Intelligence by Design: Principles of Modularity and Coordination for Engineerin

All intelligence relies on search --- for example, the search for an intelligent agent's next action. Search is only likely to succeed in resource-bounded agents if they have already been biased towards finding the right answer. In artificial agents, the primary source of bias is engineering. This dissertation describes an approach, Behavior-Oriented Design (BOD) for engineering complex agents. A complex agent is one that must arbitrate between potentially conflicting goals or behaviors. Behavior-oriented design builds on work in behavior-based and hybrid architectures for agents, and the object oriented approach to software engineering. The primary contributions of this dissertation are: 1.The BOD architecture: a modular architecture with each module providing specialized representations to facilitate learning. This includes one pre-specified module and representation for action selection or behavior arbitration. The specialized representation underlying BOD action selection is Parallel-rooted, Ordered, Slip-stack Hierarchical (POSH) reactive plans. 2.The BOD development process: an iterative process that alternately scales the agent's capabilities then optimizes the agent for simplicity, exploiting tradeoffs between the component representations. This ongoing process for controlling complexity not only provides bias for the behaving agent, but also facilitates its maintenance and extendibility. The secondary contributions of this dissertation include two implementations of POSH action selection, a procedure for identifying useful idioms in agent architectures and using them to distribute knowledge across agent paradigms, several examples of applying BOD idioms to established architectures, an analysis and comparison of the attributes and design trends of a large number of agent architectures, a comparison of biological (particularly mammalian) intelligence to artificial agent architectures, a novel model of primate transitive inference, and many other examples of BOD agents and BOD development.

Active Learning with Statistical Models

For many types of learners one can compute the statistically 'optimal' way to select data. We review how these techniques have been used with feedforward neural networks. We then show how the same principles may be used to select data for two alternative, statistically-based learning architectures: mixtures of Gaussians and locally weighted regression. While the techniques for neural networks are expensive and approximate, the techniques for mixtures of Gaussians and locally weighted regression are both efficient and accurate.

Multicast extension of unicast charging for QoS Services

In order to successfully deploy multicast services in QoS-aware networks, pricing architectures must take into account the particular characteristics of multicast sessions. With this objective, we propose a charging scheme for QoS multicast services, assuming that the unicast cost of each interconnecting link is determined and that such cost is expressed in terms of quality of service (QoS) parameters. Our scheme allows determining the cost distribution of a multicast session along a cost distribution tree (CDT), and basing such distribution in those pre-existing unicast cost functions. The paper discusses in detail the main characteristics of the problem in a realistic interdomain scenario and how the proposed scheme would contribute to its solution

Hybrid coordination of reinforcement learning-based behaviors for AUV control

This paper proposes a hybrid coordination method for behavior-based control architectures. The hybrid method takes advantages of the robustness and modularity in competitive approaches as well as optimized trajectories in cooperative ones. This paper shows the feasibility of applying this hybrid method with a 3D-navigation to an autonomous underwater vehicle (AUV). The behaviors are learnt online by means of reinforcement learning. A continuous Q-learning implemented with a feed-forward neural network is employed. Realistic simulations were carried out. The results obtained show the good performance of the hybrid method on behavior coordination as well as the convergence of the behaviors

Designing context-aware adaptive units of learning based on IMS-LD standard

Learning contents adaptation has been a subject of interest in the research area of the adaptive hypermedia systems. Defining which variables and which standards can be considered to model adaptive content delivery processes is one of the main challenges in pedagogical design over e-learning environments. In this paper some specifications, architectures and technologies that can be used in contents adaptation processes considering characteristics of the context are described and a proposal to integrate some of these characteristics in the design of units of learning using adaptation conditions in a structure of IMS-Learning Design (IMS-LD) is presented. The key contribution of this work is the generation of instructional designs considering the context, which can be used in Learning Management Systems (LMSs) and diverse mobile devices

On AUV control architecture

This paper surveys control architectures proposed in the literature and describes a control architecture that is being developed for a semi-autonomous underwater vehicle for intervention missions (SAUVIM) at the University of Hawaii. Conceived as hybrid, this architecture has been organized in three layers: planning, control and execution. The mission is planned with a sequence of subgoals. Each subgoal has a related task supervisor responsible for arranging a set of pre-programmed task modules in order to achieve the subgoal. Task modules are the key concept of the architecture. They are the main building blocks and can be dynamically re-arranged by the task supervisor. In our architecture, deliberation takes place at the planning layer while reaction is dealt through the parallel execution of the task modules. Hence, the system presents both a hierarchical and an heterarchical decomposition, being able to show a predictable response while keeping rapid reactivity to the dynamic environment

Label Space Reduction in MPLS Networks: How Much Can A Single Stacked Label Do?

