Showing 5 results for Robot
M. Barati, A. R. Khoogar, M. Nasirian,
Volume 7, Issue 4 (12-2011)
Abstract
Abstract: Using robot manipulators for high accuracy applications require precise value of the kinematics parameters. Since measurement of kinematics parameters are usually associated with errors and accurate measurement of them is an expensive task, automatic calibration of robot link parameters makes the task of kinematics parameters determination much easier. In this paper a simple and easy to use algorithm is introduced for correction and calibration of robot kinematics parameters. Actually at several end-effecter positions, the joint variables are measured simultaneously. This information is then used in two different algorithms least square (LS) and Genetic algorithm (GA) for automatic calibration and correction of the kinematics parameters. This process was also tested experimentally via a three degree of freedom manipulator which is actually used as a coordinate measuring machine (CMM). The experimental Results prove that the Genetic algorithms are better for both parameter identification and calibration of link parameters.
S. Badalkhani, R. Havangi,
Volume 17, Issue 1 (3-2021)
Abstract
Even when simultaneous localization and mapping (SLAM) solutions have been broadly developed, the vast majority of them relate to a single robot performing measurements in static environments. Researches show that the performance of SLAM algorithms deteriorates under dynamic environments. In this paper, a multi-robot simultaneous localization and mapping (MR-SLAM) system is implemented within a dynamic environment. A probabilistic approach based on extended Kalman filter (EKF) is proposed to detect moving landmarks and consequently improve the performance of SLAM in dynamic environments. The expected landmark area (ELA) is introduced. This concept allows identifying and filtering the moving landmarks. Several experiments are performed varying the speed and number of moving landmarks within the environment to investigate the effect of dynamism level and landmark speed on. The root mean square error (RMSE) is used as a form of measuring the performance of the algorithm. Results show moving landmarks, degrade the performance of classical EKF-SLAM. However, the proposed method is robust to environmental changes and is less affected by the increasing speed of the moving landmarks.
Raheel Jawad, Rawaa Jawad,
Volume 20, Issue 3 (9-2024)
Abstract
Fire accidents are a disaster that can cause loss of life, property damage and permanent disability to the affected victim. Firefighting is a very important and dangerous job. Firefighters must extinguish the fire quickly and safely to prevent further damage and destruction. Detecting and extinguishing fires is a dangerous task that always puts the lives of firefighters at risk. One of the most effective tools for early fire extinguishing is the firefighting robot. Fire sensing in most industries is absolutely essential to prevent catastrophic losses. Robots with this type of embedded system can save the lives of engineers in industrial sites with hazardous conditions. This project aims to design and implement a solar-powered with artificial intelligent of mobile fire detection robot to detect fires in disaster-prone areas and thus reduce human work effort and level of destruction. Design a robot capable of moving using a rotary motor, finding a flame using a flame sensor, and extinguishing a fire using a water spray using a pump, all of which is controlled by an Arduino Uno microcontroller and programmed using an artificial intelligence (fuzzy) logic technology) using MATLAB, the inputs It has two variations:: flame and gas with three organic functions, each of which has a gas variable (low, medium, high), flame sensor (small, normal, large), and the output is a pump, (pump off , pump on ) with 9 rules. In addition to the experimental setup of the proposed system which demonstrates the performance of sensors (gas, flame) using fuzzy and implemented logic tools. The performance of the solar panels was first tested using MATLAB software as well as experimentally under different weather conditions. The pump's performance is being tested experimentally, and the robot is also being tested to detect and extinguish fires. The process of designing and implementing robotics involves creating mechanical and electrical systems. The results showed the effect of temperature change on the solar panel, as when it increases, the panel’s production capacity decreases, as well as the effect of decreased solar radiation resulting from clouds and other things, and the extent of its effect. Impact on the performance efficiency of solar panels, and observing the pump performance in terms of flow rate and height. Hence, it can be noted that the robot designed in the project is capable of discovering fire sources and extinguishing them using fire-fighting systems equipped with a water tank and a controllable pump to spray the water necessary for the process. From this study, can be concluded that the designed model is able to work according to its initial design with artificial intelligence with the least amount of errors, and therefore it can be applied in industrial applications, avoiding fire damage and extinguishing it when it occurs for the first time.
Robinson Jimenez-Moreno, Anny Astrid Espitia Cubillos, Esperanza Rodríguez Carmona,
Volume 20, Issue 4 (11-2024)
Abstract
This document presents the design of a virtual robotic system for the supervision of physical training exercises, to be carried out in a closed environment, which only requires a computer equipment with a web camera. To do this, deep learning algorithms such as convolutional networks and short- and long-term memory networks are used to recognize voice commands and the user's video actions. A predefined dialogue template is used to guide a user's training cycle based on the execution of the exercises: push-ups, abdominal, jump or squat. The contribution of the work focuses on the integration of deep learning techniques to design and personalize virtual robotic assistants for everyday task. The results show a high level of accuracy by the virtual robot both in understanding the audio and in predicting the exercise to be performed, with a final accuracy value of 97.75% and 100%, respectively.
Haniye Merrikhi, Hossein Ebrahimnezhad,
Volume 20, Issue 4 (11-2024)
Abstract
Robots have become integral to modern society, taking over both complex and routine human tasks. Recent advancements in depth camera technology have propelled computer vision-based robotics into a prominent field of research. Many robotic tasks—such as picking up, carrying, and utilizing tools or objects—begin with an initial grasping step. Vision-based grasping requires the precise identification of grasp locations on objects, making the segmentation of objects into meaningful components a crucial stage in robotic grasping. In this paper, we present a system designed to detect the graspable parts of objects for a specific task. Recognizing that everyday household items are typically grasped at certain sections for carrying, we created a database of these objects and their corresponding graspable parts. Building on the success of the Dynamic Graph CNN (DGCNN) network in segmenting object components, we enhanced this network to detect the graspable areas of objects. The enhanced network was trained on the compiled database, and the visual results, along with the obtained Intersection over Union (IoU) metrics, demonstrate its success in detecting graspable regions. It achieved a grand mean IoU (gmIoU) of 92.57% across all classes, outperforming established networks such as PointNet++ in part segmentation for this dataset. Furthermore, statistical analysis using analysis of variance (ANOVA) and T-test validates the superiority of our method.
