Blog

This study investigates a Reinforcement Learning (RL) method to derivate control laws of a non-holonimic robot considering the coupling and non-linearty of the system. The controller is online derivated from the interaction between the agent and an unknown environment through a Q-learning based approach. This approach aims to find the best action that maximizes the rewards along attempts to follow a trajectory. Performed experiments might show that the learned controllers were able of efficiently following diverse trajectories considering different speed variations of the robot translation and rotation as well as maximizing the reward amount over iteractions for two distinct learning process configurations.   Authors: Mateus Sousa Franco, Sérgio R. Barros dos Santos and Fabio Augusto Faria from the Institute of Science and Tecnology of the Federal University of Sao Paulo, Sao Jose dos Campos, SP, Brazil. E-mails: mateus.franco@unifesp.br, sergio.ronaldo@unifesp.br, and ffaria@unifesp.br

This paper presents a decentralized learning algorithm for learning how to coordinate an automated team of actuated parts designed to build several types of structures specified by a user on a plane surface. The algorithm learns from the environment feedback and agent behavior. This problem is defined as a Markov decision process where agents (actuated parts) are modeled as small cube-shaped robots subject to the Bellman’s equation (Q-learning). The Q-learning algorithm considers the communication and conflict resolution models between the agents that lead to the emergence of intelligent global behavior (in a non-stationary stochastic environment). The main contribution of this paper is to propose a self-assembly approach capable of randomly generating the navigation routes of the multiple agents while learning the structure shape according to the hazardous dispersion area that must be isolated in the environment. Simulation trials show the feasibility of merging between the multi-agent coordination proces...

Convolutional Neural Networks (CNN) have been being widely employed to solve the challenging remote sensing task of aerial scene classification. Nevertheless, it is not straightforward to find single CNN models that can solve all aerial scene classification tasks, allowing the development of a better alternative, which is to fuse CNN-based classifiers into an ensemble. However, an appropriate choice of the classifiers that will belong to the ensemble is a critical factor, as it is unfeasible to employ all the possible classifiers in the literature. Therefore, this work proposes a novel framework based on meta-heuristic optimization for creating optimized ensembles in the context of aerial scene classification. The experimental results were performed across nine meta-heuristic algorithms and three aerial scene literature datasets, being  compared in terms of effectiveness (accuracy), efficiency (execution time), and behavioral performance in different scenarios.  Our results suggest that the Univariate Marg...