Abstract
Nowadays an increasing number of vehicles are being equipped with powerful cockpit systems capable of collecting drivers’ footprints over time. The collection of this valuable data opens effective opportunities for routine prediction. With the growing ability of vehicles to collect spatial and temporal information solving the routine prediction problem becomes crucial and feasible. It is then extremely important to advance and take advantage of the capabilities of these cockpit systems. A vehicle that is capable of predicting the next destination of the driver and when the driver intends to leave to that destination can prepare the journey in advance. Previous studies tackling the next location prediction problem have made use of Traditional Markov models, Neural Networks, Dynamic models, among others. In this work, a framework based on the hierarchical density-based clustering algorithm followed by a Long Short-Term Memory (LSTM) recurrent neural network is proposed for spatial-temporal prediction of drivers’ routines. Based on real-life driving scenarios of three different users, the proposed approach achieved a test set accuracy of 96.20%, 90.23%, and 86.40% when predicting the next destination and a Score of 93.69, 79.21, and 28.81 when predicting the departure time, respectively. The results indicate that the proposed architecture can be implemented on the vehicle cockpit for the assistance of the management of future trips. © 2020, Springer Nature Switzerland AG.

Abstract

Abstract

Abstract

Abstract
The continuous real-time motor interaction with our environment requires the capacity to measure and produce time intervals in a highly flexible manner. Recent neurophysiological evidence suggests that the neural computational principles supporting this capacity may be understood from a dynamical systems perspective: Inputs and initial conditions determine how a recurrent neural network evolves from a "resting state" to a state triggering the action. Here we test this hypothesis in a time measurement and time reproduction experiment using a model of a robust neural integrator based on the theoretical framework of dynamic neural fields. During measurement, the temporal accumulation of input leads to the evolution of a self-stabilized bump whose amplitude reflects elapsed time. During production, the stored information is used to reproduce on a trial-by-trial basis the time interval either by adjusting input strength or initial condition of the integrator. We discuss the impact of the results on our goal to endow autonomous robots with a human-like temporal cognition capacity for natural human-robot interactions.

Abstract
Neural field models, formalized by integro-differential equations, describe the large-scale spatio-temporal dynamics of neuronal populations [1]. They have been used in the past as a framework for modeling a wide range of brain functions, including multi-item working memory [2]. Neural field equations support spatially localized regions of high activity (or bumps) that are initially triggered by brief sensory inputs and subsequently become self-sustained by recurrent interactions within the neural population. We apply a special class of oscillatory coupling functions and analyze how the shape and spatial extension of multi-bump solutions change as the spatial ranges of excitation and inhibition within the field are varied [3]. More precisely, we use numerical continuation to find and follow solutions of neural field equations as the parameter controlling the distance between consecutive zeros of the coupling function is varied [4]. Important for a working memory application (e.g. [5]), we investigate how changes in this parameter affect the shape of bump solutions and therefore the maximum number of bumps that may exist in a given finite interval.