IAES International Journal of Robotics and Automation (IJRA)
Not a member yet
460 research outputs found
Sort by
Research and Application on Fractional-Order Darwinian PSO Based Adaptive Extended Kalman Filtering Algorithm
Get PDFTo resolve the difficulty in establishing accurate priori noise model for the extended Kalman filtering algorithm, propose the fractional-order Darwinian particle swarm optimization (PSO) algorithm has been proposed and introduced into the fuzzy adaptive extended Kalman filtering algorithm. The natural selection method has been adopted to improve the standard particle swarm optimization algorithm, which enhanced the diversity of particles and avoided the premature. In addition, the fractional calculus has been used to improve the evolution speed of particles. The PSO algorithm after improved has been applied to train fuzzy adaptive extended Kalman filter and achieve the simultaneous localization and mapping. The simulation results have shown that compared with the geese particle swarm optimization training of fuzzy adaptive extended Kalman filter localization and mapping algorithm, has been greatly improved in terms of localization and mapping
RSMDP-based Robust Q-learning for Optimal Path Planning in a Dynamic Environment
Get PDFThis paper presents arobust Q-learning method for path planningin a dynamic environment. The method consists of three steps: first, a regime-switching Markov decision process (RSMDP) is formed to present the dynamic environment; second a probabilistic roadmap (PRM) is constructed, integrated with the RSMDP and stored as a graph whose nodes correspond to a collision-free world state for the robot; and third, an onlineQ-learning method with dynamic stepsize, which facilitates robust convergence of the Q-value iteration, is integrated with the PRM to determine an optimal path for reaching the goal. In this manner, the robot is able to use past experience for improving its performance in avoiding not only static obstacles but also moving obstacles, without knowing the nature of the obstacle motion. The use ofregime switching in the avoidance of obstacles with unknown motion is particularly innovative. The developed approach is applied to a homecare robot in computer simulation. The results show that the online path planner with Q-learning is able torapidly and successfully converge to the correct path
Global Tracking Control of Quadrotor VTOL Aircraft in Three-Dimensional Space
Get PDFThis paper presents a method to design controllers that force a quadrotor vertical take-off and landing (VTOL) aircraft to globally asymptotically track a reference trajectory in three-dimensional space. Motivated by the vehicle's steering practice, the roll and pitch angles are considered as immediate controls plus the total thrust force provided by the aircraft's four rotors to control the position and yaw angle of the aircraft. The control design is based on the newly introduced one-step ahead backstepping, the standard backstepping and Lyapunov's direct methods. A combination of Euler angles and unit-quaternion for the attitude representation of the aircraft is used to obtain global tracking control results. The paper also includes a design of observers that exponentially estimate the aircraft's linear velocity vector and disturbances. Simulations illustrate the results
Multisensor Data Fusion and Integration for Mobile Robots: A Review
Get PDFOne of the most important and useful feature of autonomous mobile robots is their ability to adopt themselves to operate in unstructured environment. Today robots are performing autonomously in industrial floor, office environments, as well as in crowded public places where the robots need to maintain their localization and mapping parameters.The basic requirement of an intelligent mobile robot is to develop and maintain localization and mapping parameters to complete the complex missions. In such situations, several difficulties arise in due to the inaccuracies and uncertainties in sensor measurements. Various techniques are there to handle such noises where the multisensor data fusion is not the exceptional one.From the last two decades, multisensor data fusions in mobile robots become a dominant paradigm due to its potential advantages like reduction in uncertainty, increase in accuracy and reliability and reduction of cost.This paper presents the reviews of autonomous mobile robots and role of multisenosr data fusion
Actual Flight Movements of Electric Helicopters for Making a Disaster Area Monitoring System
Get PDFThis paper describes the actual flight movements of electric helicopters and how to implement a disaster area monitoring system using electric ground vehicles and electric helicopters. A quad-rotor helicopter and a hex-rotor helicopter were used in the proposed system, specifically, the AR.Drone 2.0 and the DJI Innovations frame kit with an auto pilot system, respectively. We developed a software framework for the AR.Drone 2.0, which makes it possible to obtain flight data and images and to control automatic flight operations by computer. The relationship between the flight parameters and the real flight movements of the AR.Drone 2.0 were experimentally investigated. In conclusion, we found that the AR.Drone 2.0 with a software framework and a developed hex-rotor helicopter are sufficiently effective in implementing a disaster area monitoring system using electric ground vehicles and electric helicopters
A Low-Cost Smart Glove for Hand Functions Evaluation
