RESUMO

A Kalman filter can be used to fill space-state reconstruction dynamics based on knowledge of a system and partial measurements. However, its performance relies on accurate modeling of the system dynamics and a proper characterization of the uncertainties, which can be hard to obtain in real-life scenarios. In this work, we explore how the values of a Kalman gain matrix can be estimated by using spiking neural networks through a combination of biologically plausible neuron models with spike-time-dependent plasticity learning algorithms. The performance of proposed neural architecture is verified with simulations of some representative nonlinear systems, which show promising results. This approach traces a path for its implementation in neuromorphic analog hardware that can learn and reconstruct partial and changing dynamics of a system without the massive power consumption that is typically needed in a Von Neumann-based computer architecture.

Assuntos

Algoritmos , Redes Neurais de Computação , Neurônios/fisiologia , Computadores , Sistemas Computacionais

RESUMO

Robot navigation allows mobile robots to navigate among obstacles without hitting them and reaching the specified goal point. In addition to preventing collisions, it is also essential for mobile robots to sense and maintain an appropriate battery power level at all times to avoid failures and non-fulfillment with their scheduled tasks. Therefore, selecting the proper time to recharge the batteries is crucial to address the navigation algorithm design for the robot's prolonged autonomous operation. In this paper, a machine learning algorithm is used to ensure the extended robot autonomy based on a reinforcement learning method combined with a fuzzy inference system. The proposal enables a mobile robot to learn whether to continue through its path toward the destination or modify its course on the fly, if necessary, to proceed toward the battery charging station, based on its current state. The proposal performs a flexible behavior to choose an action that allows a robot to move from a starting to a destination point, guaranteeing battery charge availability. This paper shows the obtained results using an approach with thirty-six states and its reduction with twenty states. The conducted simulations show that the robot requires fewer training epochs to achieve ten consecutive successes in the fifteen proposed scenarios than traditional reinforcement learning methods exhibit. Moreover, in four scenarios, the robot ends up with a battery level above 80%, that value is higher than the obtained results with two deterministic methods.