Teaching an Old Robot New Tricks: Learning Novel Tasks via Interaction with People and Things

As AI has begun to reach out beyond its symbolic, objectivist roots into the embodied, experientialist realm, many projects are exploring different aspects of creating machines which interact with and respond to the world as humans do. Techniques for visual processing, object recognition, emotional response, gesture production and recognition, etc., are necessary components of a complete humanoid robot. However, most projects invariably concentrate on developing a few of these individual components, neglecting the issue of how all of these pieces would eventually fit together. The focus of the work in this dissertation is on creating a framework into which such specific competencies can be embedded, in a way that they can interact with each other and build layers of new functionality. To be of any practical value, such a framework must satisfy the real-world constraints of functioning in real-time with noisy sensors and actuators. The humanoid robot Cog provides an unapologetically adequate platform from which to take on such a challenge. This work makes three contributions to embodied AI. First, it offers a general-purpose architecture for developing behavior-based systems distributed over networks of PC's. Second, it provides a motor-control system that simulates several biological features which impact the development of motor behavior. Third, it develops a framework for a system which enables a robot to learn new behaviors via interacting with itself and the outside world. A few basic functional modules are built into this framework, enough to demonstrate the robot learning some very simple behaviors taught by a human trainer. A primary motivation for this project is the notion that it is practically impossible to build an "intelligent" machine unless it is designed partly to build itself. This work is a proof-of-concept of such an approach to integrating multiple perceptual and motor systems into a complete learning agent.

Representation and Detection of Shapes in Images

We present a set of techniques that can be used to represent and detect shapes in images. Our methods revolve around a particular shape representation based on the description of objects using triangulated polygons. This representation is similar to the medial axis transform and has important properties from a computational perspective. The first problem we consider is the detection of non-rigid objects in images using deformable models. We present an efficient algorithm to solve this problem in a wide range of situations, and show examples in both natural and medical images. We also consider the problem of learning an accurate non-rigid shape model for a class of objects from examples. We show how to learn good models while constraining them to the form required by the detection algorithm. Finally, we consider the problem of low-level image segmentation and grouping. We describe a stochastic grammar that generates arbitrary triangulated polygons while capturing Gestalt principles of shape regularity. This grammar is used as a prior model over random shapes in a low level algorithm that detects objects in images.

Learning Commonsense Categorical Knowledge in a Thread Memory System

If we are to understand how we can build machines capable of broad purpose learning and reasoning, we must first aim to build systems that can represent, acquire, and reason about the kinds of commonsense knowledge that we humans have about the world. This endeavor suggests steps such as identifying the kinds of knowledge people commonly have about the world, constructing suitable knowledge representations, and exploring the mechanisms that people use to make judgments about the everyday world. In this work, I contribute to these goals by proposing an architecture for a system that can learn commonsense knowledge about the properties and behavior of objects in the world. The architecture described here augments previous machine learning systems in four ways: (1) it relies on a seven dimensional notion of context, built from information recently given to the system, to learn and reason about objects' properties; (2) it has multiple methods that it can use to reason about objects, so that when one method fails, it can fall back on others; (3) it illustrates the usefulness of reasoning about objects by thinking about their similarity to other, better known objects, and by inferring properties of objects from the categories that they belong to; and (4) it represents an attempt to build an autonomous learner and reasoner, that sets its own goals for learning about the world and deduces new facts by reflecting on its acquired knowledge. This thesis describes this architecture, as well as a first implementation, that can learn from sentences such as ``A blue bird flew to the tree'' and ``The small bird flew to the cage'' that birds can fly. One of the main contributions of this work lies in suggesting a further set of salient ideas about how we can build broader purpose commonsense artificial learners and reasoners.

Electrical Design: A Problem for Artificial Intelligence Research

This report outlines the problem of intelligent failure recovery in a problem-solver for electrical design. We want our problem solver to learn as much as it can from its mistakes. Thus we cast the engineering design process on terms of Problem Solving by Debugging Almost-Right Plans, a paradigm for automatic problem solving based on the belief that creation and removal of "bugs" is an unavoidable part of the process of solving a complex problem. The process of localization and removal of bugs called for by the PSBDARP theory requires an approach to engineering analysis in which every result has a justification which describes the exact set of assumptions it depends upon. We have developed a program based on Analysis by Propagation of Constraints which can explain the basis of its deductions. In addition to being useful to a PSBDARP designer, these justifications are used in Dependency-Directed Backtracking to limit the combinatorial search in the analysis routines. Although the research we will describe is explicitly about electrical circuits, we believe that similar principles and methods are employed by other kinds of engineers, including computer programmers.

