The past decade has witnessed an increasing interest in the use of virtual coaches in healthcare. This paper describes a virtual coach to provide mindfulness meditation training, and the coaching support necessary to begin a regular practice. The coach is implemented as an embodied conversational character, and provides mindfulness training and coaching support via a web-based application. The coach is represented as a female character, capable of showing a variety of affective and conversational expressions, and interacts with the user via a mixed-initiative, text-based, natural language dialogue. The coach adapts both its facial expressions and the dialogue content to the user’s learning needs and motivational state. Findings from a pilot evaluation study indicate that the coach-based training is more effective in helping users establish a regular practice than self-administered training via written and audio materials. The paper concludes with an analysis of the coach features that contribute to these results, discussion of key challenges in affect-adaptive coaching, and plans for future work.

There is an urgent need for interventions to assist teenagers and young adults in appreciating the physical and social risks of binge drinking. While research on the health risks associated with alcohol abuse is well developed, the translation and communication of this knowledge to young people is not. This paper describes a prototype visualisation tool, an Alcohol Risk Calculator, that provides personalised information on risks associated with alcohol consumption based on individual drinking habits. Its design is informed by studies of graphical literacy, evidence on forms of presenting risk that aid understanding, and theory that provides insight into changing health damaging behaviour.

The goal of our research is to find patterns of EEG activity that will allow us to correctly identify seizures in living rats using machine learning techniques. Features are extracted from the EEG to characterize the signal over time. We perform model selection to reduce the set of features, as the goal is to have the algorithm running on a small personal device. The chosen features are used within a supervised classifier, based on randomized forests, in order to separate the different brain states. One of the challenges of this research is to detect all seizures, while preserving a low false positive rate, and low detection latency. We present results showing we can achieve this using data from three separate animals. The long-term goal of this research is to use this seizure detection method as part of a closed-loop adaptive neuro-stimulation device to reduce the incidence and duration of seizures.

One challenge of building and maintaining large-scale data management systems is managing data fusion from multiple data sources. Often times, different data sources may represent the same data element in a slightly different way. These differences may represent an error in the data or a disagreement between sources on the correct value that best represents the data point. When the quantity of data managed and fused becomes sufficiently large, manual review becomes impossible, and automated systems must be built to manage data fusion. Some of the traditional solutions use simple voting theory, Dempster-Shafer theory, fuzzy matching and incremental learning. This paper presents a novel approach to data fusion in the domain of business listings. The task at hand, business listing categorization, suffers from conflicting and incomplete data from disparate data sources. Given the need for a high degree of accuracy in this task, we use a combination of case-based reasoning, joint probability, and domain-specific rules to improve data accuracy above other methods.

Decision-making is crucially important at all levels of biological complexity, from within single-celled organisms, through neural populations within the vertebrate brain, to collections of social organisms such as colonies of ants and honeybees, or societies of humans. What are the prospects for unifying the study of these apparently disparate systems? All can be conceptualised as voting systems at the appropriate level. In this review I will argue that optimality theory can be of fundamental importance in understanding all these systems. In particular I will argue that for groups without conflict of interests, such as neurons and social insect colonies, similar mechanisms could implement statistically optimal decision-making in apparently highly different systems at different levels of biological complexity. I will consider what currency these systems should optimize, and speculate about the possible application of this understanding to the design of voting systems where individual group members' interests are aligned, such as in certain types of human group, and in collectives of robots. I will also consider how established results from economics and political science, notably Arrow's Impossibility Theorem and Condorcet’s ‘jury theorem’, might relate to what we know of social insect voting systems, where interesting effects such as the emergence of collective rationality from the voting of irrational individuals have recently been demonstrated.

Voting systems have complex and dynamic properties that are useful in modeling behavior in physical systems. The goal of this symposium is to bring together diverse perspectives on applications of voting analysis to share ideas about gaining theoretical insight and conducting experiments to increase our knowledge. Topics will include the study of social insects, risk analysis, voting theory, combining simulations of group behavior, personal genome analysis, business classification, robots, and man-machine interaction. Joint sessions on multirobot systems and human-agent collaboration are planned.

Puck Clustering, a particularly widely studied problem domain for self-organized multi-robot systems, involves gathering spatially distributed objects, called pucks, into piles within a planar workspace. Structures in the environment (partially formed clusters) encode information about where clusters should be formed, and their positions are involved in the mechanics of subsequent cluster formation. In this paper, we consider questions regarding the spatial distribution of robots and clusters, and their relation to the boundaries of the workspace. Prior theoretical analysis has assumed a uniform distribution of robots for gathering all objects into a single pile. Yet, in some instances, a disproportionate amount of time may be spent by robots on the boundary. Also, others have documented that the boundary can cause cluster growth itself. This paper considers the problem of clustering square boxes in the center of the workspace. The flat edges of these objects appear to exacerbate the affinity for cluster growth near boundaries. However, by exploiting the shape of our objects, we show that novel "Twisting" and "Digging" operations overcome this effect and enhance production of central clusters. We analyze the dynamics of boundary versus central puck clusters, and investigate how the spatial distribution of the robots changes along with the clustering process: showing stark differences between the standard mode of clustering and the mode we introduce here.

Inspired by the Rapidly Exploring Random Tree data-structure and algorithm for path planning in high-dimensional, continuous spaces, we consider an approach for spanning a space with a group of simple robots. We employ a minimalist approach in which InfraRed and contact sensors form the primary means of communication; the agents physically embody the elements of the tree through their position and other agents can either follow the tree to useful locations or expand the tree by becoming part of it. Although robots are constrained in some of the operations they may perform in space, we argue that our approach remains consistent with the original data-structure. We demonstrate that one may perform a planning query from a point to the tree origin directly via message passing where passing involves direct physical motion or simple IR messages. Based on the work done by Werger and Matarić , our implementation proves that it is possible to form and maintain a RRT using simple position unaware robots. The work is important because it demonstrates that decentralized path planning can be performed by simple agents using purely reactive behaviors and at the same time poses significant challenges to keep the shape of the tree intact.

A multi-robot system, like a robot formation, contains information that is distributed throughout the system. As the collective increases in numbers or explores distant or difficult areas, obtaining collective situational awareness becomes critical. We propose a method for extracting system and environmental information distributed over a collective of robots.

We introduce CIM, a Commonsense Inference Memory system utilizing both Extended Semantic Networks and Bayesian Networks that builds upon the commonsense knowledgebase ConceptNet. CIM introduces a new technique for self-assembling Bayesian Networks that allows only relevant parts of the commonsense database to affect the inference. The Bayesian Network include the activity in the input sentences and the related activities appearing in the commonsense database. They are used to interpret and infer the meaning of the set of sentences input. Without self-assembled networks, only relevant inference is performed, speeding up performance of reasoning with commonsense knowledge. We demonstrate that our system can disambiguate the needs of the user even if they do not state them directly, and do not use keywords. This ability would not be possible without either the use of commonsense or significant training. Eventually this approach may be applied to increase the effectiveness of other natural language understanding techniques as well.