Luka Eciolaza

Automatic linguistic reporting in driving simulation environments

Linguistic data summarization targets the description of patterns emerging in data by means of linguistic expressions. Just as human beings do, computers can use natural language to represent and fuse heterogeneous data in a multi criteria decision making environment. Linguistic data description is particularly well suited for applications in which there is a necessity of understanding data at different levels of expertise or human-computer interaction is involved. In this paper, an application for the linguistic descriptions of driving activity in a simulation environment has been developed. In order to ensure safe driving practices, all new onboard devices in transportation systems need to be evaluated. Work performed in this application paper will be used for the automatic evaluation of onboard devices. Based on Fuzzy Logic, and as a contribution to Computational Theory of Perceptions, the proposed solution is part of our research on granular linguistic models of phenomena. The application generates a set of valid sentences describing the quality of driving. Then a relevancy analysis is performed in order to compile the most representative and suitable statements in a final report. Real time-series data from a vehicle simulator have been used to evaluate the performance of the presented application in the framework of a real project.

Linguistic reporting of driver behavior: Summary and event description

There is a clear need for computational systems able to produce automatic linguistic descriptions of data about phenomena. Linguistic summarization represents an attempt to describe by means of linguistic expressions patterns emerging in data. Generating data summaries can be seen as a very complex and non-trivial data mining task. Language is the unique meta-language to describe and understand various complex phenomena and humans use it for multi-modal data fusion in their brains. Our work is devoted to advance towards the development of a framework for the fusion of heterogenous information using linguistic descriptions based on NL. This application paper deals with the development of a computational system capable of automatically generating linguistic descriptions of driving activity from vehicle simulator data. Based on Fuzzy Logic, and as a contribution towards the development of Computational Theory of Perceptions, the proposed solution is part of our research on granular linguistic models of phenomena. We will generate a set of valid sentences describing a phenomenon through a granular linguistic model of a phenomenon. Then a relevancy analysis will be performed, in order to choose the most suitable sequence of clauses to each specific input data. We have used real time-series data from a vehicle simulator to evaluate the performance of our approach.

Piecewise Bilinear models for feedback error learning: On-line feedforward controller design

Feedback error learning is an on-line learning strategy of inverse dynamics. It sequentially acquires an inverse model of a plant through feedback control actions. The inverse model is usually implemented as a Neural Network, however we propose a new approach to implement the FEL control scheme through Piecewise Bilinear models. We present an on-line sequential learning algorithm for feedforward controller design. We also propose an algorithm for off-line identification of a pseudo-inverse model of a plant to use as an initial feedforward controller before its learning. We will prove the applicability of PB models to implement the FEL scheme through illustrative examples.

Linguistic description of human activity based on mobile phone's accelerometers

Monitoring the physical activity of a person is used for many applications such as medical assistance, personal security, etc. We use the accelerometers embedded in current mobile phones to identify the physical activities and generate periodical linguistic reports which describe relevant information about the activities carried out, their intensities and trends. Based on the Computational Theory of Perceptions, we have developed an application able to generate these linguistic descriptions, presenting a simple demonstration of our contribution in this field.

On-line design of LUT controllers based on desired closed loop plant: Vertex Placement Principle

This paper presents a systematic approach to perform an on-line global design of look up table (LUT) controllers. This paper uses Vertex Placement Principle to design a controller for an initially unknown objective plant (P) based on a desired plant (DP) model. Both the desired plant and the objective plant are approximated with piecewise bilinear (PB) models. After the on-line identification of the initially unknown plant (P), the LUT-controller (C) is designed so as to make the closed loop plant (CP) behave like a desired plant.

Quadrotor control using dynamic feedback linearization based on piecewise bilinear models

This paper proposes a tracking controller for a four rotors helicopter robot using dynamic feedback linearization based on piecewise bilinear (PB) models. The approximated model is fully parametric. Input-output (I/O) dynamic feedback linearization is applied to stabilize PB control system. Although the controller is simpler than the conventional I/O feedback linearization controller, the control performance based on PB model is the same as the conventional one. Examples are shown to confirm the feasibility of our proposals by computer simulations.

Generating Advices with Emotional Content for Promoting Efficient Consumption of Energy

Virtual agents could be a solution for companies that deal with maintaining personalized contact with high volumes of customers. Nevertheless these virtual agents must show certain emotional empath...

Gaussian Process Latent Variable Models for Fault Detection

The Gaussian process latent variable model (GPLVM) is a novel unsupervised approach to nonlinear low dimensional embedding proposed by Lawrence (2005). This paper presents the development of a framework for the implementation of the GPLVM for fault detection. A series of experiments have been carried out comparing and combining the GPLVM to the conventional and widely used linear dimension reduction technique of principal component analysis (PCA). The inclusion of the GPLVM for the visualisation and data analysis, led to a considerable improvement in the classification results

Look-Up-Table controller design for nonlinear servo systems with piecewise bilinear models

This paper deals with servo control for nonlinear systems approximated by piecewise bilinear (PB) models. The approximated model is found to be fully parametric. The input-output (I/O) feedback linearization is applied to stabilize PB control systems. This paper proposes two methods to design servo controllers for nonlinear systems with PB models based on I/O linearization. One is a two-degree of freedom controller and the other is a model following controller. Illustrative examples are given to show the validity of the proposed method, where a controller is represented as a Look-Up-Table (LUT).

Model Following Control of a Unicycle Mobile Robot via Dynamic Feedback Linearization Based on Piecewise Bilinear Models

We propose a dynamic feedback linearization of a unicycle as a non-holonomic system with a piecewise bilinear (PB) model. Inputoutput (I/O) dynamic feedback linearization is applied to stabilize PB control system. We propose a method for nonlinear model following controller to the unicycle robot. Although the controller is simpler than the conventional I/O feedback linearization controller, the tracking performance based on PB model is the same as the conventional one. Examples are shown to confirm the feasibility of our proposals by computer simulations.