Yadira Quiñonez

Response threshold models and stochastic learning automata for self-coordination of heterogeneous multi-task distribution in multi-robot systems

This paper focuses on the general problem of coordinating multiple robots. More specifically, it addresses the self-selection of heterogeneous specialized tasks by autonomous robots. In this paper we focus on a specifically distributed or decentralized approach as we are particularly interested in a decentralized solution where the robots themselves autonomously and in an individual manner, are responsible for selecting a particular task so that all the existing tasks are optimally distributed and executed. In this regard, we have established an experimental scenario to solve the corresponding multi-task distribution problem and we propose a solution using two different approaches by applying Response Threshold Models as well as Learning Automata-based probabilistic algorithms. We have evaluated the robustness of the algorithms, perturbing the number of pending loads to simulate the robot’s error in estimating the real number of pending tasks and also the dynamic generation of loads through time. The paper ends with a critical discussion of experimental results.

Self-organizing techniques to improve the decentralized multi-task distribution in multi-robot systems

This paper focuses on the general problem of coordinating multiple robots, in particular, addresses the problem of the distribution of heterogeneous multi-task in a robust and efficient manner. The main interest in these systems is to understand how from simple rules inspired by the division of labor in social insects, a group of robots can perform tasks in an organized and coordinated way. We take into account a specifically distributed or decentralized approach as we are particularly interested in experimenting with truly autonomous and decentralized techniques in which the robots themselves are responsible for choosing a particular task in an autonomous and individual way. Under this approach we can speak of multi-task selection instead of multi-task assignment, which means, that the agents or robots select the tasks instead of being assigned a task by a central controller. In this regard, we have established an experimental scenario to solve the corresponding multi-task distribution problem and we propose a solution using different approaches by applying the response threshold models inspired by division of labor in social insects, the application of the reinforcement learning algorithm based on learning automata theory and ant colony optimization-based deterministic algorithms. We have evaluated the robustness of the algorithms, perturbing the number of pending loads to simulate the robot?s error in estimating the real number of pending tasks and also the dynamic generation of loads through time. The paper ends with a critical discussion of experimental results.

Stochastic learning automata for self-coordination in heterogeneous multi-tasks selection in multi-robot systems

This paper focuses on the general problem of coordinating multiple robots. More specifically, it addresses the self-election of heterogeneous specialized tasks by autonomous robots, as opposed to the usual multi-tasks allocation problem in multi-robot systems in which an external controller distributes the existing tasks among the individual robots. In this work we are considering a specifically distributed or decentralized approach in which we are particularly interested on decentralized solution where the robots themselves autonomously and in an individual manner, are responsible of selecting a particular task so that all the existing tasks are optimally distributed and executed. In this regard, we have established an experimental scenario and we propose a solution through automata learning-based probabilistic algorithm, to solve the corresponding multi-tasks distribution problem. The paper ends with a critical discussion of experimental results.

Cooperative and Competitive Behaviors in a Multi-robot System for Surveillance Tasks

In this paper we present a control architecture for multi-robot systems in dynamic environments, where the low level behaviors are obtained through artificial neural networks and evolutionary algorithms to achieve collaborative behaviors in a multi-robot system. As an example, we have cooperative tasks establishing a surveillance scenario stressing cooperation and competition between them.

Bio-inspired decentralized self-coordination algorithms for multi-heterogeneous specialized tasks distribution in multi-robot systems

This paper focuses on the general problem of coordinating multiple robots. More specifically, it addresses the self-election of heterogeneous specialized tasks by autonomous robots, as opposed to the usual multi-tasks allocation problem in multi-robot systems in which an external controller distributes the existing tasks among the individual robots. We are rather interested on decentralized solutions in which the robots themselves, autonomously and in an individual manner, select a particular task so that all the existing tasks are optimally distributed and executed. In this regard, we establish an experimental scenario and we propose a bio-inspired solution based on threshold models to solve the corresponding multi-tasks distribution problem. The paper ends with a critical discussion of the experimental results.

Autonomous Robot Navigation Based on Pattern Recognition Techniques and Artificial Neural Networks

The autonomous navigation of robots is one of the main problems among the robots due to its complexity and dynamism as it depends on environmental conditions as the interaction between themselves, persons or any unannounced change in the environment. Pattern recognition has become an interesting research line in the area of robotics and computer vision, however, the problem of perception extends beyond that of classification, main idea is training a specified structure to perform the classifying a given pattern. In this work, we have proposed the application of pattern recognition techniques and neural networks with back propagation learning procedure for the autonomous robots navigation. The objective of this work is to achieve that a robot is capable of performing a path in an unknown environment, through pattern recognition identifying four classes that indicate what action to perform, and then, a dataset with 400 images that were randomly divided with 70% for the training process, 15% for validation and 15% for the test is generated to train by neural network with different configurations. This purpose ROS and robot TurtleBot 2 are used. The paper ends with a critical discussion of the experimental results.

Decentralized multi-tasks distribution in heterogeneous robot teams by means of ant colony optimization and learning automata

This paper focuses on the general problem of coordinating multiple robots. More specifically, it addresses the self-election of heterogeneous specialized tasks by autonomous robots. In this paper we focus on a specifically distributed or decentralized approach as we are particularly interested on decentralized solution where the robots themselves autonomously and in an individual manner, are responsible of selecting a particular task so that all the existing tasks are optimally distributed and executed. In this regard, we have established an experimental scenario to solve the corresponding multi-tasks distribution problem and we propose a solution using two different approaches by applying Ant Colony Optimization-based deterministic algorithms as well as Learning Automata-based probabilistic algorithms. We have evaluated the robustness of the algorithm, perturbing the number of pending loads to simulate the robots error in estimating the real number of pending tasks and also the dynamic generation of loads through time. The paper ends with a critical discussion of experimental results.

Performance of Predicting Surface Quality Model Using Softcomputing, a Comparative Study of Results

This paper describes a comparative study of performance of two models predicting surface quality in high-speed milling (HSM) processes using two different machining centers. The models were created with experimental data obtained from two machine-tools with different characteristics, but using the same experimental model. In both cases, work pieces (probes) of the same material were machined (steel and aluminum probes) with cutting parameters and characteristics proper of production processes in industries such as aeronautics and automotive. The main objective of this study was to compare surface quality prediction models created in two machining centers to establish differences in outcomes and the possible causes of these differences. In addition, this paper deals with the validation of each model concerning surface quality obtained, along with comparing the quality of the models with other predictive surface quality models based on similar techniques.

Simulation and path planning for quadcopter obstacle avoidance in indoor environments using the ROS framework

This work focuses on the analysis of different algorithms dedicated to the planning of trajectories in a quadcopter. The times and distances of the paths from one point to another have been evaluated autonomously, and the evaluation of the reactive algorithms Bug1, Bug2 and DistBug have been considered to carry out the planning of the quadcopter paths. From the experiments and metrics defined, the efficiency and robustness of the algorithms have been determined. To carry out the implementation of the experiments, we have chosen and evaluated an environment based on the Robot Operating System (ROS) and Gazebo development platform.

Self-Alignment Approach Based on Cooperative Behaviors for the Docking Process of Modular Mobile Robots

In this paper, a self-alignment approach based on cooperative behaviors is proposed for the docking process of modular mobile robots. Each cooperative behavior is modeled by means of artificial neural networks (ANN) to achieve a common goal. Based on RobMAT a modular robot system in the mobile configuration, two strategies are presented. For this purpose a robotic device simulator (Player) and a multi-robot simulation in 2D (Stage) are used. Experimental results display differences between both strategies and benefits in time execution.