IAES International Journal of Robotics and Automation (IJRA)
Not a member yet
460 research outputs found
Sort by
A Novel Randomized Search Technique for Multiple Mobile Robot Paths Planning In Repetitive Dynamic Environment
No full textPresented article is studying the issue of path navigating for numerous robots. Our presented approach is based on both priority and the robust method for path finding in repetitive dynamic. Presented model can be generally implementable and useable: We do not assume any restriction regarding the quantity of levels of freedom for robots, and robots of diverse kinds can be applied at the same time. We proposed a random method and hill-climbing technique in the area based on precedence plans, which is used to determine a solution to a given trajectory planning problem and to make less the extent of total track. Our method plans trajectories for particular robots in the setting-time scope. Therefore, in order to specifying the interval of constant objects similar to other robots and the extent of the tracks which is traversed. For measuring the hazard for robots to conflict with each other it applied a method based on probability of the movements of robots. This algorithm applied to real robots with successful results. The proposed method performed and judged on both real robots and in simulation. We performed sequence of100tests with 8 robots for comparing with coordination method and current performances are effective. However, maximizing the performance is still possible. These performances estimations performed on Windows operating system and 3GHz Intel Pentium IV with and compiles with GCC 3.4. We used our PCGA robot for all experiments. For a large environment of 19×15m2where we accomplished 40tests, our model is competent to plan high-quality paths in a severely short time (less than a second). Moreover, this article utilized lookup tables to keep expenses the formerly navigated robots made, increasing the number of robots don’t expand computation time.DOI: http://dx.doi.org/10.11591/ijra.v1i4.126
Indoor Robot Localisation with Active RFID
Get PDFRadio Frequency Identification (RFID) is a technology of location determination and data capture. An RFID based system relies on the interaction between readers (also known as interrogator) and tags (transponders). Active RFID technology is suitable for tracking costly assets or moving objects such as mobile robots. Once affixed with RFID tags, a robot can be localised. However, there is a tendency for accuracy to vary greatly as well as delay in readings. Those problems may be enlarged in real time applications. This paper provides an overview of implementing RFID in precision tracking of mobile robots.DOI: http://dx.doi.org/10.11591/ijra.v1i3.48
Plant Watering Autonomous Mobile Robot
Get PDFNow days, due to busy routine life, people forget to water their plants. In this paper, we present a completely autonomous and a cost-effective system for watering indoor potted plants placed on an even surface. The system comprises of a mobile robot and a temperature-humidity sensing module. The system is fully adaptive to any environment and takes into account the watering needs of the plants using the temperature-humidity sensing module. The paper describes the hardware architecture of the fully automated watering system, which uses wireless communication to communicate between the mobile robot and the sensing module. This gardening robot is completely portable and is equipped with a Radio Frequency Identification (RFID) module, a microcontroller, an on-board water reservoir and an attached water pump. It is capable of sensing the watering needs of the plants, locating them and finally watering them autonomously without any human intervention. Mobilization of the robot to the potted plant is achieved by using a predefined path. For identification, an RFID tag is attached to each potted plant. The paper also discusses the detailed implementation of the system supported with complete circuitry. Finally, the paper concludes with system performance including the analysis of the water carrying capacity and time requirements to water a set of plants.DOI: http://dx.doi.org/10.11591/ijra.v1i3.130
GEMMP - A Google Maps Enabled Mobile Mission Planning Tool for Autonomous Underwater Vehicles
Get PDFMany applications for mobile robotics involve operations in remote, outdoor environments. In these environments, it can be difficult to plan missions dynamically due to the lack of portability of existing mission planning software. Mobile platforms allow access to the Web from nearly anywhere while other features, like touch interfaces, simplify user interaction, and GPS integration allows developers and users to take advantage to location-based services. In this paper, we describe a prototype AUV mission planner developed on the Android platform, created to aid and enhance the capability of an existing AUV mission planner, VectorMap, developed and maintained by OceanServer Technology, by taking advantage of the capabilities of existing mobile computing technology.DOI: http://dx.doi.org/10.11591/ijra.v1i2.35
Design and Analysis of a Multifingered Robot Hand
Get PDFWith the advent of new control techniques and development of microactuators, manipulator designers have gained inpetus todevelop manipulators and the related devicesthat is more flexible, responsive, smart and anthropomorphic.Taking cue from the work of a number of researchersover a couple of decades, the present work is a systematic attempt to develop a five fingered anthropomorphic robotic hand with 25 DoFs. The hand closely follows the anatomy of a typical human hand. The paper presents the structure of the proposed hand and its model for kinematic analysis. The kinematic analysis has been carried out using conventional method using MATLab software. The result obtained through the analysis confirmed that the robot hand conforms to the objective.DOI: http://dx.doi.org/10.11591/ijra.v1i2.36