Most network operators have considered reducing LSR label spaces (number of labels used) as a way of simplifying management of underlaying virtual private networks (VPNs) and therefore reducing operational expenditure (OPEX). The IETF outlined the label merging feature in MPLS-allowing the configuration of multipoint-to-point connections (MP2P)-as a means of reducing label space in LSRs. We found two main drawbacks in this label space reduction a)it should be separately applied to a set of LSPs with the same egress LSR-which decreases the options for better reductions, and b)LSRs close to the edge of the network experience a greater label space reduction than those close to the core. The later implies that MP2P connections reduce the number of labels asymmetrically

A mission control system for an autonomous underwater vehicle

The presented work focuses on the theoretical and practical aspects concerning the design and development of a formal method to build a mission control system for autonomous underwater vehicles bringing systematic design principles for the formal description of missions using Petri nets. The proposed methodology compounds Petri net building blocks within it to de_ne a mission plan for which it is proved that formal properties, such as reachability and reusability, hold as long as these same properties are also guaranteed by each Petri net building block. To simplify the de_nition of these Petri net blocks as well as their composition, a high level language called Mission Control Language has been developed. Moreover, a methodology to ensure coordination constraints for teams of multiple robots as well as the de_nition of an interface between the proposed system and an on-board planner able to plan/replan sequences of prede_ned mission plans is included as well. Results of experiments with several real underwater vehicles and simulations involving an autonomous surface craft and an autonomous underwater vehicles are presented to show the system's capabilities.

A proposal of a behavior-based control architecture with reinforcement learning for an autonomous underwater robot

Aquesta tesi proposa l'ús d'un seguit de tècniques pel control a alt nivell d'un robot autònom i també per l'aprenentatge automàtic de comportaments. L'objectiu principal de la tesis fou el de dotar d'intel·ligència als robots autònoms que han d'acomplir unes missions determinades en entorns desconeguts i no estructurats. Una de les premisses tingudes en compte en tots els passos d'aquesta tesis va ser la selecció d'aquelles tècniques que poguessin ésser aplicades en temps real, i demostrar-ne el seu funcionament amb experiments reals. El camp d'aplicació de tots els experiments es la robòtica submarina. En una primera part, la tesis es centra en el disseny d'una arquitectura de control que ha de permetre l'assoliment d'una missió prèviament definida. En particular, la tesis proposa l'ús de les arquitectures de control basades en comportaments per a l'assoliment de cada una de les tasques que composen la totalitat de la missió. Una arquitectura d'aquest tipus està formada per un conjunt independent de comportaments, els quals representen diferents intencions del robot (ex.: "anar a una posició", "evitar obstacles",...). Es presenta una recerca bibliogràfica sobre aquest camp i alhora es mostren els resultats d'aplicar quatre de les arquitectures basades en comportaments més representatives a una tasca concreta. De l'anàlisi dels resultats se'n deriva que un dels factors que més influeixen en el rendiment d'aquestes arquitectures, és la metodologia emprada per coordinar les respostes dels comportaments. Per una banda, la coordinació competitiva és aquella en que només un dels comportaments controla el robot. Per altra banda, en la coordinació cooperativa el control del robot és realitza a partir d'una fusió de totes les respostes dels comportaments actius. La tesis, proposa un esquema híbrid d'arquitectura capaç de beneficiar-se dels principals avantatges d'ambdues metodologies. En una segona part, la tesis proposa la utilització de l'aprenentatge per reforç per aprendre l'estructura interna dels comportaments. Aquest tipus d'aprenentatge és adequat per entorns desconeguts i el procés d'aprenentatge es realitza al mateix temps que el robot està explorant l'entorn. La tesis presenta també un estat de l'art d'aquest camp, en el que es detallen els principals problemes que apareixen en utilitzar els algoritmes d'aprenentatge per reforç en aplicacions reals, com la robòtica. El problema de la generalització és un dels que més influeix i consisteix en permetre l'ús de variables continues sense augmentar substancialment el temps de convergència. Després de descriure breument les principals metodologies per generalitzar, la tesis proposa l'ús d'una xarxa neural combinada amb l'algoritme d'aprenentatge per reforç Q_learning. Aquesta combinació proporciona una gran capacitat de generalització i una molt bona disposició per aprendre en tasques de robòtica amb exigències de temps real. No obstant, les xarxes neurals són aproximadors de funcions no-locals, el que significa que en treballar amb un conjunt de dades no homogeni es produeix una interferència: aprendre en un subconjunt de l'espai significa desaprendre en la resta de l'espai. El problema de la interferència afecta de manera directa en robòtica, ja que l'exploració de l'espai es realitza sempre localment. L'algoritme proposat en la tesi té en compte aquest problema i manté una base de dades representativa de totes les zones explorades. Així doncs, totes les mostres de la base de dades s'utilitzen per actualitzar la xarxa neural, i per tant, l'aprenentatge és homogeni. Finalment, la tesi presenta els resultats obtinguts amb la arquitectura de control basada en comportaments i l'algoritme d'aprenentatge per reforç. Els experiments es realitzen amb el robot URIS, desenvolupat a la Universitat de Girona, i el comportament après és el seguiment d'un objecte mitjançant visió per computador. La tesi detalla tots els dispositius desenvolupats pels experiments així com les característiques del propi robot submarí. Els resultats obtinguts demostren la idoneïtat de les propostes en permetre l'aprenentatge del comportament en temps real. En un segon apartat de resultats es demostra la capacitat de generalització de l'algoritme d'aprenentatge mitjançant el "benchmark" del "cotxe i la muntanya". Els resultats obtinguts en aquest problema milloren els resultats d'altres metodologies, demostrant la millor capacitat de generalització de les xarxes neurals.

