Not all questions are asked with the same intention. Humans tend to address the implicit meaning of the question (that contributes to its pragmatic force), which requires knowledge of the context and a degree of common ground, more so than addressing the explicit propositional content of the question. Is recognizing the pragmatic force in today's human-robot dialogue systems worth the trouble? We focus on display questions (questions to which the asker already knows the answer) and argue that there are realistic human-robot interaction scenarios in existence today that would benefit from the deeper intention recognition. We also propose a method for obtaining display question annotations by embedding an elicitation question into the dialogue. The preliminary study of our robot receptionist shows that at least 16.7% of interactions with the embedded elicitation question include a display question.

The coagulation system (CS) is a complex, inter-connected biological system with major physiological and pathological roles. Adaptive mechanisms such as ubiquitous feedback and feedforward loops create non-linear relationships among its individual components and render the study of this biology at a molecular and cellular level nearly impossible. Computational modeling aims to overcome limitations of current analytical methods through in silico simulation of these complex interplays. We present herein an Agent Based Modeling and Simulation (ABMS) approach for simulating these complex interactions. Our ABMS approach utilizes a subset of 48 rules to define the interactions among 24 enzymes and factors of the CS. These rules simulate the interaction of each “agent”, such as substrates, enzymes, and cofactors, on a two-dimensional grid of ~3,000 cells and ~500,000 agents. Our ABMS method demonstrates the robustness of the physiologic CS system over large ranges of tissue factor (TF) concentrations. The system also demonstrates fragility as complete coagulation occurs at sufficiently high concentrations of TF. Removal of individual coagulation inhibitors from the physiologic system results in system fragility at relatively lower TF concentrations. The complete removal of coagulation inhibitors leads to a system that is incapable of controlling coagulation at all TF concentrations. The synergistic effects of the inhibitory pathways create an intricate regulatory mechanism that allows sufficient clot formation while preventing system wide activation of the CS; a robust system emerges.

This paper addresses the numerical estimation of the principal curvature of pattern transformation manifolds. When a visual pattern undergoes a geometric transformation, it forms a (sub)manifold in the ambient space, which is usually called the transformation manifold. The manifold curvature is an important property characterizing the manifold geometry, with several applications in manifold learning. We propose an efficient numerical algorithm for estimating the principal curvature at a certain point on the transformation manifold.

This paper describes results from a large-scale, complex human study using non-facial and non-verbal affect for victim management in robot-assisted Urban Search and Rescue Applications. Statistically significant results are presented that indicate participants felt emotive robots were more calming, friendlier, and attentive.

We summarize our past, present and future research related to human-robot dialogue, starting with its foundations in collaborative discourse theory, continuing to our current research on recognizing and generating engagement, and concluding with an outline of new work we are beginning on the modeling of long-term relationships between humans and robots.

We develop a topological approach to stratification learning. Given point cloud data drawn from a stratified space, our objective is to infer which points belong to the same strata. First we define a multi-scale notion of a stratified space, giving a stratification for each radius level. We then use methods derived from kernel and cokernel persistent homology to cluster the data points into different strata, and we prove a result which guarantees the correctness of our clustering, given certain topological conditions. We later give bounds on the minimum number of sample points required to infer, with probability, which points belong to the same strata. Finally, we give an explicit algorithm for the clustering and apply it to some simulated data.

In this paper, we propose a novel human-robot-interaction framework for the purpose of rapid visual scene understanding. The task of the robot is to correctly enumerate how many separate objects there are in the scene and to describe them in terms of their attributes. Our approach builds on top of a state-of-the-art 3D segmentation method segmenting stereo reconstructed point clouds into object hypotheses and combines it with a natural dialog system. By putting a `human in the loop', the robot gains knowledge about ambiguous situations beyond its own resolution. Specifically, we are introducing an entropy-based system to spot the poorest object hypotheses and query the user for arbitration. Based on the information obtained from the human-to-robot dialog, the scene segmentation can be re-seeded and thereby improved. We present experimental results on real data that show an improved segmentation performance compared to segmentation without interaction.

Games With A Purpose (or GWAP) provide an interesting way to collect data from web users. With over a million sentences collected and growing steadily, data verification becomes increasingly important. This research explores the alternative of designing human computation games specifically for verification purposes. Two games, Top10 and Pirate and Ghost, are designed for commonsense data verification. Top10 is a single-player game, in which the player attempts to guess the top answers to a given question. We use the frequency data to verify if the assertion is truly common. Pirate and Ghost is a multiplayer guessing role playing game in a network of concepts from the CSKB. We use the game data to identify the relation between two concepts. This paper presents the design of both games, and evaluate the efficiency and precision of each with two experiments. The results show that the two games can be coupled to achiever higher efficiency and precision in the data verification process.

The Predication-based Semantic Indexing (PSI) approach encodes both symbolic and distributional information into a semantic space using a permutation-based variant of Random Indexing. In this paper, we develop and evaluate a computational model of abductive reasoning based on PSI. Using distributional information, we identify pairs of concepts that are likely to be predicated about a common third concept, or middle term. As this occurs without the explicit identification of the middle term concerned, we refer to this process as a “logical leap”. Subsequently, we use further operations in the PSI space to retrieve this middle term and identify the predicate types involved. On evaluation using a set of 1000 randomly selected cue concepts, the model is shown to retrieve with accuracy concepts that can be connected to a cue concept by a middle term, as well as the middle term concerned, using nearest-neighbor search in the PSI space. The utility of quantum logical operators as a means to identify alternative paths through this space is also explored.

This paper presents an anytime algorithm for  incremental intention recognition in a changing world.  The algorithm is performed by dynamically constructing the intention recognition model on top of a prior domain knowledge base. The model is occasionally reconfigured by situating itself in the changing world and removing newly found out irrelevant intentions. We also discuss some approaches to knowledge base representation for supporting situation-dependent model construction. Reconfigurable Bayesian Networks are employed to produce the intention recognition model.