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.

Fast Object Recognition in Noisy Images Using Simulated Annealing

A fast simulated annealing algorithm is developed for automatic object recognition. The normalized correlation coefficient is used as a measure of the match between a hypothesized object and an image. Templates are generated on-line during the search by transforming model images. Simulated annealing reduces the search time by orders of magnitude with respect to an exhaustive search. The algorithm is applied to the problem of how landmarks, for example, traffic signs, can be recognized by an autonomous vehicle or a navigating robot. The algorithm works well in noisy, real-world images of complicated scenes for model images with high information content.

Learning from Incomplete Data

Real-world learning tasks often involve high-dimensional data sets with complex patterns of missing features. In this paper we review the problem of learning from incomplete data from two statistical perspectives---the likelihood-based and the Bayesian. The goal is two-fold: to place current neural network approaches to missing data within a statistical framework, and to describe a set of algorithms, derived from the likelihood-based framework, that handle clustering, classification, and function approximation from incomplete data in a principled and efficient manner. These algorithms are based on mixture modeling and make two distinct appeals to the Expectation-Maximization (EM) principle (Dempster, Laird, and Rubin 1977)---both for the estimation of mixture components and for coping with the missing data.

Contextual Priming for Object Detection

There is general consensus that context can be a rich source of information about an object's identity, location and scale. In fact, the structure of many real-world scenes is governed by strong configurational rules akin to those that apply to a single object. Here we introduce a simple probabilistic framework for modeling the relationship between context and object properties based on the correlation between the statistics of low-level features across the entire scene and the objects that it contains. The resulting scheme serves as an effective procedure for object priming, context driven focus of attention and automatic scale-selection on real-world scenes.

Relative Contributions of Internal and External Features to Face Recognition

The central challenge in face recognition lies in understanding the role different facial features play in our judgments of identity. Notable in this regard are the relative contributions of the internal (eyes, nose and mouth) and external (hair and jaw-line) features. Past studies that have investigated this issue have typically used high-resolution images or good-quality line drawings as facial stimuli. The results obtained are therefore most relevant for understanding the identification of faces at close range. However, given that real-world viewing conditions are rarely optimal, it is also important to know how image degradations, such as loss of resolution caused by large viewing distances, influence our ability to use internal and external features. Here, we report experiments designed to address this issue. Our data characterize how the relative contributions of internal and external features change as a function of image resolution. While we replicated results of previous studies that have shown internal features of familiar faces to be more useful for recognition than external features at high resolution, we found that the two feature sets reverse in importance as resolution decreases. These results suggest that the visual system uses a highly non-linear cue-fusion strategy in combining internal and external features along the dimension of image resolution and that the configural cues that relate the two feature sets play an important role in judgments of facial identity.

An Application of Augmented Reality (AR) in the Teaching of an Arc Welding Robot

Augmented Reality (AR) is an emerging technology that utilizes computer vision methods to overlay virtual objects onto the real world scene so as to make them appear to co-exist with the real objects. Its main objective is to enhance the user’s interaction with the real world by providing the right information needed to perform a certain task. Applications of this technology in manufacturing include maintenance, assembly and telerobotics. In this paper, we explore the potential of teaching a robot to perform an arc welding task in an AR environment. We present the motivation, features of a system using the popular ARToolkit package, and a discussion on the issues and implications of our research.

Embedding Emotional Context in Recommender Systems

Emotions are crucial for user's decision making in recommendation processes. We first introduce ambient recommender systems, which arise from the analysis of new trends on the exploitation of the emotional context in the next generation of recommender systems. We then explain some results of these new trends in real-world applications through the smart prediction assistant (SPA) platform in an intelligent learning guide with more than three million users. While most approaches to recommending have focused on algorithm performance. SPA makes recommendations to users on the basis of emotional information acquired in an incremental way. This article provides a cross-disciplinary perspective to achieve this goal in such recommender systems through a SPA platform. The methodology applied in SPA is the result of a bunch of technology transfer projects for large real-world rccommender systems

Communities and the Web

What is a social network? How does an online community differ from a real world community? See also: Anne Hornsby, 'Surfing the net for community: a Durkheimian analysis of electronic gatherings' ch.3 in Peter Kivisto (ed.) Illuminating Social Life (3rd ed 2005). Libr ref HM51KIV. Graham Crow and Catherine Maclean, 'Community' in Geoff Payne (ed.) Social Divisions (2nd ed. 2006) HM821PAY.

