Search

Autonomous Ground Vehicles play a vital role in various industries, necessitating efficient route planning for mission success without human intervention. This study examines two metaheuristic optimization approaches, Genetic Algorithms and Ant Colony Optimization, within the context of route planning for these robotic entities. The comprehensive methodology utilizes the designs of these metaheuristic methods, and a comparative analysis is conducted through simulated experiments in diverse environments. Thefindings unveil that Genetic Algorithms excel in simple terrains; while Ant Colony Optimization demonstrates robust exploration capabilities in complex environments with obstacles and additional constraints. This underscores the importance of selecting the appropriate metaheuristic based on specific mission requirements and environmental conditions. The research furnishes insights to designers and operators, enabling informed decisions in route planning strategy selection, thereby enhancing the efficiency and safety of autonomous robotic operations across various scenarios. [ABSTRACT FROM AUTHOR]

Current mobile robotics applications within the framework of Industry 4.0 require the use of a network of robots to ensure communication between different robotic agents. According to some authors, there are challenges at the robot network level given that there are delays in data transmission due to the large flow of information and the noise that can occur. Therefore, there are different performance metrics that allow evaluating the performance of robots and the robot network, but when evaluating a robot network it is not clear which of the different metrics to use. This article proposes an evaluation of performance metrics based on a selection of characteristics, in order to support decision-making that allows selecting the most appropriate metrics according to the application. It is expected that with this solution, researchers will be able to select the metrics they require for the evaluation of robot networks in the framework of Industry 4.0. [ABSTRACT FROM AUTHOR]

Quadrature encoders are the most widely used sensors to measure the position, speed and acceleration of motors. For its proper functioning, it is required the implementation of decoding circuits based on the pulse count and the determination of the direction of rotation of the motor shaft, considering the efficient use of resources and the elimination of errors. Such circuits are usually implemented in microcontrollers-based or microprocessors-based platforms. However, FPGAs have characteristics that make them ideal for this type of application. In this work, a custom IP for the conditioning of four quadrature encoders is presented, which generates count values for each encoder on a time base that can be determined internally or externally and eliminate the errors that occur in the changes of the direction of rotation. The simulation results of the hardware description and its implementation in an FPGAbased mobile robot are presented. [ABSTRACT FROM AUTHOR]

In this paper an implementation of Robotic Operating System (ROS) on a mobile robot designed for human interaction and service is presented. The platform is designed using a digital system based on an Arduino Mega board and a Single Board Computer (SBC) Raspberry Pi in communication with a remote computer. The microcontroller board is used to perform all low-level operations over the hardware. It's established a serial communication between microcontroller and Raspberry Pi which is running various ROS packages to manipulate information. A Raspberry Pi camera it's connected to the SBC and the frames captured by the camera are sent to the remote computer for image processing using ROS and OpenCv; the response is generated on the remote computer in dependence of the image taken. The project gives the description of a layered distributed implementation of ROS in a mobile platform developed in Cuba in lower cost that many present on the market. [ABSTRACT FROM AUTHOR]

Due the worldwide growing food demand, efforts toward to resource optimization in crops, are required. With this purpose, the use of technology is a big chance to deal these challenges, with the aim of automatizing agricultural processes. Within the tasks in agriculture, by example wedding, supply fertilizers or fungicides, the mobile robots have a potential use to assist these tasks. Then, from this work, velocity control of a differential mobile platform is developed, in order to perform precision agriculture tasks. Specifically, mathematical modelling, design of state feedback control and the integration to the robot hardware, through Hardware in the loop (HIL) simulations, validation test are performed by using ROS environment, embedded devices and mathematical simulations, at previous stage to real test. Showing a full integration of the proposed system to test and prove mobile robots. [ABSTRACT FROM AUTHOR]

