32 research outputs found
Using self-attention LSTMs to enhance observations in goal recognition
No full textGoal recognition is the task of identifying the goal an observed agent is pursuing. The quality of its results depends on the quality of the observed information. In most goal recognition approaches, the accuracy significantly decreases in settings with missing observations. To mitigate this issue, we develop a learning model based on LSTMs, leveraging attention mechanisms, to enhance observed traces by predicting missing observations in goal recognition problems. We experiment using a dataset of goal recognition problems and apply the model to enhance the observation traces where missing. We evaluate the technique using a state-of-the-art goal recognizer in four different domains to compare the accuracy between the standard and the enhanced observation traces. Experimental evaluation shows that recurrent neural networks with self-attention mechanisms improve the accuracy metrics of state-of-the-art goal recognition techniques by an average of 60%
Tarefas para reconhecimento de planos baseadas em pontos de refer?ncia
No full textSubmitted by Setor de Tratamento da Informa??o - BC/PUCRS ([email protected]) on 2016-07-26T14:20:24Z
No. of bitstreams: 1
DIS_RAMON_FRAGA_PEREIRA_COMPLETO.pdf: 1672915 bytes, checksum: 3cf47a5c224b3f99a343aab57bf00bf3 (MD5)Made available in DSpace on 2016-07-26T14:20:24Z (GMT). No. of bitstreams: 1
DIS_RAMON_FRAGA_PEREIRA_COMPLETO.pdf: 1672915 bytes, checksum: 3cf47a5c224b3f99a343aab57bf00bf3 (MD5)
Previous issue date: 2016-03-15Recognition of goals and plans using incomplete evidence from action execution can be
done efficiently by using automated planning techniques. In many applications it is important to recognize goals and plans not only accurately, but also quickly. In order to address this challenge, we develop recognition approaches based on planning techniques that rely on planning landmarks to filter candidate goals and plans from observations. In automated planning, landmarks are properties or actions that cannot be avoided to achieve a goal. We address the task of recognizing goals and plans without pre-defined static plan libraries, and instead we use a planning domain definition to represent the problem and the expected agent behavior. In this work, we show the applicability of planning techniques for recognition tasks in three settings: first, we use planning landmarks to develop a heuristic-based plan recognition approach; second, we refine an existing planningbased plan recognition approach; and finally, we use planning techniques to develop an approach for detecting plan abandonment. The plan abandonment detection approach we develop aims to analyze a sequence of observations and a monitored goal to determine if an observed agent is still pursuing, or has no intention to complete such monitored goal. These recognition approaches are evaluated in experiments over several planning domains. We show that our plan recognition approach yields not only accuracy comparable to other state-of-the-art techniques, but also substantially lower recognition time over such techniques. Furthermore, our plan abandonment detection approach yields high accuracy at low computational cost to detect which actions do not contribute for achieving a particular monitored goal.T?cnicas de planejamento autom?tico s?o eficientes no reconhecimento de objetivos e
planos a partir da execu??o de a??es e evid?ncias incompletas. Para muitas aplica??es ? importante
reconhecer objetivos e planos n?o somente acuradamente, mas tamb?m de maneira r?pida
e precisa. Assim, para lidar com esse desafio, desenvolvemos uma abordagem a qual utiliza uma
heur?stica baseada em t?cnicas de planejamento autom?tico, guiando-se por pontos-de-refer?ncia,
que filtra poss?veis objetivos e planos a partir de observa??es. Em planejamento autom?tico, pontosde-
refer?ncia s?o propriedades (ou a??es), em que todo o plano precisa alcan?ar (ou executar), em
alguma determinada parte da execu??o do plano a fim de atingir um objetivo estipulado. Neste
trabalho, formalizamos a tarefa de reconhecimento de objetivos e planos sem a utiliza??o de biblioteca
de planos, ou seja, utilizamos uma defini??o de dom?nio para planejamento autom?tico. Sendo
assim, estabelecemos o problema e o comportamento do agente a ser observado (a??es e objetivos)