Get PDFThis paper focuses on the development of a reliable, low cost, average size, light weight, simple, rugged, and compact design five fingers real time smart glove and a measurement hand gripper that emulate the human hand functions that can be used as a prototype model for hand rehabilitation systems for patients suffering from paralyze or contracture. The hand gripper device will move based on a human operator’s finger movement using the smart glove. Index, Middle, ring, and little fingers of the hand have a three degree of freedom, while the thumb finger has a two degree of freedom. All fingers are equipped with sensors for a smooth precise movement on a small scale with a perfect incision and without any vibration. This gripper is ideal for light objects. All the fingers have high speed motion and can be controlled individually and this gives the gripper ability to grasp complex shaped objects this work contains two PIC 18F452 microcontrollers for the instrumentation, communication and controlling applications. A series of flex sensors are built-in a master glove to get readings from the movement of human fingers. Microcontrollers will further use this information to control multiple servos that controls the movement of the slave hand
Dedicated Filter for Robust Occupancy Grid Mapping
Get PDFSensor based perception of the environment is an emerging area of the mobile robot research where sensors play a pivotal role. For autonomous mobile robots, the fundamental requirement is the convergent of the range information in to high level internal representation. Internal representation in the form of occupancy grid is commonly used in autonomous mobile robots due to its various advantages. There are several sensors such as vision sensor, laser rage finder, and ultrasonic and infrared sensors etc. play roles in mapping. However the sensor information failure, sensor inaccuracies, noise, and slow response are the major causes of an error in the mapping. To improve the reliability of the mobile robot mapping multisensory data fusion is considered as an optimal solution. This paper presents a novel architecture of sensor fusion frame work in which a dedicated filter (DF) is proposed to increase the robustness of the occupancy grid for indoor environment. The technique has been experimentally verified for different indoor test environments. The proposed configuration shows improvement in the occupancy grid with the implementation of dedicated filters
Dynamic Rocker-Bogie: A Stability Enhancement for High-Speed Traversal
Get PDFThe rocker-bogie suspension mechanism it’s currently NASA’s favored design for wheeled mobile robots, mainly because it has robust capabilities to deal with obstacles and because it uniformly distributes the payload over its 6 wheels at all times. Even though it has many advantages when dealing with obstacles, there is one major shortcoming which is its low average speed of operation, making the rocker-bogie system not suitable for situations where high-speed traversal over hard-flat surfaces is needed to cover large areas in short periods of time, mainly due to stability problems. This paper proposes to increase the stability of the rocker-bogie system by expanding its support polygon, making it more stable and adaptable while moving at high speed, but keeping its original robustness against obstacles: One rocker-bogie system, two modes of operation
A Neural Network Approach for Inverse Kinematic of a SCARA Manipulator
Get PDFInverse kinematic is one of the most interesting problems of industrial robot. The inverse kinematics problem in robotics is about the determination of joint angles for a desired Cartesian position of the end effector. It comprises of the computation need to find the joint angles for a given Cartesian position and orientation of the end effectors to control a robot arm. There is no unique solution for the inverse kinematics thus necessitating application of appropriate predictive models from the soft computing domain. Artificial neural network is one such technique which can be gainfully used to yield the acceptable results. This paper proposes a structured artificial neural network (ANN) model to find the inverse kinematics solution of a 4-dof SCARA manipulator. The ANN model used is a multi-layered perceptron neural network (MLPNN), wherein gradient descent type of learning rules is applied. An attempt has been made to find the best ANN configuration for the problem. It is found that multi-layered perceptron neural network gives minimum mean square error
Flexible Morphogenesis based Formation Control for Multi-Robot Systems
Get PDFInspired by how biological cells communicate with each other at a cell-to-cell level; morphogenesis emerged to be an effective way for local communication between homogenous robots in multi-robot systems. In this paper, we present the first steps towards a scalable morphogenesis style formation control technique, which address the drawbacks associated with current morphogenesis type formation control techniques, including their inability to distribute robots evenly across target shapes. A series of experiments, which demonstrate that the proposed technique enables groups of non-holonomic ground moving robots to generate formations in less than 9 seconds with three robots and less than 22 seconds with five robots, is also presented. These experiments furthermore reveal that the proposed technique enables groups of robots to generate formations without significantly increasing the total travel distance when faced with obstacles. This work is an important contribution to multi-robot control theory as history has shown that the success of groups often depends on efficient and robust formation control