Decentralized planning in uncertain environments is a complex task generally dealt with by using a decision-theoretic approach, mainly through the framework of Decentralized Partially Observable Markov Decision Processes (DEC-POMDPs). Although DEC-POMDPS are a general and powerful modeling tool, solving them is a task with an overwhelming complexity that can be doubly exponential. In this paper, we study an alternate formulation of DEC-POMDPs relying on a sequence-form representation of policies. From this formulation, we show how to derive Mixed Integer Linear Programming (MILP) problems that, once solved, give exact optimal solutions to the DEC-POMDPs. We show that these MILPs can be derived either by using some combinatorial characteristics of the optimal solutions of the DEC-POMDPs or by using concepts borrowed from game theory. Through an experimental validation on classical test problems from the DEC-POMDP literature, we compare our approach to existing algorithms. Results show that mathematical programming outperforms dynamic programming but is less efficient than forward search, except for some particular problems. The main contributions of this work are the use of mathematical programming for DEC-POMDPs and a better understanding of DEC-POMDPs and of their solutions. Besides, we argue that our alternate representation of DEC-POMDPs could be helpful for designing novel algorithms looking for approximate solutions to DEC-POMDPs.

In this paper, we propose a model of the web of data as a graph of interlinked graphs which goes beyond the standard single-graph RDF semantics, describe two different ways in which a query on this structure can be answered, and characterize semantically each of these ways in terms of restrictions on the relation between the domain of interpretation of each single component graph.

Semantic technologies are available, and gain popularity on the Web as well as on the desktop, but both (desktop and Web) act as large data silos, making personal and online data difficult to interlink. We propose a system that enables easy publishing of personal notes as linked social media content, while at the same time semantically enriching the desktop resources with information retrieved from the Linked Data cloud. The transformation, publication and linking process is integrated with the familiar desktop applications and online blogging platforms, providing a better usability experience.

Territorial privacy is an old concept for privacy of the personal space dating back to the 19th century. Despite its former relevance, territorial privacy has been neglected in recent years, while privacy research and legislation mainly focused on the issue of information privacy. However, with the prospect of smart and ubiquitous environments, territorial privacy deserves new attention. Walls, as boundaries between personal and public spaces, will be insufficient to guard territorial privacy when our environments are permeated with numerous computing and sensing devices, that gather and share real-time information about us. Territorial privacy boundaries spanning both the physical and virtual world are required for the demarcation of personal spaces in smart environments. In this paper, we analyze and discuss the issue of territorial privacy in smart environments. We further propose a real-time user-centric observation model to describe multimodal observation channels of multiple physical and virtual observers. The model facilitates the definition of a territorial privacy boundary by separating desired from undesired observers, regardless of whether they are physically present in the user’s private territory or virtually participating in it. Moreover, we outline future research challenges and identify areas of work that require attention in the context of territorial privacy in smart environments.

Some of the top legal ontologies developed so far include the Functional Ontology for Law [FOLaw] The increasing need for legal information and content (Valente 1995), the Frame-Based Ontology (van Kralingen management caused by the growing amount of 1995), the LRI-Core ontology (Breuker 2004), unstructured (or poorly structured) legal data managed by DOLCE CLO [Core Legal Ontology] (Gangemi et al. legal publishing companies, law firms and public 2003), or the Ontology of Fundamental Concepts (Rubino administrations, or the increasing amount of legal et al. 2006, Sartor 2006) the basis for the LKIF-Core information directly available on the World Wide Web, Ontology (Breuker et al. 2007). Nevertheless, most legal have created an urgent need to construct conceptual ontologies are domain specific ontologies, which represent structures for knowledge representation to share and particular legal domains towards search, indexing and manage intelligently all this information, whilst making reasoning in a specific domain of national or European law human-machine communication and understanding (e.g. the IPRONTO ontology by Delgado et al. 2003, the possible.

We summarise the experimental design issues related to timing in several human-robot interaction scenarios investigating turn-taking or synchronization between child-sized humanoid robots and human participants. Our aim is not to have the humanoid robots just replicate the human’s behaviours (e.g. waving, peek-a-boo, or drumming), but to engage in interactions in a socially appropriate manner. From these various studies, we have identified several ways in which time has an impact on interaction. We have also identified practical concerns about data collection for time-dependent interactions and ways to address them. The conclusions drawn from this work is likely to be useful in informing the design of systems which engage in synchronized or turn-taking interactions with people.

A key challenge for policymakers in many developing countries is to decide which intervention or collection of interventions works best to improve learning outcomes in their schools. Our aim is to develop a causal model that explains student learning outcomes in terms of observable characteristics as well as conditions and processes difficult to observe directly. We start with a theoretical model based on the results of previous research, direct experience and experts’ knowledge in the field. This model is then refined through application of supervised learning methods to available data sets. Once calibrated with local data in a country, the model estimates the probability that a given intervention would affect learning outcomes.

For autonomous systems such as unmanned aerial vehicles tosuccessfully perform complex missions, a great deal of embedded reasoning is required at varying levels of abstraction. In order to make use of diverse reasoning modules in such systems, issues ofintegration such as sensor data flow and information flow between such modules has to be taken into account. The DyKnow framework is a tool with a formal basis that pragmatically deals with many of the architectural issues which arise in such systems. This includes a systematic stream-based method for handling the sense-reasoning gap,caused by the wide difference in abstraction levels between the noisy data generally available from sensors and the symbolic, semantically meaningful information required by many high-level reasoning modules. DyKnow has proven to be quite robust and widely applicable to different aspects of hybrid software architectures forrobotics. In this paper, we describe the DyKnow framework and show how it is integrated and used in unmanned aerial vehicle systems developed in our group. In particular, we focus on issues pertaining to the sense-reasoning gap and the symbol grounding problem and the use of DyKnow as a means of generating semantic structures representing situational awareness for such systems. We also discuss the use of DyKnow in the context of automated planning, in particular execution monitoring.

With the introduction of low-cost wireless communication many new applications have been made possible; applications where systems can collaboratively learn and get wiser without human supervision. One potential application is automated monitoring for fault isolation in mobile mechatronic systems such as commercial vehicles. The paper proposes an agent design that is based on uploading software agents to a fleet of mechatronic systems. Each agent searches for interesting state representations of a system and reports them to a central server application. The states from the fleet of systems can then be used to form a consensus from which it can be possible to detect deviations and even locating a fault.

In this paper we describe the production and consumption of linked data in the scenario of the Italian news agency ANSA portal. The goal of the use-case is to provide viewers of a news item with background information and links to related news articles contained on the portal. This information enrichment process is entity-based: ANSA news archive is analyzed using Name Entity Recognition, and each detected entity is annotated with a unique identifier. These identifiers are obtained using the Entity Name Server developed within the scope of the OKKAM European project. Subsequently the news are published on the portal using RDFa and linked to a semantic search engine that provides background information harvested from sources such as DBpedia and links to additional news sources. The presented project has the potential to contribute to Linked Data by creating and publishing a large quantity of entities and assertions about them coming from the ANSA news archive.