Learning Three-Dimensional Shape Models for Sketch Recognition

Artifacts made by humans, such as items of furniture and houses, exhibit an enormous amount of variability in shape. In this paper, we concentrate on models of the shapes of objects that are made up of fixed collections of sub-parts whose dimensions and spatial arrangement exhibit variation. Our goals are: to learn these models from data and to use them for recognition. Our emphasis is on learning and recognition from three-dimensional data, to test the basic shape-modeling methodology. In this paper we also demonstrate how to use models learned in three dimensions for recognition of two-dimensional sketches of objects.

Object and Scene Classification: what does a Supervised Approach Provide us?

Given a set of images of scenes containing different object categories (e.g. grass, roads) our objective is to discover these objects in each image, and to use this object occurrences to perform a scene classification (e.g. beach scene, mountain scene). We achieve this by using a supervised learning algorithm able to learn with few images to facilitate the user task. We use a probabilistic model to recognise the objects and further we classify the scene based on their object occurrences. Experimental results are shown and evaluated to prove the validity of our proposal. Object recognition performance is compared to the approaches of He et al. (2004) and Marti et al. (2001) using their own datasets. Furthermore an unsupervised method is implemented in order to evaluate the advantages and disadvantages of our supervised classification approach versus an unsupervised one

Semi-online neural-Q_leaming for real-time robot learning

Reinforcement learning (RL) is a very suitable technique for robot learning, as it can learn in unknown environments and in real-time computation. The main difficulties in adapting classic RL algorithms to robotic systems are the generalization problem and the correct observation of the Markovian state. This paper attempts to solve the generalization problem by proposing the semi-online neural-Q_learning algorithm (SONQL). The algorithm uses the classic Q_learning technique with two modifications. First, a neural network (NN) approximates the Q_function allowing the use of continuous states and actions. Second, a database of the most representative learning samples accelerates and stabilizes the convergence. The term semi-online is referred to the fact that the algorithm uses the current but also past learning samples. However, the algorithm is able to learn in real-time while the robot is interacting with the environment. The paper shows simulated results with the "mountain-car" benchmark and, also, real results with an underwater robot in a target following behavior

A behavior-based scheme using reinforcement learning for autonomous underwater vehicles

This paper presents a hybrid behavior-based scheme using reinforcement learning for high-level control of autonomous underwater vehicles (AUVs). Two main features of the presented approach are hybrid behavior coordination and semi on-line neural-Q_learning (SONQL). Hybrid behavior coordination takes advantages of robustness and modularity in the competitive approach as well as efficient trajectories in the cooperative approach. SONQL, a new continuous approach of the Q_learning algorithm with a multilayer neural network is used to learn behavior state/action mapping online. Experimental results show the feasibility of the presented approach for AUVs

Adaptive business intelligence for an open negotiation environment

Engineering of negotiation model allows to develop effective heuristic for business intelligence. Digital ecosystems demand open negotiation models. To define in advance effective heuristics is not compliant with the requirement of openness. The new challenge is to develop business intelligence in advance exploiting an adaptive approach. The idea is to learn business strategy once new negotiation model rise in the e-market arena. In this paper we present how recommendation technology may be deployed in an open negotiation environment where the interaction protocol models are not known in advance. The solution we propose is delivered as part of the ONE Platform, open source software that implements a fully distributed open environment for business negotiation

Curriculum sequencing for an e-learning system based on learning styles

This work shows the use of adaptation techniques involved in an e-learning system that considers students' learning styles and students' knowledge states. The mentioned e-learning system is built on a multiagent framework designed to examine opportunities to improve the teaching and to motivate the students to learn what they want in a user-friendly and assisted environment

Caso exitoso de innovación comercial y organizacional

La realización de casos empresariales permite a su lector aprender sobre el funcionamiento interno de las empresas que de algún modo hacen parte de nuestras vidas diarias. El presente caso pretende ilustrar el éxito nacional e internacional de una firma colombiana que a base de mucho esfuerzo y perseverancia logra que este éxito fuera ahora una realidad.