Introduction- This study assesses the five-performance metrics, available on the Emotive Insight device in a virtual toolpath tracking task through a mobile robot. Objective- Characterize and/or determine if some EEG metrics are related to primitives of a teleoperation task, where haptic feedback is provided, in order to verify if it can be useful to incorporate the information available from the Emotiv device in a shared control strategy. Methodology- An experimental design was formulated, which includes the recording and analysis of neurosigns in five users with a Brain Computer Interface (BCI), executing tasks of teleoperation of a mobile robot in the Environment of VREP (Virtual Robot Experimentation Platform). Results- The results show that engagement and relaxation are emotions that could be useful to identify demanding situations in tracking path and evasion of obstacles such as the experimental setup proposed in this article. On the other hand, it is observed that some metrics such as stress, excitement, interest and focus, on average, remain at similar levels during the task execution. Conclusions- Including brain computer interfaces of low-cost, such as the Emotiv in tasks with haptic feedback, offers new possibilities for assessment user performance and potential for control applications. [ABSTRACT FROM AUTHOR]

At present more adult persons need of mechatronic devices that facilitate and help them in his daily activities. The mobile robots turned into a good alternative due to the fact that nowadays the technology has allowed that they can recognize and make the tracking of a person. In this work, is used the Robotics platform Pionner 3- AT® and a sensor of depth Kinect® to making the tracking of a person. Sequences of images of depth and an algorithm of recognition of skeletons, supplied by the Kinect®, it allows to know and to estimate the coordinates and speed of a person, that to be introduced to the non-linear control based on linearization by feedback, it generates the command of linear and angular speed that will made that the robot keep an orientation and distance wished to a person. Finally, we introduce and argue the results achieved after carry out the validation of the algorithm with a series of experimental tests. [ABSTRACT FROM AUTHOR]

One of the most important task in the field of mobile robotics is obstacle detection. To solve this task, computer vision has been used often, especially monocular vision. This is due to the inherently complexity of stereo vision systems and the increasing development of the research that uses a single camera to detect obstacles. Computer vision and image processing algorithms for obstacles detection require multiple parameters that need to be adjusted to work efficiently according to the characteristics of the robot and the conditions of the environment in which it operates. In the present work, a method for the optimum selection of the parameters of this kind of algorithm for a certain environment is proposed. To achieve that, the obstacle detection problem was modeled as an optimization problem. Besides, an explanation of two of these algorithms based on monocular vision are given. These are used for the validation of the given method. For the solution of the given problem, obtained results with different metaheuristics are included. Finally, the obtained results from using these techniques in different environments are compared. [ABSTRACT FROM AUTHOR]

In this paper, a control architecture based on the reactive paradigm to solve the problem of autonomous navigation of mobile robots with limited computational capabilities and sensor system is presented. Stand out as the most significant contributions to this work, the encapsulation of a behavior-based control architecture in a programmable embedded system with limited processing capabilities and the use of fuzzy control theory in the implementation of a wall following behavior. Experimental tests were performed on a robotic platform equipped with three ultrasonic sensors and a wireless communication module. This module supports the 802.15.4 protocol in the ISM (Industrial, Scientific and Medical) band, through it sensory measures are transferred to a PC where computational representations of the explored environment are made. [ABSTRACT FROM AUTHOR]

This work deals with a new smooth path generation method for a mobile robot having a tricycle configuration. The method uses elementary and bi-elementary paths in order to create four kind of basic curves or paths. The proposed algorithm takes into account the real robot dimensions and can be applied for any initial and final orientation of the robot. The method generates a smooth path which is warranted to be very near of the original planning. [ABSTRACT FROM AUTHOR]

The problem of autonomous navigation of small mobile robots in indoors is addressed. The proposed solution incorporates a behavior-based control architecture implemented through fuzzy logic, and a hierarchical scheme for behaviors coordination. This combination was tested in a small mobile robotic platform that has a ring with SRF02 sonars and a MCF51QE128 microcontroller resulting in a safe navigation of the environment at a low computational cost. [ABSTRACT FROM AUTHOR]