VLSI architecture for motion estimation in underwater imaging

El treball desenvolupat en aquesta tesi aprofundeix i aporta solucions innovadores en el camp orientat a tractar el problema de la correspondència en imatges subaquàtiques. En aquests entorns, el que realment complica les tasques de processat és la falta de contorns ben definits per culpa d'imatges esborronades; un fet aquest que es deu fonamentalment a il·luminació deficient o a la manca d'uniformitat dels sistemes d'il·luminació artificials. Els objectius aconseguits en aquesta tesi es poden remarcar en dues grans direccions. Per millorar l'algorisme d'estimació de moviment es va proposar un nou mètode que introdueix paràmetres de textura per rebutjar falses correspondències entre parells d'imatges. Un seguit d'assaigs efectuats en imatges submarines reals han estat portats a terme per seleccionar les estratègies més adients. Amb la finalitat d'aconseguir resultats en temps real, es proposa una innovadora arquitectura VLSI per la implementació d'algunes parts de l'algorisme d'estimació de moviment amb alt cost computacional.

Collaborative business networks evaluation of technological tools for decision support making

Nowadays, companies are living great difficulties on managing their business due to constant and unpredictable economic market fluctuations. Recent changes in market trends (such as the constant demand for new products and services, mass customization and the drastic reduction of delivery time) lead companies to adopt strategies of creating partnerships with other companies as a way to respond effectively to such difficult economical times. Collaborative Networks’ concept born by the consequence of companies could no longer consider their internal business processes’ management as sufficient and tend to seek for a collaborative approach with other partners for their critical processes. Information technologies (ICT) assumed a major role acting as “enablers” of these kinds of networks, enhancing information sharing and business process integration. Several new trends concerning ICT architectures have been created to support collaborative networks requirements, but still doesn’t exist a common platform to reduce the needed integration effort on virtual organizations. This study aims to investigate the current technological solutions available in the market which enhances the management of companies’ business processes (specially, Collaborative Planning). Finally, the research work ends with the presentation of a conceptual model to answer to the constraints evaluated.

