This paper presents the design, implementation and testing of a real-time system using computer vision and machine learning techniques to demonstrate learning behavior in a miniature mobile robot. The miniature robot, through environmental sensing, learns to navigate a maze choosing the optimum route. Several reinforcement learning based algorithms, such as Q-learning, Q(λ)-learning , fast onli...

Various cognitive models have been proposed to determine optimal paths in spatial navigation tasks, some of which demonstrate latent learning in Agents. We view and present the model as a Reinforcement Learning problem by using QLearning and Model-Based Learning in a deterministic environment. This paper uses a QLearning algorithm and compares its performance with the Dyna (Model based) algorit...

Learning a dynamics model and a reward model during reinforcement learning is a useful way, since the agent can also update its value function by using the models. In this paper, we propose a general dynamics model that is a composition of the feature space dynamics model and the state space dynamics model. This way enables to obtain a good generalization from a small number of samples because ...

We present the results of a research aimed at improving the Q-learning method through the use of artificial neural networks. Neural implementations are interesting due to their generalisation ability. Two implementations are proposed: one with a competitive multilayer perceptron and the other with a self-organising map. Results obtained on a task of learning an obstacle avoidance behaviour for ...

New computational models of closed-cell cellular structures that account for the effects of gas inside the pores are described in this paper. The behaviour of cellular models under uniaxial impact loading and large deformations has been analyzed with the LS-DYNA code. Parametric computational simulations illustrate the effect of pore gas on macroscopic behaviour during deformation regarding the...

The bow flare slamming load was studied by using the software Ls-dyna. A coupling finite element model including air, water and 3d established. Flare pressure picked up from in order to discuss relation between velocity as well distribution rule of different entry angle along length height ship.

in sheet metal forming processes, one-stage production of conical-cylindrical parts with high accuracy is very difficult due to wrinkling and rupturing. hydrodynamic deep drawing assisted by radial pressure is one of the most applicable procedures in sheet hydroforming process on the point of producing conical-cylindrical parts. in this paper, forming pressure path is investigated as one of the...