Kinematic Modeling and Simulation of a 2-R Robot by Using Solid Works and Verification by MATLAB/Simulink
Get PDFSimulation of robot systems which is getting very popular, especially with the lowering cost of computers, can be used for layout evaluation, feasibility studies, presentations with animation and off-line programming. Object staging modelisation using robots holds, wether for the object or the robot, the following models: The geometric one, the kinematics one and the dynamic one. To do so, the modelisation of a 2-R robot type is being implemented. Comparing between two robot postures with the same trajectory (path) and for the same length of time and establishing a computing code to obtain the kinematic and dynamic parameters are the main tasks. SolidWorks and Matlab/Simulink softwares are used to check the theory and the robot motion simulation. The verification of the obtained results by both softwares allows us to, qualitatively evaluate ,underline the rightness of the chosen model and to get the right conclusions. The results of simulations were discussed. An agreement between the two softwares is certainly Obtained.DOI: http://dx.doi.org/10.11591/ijra.v1i2.35
Towards Behavior Control for Evolutionary Robot Based on RL with ENN
No full textThis paper proposes a behavior-switching control strategy of anevolutionary robotics based on Artificial NeuralNetwork (ANN) and Genetic Algorithms (GA). This method is able not only to construct thereinforcement learning models for autonomous robots and evolutionary robot modules thatcontrol behaviors and reinforcement learning environments, and but also to perform thebehavior-switching control and obstacle avoidance of an evolutionary robotics (ER) intime-varying environments with static and moving obstacles by combining ANN and GA.The experimental results on thebasic behaviors and behavior-switching control have demonstrated that ourmethod can perform the decision-making strategy and parameters set opimization ofFNN and GA by learning and can escape successfully from the trap of a localminima and avoid \emph{"motion deadlock" status} of humanoid soccer robotics agents,and reduce the oscillation of the planned trajectory betweenthe multiple obstacles by crossover and mutation. Some results of the proposed algorithmhave been successfully applied to our simulation humanoid robotics soccer team CIT3Dwhich won \emph{the 1st prize} of RoboCup Championship and ChinaOpen2010 (July 2010) and \emph{the place}of the official RoboCup World Championship on 5-11 July, 2011 in Istanbul, Turkey.As compared with the conventional behavior network and the adaptive behavior method,the genetic encoding complexity of our algorithm is simplified, and the networkperformance and the {\em convergence rate } have been greatlyimproved.DOI: http://dx.doi.org/10.11591/ijra.v1i1.25
Reduced Search Space Algorithm for Simultaneous Localization and Mapping in Mobile Robots
Get PDFIn this paper, we propose a new algorithm for simultaneous localization and mapping in mobile robots which uses evolutionary algorithm and particle swarm optimization. The proposed method is based on both local and global heuristic search methods. In each step of robot movements, the local search is applied in the small search space of odometry errors to improve the map accuracy. A global search method is applied for loop closing. The proposed algorithm detects loops and closes them, detects and solves correspondence and avoids local extremums. With a proper representation of problem parameters in chromosome, the dimensionality of search space is reduced. The proposed algorithm utilizes occupancy grid and does not require land marks which are not available in most natural environments. A new fitness function is proposed that is computationally efficient and eliminates the need for complex statistical calculations as used in current approaches. Results of experiments on real datasets exhibit the superior performance of the proposed method compared to the current methods.DOI: http://dx.doi.org/10.11591/ijra.v1i1.27
Design and Development of Vision Based Blockage Clearance Robot for Sewer Pipes
Get PDFRobotic technology is one of the advanced technologies, which is capable of completing tasks at situations where humans are unable to reach, see or survive. The underground sewer pipelines are the major tools for the transportation of effluent water. A lot of troubles caused by blockage in sewer pipe will lead to overflow of effluent water, sanitation problems. So robotic vehicle that is capable of traveling at underneath effluent water determining blockage using ultrasonic sensors and clearing by means of drilling mechanism is done. In addition to that wireless camera is fixed which acts as a robot vision by which we can monitor video and capture images using MATLAB tool. Thus in this project a prototype model of underground sewer pipe blockage clearance robot with drilling type will be developedDOI: http://dx.doi.org/10.11591/ijra.v1i1.19
Intelligent Vision System for Door Sensing Mobile Robot
Get PDFWheeled Mobile Robots find numerous applications in the Indoor man made structured environments. In order to operate effectively, the robots must be capable of sensing its surroundings. Computer Vision is one of the prime research areas directed towards achieving these sensing capabilities. In this paper, we present a Door Sensing Mobile Robot capable of navigating in the indoor environment. A robust and inexpensive approach for recognition and classification of the door, based on monocular vision system helps the mobile robot in decision making. To prove the efficacy of the algorithm we have designed and developed a ‘Differentially’ Driven Mobile Robot. A wall following behavior using Ultra Sonic range sensors is employed by the mobile robot for navigation in the corridors. Field Programmable Gate Arrays (FPGA) have been used for the implementation of PD Controller for wall following and PID Controller to control the speed of the Geared DC Motor.DOI: http://dx.doi.org/10.11591/ijra.v1i4.126