Catherine Pelachaud

Summary

Socially interactive agents often have a human-like appearance and are modeled to communicate with their human interlocutors through verbal and nonverbal means. During an interaction, participants exhibit different adaptation mechanisms, which can take many forms, from signal imitation to synchronization and conversational strategies. Adapting the multimodal behaviors of a socially interactive agent to the behaviors of its human interlocutors can promote engagement, build rapport and trust, and support the learning process. In this lecture, I will introduce various computational approaches to generate communicative and socio-emotional behaviors to convey intentions and affect. I will also describe several experimental methods to validate these approaches. Objective and subjective measures will be introduced. I will present the open-source system Greta, which allows modeling human-agent interactions. I will conclude the lecture by indicating future lines of research.

Syllabus

• Introduction to communication, verbal and nonverbal behaviors
• Generation of communicative behaviors
• Turn-taking and adaptation mechanisms
• Real-time interaction
• Evaluation practices

References

Lugrin, B., Pelachaud, C., Traum, D. (Editors). The Handbook on Socially Interactive Agents: 20 Years of Research on Embodied Conversational Agents, Intelligent Virtual Agents, and Social Robotics. Volume 1: Methods, Behavior, Cognition, Volume 2: Interactivity, Platforms, Application, 2021 & 2022.

Pre-requisites

Human-computer interaction. Some familiarity with machine learning and neural networks is preferable.

Short bio

Catherine Pelachaud is a CNRS Director of Research in the laboratory ISIR, Sorbonne University. Her research interest includes socially interactive agents, nonverbal communication (face, gaze, gesture, and touch), and adaptive mechanisms in interaction. With her research team, she has been developing an interactive virtual agent platform, Greta, that can display emotional and communicative behaviors. She is co-editor of the ACM Handbook on Socially Interactive Agents (2021-2022). She is the recipient of the ACM – SIGAI Autonomous Agents Research Award 2015, ICMI Sustained Accomplishment Award 2024, and was honored with the title Doctor Honoris Causa of the University of Geneva in 2016. Her SIGGRAPH’94 paper received the Influential Paper Award of IFAAMAS (the International Foundation for Autonomous Agents and Multiagent Systems).