Computer Science researchers have long sought ways to apply the fruits of their labors to education. From the Logo turtles to the latest Cognitive Tutors, the allure of computers that will understand and help humans learn and grow has been a constant thread in Artificial Intelligence research. Now, advances in robotics and our understanding of Human-Robot Interaction make it feasible to develop physically-present robots that are capable of presenting educational material in an engaging manner, adapting online to sensory information from individual students, and building sophisticated, personalized models of a student’s mastery over complex educational domains. In this paper, we discuss how using physical robots as platforms for artificially intelligent tutors enables an expanded space of possible educational interactions. We also describe a work-in-progress to (1) extend previous work in personalized user models for robotic tutoring and (2) further explore the differences between interaction with physical robots and onscreen agents. Specifically, we are examining how embedding an tutoring interaction inside a story, game, or activity with an agent may differentially affect learning gains and engagement in interactions with physical robots and screen-based agents.

It is challenging to build socially-aware robots due to the inherent uncertainty in the dynamics of human behavior. To become socially-aware, robots need to be capable of recognizing activities in their environment to make informed actions in concert with co-present humans. In this paper, we present and validate an event-based method for robots to detect synchronous and asynchronous actions of humans when working as a team in a human-social environment. Our results suggest that our method is capable of detecting synchronous and asynchronous actions, which a step towards building socially aware robots.

This paper describes our ongoing research effort to explore how personality types factor into HRI; in particular, the degree of patience a person has when teaching an error-prone robot in a learning from demonstration setting.Our goal is to establish personality metrics that will ultimately allow for the design of algorithms that automatically tune robot behavior to best suit user preferences based on personality.

Engagement is a key factor in every social interaction, be it between humans or humans and robots. Many studies were aimed at designing robot behavior in order to sustain human engagement. Infants and children, however, learn how to engage their caregivers to receive more attention.We used a social robot platform, DragonBot, that learned which of its social behaviors retained human engagement. This was achieved by implementing a reinforcement learning algorithm, wherein the reward is the proximity and number of people near the robot. The experiment was run in the World Science Festival in New York, where hundreds of people interacted with the robot. After more than two continuous hours of interaction, the robot learned by itself that making a sad face was the most rewarding expression. Further analysis showed that after a sad face, people's engagement rose for thirty seconds. In other words, the robot learned by itself in two hours that almost no-one leaves a sad DragonBot.

We study the scheduling of human-robot teams where the human and robotic agents share decision-making authority over scheduling decisions. Our goal is to design AI scheduling techniques that account for how people make decisions under different control schema.

This paper presents an experiment investigating what type of progress feedback users prefer in verbal updates by a robot about remotely performed tasks. Of primary concern is that users find the information presented useful. But as users in their home may be engaged in other activities while they wait for a service, it is also important that information is presented in a way and at a frequency that they do not find distracting or disruptive. We explore these issues through a human-robot interaction experiment involving a simulated food delivery service. We also discuss future research directions that involve giving naive users more input into the planning process.

Recent psychological experiments intend to show that social intentions can be read from the recording of motor actions (Becchio, Sartori, and Castiello 2010; Ferri et al. 2011). At the center of the debate is the hypothesis that the motor system is (Blackemore and Decety 2001), or is not (Jacob and Jeannerod 2005) used to recognize social intentions, with a potential openning to a bottom-up understanding of social behavior, agentivity and theory of mind. In (Becchio et al. 2007), the authors proposed to record the arm's trajectories during episodes of a "pick and place" task with a motor vs social outcome. The results provided evidence for differences in motor patterning depending on the social context and intention, but where not yet a direct evidence of the involvement of the motor system in recognizing social intention. In (Becchio, Sartori, and Castiello 2010; Ferri et al. 2011), the authors show how social affordances can change the movement parametrization with the hypothesis that a same action linked to a social context may involve an increase of the index of difficulty.

In signal analysis and synthesis, linear approximation theory considers a linear decomposition of any given signal in a set of atoms, collected into a so-called dictionary. Relevant sparse representations are obtained by relaxing the orthogonality condition of the atoms, yielding overcomplete dictionaries with an extended number of atoms. More generally than the linear decomposition, overcomplete kernel dictionaries provide an elegant nonlinear extension by defining the atoms through a mapping kernel function (e.g., the gaussian kernel). Models based on such kernel dictionaries are used in neural networks, gaussian processes and online learning with kernels. The quality of an overcomplete dictionary is evaluated with a diversity measure the distance, the approximation, the coherence and the Babel measures. In this paper, we develop a framework to examine overcomplete kernel dictionaries with the entropy from information theory. Indeed, a higher value of the entropy is associated to a further uniform spread of the atoms over the space. For each of the aforementioned diversity measures, we derive lower bounds on the entropy. Several definitions of the entropy are examined, with an extensive analysis in both the input space and the mapped feature space.

In this study, a system for allowing combination of textmining and crowdsourcing of annotation approaches for detection of DDIs from drug package inserts is presented. An annotation study was designed to evaluate expert versus non-expert curation performance, and the impact of NLP pre-annotation on precision and recall on both groups. The design and development of the system and annotation study, consisted of three stages. First, our existing NLP pipeline for DDI extraction was improved, and it was used to preannotate 208 drug product labels with drug mentions and DDIs. Secondly, a DDI machine readable representation scheme was created using the Annotation Ontolgy. This model allowed us to load the NLP preannotated drug label sections into our plugin for human curation created using the Annotation tool DOMEO. Finally, the annotation study was performed along with usability questionnaires for collecting qualitative feedback. To our knowledge, this is the first study in comparing experts and non-experts for pharmacokinetic DDI annotation. Results showed lower performance on non-experts compared with expert annotation without the use of NLP,and an improvement of non-expert annotation performance using the NER module of the NLP assistance. Simplification of the workflow for NLP assisted annotation is necessary for scaling ourapproach.

Programming by Demonstration (PbD) can allow end-users to teach robots new actions simply by demonstrating them. However, learning generalizable actions requires a large number of demonstrations that is unreasonable to expect from end-users. In this paper, we explore the idea of using crowdsourcing to collect action demonstrations from the crowd. We propose a PbD framework in which the end-user provides an initial seed demonstration, and then the robot searches for scenarios in which the action will not work and requests the crowd to fix the action for these scenarios. We use instance-based learning with a simple yet powerful action representation that allows an intuitive visualization of the action. Crowd workers directly interact with these visualizations to fix them. We demonstrate the utility of our approach with a user study involving local crowd workers (N=31) and analyze the collected data and the impact of alternative design parameters so as to inform a real-world deployment of our system.