Liderazgo y resiliencia organizacional en la crisis financiera global del 2008–2009

Durante la crisis financiera global de 2008 muchas organizaciones y mercados financieros tuvieron que terminar sus operaciones o replantearlas debido a los choques que golpearon el bienestar de sus empresas. A pesar de esta grave situación, en la actualidad se pueden encontrar empresas que se recuperaron y salieron del terrible panorama que les presentó la crisis, incluso encontrando nuevas oportunidades de negocio y fortaleciendo su futuro. Esta capacidad que algunas organizaciones tuvieron y que permitió su salida victoriosa de la crisis se denomina resiliencia, la cual es la capacidad de sobreponerse a los efectos negativos de choques internos o externos (Briguglio, Cordina, Farrugia & Vella 2009). Por tanto en el presente trabajo se estudiará esta capacidad tanto en la organización como en los líderes para hallar factores que mejoren el desempeño de las empresas en crisis como la que ocurrió en el 2008 – 2009. Primero se realizará un estudio sobre los sucesos y el desarrollo de la crisis subprime del año 2008 para tener un entendimiento claro de sus antecedentes, desarrollo, magnitud y consecuencias. Posteriormente se realizará un estudio profundo sobre la teoría de la resiliencia organizacional y la resiliencia en el líder como individuo y los estilos de liderazgo. Finalmente teniendo un sustento teórico tanto de la crisis como del concepto de resiliencia se tomarán casos de estudio de empresas que lograron perdurar en la crisis financiera del 2008 y empresas que no lograron sobrevivir para posteriormente hallar características del líder y del liderazgo que puedan aumentar o afectar la capacidad de resiliencia de las organizaciones con el objetivo de brindar herramientas a los líderes actuales para que manejen de forma eficiente y eficaz las empresas en un mundo complejo y variable como el actual.

Power and Influence

Like any form of human interaction and communication it is possible to view Social Media as a means for the powerful to influence and control the less powerful. But what is power on social media, how might we measure or affect it, and does it translate to the real world? In this lecture we will look at the philosophical definitions of power, and explore how it has been analysed in social networks and social media systems. We will also look at the characteristics of social networks that impact on power, including Homophily, Heterophily, CyberBalkanization and Thresholds of Collective Action. Finally we will ask what evidence there is that power in social media can affect what goes on in the real world, and explore some real and fictional examples of protest to see what the consequences of social media actually are on sometimes violent political debate.

Modelling for Problem Solving in the Large

This a short presentation which introduces how models and modelling help us to solve large scale problems in the real world. It introduces the idea that dynamic behaviour is caused by interacting components in the system. Feedback in the system makes behaviour prediction difficult unless we use modelling to support understanding

Soft Sytems Modelling

This presentation introduces Soft Systems Modelling as a technique to support investigating the behaviour of dynamic systems in the real world. It combines techniques from General Systems Theory, Soft Systems Methodolgy and Critical Systems Heuristics. Personas and Scenarios are used as a technique for exploring the motivations of stakeholders in the systems.

INFO2009 2012-13 Resource Group 12 Security and Privacy

This is an educational resource that covers a number of realistic attacks on privacy from a technical perspective along with the legal issues you might face if you don't take adequate precautions with data. The format is engaging and entertaining, framing real-world issues in a familiar medium - namely that of a trailer for a blockbuster film.

WAIS seminar: Provenance Analytics and Crowdsourcing

Wednesday 26th March 2014 Speaker(s): Dr Trung Dong Huynh Organiser: Dr Tim Chown Time: 26/03/2014 11:00-11:50 Location: B32/3077 File size: 349Mb Abstract Understanding the dynamics of a crowdsourcing application and controlling the quality of the data it generates is challenging, partly due to the lack of tools to do so. Provenance is a domain-independent means to represent what happened in an application, which can help verify data and infer their quality. It can also reveal the processes that led to a data item and the interactions of contributors with it. Provenance patterns can manifest real-world phenomena such as a significant interest in a piece of content, providing an indication of its quality, or even issues such as undesirable interactions within a group of contributors. In this talk, I will present an application-independent methodology for analysing provenance graphs, constructed from provenance records, to learn about such patterns and to use them for assessing some key properties of crowdsourced data, such as their quality, in an automated manner. I will also talk about CollabMap (www.collabmap.org), an online crowdsourcing mapping application, and show how we applied the approach above to the trust classification of data generated by the crowd, achieving an accuracy over 95%.

El liderazgo organizacional: una aproximación desde la perspectiva etológica

La presente investigación plantea la necesidad fundamental de generar un proceso de análisis, tendiente a proponer dinámicas organizativas humanas, desde un enfoque etológico. La etología aparece entonces como un estudio sistemático del comportamiento animal, sus formas de asociación, su disparidad, pero sobre todo, su accionar orgánico en la búsqueda de un comportamiento colectivo que propenda por el bien común. En esta medida el liderazgo surge como una posibilidad clara de fomentar relaciones humanas centradas en las diferentes vertientes relacionales; cultura, comunicación, comunidad, axiología, y finalmente etología. Así mismo, se examinan las diferentes estrategias que el liderazgo como posibilidad de cambio dentro de las organizaciones, puede ser fundamentado mediante procesos de comparación etológica, y así generar propuestas que configuren un quehacer organizacional desde la solidaridad, el liderazgo, y el desenvolvimiento interno y externo de las organizaciones.