A social robot should be able to understand human’s profile (i.e., human’s emotions and personality), so as to make the robot able to behave appropriately to the multimodal interaction context. This research addresses the online recognition of emotions based on a new fuzzy-based methodology. It also focuses on investigating how could a match between the human’s and the robot’s personalities influence interaction. Furthermore, it studies the automatic generation of head-arm metaphoric gestures under different emotional states based on the prosodic cues of the interacting human. The conducted experiments have been validated with NAO robot from Aldebaran Robotics and ALICE robot from Hanson Robotics.

Eye contact is a crucial behaviour in human communication and therefore an essencial feature in human-robot interaction. A study regarding the development of an eye behaviour model for a robotic tutor in a task-oriented environment is presented, along with a description of how our proposed model is being used to implement an autonomous robot in the EMOTE project.

The field of socially assistive robotics (SAR) aims to build robots that help people through social interaction. Human social interaction involves complex systems of behavior, and modeling these systems is one goal of SAR. Nonverbal behaviors, such as eye gaze and gesture, are particularly amenable to modeling through machine learning because the effects of the system—the nonverbal behaviors themselves—are inherently observable. Uncovering the underlying model that defines those behaviors would allow socially assistive robots to become better interaction partners. Our research investigates how people use nonverbal behaviors in tutoring applications. We use data from human-human interactions to build a model of nonverbal behaviors using supervised machine learning. This model can both predict the context of observed behaviors and generate appropriate nonverbal behaviors.

We combined a spoken dialog system that we developed to deliver brief health interventions with the fully autonomous humanoid robot (NAO). The dialog system is based on a framework facilitating Markov decision processes (MDP). It is optimized using reinforcement learning (RL) algorithms with data we collected from real user interactions. The system begins to learn optimal dialog strategies for initiative selection and for the type of confirmations that it uses during theinteraction. The health intervention, delivered by a 3D character instead of the NAO, has already been evaluated, with positive results in terms of task completion, ease of use, and future intention to use the system.  The current spoken dialog system for the humanoid robot is a novelty and exists so far as a proof ofconcept.

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.

A contract algorithm is an algorithm which is given, as part of the input, a specified amount of allowable computation time. The algorithm must then complete its execution within the allotted time. An interruptible algorithm, in contrast, can be interrupted at an arbitrary point in time, at which point it must report its currently best solution. It is known that contract algorithms can simulate interruptible algorithms using iterative deepening techniques. This simulation is done at a penalty in the performance of the solution, as measured by the so-called acceleration ratio. In this paper we give matching (i.e., optimal) upper and lower bounds for the acceleration ratio under such a simulation. We assume the most general setting in which n problem instances must be solved by means of scheduling executions of contract algorithms in $m$ identical parallel processors. This resolves an open conjecture of Bernstein, Filkenstein, and Zilberstein who gave an optimal schedule under the restricted setting of round robin and length-increasing schedules, but whose optimality in the general unrestricted case remained open. Lastly, we show how to evaluate the average acceleration ratio of the class of exponential strategies in the setting of n problem instances and m parallel processors. This is a broad class of schedules that tend to be either optimal or near-optimal, for several variants of the basic problem.

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.

In today's age of big data, websites are collecting an increasingly wide variety of information about their users. The texts of websites' privacy policies, which serve as legal agreements between service providers and users, are often long and difficult to understand. Automated analysis of those texts has the potential to help users better understand the implications of agreeing to such policies. In this work, we present a technique that combines machine learning and crowdsourcing to semi-automatically extract key aspects of website privacy policies that is scalable, fast, and cost-effective.

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.

Crowdsourcing platforms provide attractive solutions for collecting speech synthesis data for visually impaired person. However, quality control problems remain because of low-quality volunteer workers. In this paper, we propose the design of a crowdsourcing system that allows us to devise quality control methods. We introduce four worker selection methods; preprocessing filtering, real-time filtering, post-processing filtering, and guess-processing filtering. These methods include a novel approach that utilizes a collaborative filtering technique in addition to a basic approach involving initial training or use of gold-standard data. These quality control methods improved the quality of collected speech synthesis data. Moreover, we have already collected 140,000 Japanese words from 500 million web data for speech synthesis data.