El neuromarketing : la llave de la caja de pandora

Actualmente el Marketing a desarrollado conjuntamente con las neurociencia una técnica llamada Neuromarketing, la cual explora el cerebro humano para resolver interrogantes que lleven a las organizaciones a conocer más a profundidad al ser humano, sus gustos, deseos, necesidades y motivadores de compra. Esto implica cuestionarnos sobre los valores éticos y morales que se deben aplicar en la utilización de este tipo de tecnologías, las cuales descubren los secretos más preciados del ser humano y lo hacen vulnerable frente a una sociedad que muchas veces actúa “sin cuartel” en busca de beneficios económicos y materiales, olvidado la integridad, la libertad y el respeto por la figura humana. En esta tesis se recorrerá brevemente tanto el Marketing Moderno como la aplicación del neuromarketing y el alcance que hoy tiene este para poder cuestionar y proponer soluciones frente a la ética y la moral que deben limitar y guiar el buen uso de esta maravillosa herramienta para el Marketing.

Aula de música : desarrollo de contenidos en una herramienta de e-learning para la asignatura de música en Educación Primaria.

Aula de música es una herramienta e-learning para el desarrollo del aprendizaje de la música para niños con edades comprendidas entre los 6 y 12 años, edades correspondientes a las de los alumnos de la etapa de la Educación Primaria. En esta herramienta destaca el uso de estándares y especificaciones como LOM, IMS, etc. que van a facilitar la tarea de reutilizar la documentación incluida para compartir conocimiento. El proceso de elaboración del contenido ha sido fundamental y en relación con el entorno de trabajo debe mencionarse que se ha primado la construcción de una GUI que sirva para aprender y que motive a los alumnos a aprender música de una forma diferente, en contraposición a realizar una diseño estético que fuera incapaz de adaptarse a las capacidades de cada tipo de usuario, para lo que se han tenido en cuenta criterios de usabilidad y accesibilidad (WAI).

Estudio de mercado sobre los zapatos tipo « pisahuevos »

Es de gran importancia, para determinar las tendencias de consumo, principalmente de los jóvenes y adolescentes, conocer y analizar los factores de influencia en el comportamiento del consumidor y la satisfacción de sus necesidades. Se debe conocer además, el proceso de resolución de problemas, las influencias que determinan dichos comportamientos y los niveles de respuestas existentes según el grado de participación en la compra. Es sin duda alguna, de gran valor para las empresas, conocer aspectos que llevan al ser humano a elegir o desechar productos, servicios, marcas, puntos de venta u otro elemento para estar preparados, anticiparse al mercado y aprovechar las tendencias sociales.

Modelo de internacionalización del sector de reciclaje en Colombia

El presente documento se realiza un análisis de tres empresas del sector del reciclaje: Smurfit Kappa Cartón de Colombia S.A., Ecoeficiencia S.A.S y Fibras Nacionales S.A.S, para conocer la aplicación de las teorías de internacionalización y observar cómo se desarrollan en la realidad Colombiana. El sector de reciclaje actualmente es poco explorado y explotado en Colombia, principalmente por el bajo interés del sector público y privado en alcanzar las innumerables ventajas económicas y sociales que éste ofrece, toda vez que, es considerado un sector no formal dentro de la economía colombiana. Más adelante se describe la situación actual de las tres empresas basado en una revisión bibliográfica de las teorías de internacionalización y posteriormente se aplican los conceptos a cada una de las empresas. Finalmente, se propone la ruta de internacionalización del sector del reciclaje en Colombia y un modelo logístico general para que las empresas de este sector lo apliquen y así mejoren sus procesos. Se plantea como estrategia el desarrollo de un Cluster para lograr la efectividad de la ruta de internacionalización del sector del reciclaje. Es necesaria la conformación de una red de empresas, agentes e instituciones públicas y privadas dentro del entorno del reciclaje y el manejo de residuos, para la consolidación del sector. El objetivo es que este documento sirva como medio de consulta para empresarios y empresas interesadas en mejorar el nivel de vida de los recicladores, contribuir con el medio ambiente y mejorar la competitividad y productividad del reciclaje en Colombia, logrando convertirse en un sector de talla mundial. Es importante mencionar que en la medida es que el sector se formalice, los recicladores se verán beneficiados y harán parte importante de una cadena de valor que permitirá mejorar las condiciones actuales del sector y podrán participar activamente en la economía, generando un impacto positivo y global.