Mariam Al-Sagban | American University of Sharjah (original) (raw)

Mariam Al-Sagban

Supervisors: Rached Dhaouadi

less

Uploads

Papers by Mariam Al-Sagban

Research paper thumbnail of Neural Based Autonomous Navigation of Wheeled Mobile Robots

This paper presents a novel reactive navigation algorithm for wheeled mobile robots under non-hol... more This paper presents a novel reactive navigation algorithm for wheeled mobile robots under non-holonomic constraints and in unknown environments. Two techniques are proposed: a geometrical based technique and a neural network based technique. The mobile robot travels to a pre-defined goal position safely and efficiently without any prior map of the environment by modulating its steering angle and turning radius. The dimensions and shape of the robot are incorporated to determine the set of all possible collision-free steering angles. The algorithm then selects the best steering angle candidate. In the geometrical navigation technique, a safe turning radius is computed based on an equation derived from the geometry of the problem. On the other hand, the neural-based technique aims to generate an optimized trajectory by using a user-defined objective function which minimizes the traveled distance to the goal position while avoiding obstacles. The experimental results demonstrate that the algorithms are capable of driving the robot safely across a variety of indoor environments.

Research paper thumbnail of Reactive Navigation Algorithm for Wheeled Mobile Robots under Non-Holonomic Constraints

—This paper presents a reactive navigation algorithm for wheeled mobile robot in an unknown envir... more —This paper presents a reactive navigation algorithm for wheeled mobile robot in an unknown environment populated by obstacles. The presented approach incorporates the dimensions and shape of the robot to determine the set of all possible collision-free steering angles. The steering angle that falls in the widest gap and is closest to the target is selected. The next stage in the algorithm takes into account the non-holonomic constraints of differentially steered robots by computing circular trajectories with adaptive radius of curvature. Actual experimental tests on a real mobile robot are presented. The results demonstrate the algorithm capabilities of driving a mobile robot safely through different obstacles arrangements.

Research paper thumbnail of Femto-Farad Capacitive Sensor for MEMS Thermal Actuators

—The objective of this paper is to develop a sensor to measure femto-Farad range capacitance obse... more —The objective of this paper is to develop a sensor to measure femto-Farad range capacitance observed in micro-electromechanical systems (MEMS). The sensor consists of a capacitance-to-voltage transducer and an ADALINE artificial neural network. The transducer is designed to produce an output highly sensitive to changes of the MEMS capacitance. The gain and phase of the output voltage is identified while training the neural network online.

Research paper thumbnail of AUTONOMOUS ROBOT NAVIGATION BASED ON RECURRENT NEURAL NETWORKS

The main objective of this research is to present a reactive navigation algorithm for wheeled mob... more The main objective of this research is to present a reactive navigation algorithm for wheeled mobile robots under non-holonomic constraints and in unknown environments. Two tech- niques are proposed: a geometrical based technique and a neural network based technique. The mobile robot travels to a pre-defined goal position safely and efficiently without any prior map of the environment by modulating its steering angle and turning radius. The dimensions and shape of the robot are incorporated to determine the set of all possible collision-free steering angles. The algorithm then selects the best steering angle candidate. In the geometrical navigation technique, a safe turning radius is computed based on an equation derived from the geometry of the problem. On the other hand, the neural-based technique aims to generate an optimized trajectory by using a user-defined objective func- tion which minimizes the traveled distance to the goal position while avoiding obstacles. A mobile robot is developed to test the performances of the two algorithms. The results demonstrate that the algorithms are capable of driving the robot safely across a variety of indoor environments.

Research paper thumbnail of Autonomous Robot Navigation based on Recurrent Neural Networks

Research paper thumbnail of Autonomous Mobile Robot Navigation ISMA2010

Research paper thumbnail of Brain computer interface as a forensic tool

Research paper thumbnail of Neural Based Autonomous Navigation of Wheeled Mobile Robots

This paper presents a novel reactive navigation algorithm for wheeled mobile robots under non-hol... more This paper presents a novel reactive navigation algorithm for wheeled mobile robots under non-holonomic constraints and in unknown environments. Two techniques are proposed: a geometrical based technique and a neural network based technique. The mobile robot travels to a pre-defined goal position safely and efficiently without any prior map of the environment by modulating its steering angle and turning radius. The dimensions and shape of the robot are incorporated to determine the set of all possible collision-free steering angles. The algorithm then selects the best steering angle candidate. In the geometrical navigation technique, a safe turning radius is computed based on an equation derived from the geometry of the problem. On the other hand, the neural-based technique aims to generate an optimized trajectory by using a user-defined objective function which minimizes the traveled distance to the goal position while avoiding obstacles. The experimental results demonstrate that the algorithms are capable of driving the robot safely across a variety of indoor environments.

Research paper thumbnail of Reactive Navigation Algorithm for Wheeled Mobile Robots under Non-Holonomic Constraints

—This paper presents a reactive navigation algorithm for wheeled mobile robot in an unknown envir... more —This paper presents a reactive navigation algorithm for wheeled mobile robot in an unknown environment populated by obstacles. The presented approach incorporates the dimensions and shape of the robot to determine the set of all possible collision-free steering angles. The steering angle that falls in the widest gap and is closest to the target is selected. The next stage in the algorithm takes into account the non-holonomic constraints of differentially steered robots by computing circular trajectories with adaptive radius of curvature. Actual experimental tests on a real mobile robot are presented. The results demonstrate the algorithm capabilities of driving a mobile robot safely through different obstacles arrangements.

Research paper thumbnail of Femto-Farad Capacitive Sensor for MEMS Thermal Actuators

—The objective of this paper is to develop a sensor to measure femto-Farad range capacitance obse... more —The objective of this paper is to develop a sensor to measure femto-Farad range capacitance observed in micro-electromechanical systems (MEMS). The sensor consists of a capacitance-to-voltage transducer and an ADALINE artificial neural network. The transducer is designed to produce an output highly sensitive to changes of the MEMS capacitance. The gain and phase of the output voltage is identified while training the neural network online.

Research paper thumbnail of AUTONOMOUS ROBOT NAVIGATION BASED ON RECURRENT NEURAL NETWORKS

The main objective of this research is to present a reactive navigation algorithm for wheeled mob... more The main objective of this research is to present a reactive navigation algorithm for wheeled mobile robots under non-holonomic constraints and in unknown environments. Two tech- niques are proposed: a geometrical based technique and a neural network based technique. The mobile robot travels to a pre-defined goal position safely and efficiently without any prior map of the environment by modulating its steering angle and turning radius. The dimensions and shape of the robot are incorporated to determine the set of all possible collision-free steering angles. The algorithm then selects the best steering angle candidate. In the geometrical navigation technique, a safe turning radius is computed based on an equation derived from the geometry of the problem. On the other hand, the neural-based technique aims to generate an optimized trajectory by using a user-defined objective func- tion which minimizes the traveled distance to the goal position while avoiding obstacles. A mobile robot is developed to test the performances of the two algorithms. The results demonstrate that the algorithms are capable of driving the robot safely across a variety of indoor environments.

Research paper thumbnail of Autonomous Robot Navigation based on Recurrent Neural Networks

Research paper thumbnail of Autonomous Mobile Robot Navigation ISMA2010

Research paper thumbnail of Brain computer interface as a forensic tool

Log In