Multi-modal fingerprinting for multimedia assets: optimisation of media security protection in online distribution environments

Since the advent of the internet in every day life in the 1990s, the barriers to producing, distributing and consuming multimedia data such as videos, music, ebooks, etc. have steadily been lowered for most computer users so that almost everyone with internet access can join the online communities who both produce, consume and of course also share media artefacts. Along with this trend, the violation of personal data privacy and copyright has increased with illegal file sharing being rampant across many online communities particularly for certain music genres and amongst the younger age groups. This has had a devastating effect on the traditional media distribution market; in most cases leaving the distribution companies and the content owner with huge financial losses. To prove that a copyright violation has occurred one can deploy fingerprinting mechanisms to uniquely identify the property. However this is currently based on only uni-modal approaches. In this paper we describe some of the design challenges and architectural approaches to multi-modal fingerprinting currently being examined for evaluation studies within a PhD research programme on optimisation of multi-modal fingerprinting architectures. Accordingly we outline the available modalities that are being integrated through this research programme which aims to establish the optimal architecture for multi-modal media security protection over the internet as the online distribution environment for both legal and illegal distribution of media products.

'Operation motorway': landscapes of construction on England's M1 motorway

Recent years have seen an increasing number of academics attempt to write more process-oriented and 'nonrepresentational' accounts of landscape. Drawing upon this literature, I discuss a number of the movements, materialities, and practices entailed in constructing England's M1 motorway in the late 1950s. The performances, movements and durability of a diverse range of things-including earth-moving machines, public relations brochures, maps, helicopters, senior engineers, aggregate and labourers-are shown to be important to the construction and ordering of the motorway and spaces of the construction company in different times and spaces, with people's experiences or understandings of construction, both now and in the past, emerging through memories, talk and embodied encounters with architectures, texts and artefacts which are assembled, circulated and/or archived. Aerial perspectives assumed a prominent role in depictions of construction, while journalists and engineers frequently drew upon a military vocabulary and alluded to the military nature of the project when discussing the motorway. (c) 2005 Elsevier Ltd. All rights reserved.

Mersenne numbers

These notes have been issued on a small scale in 1983 and 1987 and on request at other times. This issue follows two items of news. First, WaIter Colquitt and Luther Welsh found the 'missed' Mersenne prime M110503 and advanced the frontier of complete Mp-testing to 139,267. In so doing, they terminated Slowinski's significant string of four consecutive Mersenne primes. Secondly, a team of five established a non-Mersenne number as the largest known prime. This result terminated the 1952-89 reign of Mersenne primes. All the original Mersenne numbers with p < 258 were factorised some time ago. The Sandia Laboratories team of Davis, Holdridge & Simmons with some little assistance from a CRAY machine cracked M211 in 1983 and M251 in 1984. They contributed their results to the 'Cunningham Project', care of Sam Wagstaff. That project is now moving apace thanks to developments in technology, factorisation and primality testing. New levels of computer power and new computer architectures motivated by the open-ended promise of parallelism are now available. Once again, the suppliers may be offering free buildings with the computer. However, the Sandia '84 CRAY-l implementation of the quadratic-sieve method is now outpowered by the number-field sieve technique. This is deployed on either purpose-built hardware or large syndicates, even distributed world-wide, of collaborating standard processors. New factorisation techniques of both special and general applicability have been defined and deployed. The elliptic-curve method finds large factors with helpful properties while the number-field sieve approach is breaking down composites with over one hundred digits. The material is updated on an occasional basis to follow the latest developments in primality-testing large Mp and factorising smaller Mp; all dates derive from the published literature or referenced private communications. Minor corrections, additions and changes merely advance the issue number after the decimal point. The reader is invited to report any errors and omissions that have escaped the proof-reading, to answer the unresolved questions noted and to suggest additional material associated with this subject.

The structure of crystallisable copolymers of L-lactide, epsilon-caprolactone and glycolide

We apply a new X-ray scattering approach to the study of melt-spun filaments of tri-block and random terpolymers prepared from lactide, caprolactone and glycolide. Both terpolymers contain random sequences, in both cases the overall fraction of lactide units is similar to 0.7 and C-13 and H-1 NMR shows the lactide sequence length to be similar to 9-10. A novel representation of the X-ray fibre pattern as series of spherical harmonic functions considerably facilitates the comparison of the scattering from the minority crystalline phase with hot drawn fibres prepared from the poly(L-lactide) homopolymer. Although the fibres exhibit rather disordered structures we show that the crystal structure is equivalent to that displayed by poly(L-lactide) for both the block and random terpolymers. There are variations in the development of a two-phase structure which reflect the differences in the chain architectures. There is evidence that the random terpolymer includes non-lactide units in to the crystal interfaces to achieve a well defined two-phase structure. (c) 2005 Published by Elsevier Ltd.