Siti Nurmaini

An embedded interval type-2 neuro-fuzzy controller for mobile robot navigation

This paper describes intelligent navigation using an embedded interval type-2 neuro-fuzzy controller. Weightless neural network (WNNs) strategy is used because fast learning, easy hardware implementation and well suited to microcontroller-based-real-time systems. The WNNs utilizes previous sensor data and analyzes the situation of the current environment and classifies geometric feature such as U-shape, corridor and left or right corner. The behavior of mobile robot is implemented by means of interval type-2 fuzzy control rules can be generated directly from the WNNs classifier. This functionality is demonstrated on a mobile robot using modular platform and containing several microcontrollers implies the implementation of a robust architecture. The proposed architecture implemented using low cost range sensor and low cost microprocessor. The experiment results show, using that technique the source code is efficient. The mobile robot can recognize the current environment and to be able successfully avoid obstacle in real time and achieve smother motion compare than logic function and fuzzy type-1 controller.

An Embedded Fuzzy Type-2 Controller Based Sensor Behavior for Mobile Robot

This paper presents a type-2 fuzzy logic controller that has been applied to a mobile robot utilizing eight ultrasonic sensors as distance sensors. The inputs are obtained from the mounted ultrasonic sensors and sent to a microchip PIC16F84 microcontroller onboard the robot. Furthermore the PIC16F84 analyses the inputs as data and provides the necessary control signal. The controller, which based on sensor behavior and consist of three tasks obstacle avoidance, wall following, and emergency condition was designed using AT89times55 microcontroller. The experiment result obtained demonstrate that the efficiency of type-2 fuzzy logic controller and performs better than on-off and type-1 fuzzy logic controller.

Environmental Recognition Using RAM-Network Based Type-2 Fuzzy Neural for Navigation of Mobile Robot

Reactive autonomous mobile robot navigating in real time environment is one of the most important requirements. Most of the systems have some common drawbacks such as, large computation, expensive equipment, hard implementation, and the complexity of the system. The work presented in this paper deals with a type-2 fuzzy-neural controller using RAM-based network to make navigation decisions. The proposed architecture can be implemented easily with low cost range sensor and low cost microprocessor. To minimize the execution time, we used a look-up table and that output stored into the robot RAM memory and becomes the current controller that drives the robot. This functionality is demonstrated on a mobile robot using a simple, 8 bit microcontroller with 512 bytes of RAM. The experiment results show that source code is efficient, works well, and the robot was able to successfully avoid obstacle in real time

Motion coordination for swarm robots

In this paper describes motion coordination of swarm robots using Interval Type-2 Fuzzy Logic Controller (IT2FLC). In this experiment utilize three identical robots with different color. Every robot has three infrared sensors, two gas sensors, 1 compass sensor and one X-Bee. A camera CCD in the roof of robot arena is utilized to determine the position of each robot with color detection methods. Swarm robots and camera are connected to a computer which serves as an information center. From the experimental results the IT2FL algorithm is able to control swarm robots coordination, produce smooth trajectory without collision.

Simple Pyramid RAM-Based Neural Network Architecture for Localization of Swarm Robots

The localization of multi-agents, such as people, animals, or robots, is a requirement to accomplish several tasks. Especially in the case of multi-robotic applications, localization is the process for determining the positions of robots and targets in an unknown environment. Many sensors like GPS, lasers, and cameras are utilized in the localization process. However, these sensors produce a large amount of computational resources to process complex algorithms, because the process requires environmental mapping. Currently, combination multi-robots or swarm robots and sensor networks, as mobile sensor nodes have been widely available in indoor and outdoor environments. They allow for a type of efficient global localization that demands a relatively low amount of computational resources and for the independence of specific environmental features. However, the inherent instability in the wireless signal does not allow for it to be directly used for very accurate position estimations and making difficulty associated with conducting the localization processes of swarm robotics system. Furthermore, these swarm systems are usually highly decentralized, which makes it hard to synthesize and access global maps, it can be decrease its flexibility. In this paper, a simple pyramid RAM-based Neural Network architecture is proposed to improve the localization process of mobile sensor nodes in indoor environments. Our approach uses the capabilities of learning and generalization to reduce the effect of incorrect information and increases the accuracy of the agents position. The results show that by using simple pyramid RAM-base Neural Network approach, produces low computational resources, a fast response for processing every changing in environmental situation and mobile sensor nodes have the ability to finish several tasks especially in localization processes in real time.

