decentralized fashion. Tasks are divided into smaller subtasks which are then assigned to the optimal number of robots using Robot Utility Based Task Assignment (RUTA) algorithm. The system deploys these robots using its application program interfaces (API’s) and uploads programs that are integrated with a small routine code. The embedded routine allows robots to configure solutions when decentralized approach is adopted.
This paper presents the results of a comprehensive investigation of the current state of swarm ro... more This paper presents the results of a comprehensive investigation of the current state of swarm robotics research, organizing and classifying that research into a preliminary taxonomy. We aim to provide an analysis of existing swarm systems in an attempt to define the starting point of potential algorithms leading to the development of a new swarm system platform and software design.
In this paper, a universal quality inspection and quality control machine is presented. This mach... more In this paper, a universal quality inspection and quality control machine is presented. This machine is a fusion of different technologies such as vision system, programmable logic controller (PLC), Human machine interface (HMI) and Intelligent ROBO Actuators with other types of sensors. The electrical and mechanical design of the machine and plc program is illustrated in detail. Generally, inspection of raw materials or products at any stage in production or manufacturing or assembly industries may be done manually using measuring instruments, or by machines based on laser sensor technology, using probes, weighing scales, etc. Manual process is too slow and meant to test only few batches out of the entire lot which is less effective. Dedicated machines are usually confined to a single type of raw material considering specific property of the component. This option can be expensive when several different raw materials and product at any stage are to be tested at in-feed line. The proposed universal quality inspection machine is designed and implemented in the PLC lab at University of Bridgeport.
Uploads
articles by Tarek Sobh
The direct and inverse problems of the kinematics of the investigated parallel manipulator are solved. In the direct kinematics problem, the coordinates of the output point are determined by the given position of the input links. In the inverse kinematics problem, the positions of the input links are determined by the coordinates of the output point. The direct and inverse problems of the kinematics of the investigated parallel manipulator are reduced to solving problems on the positions of Sylvester dyads. Numerical results of structural-parametric synthesis and kinematic analysis of the considered parallel manipulator are presented. The numerical results of the kinematic analysis show that the maximum deviation of the movement of the output point from the orthogonal trajectories is 1.65 %
The direct and inverse problems of the kinematics of the investigated parallel manipulator are solved. In the direct kinematics problem, the coordinates of the output point are determined by the given position of the input links. In the inverse kinematics problem, the positions of the input links are determined by the coordinates of the output point. The direct and inverse problems of the kinematics of the investigated parallel manipulator are reduced to solving problems on the positions of Sylvester dyads. Numerical results of structural-parametric synthesis and kinematic analysis of the considered parallel manipulator are presented. The numerical results of the kinematic analysis show that the maximum deviation of the movement of the output point from the orthogonal trajectories is 1.65 %
intelligence and flexibility in a dynamic environment would be possible if its
navigation system was modeled after that of biological creatures. More
specifically, to create an agent that mimics neurobiological navigation cells and
neural network connections as found in the hippocampus and entorhinal
cortex of rodent brains (Fig. 1). These navigation cells are the: place cells,
head direction cells, boundary cells, and grid cells, as well as memory. To
navigate from one waypoint to another, our mobile robot, known as ratbot, uses
inspiration from place cells and head direction cells for path integration. This is accomplished through use of vectors and vector mathematics. Additionally, the ratbot uses a field programmable gate array (FPGA) to emulate grid cell functionality for environment mapping and spatial cognition.
task-oriented software application that facilitates the rapid
deployment of multiple robotic agents. The task solutions are
created at run-time and executed by the agents in a centralized
or decentralized fashion. Tasks are divided into smaller subtasks
which are then assigned to the optimal number of robots
using Robot Utility Based Task Assignment (RUTA) algorithm.
The system deploys these robots using its application program
interfaces (API’s) and uploads programs that are integrated
with a small routine code. The embedded routine allows robots
to configure solutions when decentralized approach is adopted.
parameters. These performance parameters are often defined in terms of workspace dexterity,
manipulability, and accuracy. Many serial manipulator applications require that the manipulator have
full dexterity about a work piece or a pre-defined trajectory, that is, to approach the given point within
the workspace with all possible orientations about that point. Grashof’s criterion defines the mobility
of four-link closed chain mechanisms in relation to its link lengths. A simple assumption can convert
a three-link serial manipulator into a four-link closed chain so that its mobility can be studied using
Grashof’s criterion. With the help of Grashof’s criterion, it is possible not only to predict and simulate
the mobility of a manipulator during its design, but also to map and identify the fully-dexterous regions
within its workspace. Mapping of the dexterous workspace is helpful in efficient task placement and path
planning. Next, the authors propose a simple algorithm using Grashof’s criterion for determining the
optimal link lengths of a three-link manipulator, in order to achieve full dexterity at the desired regions
of the workspace. Finally, the authors test the generated design by applying joint angle limitations.
With tens of thousands of educators participating, votes and comments were expertly tabulated and reviewed to present this honor and publish the list of recipients in the 2015 compendiums. This year's Volume 3 edition includes over 1,280 national award winners from over 554 U.S. colleges and universities within the disciplines of Engineering, Computer and Information Sciences and Science. Photos and winner descriptions are selectively included.
With tens of thousands of educators participating, votes and comments were expertly tabulated and reviewed to present this honor and publish the list of recipients in the 2015 compendiums. This year's Volume 2 edition includes almost 1,400 national award winners from over 730 U.S. colleges and universities within the disciplines of Health Sciences and Nursing, Medicine, Law, Public Affairs, Political & Policy Sciences, Business, Fine Arts and Education. Photos and winner descriptions are selectively included.
With tens of thousands of educators participating, votes and comments were expertly tabulated and reviewed to present this honor and publish the list of recipients in the 2015 compendiums. This year's Volume 1 edition includes 1,400 national award winners from over 500 U.S. colleges and universities within the disciplines of Liberal Arts, Social Sciences, and Humanities. Photos and winner descriptions are selectively included.
• Provides the latest in a series of books growing out of the International Joint Conferences on Computer, Information, and Systems Sciences, and Engineering;
• Includes chapters in the most advanced areas of Computing, Informatics, Systems Sciences, and Engineering;
• Accessible to a wide range of readership, including professors, researchers, practitioners and students.
· Provides the latest in a series of books growing out of the International Joint Conferences on Computer, Information, and Systems Sciences, and Engineering;
· Includes chapters in the most advanced areas of Computing, Informatics, Systems Sciences, and Engineering;
· Accessible to a wide range of readership, including professors, researchers, practitioners and students.
technologies such as vision system, programmable logic controller (PLC), Human machine interface (HMI) and
Intelligent ROBO Actuators with other types of sensors. The electrical and mechanical design of the machine and plc
program is illustrated in detail. Generally, inspection of raw materials or products at any stage in production or
manufacturing or assembly industries may be done manually using measuring instruments, or by machines based on
laser sensor technology, using probes, weighing scales, etc. Manual process is too slow and meant to test only few
batches out of the entire lot which is less effective. Dedicated machines are usually confined to a single type of raw
material considering specific property of the component. This option can be expensive when several different raw
materials and product at any stage are to be tested at in-feed line. The proposed universal quality inspection machine is
designed and implemented in the PLC lab at University of Bridgeport.