Mohammad A. Jaradat

Autonomous mobile robot dynamic motion planning using hybrid fuzzy potential field

A new fuzzy-based potential field method is presented in this paper for autonomous mobile robot motion planning with dynamic environments including static or moving target and obstacles. Two fuzzy Mamdani and TSK models have been used to develop the total attractive and repulsive forces acting on the mobile robot. The attractive and repulsive forces were estimated using four inputs representing the relative position and velocity between the target and the robot in the x and y directions, in one hand, and between the obstacle and the robot, on the other hand. The proposed fuzzy potential field motion planning was investigated based on several conducted MATLAB simulation scenarios for robot motion planning within realistic dynamic environments. As it was noticed from these simulations that the proposed approach was able to provide the robot with collision-free path to softly land on the moving target and solve the local minimum problem within any stationary or dynamic environment compared to other potential field-based approaches.

A hybrid intelligent system for fault detection and sensor fusion

In this paper, an efficient new hybrid approach for multiple sensor fusion and fault detection is proposed, addressing the problem with multiple faults, which is based on conventional fuzzy soft clustering and artificial immune systems. For this new approach, requires no prior knowledge or information about the sensors, or the system behavior, and no learning processes are required. The proposed hybrid approach consists of two main phases. In the first phase a single fuser for the input sensor signals is generated using the fuzzy clustering c-means algorithm. The fused output is based on the cluster centers that contain the maximum number of the input elements. In the second phase a fault detector was generated base on the artificial immune system AIS.

Line map construction using a mobile robot with a sonar sensor

The objective of this study is to present a way to construct a line map of an unknown indoor environment using a mobile robot equipped with a single sonar sensor. The proposed procedure consists of two main steps. In the first step, the sonar sensor measurements from the robot surroundings are mapped into a two-dimensional occupancy grid map. In the second step, the Radon transform is used to extract the line parameters from the occupancy grid map. These parameters are subsequently used to represent the profiles of the detected objects as a representation of the robot environment. Applying a wall extension process to the resulting line map completes the process within the limits of resolution of the grid map. The presented experiments in this work have confirmed that the proposed line map construction approach is able to reconstruct the unknown indoor environment in spite of the uncertainty in sensor measurements

Integrated simulation platform for indoor quadrotor applications

In this paper, an integrated simulation platform is developed for indoor quadrotor applications. The simulation platform mainly consists of two subsystems, the controller subsystem; the other subsystem is an indoor interactive environment. The two integrated subsystems can be highly deployed in quadrotor systems development cycle and validation of different algorithms for indoor navigation. Moreover, the simulation platform has visualization capability and tuning flexibility. These features provide the necessary ability to implement and inspect the developed algorithm in different scenario conditions before implementing them for indoor applications.

Genetic-Fuzzy Sliding Mode Controller for a DC Servomotor system

A Genetic-Fuzzy Sliding Mode Controller is presented for DC Servomotor system control. The fuzzy logic controller was optimized by Genetic Algorithm method to reduce and eliminate the chattering phenomenon. To demonstrate the effectiveness of the presented approach, a comparison between the proposed system, and standard Sliding Mode controller were conducted. Simulation results have shown the advantages of choosing the proposed controller, to achieve the desired results, regardless of the external disturbance, the variation in system parameters, or the feedback noise.

Using a fuzzy Poka-Yoke based controller to restrain emissions in naturally ventilated environments

Gas poisoning as a result of fuel-burning inside confined environments claims the lives of many people worldwide. Gas poisoning treatment consists of administering oxygen therapy ranging from access to fresh air to breathing 100% oxygen by a tight fitting oxygen mask. Building on these facts, this article uses Poka-Yoke concepts to prevent, alert, and control the quality of air in naturally ventilated environments. The proposed controller ensures the access of victims to fresh air until help arrives. We target naturally ventilated indoor environments where no other ventilation approaches are installed. The proposed system utilizes fuzzy logic to control the speed and cycle time of two DC-motor-powered fans based on the levels of the oxides sensed by gas detectors. As a result, fresh air is allowed into the environment to replace the polluted air utilizing one fan set while hunted air is exhausted to the outdoors using the second fan set. The proposed system is simulated where obtained results for various scenarios confirm the many advantages of the system over natural ventilation.