utilizando uma linguagem de planejamento autom?tico. A partir disso, mostramos a aplicabilidade
da nossa abordagem baseada em t?cnicas de planejamento de tr?s formas: (1) desenvolvendo uma
heur?stica baseada em pontos-de-referencia para reconhecer objetivos e planos; (2) refinando uma
abordagem existente para reconhecimento de planos; e for fim, (3) desenvolvendo uma abordagem
para reconhecer abandono de planos. A abordagem para reconhecimento de abandono de planos
desenvolvida tem como objetivo analisar uma seq??ncia de observa??es (a??es), afim de detectar
quais n?o contribuem para alcan?ar o objetivo o qual est? sendo monitorado. Para fins de avalia??o
e experimenta??o, utilizou-se v?rios dom?nios de planejamento autom?tico, e com isso, foi poss?vel
mostrar que nossa abordagem para reconhecimento de planos comporta-se acuradamente e rapidamente
quando comparada com o estado-da-arte. Ainda, demonstramos que a nossa abordagem para
detectar abandono de planos comporta-se com precis?o e com baixo custo computacional, detectando
precisamente a??es que n?o contribuem para alcan?ar um determinado objetivo monitorado
Mapping mental states into propositional planning
No full textMost BDI agent architectures rely on plan libraries in order to ensure bounded time for means-ends reasoning. Nevertheless, the usage of fast planning algorithms to provide the agent with runtime planning capabilities is an alternate approach to augment agent autonomy and flexibility. This paper proposes an autonomous agent architecture based on the integration of a logic-based BDI model with propositional planning algorithms through a mapping process. 1
2015 Brainhack Proceedings
No full textTable of contents I1 Introduction to the 2015 Brainhack Proceedings R. Cameron Craddock, Pierre Bellec, Daniel S. Margules, B. Nolan Nichols, Jörg P. Pfannmöller A1 Distributed collaboration: the case for the enhancement of Brainspell’s interface AmanPreet Badhwar, David Kennedy, Jean-Baptiste Poline, Roberto Toro A2 Advancing open science through NiData Ben Cipollini, Ariel Rokem A3 Integrating the Brain Imaging Data Structure (BIDS) standard into C-PAC Daniel Clark, Krzysztof J. Gorgolewski, R. Cameron Craddock A4 Optimized implementations of voxel-wise degree centrality and local functional connectivity density mapping in AFNI R. Cameron Craddock, Daniel J. Clark A5 LORIS: DICOM anonymizer Samir Das, Cécile Madjar, Ayan Sengupta, Zia Mohades A6 Automatic extraction of academic collaborations in neuroimaging Sebastien Dery A7 NiftyView: a zero-footprint web application for viewing DICOM and NIfTI files Weiran Deng A8 Human Connectome Project Minimal Preprocessing Pipelines to Nipype Eric Earl, Damion V. Demeter, Kate Mills, Glad Mihai, Luka Ruzic, Nick Ketz, Andrew Reineberg, Marianne C. Reddan, Anne-Lise Goddings, Javier Gonzalez-Castillo, Krzysztof J. Gorgolewski A9 Generating music with resting-state fMRI data Caroline Froehlich, Gil Dekel, Daniel S. Margulies, R. Cameron Craddock A10 Highly comparable time-series analysis in Nitime Ben D. Fulcher A11 Nipype interfaces in CBRAIN Tristan Glatard, Samir Das, Reza Adalat, Natacha Beck, Rémi Bernard, Najmeh Khalili-Mahani, Pierre Rioux, Marc-Étienne Rousseau, Alan C. Evans A12 DueCredit: automated collection of citations for software, methods, and data Yaroslav O. Halchenko, Matteo Visconti di Oleggio Castello A13 Open source low-cost device to register dog’s heart rate and tail movement Raúl Hernández-Pérez, Edgar A. Morales, Laura V. Cuaya A14 Calculating the Laterality Index Using FSL for Stroke Neuroimaging Data Kaori L. Ito, Sook-Lei Liew A15 Wrapping FreeSurfer 6 for use in high-performance computing environments Hans J. Johnson A16 Facilitating big data meta-analyses for clinical neuroimaging through ENIGMA wrapper scripts Erik Kan, Julia Anglin, Michael Borich, Neda Jahanshad, Paul Thompson, Sook-Lei Liew A17 A cortical surface-based geodesic distance package for Python Daniel S Margulies, Marcel Falkiewicz, Julia M Huntenburg A18 Sharing data in the cloud David O’Connor, Daniel J. Clark, Michael P. Milham, R. Cameron Craddock A19 Detecting task-based fMRI compliance using plan abandonment techniques Ramon Fraga Pereira, Anibal Sólon Heinsfeld, Alexandre Rosa Franco, Augusto Buchweitz, Felipe Meneguzzi A20 Self-organization and brain function Jörg P. Pfannmöller, Rickson Mesquita, Luis C.T. Herrera, Daniela Dentico A21 The Neuroimaging Data Model (NIDM) API Vanessa Sochat, B Nolan Nichols A22 NeuroView: a customizable browser-base utility Anibal Sólon Heinsfeld, Alexandre Rosa Franco, Augusto Buchweitz, Felipe Meneguzzi A23 DIPY: Brain tissue classification Julio E. Villalon-Reina, Eleftherios Garyfallidi
