The aim of this full-day workshop is to present rigorous scientific advances on social interaction and multimodal expression for socially intelligent robots, address current challenges in this area, and to set a research agenda to foster interdisciplinary collaboration between researchers on the domain.

Recent advances in the field of robotics and artificial intelligence contributed to the development of “socially interactive robots” that engage in social interactions with humans and exhibit certain human-like social characteristics, including the abilities to communicate with high-level dialogue, to perceive and express emotions using natural multimodal cues (e.g., facial expression, gaze, body posture) and to exhibit distinctive personalities and characters. Applications for socially interactive robots are plentiful: companions for children and elderly, household assistants, partners in industries, guides in public spaces, educational tutors at school and so on. Despite this progress, the social interaction and multimodal expression capabilities of robots are still far behind the intuitiveness and naturalness that is required to allow uninformed users to interact, establish and maintain social relationships with them in their everyday lives.

The area of social interaction and multimodal expression for socially intelligent robots remains very much an active research area with significant challenges in practice due to limitations both in technology and in our understanding of how different modalities must work together to convey human-like levels of social intelligence. Designing reliable and believable social behaviors for robots is an interdisciplinary challenge that cannot be solely approached from a pure engineering perspective. Human sciences, social sciences, and cognitive sciences play a primary role in the development and the enhancement of social interaction skills for socially intelligent robots.

This workshop will bring together a multidisciplinary audience interested in the study of multimodal human-human and human-robot interactions to address challenges in these areas, and elaborate on novel ways to advance research in the field, based on theories of human communication and empirical findings validated human-robot interaction studies. We welcome contributions on both theoretical aspects as well as practical applications. The analysis of human-human interactions is of particular importance to understand how humans send and receive social signals multimodally, through both parallel and sequential use of multiple modalities (e.g., eye gaze, touch, vocal, body, and facial expressions. Results achieved by researchers studying human-robot interactions offers researchers the opportunity to understand how uninformed interaction partners perceive the multimodal communication skills developed for social robots (e.g., children, elderly) and how they influence the interaction process (e.g., regarding usability and acceptance).

Submitted papers will be reviewed and selected based on relevance, originality and theoretical and/or technical quality. Organizers will prioritize having a diversity of perspectives present at the workshop, as well as a diversity of experience.

Papers must be formatted according to the guidelines and templates on the main RO-MAN 2017 conference website, anonymized, and submitted in PDF format through the EasyChair (https://easychair.org/conferences/?conf=wssime2017) conference system. At least one author will be required to register and attend the workshop.

Accepted full paper contributions will be published in the online CEUR Workshop Proceedings (CEUR-WS.org). We invite two types of submissions:

We invite two types of submissions:

Full Papers (4 pages): Accepted submissions will be presented in an oral presentation at the workshop (15 minutes + 5 minutes of Q&A).

Short Papers (2 pages): Submissions will be selected to encourage discussion. Accepted posters will have a 1-minute “teaser” presentation and will be presented in an interactive poster session at the workshop.

WORKSHOP TOPICS INCLUDE, BUT ARE NOT LIMITED TO:
1. Contributions of fundamental nature
a. Psychophysical studies and empirical research about multimodality
2. Technical contributions on multimodal interaction
a. Novel strategies of multimodal human-robot interactions
b. Dialogue management using multimodal output
c. Work focusing on novel modalities (e.g., touch)
3. Multimodal interaction evaluation
a. Evaluation and benchmarking of multimodal human-robot interactions
b. Empirical HRI studies with (partial) functional systems
c. Methodologies for the recording, annotation, and analysis of
multimodal interactions
4. Applications for multimodal interaction with social robots
a. Novel application domains for multimodal interaction
5. Position papers and reviews of the state-of-the-art and ongoing research


Further information can be found under www.ws-sime.com