Optimization of Intelligent Approach for Low-Cost INS/GPS Navigation System

Due to the inherent highly nonlinear vehicle state error dynamics obtained from low-cost inertial navigation system (INS) and Global Positioning System (GPS) along with the unknown statistical properties of these sensors, the optimality/accuracy of the classical Kalman filter for sensor fusion is not guaranteed. Therefore, in this paper, low-cost INS/GPS measurement integration is optimized based on different artificial intelligence (AI) techniques: Neural Networks (NN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) architectures. The proposed approaches are aimed at achieving high-accuracy vehicle state estimates. The architectures utilize overlapping windows for delayed input signals. Both the NN approaches and the ANFIS approaches are used once with overlapping position windows as the input and once with overlapping position and velocity windows as the input. Experimental tests are conducted to evaluate the performance of the proposed AI approaches. The achieved accuracy is presented and discussed. The study finds that using ANFIS, with both position and velocity as input, provides the best estimates of position and velocity in the navigation system. Therefore, the dynamic input delayed ANFIS approach is further analyzed at the end of the paper. The effect of the input window size on the accuracy of state estimation is also discussed.

Optimal PI-fuzzy logic controller of glucose concentration using genetic algorithm

In this paper, an optimal PI-fuzzy controller to regulate plasma glucose in Type1 diabetic patients is introduced. This controller is designed to mimic the functionality of β-cell in pancreas. Complete lack of insulin resulting from β-cell deficiency leads to a high blood glucose concentration or the so-called Type 1 diabetes. Patients having this disease need external insulin treatment to keep their blood glucose within normal ranges and to protect themselves from hyperglycemia risk. A miniaturized insulin infusion pump integrated with a continuous glucose sensor and driven by a closed-loop control algorithm can be implemented to create an artificial β-cell. For simulation purpose, the control algorithm needs a mathematical model representing the natural interaction between insulin and glucose. The up-to-date nonlinear delay differential model of glucose-insulin regulatory system, which represents the glucose-insulin metabolic system within the human body, is used as a reference and as a patient model. The controller parameters, which include membership functions and scaling parameters, are optimized by the genetic algorithm. Controller performance is evaluated thorough simulation studies and compared to that of the reference model. The results show that the plasma glucose and insulin ranges, average glucose value, and total amount of delivered insulin under the controller are very close to that of the reference model.

ADAPTIVE NEURO-FUZZY INFERENCE SYSTEM FOR AUTOMATIC SLEEP MULTISTAGE LEVEL SCORING EMPLOYING EEG, EOG, AND EMG EXTRACTED FEATURES

A new system for sleep multistage level scoring by employing extracted features from twenty five polysomnographic recording is presented. For the new system, an adaptive neuro-fuzzy inference system (ANFIS) is developed for each sleep stage. Initially, three types of electrophysiological signals including electroencephalogram (EEG), electrooculogram (EOG), and electromyogram (EMG) were collected from twenty five healthy subjects. The input pattern used for training the ANFIS subsystem is a set of extracted features based on the entropy measure which characterize the recorded signals. Finally an output selection subsystem is utilized to provide the appropriate sleep stage according to the ANFIS stage subsystems outputs. The developed system was able to provide an acceptable estimation for six sleep stages with an average accuracy of about 76.43% which confirmed its ability for multistage sleep level scoring based on the extracted features from the EEG, EOG and EMG signals compared to other approaches.

Optimal PID-Fuzzy Logic Controller for type 1 diabetic patients

In this paper, an optimal PID-FLC (Proportional Integral Derivative Fuzzy Logic Controller) is proposed. The design of this system aims to control blood glucose elevation in type 1 diabetic patients. An automated system integrated with a miniaturized insulin infusion pump and a continuous biosensor that measures the glucose level has been developed recently to replace beta cells in the pancreas. The main contribution of the paper is that it introduces an automated insulin delivery system based on a parallel PID-FLC structure tuned with genetic algorithms. This control system was compared to an optimal PIFLC and PD-FLC as well as a reference model. The results revealed that the controllers could maintain the glucose level within a normal range. In addition, the performance of the PIFLC and the PID-FLC was very close to that of beta cells in normal individuals. So, they can be exploited prosperously as control systems to manage blood glucose concentrations in Type 1 diabetic patients. In addition, the PID-FLC saved the amount of the daily delivered insulin, while, its performance was approximately the same as that of the PI-FLC.