This paper presents the development and implementation of a communication and coordination strategy among multiple mobile robotic devices, so that they can work together becoming a collaborative. This strategy will enable a group of several autonomous agents (mobile robots) to exhibit cooperative and/or coordinate behaviors, so that they can work both independently to achieve local objectives, as well as collectively to achieve overall objectives, exploring or modifying its operating environment. For the development of the proposed strategy, agents will be distributed taking into consideration a decentralized command configuration, so the integrated system can adapt dynamically to internal or external disturbances that may occur. For validation of the proposed strategy it will be used heterarchical command architecture (decentralized) in order to coordinate agents or holons with associate physical resources. The strategy discussed in this work will enable a collaborative system to automatically reconfigurate itself when a failure is detected, reallocating the activities and avoiding a total system restarting. [ABSTRACT FROM AUTHOR]

Due to the fact that the traffic accidents are one of the most relevant causes of deaths in the world, this article aims to expose the design of a System on a Chip (SoC) that has the capacity to recognize some transit signals, obstacles and white lines that delimit a road of a controlled scenery, giving a future prospect in order to implement automatic pilots in real automobiles for helping reduce accident rates. The SoC operates on an FPGA (Field Programmable Gate Array), so that the high speed processing algorithms are implemented in hardware and the low speed processing algorithms are implemented in software. Therefore different hardware modules were developed for video capturing, pre-processing images and controlling white balance in video capture. Also, software algorithms were designed, such as navigation, stereoscopy artificial vision and the intelligent recognition of the transit signals, shaping a set of processes administrated by a Real Time Operative System (RTOS). The SoC results were obtained through simulations in a robotic platform navigating on a road modeled on a small scale. [ABSTRACT FROM AUTHOR]

This paper presents the design and implementation of a low cost stereovision system for being used in mobile robots, which can estimate the distance at which objects are present in its field of vision. The location is achieved by means of an abstraction of a stereoscopic vision sensor to a sensor ring type, which will reduce the stereo information to coplanar distance readings as if it was a sonar. The vision system was used for navigating a mobile robot in a structured environment, using the techniques of reactive path planning and potential fields. The stereovision system implemented showed an average error of 5.34 cm in estimating distances, being tested as main sensor in the Pioneer 3DX robot in different environments under both structured and navigation strategies mentioned above. [ABSTRACT FROM AUTHOR]

A mobile robot (called UV-BOT) was designed at Universidad del Valle for robotics experimentation and can be employed for users with or without any previous knowledge on robotics. UV-BOT is a differential and for indoors-use-only robot; it has sensors for proximity, light detection, localization, and communications, and its speed is controlled by means of two PI controllers, one for each wheel. The robot's firmware was designed by using a real time micro-kernel, known as FreeRTOS, which supports three levels of complexity that have a set of functionalities from the standpoint of perception, mobility, communication, programming, and demos availability. These functionalities are employed by the user interface to program the robot graphically (basic level), using XML (intermediate level) or C (advanced level). At its advanced level, UV-BOT supports behavior oriented programming. Behaviors were used to carry out the performance tests for the mobile robot. As an outcome of these tests, it was found that the localization system of UV-BOT exhibits an average error of 17 cm. Homing (by position and light) and obstacle- avoidance behaviors exhibit average errors of 15 and 17 cm, respectively. In this way, tasks in cooperative robotics can be implemented successfully. [ABSTRACT FROM AUTHOR]

This paper described the problem of path-planning in mobile robots in a partially structured environment. The work was divided in three parts: design of a mechatronic system, denominated Robot IO, study of advantages and disadvantages of three path-planning algorithms: neural nets, genetic algorithms and fuzzy logic, and implementation of algorithms that allow to identify the workspace where IO moves. [ABSTRACT FROM AUTHOR]

A software system for simulation and control of mobile robots is presented, which allows hardware characteristic parametrization, sensors state visualization and to drive actuators (simulated or real). K++ uses an own programming language. Results from the programming of control algorithm are described. [ABSTRACT FROM AUTHOR]

this article shows the implementation process of a computer vision system for mobile Robots, which is based on a geometrical approximation of distance measurement and obstacle inclination. The system is mainly composed for a CCD camera, an image acquisition card, and a laser array, which projects two spot lights on to the obstacle. [ABSTRACT FROM AUTHOR]