Search

Este trabajo de fin de grado ha sido llevado a cabo en el CAR, Centro de Automática y Robótica. Se ha desarrollado un software para la detección y estimación de velocidades de obstáculos, a partir de datos obtenidos de un láser de cuatro capas y un GPS de alta precisión. Combinando los datos del instante presente con las predicciones obtenidas en instantes anteriores, se ha logrado estimar, con una gran precisión, la ocupación del espacio visible por el láser. Además, se estiman algunos espacios oclusos o fuera de rango, utilizando información recogida anteriormente. También se han desarrollado algoritmos novedosos para agrupar esta ocupación y lograr modelar objetos y sus velocidades. En conclusión: este software es capaz de mapear el espacio localizando obstáculos y sus velocidades. En esta memoria, se recoge todo el proceso, describiendo tanto el diseño de los algoritmos como el desarrollo de éstos al detalle. Se comenta el estado del arte de la conducción autónoma. También se muestran algunos resultados y se proponen algunos trabajos futuros para continuar esta línea de investigación.

This paper presents a biologically inspired, hardware-realisable spiking neuron model, which we call the Temporal Noisy-Leaky Integrator (TNLI). The dynamic applications of the model as well as its applications in Computational Neuroscience are demonstrated and a learning algorithm based on postsynaptic delays is proposed. The TNLI incorporates temporal dynamics at the neuron level by modelling both the temporal summation of dendritic postsynaptic currents which have controlled delay and duration and the decay of the somatic potential due to its membrane leak. Moreover, the TNLI models the stochastic neurotransmitter release by real neuron synapses (with probabilistic RAMs at each input) and the firing times including the refractory period and action potential repolarisation. The temporal features of the TNLI make it suitable for use in dynamic time-dependent tasks like its application as a motion and velocity detector system presented in this paper. This is done by modelling the experimental velocity selectivity curve of the motion sensitive H1 neuron of the visual system of the fly. This application of the TNLI indicates its potential applications in artificial vision systems for robots. It is also demonstrated that Hebbian-based learning can be applied in the TNLI for postsynaptic delay training based on coincidence detection, in such a way that an arbitrary temporal pattern can be detected and recognised. The paper also demonstrates that the TNLI can be used to control the firing variability through inhibition with 80% inhibition to concurrent excitation, firing at high rates is nearly consistent with a Poisson-type firing variability observed in cortical neurons. It is also shown with the TNLI, that the gain of the neuron (slope of its transfer function) can be controlled by the balance between inhibition and excitation, the gain being a decreasing function of the proportion of inhibitory inputs. Finally, in the case of perfect balance between inhibition and excitation, i.e. where the average input current is zero, the neuron can still fire as a result of membrane potential fluctuations. The firing rate is then determined by the average input firing rate. Overall this work illustrates how a hardware-realisable neuron model can capitalise on the unique computational capabilities of biological neurons. © 2002 Elsevier Science Ltd. All rights reserved. 15 7 891 908 Cited By :27