Goal-Driven Autonomy (GDA) is a model for online planning extended with dynamic goal selection. GDA has been investigated in the context of numerous abstract planning domains, and there has been recent interest in applying GDA to control unmanned vehicles. In robotic domains, certain continuous state features from sensor data must be modeled for reasoning. However, modeling these features preci...

In this paper, we present a hybrid graph-drawing algorithm (GDA) for layouting large, naturally-clustered, disconnected graphs. We called it a hybrid algorithm because it is an implementation of a series of already known graph-drawing and graphtheoretic procedures. We remedy in this hybrid the problematic nature of the current force-based GDA which has the inability to scale to large, naturally...

The Socio-Cognitive Systems (SCS) Section at Defence Research and Development Canada—Toronto (DRDC Toronto) has undertaken a Technology Investment Fund (TIF) Project entitled “A Conceptual Framework for Understanding Armed Non-state Actors (ANSAs): Strategic Roles and Operational Dynamics.” The aim of this Project is to advance our understanding of (a) the strategic roles of ANSAs in the contex...

Classification by document authorship based on statistical analysis — stylometry — is considered here by using feature vectors obtained from counts of all words in the intersecting sets of the training data. This differs from some previous stylometry, which used only selected “noncontextual” words with the highest counts, and also from conventional text search techniques, where noncontextual wo...

Unmanned vehicles have been the focus of active research on autonomous motion planning, both deliberative and reactive. However, they are fundamentally limited in their autonomy by an inability to independently reason about, prioritize, and change the goals they pursue. We describe two new projects in which we are incorporating goal autonomy on unmanned vehicle platforms. We will apply the Goal...

This paper presents a novel general purpose visualisation environment SPOD (Space Odyssey), that has evolved in relation to our research needs involving analysis and measurement of chaos and complexity in time-series data. More specifically our attention has turned to deriving sleep state information from EEG/EOG. SPOD operates largely as an interpreter of formated data files, to display surfac...

We have developed a method to determine whether a user utterance is directed at the system or not. A spoken dialogue system should not respond to audio inputs that are not directed at it (i.e., a user’s mutter), and it therefore needs to detect such inputs to avoid unsuitable responses. We classify the two cases by logistic regression based on a feature set including utterance timing, utterance...

In certain adversarial environments, reinforcement learning (RL) techniques require a prohibitively large number of episodes to learn a highperforming strategy for action selection. For example, Q-learning is particularly slow to learn a policy to win complex strategy games. We propose GRL, the first GDA system capable of learning and reusing goal-specific policies. GRL is a case-based goal-dri...

Discovering underlying structure from co-occurrence data is an important task in a variety of fields, including: insurance, intelligence, criminal investigation, epidemiology, human resources, and marketing. Previously Kubica et. al. presented the group detection algorithm (GDA) an algorithm for finding underlying groupings of entities from co-occurrence data. This algorithm is based on a proba...

 This paper investigates the effect of decision-makers’ culture on their implicit choice of how to make decisions. In a content analysis of major decisions described in American and Chinese twentieth-century novels, we test a series of hypotheses based on prior theoretical and empirical investigations of cross-cultural variation in human motivation and decision processes. The data show ...