A new control architecture in mobile robot navigation based on IT2neuro-fuzzy controller

Autonomous mobile robots navigating in changing and unknown environments need to cope with large amounts of uncertainties that are inherent in natural environments. Most of the controllers have some common drawbacks such as, large computation, expensive equipment, hard implementation, and the complexity of the system. In this paper, novel controller architecture is introduced based on interval type-2 fuzzy logic controller (IT2FLC) and weightless neural network (WNNs) classifier named interval type-2 neuro-fuzzy controller (IT2NFC) that is embedded on mobile robot. The proposed control architecture can be implemented easily with low cost range sensor and low cost microprocessor. The work presented deals with a WNNs is used to make environmental recognition and IT2FLC to make navigation decisions. Various experiments is performed use IT2NFC compared to logic function, type-1 fuzzy logic controller (T1FLC) and type-1 neuro-fuzzy controller (T1NFC). The result shows that IT2NFC achieved good performance that has outperformed its type-1 counterpart in terms of reliability and obstacle collisions in several environment conditions.

Low-cost robotic sensor networks platform for air quality monitoring

Building robotic sensor networks (RSNs) for air quality monitoring application is a challenging frontier for robotic research. Such systems must operate for extend-ed periods of time in unstructured and complex domains. The implementation requires addressing numerous issues at the systems level such as energy efficiency, planning, and controlling robots’ trajectories for achieving robust operation. Hence developing new algorithms is needed to overcome various issues in sensor networks, multi-robots, and multi-sensors system. In this paper, initial experiments towards air quality monitoring using RSNs are proposed. Multi low-cost mobile robots were set up as prototype RSNs for measuring temperature, humidity, and CO/CO2 gas concentration in urban environments.

Cooperative searching strategy for swarm robot

This paper represents a cooperative searching strategy of swarm robot in finding and localizing odor source. 3 robots, namely: Cyborg G11, Cyborg G12, and Cyborg G13 were used as agents that form the swarm in this research. The cooperation among the robots trough communication has shown the success of the swarm in odor searching. When one of the agents in swarm robot detected a high concentration of odor in its place, it will use the data of this concentration as its own information in order to decide what position it should go. Moreover, this data was also shared to the other robot trough wireless communication such that they can compare their own data with the data shared to them. By having the information, each agent can decide what solution they should take. The experimental work in this research shows that using communication among the robot can support the robots in searching and finding the odor source.

Formation control of leader-follower robot using interval type-2 fuzzy logic controller

This paper proposes formation control in leader-follower robot using interval type-2 fuzzy logic controller (IT2FLC). The controller gives the robots position and orientation between desire pose and actual pose. The IT2FLC is advantageous in comparison with type-1 fuzzy logic controller (T1FLC). Experimental result show by using IT2FLC produce good performance compare to T1FLC. In open space environment, produce small data only 836 for fuzzy process, fast response about 107.8 and smooth movement of the leader-follower posture to accomplish the target without collision.

Formation control design for real swarm robot using fuzzy logic

This paper presents is to design swarm formation control using behavior-based for real robots. Its consists of two behavior are avoiding obstacles and formation keeping. During formation, the robots are also desired to coordinate among themselves to avoid collisions and keep formation the desired distance between each other. This design is using Fuzzy Logic Controller System. In this work a fuzzy logic controller has been used successfully in control system for the obstacle avoidance and formation keeping.