Alexandros Papangelis

Towards a Dyadic Computational Model of Rapport Management for Human-Virtual Agent Interaction

Rapport has been identified as an important function of human interaction, but to our knowledge no model exists of building and maintaining rapport between humans and conversational agents over the long-term that operates at the level of the dyad. In this paper we leverage existing literature and a corpus of peer tutoring data to develop a framework able to explain how humans in dyadic interactions build, maintain, and destroy rapport through the use of specific conversational strategies that function to fulfill specific social goals, and that are instantiated in particular verbal and nonverbal behaviors. We demonstrate its functionality using examples from our experimental data.

Reinforcement Learning of Multi-Issue Negotiation Dialogue Policies

We use reinforcement learning (RL) to learn a multi-issue negotiation dialogue policy. For training and evaluation, we build a hand-crafted agenda-based policy, which serves as the negotiation partner of the RL policy. Both the agendabased and the RL policies are designed to work for a large variety of negotiation settings, and perform well against negotiation partners whose behavior has not been observed before. We evaluate the two models by having them negotiate against each other under various settings. The learned model consistently outperforms the agenda-based model. We also ask human raters to rate negotiation transcripts between the RL policy and the agenda-based policy, regarding the rationality of the two negotiators. The RL policy is perceived as more rational than the agenda-based policy.

Recognition of sleep patterns using a bed pressure mat

The monitoring of sleep patterns is of major importance for various reason such as, the detection and treatment of sleep disorders, the assessment of the effect of different medical conditions or medications on the sleep quality and the assessment of mortality risks associated with sleeping patterns in adults and children. Sleep monitoring by itself is a difficult problem due to both privacy and technical considerations. The proposed system uses a bed pressure mat to assess and report sleep patterns. To evaluate our system we used real data collected in Heracleia Labs assistive living apartment. Our method is non-invasive, as it does not disrupt the users usual sleeping behavior and it can be used both at the clinic and at home with minimal cost.

Towards a Computational Architecture of Dyadic Rapport Management for Virtual Agents

Rapport has been identified as an important factor in human task performance. Motivated by the proliferation of virtual agents that assist humans on various tasks, we propose a computational architecture for virtual agents, building on our own work on a dyadic model of rapport between humans and virtual agents. We show how such a system can be trained in order to build, maintain and destroy rapport.

A survey of assistive devices for cerebral palsy patients

In this paper, we present a survey of recent advances in assistive technologies used to foster rehabilitation and improved quality of life for children with Cerebral palsy. The survey focuses specifically on robotics and interactive games used in rehabilitative therapy, as well as general electronic assistive devices for everyday use. The systems and clinical studies discussed show that Cerebral palsy treatment can benefit greatly from emerging technologies.

An adaptive dialogue system with online dialogue policy learning

In this work we present an architecture for Adaptive Dialogue Systems and a novel system that serves as a Museum Guide. It employs several online Reinforcement Learning (RL) techniques to achieve adaptation to the environment as well as to different users. Not many systems have been proposed that apply online RL methods and this is one of the first to fully describe an Adaptive Dialogue System with online dialogue policy learning. We evaluate our system through user simulations and compare the several implemented algorithms on a simple scenario.

Audio visual speech recognition in noisy visual environments

Speech recognition is a natural means of interaction for a human with a smart assistive environment. In order for this interaction to be effective, such a system should attain a high recognition rate even under adverse conditions. Audio-visual speech recognition (AVSR) can be of help in such environments, especially under the presence of audio noise. However the impact of visual noise to its performance has not been studied sufficiently in the literature. In this paper, we examine the effects of visual noise to AVSR, reporting experiments on the relatively simple task of connected digit recognition, under moderate acoustic noise and a variety of types of visual noise. The latter can be caused by either faulty sensors or video signal transmission problems that can be found in smart assistive environments. Our AVSR system exhibits higher accuracy in comparison to an audio-only recognizer and robust performance in most cases of noisy video signals considered.

A development and evaluation platform for non-tactile power wheelchair controls

This paper presents an intelligent wheelchair designed to be used as a development and evaluation platform for alternative, non-tactile power wheelchair controls. The system is designed to be highly modular such that new human-computer interface devices and methods can be quickly integrated and evaluated as necessary. The current configuration provides full proportional steering and speed control outputs using a combination of voice commands, video-occulography (eye tracking), and a single point electrode based electroencephalography (EEG) brain-computer interface.

An adaptive dialogue system for assessing post traumatic stress disorder

In this paper, we present a system which is able to interact through natural dialogue, with PTSD patients, as well as to guide the conversation aiming to elicit enough information to make an assessment of their condition, in a manner similar to a self assessment test. Our system is able to adapt to each individual patient and can operate in two modes: one that stores information about previous sessions with a patient to provide a sense of trust and relationship; and one that does not store information to preserve anonymity.

Online Complex Action Learning and User State Estimation for Adaptive Dialogue Systems

Dialogue Systems (DS) have been rapidly evolving during the last few years. In order for them to be able to adapt to their surroundings and to individual users, researchers have focused on adaptation techniques, giving rise to the field of Adaptive Dialogue Systems (ADS). One important sub field of ADS is learning what the system should say or do next. Most of the work done in this direction assumes the system performs simple actions, rather than behaviours described by sub-dialogues, i.e. complex actions. To this end we propose a novel online algorithm that ranks complex actions according to their performance and selects the top-k performing ones. To the best of our knowledge there is currently no work describing methods to learn policies for complex actions in an online fashion. We also propose an online algorithm able to estimate the effects of system actions on the users state, in order to make more informed decisions about which action to take and guide the learning algorithm towards a desired final user state. Our results show that the proposed complex action learning algorithm outperforms simple Hierarchical Reinforcement Learning algorithms and that we are able to successfully estimate the effect an action will have on the users state, using emotional states as a case study.