This paper extends hierarchical task network (HTN) planning with lightweight learning, considering that in robotics, actions have a non-zero probability of failing. Our work applies to A*-based HTN planners with lifting. We prove that the planner finds the plan of maximal expected utility, while retaining its lifting capability and efficient heuristic-based search. We show how to learn the probabilities online, which allows a robot to adapt by replanning on execution failures. The idea behind this work is to use the HTN domain to constrain the space of possibilities, and then to learn on the constrained space in a way requiring few training samples, rendering the method applicable to autonomous mobile robots.

This would allow teams to have an objective currency for trust transactions. These systems would allow another surface for autonomous Ali, A.S., Rana, O., and Walker, D.W. (2004): "WS-QoC: agents to integrate the social fabric with information Measuring Quality of Service Compliance," International gathered in virtual environments. Further, the system would Conference on Service Oriented Computing (ICSOC04), New increase illumination of dark networks engaged in illicit York, NY. covert activity. Participants would be assigned a score Allbeck, J., and Badler, N. (2002): "Toward Representing Agent similar to FICO scores; when an individual score falls Behaviors Modified by Personality and Emotion," Autonomous noticeably or falls below a threshold, further observation Agents and Multiagent Systems, Bologna, Italy.

In this paper we examine the case of a mobile robot that is part of a human-robot urban search and rescue (USAR) team. During USAR scenarios, we would like the robot to have a geometrical-functional understand- ing of space, using which it can infer where to perform planned tasks in a manner that mimics human behav- ior. We assess the situation awareness of rescue work- ers during a simulated USAR scenario and use this as an empirical basis to build our robot’s spatial model. Based upon this spatial model, we present “functional map- ping” as an approach to identify regions in the USAR environment where planned tasks are likely to be opti- mally achievable. The system is deployed and evaluated in a simulated rescue scenario.

Existing personalisation approaches, such as collaborative filtering or content based recommendations, are highly dependent on the domain and/or the source of the data. Therefore, there is a need for more accurate means to capture and model the interests of the user across domains, and to interlink them in a semantically-enhanced interest graph. We propose a new approach for multi-source, cross-genre recommendations that can exploit the heterogeneous nature of user profile data, which has been aggregated from multiple personalised web services, such as blogs, wikis and microblogs. Our approach is based on the Spreading Activation model that exploits intrinsic links between entities across a number of data sources. The proposed method is highly customizable and applicable both to generic and specific recommendation scenarios and use cases. With the growing number of Social Web applications in the enterprise (blogs, wikis, micro blogging, etc.), it becomes difficult for knowledge workers to avoid content overload and to quickly identify relevant people, communities and information. We demonstrate the application of our approach in an industrial use case that involves recommendation of social semantic data across multiple services in a distributed collaborative environment.

Recently, online vendors and providers manage review systems as a mechanism to advertise their services and goods over the Web. In making their choice, clients can rely on feedback expressing the degree of satisfaction of past users with respect to such services and goods. This set of feedback, or reviews, may be filtered by categories of users, they may be affected by multiple factors, and they are elaborated in order to obtain an overall score, representing a global indicator aimed at summarising the level of quality of that service. In this paper, we concentrate on multi-factor review,~\ie a review whose value is computed assembling the scores given to a set of parameters that may affect the quality level of a service. Our interest is evaluating the relevance, or dominance, of some parameter with respect to the others. We advocate the use of the Analytic Hierarchy Process, a well-known technique born in the area of multi-criteria decision making, to derive the priorities to assign to the scores of the single parameters. We illustrate the proposal on the example of hotel reviews.

Open query answering is the idea of answering queries that are not given using the vocabulary of the queried knowledge base but instead the vocabulary of the inquirer. Many aspects of open query answering can be tackled through the combination of human effort with algorithmic techniques. In this paper we explore its applicability to crowdsourcing, using a framework in which human and computational intelligence can co-exist by augmenting existing Linked Data and Linked Service technology with crowdsourcing functionality. We analyze how the task can be decomposed and translated into Mechanical Turk projects in order to achieve this vision.

We present Kinect@Home, aimed at collecting a vast RGB-D dataset from real everyday living spaces. This dataset is planned to be the largest real world image col- lection of everyday environments to date, making use of the availability of a widely adopted robotics sensor which is also in the homes of millions of users, the Mi- crosoft Kinect camera.

The fragmentation of research in AI and robotics has created a vast repertoire of skills a robot could be equipped with but that must be manually integrated to form a complex action. We propose a novel evolutionary algorithm that aims at autonomously integrating, adapting and creating new actions by re-using skills that are either externally provided or previously generated. Complex actions are created by instantiating a Finite State Automaton and new skills are created using fully recurrent neural networks. We validated our approach in two scenarios, i.e. exploration and moving to pre-grasp positions. Our experiments show that complex actions can be created by composing independently developed skills. The results have been applied and tested with a real robot in a variety of scenarios.

Brain structure exhibits systematic relationships with a variety of an individual’s cognitive abilities and such relationships can be captured by voxel-based morphometry (VBM) that computes regional gray matter volume based on anatomical MRIs. This method has been successfully used to reveal brain regions that are associated with individual differences in a broad range of contexts such as perceptual performance, attention control, face recognition, introspection and personality traits. Here, we show that such relationships with brain structure extend to complex social behaviors by presenting our recent VBM studies that examined the relationships between brain structure and diverse aspects of socio-cognitive behavioral traits. Specifically, we identified brain regions in which individual differences in gray matter volumes were associated with political orientation, moral sentiment, empathy and loneliness. These findings suggest that information derived from standard MRI scans could be used to extract information about an individual’s real-world and online social behavior. Unlike conventional functional neuroimaging research, our structural neuroimaging approach does not require a virtual environment that emulates social interactions and thus can directly link brain structure to real-world human behavior. As such, our approach based on individual differences in brain structure and behavior provides an important anchor point that integrates genetic and environmental factors determining diversity of human cognition and behavior.

Successfully accomplishing everyday manipulation tasks requires robots to have substantial knowledge about the objects they interact with, the environment they operate in as well as about the properties and effects of the actions they perform. Often, this knowledge is implicitly contained in manually written control programs, which makes it hard for the robot to adapt to newly acquired information or to re-use knowledge in a different context. By explicitly representing this knowledge, control decisions can be formulated as inference tasks which can be sent as queries to a knowledge base. This allows the robot to take all information it has at query time into account to generate answers, leading to better flexibility, adaptability to changing situations, robustness, and the ability to re-use knowledge once acquired. In this paper, we report on our work towards a practical and grounded knowledge representation and inference system. The system is specifically designed to meet the challenges created by using knowledge processing techniques on autonomous robots, including specialized inference methods, grounding of symbolic knowledge in the robot's control structures, and the acquisition of the different kinds of knowledge a robot needs.