GoCo: Planning Expressive Commitment Protocols
No full textThis article addresses the challenge of planning coordinated activities for a set of autonomous agents, who coordinate according to social commitments among themselves. We develop a multi-agent plan in the form of a commitment protocol that allows the agents to coordinate in a flexible manner, retaining their autonomy in terms of the goals they adopt so long as their actions adhere to the commitments they have made. We consider an expressive first-order setting with probabilistic uncertainty over action outcomes. We contribute the first practical means to derive protocol enactments which maximise expected utility from the point of view of one agent. Our work makes two main contributions. First, we show how Hierarchical Task Network planning can be used to enact a previous semantics for commitment and goal alignment, and we extend that semantics in order to enact first-order commitment protocols. Second, supposing a cooperative setting, we introduce uncertainty in order to capture the reality that an agent does not know for certain that its partners will successfully act on their part of the commitment protocol. Altogether, we employ hierarchical planning techniques to check whether a commitment protocol can be enacted efficiently, and generate protocol enactments under a variety of conditions. The resulting protocol enactments can be optimised either for the expected reward or the probability of a successful execution of the protocol. We illustrate our approach on a real-world healthcare scenario.Algorithmic
Support for arbitrary regions in XSL-FO
No full textThis paper proposes an extension of the XSL-FO standard which allows the specification of an unlimited number of arbitrarily shaped page regions. These extensions are built on top of XSL-FO 1.1 to enable flow content to be laid out into arbitrary shapes and allowing for page layouts currently available only to desktop publishing software. Such a proposal is expected to leverage XSL-FO towards usage as an enabling technology in the generation of content intended for personalized printing
Anisotropy of Alfvénic Turbulence in the Solar Wind and Numerical Simulations
No full text10.12.13 KB. Ok to add published version to spiral, RAS/OUP polic
Avaliação do uso de agentes no desenvolvimento de aplicações com veículos aéreos não-tripulados
No full textDissertação (mestrado) - Universidade Federal de Santa Catarina, Centro Tecnológico, Programa de Pós-Graduação em Engenharia de Automação e Sistemas, Florianópolis, 2015.O uso de agentes em aplicações com Veículos Aéreos Não-Tripulados (VANTs) tem sido explorado nos últimos anos, principalmente como alternativa para dotar o veículo de autonomia na realização de suas missões. Este trabalho tem como objetivo desenvolver um modelo de comportamento autônomo para um VANT com o uso de um agente com arquitetura BDI, explorando sua capacidade de reagir rapidamente a mudanças em seu ambiente e de ter objetivos de longo prazo a serem cumpridos até se finalizar uma dada missão. O trabalho também busca avaliar a implementação do agente na plataforma de sistema embarcado de um VANT real, a aeronave do projeto ProVant, além de apresentar uma análise e comparação do sistema proposto, baseado em lógica de predicados, com uma abordagem usual empregando uma programação imperativa, organizada em uma sequencia de comandos e ações.Abstract : The use of agents in applications with Unmanned Aerial Vehicles (UAVs) has been explored in recent years, mainly as an alternative to provide autonomy to the vehicle in carrying out their missions.This study aims to develop and evaluate a model for a UAV with the use of an agent with BDI architecture, exploring its ability to reactquickly to changes in the environment and while still having goals tobe accomplished even finish a given mission. The proposed model was implemented and embedded in a real UAV system and then compared against a usual approach employing an imperative programming
